Switch to python3
This commit is contained in:
parent
531041e89a
commit
9ba4b6a91a
5286 changed files with 677347 additions and 576888 deletions
277
Darwin/lib/python3.4/site-packages/pip/__init__.py
Normal file
277
Darwin/lib/python3.4/site-packages/pip/__init__.py
Normal file
|
|
@ -0,0 +1,277 @@
|
|||
#!/usr/bin/env python
|
||||
import os
|
||||
import optparse
|
||||
|
||||
import sys
|
||||
import re
|
||||
|
||||
from pip.exceptions import InstallationError, CommandError, PipError
|
||||
from pip.log import logger
|
||||
from pip.util import get_installed_distributions, get_prog
|
||||
from pip.vcs import git, mercurial, subversion, bazaar # noqa
|
||||
from pip.baseparser import ConfigOptionParser, UpdatingDefaultsHelpFormatter
|
||||
from pip.commands import commands, get_summaries, get_similar_commands
|
||||
|
||||
# This fixes a peculiarity when importing via __import__ - as we are
|
||||
# initialising the pip module, "from pip import cmdoptions" is recursive
|
||||
# and appears not to work properly in that situation.
|
||||
import pip.cmdoptions
|
||||
cmdoptions = pip.cmdoptions
|
||||
|
||||
# The version as used in the setup.py and the docs conf.py
|
||||
__version__ = "1.5.6"
|
||||
|
||||
|
||||
def autocomplete():
|
||||
"""Command and option completion for the main option parser (and options)
|
||||
and its subcommands (and options).
|
||||
|
||||
Enable by sourcing one of the completion shell scripts (bash or zsh).
|
||||
"""
|
||||
# Don't complete if user hasn't sourced bash_completion file.
|
||||
if 'PIP_AUTO_COMPLETE' not in os.environ:
|
||||
return
|
||||
cwords = os.environ['COMP_WORDS'].split()[1:]
|
||||
cword = int(os.environ['COMP_CWORD'])
|
||||
try:
|
||||
current = cwords[cword - 1]
|
||||
except IndexError:
|
||||
current = ''
|
||||
|
||||
subcommands = [cmd for cmd, summary in get_summaries()]
|
||||
options = []
|
||||
# subcommand
|
||||
try:
|
||||
subcommand_name = [w for w in cwords if w in subcommands][0]
|
||||
except IndexError:
|
||||
subcommand_name = None
|
||||
|
||||
parser = create_main_parser()
|
||||
# subcommand options
|
||||
if subcommand_name:
|
||||
# special case: 'help' subcommand has no options
|
||||
if subcommand_name == 'help':
|
||||
sys.exit(1)
|
||||
# special case: list locally installed dists for uninstall command
|
||||
if subcommand_name == 'uninstall' and not current.startswith('-'):
|
||||
installed = []
|
||||
lc = current.lower()
|
||||
for dist in get_installed_distributions(local_only=True):
|
||||
if dist.key.startswith(lc) and dist.key not in cwords[1:]:
|
||||
installed.append(dist.key)
|
||||
# if there are no dists installed, fall back to option completion
|
||||
if installed:
|
||||
for dist in installed:
|
||||
print(dist)
|
||||
sys.exit(1)
|
||||
|
||||
subcommand = commands[subcommand_name]()
|
||||
options += [(opt.get_opt_string(), opt.nargs)
|
||||
for opt in subcommand.parser.option_list_all
|
||||
if opt.help != optparse.SUPPRESS_HELP]
|
||||
|
||||
# filter out previously specified options from available options
|
||||
prev_opts = [x.split('=')[0] for x in cwords[1:cword - 1]]
|
||||
options = [(x, v) for (x, v) in options if x not in prev_opts]
|
||||
# filter options by current input
|
||||
options = [(k, v) for k, v in options if k.startswith(current)]
|
||||
for option in options:
|
||||
opt_label = option[0]
|
||||
# append '=' to options which require args
|
||||
if option[1]:
|
||||
opt_label += '='
|
||||
print(opt_label)
|
||||
else:
|
||||
# show main parser options only when necessary
|
||||
if current.startswith('-') or current.startswith('--'):
|
||||
opts = [i.option_list for i in parser.option_groups]
|
||||
opts.append(parser.option_list)
|
||||
opts = (o for it in opts for o in it)
|
||||
|
||||
subcommands += [i.get_opt_string() for i in opts
|
||||
if i.help != optparse.SUPPRESS_HELP]
|
||||
|
||||
print(' '.join([x for x in subcommands if x.startswith(current)]))
|
||||
sys.exit(1)
|
||||
|
||||
|
||||
def create_main_parser():
|
||||
parser_kw = {
|
||||
'usage': '\n%prog <command> [options]',
|
||||
'add_help_option': False,
|
||||
'formatter': UpdatingDefaultsHelpFormatter(),
|
||||
'name': 'global',
|
||||
'prog': get_prog(),
|
||||
}
|
||||
|
||||
parser = ConfigOptionParser(**parser_kw)
|
||||
parser.disable_interspersed_args()
|
||||
|
||||
pip_pkg_dir = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
|
||||
parser.version = 'pip %s from %s (python %s)' % (
|
||||
__version__, pip_pkg_dir, sys.version[:3])
|
||||
|
||||
# add the general options
|
||||
gen_opts = cmdoptions.make_option_group(cmdoptions.general_group, parser)
|
||||
parser.add_option_group(gen_opts)
|
||||
|
||||
parser.main = True # so the help formatter knows
|
||||
|
||||
# create command listing for description
|
||||
command_summaries = get_summaries()
|
||||
description = [''] + ['%-27s %s' % (i, j) for i, j in command_summaries]
|
||||
parser.description = '\n'.join(description)
|
||||
|
||||
return parser
|
||||
|
||||
|
||||
def parseopts(args):
|
||||
parser = create_main_parser()
|
||||
|
||||
# Note: parser calls disable_interspersed_args(), so the result of this call
|
||||
# is to split the initial args into the general options before the
|
||||
# subcommand and everything else.
|
||||
# For example:
|
||||
# args: ['--timeout=5', 'install', '--user', 'INITools']
|
||||
# general_options: ['--timeout==5']
|
||||
# args_else: ['install', '--user', 'INITools']
|
||||
general_options, args_else = parser.parse_args(args)
|
||||
|
||||
# --version
|
||||
if general_options.version:
|
||||
sys.stdout.write(parser.version)
|
||||
sys.stdout.write(os.linesep)
|
||||
sys.exit()
|
||||
|
||||
# pip || pip help -> print_help()
|
||||
if not args_else or (args_else[0] == 'help' and len(args_else) == 1):
|
||||
parser.print_help()
|
||||
sys.exit()
|
||||
|
||||
# the subcommand name
|
||||
cmd_name = args_else[0].lower()
|
||||
|
||||
#all the args without the subcommand
|
||||
cmd_args = args[:]
|
||||
cmd_args.remove(args_else[0].lower())
|
||||
|
||||
if cmd_name not in commands:
|
||||
guess = get_similar_commands(cmd_name)
|
||||
|
||||
msg = ['unknown command "%s"' % cmd_name]
|
||||
if guess:
|
||||
msg.append('maybe you meant "%s"' % guess)
|
||||
|
||||
raise CommandError(' - '.join(msg))
|
||||
|
||||
return cmd_name, cmd_args
|
||||
|
||||
|
||||
def main(initial_args=None):
|
||||
if initial_args is None:
|
||||
initial_args = sys.argv[1:]
|
||||
|
||||
autocomplete()
|
||||
|
||||
try:
|
||||
cmd_name, cmd_args = parseopts(initial_args)
|
||||
except PipError:
|
||||
e = sys.exc_info()[1]
|
||||
sys.stderr.write("ERROR: %s" % e)
|
||||
sys.stderr.write(os.linesep)
|
||||
sys.exit(1)
|
||||
|
||||
command = commands[cmd_name]()
|
||||
return command.main(cmd_args)
|
||||
|
||||
|
||||
def bootstrap():
|
||||
"""
|
||||
Bootstrapping function to be called from install-pip.py script.
|
||||
"""
|
||||
pkgs = ['pip']
|
||||
try:
|
||||
import setuptools
|
||||
except ImportError:
|
||||
pkgs.append('setuptools')
|
||||
return main(['install', '--upgrade'] + pkgs + sys.argv[1:])
|
||||
|
||||
############################################################
|
||||
## Writing freeze files
|
||||
|
||||
|
||||
class FrozenRequirement(object):
|
||||
|
||||
def __init__(self, name, req, editable, comments=()):
|
||||
self.name = name
|
||||
self.req = req
|
||||
self.editable = editable
|
||||
self.comments = comments
|
||||
|
||||
_rev_re = re.compile(r'-r(\d+)$')
|
||||
_date_re = re.compile(r'-(20\d\d\d\d\d\d)$')
|
||||
|
||||
@classmethod
|
||||
def from_dist(cls, dist, dependency_links, find_tags=False):
|
||||
location = os.path.normcase(os.path.abspath(dist.location))
|
||||
comments = []
|
||||
from pip.vcs import vcs, get_src_requirement
|
||||
if vcs.get_backend_name(location):
|
||||
editable = True
|
||||
try:
|
||||
req = get_src_requirement(dist, location, find_tags)
|
||||
except InstallationError:
|
||||
ex = sys.exc_info()[1]
|
||||
logger.warn("Error when trying to get requirement for VCS system %s, falling back to uneditable format" % ex)
|
||||
req = None
|
||||
if req is None:
|
||||
logger.warn('Could not determine repository location of %s' % location)
|
||||
comments.append('## !! Could not determine repository location')
|
||||
req = dist.as_requirement()
|
||||
editable = False
|
||||
else:
|
||||
editable = False
|
||||
req = dist.as_requirement()
|
||||
specs = req.specs
|
||||
assert len(specs) == 1 and specs[0][0] == '=='
|
||||
version = specs[0][1]
|
||||
ver_match = cls._rev_re.search(version)
|
||||
date_match = cls._date_re.search(version)
|
||||
if ver_match or date_match:
|
||||
svn_backend = vcs.get_backend('svn')
|
||||
if svn_backend:
|
||||
svn_location = svn_backend(
|
||||
).get_location(dist, dependency_links)
|
||||
if not svn_location:
|
||||
logger.warn(
|
||||
'Warning: cannot find svn location for %s' % req)
|
||||
comments.append('## FIXME: could not find svn URL in dependency_links for this package:')
|
||||
else:
|
||||
comments.append('# Installing as editable to satisfy requirement %s:' % req)
|
||||
if ver_match:
|
||||
rev = ver_match.group(1)
|
||||
else:
|
||||
rev = '{%s}' % date_match.group(1)
|
||||
editable = True
|
||||
req = '%s@%s#egg=%s' % (svn_location, rev, cls.egg_name(dist))
|
||||
return cls(dist.project_name, req, editable, comments)
|
||||
|
||||
@staticmethod
|
||||
def egg_name(dist):
|
||||
name = dist.egg_name()
|
||||
match = re.search(r'-py\d\.\d$', name)
|
||||
if match:
|
||||
name = name[:match.start()]
|
||||
return name
|
||||
|
||||
def __str__(self):
|
||||
req = self.req
|
||||
if self.editable:
|
||||
req = '-e %s' % req
|
||||
return '\n'.join(list(self.comments) + [str(req)]) + '\n'
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
exit = main()
|
||||
if exit:
|
||||
sys.exit(exit)
|
||||
7
Darwin/lib/python3.4/site-packages/pip/__main__.py
Normal file
7
Darwin/lib/python3.4/site-packages/pip/__main__.py
Normal file
|
|
@ -0,0 +1,7 @@
|
|||
import sys
|
||||
from .runner import run
|
||||
|
||||
if __name__ == '__main__':
|
||||
exit = run()
|
||||
if exit:
|
||||
sys.exit(exit)
|
||||
|
|
@ -0,0 +1,8 @@
|
|||
"""
|
||||
pip._vendor is for vendoring dependencies of pip to prevent needing pip to
|
||||
depend on something external.
|
||||
|
||||
Files inside of pip._vendor should be considered immutable and should only be
|
||||
updated to versions from upstream.
|
||||
"""
|
||||
from __future__ import absolute_import
|
||||
|
|
@ -0,0 +1,16 @@
|
|||
try:
|
||||
import ast
|
||||
from pip._vendor._markerlib.markers import default_environment, compile, interpret
|
||||
except ImportError:
|
||||
if 'ast' in globals():
|
||||
raise
|
||||
def default_environment():
|
||||
return {}
|
||||
def compile(marker):
|
||||
def marker_fn(environment=None, override=None):
|
||||
# 'empty markers are True' heuristic won't install extra deps.
|
||||
return not marker.strip()
|
||||
marker_fn.__doc__ = marker
|
||||
return marker_fn
|
||||
def interpret(marker, environment=None, override=None):
|
||||
return compile(marker)()
|
||||
|
|
@ -0,0 +1,119 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
"""Interpret PEP 345 environment markers.
|
||||
|
||||
EXPR [in|==|!=|not in] EXPR [or|and] ...
|
||||
|
||||
where EXPR belongs to any of those:
|
||||
|
||||
python_version = '%s.%s' % (sys.version_info[0], sys.version_info[1])
|
||||
python_full_version = sys.version.split()[0]
|
||||
os.name = os.name
|
||||
sys.platform = sys.platform
|
||||
platform.version = platform.version()
|
||||
platform.machine = platform.machine()
|
||||
platform.python_implementation = platform.python_implementation()
|
||||
a free string, like '2.6', or 'win32'
|
||||
"""
|
||||
|
||||
__all__ = ['default_environment', 'compile', 'interpret']
|
||||
|
||||
import ast
|
||||
import os
|
||||
import platform
|
||||
import sys
|
||||
import weakref
|
||||
|
||||
_builtin_compile = compile
|
||||
|
||||
try:
|
||||
from platform import python_implementation
|
||||
except ImportError:
|
||||
if os.name == "java":
|
||||
# Jython 2.5 has ast module, but not platform.python_implementation() function.
|
||||
def python_implementation():
|
||||
return "Jython"
|
||||
else:
|
||||
raise
|
||||
|
||||
|
||||
# restricted set of variables
|
||||
_VARS = {'sys.platform': sys.platform,
|
||||
'python_version': '%s.%s' % sys.version_info[:2],
|
||||
# FIXME parsing sys.platform is not reliable, but there is no other
|
||||
# way to get e.g. 2.7.2+, and the PEP is defined with sys.version
|
||||
'python_full_version': sys.version.split(' ', 1)[0],
|
||||
'os.name': os.name,
|
||||
'platform.version': platform.version(),
|
||||
'platform.machine': platform.machine(),
|
||||
'platform.python_implementation': python_implementation(),
|
||||
'extra': None # wheel extension
|
||||
}
|
||||
|
||||
for var in list(_VARS.keys()):
|
||||
if '.' in var:
|
||||
_VARS[var.replace('.', '_')] = _VARS[var]
|
||||
|
||||
def default_environment():
|
||||
"""Return copy of default PEP 385 globals dictionary."""
|
||||
return dict(_VARS)
|
||||
|
||||
class ASTWhitelist(ast.NodeTransformer):
|
||||
def __init__(self, statement):
|
||||
self.statement = statement # for error messages
|
||||
|
||||
ALLOWED = (ast.Compare, ast.BoolOp, ast.Attribute, ast.Name, ast.Load, ast.Str)
|
||||
# Bool operations
|
||||
ALLOWED += (ast.And, ast.Or)
|
||||
# Comparison operations
|
||||
ALLOWED += (ast.Eq, ast.Gt, ast.GtE, ast.In, ast.Is, ast.IsNot, ast.Lt, ast.LtE, ast.NotEq, ast.NotIn)
|
||||
|
||||
def visit(self, node):
|
||||
"""Ensure statement only contains allowed nodes."""
|
||||
if not isinstance(node, self.ALLOWED):
|
||||
raise SyntaxError('Not allowed in environment markers.\n%s\n%s' %
|
||||
(self.statement,
|
||||
(' ' * node.col_offset) + '^'))
|
||||
return ast.NodeTransformer.visit(self, node)
|
||||
|
||||
def visit_Attribute(self, node):
|
||||
"""Flatten one level of attribute access."""
|
||||
new_node = ast.Name("%s.%s" % (node.value.id, node.attr), node.ctx)
|
||||
return ast.copy_location(new_node, node)
|
||||
|
||||
def parse_marker(marker):
|
||||
tree = ast.parse(marker, mode='eval')
|
||||
new_tree = ASTWhitelist(marker).generic_visit(tree)
|
||||
return new_tree
|
||||
|
||||
def compile_marker(parsed_marker):
|
||||
return _builtin_compile(parsed_marker, '<environment marker>', 'eval',
|
||||
dont_inherit=True)
|
||||
|
||||
_cache = weakref.WeakValueDictionary()
|
||||
|
||||
def compile(marker):
|
||||
"""Return compiled marker as a function accepting an environment dict."""
|
||||
try:
|
||||
return _cache[marker]
|
||||
except KeyError:
|
||||
pass
|
||||
if not marker.strip():
|
||||
def marker_fn(environment=None, override=None):
|
||||
""""""
|
||||
return True
|
||||
else:
|
||||
compiled_marker = compile_marker(parse_marker(marker))
|
||||
def marker_fn(environment=None, override=None):
|
||||
"""override updates environment"""
|
||||
if override is None:
|
||||
override = {}
|
||||
if environment is None:
|
||||
environment = default_environment()
|
||||
environment.update(override)
|
||||
return eval(compiled_marker, environment)
|
||||
marker_fn.__doc__ = marker
|
||||
_cache[marker] = marker_fn
|
||||
return _cache[marker]
|
||||
|
||||
def interpret(marker, environment=None):
|
||||
return compile(marker)(environment)
|
||||
|
|
@ -0,0 +1,7 @@
|
|||
# Copyright Jonathan Hartley 2013. BSD 3-Clause license, see LICENSE file.
|
||||
from .initialise import init, deinit, reinit
|
||||
from .ansi import Fore, Back, Style
|
||||
from .ansitowin32 import AnsiToWin32
|
||||
|
||||
__version__ = '0.3.1'
|
||||
|
||||
|
|
@ -0,0 +1,50 @@
|
|||
# Copyright Jonathan Hartley 2013. BSD 3-Clause license, see LICENSE file.
|
||||
'''
|
||||
This module generates ANSI character codes to printing colors to terminals.
|
||||
See: http://en.wikipedia.org/wiki/ANSI_escape_code
|
||||
'''
|
||||
|
||||
CSI = '\033['
|
||||
|
||||
def code_to_chars(code):
|
||||
return CSI + str(code) + 'm'
|
||||
|
||||
class AnsiCodes(object):
|
||||
def __init__(self, codes):
|
||||
for name in dir(codes):
|
||||
if not name.startswith('_'):
|
||||
value = getattr(codes, name)
|
||||
setattr(self, name, code_to_chars(value))
|
||||
|
||||
class AnsiFore:
|
||||
BLACK = 30
|
||||
RED = 31
|
||||
GREEN = 32
|
||||
YELLOW = 33
|
||||
BLUE = 34
|
||||
MAGENTA = 35
|
||||
CYAN = 36
|
||||
WHITE = 37
|
||||
RESET = 39
|
||||
|
||||
class AnsiBack:
|
||||
BLACK = 40
|
||||
RED = 41
|
||||
GREEN = 42
|
||||
YELLOW = 43
|
||||
BLUE = 44
|
||||
MAGENTA = 45
|
||||
CYAN = 46
|
||||
WHITE = 47
|
||||
RESET = 49
|
||||
|
||||
class AnsiStyle:
|
||||
BRIGHT = 1
|
||||
DIM = 2
|
||||
NORMAL = 22
|
||||
RESET_ALL = 0
|
||||
|
||||
Fore = AnsiCodes( AnsiFore )
|
||||
Back = AnsiCodes( AnsiBack )
|
||||
Style = AnsiCodes( AnsiStyle )
|
||||
|
||||
|
|
@ -0,0 +1,190 @@
|
|||
# Copyright Jonathan Hartley 2013. BSD 3-Clause license, see LICENSE file.
|
||||
import re
|
||||
import sys
|
||||
|
||||
from .ansi import AnsiFore, AnsiBack, AnsiStyle, Style
|
||||
from .winterm import WinTerm, WinColor, WinStyle
|
||||
from .win32 import windll
|
||||
|
||||
|
||||
winterm = None
|
||||
if windll is not None:
|
||||
winterm = WinTerm()
|
||||
|
||||
|
||||
def is_a_tty(stream):
|
||||
return hasattr(stream, 'isatty') and stream.isatty()
|
||||
|
||||
|
||||
class StreamWrapper(object):
|
||||
'''
|
||||
Wraps a stream (such as stdout), acting as a transparent proxy for all
|
||||
attribute access apart from method 'write()', which is delegated to our
|
||||
Converter instance.
|
||||
'''
|
||||
def __init__(self, wrapped, converter):
|
||||
# double-underscore everything to prevent clashes with names of
|
||||
# attributes on the wrapped stream object.
|
||||
self.__wrapped = wrapped
|
||||
self.__convertor = converter
|
||||
|
||||
def __getattr__(self, name):
|
||||
return getattr(self.__wrapped, name)
|
||||
|
||||
def write(self, text):
|
||||
self.__convertor.write(text)
|
||||
|
||||
|
||||
class AnsiToWin32(object):
|
||||
'''
|
||||
Implements a 'write()' method which, on Windows, will strip ANSI character
|
||||
sequences from the text, and if outputting to a tty, will convert them into
|
||||
win32 function calls.
|
||||
'''
|
||||
ANSI_RE = re.compile('\033\[((?:\d|;)*)([a-zA-Z])')
|
||||
|
||||
def __init__(self, wrapped, convert=None, strip=None, autoreset=False):
|
||||
# The wrapped stream (normally sys.stdout or sys.stderr)
|
||||
self.wrapped = wrapped
|
||||
|
||||
# should we reset colors to defaults after every .write()
|
||||
self.autoreset = autoreset
|
||||
|
||||
# create the proxy wrapping our output stream
|
||||
self.stream = StreamWrapper(wrapped, self)
|
||||
|
||||
on_windows = sys.platform.startswith('win')
|
||||
|
||||
# should we strip ANSI sequences from our output?
|
||||
if strip is None:
|
||||
strip = on_windows
|
||||
self.strip = strip
|
||||
|
||||
# should we should convert ANSI sequences into win32 calls?
|
||||
if convert is None:
|
||||
convert = on_windows and is_a_tty(wrapped)
|
||||
self.convert = convert
|
||||
|
||||
# dict of ansi codes to win32 functions and parameters
|
||||
self.win32_calls = self.get_win32_calls()
|
||||
|
||||
# are we wrapping stderr?
|
||||
self.on_stderr = self.wrapped is sys.stderr
|
||||
|
||||
|
||||
def should_wrap(self):
|
||||
'''
|
||||
True if this class is actually needed. If false, then the output
|
||||
stream will not be affected, nor will win32 calls be issued, so
|
||||
wrapping stdout is not actually required. This will generally be
|
||||
False on non-Windows platforms, unless optional functionality like
|
||||
autoreset has been requested using kwargs to init()
|
||||
'''
|
||||
return self.convert or self.strip or self.autoreset
|
||||
|
||||
|
||||
def get_win32_calls(self):
|
||||
if self.convert and winterm:
|
||||
return {
|
||||
AnsiStyle.RESET_ALL: (winterm.reset_all, ),
|
||||
AnsiStyle.BRIGHT: (winterm.style, WinStyle.BRIGHT),
|
||||
AnsiStyle.DIM: (winterm.style, WinStyle.NORMAL),
|
||||
AnsiStyle.NORMAL: (winterm.style, WinStyle.NORMAL),
|
||||
AnsiFore.BLACK: (winterm.fore, WinColor.BLACK),
|
||||
AnsiFore.RED: (winterm.fore, WinColor.RED),
|
||||
AnsiFore.GREEN: (winterm.fore, WinColor.GREEN),
|
||||
AnsiFore.YELLOW: (winterm.fore, WinColor.YELLOW),
|
||||
AnsiFore.BLUE: (winterm.fore, WinColor.BLUE),
|
||||
AnsiFore.MAGENTA: (winterm.fore, WinColor.MAGENTA),
|
||||
AnsiFore.CYAN: (winterm.fore, WinColor.CYAN),
|
||||
AnsiFore.WHITE: (winterm.fore, WinColor.GREY),
|
||||
AnsiFore.RESET: (winterm.fore, ),
|
||||
AnsiBack.BLACK: (winterm.back, WinColor.BLACK),
|
||||
AnsiBack.RED: (winterm.back, WinColor.RED),
|
||||
AnsiBack.GREEN: (winterm.back, WinColor.GREEN),
|
||||
AnsiBack.YELLOW: (winterm.back, WinColor.YELLOW),
|
||||
AnsiBack.BLUE: (winterm.back, WinColor.BLUE),
|
||||
AnsiBack.MAGENTA: (winterm.back, WinColor.MAGENTA),
|
||||
AnsiBack.CYAN: (winterm.back, WinColor.CYAN),
|
||||
AnsiBack.WHITE: (winterm.back, WinColor.GREY),
|
||||
AnsiBack.RESET: (winterm.back, ),
|
||||
}
|
||||
|
||||
|
||||
def write(self, text):
|
||||
if self.strip or self.convert:
|
||||
self.write_and_convert(text)
|
||||
else:
|
||||
self.wrapped.write(text)
|
||||
self.wrapped.flush()
|
||||
if self.autoreset:
|
||||
self.reset_all()
|
||||
|
||||
|
||||
def reset_all(self):
|
||||
if self.convert:
|
||||
self.call_win32('m', (0,))
|
||||
elif not self.wrapped.closed and is_a_tty(self.wrapped):
|
||||
self.wrapped.write(Style.RESET_ALL)
|
||||
|
||||
|
||||
def write_and_convert(self, text):
|
||||
'''
|
||||
Write the given text to our wrapped stream, stripping any ANSI
|
||||
sequences from the text, and optionally converting them into win32
|
||||
calls.
|
||||
'''
|
||||
cursor = 0
|
||||
for match in self.ANSI_RE.finditer(text):
|
||||
start, end = match.span()
|
||||
self.write_plain_text(text, cursor, start)
|
||||
self.convert_ansi(*match.groups())
|
||||
cursor = end
|
||||
self.write_plain_text(text, cursor, len(text))
|
||||
|
||||
|
||||
def write_plain_text(self, text, start, end):
|
||||
if start < end:
|
||||
self.wrapped.write(text[start:end])
|
||||
self.wrapped.flush()
|
||||
|
||||
|
||||
def convert_ansi(self, paramstring, command):
|
||||
if self.convert:
|
||||
params = self.extract_params(paramstring)
|
||||
self.call_win32(command, params)
|
||||
|
||||
|
||||
def extract_params(self, paramstring):
|
||||
def split(paramstring):
|
||||
for p in paramstring.split(';'):
|
||||
if p != '':
|
||||
yield int(p)
|
||||
return tuple(split(paramstring))
|
||||
|
||||
|
||||
def call_win32(self, command, params):
|
||||
if params == []:
|
||||
params = [0]
|
||||
if command == 'm':
|
||||
for param in params:
|
||||
if param in self.win32_calls:
|
||||
func_args = self.win32_calls[param]
|
||||
func = func_args[0]
|
||||
args = func_args[1:]
|
||||
kwargs = dict(on_stderr=self.on_stderr)
|
||||
func(*args, **kwargs)
|
||||
elif command in ('H', 'f'): # set cursor position
|
||||
func = winterm.set_cursor_position
|
||||
func(params, on_stderr=self.on_stderr)
|
||||
elif command in ('J'):
|
||||
func = winterm.erase_data
|
||||
func(params, on_stderr=self.on_stderr)
|
||||
elif command == 'A':
|
||||
if params == () or params == None:
|
||||
num_rows = 1
|
||||
else:
|
||||
num_rows = params[0]
|
||||
func = winterm.cursor_up
|
||||
func(num_rows, on_stderr=self.on_stderr)
|
||||
|
||||
|
|
@ -0,0 +1,56 @@
|
|||
# Copyright Jonathan Hartley 2013. BSD 3-Clause license, see LICENSE file.
|
||||
import atexit
|
||||
import sys
|
||||
|
||||
from .ansitowin32 import AnsiToWin32
|
||||
|
||||
|
||||
orig_stdout = sys.stdout
|
||||
orig_stderr = sys.stderr
|
||||
|
||||
wrapped_stdout = sys.stdout
|
||||
wrapped_stderr = sys.stderr
|
||||
|
||||
atexit_done = False
|
||||
|
||||
|
||||
def reset_all():
|
||||
AnsiToWin32(orig_stdout).reset_all()
|
||||
|
||||
|
||||
def init(autoreset=False, convert=None, strip=None, wrap=True):
|
||||
|
||||
if not wrap and any([autoreset, convert, strip]):
|
||||
raise ValueError('wrap=False conflicts with any other arg=True')
|
||||
|
||||
global wrapped_stdout, wrapped_stderr
|
||||
sys.stdout = wrapped_stdout = \
|
||||
wrap_stream(orig_stdout, convert, strip, autoreset, wrap)
|
||||
sys.stderr = wrapped_stderr = \
|
||||
wrap_stream(orig_stderr, convert, strip, autoreset, wrap)
|
||||
|
||||
global atexit_done
|
||||
if not atexit_done:
|
||||
atexit.register(reset_all)
|
||||
atexit_done = True
|
||||
|
||||
|
||||
def deinit():
|
||||
sys.stdout = orig_stdout
|
||||
sys.stderr = orig_stderr
|
||||
|
||||
|
||||
def reinit():
|
||||
sys.stdout = wrapped_stdout
|
||||
sys.stderr = wrapped_stdout
|
||||
|
||||
|
||||
def wrap_stream(stream, convert, strip, autoreset, wrap):
|
||||
if wrap:
|
||||
wrapper = AnsiToWin32(stream,
|
||||
convert=convert, strip=strip, autoreset=autoreset)
|
||||
if wrapper.should_wrap():
|
||||
stream = wrapper.stream
|
||||
return stream
|
||||
|
||||
|
||||
137
Darwin/lib/python3.4/site-packages/pip/_vendor/colorama/win32.py
Normal file
137
Darwin/lib/python3.4/site-packages/pip/_vendor/colorama/win32.py
Normal file
|
|
@ -0,0 +1,137 @@
|
|||
# Copyright Jonathan Hartley 2013. BSD 3-Clause license, see LICENSE file.
|
||||
|
||||
# from winbase.h
|
||||
STDOUT = -11
|
||||
STDERR = -12
|
||||
|
||||
import ctypes
|
||||
from ctypes import LibraryLoader
|
||||
|
||||
try:
|
||||
windll = LibraryLoader(ctypes.WinDLL)
|
||||
from ctypes import wintypes
|
||||
except (AttributeError, ImportError):
|
||||
windll = None
|
||||
SetConsoleTextAttribute = lambda *_: None
|
||||
else:
|
||||
from ctypes import (
|
||||
byref, Structure, c_char, c_short, c_uint32, c_ushort, POINTER
|
||||
)
|
||||
|
||||
class CONSOLE_SCREEN_BUFFER_INFO(Structure):
|
||||
"""struct in wincon.h."""
|
||||
_fields_ = [
|
||||
("dwSize", wintypes._COORD),
|
||||
("dwCursorPosition", wintypes._COORD),
|
||||
("wAttributes", wintypes.WORD),
|
||||
("srWindow", wintypes.SMALL_RECT),
|
||||
("dwMaximumWindowSize", wintypes._COORD),
|
||||
]
|
||||
def __str__(self):
|
||||
return '(%d,%d,%d,%d,%d,%d,%d,%d,%d,%d,%d)' % (
|
||||
self.dwSize.Y, self.dwSize.X
|
||||
, self.dwCursorPosition.Y, self.dwCursorPosition.X
|
||||
, self.wAttributes
|
||||
, self.srWindow.Top, self.srWindow.Left, self.srWindow.Bottom, self.srWindow.Right
|
||||
, self.dwMaximumWindowSize.Y, self.dwMaximumWindowSize.X
|
||||
)
|
||||
|
||||
_GetStdHandle = windll.kernel32.GetStdHandle
|
||||
_GetStdHandle.argtypes = [
|
||||
wintypes.DWORD,
|
||||
]
|
||||
_GetStdHandle.restype = wintypes.HANDLE
|
||||
|
||||
_GetConsoleScreenBufferInfo = windll.kernel32.GetConsoleScreenBufferInfo
|
||||
_GetConsoleScreenBufferInfo.argtypes = [
|
||||
wintypes.HANDLE,
|
||||
POINTER(CONSOLE_SCREEN_BUFFER_INFO),
|
||||
]
|
||||
_GetConsoleScreenBufferInfo.restype = wintypes.BOOL
|
||||
|
||||
_SetConsoleTextAttribute = windll.kernel32.SetConsoleTextAttribute
|
||||
_SetConsoleTextAttribute.argtypes = [
|
||||
wintypes.HANDLE,
|
||||
wintypes.WORD,
|
||||
]
|
||||
_SetConsoleTextAttribute.restype = wintypes.BOOL
|
||||
|
||||
_SetConsoleCursorPosition = windll.kernel32.SetConsoleCursorPosition
|
||||
_SetConsoleCursorPosition.argtypes = [
|
||||
wintypes.HANDLE,
|
||||
wintypes._COORD,
|
||||
]
|
||||
_SetConsoleCursorPosition.restype = wintypes.BOOL
|
||||
|
||||
_FillConsoleOutputCharacterA = windll.kernel32.FillConsoleOutputCharacterA
|
||||
_FillConsoleOutputCharacterA.argtypes = [
|
||||
wintypes.HANDLE,
|
||||
c_char,
|
||||
wintypes.DWORD,
|
||||
wintypes._COORD,
|
||||
POINTER(wintypes.DWORD),
|
||||
]
|
||||
_FillConsoleOutputCharacterA.restype = wintypes.BOOL
|
||||
|
||||
_FillConsoleOutputAttribute = windll.kernel32.FillConsoleOutputAttribute
|
||||
_FillConsoleOutputAttribute.argtypes = [
|
||||
wintypes.HANDLE,
|
||||
wintypes.WORD,
|
||||
wintypes.DWORD,
|
||||
wintypes._COORD,
|
||||
POINTER(wintypes.DWORD),
|
||||
]
|
||||
_FillConsoleOutputAttribute.restype = wintypes.BOOL
|
||||
|
||||
handles = {
|
||||
STDOUT: _GetStdHandle(STDOUT),
|
||||
STDERR: _GetStdHandle(STDERR),
|
||||
}
|
||||
|
||||
def GetConsoleScreenBufferInfo(stream_id=STDOUT):
|
||||
handle = handles[stream_id]
|
||||
csbi = CONSOLE_SCREEN_BUFFER_INFO()
|
||||
success = _GetConsoleScreenBufferInfo(
|
||||
handle, byref(csbi))
|
||||
return csbi
|
||||
|
||||
def SetConsoleTextAttribute(stream_id, attrs):
|
||||
handle = handles[stream_id]
|
||||
return _SetConsoleTextAttribute(handle, attrs)
|
||||
|
||||
def SetConsoleCursorPosition(stream_id, position):
|
||||
position = wintypes._COORD(*position)
|
||||
# If the position is out of range, do nothing.
|
||||
if position.Y <= 0 or position.X <= 0:
|
||||
return
|
||||
# Adjust for Windows' SetConsoleCursorPosition:
|
||||
# 1. being 0-based, while ANSI is 1-based.
|
||||
# 2. expecting (x,y), while ANSI uses (y,x).
|
||||
adjusted_position = wintypes._COORD(position.Y - 1, position.X - 1)
|
||||
# Adjust for viewport's scroll position
|
||||
sr = GetConsoleScreenBufferInfo(STDOUT).srWindow
|
||||
adjusted_position.Y += sr.Top
|
||||
adjusted_position.X += sr.Left
|
||||
# Resume normal processing
|
||||
handle = handles[stream_id]
|
||||
return _SetConsoleCursorPosition(handle, adjusted_position)
|
||||
|
||||
def FillConsoleOutputCharacter(stream_id, char, length, start):
|
||||
handle = handles[stream_id]
|
||||
char = c_char(char)
|
||||
length = wintypes.DWORD(length)
|
||||
num_written = wintypes.DWORD(0)
|
||||
# Note that this is hard-coded for ANSI (vs wide) bytes.
|
||||
success = _FillConsoleOutputCharacterA(
|
||||
handle, char, length, start, byref(num_written))
|
||||
return num_written.value
|
||||
|
||||
def FillConsoleOutputAttribute(stream_id, attr, length, start):
|
||||
''' FillConsoleOutputAttribute( hConsole, csbi.wAttributes, dwConSize, coordScreen, &cCharsWritten )'''
|
||||
handle = handles[stream_id]
|
||||
attribute = wintypes.WORD(attr)
|
||||
length = wintypes.DWORD(length)
|
||||
num_written = wintypes.DWORD(0)
|
||||
# Note that this is hard-coded for ANSI (vs wide) bytes.
|
||||
return _FillConsoleOutputAttribute(
|
||||
handle, attribute, length, start, byref(num_written))
|
||||
|
|
@ -0,0 +1,120 @@
|
|||
# Copyright Jonathan Hartley 2013. BSD 3-Clause license, see LICENSE file.
|
||||
from . import win32
|
||||
|
||||
|
||||
# from wincon.h
|
||||
class WinColor(object):
|
||||
BLACK = 0
|
||||
BLUE = 1
|
||||
GREEN = 2
|
||||
CYAN = 3
|
||||
RED = 4
|
||||
MAGENTA = 5
|
||||
YELLOW = 6
|
||||
GREY = 7
|
||||
|
||||
# from wincon.h
|
||||
class WinStyle(object):
|
||||
NORMAL = 0x00 # dim text, dim background
|
||||
BRIGHT = 0x08 # bright text, dim background
|
||||
|
||||
|
||||
class WinTerm(object):
|
||||
|
||||
def __init__(self):
|
||||
self._default = win32.GetConsoleScreenBufferInfo(win32.STDOUT).wAttributes
|
||||
self.set_attrs(self._default)
|
||||
self._default_fore = self._fore
|
||||
self._default_back = self._back
|
||||
self._default_style = self._style
|
||||
|
||||
def get_attrs(self):
|
||||
return self._fore + self._back * 16 + self._style
|
||||
|
||||
def set_attrs(self, value):
|
||||
self._fore = value & 7
|
||||
self._back = (value >> 4) & 7
|
||||
self._style = value & WinStyle.BRIGHT
|
||||
|
||||
def reset_all(self, on_stderr=None):
|
||||
self.set_attrs(self._default)
|
||||
self.set_console(attrs=self._default)
|
||||
|
||||
def fore(self, fore=None, on_stderr=False):
|
||||
if fore is None:
|
||||
fore = self._default_fore
|
||||
self._fore = fore
|
||||
self.set_console(on_stderr=on_stderr)
|
||||
|
||||
def back(self, back=None, on_stderr=False):
|
||||
if back is None:
|
||||
back = self._default_back
|
||||
self._back = back
|
||||
self.set_console(on_stderr=on_stderr)
|
||||
|
||||
def style(self, style=None, on_stderr=False):
|
||||
if style is None:
|
||||
style = self._default_style
|
||||
self._style = style
|
||||
self.set_console(on_stderr=on_stderr)
|
||||
|
||||
def set_console(self, attrs=None, on_stderr=False):
|
||||
if attrs is None:
|
||||
attrs = self.get_attrs()
|
||||
handle = win32.STDOUT
|
||||
if on_stderr:
|
||||
handle = win32.STDERR
|
||||
win32.SetConsoleTextAttribute(handle, attrs)
|
||||
|
||||
def get_position(self, handle):
|
||||
position = win32.GetConsoleScreenBufferInfo(handle).dwCursorPosition
|
||||
# Because Windows coordinates are 0-based,
|
||||
# and win32.SetConsoleCursorPosition expects 1-based.
|
||||
position.X += 1
|
||||
position.Y += 1
|
||||
return position
|
||||
|
||||
def set_cursor_position(self, position=None, on_stderr=False):
|
||||
if position is None:
|
||||
#I'm not currently tracking the position, so there is no default.
|
||||
#position = self.get_position()
|
||||
return
|
||||
handle = win32.STDOUT
|
||||
if on_stderr:
|
||||
handle = win32.STDERR
|
||||
win32.SetConsoleCursorPosition(handle, position)
|
||||
|
||||
def cursor_up(self, num_rows=0, on_stderr=False):
|
||||
if num_rows == 0:
|
||||
return
|
||||
handle = win32.STDOUT
|
||||
if on_stderr:
|
||||
handle = win32.STDERR
|
||||
position = self.get_position(handle)
|
||||
adjusted_position = (position.Y - num_rows, position.X)
|
||||
self.set_cursor_position(adjusted_position, on_stderr)
|
||||
|
||||
def erase_data(self, mode=0, on_stderr=False):
|
||||
# 0 (or None) should clear from the cursor to the end of the screen.
|
||||
# 1 should clear from the cursor to the beginning of the screen.
|
||||
# 2 should clear the entire screen. (And maybe move cursor to (1,1)?)
|
||||
#
|
||||
# At the moment, I only support mode 2. From looking at the API, it
|
||||
# should be possible to calculate a different number of bytes to clear,
|
||||
# and to do so relative to the cursor position.
|
||||
if mode[0] not in (2,):
|
||||
return
|
||||
handle = win32.STDOUT
|
||||
if on_stderr:
|
||||
handle = win32.STDERR
|
||||
# here's where we'll home the cursor
|
||||
coord_screen = win32.COORD(0,0)
|
||||
csbi = win32.GetConsoleScreenBufferInfo(handle)
|
||||
# get the number of character cells in the current buffer
|
||||
dw_con_size = csbi.dwSize.X * csbi.dwSize.Y
|
||||
# fill the entire screen with blanks
|
||||
win32.FillConsoleOutputCharacter(handle, ' ', dw_con_size, coord_screen)
|
||||
# now set the buffer's attributes accordingly
|
||||
win32.FillConsoleOutputAttribute(handle, self.get_attrs(), dw_con_size, coord_screen );
|
||||
# put the cursor at (0, 0)
|
||||
win32.SetConsoleCursorPosition(handle, (coord_screen.X, coord_screen.Y))
|
||||
|
|
@ -0,0 +1,23 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Copyright (C) 2012-2014 Vinay Sajip.
|
||||
# Licensed to the Python Software Foundation under a contributor agreement.
|
||||
# See LICENSE.txt and CONTRIBUTORS.txt.
|
||||
#
|
||||
import logging
|
||||
|
||||
__version__ = '0.1.8'
|
||||
|
||||
class DistlibException(Exception):
|
||||
pass
|
||||
|
||||
try:
|
||||
from logging import NullHandler
|
||||
except ImportError: # pragma: no cover
|
||||
class NullHandler(logging.Handler):
|
||||
def handle(self, record): pass
|
||||
def emit(self, record): pass
|
||||
def createLock(self): self.lock = None
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
logger.addHandler(NullHandler())
|
||||
|
|
@ -0,0 +1,6 @@
|
|||
"""Modules copied from Python 3 standard libraries, for internal use only.
|
||||
|
||||
Individual classes and functions are found in d2._backport.misc. Intended
|
||||
usage is to always import things missing from 3.1 from that module: the
|
||||
built-in/stdlib objects will be used if found.
|
||||
"""
|
||||
|
|
@ -0,0 +1,41 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Copyright (C) 2012 The Python Software Foundation.
|
||||
# See LICENSE.txt and CONTRIBUTORS.txt.
|
||||
#
|
||||
"""Backports for individual classes and functions."""
|
||||
|
||||
import os
|
||||
import sys
|
||||
|
||||
__all__ = ['cache_from_source', 'callable', 'fsencode']
|
||||
|
||||
|
||||
try:
|
||||
from imp import cache_from_source
|
||||
except ImportError:
|
||||
def cache_from_source(py_file, debug=__debug__):
|
||||
ext = debug and 'c' or 'o'
|
||||
return py_file + ext
|
||||
|
||||
|
||||
try:
|
||||
callable = callable
|
||||
except NameError:
|
||||
from collections import Callable
|
||||
|
||||
def callable(obj):
|
||||
return isinstance(obj, Callable)
|
||||
|
||||
|
||||
try:
|
||||
fsencode = os.fsencode
|
||||
except AttributeError:
|
||||
def fsencode(filename):
|
||||
if isinstance(filename, bytes):
|
||||
return filename
|
||||
elif isinstance(filename, str):
|
||||
return filename.encode(sys.getfilesystemencoding())
|
||||
else:
|
||||
raise TypeError("expect bytes or str, not %s" %
|
||||
type(filename).__name__)
|
||||
|
|
@ -0,0 +1,761 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Copyright (C) 2012 The Python Software Foundation.
|
||||
# See LICENSE.txt and CONTRIBUTORS.txt.
|
||||
#
|
||||
"""Utility functions for copying and archiving files and directory trees.
|
||||
|
||||
XXX The functions here don't copy the resource fork or other metadata on Mac.
|
||||
|
||||
"""
|
||||
|
||||
import os
|
||||
import sys
|
||||
import stat
|
||||
from os.path import abspath
|
||||
import fnmatch
|
||||
import collections
|
||||
import errno
|
||||
from . import tarfile
|
||||
|
||||
try:
|
||||
import bz2
|
||||
_BZ2_SUPPORTED = True
|
||||
except ImportError:
|
||||
_BZ2_SUPPORTED = False
|
||||
|
||||
try:
|
||||
from pwd import getpwnam
|
||||
except ImportError:
|
||||
getpwnam = None
|
||||
|
||||
try:
|
||||
from grp import getgrnam
|
||||
except ImportError:
|
||||
getgrnam = None
|
||||
|
||||
__all__ = ["copyfileobj", "copyfile", "copymode", "copystat", "copy", "copy2",
|
||||
"copytree", "move", "rmtree", "Error", "SpecialFileError",
|
||||
"ExecError", "make_archive", "get_archive_formats",
|
||||
"register_archive_format", "unregister_archive_format",
|
||||
"get_unpack_formats", "register_unpack_format",
|
||||
"unregister_unpack_format", "unpack_archive", "ignore_patterns"]
|
||||
|
||||
class Error(EnvironmentError):
|
||||
pass
|
||||
|
||||
class SpecialFileError(EnvironmentError):
|
||||
"""Raised when trying to do a kind of operation (e.g. copying) which is
|
||||
not supported on a special file (e.g. a named pipe)"""
|
||||
|
||||
class ExecError(EnvironmentError):
|
||||
"""Raised when a command could not be executed"""
|
||||
|
||||
class ReadError(EnvironmentError):
|
||||
"""Raised when an archive cannot be read"""
|
||||
|
||||
class RegistryError(Exception):
|
||||
"""Raised when a registery operation with the archiving
|
||||
and unpacking registeries fails"""
|
||||
|
||||
|
||||
try:
|
||||
WindowsError
|
||||
except NameError:
|
||||
WindowsError = None
|
||||
|
||||
def copyfileobj(fsrc, fdst, length=16*1024):
|
||||
"""copy data from file-like object fsrc to file-like object fdst"""
|
||||
while 1:
|
||||
buf = fsrc.read(length)
|
||||
if not buf:
|
||||
break
|
||||
fdst.write(buf)
|
||||
|
||||
def _samefile(src, dst):
|
||||
# Macintosh, Unix.
|
||||
if hasattr(os.path, 'samefile'):
|
||||
try:
|
||||
return os.path.samefile(src, dst)
|
||||
except OSError:
|
||||
return False
|
||||
|
||||
# All other platforms: check for same pathname.
|
||||
return (os.path.normcase(os.path.abspath(src)) ==
|
||||
os.path.normcase(os.path.abspath(dst)))
|
||||
|
||||
def copyfile(src, dst):
|
||||
"""Copy data from src to dst"""
|
||||
if _samefile(src, dst):
|
||||
raise Error("`%s` and `%s` are the same file" % (src, dst))
|
||||
|
||||
for fn in [src, dst]:
|
||||
try:
|
||||
st = os.stat(fn)
|
||||
except OSError:
|
||||
# File most likely does not exist
|
||||
pass
|
||||
else:
|
||||
# XXX What about other special files? (sockets, devices...)
|
||||
if stat.S_ISFIFO(st.st_mode):
|
||||
raise SpecialFileError("`%s` is a named pipe" % fn)
|
||||
|
||||
with open(src, 'rb') as fsrc:
|
||||
with open(dst, 'wb') as fdst:
|
||||
copyfileobj(fsrc, fdst)
|
||||
|
||||
def copymode(src, dst):
|
||||
"""Copy mode bits from src to dst"""
|
||||
if hasattr(os, 'chmod'):
|
||||
st = os.stat(src)
|
||||
mode = stat.S_IMODE(st.st_mode)
|
||||
os.chmod(dst, mode)
|
||||
|
||||
def copystat(src, dst):
|
||||
"""Copy all stat info (mode bits, atime, mtime, flags) from src to dst"""
|
||||
st = os.stat(src)
|
||||
mode = stat.S_IMODE(st.st_mode)
|
||||
if hasattr(os, 'utime'):
|
||||
os.utime(dst, (st.st_atime, st.st_mtime))
|
||||
if hasattr(os, 'chmod'):
|
||||
os.chmod(dst, mode)
|
||||
if hasattr(os, 'chflags') and hasattr(st, 'st_flags'):
|
||||
try:
|
||||
os.chflags(dst, st.st_flags)
|
||||
except OSError as why:
|
||||
if (not hasattr(errno, 'EOPNOTSUPP') or
|
||||
why.errno != errno.EOPNOTSUPP):
|
||||
raise
|
||||
|
||||
def copy(src, dst):
|
||||
"""Copy data and mode bits ("cp src dst").
|
||||
|
||||
The destination may be a directory.
|
||||
|
||||
"""
|
||||
if os.path.isdir(dst):
|
||||
dst = os.path.join(dst, os.path.basename(src))
|
||||
copyfile(src, dst)
|
||||
copymode(src, dst)
|
||||
|
||||
def copy2(src, dst):
|
||||
"""Copy data and all stat info ("cp -p src dst").
|
||||
|
||||
The destination may be a directory.
|
||||
|
||||
"""
|
||||
if os.path.isdir(dst):
|
||||
dst = os.path.join(dst, os.path.basename(src))
|
||||
copyfile(src, dst)
|
||||
copystat(src, dst)
|
||||
|
||||
def ignore_patterns(*patterns):
|
||||
"""Function that can be used as copytree() ignore parameter.
|
||||
|
||||
Patterns is a sequence of glob-style patterns
|
||||
that are used to exclude files"""
|
||||
def _ignore_patterns(path, names):
|
||||
ignored_names = []
|
||||
for pattern in patterns:
|
||||
ignored_names.extend(fnmatch.filter(names, pattern))
|
||||
return set(ignored_names)
|
||||
return _ignore_patterns
|
||||
|
||||
def copytree(src, dst, symlinks=False, ignore=None, copy_function=copy2,
|
||||
ignore_dangling_symlinks=False):
|
||||
"""Recursively copy a directory tree.
|
||||
|
||||
The destination directory must not already exist.
|
||||
If exception(s) occur, an Error is raised with a list of reasons.
|
||||
|
||||
If the optional symlinks flag is true, symbolic links in the
|
||||
source tree result in symbolic links in the destination tree; if
|
||||
it is false, the contents of the files pointed to by symbolic
|
||||
links are copied. If the file pointed by the symlink doesn't
|
||||
exist, an exception will be added in the list of errors raised in
|
||||
an Error exception at the end of the copy process.
|
||||
|
||||
You can set the optional ignore_dangling_symlinks flag to true if you
|
||||
want to silence this exception. Notice that this has no effect on
|
||||
platforms that don't support os.symlink.
|
||||
|
||||
The optional ignore argument is a callable. If given, it
|
||||
is called with the `src` parameter, which is the directory
|
||||
being visited by copytree(), and `names` which is the list of
|
||||
`src` contents, as returned by os.listdir():
|
||||
|
||||
callable(src, names) -> ignored_names
|
||||
|
||||
Since copytree() is called recursively, the callable will be
|
||||
called once for each directory that is copied. It returns a
|
||||
list of names relative to the `src` directory that should
|
||||
not be copied.
|
||||
|
||||
The optional copy_function argument is a callable that will be used
|
||||
to copy each file. It will be called with the source path and the
|
||||
destination path as arguments. By default, copy2() is used, but any
|
||||
function that supports the same signature (like copy()) can be used.
|
||||
|
||||
"""
|
||||
names = os.listdir(src)
|
||||
if ignore is not None:
|
||||
ignored_names = ignore(src, names)
|
||||
else:
|
||||
ignored_names = set()
|
||||
|
||||
os.makedirs(dst)
|
||||
errors = []
|
||||
for name in names:
|
||||
if name in ignored_names:
|
||||
continue
|
||||
srcname = os.path.join(src, name)
|
||||
dstname = os.path.join(dst, name)
|
||||
try:
|
||||
if os.path.islink(srcname):
|
||||
linkto = os.readlink(srcname)
|
||||
if symlinks:
|
||||
os.symlink(linkto, dstname)
|
||||
else:
|
||||
# ignore dangling symlink if the flag is on
|
||||
if not os.path.exists(linkto) and ignore_dangling_symlinks:
|
||||
continue
|
||||
# otherwise let the copy occurs. copy2 will raise an error
|
||||
copy_function(srcname, dstname)
|
||||
elif os.path.isdir(srcname):
|
||||
copytree(srcname, dstname, symlinks, ignore, copy_function)
|
||||
else:
|
||||
# Will raise a SpecialFileError for unsupported file types
|
||||
copy_function(srcname, dstname)
|
||||
# catch the Error from the recursive copytree so that we can
|
||||
# continue with other files
|
||||
except Error as err:
|
||||
errors.extend(err.args[0])
|
||||
except EnvironmentError as why:
|
||||
errors.append((srcname, dstname, str(why)))
|
||||
try:
|
||||
copystat(src, dst)
|
||||
except OSError as why:
|
||||
if WindowsError is not None and isinstance(why, WindowsError):
|
||||
# Copying file access times may fail on Windows
|
||||
pass
|
||||
else:
|
||||
errors.extend((src, dst, str(why)))
|
||||
if errors:
|
||||
raise Error(errors)
|
||||
|
||||
def rmtree(path, ignore_errors=False, onerror=None):
|
||||
"""Recursively delete a directory tree.
|
||||
|
||||
If ignore_errors is set, errors are ignored; otherwise, if onerror
|
||||
is set, it is called to handle the error with arguments (func,
|
||||
path, exc_info) where func is os.listdir, os.remove, or os.rmdir;
|
||||
path is the argument to that function that caused it to fail; and
|
||||
exc_info is a tuple returned by sys.exc_info(). If ignore_errors
|
||||
is false and onerror is None, an exception is raised.
|
||||
|
||||
"""
|
||||
if ignore_errors:
|
||||
def onerror(*args):
|
||||
pass
|
||||
elif onerror is None:
|
||||
def onerror(*args):
|
||||
raise
|
||||
try:
|
||||
if os.path.islink(path):
|
||||
# symlinks to directories are forbidden, see bug #1669
|
||||
raise OSError("Cannot call rmtree on a symbolic link")
|
||||
except OSError:
|
||||
onerror(os.path.islink, path, sys.exc_info())
|
||||
# can't continue even if onerror hook returns
|
||||
return
|
||||
names = []
|
||||
try:
|
||||
names = os.listdir(path)
|
||||
except os.error:
|
||||
onerror(os.listdir, path, sys.exc_info())
|
||||
for name in names:
|
||||
fullname = os.path.join(path, name)
|
||||
try:
|
||||
mode = os.lstat(fullname).st_mode
|
||||
except os.error:
|
||||
mode = 0
|
||||
if stat.S_ISDIR(mode):
|
||||
rmtree(fullname, ignore_errors, onerror)
|
||||
else:
|
||||
try:
|
||||
os.remove(fullname)
|
||||
except os.error:
|
||||
onerror(os.remove, fullname, sys.exc_info())
|
||||
try:
|
||||
os.rmdir(path)
|
||||
except os.error:
|
||||
onerror(os.rmdir, path, sys.exc_info())
|
||||
|
||||
|
||||
def _basename(path):
|
||||
# A basename() variant which first strips the trailing slash, if present.
|
||||
# Thus we always get the last component of the path, even for directories.
|
||||
return os.path.basename(path.rstrip(os.path.sep))
|
||||
|
||||
def move(src, dst):
|
||||
"""Recursively move a file or directory to another location. This is
|
||||
similar to the Unix "mv" command.
|
||||
|
||||
If the destination is a directory or a symlink to a directory, the source
|
||||
is moved inside the directory. The destination path must not already
|
||||
exist.
|
||||
|
||||
If the destination already exists but is not a directory, it may be
|
||||
overwritten depending on os.rename() semantics.
|
||||
|
||||
If the destination is on our current filesystem, then rename() is used.
|
||||
Otherwise, src is copied to the destination and then removed.
|
||||
A lot more could be done here... A look at a mv.c shows a lot of
|
||||
the issues this implementation glosses over.
|
||||
|
||||
"""
|
||||
real_dst = dst
|
||||
if os.path.isdir(dst):
|
||||
if _samefile(src, dst):
|
||||
# We might be on a case insensitive filesystem,
|
||||
# perform the rename anyway.
|
||||
os.rename(src, dst)
|
||||
return
|
||||
|
||||
real_dst = os.path.join(dst, _basename(src))
|
||||
if os.path.exists(real_dst):
|
||||
raise Error("Destination path '%s' already exists" % real_dst)
|
||||
try:
|
||||
os.rename(src, real_dst)
|
||||
except OSError:
|
||||
if os.path.isdir(src):
|
||||
if _destinsrc(src, dst):
|
||||
raise Error("Cannot move a directory '%s' into itself '%s'." % (src, dst))
|
||||
copytree(src, real_dst, symlinks=True)
|
||||
rmtree(src)
|
||||
else:
|
||||
copy2(src, real_dst)
|
||||
os.unlink(src)
|
||||
|
||||
def _destinsrc(src, dst):
|
||||
src = abspath(src)
|
||||
dst = abspath(dst)
|
||||
if not src.endswith(os.path.sep):
|
||||
src += os.path.sep
|
||||
if not dst.endswith(os.path.sep):
|
||||
dst += os.path.sep
|
||||
return dst.startswith(src)
|
||||
|
||||
def _get_gid(name):
|
||||
"""Returns a gid, given a group name."""
|
||||
if getgrnam is None or name is None:
|
||||
return None
|
||||
try:
|
||||
result = getgrnam(name)
|
||||
except KeyError:
|
||||
result = None
|
||||
if result is not None:
|
||||
return result[2]
|
||||
return None
|
||||
|
||||
def _get_uid(name):
|
||||
"""Returns an uid, given a user name."""
|
||||
if getpwnam is None or name is None:
|
||||
return None
|
||||
try:
|
||||
result = getpwnam(name)
|
||||
except KeyError:
|
||||
result = None
|
||||
if result is not None:
|
||||
return result[2]
|
||||
return None
|
||||
|
||||
def _make_tarball(base_name, base_dir, compress="gzip", verbose=0, dry_run=0,
|
||||
owner=None, group=None, logger=None):
|
||||
"""Create a (possibly compressed) tar file from all the files under
|
||||
'base_dir'.
|
||||
|
||||
'compress' must be "gzip" (the default), "bzip2", or None.
|
||||
|
||||
'owner' and 'group' can be used to define an owner and a group for the
|
||||
archive that is being built. If not provided, the current owner and group
|
||||
will be used.
|
||||
|
||||
The output tar file will be named 'base_name' + ".tar", possibly plus
|
||||
the appropriate compression extension (".gz", or ".bz2").
|
||||
|
||||
Returns the output filename.
|
||||
"""
|
||||
tar_compression = {'gzip': 'gz', None: ''}
|
||||
compress_ext = {'gzip': '.gz'}
|
||||
|
||||
if _BZ2_SUPPORTED:
|
||||
tar_compression['bzip2'] = 'bz2'
|
||||
compress_ext['bzip2'] = '.bz2'
|
||||
|
||||
# flags for compression program, each element of list will be an argument
|
||||
if compress is not None and compress not in compress_ext:
|
||||
raise ValueError("bad value for 'compress', or compression format not "
|
||||
"supported : {0}".format(compress))
|
||||
|
||||
archive_name = base_name + '.tar' + compress_ext.get(compress, '')
|
||||
archive_dir = os.path.dirname(archive_name)
|
||||
|
||||
if not os.path.exists(archive_dir):
|
||||
if logger is not None:
|
||||
logger.info("creating %s", archive_dir)
|
||||
if not dry_run:
|
||||
os.makedirs(archive_dir)
|
||||
|
||||
# creating the tarball
|
||||
if logger is not None:
|
||||
logger.info('Creating tar archive')
|
||||
|
||||
uid = _get_uid(owner)
|
||||
gid = _get_gid(group)
|
||||
|
||||
def _set_uid_gid(tarinfo):
|
||||
if gid is not None:
|
||||
tarinfo.gid = gid
|
||||
tarinfo.gname = group
|
||||
if uid is not None:
|
||||
tarinfo.uid = uid
|
||||
tarinfo.uname = owner
|
||||
return tarinfo
|
||||
|
||||
if not dry_run:
|
||||
tar = tarfile.open(archive_name, 'w|%s' % tar_compression[compress])
|
||||
try:
|
||||
tar.add(base_dir, filter=_set_uid_gid)
|
||||
finally:
|
||||
tar.close()
|
||||
|
||||
return archive_name
|
||||
|
||||
def _call_external_zip(base_dir, zip_filename, verbose=False, dry_run=False):
|
||||
# XXX see if we want to keep an external call here
|
||||
if verbose:
|
||||
zipoptions = "-r"
|
||||
else:
|
||||
zipoptions = "-rq"
|
||||
from distutils.errors import DistutilsExecError
|
||||
from distutils.spawn import spawn
|
||||
try:
|
||||
spawn(["zip", zipoptions, zip_filename, base_dir], dry_run=dry_run)
|
||||
except DistutilsExecError:
|
||||
# XXX really should distinguish between "couldn't find
|
||||
# external 'zip' command" and "zip failed".
|
||||
raise ExecError("unable to create zip file '%s': "
|
||||
"could neither import the 'zipfile' module nor "
|
||||
"find a standalone zip utility") % zip_filename
|
||||
|
||||
def _make_zipfile(base_name, base_dir, verbose=0, dry_run=0, logger=None):
|
||||
"""Create a zip file from all the files under 'base_dir'.
|
||||
|
||||
The output zip file will be named 'base_name' + ".zip". Uses either the
|
||||
"zipfile" Python module (if available) or the InfoZIP "zip" utility
|
||||
(if installed and found on the default search path). If neither tool is
|
||||
available, raises ExecError. Returns the name of the output zip
|
||||
file.
|
||||
"""
|
||||
zip_filename = base_name + ".zip"
|
||||
archive_dir = os.path.dirname(base_name)
|
||||
|
||||
if not os.path.exists(archive_dir):
|
||||
if logger is not None:
|
||||
logger.info("creating %s", archive_dir)
|
||||
if not dry_run:
|
||||
os.makedirs(archive_dir)
|
||||
|
||||
# If zipfile module is not available, try spawning an external 'zip'
|
||||
# command.
|
||||
try:
|
||||
import zipfile
|
||||
except ImportError:
|
||||
zipfile = None
|
||||
|
||||
if zipfile is None:
|
||||
_call_external_zip(base_dir, zip_filename, verbose, dry_run)
|
||||
else:
|
||||
if logger is not None:
|
||||
logger.info("creating '%s' and adding '%s' to it",
|
||||
zip_filename, base_dir)
|
||||
|
||||
if not dry_run:
|
||||
zip = zipfile.ZipFile(zip_filename, "w",
|
||||
compression=zipfile.ZIP_DEFLATED)
|
||||
|
||||
for dirpath, dirnames, filenames in os.walk(base_dir):
|
||||
for name in filenames:
|
||||
path = os.path.normpath(os.path.join(dirpath, name))
|
||||
if os.path.isfile(path):
|
||||
zip.write(path, path)
|
||||
if logger is not None:
|
||||
logger.info("adding '%s'", path)
|
||||
zip.close()
|
||||
|
||||
return zip_filename
|
||||
|
||||
_ARCHIVE_FORMATS = {
|
||||
'gztar': (_make_tarball, [('compress', 'gzip')], "gzip'ed tar-file"),
|
||||
'bztar': (_make_tarball, [('compress', 'bzip2')], "bzip2'ed tar-file"),
|
||||
'tar': (_make_tarball, [('compress', None)], "uncompressed tar file"),
|
||||
'zip': (_make_zipfile, [], "ZIP file"),
|
||||
}
|
||||
|
||||
if _BZ2_SUPPORTED:
|
||||
_ARCHIVE_FORMATS['bztar'] = (_make_tarball, [('compress', 'bzip2')],
|
||||
"bzip2'ed tar-file")
|
||||
|
||||
def get_archive_formats():
|
||||
"""Returns a list of supported formats for archiving and unarchiving.
|
||||
|
||||
Each element of the returned sequence is a tuple (name, description)
|
||||
"""
|
||||
formats = [(name, registry[2]) for name, registry in
|
||||
_ARCHIVE_FORMATS.items()]
|
||||
formats.sort()
|
||||
return formats
|
||||
|
||||
def register_archive_format(name, function, extra_args=None, description=''):
|
||||
"""Registers an archive format.
|
||||
|
||||
name is the name of the format. function is the callable that will be
|
||||
used to create archives. If provided, extra_args is a sequence of
|
||||
(name, value) tuples that will be passed as arguments to the callable.
|
||||
description can be provided to describe the format, and will be returned
|
||||
by the get_archive_formats() function.
|
||||
"""
|
||||
if extra_args is None:
|
||||
extra_args = []
|
||||
if not isinstance(function, collections.Callable):
|
||||
raise TypeError('The %s object is not callable' % function)
|
||||
if not isinstance(extra_args, (tuple, list)):
|
||||
raise TypeError('extra_args needs to be a sequence')
|
||||
for element in extra_args:
|
||||
if not isinstance(element, (tuple, list)) or len(element) !=2:
|
||||
raise TypeError('extra_args elements are : (arg_name, value)')
|
||||
|
||||
_ARCHIVE_FORMATS[name] = (function, extra_args, description)
|
||||
|
||||
def unregister_archive_format(name):
|
||||
del _ARCHIVE_FORMATS[name]
|
||||
|
||||
def make_archive(base_name, format, root_dir=None, base_dir=None, verbose=0,
|
||||
dry_run=0, owner=None, group=None, logger=None):
|
||||
"""Create an archive file (eg. zip or tar).
|
||||
|
||||
'base_name' is the name of the file to create, minus any format-specific
|
||||
extension; 'format' is the archive format: one of "zip", "tar", "bztar"
|
||||
or "gztar".
|
||||
|
||||
'root_dir' is a directory that will be the root directory of the
|
||||
archive; ie. we typically chdir into 'root_dir' before creating the
|
||||
archive. 'base_dir' is the directory where we start archiving from;
|
||||
ie. 'base_dir' will be the common prefix of all files and
|
||||
directories in the archive. 'root_dir' and 'base_dir' both default
|
||||
to the current directory. Returns the name of the archive file.
|
||||
|
||||
'owner' and 'group' are used when creating a tar archive. By default,
|
||||
uses the current owner and group.
|
||||
"""
|
||||
save_cwd = os.getcwd()
|
||||
if root_dir is not None:
|
||||
if logger is not None:
|
||||
logger.debug("changing into '%s'", root_dir)
|
||||
base_name = os.path.abspath(base_name)
|
||||
if not dry_run:
|
||||
os.chdir(root_dir)
|
||||
|
||||
if base_dir is None:
|
||||
base_dir = os.curdir
|
||||
|
||||
kwargs = {'dry_run': dry_run, 'logger': logger}
|
||||
|
||||
try:
|
||||
format_info = _ARCHIVE_FORMATS[format]
|
||||
except KeyError:
|
||||
raise ValueError("unknown archive format '%s'" % format)
|
||||
|
||||
func = format_info[0]
|
||||
for arg, val in format_info[1]:
|
||||
kwargs[arg] = val
|
||||
|
||||
if format != 'zip':
|
||||
kwargs['owner'] = owner
|
||||
kwargs['group'] = group
|
||||
|
||||
try:
|
||||
filename = func(base_name, base_dir, **kwargs)
|
||||
finally:
|
||||
if root_dir is not None:
|
||||
if logger is not None:
|
||||
logger.debug("changing back to '%s'", save_cwd)
|
||||
os.chdir(save_cwd)
|
||||
|
||||
return filename
|
||||
|
||||
|
||||
def get_unpack_formats():
|
||||
"""Returns a list of supported formats for unpacking.
|
||||
|
||||
Each element of the returned sequence is a tuple
|
||||
(name, extensions, description)
|
||||
"""
|
||||
formats = [(name, info[0], info[3]) for name, info in
|
||||
_UNPACK_FORMATS.items()]
|
||||
formats.sort()
|
||||
return formats
|
||||
|
||||
def _check_unpack_options(extensions, function, extra_args):
|
||||
"""Checks what gets registered as an unpacker."""
|
||||
# first make sure no other unpacker is registered for this extension
|
||||
existing_extensions = {}
|
||||
for name, info in _UNPACK_FORMATS.items():
|
||||
for ext in info[0]:
|
||||
existing_extensions[ext] = name
|
||||
|
||||
for extension in extensions:
|
||||
if extension in existing_extensions:
|
||||
msg = '%s is already registered for "%s"'
|
||||
raise RegistryError(msg % (extension,
|
||||
existing_extensions[extension]))
|
||||
|
||||
if not isinstance(function, collections.Callable):
|
||||
raise TypeError('The registered function must be a callable')
|
||||
|
||||
|
||||
def register_unpack_format(name, extensions, function, extra_args=None,
|
||||
description=''):
|
||||
"""Registers an unpack format.
|
||||
|
||||
`name` is the name of the format. `extensions` is a list of extensions
|
||||
corresponding to the format.
|
||||
|
||||
`function` is the callable that will be
|
||||
used to unpack archives. The callable will receive archives to unpack.
|
||||
If it's unable to handle an archive, it needs to raise a ReadError
|
||||
exception.
|
||||
|
||||
If provided, `extra_args` is a sequence of
|
||||
(name, value) tuples that will be passed as arguments to the callable.
|
||||
description can be provided to describe the format, and will be returned
|
||||
by the get_unpack_formats() function.
|
||||
"""
|
||||
if extra_args is None:
|
||||
extra_args = []
|
||||
_check_unpack_options(extensions, function, extra_args)
|
||||
_UNPACK_FORMATS[name] = extensions, function, extra_args, description
|
||||
|
||||
def unregister_unpack_format(name):
|
||||
"""Removes the pack format from the registery."""
|
||||
del _UNPACK_FORMATS[name]
|
||||
|
||||
def _ensure_directory(path):
|
||||
"""Ensure that the parent directory of `path` exists"""
|
||||
dirname = os.path.dirname(path)
|
||||
if not os.path.isdir(dirname):
|
||||
os.makedirs(dirname)
|
||||
|
||||
def _unpack_zipfile(filename, extract_dir):
|
||||
"""Unpack zip `filename` to `extract_dir`
|
||||
"""
|
||||
try:
|
||||
import zipfile
|
||||
except ImportError:
|
||||
raise ReadError('zlib not supported, cannot unpack this archive.')
|
||||
|
||||
if not zipfile.is_zipfile(filename):
|
||||
raise ReadError("%s is not a zip file" % filename)
|
||||
|
||||
zip = zipfile.ZipFile(filename)
|
||||
try:
|
||||
for info in zip.infolist():
|
||||
name = info.filename
|
||||
|
||||
# don't extract absolute paths or ones with .. in them
|
||||
if name.startswith('/') or '..' in name:
|
||||
continue
|
||||
|
||||
target = os.path.join(extract_dir, *name.split('/'))
|
||||
if not target:
|
||||
continue
|
||||
|
||||
_ensure_directory(target)
|
||||
if not name.endswith('/'):
|
||||
# file
|
||||
data = zip.read(info.filename)
|
||||
f = open(target, 'wb')
|
||||
try:
|
||||
f.write(data)
|
||||
finally:
|
||||
f.close()
|
||||
del data
|
||||
finally:
|
||||
zip.close()
|
||||
|
||||
def _unpack_tarfile(filename, extract_dir):
|
||||
"""Unpack tar/tar.gz/tar.bz2 `filename` to `extract_dir`
|
||||
"""
|
||||
try:
|
||||
tarobj = tarfile.open(filename)
|
||||
except tarfile.TarError:
|
||||
raise ReadError(
|
||||
"%s is not a compressed or uncompressed tar file" % filename)
|
||||
try:
|
||||
tarobj.extractall(extract_dir)
|
||||
finally:
|
||||
tarobj.close()
|
||||
|
||||
_UNPACK_FORMATS = {
|
||||
'gztar': (['.tar.gz', '.tgz'], _unpack_tarfile, [], "gzip'ed tar-file"),
|
||||
'tar': (['.tar'], _unpack_tarfile, [], "uncompressed tar file"),
|
||||
'zip': (['.zip'], _unpack_zipfile, [], "ZIP file")
|
||||
}
|
||||
|
||||
if _BZ2_SUPPORTED:
|
||||
_UNPACK_FORMATS['bztar'] = (['.bz2'], _unpack_tarfile, [],
|
||||
"bzip2'ed tar-file")
|
||||
|
||||
def _find_unpack_format(filename):
|
||||
for name, info in _UNPACK_FORMATS.items():
|
||||
for extension in info[0]:
|
||||
if filename.endswith(extension):
|
||||
return name
|
||||
return None
|
||||
|
||||
def unpack_archive(filename, extract_dir=None, format=None):
|
||||
"""Unpack an archive.
|
||||
|
||||
`filename` is the name of the archive.
|
||||
|
||||
`extract_dir` is the name of the target directory, where the archive
|
||||
is unpacked. If not provided, the current working directory is used.
|
||||
|
||||
`format` is the archive format: one of "zip", "tar", or "gztar". Or any
|
||||
other registered format. If not provided, unpack_archive will use the
|
||||
filename extension and see if an unpacker was registered for that
|
||||
extension.
|
||||
|
||||
In case none is found, a ValueError is raised.
|
||||
"""
|
||||
if extract_dir is None:
|
||||
extract_dir = os.getcwd()
|
||||
|
||||
if format is not None:
|
||||
try:
|
||||
format_info = _UNPACK_FORMATS[format]
|
||||
except KeyError:
|
||||
raise ValueError("Unknown unpack format '{0}'".format(format))
|
||||
|
||||
func = format_info[1]
|
||||
func(filename, extract_dir, **dict(format_info[2]))
|
||||
else:
|
||||
# we need to look at the registered unpackers supported extensions
|
||||
format = _find_unpack_format(filename)
|
||||
if format is None:
|
||||
raise ReadError("Unknown archive format '{0}'".format(filename))
|
||||
|
||||
func = _UNPACK_FORMATS[format][1]
|
||||
kwargs = dict(_UNPACK_FORMATS[format][2])
|
||||
func(filename, extract_dir, **kwargs)
|
||||
|
|
@ -0,0 +1,84 @@
|
|||
[posix_prefix]
|
||||
# Configuration directories. Some of these come straight out of the
|
||||
# configure script. They are for implementing the other variables, not to
|
||||
# be used directly in [resource_locations].
|
||||
confdir = /etc
|
||||
datadir = /usr/share
|
||||
libdir = /usr/lib
|
||||
statedir = /var
|
||||
# User resource directory
|
||||
local = ~/.local/{distribution.name}
|
||||
|
||||
stdlib = {base}/lib/python{py_version_short}
|
||||
platstdlib = {platbase}/lib/python{py_version_short}
|
||||
purelib = {base}/lib/python{py_version_short}/site-packages
|
||||
platlib = {platbase}/lib/python{py_version_short}/site-packages
|
||||
include = {base}/include/python{py_version_short}{abiflags}
|
||||
platinclude = {platbase}/include/python{py_version_short}{abiflags}
|
||||
data = {base}
|
||||
|
||||
[posix_home]
|
||||
stdlib = {base}/lib/python
|
||||
platstdlib = {base}/lib/python
|
||||
purelib = {base}/lib/python
|
||||
platlib = {base}/lib/python
|
||||
include = {base}/include/python
|
||||
platinclude = {base}/include/python
|
||||
scripts = {base}/bin
|
||||
data = {base}
|
||||
|
||||
[nt]
|
||||
stdlib = {base}/Lib
|
||||
platstdlib = {base}/Lib
|
||||
purelib = {base}/Lib/site-packages
|
||||
platlib = {base}/Lib/site-packages
|
||||
include = {base}/Include
|
||||
platinclude = {base}/Include
|
||||
scripts = {base}/Scripts
|
||||
data = {base}
|
||||
|
||||
[os2]
|
||||
stdlib = {base}/Lib
|
||||
platstdlib = {base}/Lib
|
||||
purelib = {base}/Lib/site-packages
|
||||
platlib = {base}/Lib/site-packages
|
||||
include = {base}/Include
|
||||
platinclude = {base}/Include
|
||||
scripts = {base}/Scripts
|
||||
data = {base}
|
||||
|
||||
[os2_home]
|
||||
stdlib = {userbase}/lib/python{py_version_short}
|
||||
platstdlib = {userbase}/lib/python{py_version_short}
|
||||
purelib = {userbase}/lib/python{py_version_short}/site-packages
|
||||
platlib = {userbase}/lib/python{py_version_short}/site-packages
|
||||
include = {userbase}/include/python{py_version_short}
|
||||
scripts = {userbase}/bin
|
||||
data = {userbase}
|
||||
|
||||
[nt_user]
|
||||
stdlib = {userbase}/Python{py_version_nodot}
|
||||
platstdlib = {userbase}/Python{py_version_nodot}
|
||||
purelib = {userbase}/Python{py_version_nodot}/site-packages
|
||||
platlib = {userbase}/Python{py_version_nodot}/site-packages
|
||||
include = {userbase}/Python{py_version_nodot}/Include
|
||||
scripts = {userbase}/Scripts
|
||||
data = {userbase}
|
||||
|
||||
[posix_user]
|
||||
stdlib = {userbase}/lib/python{py_version_short}
|
||||
platstdlib = {userbase}/lib/python{py_version_short}
|
||||
purelib = {userbase}/lib/python{py_version_short}/site-packages
|
||||
platlib = {userbase}/lib/python{py_version_short}/site-packages
|
||||
include = {userbase}/include/python{py_version_short}
|
||||
scripts = {userbase}/bin
|
||||
data = {userbase}
|
||||
|
||||
[osx_framework_user]
|
||||
stdlib = {userbase}/lib/python
|
||||
platstdlib = {userbase}/lib/python
|
||||
purelib = {userbase}/lib/python/site-packages
|
||||
platlib = {userbase}/lib/python/site-packages
|
||||
include = {userbase}/include
|
||||
scripts = {userbase}/bin
|
||||
data = {userbase}
|
||||
|
|
@ -0,0 +1,788 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Copyright (C) 2012 The Python Software Foundation.
|
||||
# See LICENSE.txt and CONTRIBUTORS.txt.
|
||||
#
|
||||
"""Access to Python's configuration information."""
|
||||
|
||||
import codecs
|
||||
import os
|
||||
import re
|
||||
import sys
|
||||
from os.path import pardir, realpath
|
||||
try:
|
||||
import configparser
|
||||
except ImportError:
|
||||
import ConfigParser as configparser
|
||||
|
||||
|
||||
__all__ = [
|
||||
'get_config_h_filename',
|
||||
'get_config_var',
|
||||
'get_config_vars',
|
||||
'get_makefile_filename',
|
||||
'get_path',
|
||||
'get_path_names',
|
||||
'get_paths',
|
||||
'get_platform',
|
||||
'get_python_version',
|
||||
'get_scheme_names',
|
||||
'parse_config_h',
|
||||
]
|
||||
|
||||
|
||||
def _safe_realpath(path):
|
||||
try:
|
||||
return realpath(path)
|
||||
except OSError:
|
||||
return path
|
||||
|
||||
|
||||
if sys.executable:
|
||||
_PROJECT_BASE = os.path.dirname(_safe_realpath(sys.executable))
|
||||
else:
|
||||
# sys.executable can be empty if argv[0] has been changed and Python is
|
||||
# unable to retrieve the real program name
|
||||
_PROJECT_BASE = _safe_realpath(os.getcwd())
|
||||
|
||||
if os.name == "nt" and "pcbuild" in _PROJECT_BASE[-8:].lower():
|
||||
_PROJECT_BASE = _safe_realpath(os.path.join(_PROJECT_BASE, pardir))
|
||||
# PC/VS7.1
|
||||
if os.name == "nt" and "\\pc\\v" in _PROJECT_BASE[-10:].lower():
|
||||
_PROJECT_BASE = _safe_realpath(os.path.join(_PROJECT_BASE, pardir, pardir))
|
||||
# PC/AMD64
|
||||
if os.name == "nt" and "\\pcbuild\\amd64" in _PROJECT_BASE[-14:].lower():
|
||||
_PROJECT_BASE = _safe_realpath(os.path.join(_PROJECT_BASE, pardir, pardir))
|
||||
|
||||
|
||||
def is_python_build():
|
||||
for fn in ("Setup.dist", "Setup.local"):
|
||||
if os.path.isfile(os.path.join(_PROJECT_BASE, "Modules", fn)):
|
||||
return True
|
||||
return False
|
||||
|
||||
_PYTHON_BUILD = is_python_build()
|
||||
|
||||
_cfg_read = False
|
||||
|
||||
def _ensure_cfg_read():
|
||||
global _cfg_read
|
||||
if not _cfg_read:
|
||||
from ..resources import finder
|
||||
backport_package = __name__.rsplit('.', 1)[0]
|
||||
_finder = finder(backport_package)
|
||||
_cfgfile = _finder.find('sysconfig.cfg')
|
||||
assert _cfgfile, 'sysconfig.cfg exists'
|
||||
with _cfgfile.as_stream() as s:
|
||||
_SCHEMES.readfp(s)
|
||||
if _PYTHON_BUILD:
|
||||
for scheme in ('posix_prefix', 'posix_home'):
|
||||
_SCHEMES.set(scheme, 'include', '{srcdir}/Include')
|
||||
_SCHEMES.set(scheme, 'platinclude', '{projectbase}/.')
|
||||
|
||||
_cfg_read = True
|
||||
|
||||
|
||||
_SCHEMES = configparser.RawConfigParser()
|
||||
_VAR_REPL = re.compile(r'\{([^{]*?)\}')
|
||||
|
||||
def _expand_globals(config):
|
||||
_ensure_cfg_read()
|
||||
if config.has_section('globals'):
|
||||
globals = config.items('globals')
|
||||
else:
|
||||
globals = tuple()
|
||||
|
||||
sections = config.sections()
|
||||
for section in sections:
|
||||
if section == 'globals':
|
||||
continue
|
||||
for option, value in globals:
|
||||
if config.has_option(section, option):
|
||||
continue
|
||||
config.set(section, option, value)
|
||||
config.remove_section('globals')
|
||||
|
||||
# now expanding local variables defined in the cfg file
|
||||
#
|
||||
for section in config.sections():
|
||||
variables = dict(config.items(section))
|
||||
|
||||
def _replacer(matchobj):
|
||||
name = matchobj.group(1)
|
||||
if name in variables:
|
||||
return variables[name]
|
||||
return matchobj.group(0)
|
||||
|
||||
for option, value in config.items(section):
|
||||
config.set(section, option, _VAR_REPL.sub(_replacer, value))
|
||||
|
||||
#_expand_globals(_SCHEMES)
|
||||
|
||||
# FIXME don't rely on sys.version here, its format is an implementation detail
|
||||
# of CPython, use sys.version_info or sys.hexversion
|
||||
_PY_VERSION = sys.version.split()[0]
|
||||
_PY_VERSION_SHORT = sys.version[:3]
|
||||
_PY_VERSION_SHORT_NO_DOT = _PY_VERSION[0] + _PY_VERSION[2]
|
||||
_PREFIX = os.path.normpath(sys.prefix)
|
||||
_EXEC_PREFIX = os.path.normpath(sys.exec_prefix)
|
||||
_CONFIG_VARS = None
|
||||
_USER_BASE = None
|
||||
|
||||
|
||||
def _subst_vars(path, local_vars):
|
||||
"""In the string `path`, replace tokens like {some.thing} with the
|
||||
corresponding value from the map `local_vars`.
|
||||
|
||||
If there is no corresponding value, leave the token unchanged.
|
||||
"""
|
||||
def _replacer(matchobj):
|
||||
name = matchobj.group(1)
|
||||
if name in local_vars:
|
||||
return local_vars[name]
|
||||
elif name in os.environ:
|
||||
return os.environ[name]
|
||||
return matchobj.group(0)
|
||||
return _VAR_REPL.sub(_replacer, path)
|
||||
|
||||
|
||||
def _extend_dict(target_dict, other_dict):
|
||||
target_keys = target_dict.keys()
|
||||
for key, value in other_dict.items():
|
||||
if key in target_keys:
|
||||
continue
|
||||
target_dict[key] = value
|
||||
|
||||
|
||||
def _expand_vars(scheme, vars):
|
||||
res = {}
|
||||
if vars is None:
|
||||
vars = {}
|
||||
_extend_dict(vars, get_config_vars())
|
||||
|
||||
for key, value in _SCHEMES.items(scheme):
|
||||
if os.name in ('posix', 'nt'):
|
||||
value = os.path.expanduser(value)
|
||||
res[key] = os.path.normpath(_subst_vars(value, vars))
|
||||
return res
|
||||
|
||||
|
||||
def format_value(value, vars):
|
||||
def _replacer(matchobj):
|
||||
name = matchobj.group(1)
|
||||
if name in vars:
|
||||
return vars[name]
|
||||
return matchobj.group(0)
|
||||
return _VAR_REPL.sub(_replacer, value)
|
||||
|
||||
|
||||
def _get_default_scheme():
|
||||
if os.name == 'posix':
|
||||
# the default scheme for posix is posix_prefix
|
||||
return 'posix_prefix'
|
||||
return os.name
|
||||
|
||||
|
||||
def _getuserbase():
|
||||
env_base = os.environ.get("PYTHONUSERBASE", None)
|
||||
|
||||
def joinuser(*args):
|
||||
return os.path.expanduser(os.path.join(*args))
|
||||
|
||||
# what about 'os2emx', 'riscos' ?
|
||||
if os.name == "nt":
|
||||
base = os.environ.get("APPDATA") or "~"
|
||||
if env_base:
|
||||
return env_base
|
||||
else:
|
||||
return joinuser(base, "Python")
|
||||
|
||||
if sys.platform == "darwin":
|
||||
framework = get_config_var("PYTHONFRAMEWORK")
|
||||
if framework:
|
||||
if env_base:
|
||||
return env_base
|
||||
else:
|
||||
return joinuser("~", "Library", framework, "%d.%d" %
|
||||
sys.version_info[:2])
|
||||
|
||||
if env_base:
|
||||
return env_base
|
||||
else:
|
||||
return joinuser("~", ".local")
|
||||
|
||||
|
||||
def _parse_makefile(filename, vars=None):
|
||||
"""Parse a Makefile-style file.
|
||||
|
||||
A dictionary containing name/value pairs is returned. If an
|
||||
optional dictionary is passed in as the second argument, it is
|
||||
used instead of a new dictionary.
|
||||
"""
|
||||
# Regexes needed for parsing Makefile (and similar syntaxes,
|
||||
# like old-style Setup files).
|
||||
_variable_rx = re.compile("([a-zA-Z][a-zA-Z0-9_]+)\s*=\s*(.*)")
|
||||
_findvar1_rx = re.compile(r"\$\(([A-Za-z][A-Za-z0-9_]*)\)")
|
||||
_findvar2_rx = re.compile(r"\${([A-Za-z][A-Za-z0-9_]*)}")
|
||||
|
||||
if vars is None:
|
||||
vars = {}
|
||||
done = {}
|
||||
notdone = {}
|
||||
|
||||
with codecs.open(filename, encoding='utf-8', errors="surrogateescape") as f:
|
||||
lines = f.readlines()
|
||||
|
||||
for line in lines:
|
||||
if line.startswith('#') or line.strip() == '':
|
||||
continue
|
||||
m = _variable_rx.match(line)
|
||||
if m:
|
||||
n, v = m.group(1, 2)
|
||||
v = v.strip()
|
||||
# `$$' is a literal `$' in make
|
||||
tmpv = v.replace('$$', '')
|
||||
|
||||
if "$" in tmpv:
|
||||
notdone[n] = v
|
||||
else:
|
||||
try:
|
||||
v = int(v)
|
||||
except ValueError:
|
||||
# insert literal `$'
|
||||
done[n] = v.replace('$$', '$')
|
||||
else:
|
||||
done[n] = v
|
||||
|
||||
# do variable interpolation here
|
||||
variables = list(notdone.keys())
|
||||
|
||||
# Variables with a 'PY_' prefix in the makefile. These need to
|
||||
# be made available without that prefix through sysconfig.
|
||||
# Special care is needed to ensure that variable expansion works, even
|
||||
# if the expansion uses the name without a prefix.
|
||||
renamed_variables = ('CFLAGS', 'LDFLAGS', 'CPPFLAGS')
|
||||
|
||||
while len(variables) > 0:
|
||||
for name in tuple(variables):
|
||||
value = notdone[name]
|
||||
m = _findvar1_rx.search(value) or _findvar2_rx.search(value)
|
||||
if m is not None:
|
||||
n = m.group(1)
|
||||
found = True
|
||||
if n in done:
|
||||
item = str(done[n])
|
||||
elif n in notdone:
|
||||
# get it on a subsequent round
|
||||
found = False
|
||||
elif n in os.environ:
|
||||
# do it like make: fall back to environment
|
||||
item = os.environ[n]
|
||||
|
||||
elif n in renamed_variables:
|
||||
if (name.startswith('PY_') and
|
||||
name[3:] in renamed_variables):
|
||||
item = ""
|
||||
|
||||
elif 'PY_' + n in notdone:
|
||||
found = False
|
||||
|
||||
else:
|
||||
item = str(done['PY_' + n])
|
||||
|
||||
else:
|
||||
done[n] = item = ""
|
||||
|
||||
if found:
|
||||
after = value[m.end():]
|
||||
value = value[:m.start()] + item + after
|
||||
if "$" in after:
|
||||
notdone[name] = value
|
||||
else:
|
||||
try:
|
||||
value = int(value)
|
||||
except ValueError:
|
||||
done[name] = value.strip()
|
||||
else:
|
||||
done[name] = value
|
||||
variables.remove(name)
|
||||
|
||||
if (name.startswith('PY_') and
|
||||
name[3:] in renamed_variables):
|
||||
|
||||
name = name[3:]
|
||||
if name not in done:
|
||||
done[name] = value
|
||||
|
||||
else:
|
||||
# bogus variable reference (e.g. "prefix=$/opt/python");
|
||||
# just drop it since we can't deal
|
||||
done[name] = value
|
||||
variables.remove(name)
|
||||
|
||||
# strip spurious spaces
|
||||
for k, v in done.items():
|
||||
if isinstance(v, str):
|
||||
done[k] = v.strip()
|
||||
|
||||
# save the results in the global dictionary
|
||||
vars.update(done)
|
||||
return vars
|
||||
|
||||
|
||||
def get_makefile_filename():
|
||||
"""Return the path of the Makefile."""
|
||||
if _PYTHON_BUILD:
|
||||
return os.path.join(_PROJECT_BASE, "Makefile")
|
||||
if hasattr(sys, 'abiflags'):
|
||||
config_dir_name = 'config-%s%s' % (_PY_VERSION_SHORT, sys.abiflags)
|
||||
else:
|
||||
config_dir_name = 'config'
|
||||
return os.path.join(get_path('stdlib'), config_dir_name, 'Makefile')
|
||||
|
||||
|
||||
def _init_posix(vars):
|
||||
"""Initialize the module as appropriate for POSIX systems."""
|
||||
# load the installed Makefile:
|
||||
makefile = get_makefile_filename()
|
||||
try:
|
||||
_parse_makefile(makefile, vars)
|
||||
except IOError as e:
|
||||
msg = "invalid Python installation: unable to open %s" % makefile
|
||||
if hasattr(e, "strerror"):
|
||||
msg = msg + " (%s)" % e.strerror
|
||||
raise IOError(msg)
|
||||
# load the installed pyconfig.h:
|
||||
config_h = get_config_h_filename()
|
||||
try:
|
||||
with open(config_h) as f:
|
||||
parse_config_h(f, vars)
|
||||
except IOError as e:
|
||||
msg = "invalid Python installation: unable to open %s" % config_h
|
||||
if hasattr(e, "strerror"):
|
||||
msg = msg + " (%s)" % e.strerror
|
||||
raise IOError(msg)
|
||||
# On AIX, there are wrong paths to the linker scripts in the Makefile
|
||||
# -- these paths are relative to the Python source, but when installed
|
||||
# the scripts are in another directory.
|
||||
if _PYTHON_BUILD:
|
||||
vars['LDSHARED'] = vars['BLDSHARED']
|
||||
|
||||
|
||||
def _init_non_posix(vars):
|
||||
"""Initialize the module as appropriate for NT"""
|
||||
# set basic install directories
|
||||
vars['LIBDEST'] = get_path('stdlib')
|
||||
vars['BINLIBDEST'] = get_path('platstdlib')
|
||||
vars['INCLUDEPY'] = get_path('include')
|
||||
vars['SO'] = '.pyd'
|
||||
vars['EXE'] = '.exe'
|
||||
vars['VERSION'] = _PY_VERSION_SHORT_NO_DOT
|
||||
vars['BINDIR'] = os.path.dirname(_safe_realpath(sys.executable))
|
||||
|
||||
#
|
||||
# public APIs
|
||||
#
|
||||
|
||||
|
||||
def parse_config_h(fp, vars=None):
|
||||
"""Parse a config.h-style file.
|
||||
|
||||
A dictionary containing name/value pairs is returned. If an
|
||||
optional dictionary is passed in as the second argument, it is
|
||||
used instead of a new dictionary.
|
||||
"""
|
||||
if vars is None:
|
||||
vars = {}
|
||||
define_rx = re.compile("#define ([A-Z][A-Za-z0-9_]+) (.*)\n")
|
||||
undef_rx = re.compile("/[*] #undef ([A-Z][A-Za-z0-9_]+) [*]/\n")
|
||||
|
||||
while True:
|
||||
line = fp.readline()
|
||||
if not line:
|
||||
break
|
||||
m = define_rx.match(line)
|
||||
if m:
|
||||
n, v = m.group(1, 2)
|
||||
try:
|
||||
v = int(v)
|
||||
except ValueError:
|
||||
pass
|
||||
vars[n] = v
|
||||
else:
|
||||
m = undef_rx.match(line)
|
||||
if m:
|
||||
vars[m.group(1)] = 0
|
||||
return vars
|
||||
|
||||
|
||||
def get_config_h_filename():
|
||||
"""Return the path of pyconfig.h."""
|
||||
if _PYTHON_BUILD:
|
||||
if os.name == "nt":
|
||||
inc_dir = os.path.join(_PROJECT_BASE, "PC")
|
||||
else:
|
||||
inc_dir = _PROJECT_BASE
|
||||
else:
|
||||
inc_dir = get_path('platinclude')
|
||||
return os.path.join(inc_dir, 'pyconfig.h')
|
||||
|
||||
|
||||
def get_scheme_names():
|
||||
"""Return a tuple containing the schemes names."""
|
||||
return tuple(sorted(_SCHEMES.sections()))
|
||||
|
||||
|
||||
def get_path_names():
|
||||
"""Return a tuple containing the paths names."""
|
||||
# xxx see if we want a static list
|
||||
return _SCHEMES.options('posix_prefix')
|
||||
|
||||
|
||||
def get_paths(scheme=_get_default_scheme(), vars=None, expand=True):
|
||||
"""Return a mapping containing an install scheme.
|
||||
|
||||
``scheme`` is the install scheme name. If not provided, it will
|
||||
return the default scheme for the current platform.
|
||||
"""
|
||||
_ensure_cfg_read()
|
||||
if expand:
|
||||
return _expand_vars(scheme, vars)
|
||||
else:
|
||||
return dict(_SCHEMES.items(scheme))
|
||||
|
||||
|
||||
def get_path(name, scheme=_get_default_scheme(), vars=None, expand=True):
|
||||
"""Return a path corresponding to the scheme.
|
||||
|
||||
``scheme`` is the install scheme name.
|
||||
"""
|
||||
return get_paths(scheme, vars, expand)[name]
|
||||
|
||||
|
||||
def get_config_vars(*args):
|
||||
"""With no arguments, return a dictionary of all configuration
|
||||
variables relevant for the current platform.
|
||||
|
||||
On Unix, this means every variable defined in Python's installed Makefile;
|
||||
On Windows and Mac OS it's a much smaller set.
|
||||
|
||||
With arguments, return a list of values that result from looking up
|
||||
each argument in the configuration variable dictionary.
|
||||
"""
|
||||
global _CONFIG_VARS
|
||||
if _CONFIG_VARS is None:
|
||||
_CONFIG_VARS = {}
|
||||
# Normalized versions of prefix and exec_prefix are handy to have;
|
||||
# in fact, these are the standard versions used most places in the
|
||||
# distutils2 module.
|
||||
_CONFIG_VARS['prefix'] = _PREFIX
|
||||
_CONFIG_VARS['exec_prefix'] = _EXEC_PREFIX
|
||||
_CONFIG_VARS['py_version'] = _PY_VERSION
|
||||
_CONFIG_VARS['py_version_short'] = _PY_VERSION_SHORT
|
||||
_CONFIG_VARS['py_version_nodot'] = _PY_VERSION[0] + _PY_VERSION[2]
|
||||
_CONFIG_VARS['base'] = _PREFIX
|
||||
_CONFIG_VARS['platbase'] = _EXEC_PREFIX
|
||||
_CONFIG_VARS['projectbase'] = _PROJECT_BASE
|
||||
try:
|
||||
_CONFIG_VARS['abiflags'] = sys.abiflags
|
||||
except AttributeError:
|
||||
# sys.abiflags may not be defined on all platforms.
|
||||
_CONFIG_VARS['abiflags'] = ''
|
||||
|
||||
if os.name in ('nt', 'os2'):
|
||||
_init_non_posix(_CONFIG_VARS)
|
||||
if os.name == 'posix':
|
||||
_init_posix(_CONFIG_VARS)
|
||||
# Setting 'userbase' is done below the call to the
|
||||
# init function to enable using 'get_config_var' in
|
||||
# the init-function.
|
||||
if sys.version >= '2.6':
|
||||
_CONFIG_VARS['userbase'] = _getuserbase()
|
||||
|
||||
if 'srcdir' not in _CONFIG_VARS:
|
||||
_CONFIG_VARS['srcdir'] = _PROJECT_BASE
|
||||
else:
|
||||
_CONFIG_VARS['srcdir'] = _safe_realpath(_CONFIG_VARS['srcdir'])
|
||||
|
||||
# Convert srcdir into an absolute path if it appears necessary.
|
||||
# Normally it is relative to the build directory. However, during
|
||||
# testing, for example, we might be running a non-installed python
|
||||
# from a different directory.
|
||||
if _PYTHON_BUILD and os.name == "posix":
|
||||
base = _PROJECT_BASE
|
||||
try:
|
||||
cwd = os.getcwd()
|
||||
except OSError:
|
||||
cwd = None
|
||||
if (not os.path.isabs(_CONFIG_VARS['srcdir']) and
|
||||
base != cwd):
|
||||
# srcdir is relative and we are not in the same directory
|
||||
# as the executable. Assume executable is in the build
|
||||
# directory and make srcdir absolute.
|
||||
srcdir = os.path.join(base, _CONFIG_VARS['srcdir'])
|
||||
_CONFIG_VARS['srcdir'] = os.path.normpath(srcdir)
|
||||
|
||||
if sys.platform == 'darwin':
|
||||
kernel_version = os.uname()[2] # Kernel version (8.4.3)
|
||||
major_version = int(kernel_version.split('.')[0])
|
||||
|
||||
if major_version < 8:
|
||||
# On Mac OS X before 10.4, check if -arch and -isysroot
|
||||
# are in CFLAGS or LDFLAGS and remove them if they are.
|
||||
# This is needed when building extensions on a 10.3 system
|
||||
# using a universal build of python.
|
||||
for key in ('LDFLAGS', 'BASECFLAGS',
|
||||
# a number of derived variables. These need to be
|
||||
# patched up as well.
|
||||
'CFLAGS', 'PY_CFLAGS', 'BLDSHARED'):
|
||||
flags = _CONFIG_VARS[key]
|
||||
flags = re.sub('-arch\s+\w+\s', ' ', flags)
|
||||
flags = re.sub('-isysroot [^ \t]*', ' ', flags)
|
||||
_CONFIG_VARS[key] = flags
|
||||
else:
|
||||
# Allow the user to override the architecture flags using
|
||||
# an environment variable.
|
||||
# NOTE: This name was introduced by Apple in OSX 10.5 and
|
||||
# is used by several scripting languages distributed with
|
||||
# that OS release.
|
||||
if 'ARCHFLAGS' in os.environ:
|
||||
arch = os.environ['ARCHFLAGS']
|
||||
for key in ('LDFLAGS', 'BASECFLAGS',
|
||||
# a number of derived variables. These need to be
|
||||
# patched up as well.
|
||||
'CFLAGS', 'PY_CFLAGS', 'BLDSHARED'):
|
||||
|
||||
flags = _CONFIG_VARS[key]
|
||||
flags = re.sub('-arch\s+\w+\s', ' ', flags)
|
||||
flags = flags + ' ' + arch
|
||||
_CONFIG_VARS[key] = flags
|
||||
|
||||
# If we're on OSX 10.5 or later and the user tries to
|
||||
# compiles an extension using an SDK that is not present
|
||||
# on the current machine it is better to not use an SDK
|
||||
# than to fail.
|
||||
#
|
||||
# The major usecase for this is users using a Python.org
|
||||
# binary installer on OSX 10.6: that installer uses
|
||||
# the 10.4u SDK, but that SDK is not installed by default
|
||||
# when you install Xcode.
|
||||
#
|
||||
CFLAGS = _CONFIG_VARS.get('CFLAGS', '')
|
||||
m = re.search('-isysroot\s+(\S+)', CFLAGS)
|
||||
if m is not None:
|
||||
sdk = m.group(1)
|
||||
if not os.path.exists(sdk):
|
||||
for key in ('LDFLAGS', 'BASECFLAGS',
|
||||
# a number of derived variables. These need to be
|
||||
# patched up as well.
|
||||
'CFLAGS', 'PY_CFLAGS', 'BLDSHARED'):
|
||||
|
||||
flags = _CONFIG_VARS[key]
|
||||
flags = re.sub('-isysroot\s+\S+(\s|$)', ' ', flags)
|
||||
_CONFIG_VARS[key] = flags
|
||||
|
||||
if args:
|
||||
vals = []
|
||||
for name in args:
|
||||
vals.append(_CONFIG_VARS.get(name))
|
||||
return vals
|
||||
else:
|
||||
return _CONFIG_VARS
|
||||
|
||||
|
||||
def get_config_var(name):
|
||||
"""Return the value of a single variable using the dictionary returned by
|
||||
'get_config_vars()'.
|
||||
|
||||
Equivalent to get_config_vars().get(name)
|
||||
"""
|
||||
return get_config_vars().get(name)
|
||||
|
||||
|
||||
def get_platform():
|
||||
"""Return a string that identifies the current platform.
|
||||
|
||||
This is used mainly to distinguish platform-specific build directories and
|
||||
platform-specific built distributions. Typically includes the OS name
|
||||
and version and the architecture (as supplied by 'os.uname()'),
|
||||
although the exact information included depends on the OS; eg. for IRIX
|
||||
the architecture isn't particularly important (IRIX only runs on SGI
|
||||
hardware), but for Linux the kernel version isn't particularly
|
||||
important.
|
||||
|
||||
Examples of returned values:
|
||||
linux-i586
|
||||
linux-alpha (?)
|
||||
solaris-2.6-sun4u
|
||||
irix-5.3
|
||||
irix64-6.2
|
||||
|
||||
Windows will return one of:
|
||||
win-amd64 (64bit Windows on AMD64 (aka x86_64, Intel64, EM64T, etc)
|
||||
win-ia64 (64bit Windows on Itanium)
|
||||
win32 (all others - specifically, sys.platform is returned)
|
||||
|
||||
For other non-POSIX platforms, currently just returns 'sys.platform'.
|
||||
"""
|
||||
if os.name == 'nt':
|
||||
# sniff sys.version for architecture.
|
||||
prefix = " bit ("
|
||||
i = sys.version.find(prefix)
|
||||
if i == -1:
|
||||
return sys.platform
|
||||
j = sys.version.find(")", i)
|
||||
look = sys.version[i+len(prefix):j].lower()
|
||||
if look == 'amd64':
|
||||
return 'win-amd64'
|
||||
if look == 'itanium':
|
||||
return 'win-ia64'
|
||||
return sys.platform
|
||||
|
||||
if os.name != "posix" or not hasattr(os, 'uname'):
|
||||
# XXX what about the architecture? NT is Intel or Alpha,
|
||||
# Mac OS is M68k or PPC, etc.
|
||||
return sys.platform
|
||||
|
||||
# Try to distinguish various flavours of Unix
|
||||
osname, host, release, version, machine = os.uname()
|
||||
|
||||
# Convert the OS name to lowercase, remove '/' characters
|
||||
# (to accommodate BSD/OS), and translate spaces (for "Power Macintosh")
|
||||
osname = osname.lower().replace('/', '')
|
||||
machine = machine.replace(' ', '_')
|
||||
machine = machine.replace('/', '-')
|
||||
|
||||
if osname[:5] == "linux":
|
||||
# At least on Linux/Intel, 'machine' is the processor --
|
||||
# i386, etc.
|
||||
# XXX what about Alpha, SPARC, etc?
|
||||
return "%s-%s" % (osname, machine)
|
||||
elif osname[:5] == "sunos":
|
||||
if release[0] >= "5": # SunOS 5 == Solaris 2
|
||||
osname = "solaris"
|
||||
release = "%d.%s" % (int(release[0]) - 3, release[2:])
|
||||
# fall through to standard osname-release-machine representation
|
||||
elif osname[:4] == "irix": # could be "irix64"!
|
||||
return "%s-%s" % (osname, release)
|
||||
elif osname[:3] == "aix":
|
||||
return "%s-%s.%s" % (osname, version, release)
|
||||
elif osname[:6] == "cygwin":
|
||||
osname = "cygwin"
|
||||
rel_re = re.compile(r'[\d.]+')
|
||||
m = rel_re.match(release)
|
||||
if m:
|
||||
release = m.group()
|
||||
elif osname[:6] == "darwin":
|
||||
#
|
||||
# For our purposes, we'll assume that the system version from
|
||||
# distutils' perspective is what MACOSX_DEPLOYMENT_TARGET is set
|
||||
# to. This makes the compatibility story a bit more sane because the
|
||||
# machine is going to compile and link as if it were
|
||||
# MACOSX_DEPLOYMENT_TARGET.
|
||||
cfgvars = get_config_vars()
|
||||
macver = cfgvars.get('MACOSX_DEPLOYMENT_TARGET')
|
||||
|
||||
if True:
|
||||
# Always calculate the release of the running machine,
|
||||
# needed to determine if we can build fat binaries or not.
|
||||
|
||||
macrelease = macver
|
||||
# Get the system version. Reading this plist is a documented
|
||||
# way to get the system version (see the documentation for
|
||||
# the Gestalt Manager)
|
||||
try:
|
||||
f = open('/System/Library/CoreServices/SystemVersion.plist')
|
||||
except IOError:
|
||||
# We're on a plain darwin box, fall back to the default
|
||||
# behaviour.
|
||||
pass
|
||||
else:
|
||||
try:
|
||||
m = re.search(r'<key>ProductUserVisibleVersion</key>\s*'
|
||||
r'<string>(.*?)</string>', f.read())
|
||||
finally:
|
||||
f.close()
|
||||
if m is not None:
|
||||
macrelease = '.'.join(m.group(1).split('.')[:2])
|
||||
# else: fall back to the default behaviour
|
||||
|
||||
if not macver:
|
||||
macver = macrelease
|
||||
|
||||
if macver:
|
||||
release = macver
|
||||
osname = "macosx"
|
||||
|
||||
if ((macrelease + '.') >= '10.4.' and
|
||||
'-arch' in get_config_vars().get('CFLAGS', '').strip()):
|
||||
# The universal build will build fat binaries, but not on
|
||||
# systems before 10.4
|
||||
#
|
||||
# Try to detect 4-way universal builds, those have machine-type
|
||||
# 'universal' instead of 'fat'.
|
||||
|
||||
machine = 'fat'
|
||||
cflags = get_config_vars().get('CFLAGS')
|
||||
|
||||
archs = re.findall('-arch\s+(\S+)', cflags)
|
||||
archs = tuple(sorted(set(archs)))
|
||||
|
||||
if len(archs) == 1:
|
||||
machine = archs[0]
|
||||
elif archs == ('i386', 'ppc'):
|
||||
machine = 'fat'
|
||||
elif archs == ('i386', 'x86_64'):
|
||||
machine = 'intel'
|
||||
elif archs == ('i386', 'ppc', 'x86_64'):
|
||||
machine = 'fat3'
|
||||
elif archs == ('ppc64', 'x86_64'):
|
||||
machine = 'fat64'
|
||||
elif archs == ('i386', 'ppc', 'ppc64', 'x86_64'):
|
||||
machine = 'universal'
|
||||
else:
|
||||
raise ValueError(
|
||||
"Don't know machine value for archs=%r" % (archs,))
|
||||
|
||||
elif machine == 'i386':
|
||||
# On OSX the machine type returned by uname is always the
|
||||
# 32-bit variant, even if the executable architecture is
|
||||
# the 64-bit variant
|
||||
if sys.maxsize >= 2**32:
|
||||
machine = 'x86_64'
|
||||
|
||||
elif machine in ('PowerPC', 'Power_Macintosh'):
|
||||
# Pick a sane name for the PPC architecture.
|
||||
# See 'i386' case
|
||||
if sys.maxsize >= 2**32:
|
||||
machine = 'ppc64'
|
||||
else:
|
||||
machine = 'ppc'
|
||||
|
||||
return "%s-%s-%s" % (osname, release, machine)
|
||||
|
||||
|
||||
def get_python_version():
|
||||
return _PY_VERSION_SHORT
|
||||
|
||||
|
||||
def _print_dict(title, data):
|
||||
for index, (key, value) in enumerate(sorted(data.items())):
|
||||
if index == 0:
|
||||
print('%s: ' % (title))
|
||||
print('\t%s = "%s"' % (key, value))
|
||||
|
||||
|
||||
def _main():
|
||||
"""Display all information sysconfig detains."""
|
||||
print('Platform: "%s"' % get_platform())
|
||||
print('Python version: "%s"' % get_python_version())
|
||||
print('Current installation scheme: "%s"' % _get_default_scheme())
|
||||
print()
|
||||
_print_dict('Paths', get_paths())
|
||||
print()
|
||||
_print_dict('Variables', get_config_vars())
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
_main()
|
||||
File diff suppressed because it is too large
Load diff
1064
Darwin/lib/python3.4/site-packages/pip/_vendor/distlib/compat.py
Normal file
1064
Darwin/lib/python3.4/site-packages/pip/_vendor/distlib/compat.py
Normal file
File diff suppressed because it is too large
Load diff
1301
Darwin/lib/python3.4/site-packages/pip/_vendor/distlib/database.py
Normal file
1301
Darwin/lib/python3.4/site-packages/pip/_vendor/distlib/database.py
Normal file
File diff suppressed because it is too large
Load diff
488
Darwin/lib/python3.4/site-packages/pip/_vendor/distlib/index.py
Normal file
488
Darwin/lib/python3.4/site-packages/pip/_vendor/distlib/index.py
Normal file
|
|
@ -0,0 +1,488 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Copyright (C) 2013 Vinay Sajip.
|
||||
# Licensed to the Python Software Foundation under a contributor agreement.
|
||||
# See LICENSE.txt and CONTRIBUTORS.txt.
|
||||
#
|
||||
import hashlib
|
||||
import logging
|
||||
import os
|
||||
import shutil
|
||||
import subprocess
|
||||
import tempfile
|
||||
try:
|
||||
from threading import Thread
|
||||
except ImportError:
|
||||
from dummy_threading import Thread
|
||||
|
||||
from . import DistlibException
|
||||
from .compat import (HTTPBasicAuthHandler, Request, HTTPPasswordMgr,
|
||||
urlparse, build_opener, string_types)
|
||||
from .util import cached_property, zip_dir, ServerProxy
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
DEFAULT_INDEX = 'https://pypi.python.org/pypi'
|
||||
DEFAULT_REALM = 'pypi'
|
||||
|
||||
class PackageIndex(object):
|
||||
"""
|
||||
This class represents a package index compatible with PyPI, the Python
|
||||
Package Index.
|
||||
"""
|
||||
|
||||
boundary = b'----------ThIs_Is_tHe_distlib_index_bouNdaRY_$'
|
||||
|
||||
def __init__(self, url=None):
|
||||
"""
|
||||
Initialise an instance.
|
||||
|
||||
:param url: The URL of the index. If not specified, the URL for PyPI is
|
||||
used.
|
||||
"""
|
||||
self.url = url or DEFAULT_INDEX
|
||||
self.read_configuration()
|
||||
scheme, netloc, path, params, query, frag = urlparse(self.url)
|
||||
if params or query or frag or scheme not in ('http', 'https'):
|
||||
raise DistlibException('invalid repository: %s' % self.url)
|
||||
self.password_handler = None
|
||||
self.ssl_verifier = None
|
||||
self.gpg = None
|
||||
self.gpg_home = None
|
||||
self.rpc_proxy = None
|
||||
with open(os.devnull, 'w') as sink:
|
||||
for s in ('gpg2', 'gpg'):
|
||||
try:
|
||||
rc = subprocess.check_call([s, '--version'], stdout=sink,
|
||||
stderr=sink)
|
||||
if rc == 0:
|
||||
self.gpg = s
|
||||
break
|
||||
except OSError:
|
||||
pass
|
||||
|
||||
def _get_pypirc_command(self):
|
||||
"""
|
||||
Get the distutils command for interacting with PyPI configurations.
|
||||
:return: the command.
|
||||
"""
|
||||
from distutils.core import Distribution
|
||||
from distutils.config import PyPIRCCommand
|
||||
d = Distribution()
|
||||
return PyPIRCCommand(d)
|
||||
|
||||
def read_configuration(self):
|
||||
"""
|
||||
Read the PyPI access configuration as supported by distutils, getting
|
||||
PyPI to do the acutal work. This populates ``username``, ``password``,
|
||||
``realm`` and ``url`` attributes from the configuration.
|
||||
"""
|
||||
# get distutils to do the work
|
||||
c = self._get_pypirc_command()
|
||||
c.repository = self.url
|
||||
cfg = c._read_pypirc()
|
||||
self.username = cfg.get('username')
|
||||
self.password = cfg.get('password')
|
||||
self.realm = cfg.get('realm', 'pypi')
|
||||
self.url = cfg.get('repository', self.url)
|
||||
|
||||
def save_configuration(self):
|
||||
"""
|
||||
Save the PyPI access configuration. You must have set ``username`` and
|
||||
``password`` attributes before calling this method.
|
||||
|
||||
Again, distutils is used to do the actual work.
|
||||
"""
|
||||
self.check_credentials()
|
||||
# get distutils to do the work
|
||||
c = self._get_pypirc_command()
|
||||
c._store_pypirc(self.username, self.password)
|
||||
|
||||
def check_credentials(self):
|
||||
"""
|
||||
Check that ``username`` and ``password`` have been set, and raise an
|
||||
exception if not.
|
||||
"""
|
||||
if self.username is None or self.password is None:
|
||||
raise DistlibException('username and password must be set')
|
||||
pm = HTTPPasswordMgr()
|
||||
_, netloc, _, _, _, _ = urlparse(self.url)
|
||||
pm.add_password(self.realm, netloc, self.username, self.password)
|
||||
self.password_handler = HTTPBasicAuthHandler(pm)
|
||||
|
||||
def register(self, metadata):
|
||||
"""
|
||||
Register a distribution on PyPI, using the provided metadata.
|
||||
|
||||
:param metadata: A :class:`Metadata` instance defining at least a name
|
||||
and version number for the distribution to be
|
||||
registered.
|
||||
:return: The HTTP response received from PyPI upon submission of the
|
||||
request.
|
||||
"""
|
||||
self.check_credentials()
|
||||
metadata.validate()
|
||||
d = metadata.todict()
|
||||
d[':action'] = 'verify'
|
||||
request = self.encode_request(d.items(), [])
|
||||
response = self.send_request(request)
|
||||
d[':action'] = 'submit'
|
||||
request = self.encode_request(d.items(), [])
|
||||
return self.send_request(request)
|
||||
|
||||
def _reader(self, name, stream, outbuf):
|
||||
"""
|
||||
Thread runner for reading lines of from a subprocess into a buffer.
|
||||
|
||||
:param name: The logical name of the stream (used for logging only).
|
||||
:param stream: The stream to read from. This will typically a pipe
|
||||
connected to the output stream of a subprocess.
|
||||
:param outbuf: The list to append the read lines to.
|
||||
"""
|
||||
while True:
|
||||
s = stream.readline()
|
||||
if not s:
|
||||
break
|
||||
s = s.decode('utf-8').rstrip()
|
||||
outbuf.append(s)
|
||||
logger.debug('%s: %s' % (name, s))
|
||||
stream.close()
|
||||
|
||||
def get_sign_command(self, filename, signer, sign_password):
|
||||
"""
|
||||
Return a suitable command for signing a file.
|
||||
|
||||
:param filename: The pathname to the file to be signed.
|
||||
:param signer: The identifier of the signer of the file.
|
||||
:param sign_password: The passphrase for the signer's
|
||||
private key used for signing.
|
||||
:return: The signing command as a list suitable to be
|
||||
passed to :class:`subprocess.Popen`.
|
||||
"""
|
||||
cmd = [self.gpg, '--status-fd', '2', '--no-tty']
|
||||
if self.gpg_home:
|
||||
cmd.extend(['--homedir', self.gpg_home])
|
||||
if sign_password is not None:
|
||||
cmd.extend(['--batch', '--passphrase-fd', '0'])
|
||||
td = tempfile.mkdtemp()
|
||||
sf = os.path.join(td, os.path.basename(filename) + '.asc')
|
||||
cmd.extend(['--detach-sign', '--armor', '--local-user',
|
||||
signer, '--output', sf, filename])
|
||||
logger.debug('invoking: %s', ' '.join(cmd))
|
||||
return cmd, sf
|
||||
|
||||
def run_command(self, cmd, input_data=None):
|
||||
"""
|
||||
Run a command in a child process , passing it any input data specified.
|
||||
|
||||
:param cmd: The command to run.
|
||||
:param input_data: If specified, this must be a byte string containing
|
||||
data to be sent to the child process.
|
||||
:return: A tuple consisting of the subprocess' exit code, a list of
|
||||
lines read from the subprocess' ``stdout``, and a list of
|
||||
lines read from the subprocess' ``stderr``.
|
||||
"""
|
||||
kwargs = {
|
||||
'stdout': subprocess.PIPE,
|
||||
'stderr': subprocess.PIPE,
|
||||
}
|
||||
if input_data is not None:
|
||||
kwargs['stdin'] = subprocess.PIPE
|
||||
stdout = []
|
||||
stderr = []
|
||||
p = subprocess.Popen(cmd, **kwargs)
|
||||
# We don't use communicate() here because we may need to
|
||||
# get clever with interacting with the command
|
||||
t1 = Thread(target=self._reader, args=('stdout', p.stdout, stdout))
|
||||
t1.start()
|
||||
t2 = Thread(target=self._reader, args=('stderr', p.stderr, stderr))
|
||||
t2.start()
|
||||
if input_data is not None:
|
||||
p.stdin.write(input_data)
|
||||
p.stdin.close()
|
||||
|
||||
p.wait()
|
||||
t1.join()
|
||||
t2.join()
|
||||
return p.returncode, stdout, stderr
|
||||
|
||||
def sign_file(self, filename, signer, sign_password):
|
||||
"""
|
||||
Sign a file.
|
||||
|
||||
:param filename: The pathname to the file to be signed.
|
||||
:param signer: The identifier of the signer of the file.
|
||||
:param sign_password: The passphrase for the signer's
|
||||
private key used for signing.
|
||||
:return: The absolute pathname of the file where the signature is
|
||||
stored.
|
||||
"""
|
||||
cmd, sig_file = self.get_sign_command(filename, signer, sign_password)
|
||||
rc, stdout, stderr = self.run_command(cmd,
|
||||
sign_password.encode('utf-8'))
|
||||
if rc != 0:
|
||||
raise DistlibException('sign command failed with error '
|
||||
'code %s' % rc)
|
||||
return sig_file
|
||||
|
||||
def upload_file(self, metadata, filename, signer=None, sign_password=None,
|
||||
filetype='sdist', pyversion='source'):
|
||||
"""
|
||||
Upload a release file to the index.
|
||||
|
||||
:param metadata: A :class:`Metadata` instance defining at least a name
|
||||
and version number for the file to be uploaded.
|
||||
:param filename: The pathname of the file to be uploaded.
|
||||
:param signer: The identifier of the signer of the file.
|
||||
:param sign_password: The passphrase for the signer's
|
||||
private key used for signing.
|
||||
:param filetype: The type of the file being uploaded. This is the
|
||||
distutils command which produced that file, e.g.
|
||||
``sdist`` or ``bdist_wheel``.
|
||||
:param pyversion: The version of Python which the release relates
|
||||
to. For code compatible with any Python, this would
|
||||
be ``source``, otherwise it would be e.g. ``3.2``.
|
||||
:return: The HTTP response received from PyPI upon submission of the
|
||||
request.
|
||||
"""
|
||||
self.check_credentials()
|
||||
if not os.path.exists(filename):
|
||||
raise DistlibException('not found: %s' % filename)
|
||||
metadata.validate()
|
||||
d = metadata.todict()
|
||||
sig_file = None
|
||||
if signer:
|
||||
if not self.gpg:
|
||||
logger.warning('no signing program available - not signed')
|
||||
else:
|
||||
sig_file = self.sign_file(filename, signer, sign_password)
|
||||
with open(filename, 'rb') as f:
|
||||
file_data = f.read()
|
||||
md5_digest = hashlib.md5(file_data).hexdigest()
|
||||
sha256_digest = hashlib.sha256(file_data).hexdigest()
|
||||
d.update({
|
||||
':action': 'file_upload',
|
||||
'protcol_version': '1',
|
||||
'filetype': filetype,
|
||||
'pyversion': pyversion,
|
||||
'md5_digest': md5_digest,
|
||||
'sha256_digest': sha256_digest,
|
||||
})
|
||||
files = [('content', os.path.basename(filename), file_data)]
|
||||
if sig_file:
|
||||
with open(sig_file, 'rb') as f:
|
||||
sig_data = f.read()
|
||||
files.append(('gpg_signature', os.path.basename(sig_file),
|
||||
sig_data))
|
||||
shutil.rmtree(os.path.dirname(sig_file))
|
||||
request = self.encode_request(d.items(), files)
|
||||
return self.send_request(request)
|
||||
|
||||
def upload_documentation(self, metadata, doc_dir):
|
||||
"""
|
||||
Upload documentation to the index.
|
||||
|
||||
:param metadata: A :class:`Metadata` instance defining at least a name
|
||||
and version number for the documentation to be
|
||||
uploaded.
|
||||
:param doc_dir: The pathname of the directory which contains the
|
||||
documentation. This should be the directory that
|
||||
contains the ``index.html`` for the documentation.
|
||||
:return: The HTTP response received from PyPI upon submission of the
|
||||
request.
|
||||
"""
|
||||
self.check_credentials()
|
||||
if not os.path.isdir(doc_dir):
|
||||
raise DistlibException('not a directory: %r' % doc_dir)
|
||||
fn = os.path.join(doc_dir, 'index.html')
|
||||
if not os.path.exists(fn):
|
||||
raise DistlibException('not found: %r' % fn)
|
||||
metadata.validate()
|
||||
name, version = metadata.name, metadata.version
|
||||
zip_data = zip_dir(doc_dir).getvalue()
|
||||
fields = [(':action', 'doc_upload'),
|
||||
('name', name), ('version', version)]
|
||||
files = [('content', name, zip_data)]
|
||||
request = self.encode_request(fields, files)
|
||||
return self.send_request(request)
|
||||
|
||||
def get_verify_command(self, signature_filename, data_filename):
|
||||
"""
|
||||
Return a suitable command for verifying a file.
|
||||
|
||||
:param signature_filename: The pathname to the file containing the
|
||||
signature.
|
||||
:param data_filename: The pathname to the file containing the
|
||||
signed data.
|
||||
:return: The verifying command as a list suitable to be
|
||||
passed to :class:`subprocess.Popen`.
|
||||
"""
|
||||
cmd = [self.gpg, '--status-fd', '2', '--no-tty']
|
||||
if self.gpg_home:
|
||||
cmd.extend(['--homedir', self.gpg_home])
|
||||
cmd.extend(['--verify', signature_filename, data_filename])
|
||||
logger.debug('invoking: %s', ' '.join(cmd))
|
||||
return cmd
|
||||
|
||||
def verify_signature(self, signature_filename, data_filename):
|
||||
"""
|
||||
Verify a signature for a file.
|
||||
|
||||
:param signature_filename: The pathname to the file containing the
|
||||
signature.
|
||||
:param data_filename: The pathname to the file containing the
|
||||
signed data.
|
||||
:return: True if the signature was verified, else False.
|
||||
"""
|
||||
if not self.gpg:
|
||||
raise DistlibException('verification unavailable because gpg '
|
||||
'unavailable')
|
||||
cmd = self.get_verify_command(signature_filename, data_filename)
|
||||
rc, stdout, stderr = self.run_command(cmd)
|
||||
if rc not in (0, 1):
|
||||
raise DistlibException('verify command failed with error '
|
||||
'code %s' % rc)
|
||||
return rc == 0
|
||||
|
||||
def download_file(self, url, destfile, digest=None, reporthook=None):
|
||||
"""
|
||||
This is a convenience method for downloading a file from an URL.
|
||||
Normally, this will be a file from the index, though currently
|
||||
no check is made for this (i.e. a file can be downloaded from
|
||||
anywhere).
|
||||
|
||||
The method is just like the :func:`urlretrieve` function in the
|
||||
standard library, except that it allows digest computation to be
|
||||
done during download and checking that the downloaded data
|
||||
matched any expected value.
|
||||
|
||||
:param url: The URL of the file to be downloaded (assumed to be
|
||||
available via an HTTP GET request).
|
||||
:param destfile: The pathname where the downloaded file is to be
|
||||
saved.
|
||||
:param digest: If specified, this must be a (hasher, value)
|
||||
tuple, where hasher is the algorithm used (e.g.
|
||||
``'md5'``) and ``value`` is the expected value.
|
||||
:param reporthook: The same as for :func:`urlretrieve` in the
|
||||
standard library.
|
||||
"""
|
||||
if digest is None:
|
||||
digester = None
|
||||
logger.debug('No digest specified')
|
||||
else:
|
||||
if isinstance(digest, (list, tuple)):
|
||||
hasher, digest = digest
|
||||
else:
|
||||
hasher = 'md5'
|
||||
digester = getattr(hashlib, hasher)()
|
||||
logger.debug('Digest specified: %s' % digest)
|
||||
# The following code is equivalent to urlretrieve.
|
||||
# We need to do it this way so that we can compute the
|
||||
# digest of the file as we go.
|
||||
with open(destfile, 'wb') as dfp:
|
||||
# addinfourl is not a context manager on 2.x
|
||||
# so we have to use try/finally
|
||||
sfp = self.send_request(Request(url))
|
||||
try:
|
||||
headers = sfp.info()
|
||||
blocksize = 8192
|
||||
size = -1
|
||||
read = 0
|
||||
blocknum = 0
|
||||
if "content-length" in headers:
|
||||
size = int(headers["Content-Length"])
|
||||
if reporthook:
|
||||
reporthook(blocknum, blocksize, size)
|
||||
while True:
|
||||
block = sfp.read(blocksize)
|
||||
if not block:
|
||||
break
|
||||
read += len(block)
|
||||
dfp.write(block)
|
||||
if digester:
|
||||
digester.update(block)
|
||||
blocknum += 1
|
||||
if reporthook:
|
||||
reporthook(blocknum, blocksize, size)
|
||||
finally:
|
||||
sfp.close()
|
||||
|
||||
# check that we got the whole file, if we can
|
||||
if size >= 0 and read < size:
|
||||
raise DistlibException(
|
||||
'retrieval incomplete: got only %d out of %d bytes'
|
||||
% (read, size))
|
||||
# if we have a digest, it must match.
|
||||
if digester:
|
||||
actual = digester.hexdigest()
|
||||
if digest != actual:
|
||||
raise DistlibException('%s digest mismatch for %s: expected '
|
||||
'%s, got %s' % (hasher, destfile,
|
||||
digest, actual))
|
||||
logger.debug('Digest verified: %s', digest)
|
||||
|
||||
def send_request(self, req):
|
||||
"""
|
||||
Send a standard library :class:`Request` to PyPI and return its
|
||||
response.
|
||||
|
||||
:param req: The request to send.
|
||||
:return: The HTTP response from PyPI (a standard library HTTPResponse).
|
||||
"""
|
||||
handlers = []
|
||||
if self.password_handler:
|
||||
handlers.append(self.password_handler)
|
||||
if self.ssl_verifier:
|
||||
handlers.append(self.ssl_verifier)
|
||||
opener = build_opener(*handlers)
|
||||
return opener.open(req)
|
||||
|
||||
def encode_request(self, fields, files):
|
||||
"""
|
||||
Encode fields and files for posting to an HTTP server.
|
||||
|
||||
:param fields: The fields to send as a list of (fieldname, value)
|
||||
tuples.
|
||||
:param files: The files to send as a list of (fieldname, filename,
|
||||
file_bytes) tuple.
|
||||
"""
|
||||
# Adapted from packaging, which in turn was adapted from
|
||||
# http://code.activestate.com/recipes/146306
|
||||
|
||||
parts = []
|
||||
boundary = self.boundary
|
||||
for k, values in fields:
|
||||
if not isinstance(values, (list, tuple)):
|
||||
values = [values]
|
||||
|
||||
for v in values:
|
||||
parts.extend((
|
||||
b'--' + boundary,
|
||||
('Content-Disposition: form-data; name="%s"' %
|
||||
k).encode('utf-8'),
|
||||
b'',
|
||||
v.encode('utf-8')))
|
||||
for key, filename, value in files:
|
||||
parts.extend((
|
||||
b'--' + boundary,
|
||||
('Content-Disposition: form-data; name="%s"; filename="%s"' %
|
||||
(key, filename)).encode('utf-8'),
|
||||
b'',
|
||||
value))
|
||||
|
||||
parts.extend((b'--' + boundary + b'--', b''))
|
||||
|
||||
body = b'\r\n'.join(parts)
|
||||
ct = b'multipart/form-data; boundary=' + boundary
|
||||
headers = {
|
||||
'Content-type': ct,
|
||||
'Content-length': str(len(body))
|
||||
}
|
||||
return Request(self.url, body, headers)
|
||||
|
||||
def search(self, terms, operator=None):
|
||||
if isinstance(terms, string_types):
|
||||
terms = {'name': terms}
|
||||
if self.rpc_proxy is None:
|
||||
self.rpc_proxy = ServerProxy(self.url, timeout=3.0)
|
||||
return self.rpc_proxy.search(terms, operator or 'and')
|
||||
1194
Darwin/lib/python3.4/site-packages/pip/_vendor/distlib/locators.py
Normal file
1194
Darwin/lib/python3.4/site-packages/pip/_vendor/distlib/locators.py
Normal file
File diff suppressed because it is too large
Load diff
|
|
@ -0,0 +1,364 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Copyright (C) 2012-2013 Python Software Foundation.
|
||||
# See LICENSE.txt and CONTRIBUTORS.txt.
|
||||
#
|
||||
"""
|
||||
Class representing the list of files in a distribution.
|
||||
|
||||
Equivalent to distutils.filelist, but fixes some problems.
|
||||
"""
|
||||
import fnmatch
|
||||
import logging
|
||||
import os
|
||||
import re
|
||||
|
||||
from . import DistlibException
|
||||
from .compat import fsdecode
|
||||
from .util import convert_path
|
||||
|
||||
|
||||
__all__ = ['Manifest']
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
# a \ followed by some spaces + EOL
|
||||
_COLLAPSE_PATTERN = re.compile('\\\w*\n', re.M)
|
||||
_COMMENTED_LINE = re.compile('#.*?(?=\n)|\n(?=$)', re.M | re.S)
|
||||
|
||||
|
||||
class Manifest(object):
|
||||
"""A list of files built by on exploring the filesystem and filtered by
|
||||
applying various patterns to what we find there.
|
||||
"""
|
||||
|
||||
def __init__(self, base=None):
|
||||
"""
|
||||
Initialise an instance.
|
||||
|
||||
:param base: The base directory to explore under.
|
||||
"""
|
||||
self.base = os.path.abspath(os.path.normpath(base or os.getcwd()))
|
||||
self.prefix = self.base + os.sep
|
||||
self.allfiles = None
|
||||
self.files = set()
|
||||
|
||||
#
|
||||
# Public API
|
||||
#
|
||||
|
||||
def findall(self):
|
||||
"""Find all files under the base and set ``allfiles`` to the absolute
|
||||
pathnames of files found.
|
||||
"""
|
||||
from stat import S_ISREG, S_ISDIR, S_ISLNK
|
||||
|
||||
self.allfiles = allfiles = []
|
||||
root = self.base
|
||||
stack = [root]
|
||||
pop = stack.pop
|
||||
push = stack.append
|
||||
|
||||
while stack:
|
||||
root = pop()
|
||||
names = os.listdir(root)
|
||||
|
||||
for name in names:
|
||||
fullname = os.path.join(root, name)
|
||||
|
||||
# Avoid excess stat calls -- just one will do, thank you!
|
||||
stat = os.stat(fullname)
|
||||
mode = stat.st_mode
|
||||
if S_ISREG(mode):
|
||||
allfiles.append(fsdecode(fullname))
|
||||
elif S_ISDIR(mode) and not S_ISLNK(mode):
|
||||
push(fullname)
|
||||
|
||||
def add(self, item):
|
||||
"""
|
||||
Add a file to the manifest.
|
||||
|
||||
:param item: The pathname to add. This can be relative to the base.
|
||||
"""
|
||||
if not item.startswith(self.prefix):
|
||||
item = os.path.join(self.base, item)
|
||||
self.files.add(os.path.normpath(item))
|
||||
|
||||
def add_many(self, items):
|
||||
"""
|
||||
Add a list of files to the manifest.
|
||||
|
||||
:param items: The pathnames to add. These can be relative to the base.
|
||||
"""
|
||||
for item in items:
|
||||
self.add(item)
|
||||
|
||||
def sorted(self, wantdirs=False):
|
||||
"""
|
||||
Return sorted files in directory order
|
||||
"""
|
||||
|
||||
def add_dir(dirs, d):
|
||||
dirs.add(d)
|
||||
logger.debug('add_dir added %s', d)
|
||||
if d != self.base:
|
||||
parent, _ = os.path.split(d)
|
||||
assert parent not in ('', '/')
|
||||
add_dir(dirs, parent)
|
||||
|
||||
result = set(self.files) # make a copy!
|
||||
if wantdirs:
|
||||
dirs = set()
|
||||
for f in result:
|
||||
add_dir(dirs, os.path.dirname(f))
|
||||
result |= dirs
|
||||
return [os.path.join(*path_tuple) for path_tuple in
|
||||
sorted(os.path.split(path) for path in result)]
|
||||
|
||||
def clear(self):
|
||||
"""Clear all collected files."""
|
||||
self.files = set()
|
||||
self.allfiles = []
|
||||
|
||||
def process_directive(self, directive):
|
||||
"""
|
||||
Process a directive which either adds some files from ``allfiles`` to
|
||||
``files``, or removes some files from ``files``.
|
||||
|
||||
:param directive: The directive to process. This should be in a format
|
||||
compatible with distutils ``MANIFEST.in`` files:
|
||||
|
||||
http://docs.python.org/distutils/sourcedist.html#commands
|
||||
"""
|
||||
# Parse the line: split it up, make sure the right number of words
|
||||
# is there, and return the relevant words. 'action' is always
|
||||
# defined: it's the first word of the line. Which of the other
|
||||
# three are defined depends on the action; it'll be either
|
||||
# patterns, (dir and patterns), or (dirpattern).
|
||||
action, patterns, thedir, dirpattern = self._parse_directive(directive)
|
||||
|
||||
# OK, now we know that the action is valid and we have the
|
||||
# right number of words on the line for that action -- so we
|
||||
# can proceed with minimal error-checking.
|
||||
if action == 'include':
|
||||
for pattern in patterns:
|
||||
if not self._include_pattern(pattern, anchor=True):
|
||||
logger.warning('no files found matching %r', pattern)
|
||||
|
||||
elif action == 'exclude':
|
||||
for pattern in patterns:
|
||||
if not self._exclude_pattern(pattern, anchor=True):
|
||||
logger.warning('no previously-included files '
|
||||
'found matching %r', pattern)
|
||||
|
||||
elif action == 'global-include':
|
||||
for pattern in patterns:
|
||||
if not self._include_pattern(pattern, anchor=False):
|
||||
logger.warning('no files found matching %r '
|
||||
'anywhere in distribution', pattern)
|
||||
|
||||
elif action == 'global-exclude':
|
||||
for pattern in patterns:
|
||||
if not self._exclude_pattern(pattern, anchor=False):
|
||||
logger.warning('no previously-included files '
|
||||
'matching %r found anywhere in '
|
||||
'distribution', pattern)
|
||||
|
||||
elif action == 'recursive-include':
|
||||
for pattern in patterns:
|
||||
if not self._include_pattern(pattern, prefix=thedir):
|
||||
logger.warning('no files found matching %r '
|
||||
'under directory %r', pattern, thedir)
|
||||
|
||||
elif action == 'recursive-exclude':
|
||||
for pattern in patterns:
|
||||
if not self._exclude_pattern(pattern, prefix=thedir):
|
||||
logger.warning('no previously-included files '
|
||||
'matching %r found under directory %r',
|
||||
pattern, thedir)
|
||||
|
||||
elif action == 'graft':
|
||||
if not self._include_pattern(None, prefix=dirpattern):
|
||||
logger.warning('no directories found matching %r',
|
||||
dirpattern)
|
||||
|
||||
elif action == 'prune':
|
||||
if not self._exclude_pattern(None, prefix=dirpattern):
|
||||
logger.warning('no previously-included directories found '
|
||||
'matching %r', dirpattern)
|
||||
else: # pragma: no cover
|
||||
# This should never happen, as it should be caught in
|
||||
# _parse_template_line
|
||||
raise DistlibException(
|
||||
'invalid action %r' % action)
|
||||
|
||||
#
|
||||
# Private API
|
||||
#
|
||||
|
||||
def _parse_directive(self, directive):
|
||||
"""
|
||||
Validate a directive.
|
||||
:param directive: The directive to validate.
|
||||
:return: A tuple of action, patterns, thedir, dir_patterns
|
||||
"""
|
||||
words = directive.split()
|
||||
if len(words) == 1 and words[0] not in ('include', 'exclude',
|
||||
'global-include',
|
||||
'global-exclude',
|
||||
'recursive-include',
|
||||
'recursive-exclude',
|
||||
'graft', 'prune'):
|
||||
# no action given, let's use the default 'include'
|
||||
words.insert(0, 'include')
|
||||
|
||||
action = words[0]
|
||||
patterns = thedir = dir_pattern = None
|
||||
|
||||
if action in ('include', 'exclude',
|
||||
'global-include', 'global-exclude'):
|
||||
if len(words) < 2:
|
||||
raise DistlibException(
|
||||
'%r expects <pattern1> <pattern2> ...' % action)
|
||||
|
||||
patterns = [convert_path(word) for word in words[1:]]
|
||||
|
||||
elif action in ('recursive-include', 'recursive-exclude'):
|
||||
if len(words) < 3:
|
||||
raise DistlibException(
|
||||
'%r expects <dir> <pattern1> <pattern2> ...' % action)
|
||||
|
||||
thedir = convert_path(words[1])
|
||||
patterns = [convert_path(word) for word in words[2:]]
|
||||
|
||||
elif action in ('graft', 'prune'):
|
||||
if len(words) != 2:
|
||||
raise DistlibException(
|
||||
'%r expects a single <dir_pattern>' % action)
|
||||
|
||||
dir_pattern = convert_path(words[1])
|
||||
|
||||
else:
|
||||
raise DistlibException('unknown action %r' % action)
|
||||
|
||||
return action, patterns, thedir, dir_pattern
|
||||
|
||||
def _include_pattern(self, pattern, anchor=True, prefix=None,
|
||||
is_regex=False):
|
||||
"""Select strings (presumably filenames) from 'self.files' that
|
||||
match 'pattern', a Unix-style wildcard (glob) pattern.
|
||||
|
||||
Patterns are not quite the same as implemented by the 'fnmatch'
|
||||
module: '*' and '?' match non-special characters, where "special"
|
||||
is platform-dependent: slash on Unix; colon, slash, and backslash on
|
||||
DOS/Windows; and colon on Mac OS.
|
||||
|
||||
If 'anchor' is true (the default), then the pattern match is more
|
||||
stringent: "*.py" will match "foo.py" but not "foo/bar.py". If
|
||||
'anchor' is false, both of these will match.
|
||||
|
||||
If 'prefix' is supplied, then only filenames starting with 'prefix'
|
||||
(itself a pattern) and ending with 'pattern', with anything in between
|
||||
them, will match. 'anchor' is ignored in this case.
|
||||
|
||||
If 'is_regex' is true, 'anchor' and 'prefix' are ignored, and
|
||||
'pattern' is assumed to be either a string containing a regex or a
|
||||
regex object -- no translation is done, the regex is just compiled
|
||||
and used as-is.
|
||||
|
||||
Selected strings will be added to self.files.
|
||||
|
||||
Return True if files are found.
|
||||
"""
|
||||
# XXX docstring lying about what the special chars are?
|
||||
found = False
|
||||
pattern_re = self._translate_pattern(pattern, anchor, prefix, is_regex)
|
||||
|
||||
# delayed loading of allfiles list
|
||||
if self.allfiles is None:
|
||||
self.findall()
|
||||
|
||||
for name in self.allfiles:
|
||||
if pattern_re.search(name):
|
||||
self.files.add(name)
|
||||
found = True
|
||||
return found
|
||||
|
||||
def _exclude_pattern(self, pattern, anchor=True, prefix=None,
|
||||
is_regex=False):
|
||||
"""Remove strings (presumably filenames) from 'files' that match
|
||||
'pattern'.
|
||||
|
||||
Other parameters are the same as for 'include_pattern()', above.
|
||||
The list 'self.files' is modified in place. Return True if files are
|
||||
found.
|
||||
|
||||
This API is public to allow e.g. exclusion of SCM subdirs, e.g. when
|
||||
packaging source distributions
|
||||
"""
|
||||
found = False
|
||||
pattern_re = self._translate_pattern(pattern, anchor, prefix, is_regex)
|
||||
for f in list(self.files):
|
||||
if pattern_re.search(f):
|
||||
self.files.remove(f)
|
||||
found = True
|
||||
return found
|
||||
|
||||
def _translate_pattern(self, pattern, anchor=True, prefix=None,
|
||||
is_regex=False):
|
||||
"""Translate a shell-like wildcard pattern to a compiled regular
|
||||
expression.
|
||||
|
||||
Return the compiled regex. If 'is_regex' true,
|
||||
then 'pattern' is directly compiled to a regex (if it's a string)
|
||||
or just returned as-is (assumes it's a regex object).
|
||||
"""
|
||||
if is_regex:
|
||||
if isinstance(pattern, str):
|
||||
return re.compile(pattern)
|
||||
else:
|
||||
return pattern
|
||||
|
||||
if pattern:
|
||||
pattern_re = self._glob_to_re(pattern)
|
||||
else:
|
||||
pattern_re = ''
|
||||
|
||||
base = re.escape(os.path.join(self.base, ''))
|
||||
if prefix is not None:
|
||||
# ditch end of pattern character
|
||||
empty_pattern = self._glob_to_re('')
|
||||
prefix_re = self._glob_to_re(prefix)[:-len(empty_pattern)]
|
||||
sep = os.sep
|
||||
if os.sep == '\\':
|
||||
sep = r'\\'
|
||||
pattern_re = '^' + base + sep.join((prefix_re,
|
||||
'.*' + pattern_re))
|
||||
else: # no prefix -- respect anchor flag
|
||||
if anchor:
|
||||
pattern_re = '^' + base + pattern_re
|
||||
|
||||
return re.compile(pattern_re)
|
||||
|
||||
def _glob_to_re(self, pattern):
|
||||
"""Translate a shell-like glob pattern to a regular expression.
|
||||
|
||||
Return a string containing the regex. Differs from
|
||||
'fnmatch.translate()' in that '*' does not match "special characters"
|
||||
(which are platform-specific).
|
||||
"""
|
||||
pattern_re = fnmatch.translate(pattern)
|
||||
|
||||
# '?' and '*' in the glob pattern become '.' and '.*' in the RE, which
|
||||
# IMHO is wrong -- '?' and '*' aren't supposed to match slash in Unix,
|
||||
# and by extension they shouldn't match such "special characters" under
|
||||
# any OS. So change all non-escaped dots in the RE to match any
|
||||
# character except the special characters (currently: just os.sep).
|
||||
sep = os.sep
|
||||
if os.sep == '\\':
|
||||
# we're using a regex to manipulate a regex, so we need
|
||||
# to escape the backslash twice
|
||||
sep = r'\\\\'
|
||||
escaped = r'\1[^%s]' % sep
|
||||
pattern_re = re.sub(r'((?<!\\)(\\\\)*)\.', escaped, pattern_re)
|
||||
return pattern_re
|
||||
|
|
@ -0,0 +1,190 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Copyright (C) 2012-2013 Vinay Sajip.
|
||||
# Licensed to the Python Software Foundation under a contributor agreement.
|
||||
# See LICENSE.txt and CONTRIBUTORS.txt.
|
||||
#
|
||||
"""Parser for the environment markers micro-language defined in PEP 345."""
|
||||
|
||||
import ast
|
||||
import os
|
||||
import sys
|
||||
import platform
|
||||
|
||||
from .compat import python_implementation, string_types
|
||||
from .util import in_venv
|
||||
|
||||
__all__ = ['interpret']
|
||||
|
||||
|
||||
class Evaluator(object):
|
||||
"""
|
||||
A limited evaluator for Python expressions.
|
||||
"""
|
||||
|
||||
operators = {
|
||||
'eq': lambda x, y: x == y,
|
||||
'gt': lambda x, y: x > y,
|
||||
'gte': lambda x, y: x >= y,
|
||||
'in': lambda x, y: x in y,
|
||||
'lt': lambda x, y: x < y,
|
||||
'lte': lambda x, y: x <= y,
|
||||
'not': lambda x: not x,
|
||||
'noteq': lambda x, y: x != y,
|
||||
'notin': lambda x, y: x not in y,
|
||||
}
|
||||
|
||||
allowed_values = {
|
||||
'sys_platform': sys.platform,
|
||||
'python_version': '%s.%s' % sys.version_info[:2],
|
||||
# parsing sys.platform is not reliable, but there is no other
|
||||
# way to get e.g. 2.7.2+, and the PEP is defined with sys.version
|
||||
'python_full_version': sys.version.split(' ', 1)[0],
|
||||
'os_name': os.name,
|
||||
'platform_in_venv': str(in_venv()),
|
||||
'platform_release': platform.release(),
|
||||
'platform_version': platform.version(),
|
||||
'platform_machine': platform.machine(),
|
||||
'platform_python_implementation': python_implementation(),
|
||||
}
|
||||
|
||||
def __init__(self, context=None):
|
||||
"""
|
||||
Initialise an instance.
|
||||
|
||||
:param context: If specified, names are looked up in this mapping.
|
||||
"""
|
||||
self.context = context or {}
|
||||
self.source = None
|
||||
|
||||
def get_fragment(self, offset):
|
||||
"""
|
||||
Get the part of the source which is causing a problem.
|
||||
"""
|
||||
fragment_len = 10
|
||||
s = '%r' % (self.source[offset:offset + fragment_len])
|
||||
if offset + fragment_len < len(self.source):
|
||||
s += '...'
|
||||
return s
|
||||
|
||||
def get_handler(self, node_type):
|
||||
"""
|
||||
Get a handler for the specified AST node type.
|
||||
"""
|
||||
return getattr(self, 'do_%s' % node_type, None)
|
||||
|
||||
def evaluate(self, node, filename=None):
|
||||
"""
|
||||
Evaluate a source string or node, using ``filename`` when
|
||||
displaying errors.
|
||||
"""
|
||||
if isinstance(node, string_types):
|
||||
self.source = node
|
||||
kwargs = {'mode': 'eval'}
|
||||
if filename:
|
||||
kwargs['filename'] = filename
|
||||
try:
|
||||
node = ast.parse(node, **kwargs)
|
||||
except SyntaxError as e:
|
||||
s = self.get_fragment(e.offset)
|
||||
raise SyntaxError('syntax error %s' % s)
|
||||
node_type = node.__class__.__name__.lower()
|
||||
handler = self.get_handler(node_type)
|
||||
if handler is None:
|
||||
if self.source is None:
|
||||
s = '(source not available)'
|
||||
else:
|
||||
s = self.get_fragment(node.col_offset)
|
||||
raise SyntaxError("don't know how to evaluate %r %s" % (
|
||||
node_type, s))
|
||||
return handler(node)
|
||||
|
||||
def get_attr_key(self, node):
|
||||
assert isinstance(node, ast.Attribute), 'attribute node expected'
|
||||
return '%s.%s' % (node.value.id, node.attr)
|
||||
|
||||
def do_attribute(self, node):
|
||||
if not isinstance(node.value, ast.Name):
|
||||
valid = False
|
||||
else:
|
||||
key = self.get_attr_key(node)
|
||||
valid = key in self.context or key in self.allowed_values
|
||||
if not valid:
|
||||
raise SyntaxError('invalid expression: %s' % key)
|
||||
if key in self.context:
|
||||
result = self.context[key]
|
||||
else:
|
||||
result = self.allowed_values[key]
|
||||
return result
|
||||
|
||||
def do_boolop(self, node):
|
||||
result = self.evaluate(node.values[0])
|
||||
is_or = node.op.__class__ is ast.Or
|
||||
is_and = node.op.__class__ is ast.And
|
||||
assert is_or or is_and
|
||||
if (is_and and result) or (is_or and not result):
|
||||
for n in node.values[1:]:
|
||||
result = self.evaluate(n)
|
||||
if (is_or and result) or (is_and and not result):
|
||||
break
|
||||
return result
|
||||
|
||||
def do_compare(self, node):
|
||||
def sanity_check(lhsnode, rhsnode):
|
||||
valid = True
|
||||
if isinstance(lhsnode, ast.Str) and isinstance(rhsnode, ast.Str):
|
||||
valid = False
|
||||
#elif (isinstance(lhsnode, ast.Attribute)
|
||||
# and isinstance(rhsnode, ast.Attribute)):
|
||||
# klhs = self.get_attr_key(lhsnode)
|
||||
# krhs = self.get_attr_key(rhsnode)
|
||||
# valid = klhs != krhs
|
||||
if not valid:
|
||||
s = self.get_fragment(node.col_offset)
|
||||
raise SyntaxError('Invalid comparison: %s' % s)
|
||||
|
||||
lhsnode = node.left
|
||||
lhs = self.evaluate(lhsnode)
|
||||
result = True
|
||||
for op, rhsnode in zip(node.ops, node.comparators):
|
||||
sanity_check(lhsnode, rhsnode)
|
||||
op = op.__class__.__name__.lower()
|
||||
if op not in self.operators:
|
||||
raise SyntaxError('unsupported operation: %r' % op)
|
||||
rhs = self.evaluate(rhsnode)
|
||||
result = self.operators[op](lhs, rhs)
|
||||
if not result:
|
||||
break
|
||||
lhs = rhs
|
||||
lhsnode = rhsnode
|
||||
return result
|
||||
|
||||
def do_expression(self, node):
|
||||
return self.evaluate(node.body)
|
||||
|
||||
def do_name(self, node):
|
||||
valid = False
|
||||
if node.id in self.context:
|
||||
valid = True
|
||||
result = self.context[node.id]
|
||||
elif node.id in self.allowed_values:
|
||||
valid = True
|
||||
result = self.allowed_values[node.id]
|
||||
if not valid:
|
||||
raise SyntaxError('invalid expression: %s' % node.id)
|
||||
return result
|
||||
|
||||
def do_str(self, node):
|
||||
return node.s
|
||||
|
||||
|
||||
def interpret(marker, execution_context=None):
|
||||
"""
|
||||
Interpret a marker and return a result depending on environment.
|
||||
|
||||
:param marker: The marker to interpret.
|
||||
:type marker: str
|
||||
:param execution_context: The context used for name lookup.
|
||||
:type execution_context: mapping
|
||||
"""
|
||||
return Evaluator(execution_context).evaluate(marker.strip())
|
||||
1026
Darwin/lib/python3.4/site-packages/pip/_vendor/distlib/metadata.py
Normal file
1026
Darwin/lib/python3.4/site-packages/pip/_vendor/distlib/metadata.py
Normal file
File diff suppressed because it is too large
Load diff
|
|
@ -0,0 +1,317 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Copyright (C) 2013 Vinay Sajip.
|
||||
# Licensed to the Python Software Foundation under a contributor agreement.
|
||||
# See LICENSE.txt and CONTRIBUTORS.txt.
|
||||
#
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import bisect
|
||||
import io
|
||||
import logging
|
||||
import os
|
||||
import pkgutil
|
||||
import shutil
|
||||
import sys
|
||||
import types
|
||||
import zipimport
|
||||
|
||||
from . import DistlibException
|
||||
from .util import cached_property, get_cache_base, path_to_cache_dir, Cache
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
cache = None # created when needed
|
||||
|
||||
|
||||
class ResourceCache(Cache):
|
||||
def __init__(self, base=None):
|
||||
if base is None:
|
||||
# Use native string to avoid issues on 2.x: see Python #20140.
|
||||
base = os.path.join(get_cache_base(), str('resource-cache'))
|
||||
super(ResourceCache, self).__init__(base)
|
||||
|
||||
def is_stale(self, resource, path):
|
||||
"""
|
||||
Is the cache stale for the given resource?
|
||||
|
||||
:param resource: The :class:`Resource` being cached.
|
||||
:param path: The path of the resource in the cache.
|
||||
:return: True if the cache is stale.
|
||||
"""
|
||||
# Cache invalidation is a hard problem :-)
|
||||
return True
|
||||
|
||||
def get(self, resource):
|
||||
"""
|
||||
Get a resource into the cache,
|
||||
|
||||
:param resource: A :class:`Resource` instance.
|
||||
:return: The pathname of the resource in the cache.
|
||||
"""
|
||||
prefix, path = resource.finder.get_cache_info(resource)
|
||||
if prefix is None:
|
||||
result = path
|
||||
else:
|
||||
result = os.path.join(self.base, self.prefix_to_dir(prefix), path)
|
||||
dirname = os.path.dirname(result)
|
||||
if not os.path.isdir(dirname):
|
||||
os.makedirs(dirname)
|
||||
if not os.path.exists(result):
|
||||
stale = True
|
||||
else:
|
||||
stale = self.is_stale(resource, path)
|
||||
if stale:
|
||||
# write the bytes of the resource to the cache location
|
||||
with open(result, 'wb') as f:
|
||||
f.write(resource.bytes)
|
||||
return result
|
||||
|
||||
|
||||
class ResourceBase(object):
|
||||
def __init__(self, finder, name):
|
||||
self.finder = finder
|
||||
self.name = name
|
||||
|
||||
|
||||
class Resource(ResourceBase):
|
||||
"""
|
||||
A class representing an in-package resource, such as a data file. This is
|
||||
not normally instantiated by user code, but rather by a
|
||||
:class:`ResourceFinder` which manages the resource.
|
||||
"""
|
||||
is_container = False # Backwards compatibility
|
||||
|
||||
def as_stream(self):
|
||||
"""
|
||||
Get the resource as a stream.
|
||||
|
||||
This is not a property to make it obvious that it returns a new stream
|
||||
each time.
|
||||
"""
|
||||
return self.finder.get_stream(self)
|
||||
|
||||
@cached_property
|
||||
def file_path(self):
|
||||
global cache
|
||||
if cache is None:
|
||||
cache = ResourceCache()
|
||||
return cache.get(self)
|
||||
|
||||
@cached_property
|
||||
def bytes(self):
|
||||
return self.finder.get_bytes(self)
|
||||
|
||||
@cached_property
|
||||
def size(self):
|
||||
return self.finder.get_size(self)
|
||||
|
||||
|
||||
class ResourceContainer(ResourceBase):
|
||||
is_container = True # Backwards compatibility
|
||||
|
||||
@cached_property
|
||||
def resources(self):
|
||||
return self.finder.get_resources(self)
|
||||
|
||||
|
||||
class ResourceFinder(object):
|
||||
"""
|
||||
Resource finder for file system resources.
|
||||
"""
|
||||
def __init__(self, module):
|
||||
self.module = module
|
||||
self.loader = getattr(module, '__loader__', None)
|
||||
self.base = os.path.dirname(getattr(module, '__file__', ''))
|
||||
|
||||
def _adjust_path(self, path):
|
||||
return os.path.realpath(path)
|
||||
|
||||
def _make_path(self, resource_name):
|
||||
parts = resource_name.split('/')
|
||||
parts.insert(0, self.base)
|
||||
result = os.path.join(*parts)
|
||||
return self._adjust_path(result)
|
||||
|
||||
def _find(self, path):
|
||||
return os.path.exists(path)
|
||||
|
||||
def get_cache_info(self, resource):
|
||||
return None, resource.path
|
||||
|
||||
def find(self, resource_name):
|
||||
path = self._make_path(resource_name)
|
||||
if not self._find(path):
|
||||
result = None
|
||||
else:
|
||||
if self._is_directory(path):
|
||||
result = ResourceContainer(self, resource_name)
|
||||
else:
|
||||
result = Resource(self, resource_name)
|
||||
result.path = path
|
||||
return result
|
||||
|
||||
def get_stream(self, resource):
|
||||
return open(resource.path, 'rb')
|
||||
|
||||
def get_bytes(self, resource):
|
||||
with open(resource.path, 'rb') as f:
|
||||
return f.read()
|
||||
|
||||
def get_size(self, resource):
|
||||
return os.path.getsize(resource.path)
|
||||
|
||||
def get_resources(self, resource):
|
||||
def allowed(f):
|
||||
return f != '__pycache__' and not f.endswith(('.pyc', '.pyo'))
|
||||
return set([f for f in os.listdir(resource.path) if allowed(f)])
|
||||
|
||||
def is_container(self, resource):
|
||||
return self._is_directory(resource.path)
|
||||
|
||||
_is_directory = staticmethod(os.path.isdir)
|
||||
|
||||
|
||||
class ZipResourceFinder(ResourceFinder):
|
||||
"""
|
||||
Resource finder for resources in .zip files.
|
||||
"""
|
||||
def __init__(self, module):
|
||||
super(ZipResourceFinder, self).__init__(module)
|
||||
archive = self.loader.archive
|
||||
self.prefix_len = 1 + len(archive)
|
||||
# PyPy doesn't have a _files attr on zipimporter, and you can't set one
|
||||
if hasattr(self.loader, '_files'):
|
||||
self._files = self.loader._files
|
||||
else:
|
||||
self._files = zipimport._zip_directory_cache[archive]
|
||||
self.index = sorted(self._files)
|
||||
|
||||
def _adjust_path(self, path):
|
||||
return path
|
||||
|
||||
def _find(self, path):
|
||||
path = path[self.prefix_len:]
|
||||
if path in self._files:
|
||||
result = True
|
||||
else:
|
||||
if path and path[-1] != os.sep:
|
||||
path = path + os.sep
|
||||
i = bisect.bisect(self.index, path)
|
||||
try:
|
||||
result = self.index[i].startswith(path)
|
||||
except IndexError:
|
||||
result = False
|
||||
if not result:
|
||||
logger.debug('_find failed: %r %r', path, self.loader.prefix)
|
||||
else:
|
||||
logger.debug('_find worked: %r %r', path, self.loader.prefix)
|
||||
return result
|
||||
|
||||
def get_cache_info(self, resource):
|
||||
prefix = self.loader.archive
|
||||
path = resource.path[1 + len(prefix):]
|
||||
return prefix, path
|
||||
|
||||
def get_bytes(self, resource):
|
||||
return self.loader.get_data(resource.path)
|
||||
|
||||
def get_stream(self, resource):
|
||||
return io.BytesIO(self.get_bytes(resource))
|
||||
|
||||
def get_size(self, resource):
|
||||
path = resource.path[self.prefix_len:]
|
||||
return self._files[path][3]
|
||||
|
||||
def get_resources(self, resource):
|
||||
path = resource.path[self.prefix_len:]
|
||||
if path and path[-1] != os.sep:
|
||||
path += os.sep
|
||||
plen = len(path)
|
||||
result = set()
|
||||
i = bisect.bisect(self.index, path)
|
||||
while i < len(self.index):
|
||||
if not self.index[i].startswith(path):
|
||||
break
|
||||
s = self.index[i][plen:]
|
||||
result.add(s.split(os.sep, 1)[0]) # only immediate children
|
||||
i += 1
|
||||
return result
|
||||
|
||||
def _is_directory(self, path):
|
||||
path = path[self.prefix_len:]
|
||||
if path and path[-1] != os.sep:
|
||||
path += os.sep
|
||||
i = bisect.bisect(self.index, path)
|
||||
try:
|
||||
result = self.index[i].startswith(path)
|
||||
except IndexError:
|
||||
result = False
|
||||
return result
|
||||
|
||||
_finder_registry = {
|
||||
type(None): ResourceFinder,
|
||||
zipimport.zipimporter: ZipResourceFinder
|
||||
}
|
||||
|
||||
try:
|
||||
import _frozen_importlib
|
||||
_finder_registry[_frozen_importlib.SourceFileLoader] = ResourceFinder
|
||||
_finder_registry[_frozen_importlib.FileFinder] = ResourceFinder
|
||||
except (ImportError, AttributeError):
|
||||
pass
|
||||
|
||||
|
||||
def register_finder(loader, finder_maker):
|
||||
_finder_registry[type(loader)] = finder_maker
|
||||
|
||||
_finder_cache = {}
|
||||
|
||||
|
||||
def finder(package):
|
||||
"""
|
||||
Return a resource finder for a package.
|
||||
:param package: The name of the package.
|
||||
:return: A :class:`ResourceFinder` instance for the package.
|
||||
"""
|
||||
if package in _finder_cache:
|
||||
result = _finder_cache[package]
|
||||
else:
|
||||
if package not in sys.modules:
|
||||
__import__(package)
|
||||
module = sys.modules[package]
|
||||
path = getattr(module, '__path__', None)
|
||||
if path is None:
|
||||
raise DistlibException('You cannot get a finder for a module, '
|
||||
'only for a package')
|
||||
loader = getattr(module, '__loader__', None)
|
||||
finder_maker = _finder_registry.get(type(loader))
|
||||
if finder_maker is None:
|
||||
raise DistlibException('Unable to locate finder for %r' % package)
|
||||
result = finder_maker(module)
|
||||
_finder_cache[package] = result
|
||||
return result
|
||||
|
||||
|
||||
_dummy_module = types.ModuleType(str('__dummy__'))
|
||||
|
||||
|
||||
def finder_for_path(path):
|
||||
"""
|
||||
Return a resource finder for a path, which should represent a container.
|
||||
|
||||
:param path: The path.
|
||||
:return: A :class:`ResourceFinder` instance for the path.
|
||||
"""
|
||||
result = None
|
||||
# calls any path hooks, gets importer into cache
|
||||
pkgutil.get_importer(path)
|
||||
loader = sys.path_importer_cache.get(path)
|
||||
finder = _finder_registry.get(type(loader))
|
||||
if finder:
|
||||
module = _dummy_module
|
||||
module.__file__ = os.path.join(path, '')
|
||||
module.__loader__ = loader
|
||||
result = finder(module)
|
||||
return result
|
||||
|
|
@ -0,0 +1,323 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Copyright (C) 2013 Vinay Sajip.
|
||||
# Licensed to the Python Software Foundation under a contributor agreement.
|
||||
# See LICENSE.txt and CONTRIBUTORS.txt.
|
||||
#
|
||||
from io import BytesIO
|
||||
import logging
|
||||
import os
|
||||
import re
|
||||
import struct
|
||||
import sys
|
||||
|
||||
from .compat import sysconfig, fsencode, detect_encoding, ZipFile
|
||||
from .resources import finder
|
||||
from .util import (FileOperator, get_export_entry, convert_path,
|
||||
get_executable, in_venv)
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
_DEFAULT_MANIFEST = '''
|
||||
<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
|
||||
<assembly xmlns="urn:schemas-microsoft-com:asm.v1" manifestVersion="1.0">
|
||||
<assemblyIdentity version="1.0.0.0"
|
||||
processorArchitecture="X86"
|
||||
name="%s"
|
||||
type="win32"/>
|
||||
|
||||
<!-- Identify the application security requirements. -->
|
||||
<trustInfo xmlns="urn:schemas-microsoft-com:asm.v3">
|
||||
<security>
|
||||
<requestedPrivileges>
|
||||
<requestedExecutionLevel level="asInvoker" uiAccess="false"/>
|
||||
</requestedPrivileges>
|
||||
</security>
|
||||
</trustInfo>
|
||||
</assembly>'''.strip()
|
||||
|
||||
# check if Python is called on the first line with this expression
|
||||
FIRST_LINE_RE = re.compile(b'^#!.*pythonw?[0-9.]*([ \t].*)?$')
|
||||
SCRIPT_TEMPLATE = '''# -*- coding: utf-8 -*-
|
||||
if __name__ == '__main__':
|
||||
import sys, re
|
||||
|
||||
def _resolve(module, func):
|
||||
__import__(module)
|
||||
mod = sys.modules[module]
|
||||
parts = func.split('.')
|
||||
result = getattr(mod, parts.pop(0))
|
||||
for p in parts:
|
||||
result = getattr(result, p)
|
||||
return result
|
||||
|
||||
try:
|
||||
sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
|
||||
|
||||
func = _resolve('%(module)s', '%(func)s')
|
||||
rc = func() # None interpreted as 0
|
||||
except Exception as e: # only supporting Python >= 2.6
|
||||
sys.stderr.write('%%s\\n' %% e)
|
||||
rc = 1
|
||||
sys.exit(rc)
|
||||
'''
|
||||
|
||||
|
||||
class ScriptMaker(object):
|
||||
"""
|
||||
A class to copy or create scripts from source scripts or callable
|
||||
specifications.
|
||||
"""
|
||||
script_template = SCRIPT_TEMPLATE
|
||||
|
||||
executable = None # for shebangs
|
||||
|
||||
def __init__(self, source_dir, target_dir, add_launchers=True,
|
||||
dry_run=False, fileop=None):
|
||||
self.source_dir = source_dir
|
||||
self.target_dir = target_dir
|
||||
self.add_launchers = add_launchers
|
||||
self.force = False
|
||||
self.clobber = False
|
||||
# It only makes sense to set mode bits on POSIX.
|
||||
self.set_mode = (os.name == 'posix')
|
||||
self.variants = set(('', 'X.Y'))
|
||||
self._fileop = fileop or FileOperator(dry_run)
|
||||
|
||||
def _get_alternate_executable(self, executable, options):
|
||||
if options.get('gui', False) and os.name == 'nt':
|
||||
dn, fn = os.path.split(executable)
|
||||
fn = fn.replace('python', 'pythonw')
|
||||
executable = os.path.join(dn, fn)
|
||||
return executable
|
||||
|
||||
def _get_shebang(self, encoding, post_interp=b'', options=None):
|
||||
enquote = True
|
||||
if self.executable:
|
||||
executable = self.executable
|
||||
enquote = False # assume this will be taken care of
|
||||
elif not sysconfig.is_python_build():
|
||||
executable = get_executable()
|
||||
elif in_venv():
|
||||
executable = os.path.join(sysconfig.get_path('scripts'),
|
||||
'python%s' % sysconfig.get_config_var('EXE'))
|
||||
else:
|
||||
executable = os.path.join(
|
||||
sysconfig.get_config_var('BINDIR'),
|
||||
'python%s%s' % (sysconfig.get_config_var('VERSION'),
|
||||
sysconfig.get_config_var('EXE')))
|
||||
if options:
|
||||
executable = self._get_alternate_executable(executable, options)
|
||||
|
||||
# If the user didn't specify an executable, it may be necessary to
|
||||
# cater for executable paths with spaces (not uncommon on Windows)
|
||||
if enquote and ' ' in executable:
|
||||
executable = '"%s"' % executable
|
||||
executable = fsencode(executable)
|
||||
shebang = b'#!' + executable + post_interp + b'\n'
|
||||
# Python parser starts to read a script using UTF-8 until
|
||||
# it gets a #coding:xxx cookie. The shebang has to be the
|
||||
# first line of a file, the #coding:xxx cookie cannot be
|
||||
# written before. So the shebang has to be decodable from
|
||||
# UTF-8.
|
||||
try:
|
||||
shebang.decode('utf-8')
|
||||
except UnicodeDecodeError:
|
||||
raise ValueError(
|
||||
'The shebang (%r) is not decodable from utf-8' % shebang)
|
||||
# If the script is encoded to a custom encoding (use a
|
||||
# #coding:xxx cookie), the shebang has to be decodable from
|
||||
# the script encoding too.
|
||||
if encoding != 'utf-8':
|
||||
try:
|
||||
shebang.decode(encoding)
|
||||
except UnicodeDecodeError:
|
||||
raise ValueError(
|
||||
'The shebang (%r) is not decodable '
|
||||
'from the script encoding (%r)' % (shebang, encoding))
|
||||
return shebang
|
||||
|
||||
def _get_script_text(self, entry):
|
||||
return self.script_template % dict(module=entry.prefix,
|
||||
func=entry.suffix)
|
||||
|
||||
manifest = _DEFAULT_MANIFEST
|
||||
|
||||
def get_manifest(self, exename):
|
||||
base = os.path.basename(exename)
|
||||
return self.manifest % base
|
||||
|
||||
def _write_script(self, names, shebang, script_bytes, filenames, ext):
|
||||
use_launcher = self.add_launchers and os.name == 'nt'
|
||||
linesep = os.linesep.encode('utf-8')
|
||||
if not use_launcher:
|
||||
script_bytes = shebang + linesep + script_bytes
|
||||
else:
|
||||
if ext == 'py':
|
||||
launcher = self._get_launcher('t')
|
||||
else:
|
||||
launcher = self._get_launcher('w')
|
||||
stream = BytesIO()
|
||||
with ZipFile(stream, 'w') as zf:
|
||||
zf.writestr('__main__.py', script_bytes)
|
||||
zip_data = stream.getvalue()
|
||||
script_bytes = launcher + shebang + linesep + zip_data
|
||||
for name in names:
|
||||
outname = os.path.join(self.target_dir, name)
|
||||
if use_launcher:
|
||||
n, e = os.path.splitext(outname)
|
||||
if e.startswith('.py'):
|
||||
outname = n
|
||||
outname = '%s.exe' % outname
|
||||
try:
|
||||
self._fileop.write_binary_file(outname, script_bytes)
|
||||
except Exception:
|
||||
# Failed writing an executable - it might be in use.
|
||||
logger.warning('Failed to write executable - trying to '
|
||||
'use .deleteme logic')
|
||||
dfname = '%s.deleteme' % outname
|
||||
if os.path.exists(dfname):
|
||||
os.remove(dfname) # Not allowed to fail here
|
||||
os.rename(outname, dfname) # nor here
|
||||
self._fileop.write_binary_file(outname, script_bytes)
|
||||
logger.debug('Able to replace executable using '
|
||||
'.deleteme logic')
|
||||
try:
|
||||
os.remove(dfname)
|
||||
except Exception:
|
||||
pass # still in use - ignore error
|
||||
else:
|
||||
if os.name == 'nt' and not outname.endswith('.' + ext):
|
||||
outname = '%s.%s' % (outname, ext)
|
||||
if os.path.exists(outname) and not self.clobber:
|
||||
logger.warning('Skipping existing file %s', outname)
|
||||
continue
|
||||
self._fileop.write_binary_file(outname, script_bytes)
|
||||
if self.set_mode:
|
||||
self._fileop.set_executable_mode([outname])
|
||||
filenames.append(outname)
|
||||
|
||||
def _make_script(self, entry, filenames, options=None):
|
||||
shebang = self._get_shebang('utf-8', options=options)
|
||||
script = self._get_script_text(entry).encode('utf-8')
|
||||
name = entry.name
|
||||
scriptnames = set()
|
||||
if '' in self.variants:
|
||||
scriptnames.add(name)
|
||||
if 'X' in self.variants:
|
||||
scriptnames.add('%s%s' % (name, sys.version[0]))
|
||||
if 'X.Y' in self.variants:
|
||||
scriptnames.add('%s-%s' % (name, sys.version[:3]))
|
||||
if options and options.get('gui', False):
|
||||
ext = 'pyw'
|
||||
else:
|
||||
ext = 'py'
|
||||
self._write_script(scriptnames, shebang, script, filenames, ext)
|
||||
|
||||
def _copy_script(self, script, filenames):
|
||||
adjust = False
|
||||
script = os.path.join(self.source_dir, convert_path(script))
|
||||
outname = os.path.join(self.target_dir, os.path.basename(script))
|
||||
if not self.force and not self._fileop.newer(script, outname):
|
||||
logger.debug('not copying %s (up-to-date)', script)
|
||||
return
|
||||
|
||||
# Always open the file, but ignore failures in dry-run mode --
|
||||
# that way, we'll get accurate feedback if we can read the
|
||||
# script.
|
||||
try:
|
||||
f = open(script, 'rb')
|
||||
except IOError:
|
||||
if not self.dry_run:
|
||||
raise
|
||||
f = None
|
||||
else:
|
||||
encoding, lines = detect_encoding(f.readline)
|
||||
f.seek(0)
|
||||
first_line = f.readline()
|
||||
if not first_line:
|
||||
logger.warning('%s: %s is an empty file (skipping)',
|
||||
self.get_command_name(), script)
|
||||
return
|
||||
|
||||
match = FIRST_LINE_RE.match(first_line.replace(b'\r\n', b'\n'))
|
||||
if match:
|
||||
adjust = True
|
||||
post_interp = match.group(1) or b''
|
||||
|
||||
if not adjust:
|
||||
if f:
|
||||
f.close()
|
||||
self._fileop.copy_file(script, outname)
|
||||
if self.set_mode:
|
||||
self._fileop.set_executable_mode([outname])
|
||||
filenames.append(outname)
|
||||
else:
|
||||
logger.info('copying and adjusting %s -> %s', script,
|
||||
self.target_dir)
|
||||
if not self._fileop.dry_run:
|
||||
shebang = self._get_shebang(encoding, post_interp)
|
||||
if b'pythonw' in first_line:
|
||||
ext = 'pyw'
|
||||
else:
|
||||
ext = 'py'
|
||||
n = os.path.basename(outname)
|
||||
self._write_script([n], shebang, f.read(), filenames, ext)
|
||||
if f:
|
||||
f.close()
|
||||
|
||||
@property
|
||||
def dry_run(self):
|
||||
return self._fileop.dry_run
|
||||
|
||||
@dry_run.setter
|
||||
def dry_run(self, value):
|
||||
self._fileop.dry_run = value
|
||||
|
||||
if os.name == 'nt':
|
||||
# Executable launcher support.
|
||||
# Launchers are from https://bitbucket.org/vinay.sajip/simple_launcher/
|
||||
|
||||
def _get_launcher(self, kind):
|
||||
if struct.calcsize('P') == 8: # 64-bit
|
||||
bits = '64'
|
||||
else:
|
||||
bits = '32'
|
||||
name = '%s%s.exe' % (kind, bits)
|
||||
# Issue 31: don't hardcode an absolute package name, but
|
||||
# determine it relative to the current package
|
||||
distlib_package = __name__.rsplit('.', 1)[0]
|
||||
result = finder(distlib_package).find(name).bytes
|
||||
return result
|
||||
|
||||
# Public API follows
|
||||
|
||||
def make(self, specification, options=None):
|
||||
"""
|
||||
Make a script.
|
||||
|
||||
:param specification: The specification, which is either a valid export
|
||||
entry specification (to make a script from a
|
||||
callable) or a filename (to make a script by
|
||||
copying from a source location).
|
||||
:param options: A dictionary of options controlling script generation.
|
||||
:return: A list of all absolute pathnames written to.
|
||||
"""
|
||||
filenames = []
|
||||
entry = get_export_entry(specification)
|
||||
if entry is None:
|
||||
self._copy_script(specification, filenames)
|
||||
else:
|
||||
self._make_script(entry, filenames, options=options)
|
||||
return filenames
|
||||
|
||||
def make_multiple(self, specifications, options=None):
|
||||
"""
|
||||
Take a list of specifications and make scripts from them,
|
||||
:param specifications: A list of specifications.
|
||||
:return: A list of all absolute pathnames written to,
|
||||
"""
|
||||
filenames = []
|
||||
for specification in specifications:
|
||||
filenames.extend(self.make(specification, options))
|
||||
return filenames
|
||||
BIN
Darwin/lib/python3.4/site-packages/pip/_vendor/distlib/t32.exe
Normal file
BIN
Darwin/lib/python3.4/site-packages/pip/_vendor/distlib/t32.exe
Normal file
Binary file not shown.
BIN
Darwin/lib/python3.4/site-packages/pip/_vendor/distlib/t64.exe
Normal file
BIN
Darwin/lib/python3.4/site-packages/pip/_vendor/distlib/t64.exe
Normal file
Binary file not shown.
1575
Darwin/lib/python3.4/site-packages/pip/_vendor/distlib/util.py
Normal file
1575
Darwin/lib/python3.4/site-packages/pip/_vendor/distlib/util.py
Normal file
File diff suppressed because it is too large
Load diff
|
|
@ -0,0 +1,721 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Copyright (C) 2012-2013 The Python Software Foundation.
|
||||
# See LICENSE.txt and CONTRIBUTORS.txt.
|
||||
#
|
||||
"""
|
||||
Implementation of a flexible versioning scheme providing support for PEP-386,
|
||||
distribute-compatible and semantic versioning.
|
||||
"""
|
||||
|
||||
import logging
|
||||
import re
|
||||
|
||||
from .compat import string_types
|
||||
|
||||
__all__ = ['NormalizedVersion', 'NormalizedMatcher',
|
||||
'LegacyVersion', 'LegacyMatcher',
|
||||
'SemanticVersion', 'SemanticMatcher',
|
||||
'UnsupportedVersionError', 'get_scheme']
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class UnsupportedVersionError(ValueError):
|
||||
"""This is an unsupported version."""
|
||||
pass
|
||||
|
||||
|
||||
class Version(object):
|
||||
def __init__(self, s):
|
||||
self._string = s = s.strip()
|
||||
self._parts = parts = self.parse(s)
|
||||
assert isinstance(parts, tuple)
|
||||
assert len(parts) > 0
|
||||
|
||||
def parse(self, s):
|
||||
raise NotImplementedError('please implement in a subclass')
|
||||
|
||||
def _check_compatible(self, other):
|
||||
if type(self) != type(other):
|
||||
raise TypeError('cannot compare %r and %r' % (self, other))
|
||||
|
||||
def __eq__(self, other):
|
||||
self._check_compatible(other)
|
||||
return self._parts == other._parts
|
||||
|
||||
def __ne__(self, other):
|
||||
return not self.__eq__(other)
|
||||
|
||||
def __lt__(self, other):
|
||||
self._check_compatible(other)
|
||||
return self._parts < other._parts
|
||||
|
||||
def __gt__(self, other):
|
||||
return not (self.__lt__(other) or self.__eq__(other))
|
||||
|
||||
def __le__(self, other):
|
||||
return self.__lt__(other) or self.__eq__(other)
|
||||
|
||||
def __ge__(self, other):
|
||||
return self.__gt__(other) or self.__eq__(other)
|
||||
|
||||
# See http://docs.python.org/reference/datamodel#object.__hash__
|
||||
def __hash__(self):
|
||||
return hash(self._parts)
|
||||
|
||||
def __repr__(self):
|
||||
return "%s('%s')" % (self.__class__.__name__, self._string)
|
||||
|
||||
def __str__(self):
|
||||
return self._string
|
||||
|
||||
@property
|
||||
def is_prerelease(self):
|
||||
raise NotImplementedError('Please implement in subclasses.')
|
||||
|
||||
|
||||
class Matcher(object):
|
||||
version_class = None
|
||||
|
||||
dist_re = re.compile(r"^(\w[\s\w'.-]*)(\((.*)\))?")
|
||||
comp_re = re.compile(r'^(<=|>=|<|>|!=|==|~=)?\s*([^\s,]+)$')
|
||||
num_re = re.compile(r'^\d+(\.\d+)*$')
|
||||
|
||||
# value is either a callable or the name of a method
|
||||
_operators = {
|
||||
'<': lambda v, c, p: v < c,
|
||||
'>': lambda v, c, p: v > c,
|
||||
'<=': lambda v, c, p: v == c or v < c,
|
||||
'>=': lambda v, c, p: v == c or v > c,
|
||||
'==': lambda v, c, p: v == c,
|
||||
# by default, compatible => >=.
|
||||
'~=': lambda v, c, p: v == c or v > c,
|
||||
'!=': lambda v, c, p: v != c,
|
||||
}
|
||||
|
||||
def __init__(self, s):
|
||||
if self.version_class is None:
|
||||
raise ValueError('Please specify a version class')
|
||||
self._string = s = s.strip()
|
||||
m = self.dist_re.match(s)
|
||||
if not m:
|
||||
raise ValueError('Not valid: %r' % s)
|
||||
groups = m.groups('')
|
||||
self.name = groups[0].strip()
|
||||
self.key = self.name.lower() # for case-insensitive comparisons
|
||||
clist = []
|
||||
if groups[2]:
|
||||
constraints = [c.strip() for c in groups[2].split(',')]
|
||||
for c in constraints:
|
||||
m = self.comp_re.match(c)
|
||||
if not m:
|
||||
raise ValueError('Invalid %r in %r' % (c, s))
|
||||
groups = m.groups()
|
||||
op = groups[0] or '~='
|
||||
s = groups[1]
|
||||
if s.endswith('.*'):
|
||||
if op not in ('==', '!='):
|
||||
raise ValueError('\'.*\' not allowed for '
|
||||
'%r constraints' % op)
|
||||
# Could be a partial version (e.g. for '2.*') which
|
||||
# won't parse as a version, so keep it as a string
|
||||
vn, prefix = s[:-2], True
|
||||
if not self.num_re.match(vn):
|
||||
# Just to check that vn is a valid version
|
||||
self.version_class(vn)
|
||||
else:
|
||||
# Should parse as a version, so we can create an
|
||||
# instance for the comparison
|
||||
vn, prefix = self.version_class(s), False
|
||||
clist.append((op, vn, prefix))
|
||||
self._parts = tuple(clist)
|
||||
|
||||
def match(self, version):
|
||||
"""
|
||||
Check if the provided version matches the constraints.
|
||||
|
||||
:param version: The version to match against this instance.
|
||||
:type version: Strring or :class:`Version` instance.
|
||||
"""
|
||||
if isinstance(version, string_types):
|
||||
version = self.version_class(version)
|
||||
for operator, constraint, prefix in self._parts:
|
||||
f = self._operators.get(operator)
|
||||
if isinstance(f, string_types):
|
||||
f = getattr(self, f)
|
||||
if not f:
|
||||
msg = ('%r not implemented '
|
||||
'for %s' % (operator, self.__class__.__name__))
|
||||
raise NotImplementedError(msg)
|
||||
if not f(version, constraint, prefix):
|
||||
return False
|
||||
return True
|
||||
|
||||
@property
|
||||
def exact_version(self):
|
||||
result = None
|
||||
if len(self._parts) == 1 and self._parts[0][0] == '==':
|
||||
result = self._parts[0][1]
|
||||
return result
|
||||
|
||||
def _check_compatible(self, other):
|
||||
if type(self) != type(other) or self.name != other.name:
|
||||
raise TypeError('cannot compare %s and %s' % (self, other))
|
||||
|
||||
def __eq__(self, other):
|
||||
self._check_compatible(other)
|
||||
return self.key == other.key and self._parts == other._parts
|
||||
|
||||
def __ne__(self, other):
|
||||
return not self.__eq__(other)
|
||||
|
||||
# See http://docs.python.org/reference/datamodel#object.__hash__
|
||||
def __hash__(self):
|
||||
return hash(self.key) + hash(self._parts)
|
||||
|
||||
def __repr__(self):
|
||||
return "%s(%r)" % (self.__class__.__name__, self._string)
|
||||
|
||||
def __str__(self):
|
||||
return self._string
|
||||
|
||||
|
||||
PEP426_VERSION_RE = re.compile(r'^(\d+(\.\d+)*)((a|b|c|rc)(\d+))?'
|
||||
r'(\.(post)(\d+))?(\.(dev)(\d+))?'
|
||||
r'(-(\d+(\.\d+)?))?$')
|
||||
|
||||
|
||||
def _pep426_key(s):
|
||||
s = s.strip()
|
||||
m = PEP426_VERSION_RE.match(s)
|
||||
if not m:
|
||||
raise UnsupportedVersionError('Not a valid version: %s' % s)
|
||||
groups = m.groups()
|
||||
nums = tuple(int(v) for v in groups[0].split('.'))
|
||||
while len(nums) > 1 and nums[-1] == 0:
|
||||
nums = nums[:-1]
|
||||
|
||||
pre = groups[3:5]
|
||||
post = groups[6:8]
|
||||
dev = groups[9:11]
|
||||
local = groups[12]
|
||||
if pre == (None, None):
|
||||
pre = ()
|
||||
else:
|
||||
pre = pre[0], int(pre[1])
|
||||
if post == (None, None):
|
||||
post = ()
|
||||
else:
|
||||
post = post[0], int(post[1])
|
||||
if dev == (None, None):
|
||||
dev = ()
|
||||
else:
|
||||
dev = dev[0], int(dev[1])
|
||||
if local is None:
|
||||
local = ()
|
||||
else:
|
||||
local = tuple([int(s) for s in local.split('.')])
|
||||
if not pre:
|
||||
# either before pre-release, or final release and after
|
||||
if not post and dev:
|
||||
# before pre-release
|
||||
pre = ('a', -1) # to sort before a0
|
||||
else:
|
||||
pre = ('z',) # to sort after all pre-releases
|
||||
# now look at the state of post and dev.
|
||||
if not post:
|
||||
post = ('_',) # sort before 'a'
|
||||
if not dev:
|
||||
dev = ('final',)
|
||||
|
||||
#print('%s -> %s' % (s, m.groups()))
|
||||
return nums, pre, post, dev, local
|
||||
|
||||
|
||||
_normalized_key = _pep426_key
|
||||
|
||||
|
||||
class NormalizedVersion(Version):
|
||||
"""A rational version.
|
||||
|
||||
Good:
|
||||
1.2 # equivalent to "1.2.0"
|
||||
1.2.0
|
||||
1.2a1
|
||||
1.2.3a2
|
||||
1.2.3b1
|
||||
1.2.3c1
|
||||
1.2.3.4
|
||||
TODO: fill this out
|
||||
|
||||
Bad:
|
||||
1 # mininum two numbers
|
||||
1.2a # release level must have a release serial
|
||||
1.2.3b
|
||||
"""
|
||||
def parse(self, s):
|
||||
result = _normalized_key(s)
|
||||
# _normalized_key loses trailing zeroes in the release
|
||||
# clause, since that's needed to ensure that X.Y == X.Y.0 == X.Y.0.0
|
||||
# However, PEP 440 prefix matching needs it: for example,
|
||||
# (~= 1.4.5.0) matches differently to (~= 1.4.5.0.0).
|
||||
m = PEP426_VERSION_RE.match(s) # must succeed
|
||||
groups = m.groups()
|
||||
self._release_clause = tuple(int(v) for v in groups[0].split('.'))
|
||||
return result
|
||||
|
||||
PREREL_TAGS = set(['a', 'b', 'c', 'rc', 'dev'])
|
||||
|
||||
@property
|
||||
def is_prerelease(self):
|
||||
return any(t[0] in self.PREREL_TAGS for t in self._parts if t)
|
||||
|
||||
|
||||
def _match_prefix(x, y):
|
||||
x = str(x)
|
||||
y = str(y)
|
||||
if x == y:
|
||||
return True
|
||||
if not x.startswith(y):
|
||||
return False
|
||||
n = len(y)
|
||||
return x[n] == '.'
|
||||
|
||||
|
||||
class NormalizedMatcher(Matcher):
|
||||
version_class = NormalizedVersion
|
||||
|
||||
# value is either a callable or the name of a method
|
||||
_operators = {
|
||||
'~=': '_match_compatible',
|
||||
'<': '_match_lt',
|
||||
'>': '_match_gt',
|
||||
'<=': '_match_le',
|
||||
'>=': '_match_ge',
|
||||
'==': '_match_eq',
|
||||
'!=': '_match_ne',
|
||||
}
|
||||
|
||||
def _adjust_local(self, version, constraint, prefix):
|
||||
if prefix:
|
||||
strip_local = '-' not in constraint and version._parts[-1]
|
||||
else:
|
||||
# both constraint and version are
|
||||
# NormalizedVersion instances.
|
||||
# If constraint does not have a local component,
|
||||
# ensure the version doesn't, either.
|
||||
strip_local = not constraint._parts[-1] and version._parts[-1]
|
||||
if strip_local:
|
||||
s = version._string.split('-', 1)[0]
|
||||
version = self.version_class(s)
|
||||
return version, constraint
|
||||
|
||||
def _match_lt(self, version, constraint, prefix):
|
||||
version, constraint = self._adjust_local(version, constraint, prefix)
|
||||
if version >= constraint:
|
||||
return False
|
||||
release_clause = constraint._release_clause
|
||||
pfx = '.'.join([str(i) for i in release_clause])
|
||||
return not _match_prefix(version, pfx)
|
||||
|
||||
def _match_gt(self, version, constraint, prefix):
|
||||
version, constraint = self._adjust_local(version, constraint, prefix)
|
||||
if version <= constraint:
|
||||
return False
|
||||
release_clause = constraint._release_clause
|
||||
pfx = '.'.join([str(i) for i in release_clause])
|
||||
return not _match_prefix(version, pfx)
|
||||
|
||||
def _match_le(self, version, constraint, prefix):
|
||||
version, constraint = self._adjust_local(version, constraint, prefix)
|
||||
return version <= constraint
|
||||
|
||||
def _match_ge(self, version, constraint, prefix):
|
||||
version, constraint = self._adjust_local(version, constraint, prefix)
|
||||
return version >= constraint
|
||||
|
||||
def _match_eq(self, version, constraint, prefix):
|
||||
version, constraint = self._adjust_local(version, constraint, prefix)
|
||||
if not prefix:
|
||||
result = (version == constraint)
|
||||
else:
|
||||
result = _match_prefix(version, constraint)
|
||||
return result
|
||||
|
||||
def _match_ne(self, version, constraint, prefix):
|
||||
version, constraint = self._adjust_local(version, constraint, prefix)
|
||||
if not prefix:
|
||||
result = (version != constraint)
|
||||
else:
|
||||
result = not _match_prefix(version, constraint)
|
||||
return result
|
||||
|
||||
def _match_compatible(self, version, constraint, prefix):
|
||||
version, constraint = self._adjust_local(version, constraint, prefix)
|
||||
if version == constraint:
|
||||
return True
|
||||
if version < constraint:
|
||||
return False
|
||||
release_clause = constraint._release_clause
|
||||
if len(release_clause) > 1:
|
||||
release_clause = release_clause[:-1]
|
||||
pfx = '.'.join([str(i) for i in release_clause])
|
||||
return _match_prefix(version, pfx)
|
||||
|
||||
_REPLACEMENTS = (
|
||||
(re.compile('[.+-]$'), ''), # remove trailing puncts
|
||||
(re.compile(r'^[.](\d)'), r'0.\1'), # .N -> 0.N at start
|
||||
(re.compile('^[.-]'), ''), # remove leading puncts
|
||||
(re.compile(r'^\((.*)\)$'), r'\1'), # remove parentheses
|
||||
(re.compile(r'^v(ersion)?\s*(\d+)'), r'\2'), # remove leading v(ersion)
|
||||
(re.compile(r'^r(ev)?\s*(\d+)'), r'\2'), # remove leading v(ersion)
|
||||
(re.compile('[.]{2,}'), '.'), # multiple runs of '.'
|
||||
(re.compile(r'\b(alfa|apha)\b'), 'alpha'), # misspelt alpha
|
||||
(re.compile(r'\b(pre-alpha|prealpha)\b'),
|
||||
'pre.alpha'), # standardise
|
||||
(re.compile(r'\(beta\)$'), 'beta'), # remove parentheses
|
||||
)
|
||||
|
||||
_SUFFIX_REPLACEMENTS = (
|
||||
(re.compile('^[:~._+-]+'), ''), # remove leading puncts
|
||||
(re.compile('[,*")([\]]'), ''), # remove unwanted chars
|
||||
(re.compile('[~:+_ -]'), '.'), # replace illegal chars
|
||||
(re.compile('[.]{2,}'), '.'), # multiple runs of '.'
|
||||
(re.compile(r'\.$'), ''), # trailing '.'
|
||||
)
|
||||
|
||||
_NUMERIC_PREFIX = re.compile(r'(\d+(\.\d+)*)')
|
||||
|
||||
|
||||
def _suggest_semantic_version(s):
|
||||
"""
|
||||
Try to suggest a semantic form for a version for which
|
||||
_suggest_normalized_version couldn't come up with anything.
|
||||
"""
|
||||
result = s.strip().lower()
|
||||
for pat, repl in _REPLACEMENTS:
|
||||
result = pat.sub(repl, result)
|
||||
if not result:
|
||||
result = '0.0.0'
|
||||
|
||||
# Now look for numeric prefix, and separate it out from
|
||||
# the rest.
|
||||
#import pdb; pdb.set_trace()
|
||||
m = _NUMERIC_PREFIX.match(result)
|
||||
if not m:
|
||||
prefix = '0.0.0'
|
||||
suffix = result
|
||||
else:
|
||||
prefix = m.groups()[0].split('.')
|
||||
prefix = [int(i) for i in prefix]
|
||||
while len(prefix) < 3:
|
||||
prefix.append(0)
|
||||
if len(prefix) == 3:
|
||||
suffix = result[m.end():]
|
||||
else:
|
||||
suffix = '.'.join([str(i) for i in prefix[3:]]) + result[m.end():]
|
||||
prefix = prefix[:3]
|
||||
prefix = '.'.join([str(i) for i in prefix])
|
||||
suffix = suffix.strip()
|
||||
if suffix:
|
||||
#import pdb; pdb.set_trace()
|
||||
# massage the suffix.
|
||||
for pat, repl in _SUFFIX_REPLACEMENTS:
|
||||
suffix = pat.sub(repl, suffix)
|
||||
|
||||
if not suffix:
|
||||
result = prefix
|
||||
else:
|
||||
sep = '-' if 'dev' in suffix else '+'
|
||||
result = prefix + sep + suffix
|
||||
if not is_semver(result):
|
||||
result = None
|
||||
return result
|
||||
|
||||
|
||||
def _suggest_normalized_version(s):
|
||||
"""Suggest a normalized version close to the given version string.
|
||||
|
||||
If you have a version string that isn't rational (i.e. NormalizedVersion
|
||||
doesn't like it) then you might be able to get an equivalent (or close)
|
||||
rational version from this function.
|
||||
|
||||
This does a number of simple normalizations to the given string, based
|
||||
on observation of versions currently in use on PyPI. Given a dump of
|
||||
those version during PyCon 2009, 4287 of them:
|
||||
- 2312 (53.93%) match NormalizedVersion without change
|
||||
with the automatic suggestion
|
||||
- 3474 (81.04%) match when using this suggestion method
|
||||
|
||||
@param s {str} An irrational version string.
|
||||
@returns A rational version string, or None, if couldn't determine one.
|
||||
"""
|
||||
try:
|
||||
_normalized_key(s)
|
||||
return s # already rational
|
||||
except UnsupportedVersionError:
|
||||
pass
|
||||
|
||||
rs = s.lower()
|
||||
|
||||
# part of this could use maketrans
|
||||
for orig, repl in (('-alpha', 'a'), ('-beta', 'b'), ('alpha', 'a'),
|
||||
('beta', 'b'), ('rc', 'c'), ('-final', ''),
|
||||
('-pre', 'c'),
|
||||
('-release', ''), ('.release', ''), ('-stable', ''),
|
||||
('+', '.'), ('_', '.'), (' ', ''), ('.final', ''),
|
||||
('final', '')):
|
||||
rs = rs.replace(orig, repl)
|
||||
|
||||
# if something ends with dev or pre, we add a 0
|
||||
rs = re.sub(r"pre$", r"pre0", rs)
|
||||
rs = re.sub(r"dev$", r"dev0", rs)
|
||||
|
||||
# if we have something like "b-2" or "a.2" at the end of the
|
||||
# version, that is pobably beta, alpha, etc
|
||||
# let's remove the dash or dot
|
||||
rs = re.sub(r"([abc]|rc)[\-\.](\d+)$", r"\1\2", rs)
|
||||
|
||||
# 1.0-dev-r371 -> 1.0.dev371
|
||||
# 0.1-dev-r79 -> 0.1.dev79
|
||||
rs = re.sub(r"[\-\.](dev)[\-\.]?r?(\d+)$", r".\1\2", rs)
|
||||
|
||||
# Clean: 2.0.a.3, 2.0.b1, 0.9.0~c1
|
||||
rs = re.sub(r"[.~]?([abc])\.?", r"\1", rs)
|
||||
|
||||
# Clean: v0.3, v1.0
|
||||
if rs.startswith('v'):
|
||||
rs = rs[1:]
|
||||
|
||||
# Clean leading '0's on numbers.
|
||||
#TODO: unintended side-effect on, e.g., "2003.05.09"
|
||||
# PyPI stats: 77 (~2%) better
|
||||
rs = re.sub(r"\b0+(\d+)(?!\d)", r"\1", rs)
|
||||
|
||||
# Clean a/b/c with no version. E.g. "1.0a" -> "1.0a0". Setuptools infers
|
||||
# zero.
|
||||
# PyPI stats: 245 (7.56%) better
|
||||
rs = re.sub(r"(\d+[abc])$", r"\g<1>0", rs)
|
||||
|
||||
# the 'dev-rNNN' tag is a dev tag
|
||||
rs = re.sub(r"\.?(dev-r|dev\.r)\.?(\d+)$", r".dev\2", rs)
|
||||
|
||||
# clean the - when used as a pre delimiter
|
||||
rs = re.sub(r"-(a|b|c)(\d+)$", r"\1\2", rs)
|
||||
|
||||
# a terminal "dev" or "devel" can be changed into ".dev0"
|
||||
rs = re.sub(r"[\.\-](dev|devel)$", r".dev0", rs)
|
||||
|
||||
# a terminal "dev" can be changed into ".dev0"
|
||||
rs = re.sub(r"(?![\.\-])dev$", r".dev0", rs)
|
||||
|
||||
# a terminal "final" or "stable" can be removed
|
||||
rs = re.sub(r"(final|stable)$", "", rs)
|
||||
|
||||
# The 'r' and the '-' tags are post release tags
|
||||
# 0.4a1.r10 -> 0.4a1.post10
|
||||
# 0.9.33-17222 -> 0.9.33.post17222
|
||||
# 0.9.33-r17222 -> 0.9.33.post17222
|
||||
rs = re.sub(r"\.?(r|-|-r)\.?(\d+)$", r".post\2", rs)
|
||||
|
||||
# Clean 'r' instead of 'dev' usage:
|
||||
# 0.9.33+r17222 -> 0.9.33.dev17222
|
||||
# 1.0dev123 -> 1.0.dev123
|
||||
# 1.0.git123 -> 1.0.dev123
|
||||
# 1.0.bzr123 -> 1.0.dev123
|
||||
# 0.1a0dev.123 -> 0.1a0.dev123
|
||||
# PyPI stats: ~150 (~4%) better
|
||||
rs = re.sub(r"\.?(dev|git|bzr)\.?(\d+)$", r".dev\2", rs)
|
||||
|
||||
# Clean '.pre' (normalized from '-pre' above) instead of 'c' usage:
|
||||
# 0.2.pre1 -> 0.2c1
|
||||
# 0.2-c1 -> 0.2c1
|
||||
# 1.0preview123 -> 1.0c123
|
||||
# PyPI stats: ~21 (0.62%) better
|
||||
rs = re.sub(r"\.?(pre|preview|-c)(\d+)$", r"c\g<2>", rs)
|
||||
|
||||
# Tcl/Tk uses "px" for their post release markers
|
||||
rs = re.sub(r"p(\d+)$", r".post\1", rs)
|
||||
|
||||
try:
|
||||
_normalized_key(rs)
|
||||
except UnsupportedVersionError:
|
||||
rs = None
|
||||
return rs
|
||||
|
||||
#
|
||||
# Legacy version processing (distribute-compatible)
|
||||
#
|
||||
|
||||
_VERSION_PART = re.compile(r'([a-z]+|\d+|[\.-])', re.I)
|
||||
_VERSION_REPLACE = {
|
||||
'pre': 'c',
|
||||
'preview': 'c',
|
||||
'-': 'final-',
|
||||
'rc': 'c',
|
||||
'dev': '@',
|
||||
'': None,
|
||||
'.': None,
|
||||
}
|
||||
|
||||
|
||||
def _legacy_key(s):
|
||||
def get_parts(s):
|
||||
result = []
|
||||
for p in _VERSION_PART.split(s.lower()):
|
||||
p = _VERSION_REPLACE.get(p, p)
|
||||
if p:
|
||||
if '0' <= p[:1] <= '9':
|
||||
p = p.zfill(8)
|
||||
else:
|
||||
p = '*' + p
|
||||
result.append(p)
|
||||
result.append('*final')
|
||||
return result
|
||||
|
||||
result = []
|
||||
for p in get_parts(s):
|
||||
if p.startswith('*'):
|
||||
if p < '*final':
|
||||
while result and result[-1] == '*final-':
|
||||
result.pop()
|
||||
while result and result[-1] == '00000000':
|
||||
result.pop()
|
||||
result.append(p)
|
||||
return tuple(result)
|
||||
|
||||
|
||||
class LegacyVersion(Version):
|
||||
def parse(self, s):
|
||||
return _legacy_key(s)
|
||||
|
||||
@property
|
||||
def is_prerelease(self):
|
||||
result = False
|
||||
for x in self._parts:
|
||||
if (isinstance(x, string_types) and x.startswith('*') and
|
||||
x < '*final'):
|
||||
result = True
|
||||
break
|
||||
return result
|
||||
|
||||
|
||||
class LegacyMatcher(Matcher):
|
||||
version_class = LegacyVersion
|
||||
|
||||
_operators = dict(Matcher._operators)
|
||||
_operators['~='] = '_match_compatible'
|
||||
|
||||
numeric_re = re.compile('^(\d+(\.\d+)*)')
|
||||
|
||||
def _match_compatible(self, version, constraint, prefix):
|
||||
if version < constraint:
|
||||
return False
|
||||
m = self.numeric_re.match(str(constraint))
|
||||
if not m:
|
||||
logger.warning('Cannot compute compatible match for version %s '
|
||||
' and constraint %s', version, constraint)
|
||||
return True
|
||||
s = m.groups()[0]
|
||||
if '.' in s:
|
||||
s = s.rsplit('.', 1)[0]
|
||||
return _match_prefix(version, s)
|
||||
|
||||
#
|
||||
# Semantic versioning
|
||||
#
|
||||
|
||||
_SEMVER_RE = re.compile(r'^(\d+)\.(\d+)\.(\d+)'
|
||||
r'(-[a-z0-9]+(\.[a-z0-9-]+)*)?'
|
||||
r'(\+[a-z0-9]+(\.[a-z0-9-]+)*)?$', re.I)
|
||||
|
||||
|
||||
def is_semver(s):
|
||||
return _SEMVER_RE.match(s)
|
||||
|
||||
|
||||
def _semantic_key(s):
|
||||
def make_tuple(s, absent):
|
||||
if s is None:
|
||||
result = (absent,)
|
||||
else:
|
||||
parts = s[1:].split('.')
|
||||
# We can't compare ints and strings on Python 3, so fudge it
|
||||
# by zero-filling numeric values so simulate a numeric comparison
|
||||
result = tuple([p.zfill(8) if p.isdigit() else p for p in parts])
|
||||
return result
|
||||
|
||||
m = is_semver(s)
|
||||
if not m:
|
||||
raise UnsupportedVersionError(s)
|
||||
groups = m.groups()
|
||||
major, minor, patch = [int(i) for i in groups[:3]]
|
||||
# choose the '|' and '*' so that versions sort correctly
|
||||
pre, build = make_tuple(groups[3], '|'), make_tuple(groups[5], '*')
|
||||
return (major, minor, patch), pre, build
|
||||
|
||||
|
||||
class SemanticVersion(Version):
|
||||
def parse(self, s):
|
||||
return _semantic_key(s)
|
||||
|
||||
@property
|
||||
def is_prerelease(self):
|
||||
return self._parts[1][0] != '|'
|
||||
|
||||
|
||||
class SemanticMatcher(Matcher):
|
||||
version_class = SemanticVersion
|
||||
|
||||
|
||||
class VersionScheme(object):
|
||||
def __init__(self, key, matcher, suggester=None):
|
||||
self.key = key
|
||||
self.matcher = matcher
|
||||
self.suggester = suggester
|
||||
|
||||
def is_valid_version(self, s):
|
||||
try:
|
||||
self.matcher.version_class(s)
|
||||
result = True
|
||||
except UnsupportedVersionError:
|
||||
result = False
|
||||
return result
|
||||
|
||||
def is_valid_matcher(self, s):
|
||||
try:
|
||||
self.matcher(s)
|
||||
result = True
|
||||
except UnsupportedVersionError:
|
||||
result = False
|
||||
return result
|
||||
|
||||
def is_valid_constraint_list(self, s):
|
||||
"""
|
||||
Used for processing some metadata fields
|
||||
"""
|
||||
return self.is_valid_matcher('dummy_name (%s)' % s)
|
||||
|
||||
def suggest(self, s):
|
||||
if self.suggester is None:
|
||||
result = None
|
||||
else:
|
||||
result = self.suggester(s)
|
||||
return result
|
||||
|
||||
_SCHEMES = {
|
||||
'normalized': VersionScheme(_normalized_key, NormalizedMatcher,
|
||||
_suggest_normalized_version),
|
||||
'legacy': VersionScheme(_legacy_key, LegacyMatcher, lambda self, s: s),
|
||||
'semantic': VersionScheme(_semantic_key, SemanticMatcher,
|
||||
_suggest_semantic_version),
|
||||
}
|
||||
|
||||
_SCHEMES['default'] = _SCHEMES['normalized']
|
||||
|
||||
|
||||
def get_scheme(name):
|
||||
if name not in _SCHEMES:
|
||||
raise ValueError('unknown scheme name: %r' % name)
|
||||
return _SCHEMES[name]
|
||||
BIN
Darwin/lib/python3.4/site-packages/pip/_vendor/distlib/w32.exe
Normal file
BIN
Darwin/lib/python3.4/site-packages/pip/_vendor/distlib/w32.exe
Normal file
Binary file not shown.
BIN
Darwin/lib/python3.4/site-packages/pip/_vendor/distlib/w64.exe
Normal file
BIN
Darwin/lib/python3.4/site-packages/pip/_vendor/distlib/w64.exe
Normal file
Binary file not shown.
958
Darwin/lib/python3.4/site-packages/pip/_vendor/distlib/wheel.py
Normal file
958
Darwin/lib/python3.4/site-packages/pip/_vendor/distlib/wheel.py
Normal file
|
|
@ -0,0 +1,958 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
#
|
||||
# Copyright (C) 2013-2014 Vinay Sajip.
|
||||
# Licensed to the Python Software Foundation under a contributor agreement.
|
||||
# See LICENSE.txt and CONTRIBUTORS.txt.
|
||||
#
|
||||
from __future__ import unicode_literals
|
||||
|
||||
import base64
|
||||
import codecs
|
||||
import datetime
|
||||
import distutils.util
|
||||
from email import message_from_file
|
||||
import hashlib
|
||||
import imp
|
||||
import json
|
||||
import logging
|
||||
import os
|
||||
import posixpath
|
||||
import re
|
||||
import shutil
|
||||
import sys
|
||||
import tempfile
|
||||
import zipfile
|
||||
|
||||
from . import __version__, DistlibException
|
||||
from .compat import sysconfig, ZipFile, fsdecode, text_type, filter
|
||||
from .database import InstalledDistribution
|
||||
from .metadata import Metadata, METADATA_FILENAME
|
||||
from .util import (FileOperator, convert_path, CSVReader, CSVWriter, Cache,
|
||||
cached_property, get_cache_base, read_exports, tempdir)
|
||||
from .version import NormalizedVersion, UnsupportedVersionError
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
cache = None # created when needed
|
||||
|
||||
if hasattr(sys, 'pypy_version_info'):
|
||||
IMP_PREFIX = 'pp'
|
||||
elif sys.platform.startswith('java'):
|
||||
IMP_PREFIX = 'jy'
|
||||
elif sys.platform == 'cli':
|
||||
IMP_PREFIX = 'ip'
|
||||
else:
|
||||
IMP_PREFIX = 'cp'
|
||||
|
||||
VER_SUFFIX = sysconfig.get_config_var('py_version_nodot')
|
||||
if not VER_SUFFIX: # pragma: no cover
|
||||
VER_SUFFIX = '%s%s' % sys.version_info[:2]
|
||||
PYVER = 'py' + VER_SUFFIX
|
||||
IMPVER = IMP_PREFIX + VER_SUFFIX
|
||||
|
||||
ARCH = distutils.util.get_platform().replace('-', '_').replace('.', '_')
|
||||
|
||||
ABI = sysconfig.get_config_var('SOABI')
|
||||
if ABI and ABI.startswith('cpython-'):
|
||||
ABI = ABI.replace('cpython-', 'cp')
|
||||
else:
|
||||
def _derive_abi():
|
||||
parts = ['cp', VER_SUFFIX]
|
||||
if sysconfig.get_config_var('Py_DEBUG'):
|
||||
parts.append('d')
|
||||
if sysconfig.get_config_var('WITH_PYMALLOC'):
|
||||
parts.append('m')
|
||||
if sysconfig.get_config_var('Py_UNICODE_SIZE') == 4:
|
||||
parts.append('u')
|
||||
return ''.join(parts)
|
||||
ABI = _derive_abi()
|
||||
del _derive_abi
|
||||
|
||||
FILENAME_RE = re.compile(r'''
|
||||
(?P<nm>[^-]+)
|
||||
-(?P<vn>\d+[^-]*)
|
||||
(-(?P<bn>\d+[^-]*))?
|
||||
-(?P<py>\w+\d+(\.\w+\d+)*)
|
||||
-(?P<bi>\w+)
|
||||
-(?P<ar>\w+)
|
||||
\.whl$
|
||||
''', re.IGNORECASE | re.VERBOSE)
|
||||
|
||||
NAME_VERSION_RE = re.compile(r'''
|
||||
(?P<nm>[^-]+)
|
||||
-(?P<vn>\d+[^-]*)
|
||||
(-(?P<bn>\d+[^-]*))?$
|
||||
''', re.IGNORECASE | re.VERBOSE)
|
||||
|
||||
SHEBANG_RE = re.compile(br'\s*#![^\r\n]*')
|
||||
|
||||
if os.sep == '/':
|
||||
to_posix = lambda o: o
|
||||
else:
|
||||
to_posix = lambda o: o.replace(os.sep, '/')
|
||||
|
||||
|
||||
class Mounter(object):
|
||||
def __init__(self):
|
||||
self.impure_wheels = {}
|
||||
self.libs = {}
|
||||
|
||||
def add(self, pathname, extensions):
|
||||
self.impure_wheels[pathname] = extensions
|
||||
self.libs.update(extensions)
|
||||
|
||||
def remove(self, pathname):
|
||||
extensions = self.impure_wheels.pop(pathname)
|
||||
for k, v in extensions:
|
||||
if k in self.libs:
|
||||
del self.libs[k]
|
||||
|
||||
def find_module(self, fullname, path=None):
|
||||
if fullname in self.libs:
|
||||
result = self
|
||||
else:
|
||||
result = None
|
||||
return result
|
||||
|
||||
def load_module(self, fullname):
|
||||
if fullname in sys.modules:
|
||||
result = sys.modules[fullname]
|
||||
else:
|
||||
if fullname not in self.libs:
|
||||
raise ImportError('unable to find extension for %s' % fullname)
|
||||
result = imp.load_dynamic(fullname, self.libs[fullname])
|
||||
result.__loader__ = self
|
||||
parts = fullname.rsplit('.', 1)
|
||||
if len(parts) > 1:
|
||||
result.__package__ = parts[0]
|
||||
return result
|
||||
|
||||
_hook = Mounter()
|
||||
|
||||
|
||||
class Wheel(object):
|
||||
"""
|
||||
Class to build and install from Wheel files (PEP 427).
|
||||
"""
|
||||
|
||||
wheel_version = (1, 1)
|
||||
hash_kind = 'sha256'
|
||||
|
||||
def __init__(self, filename=None, sign=False, verify=False):
|
||||
"""
|
||||
Initialise an instance using a (valid) filename.
|
||||
"""
|
||||
self.sign = sign
|
||||
self.should_verify = verify
|
||||
self.buildver = ''
|
||||
self.pyver = [PYVER]
|
||||
self.abi = ['none']
|
||||
self.arch = ['any']
|
||||
self.dirname = os.getcwd()
|
||||
if filename is None:
|
||||
self.name = 'dummy'
|
||||
self.version = '0.1'
|
||||
self._filename = self.filename
|
||||
else:
|
||||
m = NAME_VERSION_RE.match(filename)
|
||||
if m:
|
||||
info = m.groupdict('')
|
||||
self.name = info['nm']
|
||||
# Reinstate the local version separator
|
||||
self.version = info['vn'].replace('_', '-')
|
||||
self.buildver = info['bn']
|
||||
self._filename = self.filename
|
||||
else:
|
||||
dirname, filename = os.path.split(filename)
|
||||
m = FILENAME_RE.match(filename)
|
||||
if not m:
|
||||
raise DistlibException('Invalid name or '
|
||||
'filename: %r' % filename)
|
||||
if dirname:
|
||||
self.dirname = os.path.abspath(dirname)
|
||||
self._filename = filename
|
||||
info = m.groupdict('')
|
||||
self.name = info['nm']
|
||||
self.version = info['vn']
|
||||
self.buildver = info['bn']
|
||||
self.pyver = info['py'].split('.')
|
||||
self.abi = info['bi'].split('.')
|
||||
self.arch = info['ar'].split('.')
|
||||
|
||||
@property
|
||||
def filename(self):
|
||||
"""
|
||||
Build and return a filename from the various components.
|
||||
"""
|
||||
if self.buildver:
|
||||
buildver = '-' + self.buildver
|
||||
else:
|
||||
buildver = ''
|
||||
pyver = '.'.join(self.pyver)
|
||||
abi = '.'.join(self.abi)
|
||||
arch = '.'.join(self.arch)
|
||||
# replace - with _ as a local version separator
|
||||
version = self.version.replace('-', '_')
|
||||
return '%s-%s%s-%s-%s-%s.whl' % (self.name, version, buildver,
|
||||
pyver, abi, arch)
|
||||
|
||||
@property
|
||||
def exists(self):
|
||||
path = os.path.join(self.dirname, self.filename)
|
||||
return os.path.isfile(path)
|
||||
|
||||
@property
|
||||
def tags(self):
|
||||
for pyver in self.pyver:
|
||||
for abi in self.abi:
|
||||
for arch in self.arch:
|
||||
yield pyver, abi, arch
|
||||
|
||||
@cached_property
|
||||
def metadata(self):
|
||||
pathname = os.path.join(self.dirname, self.filename)
|
||||
name_ver = '%s-%s' % (self.name, self.version)
|
||||
info_dir = '%s.dist-info' % name_ver
|
||||
wrapper = codecs.getreader('utf-8')
|
||||
with ZipFile(pathname, 'r') as zf:
|
||||
wheel_metadata = self.get_wheel_metadata(zf)
|
||||
wv = wheel_metadata['Wheel-Version'].split('.', 1)
|
||||
file_version = tuple([int(i) for i in wv])
|
||||
if file_version < (1, 1):
|
||||
fn = 'METADATA'
|
||||
else:
|
||||
fn = METADATA_FILENAME
|
||||
try:
|
||||
metadata_filename = posixpath.join(info_dir, fn)
|
||||
with zf.open(metadata_filename) as bf:
|
||||
wf = wrapper(bf)
|
||||
result = Metadata(fileobj=wf)
|
||||
except KeyError:
|
||||
raise ValueError('Invalid wheel, because %s is '
|
||||
'missing' % fn)
|
||||
return result
|
||||
|
||||
def get_wheel_metadata(self, zf):
|
||||
name_ver = '%s-%s' % (self.name, self.version)
|
||||
info_dir = '%s.dist-info' % name_ver
|
||||
metadata_filename = posixpath.join(info_dir, 'WHEEL')
|
||||
with zf.open(metadata_filename) as bf:
|
||||
wf = codecs.getreader('utf-8')(bf)
|
||||
message = message_from_file(wf)
|
||||
return dict(message)
|
||||
|
||||
@cached_property
|
||||
def info(self):
|
||||
pathname = os.path.join(self.dirname, self.filename)
|
||||
with ZipFile(pathname, 'r') as zf:
|
||||
result = self.get_wheel_metadata(zf)
|
||||
return result
|
||||
|
||||
def process_shebang(self, data):
|
||||
m = SHEBANG_RE.match(data)
|
||||
if m:
|
||||
data = b'#!python' + data[m.end():]
|
||||
else:
|
||||
cr = data.find(b'\r')
|
||||
lf = data.find(b'\n')
|
||||
if cr < 0 or cr > lf:
|
||||
term = b'\n'
|
||||
else:
|
||||
if data[cr:cr + 2] == b'\r\n':
|
||||
term = b'\r\n'
|
||||
else:
|
||||
term = b'\r'
|
||||
data = b'#!python' + term + data
|
||||
return data
|
||||
|
||||
def get_hash(self, data, hash_kind=None):
|
||||
if hash_kind is None:
|
||||
hash_kind = self.hash_kind
|
||||
try:
|
||||
hasher = getattr(hashlib, hash_kind)
|
||||
except AttributeError:
|
||||
raise DistlibException('Unsupported hash algorithm: %r' % hash_kind)
|
||||
result = hasher(data).digest()
|
||||
result = base64.urlsafe_b64encode(result).rstrip(b'=').decode('ascii')
|
||||
return hash_kind, result
|
||||
|
||||
def write_record(self, records, record_path, base):
|
||||
with CSVWriter(record_path) as writer:
|
||||
for row in records:
|
||||
writer.writerow(row)
|
||||
p = to_posix(os.path.relpath(record_path, base))
|
||||
writer.writerow((p, '', ''))
|
||||
|
||||
def write_records(self, info, libdir, archive_paths):
|
||||
records = []
|
||||
distinfo, info_dir = info
|
||||
hasher = getattr(hashlib, self.hash_kind)
|
||||
for ap, p in archive_paths:
|
||||
with open(p, 'rb') as f:
|
||||
data = f.read()
|
||||
digest = '%s=%s' % self.get_hash(data)
|
||||
size = os.path.getsize(p)
|
||||
records.append((ap, digest, size))
|
||||
|
||||
p = os.path.join(distinfo, 'RECORD')
|
||||
self.write_record(records, p, libdir)
|
||||
ap = to_posix(os.path.join(info_dir, 'RECORD'))
|
||||
archive_paths.append((ap, p))
|
||||
|
||||
def build_zip(self, pathname, archive_paths):
|
||||
with ZipFile(pathname, 'w', zipfile.ZIP_DEFLATED) as zf:
|
||||
for ap, p in archive_paths:
|
||||
logger.debug('Wrote %s to %s in wheel', p, ap)
|
||||
zf.write(p, ap)
|
||||
|
||||
def build(self, paths, tags=None, wheel_version=None):
|
||||
"""
|
||||
Build a wheel from files in specified paths, and use any specified tags
|
||||
when determining the name of the wheel.
|
||||
"""
|
||||
if tags is None:
|
||||
tags = {}
|
||||
|
||||
libkey = list(filter(lambda o: o in paths, ('purelib', 'platlib')))[0]
|
||||
if libkey == 'platlib':
|
||||
is_pure = 'false'
|
||||
default_pyver = [IMPVER]
|
||||
default_abi = [ABI]
|
||||
default_arch = [ARCH]
|
||||
else:
|
||||
is_pure = 'true'
|
||||
default_pyver = [PYVER]
|
||||
default_abi = ['none']
|
||||
default_arch = ['any']
|
||||
|
||||
self.pyver = tags.get('pyver', default_pyver)
|
||||
self.abi = tags.get('abi', default_abi)
|
||||
self.arch = tags.get('arch', default_arch)
|
||||
|
||||
libdir = paths[libkey]
|
||||
|
||||
name_ver = '%s-%s' % (self.name, self.version)
|
||||
data_dir = '%s.data' % name_ver
|
||||
info_dir = '%s.dist-info' % name_ver
|
||||
|
||||
archive_paths = []
|
||||
|
||||
# First, stuff which is not in site-packages
|
||||
for key in ('data', 'headers', 'scripts'):
|
||||
if key not in paths:
|
||||
continue
|
||||
path = paths[key]
|
||||
if os.path.isdir(path):
|
||||
for root, dirs, files in os.walk(path):
|
||||
for fn in files:
|
||||
p = fsdecode(os.path.join(root, fn))
|
||||
rp = os.path.relpath(p, path)
|
||||
ap = to_posix(os.path.join(data_dir, key, rp))
|
||||
archive_paths.append((ap, p))
|
||||
if key == 'scripts' and not p.endswith('.exe'):
|
||||
with open(p, 'rb') as f:
|
||||
data = f.read()
|
||||
data = self.process_shebang(data)
|
||||
with open(p, 'wb') as f:
|
||||
f.write(data)
|
||||
|
||||
# Now, stuff which is in site-packages, other than the
|
||||
# distinfo stuff.
|
||||
path = libdir
|
||||
distinfo = None
|
||||
for root, dirs, files in os.walk(path):
|
||||
if root == path:
|
||||
# At the top level only, save distinfo for later
|
||||
# and skip it for now
|
||||
for i, dn in enumerate(dirs):
|
||||
dn = fsdecode(dn)
|
||||
if dn.endswith('.dist-info'):
|
||||
distinfo = os.path.join(root, dn)
|
||||
del dirs[i]
|
||||
break
|
||||
assert distinfo, '.dist-info directory expected, not found'
|
||||
|
||||
for fn in files:
|
||||
# comment out next suite to leave .pyc files in
|
||||
if fsdecode(fn).endswith(('.pyc', '.pyo')):
|
||||
continue
|
||||
p = os.path.join(root, fn)
|
||||
rp = to_posix(os.path.relpath(p, path))
|
||||
archive_paths.append((rp, p))
|
||||
|
||||
# Now distinfo. Assumed to be flat, i.e. os.listdir is enough.
|
||||
files = os.listdir(distinfo)
|
||||
for fn in files:
|
||||
if fn not in ('RECORD', 'INSTALLER', 'SHARED'):
|
||||
p = fsdecode(os.path.join(distinfo, fn))
|
||||
ap = to_posix(os.path.join(info_dir, fn))
|
||||
archive_paths.append((ap, p))
|
||||
|
||||
wheel_metadata = [
|
||||
'Wheel-Version: %d.%d' % (wheel_version or self.wheel_version),
|
||||
'Generator: distlib %s' % __version__,
|
||||
'Root-Is-Purelib: %s' % is_pure,
|
||||
]
|
||||
for pyver, abi, arch in self.tags:
|
||||
wheel_metadata.append('Tag: %s-%s-%s' % (pyver, abi, arch))
|
||||
p = os.path.join(distinfo, 'WHEEL')
|
||||
with open(p, 'w') as f:
|
||||
f.write('\n'.join(wheel_metadata))
|
||||
ap = to_posix(os.path.join(info_dir, 'WHEEL'))
|
||||
archive_paths.append((ap, p))
|
||||
|
||||
# Now, at last, RECORD.
|
||||
# Paths in here are archive paths - nothing else makes sense.
|
||||
self.write_records((distinfo, info_dir), libdir, archive_paths)
|
||||
# Now, ready to build the zip file
|
||||
pathname = os.path.join(self.dirname, self.filename)
|
||||
self.build_zip(pathname, archive_paths)
|
||||
return pathname
|
||||
|
||||
def install(self, paths, maker, **kwargs):
|
||||
"""
|
||||
Install a wheel to the specified paths. If kwarg ``warner`` is
|
||||
specified, it should be a callable, which will be called with two
|
||||
tuples indicating the wheel version of this software and the wheel
|
||||
version in the file, if there is a discrepancy in the versions.
|
||||
This can be used to issue any warnings to raise any exceptions.
|
||||
If kwarg ``lib_only`` is True, only the purelib/platlib files are
|
||||
installed, and the headers, scripts, data and dist-info metadata are
|
||||
not written.
|
||||
|
||||
The return value is a :class:`InstalledDistribution` instance unless
|
||||
``options.lib_only`` is True, in which case the return value is ``None``.
|
||||
"""
|
||||
|
||||
dry_run = maker.dry_run
|
||||
warner = kwargs.get('warner')
|
||||
lib_only = kwargs.get('lib_only', False)
|
||||
|
||||
pathname = os.path.join(self.dirname, self.filename)
|
||||
name_ver = '%s-%s' % (self.name, self.version)
|
||||
data_dir = '%s.data' % name_ver
|
||||
info_dir = '%s.dist-info' % name_ver
|
||||
|
||||
metadata_name = posixpath.join(info_dir, METADATA_FILENAME)
|
||||
wheel_metadata_name = posixpath.join(info_dir, 'WHEEL')
|
||||
record_name = posixpath.join(info_dir, 'RECORD')
|
||||
|
||||
wrapper = codecs.getreader('utf-8')
|
||||
|
||||
with ZipFile(pathname, 'r') as zf:
|
||||
with zf.open(wheel_metadata_name) as bwf:
|
||||
wf = wrapper(bwf)
|
||||
message = message_from_file(wf)
|
||||
wv = message['Wheel-Version'].split('.', 1)
|
||||
file_version = tuple([int(i) for i in wv])
|
||||
if (file_version != self.wheel_version) and warner:
|
||||
warner(self.wheel_version, file_version)
|
||||
|
||||
if message['Root-Is-Purelib'] == 'true':
|
||||
libdir = paths['purelib']
|
||||
else:
|
||||
libdir = paths['platlib']
|
||||
|
||||
records = {}
|
||||
with zf.open(record_name) as bf:
|
||||
with CSVReader(stream=bf) as reader:
|
||||
for row in reader:
|
||||
p = row[0]
|
||||
records[p] = row
|
||||
|
||||
data_pfx = posixpath.join(data_dir, '')
|
||||
info_pfx = posixpath.join(info_dir, '')
|
||||
script_pfx = posixpath.join(data_dir, 'scripts', '')
|
||||
|
||||
# make a new instance rather than a copy of maker's,
|
||||
# as we mutate it
|
||||
fileop = FileOperator(dry_run=dry_run)
|
||||
fileop.record = True # so we can rollback if needed
|
||||
|
||||
bc = not sys.dont_write_bytecode # Double negatives. Lovely!
|
||||
|
||||
outfiles = [] # for RECORD writing
|
||||
|
||||
# for script copying/shebang processing
|
||||
workdir = tempfile.mkdtemp()
|
||||
# set target dir later
|
||||
# we default add_launchers to False, as the
|
||||
# Python Launcher should be used instead
|
||||
maker.source_dir = workdir
|
||||
maker.target_dir = None
|
||||
try:
|
||||
for zinfo in zf.infolist():
|
||||
arcname = zinfo.filename
|
||||
if isinstance(arcname, text_type):
|
||||
u_arcname = arcname
|
||||
else:
|
||||
u_arcname = arcname.decode('utf-8')
|
||||
# The signature file won't be in RECORD,
|
||||
# and we don't currently don't do anything with it
|
||||
if u_arcname.endswith('/RECORD.jws'):
|
||||
continue
|
||||
row = records[u_arcname]
|
||||
if row[2] and str(zinfo.file_size) != row[2]:
|
||||
raise DistlibException('size mismatch for '
|
||||
'%s' % u_arcname)
|
||||
if row[1]:
|
||||
kind, value = row[1].split('=', 1)
|
||||
with zf.open(arcname) as bf:
|
||||
data = bf.read()
|
||||
_, digest = self.get_hash(data, kind)
|
||||
if digest != value:
|
||||
raise DistlibException('digest mismatch for '
|
||||
'%s' % arcname)
|
||||
|
||||
if lib_only and u_arcname.startswith((info_pfx, data_pfx)):
|
||||
logger.debug('lib_only: skipping %s', u_arcname)
|
||||
continue
|
||||
is_script = (u_arcname.startswith(script_pfx)
|
||||
and not u_arcname.endswith('.exe'))
|
||||
|
||||
if u_arcname.startswith(data_pfx):
|
||||
_, where, rp = u_arcname.split('/', 2)
|
||||
outfile = os.path.join(paths[where], convert_path(rp))
|
||||
else:
|
||||
# meant for site-packages.
|
||||
if u_arcname in (wheel_metadata_name, record_name):
|
||||
continue
|
||||
outfile = os.path.join(libdir, convert_path(u_arcname))
|
||||
if not is_script:
|
||||
with zf.open(arcname) as bf:
|
||||
fileop.copy_stream(bf, outfile)
|
||||
outfiles.append(outfile)
|
||||
# Double check the digest of the written file
|
||||
if not dry_run and row[1]:
|
||||
with open(outfile, 'rb') as bf:
|
||||
data = bf.read()
|
||||
_, newdigest = self.get_hash(data, kind)
|
||||
if newdigest != digest:
|
||||
raise DistlibException('digest mismatch '
|
||||
'on write for '
|
||||
'%s' % outfile)
|
||||
if bc and outfile.endswith('.py'):
|
||||
try:
|
||||
pyc = fileop.byte_compile(outfile)
|
||||
outfiles.append(pyc)
|
||||
except Exception:
|
||||
# Don't give up if byte-compilation fails,
|
||||
# but log it and perhaps warn the user
|
||||
logger.warning('Byte-compilation failed',
|
||||
exc_info=True)
|
||||
else:
|
||||
fn = os.path.basename(convert_path(arcname))
|
||||
workname = os.path.join(workdir, fn)
|
||||
with zf.open(arcname) as bf:
|
||||
fileop.copy_stream(bf, workname)
|
||||
|
||||
dn, fn = os.path.split(outfile)
|
||||
maker.target_dir = dn
|
||||
filenames = maker.make(fn)
|
||||
fileop.set_executable_mode(filenames)
|
||||
outfiles.extend(filenames)
|
||||
|
||||
if lib_only:
|
||||
logger.debug('lib_only: returning None')
|
||||
dist = None
|
||||
else:
|
||||
# Generate scripts
|
||||
|
||||
# Try to get pydist.json so we can see if there are
|
||||
# any commands to generate. If this fails (e.g. because
|
||||
# of a legacy wheel), log a warning but don't give up.
|
||||
commands = None
|
||||
file_version = self.info['Wheel-Version']
|
||||
if file_version == '1.0':
|
||||
# Use legacy info
|
||||
ep = posixpath.join(info_dir, 'entry_points.txt')
|
||||
try:
|
||||
with zf.open(ep) as bwf:
|
||||
epdata = read_exports(bwf)
|
||||
commands = {}
|
||||
for key in ('console', 'gui'):
|
||||
k = '%s_scripts' % key
|
||||
if k in epdata:
|
||||
commands['wrap_%s' % key] = d = {}
|
||||
for v in epdata[k].values():
|
||||
s = '%s:%s' % (v.prefix, v.suffix)
|
||||
if v.flags:
|
||||
s += ' %s' % v.flags
|
||||
d[v.name] = s
|
||||
except Exception:
|
||||
logger.warning('Unable to read legacy script '
|
||||
'metadata, so cannot generate '
|
||||
'scripts')
|
||||
else:
|
||||
try:
|
||||
with zf.open(metadata_name) as bwf:
|
||||
wf = wrapper(bwf)
|
||||
commands = json.load(wf).get('commands')
|
||||
except Exception:
|
||||
logger.warning('Unable to read JSON metadata, so '
|
||||
'cannot generate scripts')
|
||||
if commands:
|
||||
console_scripts = commands.get('wrap_console', {})
|
||||
gui_scripts = commands.get('wrap_gui', {})
|
||||
if console_scripts or gui_scripts:
|
||||
script_dir = paths.get('scripts', '')
|
||||
if not os.path.isdir(script_dir):
|
||||
raise ValueError('Valid script path not '
|
||||
'specified')
|
||||
maker.target_dir = script_dir
|
||||
for k, v in console_scripts.items():
|
||||
script = '%s = %s' % (k, v)
|
||||
filenames = maker.make(script)
|
||||
fileop.set_executable_mode(filenames)
|
||||
|
||||
if gui_scripts:
|
||||
options = {'gui': True }
|
||||
for k, v in gui_scripts.items():
|
||||
script = '%s = %s' % (k, v)
|
||||
filenames = maker.make(script, options)
|
||||
fileop.set_executable_mode(filenames)
|
||||
|
||||
p = os.path.join(libdir, info_dir)
|
||||
dist = InstalledDistribution(p)
|
||||
|
||||
# Write SHARED
|
||||
paths = dict(paths) # don't change passed in dict
|
||||
del paths['purelib']
|
||||
del paths['platlib']
|
||||
paths['lib'] = libdir
|
||||
p = dist.write_shared_locations(paths, dry_run)
|
||||
if p:
|
||||
outfiles.append(p)
|
||||
|
||||
# Write RECORD
|
||||
dist.write_installed_files(outfiles, paths['prefix'],
|
||||
dry_run)
|
||||
return dist
|
||||
except Exception: # pragma: no cover
|
||||
logger.exception('installation failed.')
|
||||
fileop.rollback()
|
||||
raise
|
||||
finally:
|
||||
shutil.rmtree(workdir)
|
||||
|
||||
def _get_dylib_cache(self):
|
||||
global cache
|
||||
if cache is None:
|
||||
# Use native string to avoid issues on 2.x: see Python #20140.
|
||||
base = os.path.join(get_cache_base(), str('dylib-cache'),
|
||||
sys.version[:3])
|
||||
cache = Cache(base)
|
||||
return cache
|
||||
|
||||
def _get_extensions(self):
|
||||
pathname = os.path.join(self.dirname, self.filename)
|
||||
name_ver = '%s-%s' % (self.name, self.version)
|
||||
info_dir = '%s.dist-info' % name_ver
|
||||
arcname = posixpath.join(info_dir, 'EXTENSIONS')
|
||||
wrapper = codecs.getreader('utf-8')
|
||||
result = []
|
||||
with ZipFile(pathname, 'r') as zf:
|
||||
try:
|
||||
with zf.open(arcname) as bf:
|
||||
wf = wrapper(bf)
|
||||
extensions = json.load(wf)
|
||||
cache = self._get_dylib_cache()
|
||||
prefix = cache.prefix_to_dir(pathname)
|
||||
cache_base = os.path.join(cache.base, prefix)
|
||||
if not os.path.isdir(cache_base):
|
||||
os.makedirs(cache_base)
|
||||
for name, relpath in extensions.items():
|
||||
dest = os.path.join(cache_base, convert_path(relpath))
|
||||
if not os.path.exists(dest):
|
||||
extract = True
|
||||
else:
|
||||
file_time = os.stat(dest).st_mtime
|
||||
file_time = datetime.datetime.fromtimestamp(file_time)
|
||||
info = zf.getinfo(relpath)
|
||||
wheel_time = datetime.datetime(*info.date_time)
|
||||
extract = wheel_time > file_time
|
||||
if extract:
|
||||
zf.extract(relpath, cache_base)
|
||||
result.append((name, dest))
|
||||
except KeyError:
|
||||
pass
|
||||
return result
|
||||
|
||||
def is_compatible(self):
|
||||
"""
|
||||
Determine if a wheel is compatible with the running system.
|
||||
"""
|
||||
return is_compatible(self)
|
||||
|
||||
def is_mountable(self):
|
||||
"""
|
||||
Determine if a wheel is asserted as mountable by its metadata.
|
||||
"""
|
||||
return True # for now - metadata details TBD
|
||||
|
||||
def mount(self, append=False):
|
||||
pathname = os.path.abspath(os.path.join(self.dirname, self.filename))
|
||||
if not self.is_compatible():
|
||||
msg = 'Wheel %s not compatible with this Python.' % pathname
|
||||
raise DistlibException(msg)
|
||||
if not self.is_mountable():
|
||||
msg = 'Wheel %s is marked as not mountable.' % pathname
|
||||
raise DistlibException(msg)
|
||||
if pathname in sys.path:
|
||||
logger.debug('%s already in path', pathname)
|
||||
else:
|
||||
if append:
|
||||
sys.path.append(pathname)
|
||||
else:
|
||||
sys.path.insert(0, pathname)
|
||||
extensions = self._get_extensions()
|
||||
if extensions:
|
||||
if _hook not in sys.meta_path:
|
||||
sys.meta_path.append(_hook)
|
||||
_hook.add(pathname, extensions)
|
||||
|
||||
def unmount(self):
|
||||
pathname = os.path.abspath(os.path.join(self.dirname, self.filename))
|
||||
if pathname not in sys.path:
|
||||
logger.debug('%s not in path', pathname)
|
||||
else:
|
||||
sys.path.remove(pathname)
|
||||
if pathname in _hook.impure_wheels:
|
||||
_hook.remove(pathname)
|
||||
if not _hook.impure_wheels:
|
||||
if _hook in sys.meta_path:
|
||||
sys.meta_path.remove(_hook)
|
||||
|
||||
def verify(self):
|
||||
pathname = os.path.join(self.dirname, self.filename)
|
||||
name_ver = '%s-%s' % (self.name, self.version)
|
||||
data_dir = '%s.data' % name_ver
|
||||
info_dir = '%s.dist-info' % name_ver
|
||||
|
||||
metadata_name = posixpath.join(info_dir, METADATA_FILENAME)
|
||||
wheel_metadata_name = posixpath.join(info_dir, 'WHEEL')
|
||||
record_name = posixpath.join(info_dir, 'RECORD')
|
||||
|
||||
wrapper = codecs.getreader('utf-8')
|
||||
|
||||
with ZipFile(pathname, 'r') as zf:
|
||||
with zf.open(wheel_metadata_name) as bwf:
|
||||
wf = wrapper(bwf)
|
||||
message = message_from_file(wf)
|
||||
wv = message['Wheel-Version'].split('.', 1)
|
||||
file_version = tuple([int(i) for i in wv])
|
||||
# TODO version verification
|
||||
|
||||
records = {}
|
||||
with zf.open(record_name) as bf:
|
||||
with CSVReader(stream=bf) as reader:
|
||||
for row in reader:
|
||||
p = row[0]
|
||||
records[p] = row
|
||||
|
||||
for zinfo in zf.infolist():
|
||||
arcname = zinfo.filename
|
||||
if isinstance(arcname, text_type):
|
||||
u_arcname = arcname
|
||||
else:
|
||||
u_arcname = arcname.decode('utf-8')
|
||||
if '..' in u_arcname:
|
||||
raise DistlibException('invalid entry in '
|
||||
'wheel: %r' % u_arcname)
|
||||
|
||||
# The signature file won't be in RECORD,
|
||||
# and we don't currently don't do anything with it
|
||||
if u_arcname.endswith('/RECORD.jws'):
|
||||
continue
|
||||
row = records[u_arcname]
|
||||
if row[2] and str(zinfo.file_size) != row[2]:
|
||||
raise DistlibException('size mismatch for '
|
||||
'%s' % u_arcname)
|
||||
if row[1]:
|
||||
kind, value = row[1].split('=', 1)
|
||||
with zf.open(arcname) as bf:
|
||||
data = bf.read()
|
||||
_, digest = self.get_hash(data, kind)
|
||||
if digest != value:
|
||||
raise DistlibException('digest mismatch for '
|
||||
'%s' % arcname)
|
||||
|
||||
def update(self, modifier, dest_dir=None, **kwargs):
|
||||
"""
|
||||
Update the contents of a wheel in a generic way. The modifier should
|
||||
be a callable which expects a dictionary argument: its keys are
|
||||
archive-entry paths, and its values are absolute filesystem paths
|
||||
where the contents the corresponding archive entries can be found. The
|
||||
modifier is free to change the contents of the files pointed to, add
|
||||
new entries and remove entries, before returning. This method will
|
||||
extract the entire contents of the wheel to a temporary location, call
|
||||
the modifier, and then use the passed (and possibly updated)
|
||||
dictionary to write a new wheel. If ``dest_dir`` is specified, the new
|
||||
wheel is written there -- otherwise, the original wheel is overwritten.
|
||||
|
||||
The modifier should return True if it updated the wheel, else False.
|
||||
This method returns the same value the modifier returns.
|
||||
"""
|
||||
|
||||
def get_version(path_map, info_dir):
|
||||
version = path = None
|
||||
key = '%s/%s' % (info_dir, METADATA_FILENAME)
|
||||
if key not in path_map:
|
||||
key = '%s/PKG-INFO' % info_dir
|
||||
if key in path_map:
|
||||
path = path_map[key]
|
||||
version = Metadata(path=path).version
|
||||
return version, path
|
||||
|
||||
def update_version(version, path):
|
||||
updated = None
|
||||
try:
|
||||
v = NormalizedVersion(version)
|
||||
i = version.find('-')
|
||||
if i < 0:
|
||||
updated = '%s-1' % version
|
||||
else:
|
||||
parts = [int(s) for s in version[i + 1:].split('.')]
|
||||
parts[-1] += 1
|
||||
updated = '%s-%s' % (version[:i],
|
||||
'.'.join(str(i) for i in parts))
|
||||
except UnsupportedVersionError:
|
||||
logger.debug('Cannot update non-compliant (PEP-440) '
|
||||
'version %r', version)
|
||||
if updated:
|
||||
md = Metadata(path=path)
|
||||
md.version = updated
|
||||
legacy = not path.endswith(METADATA_FILENAME)
|
||||
md.write(path=path, legacy=legacy)
|
||||
logger.debug('Version updated from %r to %r', version,
|
||||
updated)
|
||||
|
||||
pathname = os.path.join(self.dirname, self.filename)
|
||||
name_ver = '%s-%s' % (self.name, self.version)
|
||||
info_dir = '%s.dist-info' % name_ver
|
||||
record_name = posixpath.join(info_dir, 'RECORD')
|
||||
with tempdir() as workdir:
|
||||
with ZipFile(pathname, 'r') as zf:
|
||||
path_map = {}
|
||||
for zinfo in zf.infolist():
|
||||
arcname = zinfo.filename
|
||||
if isinstance(arcname, text_type):
|
||||
u_arcname = arcname
|
||||
else:
|
||||
u_arcname = arcname.decode('utf-8')
|
||||
if u_arcname == record_name:
|
||||
continue
|
||||
if '..' in u_arcname:
|
||||
raise DistlibException('invalid entry in '
|
||||
'wheel: %r' % u_arcname)
|
||||
zf.extract(zinfo, workdir)
|
||||
path = os.path.join(workdir, convert_path(u_arcname))
|
||||
path_map[u_arcname] = path
|
||||
|
||||
# Remember the version.
|
||||
original_version, _ = get_version(path_map, info_dir)
|
||||
# Files extracted. Call the modifier.
|
||||
modified = modifier(path_map, **kwargs)
|
||||
if modified:
|
||||
# Something changed - need to build a new wheel.
|
||||
current_version, path = get_version(path_map, info_dir)
|
||||
if current_version and (current_version == original_version):
|
||||
# Add or update local version to signify changes.
|
||||
update_version(current_version, path)
|
||||
# Decide where the new wheel goes.
|
||||
if dest_dir is None:
|
||||
fd, newpath = tempfile.mkstemp(suffix='.whl',
|
||||
prefix='wheel-update-',
|
||||
dir=workdir)
|
||||
os.close(fd)
|
||||
else:
|
||||
if not os.path.isdir(dest_dir):
|
||||
raise DistlibException('Not a directory: %r' % dest_dir)
|
||||
newpath = os.path.join(dest_dir, self.filename)
|
||||
archive_paths = list(path_map.items())
|
||||
distinfo = os.path.join(workdir, info_dir)
|
||||
info = distinfo, info_dir
|
||||
self.write_records(info, workdir, archive_paths)
|
||||
self.build_zip(newpath, archive_paths)
|
||||
if dest_dir is None:
|
||||
shutil.copyfile(newpath, pathname)
|
||||
return modified
|
||||
|
||||
def compatible_tags():
|
||||
"""
|
||||
Return (pyver, abi, arch) tuples compatible with this Python.
|
||||
"""
|
||||
versions = [VER_SUFFIX]
|
||||
major = VER_SUFFIX[0]
|
||||
for minor in range(sys.version_info[1] - 1, - 1, -1):
|
||||
versions.append(''.join([major, str(minor)]))
|
||||
|
||||
abis = []
|
||||
for suffix, _, _ in imp.get_suffixes():
|
||||
if suffix.startswith('.abi'):
|
||||
abis.append(suffix.split('.', 2)[1])
|
||||
abis.sort()
|
||||
if ABI != 'none':
|
||||
abis.insert(0, ABI)
|
||||
abis.append('none')
|
||||
result = []
|
||||
|
||||
arches = [ARCH]
|
||||
if sys.platform == 'darwin':
|
||||
m = re.match('(\w+)_(\d+)_(\d+)_(\w+)$', ARCH)
|
||||
if m:
|
||||
name, major, minor, arch = m.groups()
|
||||
minor = int(minor)
|
||||
matches = [arch]
|
||||
if arch in ('i386', 'ppc'):
|
||||
matches.append('fat')
|
||||
if arch in ('i386', 'ppc', 'x86_64'):
|
||||
matches.append('fat3')
|
||||
if arch in ('ppc64', 'x86_64'):
|
||||
matches.append('fat64')
|
||||
if arch in ('i386', 'x86_64'):
|
||||
matches.append('intel')
|
||||
if arch in ('i386', 'x86_64', 'intel', 'ppc', 'ppc64'):
|
||||
matches.append('universal')
|
||||
while minor >= 0:
|
||||
for match in matches:
|
||||
s = '%s_%s_%s_%s' % (name, major, minor, match)
|
||||
if s != ARCH: # already there
|
||||
arches.append(s)
|
||||
minor -= 1
|
||||
|
||||
# Most specific - our Python version, ABI and arch
|
||||
for abi in abis:
|
||||
for arch in arches:
|
||||
result.append((''.join((IMP_PREFIX, versions[0])), abi, arch))
|
||||
|
||||
# where no ABI / arch dependency, but IMP_PREFIX dependency
|
||||
for i, version in enumerate(versions):
|
||||
result.append((''.join((IMP_PREFIX, version)), 'none', 'any'))
|
||||
if i == 0:
|
||||
result.append((''.join((IMP_PREFIX, version[0])), 'none', 'any'))
|
||||
|
||||
# no IMP_PREFIX, ABI or arch dependency
|
||||
for i, version in enumerate(versions):
|
||||
result.append((''.join(('py', version)), 'none', 'any'))
|
||||
if i == 0:
|
||||
result.append((''.join(('py', version[0])), 'none', 'any'))
|
||||
return set(result)
|
||||
|
||||
|
||||
COMPATIBLE_TAGS = compatible_tags()
|
||||
|
||||
del compatible_tags
|
||||
|
||||
|
||||
def is_compatible(wheel, tags=None):
|
||||
if not isinstance(wheel, Wheel):
|
||||
wheel = Wheel(wheel) # assume it's a filename
|
||||
result = False
|
||||
if tags is None:
|
||||
tags = COMPATIBLE_TAGS
|
||||
for ver, abi, arch in tags:
|
||||
if ver in wheel.pyver and abi in wheel.abi and arch in wheel.arch:
|
||||
result = True
|
||||
break
|
||||
return result
|
||||
|
|
@ -0,0 +1,23 @@
|
|||
"""
|
||||
HTML parsing library based on the WHATWG "HTML5"
|
||||
specification. The parser is designed to be compatible with existing
|
||||
HTML found in the wild and implements well-defined error recovery that
|
||||
is largely compatible with modern desktop web browsers.
|
||||
|
||||
Example usage:
|
||||
|
||||
import html5lib
|
||||
f = open("my_document.html")
|
||||
tree = html5lib.parse(f)
|
||||
"""
|
||||
|
||||
from __future__ import absolute_import, division, unicode_literals
|
||||
|
||||
from .html5parser import HTMLParser, parse, parseFragment
|
||||
from .treebuilders import getTreeBuilder
|
||||
from .treewalkers import getTreeWalker
|
||||
from .serializer import serialize
|
||||
|
||||
__all__ = ["HTMLParser", "parse", "parseFragment", "getTreeBuilder",
|
||||
"getTreeWalker", "serialize"]
|
||||
__version__ = "1.0b3"
|
||||
3104
Darwin/lib/python3.4/site-packages/pip/_vendor/html5lib/constants.py
Normal file
3104
Darwin/lib/python3.4/site-packages/pip/_vendor/html5lib/constants.py
Normal file
File diff suppressed because it is too large
Load diff
|
|
@ -0,0 +1,12 @@
|
|||
from __future__ import absolute_import, division, unicode_literals
|
||||
|
||||
|
||||
class Filter(object):
|
||||
def __init__(self, source):
|
||||
self.source = source
|
||||
|
||||
def __iter__(self):
|
||||
return iter(self.source)
|
||||
|
||||
def __getattr__(self, name):
|
||||
return getattr(self.source, name)
|
||||
|
|
@ -0,0 +1,20 @@
|
|||
from __future__ import absolute_import, division, unicode_literals
|
||||
|
||||
from . import _base
|
||||
|
||||
try:
|
||||
from collections import OrderedDict
|
||||
except ImportError:
|
||||
from ordereddict import OrderedDict
|
||||
|
||||
|
||||
class Filter(_base.Filter):
|
||||
def __iter__(self):
|
||||
for token in _base.Filter.__iter__(self):
|
||||
if token["type"] in ("StartTag", "EmptyTag"):
|
||||
attrs = OrderedDict()
|
||||
for name, value in sorted(token["data"].items(),
|
||||
key=lambda x: x[0]):
|
||||
attrs[name] = value
|
||||
token["data"] = attrs
|
||||
yield token
|
||||
|
|
@ -0,0 +1,65 @@
|
|||
from __future__ import absolute_import, division, unicode_literals
|
||||
|
||||
from . import _base
|
||||
|
||||
|
||||
class Filter(_base.Filter):
|
||||
def __init__(self, source, encoding):
|
||||
_base.Filter.__init__(self, source)
|
||||
self.encoding = encoding
|
||||
|
||||
def __iter__(self):
|
||||
state = "pre_head"
|
||||
meta_found = (self.encoding is None)
|
||||
pending = []
|
||||
|
||||
for token in _base.Filter.__iter__(self):
|
||||
type = token["type"]
|
||||
if type == "StartTag":
|
||||
if token["name"].lower() == "head":
|
||||
state = "in_head"
|
||||
|
||||
elif type == "EmptyTag":
|
||||
if token["name"].lower() == "meta":
|
||||
# replace charset with actual encoding
|
||||
has_http_equiv_content_type = False
|
||||
for (namespace, name), value in token["data"].items():
|
||||
if namespace is not None:
|
||||
continue
|
||||
elif name.lower() == 'charset':
|
||||
token["data"][(namespace, name)] = self.encoding
|
||||
meta_found = True
|
||||
break
|
||||
elif name == 'http-equiv' and value.lower() == 'content-type':
|
||||
has_http_equiv_content_type = True
|
||||
else:
|
||||
if has_http_equiv_content_type and (None, "content") in token["data"]:
|
||||
token["data"][(None, "content")] = 'text/html; charset=%s' % self.encoding
|
||||
meta_found = True
|
||||
|
||||
elif token["name"].lower() == "head" and not meta_found:
|
||||
# insert meta into empty head
|
||||
yield {"type": "StartTag", "name": "head",
|
||||
"data": token["data"]}
|
||||
yield {"type": "EmptyTag", "name": "meta",
|
||||
"data": {(None, "charset"): self.encoding}}
|
||||
yield {"type": "EndTag", "name": "head"}
|
||||
meta_found = True
|
||||
continue
|
||||
|
||||
elif type == "EndTag":
|
||||
if token["name"].lower() == "head" and pending:
|
||||
# insert meta into head (if necessary) and flush pending queue
|
||||
yield pending.pop(0)
|
||||
if not meta_found:
|
||||
yield {"type": "EmptyTag", "name": "meta",
|
||||
"data": {(None, "charset"): self.encoding}}
|
||||
while pending:
|
||||
yield pending.pop(0)
|
||||
meta_found = True
|
||||
state = "post_head"
|
||||
|
||||
if state == "in_head":
|
||||
pending.append(token)
|
||||
else:
|
||||
yield token
|
||||
|
|
@ -0,0 +1,93 @@
|
|||
from __future__ import absolute_import, division, unicode_literals
|
||||
|
||||
from gettext import gettext
|
||||
_ = gettext
|
||||
|
||||
from . import _base
|
||||
from ..constants import cdataElements, rcdataElements, voidElements
|
||||
|
||||
from ..constants import spaceCharacters
|
||||
spaceCharacters = "".join(spaceCharacters)
|
||||
|
||||
|
||||
class LintError(Exception):
|
||||
pass
|
||||
|
||||
|
||||
class Filter(_base.Filter):
|
||||
def __iter__(self):
|
||||
open_elements = []
|
||||
contentModelFlag = "PCDATA"
|
||||
for token in _base.Filter.__iter__(self):
|
||||
type = token["type"]
|
||||
if type in ("StartTag", "EmptyTag"):
|
||||
name = token["name"]
|
||||
if contentModelFlag != "PCDATA":
|
||||
raise LintError(_("StartTag not in PCDATA content model flag: %(tag)s") % {"tag": name})
|
||||
if not isinstance(name, str):
|
||||
raise LintError(_("Tag name is not a string: %(tag)r") % {"tag": name})
|
||||
if not name:
|
||||
raise LintError(_("Empty tag name"))
|
||||
if type == "StartTag" and name in voidElements:
|
||||
raise LintError(_("Void element reported as StartTag token: %(tag)s") % {"tag": name})
|
||||
elif type == "EmptyTag" and name not in voidElements:
|
||||
raise LintError(_("Non-void element reported as EmptyTag token: %(tag)s") % {"tag": token["name"]})
|
||||
if type == "StartTag":
|
||||
open_elements.append(name)
|
||||
for name, value in token["data"]:
|
||||
if not isinstance(name, str):
|
||||
raise LintError(_("Attribute name is not a string: %(name)r") % {"name": name})
|
||||
if not name:
|
||||
raise LintError(_("Empty attribute name"))
|
||||
if not isinstance(value, str):
|
||||
raise LintError(_("Attribute value is not a string: %(value)r") % {"value": value})
|
||||
if name in cdataElements:
|
||||
contentModelFlag = "CDATA"
|
||||
elif name in rcdataElements:
|
||||
contentModelFlag = "RCDATA"
|
||||
elif name == "plaintext":
|
||||
contentModelFlag = "PLAINTEXT"
|
||||
|
||||
elif type == "EndTag":
|
||||
name = token["name"]
|
||||
if not isinstance(name, str):
|
||||
raise LintError(_("Tag name is not a string: %(tag)r") % {"tag": name})
|
||||
if not name:
|
||||
raise LintError(_("Empty tag name"))
|
||||
if name in voidElements:
|
||||
raise LintError(_("Void element reported as EndTag token: %(tag)s") % {"tag": name})
|
||||
start_name = open_elements.pop()
|
||||
if start_name != name:
|
||||
raise LintError(_("EndTag (%(end)s) does not match StartTag (%(start)s)") % {"end": name, "start": start_name})
|
||||
contentModelFlag = "PCDATA"
|
||||
|
||||
elif type == "Comment":
|
||||
if contentModelFlag != "PCDATA":
|
||||
raise LintError(_("Comment not in PCDATA content model flag"))
|
||||
|
||||
elif type in ("Characters", "SpaceCharacters"):
|
||||
data = token["data"]
|
||||
if not isinstance(data, str):
|
||||
raise LintError(_("Attribute name is not a string: %(name)r") % {"name": data})
|
||||
if not data:
|
||||
raise LintError(_("%(type)s token with empty data") % {"type": type})
|
||||
if type == "SpaceCharacters":
|
||||
data = data.strip(spaceCharacters)
|
||||
if data:
|
||||
raise LintError(_("Non-space character(s) found in SpaceCharacters token: %(token)r") % {"token": data})
|
||||
|
||||
elif type == "Doctype":
|
||||
name = token["name"]
|
||||
if contentModelFlag != "PCDATA":
|
||||
raise LintError(_("Doctype not in PCDATA content model flag: %(name)s") % {"name": name})
|
||||
if not isinstance(name, str):
|
||||
raise LintError(_("Tag name is not a string: %(tag)r") % {"tag": name})
|
||||
# XXX: what to do with token["data"] ?
|
||||
|
||||
elif type in ("ParseError", "SerializeError"):
|
||||
pass
|
||||
|
||||
else:
|
||||
raise LintError(_("Unknown token type: %(type)s") % {"type": type})
|
||||
|
||||
yield token
|
||||
|
|
@ -0,0 +1,205 @@
|
|||
from __future__ import absolute_import, division, unicode_literals
|
||||
|
||||
from . import _base
|
||||
|
||||
|
||||
class Filter(_base.Filter):
|
||||
def slider(self):
|
||||
previous1 = previous2 = None
|
||||
for token in self.source:
|
||||
if previous1 is not None:
|
||||
yield previous2, previous1, token
|
||||
previous2 = previous1
|
||||
previous1 = token
|
||||
yield previous2, previous1, None
|
||||
|
||||
def __iter__(self):
|
||||
for previous, token, next in self.slider():
|
||||
type = token["type"]
|
||||
if type == "StartTag":
|
||||
if (token["data"] or
|
||||
not self.is_optional_start(token["name"], previous, next)):
|
||||
yield token
|
||||
elif type == "EndTag":
|
||||
if not self.is_optional_end(token["name"], next):
|
||||
yield token
|
||||
else:
|
||||
yield token
|
||||
|
||||
def is_optional_start(self, tagname, previous, next):
|
||||
type = next and next["type"] or None
|
||||
if tagname in 'html':
|
||||
# An html element's start tag may be omitted if the first thing
|
||||
# inside the html element is not a space character or a comment.
|
||||
return type not in ("Comment", "SpaceCharacters")
|
||||
elif tagname == 'head':
|
||||
# A head element's start tag may be omitted if the first thing
|
||||
# inside the head element is an element.
|
||||
# XXX: we also omit the start tag if the head element is empty
|
||||
if type in ("StartTag", "EmptyTag"):
|
||||
return True
|
||||
elif type == "EndTag":
|
||||
return next["name"] == "head"
|
||||
elif tagname == 'body':
|
||||
# A body element's start tag may be omitted if the first thing
|
||||
# inside the body element is not a space character or a comment,
|
||||
# except if the first thing inside the body element is a script
|
||||
# or style element and the node immediately preceding the body
|
||||
# element is a head element whose end tag has been omitted.
|
||||
if type in ("Comment", "SpaceCharacters"):
|
||||
return False
|
||||
elif type == "StartTag":
|
||||
# XXX: we do not look at the preceding event, so we never omit
|
||||
# the body element's start tag if it's followed by a script or
|
||||
# a style element.
|
||||
return next["name"] not in ('script', 'style')
|
||||
else:
|
||||
return True
|
||||
elif tagname == 'colgroup':
|
||||
# A colgroup element's start tag may be omitted if the first thing
|
||||
# inside the colgroup element is a col element, and if the element
|
||||
# is not immediately preceeded by another colgroup element whose
|
||||
# end tag has been omitted.
|
||||
if type in ("StartTag", "EmptyTag"):
|
||||
# XXX: we do not look at the preceding event, so instead we never
|
||||
# omit the colgroup element's end tag when it is immediately
|
||||
# followed by another colgroup element. See is_optional_end.
|
||||
return next["name"] == "col"
|
||||
else:
|
||||
return False
|
||||
elif tagname == 'tbody':
|
||||
# A tbody element's start tag may be omitted if the first thing
|
||||
# inside the tbody element is a tr element, and if the element is
|
||||
# not immediately preceeded by a tbody, thead, or tfoot element
|
||||
# whose end tag has been omitted.
|
||||
if type == "StartTag":
|
||||
# omit the thead and tfoot elements' end tag when they are
|
||||
# immediately followed by a tbody element. See is_optional_end.
|
||||
if previous and previous['type'] == 'EndTag' and \
|
||||
previous['name'] in ('tbody', 'thead', 'tfoot'):
|
||||
return False
|
||||
return next["name"] == 'tr'
|
||||
else:
|
||||
return False
|
||||
return False
|
||||
|
||||
def is_optional_end(self, tagname, next):
|
||||
type = next and next["type"] or None
|
||||
if tagname in ('html', 'head', 'body'):
|
||||
# An html element's end tag may be omitted if the html element
|
||||
# is not immediately followed by a space character or a comment.
|
||||
return type not in ("Comment", "SpaceCharacters")
|
||||
elif tagname in ('li', 'optgroup', 'tr'):
|
||||
# A li element's end tag may be omitted if the li element is
|
||||
# immediately followed by another li element or if there is
|
||||
# no more content in the parent element.
|
||||
# An optgroup element's end tag may be omitted if the optgroup
|
||||
# element is immediately followed by another optgroup element,
|
||||
# or if there is no more content in the parent element.
|
||||
# A tr element's end tag may be omitted if the tr element is
|
||||
# immediately followed by another tr element, or if there is
|
||||
# no more content in the parent element.
|
||||
if type == "StartTag":
|
||||
return next["name"] == tagname
|
||||
else:
|
||||
return type == "EndTag" or type is None
|
||||
elif tagname in ('dt', 'dd'):
|
||||
# A dt element's end tag may be omitted if the dt element is
|
||||
# immediately followed by another dt element or a dd element.
|
||||
# A dd element's end tag may be omitted if the dd element is
|
||||
# immediately followed by another dd element or a dt element,
|
||||
# or if there is no more content in the parent element.
|
||||
if type == "StartTag":
|
||||
return next["name"] in ('dt', 'dd')
|
||||
elif tagname == 'dd':
|
||||
return type == "EndTag" or type is None
|
||||
else:
|
||||
return False
|
||||
elif tagname == 'p':
|
||||
# A p element's end tag may be omitted if the p element is
|
||||
# immediately followed by an address, article, aside,
|
||||
# blockquote, datagrid, dialog, dir, div, dl, fieldset,
|
||||
# footer, form, h1, h2, h3, h4, h5, h6, header, hr, menu,
|
||||
# nav, ol, p, pre, section, table, or ul, element, or if
|
||||
# there is no more content in the parent element.
|
||||
if type in ("StartTag", "EmptyTag"):
|
||||
return next["name"] in ('address', 'article', 'aside',
|
||||
'blockquote', 'datagrid', 'dialog',
|
||||
'dir', 'div', 'dl', 'fieldset', 'footer',
|
||||
'form', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6',
|
||||
'header', 'hr', 'menu', 'nav', 'ol',
|
||||
'p', 'pre', 'section', 'table', 'ul')
|
||||
else:
|
||||
return type == "EndTag" or type is None
|
||||
elif tagname == 'option':
|
||||
# An option element's end tag may be omitted if the option
|
||||
# element is immediately followed by another option element,
|
||||
# or if it is immediately followed by an <code>optgroup</code>
|
||||
# element, or if there is no more content in the parent
|
||||
# element.
|
||||
if type == "StartTag":
|
||||
return next["name"] in ('option', 'optgroup')
|
||||
else:
|
||||
return type == "EndTag" or type is None
|
||||
elif tagname in ('rt', 'rp'):
|
||||
# An rt element's end tag may be omitted if the rt element is
|
||||
# immediately followed by an rt or rp element, or if there is
|
||||
# no more content in the parent element.
|
||||
# An rp element's end tag may be omitted if the rp element is
|
||||
# immediately followed by an rt or rp element, or if there is
|
||||
# no more content in the parent element.
|
||||
if type == "StartTag":
|
||||
return next["name"] in ('rt', 'rp')
|
||||
else:
|
||||
return type == "EndTag" or type is None
|
||||
elif tagname == 'colgroup':
|
||||
# A colgroup element's end tag may be omitted if the colgroup
|
||||
# element is not immediately followed by a space character or
|
||||
# a comment.
|
||||
if type in ("Comment", "SpaceCharacters"):
|
||||
return False
|
||||
elif type == "StartTag":
|
||||
# XXX: we also look for an immediately following colgroup
|
||||
# element. See is_optional_start.
|
||||
return next["name"] != 'colgroup'
|
||||
else:
|
||||
return True
|
||||
elif tagname in ('thead', 'tbody'):
|
||||
# A thead element's end tag may be omitted if the thead element
|
||||
# is immediately followed by a tbody or tfoot element.
|
||||
# A tbody element's end tag may be omitted if the tbody element
|
||||
# is immediately followed by a tbody or tfoot element, or if
|
||||
# there is no more content in the parent element.
|
||||
# A tfoot element's end tag may be omitted if the tfoot element
|
||||
# is immediately followed by a tbody element, or if there is no
|
||||
# more content in the parent element.
|
||||
# XXX: we never omit the end tag when the following element is
|
||||
# a tbody. See is_optional_start.
|
||||
if type == "StartTag":
|
||||
return next["name"] in ['tbody', 'tfoot']
|
||||
elif tagname == 'tbody':
|
||||
return type == "EndTag" or type is None
|
||||
else:
|
||||
return False
|
||||
elif tagname == 'tfoot':
|
||||
# A tfoot element's end tag may be omitted if the tfoot element
|
||||
# is immediately followed by a tbody element, or if there is no
|
||||
# more content in the parent element.
|
||||
# XXX: we never omit the end tag when the following element is
|
||||
# a tbody. See is_optional_start.
|
||||
if type == "StartTag":
|
||||
return next["name"] == 'tbody'
|
||||
else:
|
||||
return type == "EndTag" or type is None
|
||||
elif tagname in ('td', 'th'):
|
||||
# A td element's end tag may be omitted if the td element is
|
||||
# immediately followed by a td or th element, or if there is
|
||||
# no more content in the parent element.
|
||||
# A th element's end tag may be omitted if the th element is
|
||||
# immediately followed by a td or th element, or if there is
|
||||
# no more content in the parent element.
|
||||
if type == "StartTag":
|
||||
return next["name"] in ('td', 'th')
|
||||
else:
|
||||
return type == "EndTag" or type is None
|
||||
return False
|
||||
|
|
@ -0,0 +1,12 @@
|
|||
from __future__ import absolute_import, division, unicode_literals
|
||||
|
||||
from . import _base
|
||||
from ..sanitizer import HTMLSanitizerMixin
|
||||
|
||||
|
||||
class Filter(_base.Filter, HTMLSanitizerMixin):
|
||||
def __iter__(self):
|
||||
for token in _base.Filter.__iter__(self):
|
||||
token = self.sanitize_token(token)
|
||||
if token:
|
||||
yield token
|
||||
|
|
@ -0,0 +1,38 @@
|
|||
from __future__ import absolute_import, division, unicode_literals
|
||||
|
||||
import re
|
||||
|
||||
from . import _base
|
||||
from ..constants import rcdataElements, spaceCharacters
|
||||
spaceCharacters = "".join(spaceCharacters)
|
||||
|
||||
SPACES_REGEX = re.compile("[%s]+" % spaceCharacters)
|
||||
|
||||
|
||||
class Filter(_base.Filter):
|
||||
|
||||
spacePreserveElements = frozenset(["pre", "textarea"] + list(rcdataElements))
|
||||
|
||||
def __iter__(self):
|
||||
preserve = 0
|
||||
for token in _base.Filter.__iter__(self):
|
||||
type = token["type"]
|
||||
if type == "StartTag" \
|
||||
and (preserve or token["name"] in self.spacePreserveElements):
|
||||
preserve += 1
|
||||
|
||||
elif type == "EndTag" and preserve:
|
||||
preserve -= 1
|
||||
|
||||
elif not preserve and type == "SpaceCharacters" and token["data"]:
|
||||
# Test on token["data"] above to not introduce spaces where there were not
|
||||
token["data"] = " "
|
||||
|
||||
elif not preserve and type == "Characters":
|
||||
token["data"] = collapse_spaces(token["data"])
|
||||
|
||||
yield token
|
||||
|
||||
|
||||
def collapse_spaces(text):
|
||||
return SPACES_REGEX.sub(' ', text)
|
||||
File diff suppressed because it is too large
Load diff
|
|
@ -0,0 +1,285 @@
|
|||
from __future__ import absolute_import, division, unicode_literals
|
||||
|
||||
import re
|
||||
import warnings
|
||||
|
||||
from .constants import DataLossWarning
|
||||
|
||||
baseChar = """
|
||||
[#x0041-#x005A] | [#x0061-#x007A] | [#x00C0-#x00D6] | [#x00D8-#x00F6] |
|
||||
[#x00F8-#x00FF] | [#x0100-#x0131] | [#x0134-#x013E] | [#x0141-#x0148] |
|
||||
[#x014A-#x017E] | [#x0180-#x01C3] | [#x01CD-#x01F0] | [#x01F4-#x01F5] |
|
||||
[#x01FA-#x0217] | [#x0250-#x02A8] | [#x02BB-#x02C1] | #x0386 |
|
||||
[#x0388-#x038A] | #x038C | [#x038E-#x03A1] | [#x03A3-#x03CE] |
|
||||
[#x03D0-#x03D6] | #x03DA | #x03DC | #x03DE | #x03E0 | [#x03E2-#x03F3] |
|
||||
[#x0401-#x040C] | [#x040E-#x044F] | [#x0451-#x045C] | [#x045E-#x0481] |
|
||||
[#x0490-#x04C4] | [#x04C7-#x04C8] | [#x04CB-#x04CC] | [#x04D0-#x04EB] |
|
||||
[#x04EE-#x04F5] | [#x04F8-#x04F9] | [#x0531-#x0556] | #x0559 |
|
||||
[#x0561-#x0586] | [#x05D0-#x05EA] | [#x05F0-#x05F2] | [#x0621-#x063A] |
|
||||
[#x0641-#x064A] | [#x0671-#x06B7] | [#x06BA-#x06BE] | [#x06C0-#x06CE] |
|
||||
[#x06D0-#x06D3] | #x06D5 | [#x06E5-#x06E6] | [#x0905-#x0939] | #x093D |
|
||||
[#x0958-#x0961] | [#x0985-#x098C] | [#x098F-#x0990] | [#x0993-#x09A8] |
|
||||
[#x09AA-#x09B0] | #x09B2 | [#x09B6-#x09B9] | [#x09DC-#x09DD] |
|
||||
[#x09DF-#x09E1] | [#x09F0-#x09F1] | [#x0A05-#x0A0A] | [#x0A0F-#x0A10] |
|
||||
[#x0A13-#x0A28] | [#x0A2A-#x0A30] | [#x0A32-#x0A33] | [#x0A35-#x0A36] |
|
||||
[#x0A38-#x0A39] | [#x0A59-#x0A5C] | #x0A5E | [#x0A72-#x0A74] |
|
||||
[#x0A85-#x0A8B] | #x0A8D | [#x0A8F-#x0A91] | [#x0A93-#x0AA8] |
|
||||
[#x0AAA-#x0AB0] | [#x0AB2-#x0AB3] | [#x0AB5-#x0AB9] | #x0ABD | #x0AE0 |
|
||||
[#x0B05-#x0B0C] | [#x0B0F-#x0B10] | [#x0B13-#x0B28] | [#x0B2A-#x0B30] |
|
||||
[#x0B32-#x0B33] | [#x0B36-#x0B39] | #x0B3D | [#x0B5C-#x0B5D] |
|
||||
[#x0B5F-#x0B61] | [#x0B85-#x0B8A] | [#x0B8E-#x0B90] | [#x0B92-#x0B95] |
|
||||
[#x0B99-#x0B9A] | #x0B9C | [#x0B9E-#x0B9F] | [#x0BA3-#x0BA4] |
|
||||
[#x0BA8-#x0BAA] | [#x0BAE-#x0BB5] | [#x0BB7-#x0BB9] | [#x0C05-#x0C0C] |
|
||||
[#x0C0E-#x0C10] | [#x0C12-#x0C28] | [#x0C2A-#x0C33] | [#x0C35-#x0C39] |
|
||||
[#x0C60-#x0C61] | [#x0C85-#x0C8C] | [#x0C8E-#x0C90] | [#x0C92-#x0CA8] |
|
||||
[#x0CAA-#x0CB3] | [#x0CB5-#x0CB9] | #x0CDE | [#x0CE0-#x0CE1] |
|
||||
[#x0D05-#x0D0C] | [#x0D0E-#x0D10] | [#x0D12-#x0D28] | [#x0D2A-#x0D39] |
|
||||
[#x0D60-#x0D61] | [#x0E01-#x0E2E] | #x0E30 | [#x0E32-#x0E33] |
|
||||
[#x0E40-#x0E45] | [#x0E81-#x0E82] | #x0E84 | [#x0E87-#x0E88] | #x0E8A |
|
||||
#x0E8D | [#x0E94-#x0E97] | [#x0E99-#x0E9F] | [#x0EA1-#x0EA3] | #x0EA5 |
|
||||
#x0EA7 | [#x0EAA-#x0EAB] | [#x0EAD-#x0EAE] | #x0EB0 | [#x0EB2-#x0EB3] |
|
||||
#x0EBD | [#x0EC0-#x0EC4] | [#x0F40-#x0F47] | [#x0F49-#x0F69] |
|
||||
[#x10A0-#x10C5] | [#x10D0-#x10F6] | #x1100 | [#x1102-#x1103] |
|
||||
[#x1105-#x1107] | #x1109 | [#x110B-#x110C] | [#x110E-#x1112] | #x113C |
|
||||
#x113E | #x1140 | #x114C | #x114E | #x1150 | [#x1154-#x1155] | #x1159 |
|
||||
[#x115F-#x1161] | #x1163 | #x1165 | #x1167 | #x1169 | [#x116D-#x116E] |
|
||||
[#x1172-#x1173] | #x1175 | #x119E | #x11A8 | #x11AB | [#x11AE-#x11AF] |
|
||||
[#x11B7-#x11B8] | #x11BA | [#x11BC-#x11C2] | #x11EB | #x11F0 | #x11F9 |
|
||||
[#x1E00-#x1E9B] | [#x1EA0-#x1EF9] | [#x1F00-#x1F15] | [#x1F18-#x1F1D] |
|
||||
[#x1F20-#x1F45] | [#x1F48-#x1F4D] | [#x1F50-#x1F57] | #x1F59 | #x1F5B |
|
||||
#x1F5D | [#x1F5F-#x1F7D] | [#x1F80-#x1FB4] | [#x1FB6-#x1FBC] | #x1FBE |
|
||||
[#x1FC2-#x1FC4] | [#x1FC6-#x1FCC] | [#x1FD0-#x1FD3] | [#x1FD6-#x1FDB] |
|
||||
[#x1FE0-#x1FEC] | [#x1FF2-#x1FF4] | [#x1FF6-#x1FFC] | #x2126 |
|
||||
[#x212A-#x212B] | #x212E | [#x2180-#x2182] | [#x3041-#x3094] |
|
||||
[#x30A1-#x30FA] | [#x3105-#x312C] | [#xAC00-#xD7A3]"""
|
||||
|
||||
ideographic = """[#x4E00-#x9FA5] | #x3007 | [#x3021-#x3029]"""
|
||||
|
||||
combiningCharacter = """
|
||||
[#x0300-#x0345] | [#x0360-#x0361] | [#x0483-#x0486] | [#x0591-#x05A1] |
|
||||
[#x05A3-#x05B9] | [#x05BB-#x05BD] | #x05BF | [#x05C1-#x05C2] | #x05C4 |
|
||||
[#x064B-#x0652] | #x0670 | [#x06D6-#x06DC] | [#x06DD-#x06DF] |
|
||||
[#x06E0-#x06E4] | [#x06E7-#x06E8] | [#x06EA-#x06ED] | [#x0901-#x0903] |
|
||||
#x093C | [#x093E-#x094C] | #x094D | [#x0951-#x0954] | [#x0962-#x0963] |
|
||||
[#x0981-#x0983] | #x09BC | #x09BE | #x09BF | [#x09C0-#x09C4] |
|
||||
[#x09C7-#x09C8] | [#x09CB-#x09CD] | #x09D7 | [#x09E2-#x09E3] | #x0A02 |
|
||||
#x0A3C | #x0A3E | #x0A3F | [#x0A40-#x0A42] | [#x0A47-#x0A48] |
|
||||
[#x0A4B-#x0A4D] | [#x0A70-#x0A71] | [#x0A81-#x0A83] | #x0ABC |
|
||||
[#x0ABE-#x0AC5] | [#x0AC7-#x0AC9] | [#x0ACB-#x0ACD] | [#x0B01-#x0B03] |
|
||||
#x0B3C | [#x0B3E-#x0B43] | [#x0B47-#x0B48] | [#x0B4B-#x0B4D] |
|
||||
[#x0B56-#x0B57] | [#x0B82-#x0B83] | [#x0BBE-#x0BC2] | [#x0BC6-#x0BC8] |
|
||||
[#x0BCA-#x0BCD] | #x0BD7 | [#x0C01-#x0C03] | [#x0C3E-#x0C44] |
|
||||
[#x0C46-#x0C48] | [#x0C4A-#x0C4D] | [#x0C55-#x0C56] | [#x0C82-#x0C83] |
|
||||
[#x0CBE-#x0CC4] | [#x0CC6-#x0CC8] | [#x0CCA-#x0CCD] | [#x0CD5-#x0CD6] |
|
||||
[#x0D02-#x0D03] | [#x0D3E-#x0D43] | [#x0D46-#x0D48] | [#x0D4A-#x0D4D] |
|
||||
#x0D57 | #x0E31 | [#x0E34-#x0E3A] | [#x0E47-#x0E4E] | #x0EB1 |
|
||||
[#x0EB4-#x0EB9] | [#x0EBB-#x0EBC] | [#x0EC8-#x0ECD] | [#x0F18-#x0F19] |
|
||||
#x0F35 | #x0F37 | #x0F39 | #x0F3E | #x0F3F | [#x0F71-#x0F84] |
|
||||
[#x0F86-#x0F8B] | [#x0F90-#x0F95] | #x0F97 | [#x0F99-#x0FAD] |
|
||||
[#x0FB1-#x0FB7] | #x0FB9 | [#x20D0-#x20DC] | #x20E1 | [#x302A-#x302F] |
|
||||
#x3099 | #x309A"""
|
||||
|
||||
digit = """
|
||||
[#x0030-#x0039] | [#x0660-#x0669] | [#x06F0-#x06F9] | [#x0966-#x096F] |
|
||||
[#x09E6-#x09EF] | [#x0A66-#x0A6F] | [#x0AE6-#x0AEF] | [#x0B66-#x0B6F] |
|
||||
[#x0BE7-#x0BEF] | [#x0C66-#x0C6F] | [#x0CE6-#x0CEF] | [#x0D66-#x0D6F] |
|
||||
[#x0E50-#x0E59] | [#x0ED0-#x0ED9] | [#x0F20-#x0F29]"""
|
||||
|
||||
extender = """
|
||||
#x00B7 | #x02D0 | #x02D1 | #x0387 | #x0640 | #x0E46 | #x0EC6 | #x3005 |
|
||||
#[#x3031-#x3035] | [#x309D-#x309E] | [#x30FC-#x30FE]"""
|
||||
|
||||
letter = " | ".join([baseChar, ideographic])
|
||||
|
||||
# Without the
|
||||
name = " | ".join([letter, digit, ".", "-", "_", combiningCharacter,
|
||||
extender])
|
||||
nameFirst = " | ".join([letter, "_"])
|
||||
|
||||
reChar = re.compile(r"#x([\d|A-F]{4,4})")
|
||||
reCharRange = re.compile(r"\[#x([\d|A-F]{4,4})-#x([\d|A-F]{4,4})\]")
|
||||
|
||||
|
||||
def charStringToList(chars):
|
||||
charRanges = [item.strip() for item in chars.split(" | ")]
|
||||
rv = []
|
||||
for item in charRanges:
|
||||
foundMatch = False
|
||||
for regexp in (reChar, reCharRange):
|
||||
match = regexp.match(item)
|
||||
if match is not None:
|
||||
rv.append([hexToInt(item) for item in match.groups()])
|
||||
if len(rv[-1]) == 1:
|
||||
rv[-1] = rv[-1] * 2
|
||||
foundMatch = True
|
||||
break
|
||||
if not foundMatch:
|
||||
assert len(item) == 1
|
||||
|
||||
rv.append([ord(item)] * 2)
|
||||
rv = normaliseCharList(rv)
|
||||
return rv
|
||||
|
||||
|
||||
def normaliseCharList(charList):
|
||||
charList = sorted(charList)
|
||||
for item in charList:
|
||||
assert item[1] >= item[0]
|
||||
rv = []
|
||||
i = 0
|
||||
while i < len(charList):
|
||||
j = 1
|
||||
rv.append(charList[i])
|
||||
while i + j < len(charList) and charList[i + j][0] <= rv[-1][1] + 1:
|
||||
rv[-1][1] = charList[i + j][1]
|
||||
j += 1
|
||||
i += j
|
||||
return rv
|
||||
|
||||
# We don't really support characters above the BMP :(
|
||||
max_unicode = int("FFFF", 16)
|
||||
|
||||
|
||||
def missingRanges(charList):
|
||||
rv = []
|
||||
if charList[0] != 0:
|
||||
rv.append([0, charList[0][0] - 1])
|
||||
for i, item in enumerate(charList[:-1]):
|
||||
rv.append([item[1] + 1, charList[i + 1][0] - 1])
|
||||
if charList[-1][1] != max_unicode:
|
||||
rv.append([charList[-1][1] + 1, max_unicode])
|
||||
return rv
|
||||
|
||||
|
||||
def listToRegexpStr(charList):
|
||||
rv = []
|
||||
for item in charList:
|
||||
if item[0] == item[1]:
|
||||
rv.append(escapeRegexp(chr(item[0])))
|
||||
else:
|
||||
rv.append(escapeRegexp(chr(item[0])) + "-" +
|
||||
escapeRegexp(chr(item[1])))
|
||||
return "[%s]" % "".join(rv)
|
||||
|
||||
|
||||
def hexToInt(hex_str):
|
||||
return int(hex_str, 16)
|
||||
|
||||
|
||||
def escapeRegexp(string):
|
||||
specialCharacters = (".", "^", "$", "*", "+", "?", "{", "}",
|
||||
"[", "]", "|", "(", ")", "-")
|
||||
for char in specialCharacters:
|
||||
string = string.replace(char, "\\" + char)
|
||||
|
||||
return string
|
||||
|
||||
# output from the above
|
||||
nonXmlNameBMPRegexp = re.compile('[\x00-,/:-@\\[-\\^`\\{-\xb6\xb8-\xbf\xd7\xf7\u0132-\u0133\u013f-\u0140\u0149\u017f\u01c4-\u01cc\u01f1-\u01f3\u01f6-\u01f9\u0218-\u024f\u02a9-\u02ba\u02c2-\u02cf\u02d2-\u02ff\u0346-\u035f\u0362-\u0385\u038b\u038d\u03a2\u03cf\u03d7-\u03d9\u03db\u03dd\u03df\u03e1\u03f4-\u0400\u040d\u0450\u045d\u0482\u0487-\u048f\u04c5-\u04c6\u04c9-\u04ca\u04cd-\u04cf\u04ec-\u04ed\u04f6-\u04f7\u04fa-\u0530\u0557-\u0558\u055a-\u0560\u0587-\u0590\u05a2\u05ba\u05be\u05c0\u05c3\u05c5-\u05cf\u05eb-\u05ef\u05f3-\u0620\u063b-\u063f\u0653-\u065f\u066a-\u066f\u06b8-\u06b9\u06bf\u06cf\u06d4\u06e9\u06ee-\u06ef\u06fa-\u0900\u0904\u093a-\u093b\u094e-\u0950\u0955-\u0957\u0964-\u0965\u0970-\u0980\u0984\u098d-\u098e\u0991-\u0992\u09a9\u09b1\u09b3-\u09b5\u09ba-\u09bb\u09bd\u09c5-\u09c6\u09c9-\u09ca\u09ce-\u09d6\u09d8-\u09db\u09de\u09e4-\u09e5\u09f2-\u0a01\u0a03-\u0a04\u0a0b-\u0a0e\u0a11-\u0a12\u0a29\u0a31\u0a34\u0a37\u0a3a-\u0a3b\u0a3d\u0a43-\u0a46\u0a49-\u0a4a\u0a4e-\u0a58\u0a5d\u0a5f-\u0a65\u0a75-\u0a80\u0a84\u0a8c\u0a8e\u0a92\u0aa9\u0ab1\u0ab4\u0aba-\u0abb\u0ac6\u0aca\u0ace-\u0adf\u0ae1-\u0ae5\u0af0-\u0b00\u0b04\u0b0d-\u0b0e\u0b11-\u0b12\u0b29\u0b31\u0b34-\u0b35\u0b3a-\u0b3b\u0b44-\u0b46\u0b49-\u0b4a\u0b4e-\u0b55\u0b58-\u0b5b\u0b5e\u0b62-\u0b65\u0b70-\u0b81\u0b84\u0b8b-\u0b8d\u0b91\u0b96-\u0b98\u0b9b\u0b9d\u0ba0-\u0ba2\u0ba5-\u0ba7\u0bab-\u0bad\u0bb6\u0bba-\u0bbd\u0bc3-\u0bc5\u0bc9\u0bce-\u0bd6\u0bd8-\u0be6\u0bf0-\u0c00\u0c04\u0c0d\u0c11\u0c29\u0c34\u0c3a-\u0c3d\u0c45\u0c49\u0c4e-\u0c54\u0c57-\u0c5f\u0c62-\u0c65\u0c70-\u0c81\u0c84\u0c8d\u0c91\u0ca9\u0cb4\u0cba-\u0cbd\u0cc5\u0cc9\u0cce-\u0cd4\u0cd7-\u0cdd\u0cdf\u0ce2-\u0ce5\u0cf0-\u0d01\u0d04\u0d0d\u0d11\u0d29\u0d3a-\u0d3d\u0d44-\u0d45\u0d49\u0d4e-\u0d56\u0d58-\u0d5f\u0d62-\u0d65\u0d70-\u0e00\u0e2f\u0e3b-\u0e3f\u0e4f\u0e5a-\u0e80\u0e83\u0e85-\u0e86\u0e89\u0e8b-\u0e8c\u0e8e-\u0e93\u0e98\u0ea0\u0ea4\u0ea6\u0ea8-\u0ea9\u0eac\u0eaf\u0eba\u0ebe-\u0ebf\u0ec5\u0ec7\u0ece-\u0ecf\u0eda-\u0f17\u0f1a-\u0f1f\u0f2a-\u0f34\u0f36\u0f38\u0f3a-\u0f3d\u0f48\u0f6a-\u0f70\u0f85\u0f8c-\u0f8f\u0f96\u0f98\u0fae-\u0fb0\u0fb8\u0fba-\u109f\u10c6-\u10cf\u10f7-\u10ff\u1101\u1104\u1108\u110a\u110d\u1113-\u113b\u113d\u113f\u1141-\u114b\u114d\u114f\u1151-\u1153\u1156-\u1158\u115a-\u115e\u1162\u1164\u1166\u1168\u116a-\u116c\u116f-\u1171\u1174\u1176-\u119d\u119f-\u11a7\u11a9-\u11aa\u11ac-\u11ad\u11b0-\u11b6\u11b9\u11bb\u11c3-\u11ea\u11ec-\u11ef\u11f1-\u11f8\u11fa-\u1dff\u1e9c-\u1e9f\u1efa-\u1eff\u1f16-\u1f17\u1f1e-\u1f1f\u1f46-\u1f47\u1f4e-\u1f4f\u1f58\u1f5a\u1f5c\u1f5e\u1f7e-\u1f7f\u1fb5\u1fbd\u1fbf-\u1fc1\u1fc5\u1fcd-\u1fcf\u1fd4-\u1fd5\u1fdc-\u1fdf\u1fed-\u1ff1\u1ff5\u1ffd-\u20cf\u20dd-\u20e0\u20e2-\u2125\u2127-\u2129\u212c-\u212d\u212f-\u217f\u2183-\u3004\u3006\u3008-\u3020\u3030\u3036-\u3040\u3095-\u3098\u309b-\u309c\u309f-\u30a0\u30fb\u30ff-\u3104\u312d-\u4dff\u9fa6-\uabff\ud7a4-\uffff]')
|
||||
|
||||
nonXmlNameFirstBMPRegexp = re.compile('[\x00-@\\[-\\^`\\{-\xbf\xd7\xf7\u0132-\u0133\u013f-\u0140\u0149\u017f\u01c4-\u01cc\u01f1-\u01f3\u01f6-\u01f9\u0218-\u024f\u02a9-\u02ba\u02c2-\u0385\u0387\u038b\u038d\u03a2\u03cf\u03d7-\u03d9\u03db\u03dd\u03df\u03e1\u03f4-\u0400\u040d\u0450\u045d\u0482-\u048f\u04c5-\u04c6\u04c9-\u04ca\u04cd-\u04cf\u04ec-\u04ed\u04f6-\u04f7\u04fa-\u0530\u0557-\u0558\u055a-\u0560\u0587-\u05cf\u05eb-\u05ef\u05f3-\u0620\u063b-\u0640\u064b-\u0670\u06b8-\u06b9\u06bf\u06cf\u06d4\u06d6-\u06e4\u06e7-\u0904\u093a-\u093c\u093e-\u0957\u0962-\u0984\u098d-\u098e\u0991-\u0992\u09a9\u09b1\u09b3-\u09b5\u09ba-\u09db\u09de\u09e2-\u09ef\u09f2-\u0a04\u0a0b-\u0a0e\u0a11-\u0a12\u0a29\u0a31\u0a34\u0a37\u0a3a-\u0a58\u0a5d\u0a5f-\u0a71\u0a75-\u0a84\u0a8c\u0a8e\u0a92\u0aa9\u0ab1\u0ab4\u0aba-\u0abc\u0abe-\u0adf\u0ae1-\u0b04\u0b0d-\u0b0e\u0b11-\u0b12\u0b29\u0b31\u0b34-\u0b35\u0b3a-\u0b3c\u0b3e-\u0b5b\u0b5e\u0b62-\u0b84\u0b8b-\u0b8d\u0b91\u0b96-\u0b98\u0b9b\u0b9d\u0ba0-\u0ba2\u0ba5-\u0ba7\u0bab-\u0bad\u0bb6\u0bba-\u0c04\u0c0d\u0c11\u0c29\u0c34\u0c3a-\u0c5f\u0c62-\u0c84\u0c8d\u0c91\u0ca9\u0cb4\u0cba-\u0cdd\u0cdf\u0ce2-\u0d04\u0d0d\u0d11\u0d29\u0d3a-\u0d5f\u0d62-\u0e00\u0e2f\u0e31\u0e34-\u0e3f\u0e46-\u0e80\u0e83\u0e85-\u0e86\u0e89\u0e8b-\u0e8c\u0e8e-\u0e93\u0e98\u0ea0\u0ea4\u0ea6\u0ea8-\u0ea9\u0eac\u0eaf\u0eb1\u0eb4-\u0ebc\u0ebe-\u0ebf\u0ec5-\u0f3f\u0f48\u0f6a-\u109f\u10c6-\u10cf\u10f7-\u10ff\u1101\u1104\u1108\u110a\u110d\u1113-\u113b\u113d\u113f\u1141-\u114b\u114d\u114f\u1151-\u1153\u1156-\u1158\u115a-\u115e\u1162\u1164\u1166\u1168\u116a-\u116c\u116f-\u1171\u1174\u1176-\u119d\u119f-\u11a7\u11a9-\u11aa\u11ac-\u11ad\u11b0-\u11b6\u11b9\u11bb\u11c3-\u11ea\u11ec-\u11ef\u11f1-\u11f8\u11fa-\u1dff\u1e9c-\u1e9f\u1efa-\u1eff\u1f16-\u1f17\u1f1e-\u1f1f\u1f46-\u1f47\u1f4e-\u1f4f\u1f58\u1f5a\u1f5c\u1f5e\u1f7e-\u1f7f\u1fb5\u1fbd\u1fbf-\u1fc1\u1fc5\u1fcd-\u1fcf\u1fd4-\u1fd5\u1fdc-\u1fdf\u1fed-\u1ff1\u1ff5\u1ffd-\u2125\u2127-\u2129\u212c-\u212d\u212f-\u217f\u2183-\u3006\u3008-\u3020\u302a-\u3040\u3095-\u30a0\u30fb-\u3104\u312d-\u4dff\u9fa6-\uabff\ud7a4-\uffff]')
|
||||
|
||||
# Simpler things
|
||||
nonPubidCharRegexp = re.compile("[^\x20\x0D\x0Aa-zA-Z0-9\-\'()+,./:=?;!*#@$_%]")
|
||||
|
||||
|
||||
class InfosetFilter(object):
|
||||
replacementRegexp = re.compile(r"U[\dA-F]{5,5}")
|
||||
|
||||
def __init__(self, replaceChars=None,
|
||||
dropXmlnsLocalName=False,
|
||||
dropXmlnsAttrNs=False,
|
||||
preventDoubleDashComments=False,
|
||||
preventDashAtCommentEnd=False,
|
||||
replaceFormFeedCharacters=True,
|
||||
preventSingleQuotePubid=False):
|
||||
|
||||
self.dropXmlnsLocalName = dropXmlnsLocalName
|
||||
self.dropXmlnsAttrNs = dropXmlnsAttrNs
|
||||
|
||||
self.preventDoubleDashComments = preventDoubleDashComments
|
||||
self.preventDashAtCommentEnd = preventDashAtCommentEnd
|
||||
|
||||
self.replaceFormFeedCharacters = replaceFormFeedCharacters
|
||||
|
||||
self.preventSingleQuotePubid = preventSingleQuotePubid
|
||||
|
||||
self.replaceCache = {}
|
||||
|
||||
def coerceAttribute(self, name, namespace=None):
|
||||
if self.dropXmlnsLocalName and name.startswith("xmlns:"):
|
||||
warnings.warn("Attributes cannot begin with xmlns", DataLossWarning)
|
||||
return None
|
||||
elif (self.dropXmlnsAttrNs and
|
||||
namespace == "http://www.w3.org/2000/xmlns/"):
|
||||
warnings.warn("Attributes cannot be in the xml namespace", DataLossWarning)
|
||||
return None
|
||||
else:
|
||||
return self.toXmlName(name)
|
||||
|
||||
def coerceElement(self, name, namespace=None):
|
||||
return self.toXmlName(name)
|
||||
|
||||
def coerceComment(self, data):
|
||||
if self.preventDoubleDashComments:
|
||||
while "--" in data:
|
||||
warnings.warn("Comments cannot contain adjacent dashes", DataLossWarning)
|
||||
data = data.replace("--", "- -")
|
||||
return data
|
||||
|
||||
def coerceCharacters(self, data):
|
||||
if self.replaceFormFeedCharacters:
|
||||
for i in range(data.count("\x0C")):
|
||||
warnings.warn("Text cannot contain U+000C", DataLossWarning)
|
||||
data = data.replace("\x0C", " ")
|
||||
# Other non-xml characters
|
||||
return data
|
||||
|
||||
def coercePubid(self, data):
|
||||
dataOutput = data
|
||||
for char in nonPubidCharRegexp.findall(data):
|
||||
warnings.warn("Coercing non-XML pubid", DataLossWarning)
|
||||
replacement = self.getReplacementCharacter(char)
|
||||
dataOutput = dataOutput.replace(char, replacement)
|
||||
if self.preventSingleQuotePubid and dataOutput.find("'") >= 0:
|
||||
warnings.warn("Pubid cannot contain single quote", DataLossWarning)
|
||||
dataOutput = dataOutput.replace("'", self.getReplacementCharacter("'"))
|
||||
return dataOutput
|
||||
|
||||
def toXmlName(self, name):
|
||||
nameFirst = name[0]
|
||||
nameRest = name[1:]
|
||||
m = nonXmlNameFirstBMPRegexp.match(nameFirst)
|
||||
if m:
|
||||
warnings.warn("Coercing non-XML name", DataLossWarning)
|
||||
nameFirstOutput = self.getReplacementCharacter(nameFirst)
|
||||
else:
|
||||
nameFirstOutput = nameFirst
|
||||
|
||||
nameRestOutput = nameRest
|
||||
replaceChars = set(nonXmlNameBMPRegexp.findall(nameRest))
|
||||
for char in replaceChars:
|
||||
warnings.warn("Coercing non-XML name", DataLossWarning)
|
||||
replacement = self.getReplacementCharacter(char)
|
||||
nameRestOutput = nameRestOutput.replace(char, replacement)
|
||||
return nameFirstOutput + nameRestOutput
|
||||
|
||||
def getReplacementCharacter(self, char):
|
||||
if char in self.replaceCache:
|
||||
replacement = self.replaceCache[char]
|
||||
else:
|
||||
replacement = self.escapeChar(char)
|
||||
return replacement
|
||||
|
||||
def fromXmlName(self, name):
|
||||
for item in set(self.replacementRegexp.findall(name)):
|
||||
name = name.replace(item, self.unescapeChar(item))
|
||||
return name
|
||||
|
||||
def escapeChar(self, char):
|
||||
replacement = "U%05X" % ord(char)
|
||||
self.replaceCache[char] = replacement
|
||||
return replacement
|
||||
|
||||
def unescapeChar(self, charcode):
|
||||
return chr(int(charcode[1:], 16))
|
||||
|
|
@ -0,0 +1,881 @@
|
|||
from __future__ import absolute_import, division, unicode_literals
|
||||
from pip._vendor.six import text_type
|
||||
|
||||
import codecs
|
||||
import re
|
||||
|
||||
from .constants import EOF, spaceCharacters, asciiLetters, asciiUppercase
|
||||
from .constants import encodings, ReparseException
|
||||
from . import utils
|
||||
|
||||
from io import StringIO
|
||||
|
||||
try:
|
||||
from io import BytesIO
|
||||
except ImportError:
|
||||
BytesIO = StringIO
|
||||
|
||||
try:
|
||||
from io import BufferedIOBase
|
||||
except ImportError:
|
||||
class BufferedIOBase(object):
|
||||
pass
|
||||
|
||||
# Non-unicode versions of constants for use in the pre-parser
|
||||
spaceCharactersBytes = frozenset([item.encode("ascii") for item in spaceCharacters])
|
||||
asciiLettersBytes = frozenset([item.encode("ascii") for item in asciiLetters])
|
||||
asciiUppercaseBytes = frozenset([item.encode("ascii") for item in asciiUppercase])
|
||||
spacesAngleBrackets = spaceCharactersBytes | frozenset([b">", b"<"])
|
||||
|
||||
invalid_unicode_re = re.compile("[\u0001-\u0008\u000B\u000E-\u001F\u007F-\u009F\uD800-\uDFFF\uFDD0-\uFDEF\uFFFE\uFFFF\U0001FFFE\U0001FFFF\U0002FFFE\U0002FFFF\U0003FFFE\U0003FFFF\U0004FFFE\U0004FFFF\U0005FFFE\U0005FFFF\U0006FFFE\U0006FFFF\U0007FFFE\U0007FFFF\U0008FFFE\U0008FFFF\U0009FFFE\U0009FFFF\U000AFFFE\U000AFFFF\U000BFFFE\U000BFFFF\U000CFFFE\U000CFFFF\U000DFFFE\U000DFFFF\U000EFFFE\U000EFFFF\U000FFFFE\U000FFFFF\U0010FFFE\U0010FFFF]")
|
||||
|
||||
non_bmp_invalid_codepoints = set([0x1FFFE, 0x1FFFF, 0x2FFFE, 0x2FFFF, 0x3FFFE,
|
||||
0x3FFFF, 0x4FFFE, 0x4FFFF, 0x5FFFE, 0x5FFFF,
|
||||
0x6FFFE, 0x6FFFF, 0x7FFFE, 0x7FFFF, 0x8FFFE,
|
||||
0x8FFFF, 0x9FFFE, 0x9FFFF, 0xAFFFE, 0xAFFFF,
|
||||
0xBFFFE, 0xBFFFF, 0xCFFFE, 0xCFFFF, 0xDFFFE,
|
||||
0xDFFFF, 0xEFFFE, 0xEFFFF, 0xFFFFE, 0xFFFFF,
|
||||
0x10FFFE, 0x10FFFF])
|
||||
|
||||
ascii_punctuation_re = re.compile("[\u0009-\u000D\u0020-\u002F\u003A-\u0040\u005B-\u0060\u007B-\u007E]")
|
||||
|
||||
# Cache for charsUntil()
|
||||
charsUntilRegEx = {}
|
||||
|
||||
|
||||
class BufferedStream(object):
|
||||
"""Buffering for streams that do not have buffering of their own
|
||||
|
||||
The buffer is implemented as a list of chunks on the assumption that
|
||||
joining many strings will be slow since it is O(n**2)
|
||||
"""
|
||||
|
||||
def __init__(self, stream):
|
||||
self.stream = stream
|
||||
self.buffer = []
|
||||
self.position = [-1, 0] # chunk number, offset
|
||||
|
||||
def tell(self):
|
||||
pos = 0
|
||||
for chunk in self.buffer[:self.position[0]]:
|
||||
pos += len(chunk)
|
||||
pos += self.position[1]
|
||||
return pos
|
||||
|
||||
def seek(self, pos):
|
||||
assert pos <= self._bufferedBytes()
|
||||
offset = pos
|
||||
i = 0
|
||||
while len(self.buffer[i]) < offset:
|
||||
offset -= len(self.buffer[i])
|
||||
i += 1
|
||||
self.position = [i, offset]
|
||||
|
||||
def read(self, bytes):
|
||||
if not self.buffer:
|
||||
return self._readStream(bytes)
|
||||
elif (self.position[0] == len(self.buffer) and
|
||||
self.position[1] == len(self.buffer[-1])):
|
||||
return self._readStream(bytes)
|
||||
else:
|
||||
return self._readFromBuffer(bytes)
|
||||
|
||||
def _bufferedBytes(self):
|
||||
return sum([len(item) for item in self.buffer])
|
||||
|
||||
def _readStream(self, bytes):
|
||||
data = self.stream.read(bytes)
|
||||
self.buffer.append(data)
|
||||
self.position[0] += 1
|
||||
self.position[1] = len(data)
|
||||
return data
|
||||
|
||||
def _readFromBuffer(self, bytes):
|
||||
remainingBytes = bytes
|
||||
rv = []
|
||||
bufferIndex = self.position[0]
|
||||
bufferOffset = self.position[1]
|
||||
while bufferIndex < len(self.buffer) and remainingBytes != 0:
|
||||
assert remainingBytes > 0
|
||||
bufferedData = self.buffer[bufferIndex]
|
||||
|
||||
if remainingBytes <= len(bufferedData) - bufferOffset:
|
||||
bytesToRead = remainingBytes
|
||||
self.position = [bufferIndex, bufferOffset + bytesToRead]
|
||||
else:
|
||||
bytesToRead = len(bufferedData) - bufferOffset
|
||||
self.position = [bufferIndex, len(bufferedData)]
|
||||
bufferIndex += 1
|
||||
rv.append(bufferedData[bufferOffset:bufferOffset + bytesToRead])
|
||||
remainingBytes -= bytesToRead
|
||||
|
||||
bufferOffset = 0
|
||||
|
||||
if remainingBytes:
|
||||
rv.append(self._readStream(remainingBytes))
|
||||
|
||||
return b"".join(rv)
|
||||
|
||||
|
||||
def HTMLInputStream(source, encoding=None, parseMeta=True, chardet=True):
|
||||
if hasattr(source, "read"):
|
||||
isUnicode = isinstance(source.read(0), text_type)
|
||||
else:
|
||||
isUnicode = isinstance(source, text_type)
|
||||
|
||||
if isUnicode:
|
||||
if encoding is not None:
|
||||
raise TypeError("Cannot explicitly set an encoding with a unicode string")
|
||||
|
||||
return HTMLUnicodeInputStream(source)
|
||||
else:
|
||||
return HTMLBinaryInputStream(source, encoding, parseMeta, chardet)
|
||||
|
||||
|
||||
class HTMLUnicodeInputStream(object):
|
||||
"""Provides a unicode stream of characters to the HTMLTokenizer.
|
||||
|
||||
This class takes care of character encoding and removing or replacing
|
||||
incorrect byte-sequences and also provides column and line tracking.
|
||||
|
||||
"""
|
||||
|
||||
_defaultChunkSize = 10240
|
||||
|
||||
def __init__(self, source):
|
||||
"""Initialises the HTMLInputStream.
|
||||
|
||||
HTMLInputStream(source, [encoding]) -> Normalized stream from source
|
||||
for use by html5lib.
|
||||
|
||||
source can be either a file-object, local filename or a string.
|
||||
|
||||
The optional encoding parameter must be a string that indicates
|
||||
the encoding. If specified, that encoding will be used,
|
||||
regardless of any BOM or later declaration (such as in a meta
|
||||
element)
|
||||
|
||||
parseMeta - Look for a <meta> element containing encoding information
|
||||
|
||||
"""
|
||||
|
||||
# Craziness
|
||||
if len("\U0010FFFF") == 1:
|
||||
self.reportCharacterErrors = self.characterErrorsUCS4
|
||||
self.replaceCharactersRegexp = re.compile("[\uD800-\uDFFF]")
|
||||
else:
|
||||
self.reportCharacterErrors = self.characterErrorsUCS2
|
||||
self.replaceCharactersRegexp = re.compile("([\uD800-\uDBFF](?![\uDC00-\uDFFF])|(?<![\uD800-\uDBFF])[\uDC00-\uDFFF])")
|
||||
|
||||
# List of where new lines occur
|
||||
self.newLines = [0]
|
||||
|
||||
self.charEncoding = ("utf-8", "certain")
|
||||
self.dataStream = self.openStream(source)
|
||||
|
||||
self.reset()
|
||||
|
||||
def reset(self):
|
||||
self.chunk = ""
|
||||
self.chunkSize = 0
|
||||
self.chunkOffset = 0
|
||||
self.errors = []
|
||||
|
||||
# number of (complete) lines in previous chunks
|
||||
self.prevNumLines = 0
|
||||
# number of columns in the last line of the previous chunk
|
||||
self.prevNumCols = 0
|
||||
|
||||
# Deal with CR LF and surrogates split over chunk boundaries
|
||||
self._bufferedCharacter = None
|
||||
|
||||
def openStream(self, source):
|
||||
"""Produces a file object from source.
|
||||
|
||||
source can be either a file object, local filename or a string.
|
||||
|
||||
"""
|
||||
# Already a file object
|
||||
if hasattr(source, 'read'):
|
||||
stream = source
|
||||
else:
|
||||
stream = StringIO(source)
|
||||
|
||||
return stream
|
||||
|
||||
def _position(self, offset):
|
||||
chunk = self.chunk
|
||||
nLines = chunk.count('\n', 0, offset)
|
||||
positionLine = self.prevNumLines + nLines
|
||||
lastLinePos = chunk.rfind('\n', 0, offset)
|
||||
if lastLinePos == -1:
|
||||
positionColumn = self.prevNumCols + offset
|
||||
else:
|
||||
positionColumn = offset - (lastLinePos + 1)
|
||||
return (positionLine, positionColumn)
|
||||
|
||||
def position(self):
|
||||
"""Returns (line, col) of the current position in the stream."""
|
||||
line, col = self._position(self.chunkOffset)
|
||||
return (line + 1, col)
|
||||
|
||||
def char(self):
|
||||
""" Read one character from the stream or queue if available. Return
|
||||
EOF when EOF is reached.
|
||||
"""
|
||||
# Read a new chunk from the input stream if necessary
|
||||
if self.chunkOffset >= self.chunkSize:
|
||||
if not self.readChunk():
|
||||
return EOF
|
||||
|
||||
chunkOffset = self.chunkOffset
|
||||
char = self.chunk[chunkOffset]
|
||||
self.chunkOffset = chunkOffset + 1
|
||||
|
||||
return char
|
||||
|
||||
def readChunk(self, chunkSize=None):
|
||||
if chunkSize is None:
|
||||
chunkSize = self._defaultChunkSize
|
||||
|
||||
self.prevNumLines, self.prevNumCols = self._position(self.chunkSize)
|
||||
|
||||
self.chunk = ""
|
||||
self.chunkSize = 0
|
||||
self.chunkOffset = 0
|
||||
|
||||
data = self.dataStream.read(chunkSize)
|
||||
|
||||
# Deal with CR LF and surrogates broken across chunks
|
||||
if self._bufferedCharacter:
|
||||
data = self._bufferedCharacter + data
|
||||
self._bufferedCharacter = None
|
||||
elif not data:
|
||||
# We have no more data, bye-bye stream
|
||||
return False
|
||||
|
||||
if len(data) > 1:
|
||||
lastv = ord(data[-1])
|
||||
if lastv == 0x0D or 0xD800 <= lastv <= 0xDBFF:
|
||||
self._bufferedCharacter = data[-1]
|
||||
data = data[:-1]
|
||||
|
||||
self.reportCharacterErrors(data)
|
||||
|
||||
# Replace invalid characters
|
||||
# Note U+0000 is dealt with in the tokenizer
|
||||
data = self.replaceCharactersRegexp.sub("\ufffd", data)
|
||||
|
||||
data = data.replace("\r\n", "\n")
|
||||
data = data.replace("\r", "\n")
|
||||
|
||||
self.chunk = data
|
||||
self.chunkSize = len(data)
|
||||
|
||||
return True
|
||||
|
||||
def characterErrorsUCS4(self, data):
|
||||
for i in range(len(invalid_unicode_re.findall(data))):
|
||||
self.errors.append("invalid-codepoint")
|
||||
|
||||
def characterErrorsUCS2(self, data):
|
||||
# Someone picked the wrong compile option
|
||||
# You lose
|
||||
skip = False
|
||||
for match in invalid_unicode_re.finditer(data):
|
||||
if skip:
|
||||
continue
|
||||
codepoint = ord(match.group())
|
||||
pos = match.start()
|
||||
# Pretty sure there should be endianness issues here
|
||||
if utils.isSurrogatePair(data[pos:pos + 2]):
|
||||
# We have a surrogate pair!
|
||||
char_val = utils.surrogatePairToCodepoint(data[pos:pos + 2])
|
||||
if char_val in non_bmp_invalid_codepoints:
|
||||
self.errors.append("invalid-codepoint")
|
||||
skip = True
|
||||
elif (codepoint >= 0xD800 and codepoint <= 0xDFFF and
|
||||
pos == len(data) - 1):
|
||||
self.errors.append("invalid-codepoint")
|
||||
else:
|
||||
skip = False
|
||||
self.errors.append("invalid-codepoint")
|
||||
|
||||
def charsUntil(self, characters, opposite=False):
|
||||
""" Returns a string of characters from the stream up to but not
|
||||
including any character in 'characters' or EOF. 'characters' must be
|
||||
a container that supports the 'in' method and iteration over its
|
||||
characters.
|
||||
"""
|
||||
|
||||
# Use a cache of regexps to find the required characters
|
||||
try:
|
||||
chars = charsUntilRegEx[(characters, opposite)]
|
||||
except KeyError:
|
||||
if __debug__:
|
||||
for c in characters:
|
||||
assert(ord(c) < 128)
|
||||
regex = "".join(["\\x%02x" % ord(c) for c in characters])
|
||||
if not opposite:
|
||||
regex = "^%s" % regex
|
||||
chars = charsUntilRegEx[(characters, opposite)] = re.compile("[%s]+" % regex)
|
||||
|
||||
rv = []
|
||||
|
||||
while True:
|
||||
# Find the longest matching prefix
|
||||
m = chars.match(self.chunk, self.chunkOffset)
|
||||
if m is None:
|
||||
# If nothing matched, and it wasn't because we ran out of chunk,
|
||||
# then stop
|
||||
if self.chunkOffset != self.chunkSize:
|
||||
break
|
||||
else:
|
||||
end = m.end()
|
||||
# If not the whole chunk matched, return everything
|
||||
# up to the part that didn't match
|
||||
if end != self.chunkSize:
|
||||
rv.append(self.chunk[self.chunkOffset:end])
|
||||
self.chunkOffset = end
|
||||
break
|
||||
# If the whole remainder of the chunk matched,
|
||||
# use it all and read the next chunk
|
||||
rv.append(self.chunk[self.chunkOffset:])
|
||||
if not self.readChunk():
|
||||
# Reached EOF
|
||||
break
|
||||
|
||||
r = "".join(rv)
|
||||
return r
|
||||
|
||||
def unget(self, char):
|
||||
# Only one character is allowed to be ungotten at once - it must
|
||||
# be consumed again before any further call to unget
|
||||
if char is not None:
|
||||
if self.chunkOffset == 0:
|
||||
# unget is called quite rarely, so it's a good idea to do
|
||||
# more work here if it saves a bit of work in the frequently
|
||||
# called char and charsUntil.
|
||||
# So, just prepend the ungotten character onto the current
|
||||
# chunk:
|
||||
self.chunk = char + self.chunk
|
||||
self.chunkSize += 1
|
||||
else:
|
||||
self.chunkOffset -= 1
|
||||
assert self.chunk[self.chunkOffset] == char
|
||||
|
||||
|
||||
class HTMLBinaryInputStream(HTMLUnicodeInputStream):
|
||||
"""Provides a unicode stream of characters to the HTMLTokenizer.
|
||||
|
||||
This class takes care of character encoding and removing or replacing
|
||||
incorrect byte-sequences and also provides column and line tracking.
|
||||
|
||||
"""
|
||||
|
||||
def __init__(self, source, encoding=None, parseMeta=True, chardet=True):
|
||||
"""Initialises the HTMLInputStream.
|
||||
|
||||
HTMLInputStream(source, [encoding]) -> Normalized stream from source
|
||||
for use by html5lib.
|
||||
|
||||
source can be either a file-object, local filename or a string.
|
||||
|
||||
The optional encoding parameter must be a string that indicates
|
||||
the encoding. If specified, that encoding will be used,
|
||||
regardless of any BOM or later declaration (such as in a meta
|
||||
element)
|
||||
|
||||
parseMeta - Look for a <meta> element containing encoding information
|
||||
|
||||
"""
|
||||
# Raw Stream - for unicode objects this will encode to utf-8 and set
|
||||
# self.charEncoding as appropriate
|
||||
self.rawStream = self.openStream(source)
|
||||
|
||||
HTMLUnicodeInputStream.__init__(self, self.rawStream)
|
||||
|
||||
self.charEncoding = (codecName(encoding), "certain")
|
||||
|
||||
# Encoding Information
|
||||
# Number of bytes to use when looking for a meta element with
|
||||
# encoding information
|
||||
self.numBytesMeta = 512
|
||||
# Number of bytes to use when using detecting encoding using chardet
|
||||
self.numBytesChardet = 100
|
||||
# Encoding to use if no other information can be found
|
||||
self.defaultEncoding = "windows-1252"
|
||||
|
||||
# Detect encoding iff no explicit "transport level" encoding is supplied
|
||||
if (self.charEncoding[0] is None):
|
||||
self.charEncoding = self.detectEncoding(parseMeta, chardet)
|
||||
|
||||
# Call superclass
|
||||
self.reset()
|
||||
|
||||
def reset(self):
|
||||
self.dataStream = codecs.getreader(self.charEncoding[0])(self.rawStream,
|
||||
'replace')
|
||||
HTMLUnicodeInputStream.reset(self)
|
||||
|
||||
def openStream(self, source):
|
||||
"""Produces a file object from source.
|
||||
|
||||
source can be either a file object, local filename or a string.
|
||||
|
||||
"""
|
||||
# Already a file object
|
||||
if hasattr(source, 'read'):
|
||||
stream = source
|
||||
else:
|
||||
stream = BytesIO(source)
|
||||
|
||||
try:
|
||||
stream.seek(stream.tell())
|
||||
except:
|
||||
stream = BufferedStream(stream)
|
||||
|
||||
return stream
|
||||
|
||||
def detectEncoding(self, parseMeta=True, chardet=True):
|
||||
# First look for a BOM
|
||||
# This will also read past the BOM if present
|
||||
encoding = self.detectBOM()
|
||||
confidence = "certain"
|
||||
# If there is no BOM need to look for meta elements with encoding
|
||||
# information
|
||||
if encoding is None and parseMeta:
|
||||
encoding = self.detectEncodingMeta()
|
||||
confidence = "tentative"
|
||||
# Guess with chardet, if avaliable
|
||||
if encoding is None and chardet:
|
||||
confidence = "tentative"
|
||||
try:
|
||||
try:
|
||||
from charade.universaldetector import UniversalDetector
|
||||
except ImportError:
|
||||
from chardet.universaldetector import UniversalDetector
|
||||
buffers = []
|
||||
detector = UniversalDetector()
|
||||
while not detector.done:
|
||||
buffer = self.rawStream.read(self.numBytesChardet)
|
||||
assert isinstance(buffer, bytes)
|
||||
if not buffer:
|
||||
break
|
||||
buffers.append(buffer)
|
||||
detector.feed(buffer)
|
||||
detector.close()
|
||||
encoding = detector.result['encoding']
|
||||
self.rawStream.seek(0)
|
||||
except ImportError:
|
||||
pass
|
||||
# If all else fails use the default encoding
|
||||
if encoding is None:
|
||||
confidence = "tentative"
|
||||
encoding = self.defaultEncoding
|
||||
|
||||
# Substitute for equivalent encodings:
|
||||
encodingSub = {"iso-8859-1": "windows-1252"}
|
||||
|
||||
if encoding.lower() in encodingSub:
|
||||
encoding = encodingSub[encoding.lower()]
|
||||
|
||||
return encoding, confidence
|
||||
|
||||
def changeEncoding(self, newEncoding):
|
||||
assert self.charEncoding[1] != "certain"
|
||||
newEncoding = codecName(newEncoding)
|
||||
if newEncoding in ("utf-16", "utf-16-be", "utf-16-le"):
|
||||
newEncoding = "utf-8"
|
||||
if newEncoding is None:
|
||||
return
|
||||
elif newEncoding == self.charEncoding[0]:
|
||||
self.charEncoding = (self.charEncoding[0], "certain")
|
||||
else:
|
||||
self.rawStream.seek(0)
|
||||
self.reset()
|
||||
self.charEncoding = (newEncoding, "certain")
|
||||
raise ReparseException("Encoding changed from %s to %s" % (self.charEncoding[0], newEncoding))
|
||||
|
||||
def detectBOM(self):
|
||||
"""Attempts to detect at BOM at the start of the stream. If
|
||||
an encoding can be determined from the BOM return the name of the
|
||||
encoding otherwise return None"""
|
||||
bomDict = {
|
||||
codecs.BOM_UTF8: 'utf-8',
|
||||
codecs.BOM_UTF16_LE: 'utf-16-le', codecs.BOM_UTF16_BE: 'utf-16-be',
|
||||
codecs.BOM_UTF32_LE: 'utf-32-le', codecs.BOM_UTF32_BE: 'utf-32-be'
|
||||
}
|
||||
|
||||
# Go to beginning of file and read in 4 bytes
|
||||
string = self.rawStream.read(4)
|
||||
assert isinstance(string, bytes)
|
||||
|
||||
# Try detecting the BOM using bytes from the string
|
||||
encoding = bomDict.get(string[:3]) # UTF-8
|
||||
seek = 3
|
||||
if not encoding:
|
||||
# Need to detect UTF-32 before UTF-16
|
||||
encoding = bomDict.get(string) # UTF-32
|
||||
seek = 4
|
||||
if not encoding:
|
||||
encoding = bomDict.get(string[:2]) # UTF-16
|
||||
seek = 2
|
||||
|
||||
# Set the read position past the BOM if one was found, otherwise
|
||||
# set it to the start of the stream
|
||||
self.rawStream.seek(encoding and seek or 0)
|
||||
|
||||
return encoding
|
||||
|
||||
def detectEncodingMeta(self):
|
||||
"""Report the encoding declared by the meta element
|
||||
"""
|
||||
buffer = self.rawStream.read(self.numBytesMeta)
|
||||
assert isinstance(buffer, bytes)
|
||||
parser = EncodingParser(buffer)
|
||||
self.rawStream.seek(0)
|
||||
encoding = parser.getEncoding()
|
||||
|
||||
if encoding in ("utf-16", "utf-16-be", "utf-16-le"):
|
||||
encoding = "utf-8"
|
||||
|
||||
return encoding
|
||||
|
||||
|
||||
class EncodingBytes(bytes):
|
||||
"""String-like object with an associated position and various extra methods
|
||||
If the position is ever greater than the string length then an exception is
|
||||
raised"""
|
||||
def __new__(self, value):
|
||||
assert isinstance(value, bytes)
|
||||
return bytes.__new__(self, value.lower())
|
||||
|
||||
def __init__(self, value):
|
||||
self._position = -1
|
||||
|
||||
def __iter__(self):
|
||||
return self
|
||||
|
||||
def __next__(self):
|
||||
p = self._position = self._position + 1
|
||||
if p >= len(self):
|
||||
raise StopIteration
|
||||
elif p < 0:
|
||||
raise TypeError
|
||||
return self[p:p + 1]
|
||||
|
||||
def next(self):
|
||||
# Py2 compat
|
||||
return self.__next__()
|
||||
|
||||
def previous(self):
|
||||
p = self._position
|
||||
if p >= len(self):
|
||||
raise StopIteration
|
||||
elif p < 0:
|
||||
raise TypeError
|
||||
self._position = p = p - 1
|
||||
return self[p:p + 1]
|
||||
|
||||
def setPosition(self, position):
|
||||
if self._position >= len(self):
|
||||
raise StopIteration
|
||||
self._position = position
|
||||
|
||||
def getPosition(self):
|
||||
if self._position >= len(self):
|
||||
raise StopIteration
|
||||
if self._position >= 0:
|
||||
return self._position
|
||||
else:
|
||||
return None
|
||||
|
||||
position = property(getPosition, setPosition)
|
||||
|
||||
def getCurrentByte(self):
|
||||
return self[self.position:self.position + 1]
|
||||
|
||||
currentByte = property(getCurrentByte)
|
||||
|
||||
def skip(self, chars=spaceCharactersBytes):
|
||||
"""Skip past a list of characters"""
|
||||
p = self.position # use property for the error-checking
|
||||
while p < len(self):
|
||||
c = self[p:p + 1]
|
||||
if c not in chars:
|
||||
self._position = p
|
||||
return c
|
||||
p += 1
|
||||
self._position = p
|
||||
return None
|
||||
|
||||
def skipUntil(self, chars):
|
||||
p = self.position
|
||||
while p < len(self):
|
||||
c = self[p:p + 1]
|
||||
if c in chars:
|
||||
self._position = p
|
||||
return c
|
||||
p += 1
|
||||
self._position = p
|
||||
return None
|
||||
|
||||
def matchBytes(self, bytes):
|
||||
"""Look for a sequence of bytes at the start of a string. If the bytes
|
||||
are found return True and advance the position to the byte after the
|
||||
match. Otherwise return False and leave the position alone"""
|
||||
p = self.position
|
||||
data = self[p:p + len(bytes)]
|
||||
rv = data.startswith(bytes)
|
||||
if rv:
|
||||
self.position += len(bytes)
|
||||
return rv
|
||||
|
||||
def jumpTo(self, bytes):
|
||||
"""Look for the next sequence of bytes matching a given sequence. If
|
||||
a match is found advance the position to the last byte of the match"""
|
||||
newPosition = self[self.position:].find(bytes)
|
||||
if newPosition > -1:
|
||||
# XXX: This is ugly, but I can't see a nicer way to fix this.
|
||||
if self._position == -1:
|
||||
self._position = 0
|
||||
self._position += (newPosition + len(bytes) - 1)
|
||||
return True
|
||||
else:
|
||||
raise StopIteration
|
||||
|
||||
|
||||
class EncodingParser(object):
|
||||
"""Mini parser for detecting character encoding from meta elements"""
|
||||
|
||||
def __init__(self, data):
|
||||
"""string - the data to work on for encoding detection"""
|
||||
self.data = EncodingBytes(data)
|
||||
self.encoding = None
|
||||
|
||||
def getEncoding(self):
|
||||
methodDispatch = (
|
||||
(b"<!--", self.handleComment),
|
||||
(b"<meta", self.handleMeta),
|
||||
(b"</", self.handlePossibleEndTag),
|
||||
(b"<!", self.handleOther),
|
||||
(b"<?", self.handleOther),
|
||||
(b"<", self.handlePossibleStartTag))
|
||||
for byte in self.data:
|
||||
keepParsing = True
|
||||
for key, method in methodDispatch:
|
||||
if self.data.matchBytes(key):
|
||||
try:
|
||||
keepParsing = method()
|
||||
break
|
||||
except StopIteration:
|
||||
keepParsing = False
|
||||
break
|
||||
if not keepParsing:
|
||||
break
|
||||
|
||||
return self.encoding
|
||||
|
||||
def handleComment(self):
|
||||
"""Skip over comments"""
|
||||
return self.data.jumpTo(b"-->")
|
||||
|
||||
def handleMeta(self):
|
||||
if self.data.currentByte not in spaceCharactersBytes:
|
||||
# if we have <meta not followed by a space so just keep going
|
||||
return True
|
||||
# We have a valid meta element we want to search for attributes
|
||||
hasPragma = False
|
||||
pendingEncoding = None
|
||||
while True:
|
||||
# Try to find the next attribute after the current position
|
||||
attr = self.getAttribute()
|
||||
if attr is None:
|
||||
return True
|
||||
else:
|
||||
if attr[0] == b"http-equiv":
|
||||
hasPragma = attr[1] == b"content-type"
|
||||
if hasPragma and pendingEncoding is not None:
|
||||
self.encoding = pendingEncoding
|
||||
return False
|
||||
elif attr[0] == b"charset":
|
||||
tentativeEncoding = attr[1]
|
||||
codec = codecName(tentativeEncoding)
|
||||
if codec is not None:
|
||||
self.encoding = codec
|
||||
return False
|
||||
elif attr[0] == b"content":
|
||||
contentParser = ContentAttrParser(EncodingBytes(attr[1]))
|
||||
tentativeEncoding = contentParser.parse()
|
||||
if tentativeEncoding is not None:
|
||||
codec = codecName(tentativeEncoding)
|
||||
if codec is not None:
|
||||
if hasPragma:
|
||||
self.encoding = codec
|
||||
return False
|
||||
else:
|
||||
pendingEncoding = codec
|
||||
|
||||
def handlePossibleStartTag(self):
|
||||
return self.handlePossibleTag(False)
|
||||
|
||||
def handlePossibleEndTag(self):
|
||||
next(self.data)
|
||||
return self.handlePossibleTag(True)
|
||||
|
||||
def handlePossibleTag(self, endTag):
|
||||
data = self.data
|
||||
if data.currentByte not in asciiLettersBytes:
|
||||
# If the next byte is not an ascii letter either ignore this
|
||||
# fragment (possible start tag case) or treat it according to
|
||||
# handleOther
|
||||
if endTag:
|
||||
data.previous()
|
||||
self.handleOther()
|
||||
return True
|
||||
|
||||
c = data.skipUntil(spacesAngleBrackets)
|
||||
if c == b"<":
|
||||
# return to the first step in the overall "two step" algorithm
|
||||
# reprocessing the < byte
|
||||
data.previous()
|
||||
else:
|
||||
# Read all attributes
|
||||
attr = self.getAttribute()
|
||||
while attr is not None:
|
||||
attr = self.getAttribute()
|
||||
return True
|
||||
|
||||
def handleOther(self):
|
||||
return self.data.jumpTo(b">")
|
||||
|
||||
def getAttribute(self):
|
||||
"""Return a name,value pair for the next attribute in the stream,
|
||||
if one is found, or None"""
|
||||
data = self.data
|
||||
# Step 1 (skip chars)
|
||||
c = data.skip(spaceCharactersBytes | frozenset([b"/"]))
|
||||
assert c is None or len(c) == 1
|
||||
# Step 2
|
||||
if c in (b">", None):
|
||||
return None
|
||||
# Step 3
|
||||
attrName = []
|
||||
attrValue = []
|
||||
# Step 4 attribute name
|
||||
while True:
|
||||
if c == b"=" and attrName:
|
||||
break
|
||||
elif c in spaceCharactersBytes:
|
||||
# Step 6!
|
||||
c = data.skip()
|
||||
break
|
||||
elif c in (b"/", b">"):
|
||||
return b"".join(attrName), b""
|
||||
elif c in asciiUppercaseBytes:
|
||||
attrName.append(c.lower())
|
||||
elif c is None:
|
||||
return None
|
||||
else:
|
||||
attrName.append(c)
|
||||
# Step 5
|
||||
c = next(data)
|
||||
# Step 7
|
||||
if c != b"=":
|
||||
data.previous()
|
||||
return b"".join(attrName), b""
|
||||
# Step 8
|
||||
next(data)
|
||||
# Step 9
|
||||
c = data.skip()
|
||||
# Step 10
|
||||
if c in (b"'", b'"'):
|
||||
# 10.1
|
||||
quoteChar = c
|
||||
while True:
|
||||
# 10.2
|
||||
c = next(data)
|
||||
# 10.3
|
||||
if c == quoteChar:
|
||||
next(data)
|
||||
return b"".join(attrName), b"".join(attrValue)
|
||||
# 10.4
|
||||
elif c in asciiUppercaseBytes:
|
||||
attrValue.append(c.lower())
|
||||
# 10.5
|
||||
else:
|
||||
attrValue.append(c)
|
||||
elif c == b">":
|
||||
return b"".join(attrName), b""
|
||||
elif c in asciiUppercaseBytes:
|
||||
attrValue.append(c.lower())
|
||||
elif c is None:
|
||||
return None
|
||||
else:
|
||||
attrValue.append(c)
|
||||
# Step 11
|
||||
while True:
|
||||
c = next(data)
|
||||
if c in spacesAngleBrackets:
|
||||
return b"".join(attrName), b"".join(attrValue)
|
||||
elif c in asciiUppercaseBytes:
|
||||
attrValue.append(c.lower())
|
||||
elif c is None:
|
||||
return None
|
||||
else:
|
||||
attrValue.append(c)
|
||||
|
||||
|
||||
class ContentAttrParser(object):
|
||||
def __init__(self, data):
|
||||
assert isinstance(data, bytes)
|
||||
self.data = data
|
||||
|
||||
def parse(self):
|
||||
try:
|
||||
# Check if the attr name is charset
|
||||
# otherwise return
|
||||
self.data.jumpTo(b"charset")
|
||||
self.data.position += 1
|
||||
self.data.skip()
|
||||
if not self.data.currentByte == b"=":
|
||||
# If there is no = sign keep looking for attrs
|
||||
return None
|
||||
self.data.position += 1
|
||||
self.data.skip()
|
||||
# Look for an encoding between matching quote marks
|
||||
if self.data.currentByte in (b'"', b"'"):
|
||||
quoteMark = self.data.currentByte
|
||||
self.data.position += 1
|
||||
oldPosition = self.data.position
|
||||
if self.data.jumpTo(quoteMark):
|
||||
return self.data[oldPosition:self.data.position]
|
||||
else:
|
||||
return None
|
||||
else:
|
||||
# Unquoted value
|
||||
oldPosition = self.data.position
|
||||
try:
|
||||
self.data.skipUntil(spaceCharactersBytes)
|
||||
return self.data[oldPosition:self.data.position]
|
||||
except StopIteration:
|
||||
# Return the whole remaining value
|
||||
return self.data[oldPosition:]
|
||||
except StopIteration:
|
||||
return None
|
||||
|
||||
|
||||
def codecName(encoding):
|
||||
"""Return the python codec name corresponding to an encoding or None if the
|
||||
string doesn't correspond to a valid encoding."""
|
||||
if isinstance(encoding, bytes):
|
||||
try:
|
||||
encoding = encoding.decode("ascii")
|
||||
except UnicodeDecodeError:
|
||||
return None
|
||||
if encoding:
|
||||
canonicalName = ascii_punctuation_re.sub("", encoding).lower()
|
||||
return encodings.get(canonicalName, None)
|
||||
else:
|
||||
return None
|
||||
|
|
@ -0,0 +1,271 @@
|
|||
from __future__ import absolute_import, division, unicode_literals
|
||||
|
||||
import re
|
||||
from xml.sax.saxutils import escape, unescape
|
||||
|
||||
from .tokenizer import HTMLTokenizer
|
||||
from .constants import tokenTypes
|
||||
|
||||
|
||||
class HTMLSanitizerMixin(object):
|
||||
""" sanitization of XHTML+MathML+SVG and of inline style attributes."""
|
||||
|
||||
acceptable_elements = ['a', 'abbr', 'acronym', 'address', 'area',
|
||||
'article', 'aside', 'audio', 'b', 'big', 'blockquote', 'br', 'button',
|
||||
'canvas', 'caption', 'center', 'cite', 'code', 'col', 'colgroup',
|
||||
'command', 'datagrid', 'datalist', 'dd', 'del', 'details', 'dfn',
|
||||
'dialog', 'dir', 'div', 'dl', 'dt', 'em', 'event-source', 'fieldset',
|
||||
'figcaption', 'figure', 'footer', 'font', 'form', 'header', 'h1',
|
||||
'h2', 'h3', 'h4', 'h5', 'h6', 'hr', 'i', 'img', 'input', 'ins',
|
||||
'keygen', 'kbd', 'label', 'legend', 'li', 'm', 'map', 'menu', 'meter',
|
||||
'multicol', 'nav', 'nextid', 'ol', 'output', 'optgroup', 'option',
|
||||
'p', 'pre', 'progress', 'q', 's', 'samp', 'section', 'select',
|
||||
'small', 'sound', 'source', 'spacer', 'span', 'strike', 'strong',
|
||||
'sub', 'sup', 'table', 'tbody', 'td', 'textarea', 'time', 'tfoot',
|
||||
'th', 'thead', 'tr', 'tt', 'u', 'ul', 'var', 'video']
|
||||
|
||||
mathml_elements = ['maction', 'math', 'merror', 'mfrac', 'mi',
|
||||
'mmultiscripts', 'mn', 'mo', 'mover', 'mpadded', 'mphantom',
|
||||
'mprescripts', 'mroot', 'mrow', 'mspace', 'msqrt', 'mstyle', 'msub',
|
||||
'msubsup', 'msup', 'mtable', 'mtd', 'mtext', 'mtr', 'munder',
|
||||
'munderover', 'none']
|
||||
|
||||
svg_elements = ['a', 'animate', 'animateColor', 'animateMotion',
|
||||
'animateTransform', 'clipPath', 'circle', 'defs', 'desc', 'ellipse',
|
||||
'font-face', 'font-face-name', 'font-face-src', 'g', 'glyph', 'hkern',
|
||||
'linearGradient', 'line', 'marker', 'metadata', 'missing-glyph',
|
||||
'mpath', 'path', 'polygon', 'polyline', 'radialGradient', 'rect',
|
||||
'set', 'stop', 'svg', 'switch', 'text', 'title', 'tspan', 'use']
|
||||
|
||||
acceptable_attributes = ['abbr', 'accept', 'accept-charset', 'accesskey',
|
||||
'action', 'align', 'alt', 'autocomplete', 'autofocus', 'axis',
|
||||
'background', 'balance', 'bgcolor', 'bgproperties', 'border',
|
||||
'bordercolor', 'bordercolordark', 'bordercolorlight', 'bottompadding',
|
||||
'cellpadding', 'cellspacing', 'ch', 'challenge', 'char', 'charoff',
|
||||
'choff', 'charset', 'checked', 'cite', 'class', 'clear', 'color',
|
||||
'cols', 'colspan', 'compact', 'contenteditable', 'controls', 'coords',
|
||||
'data', 'datafld', 'datapagesize', 'datasrc', 'datetime', 'default',
|
||||
'delay', 'dir', 'disabled', 'draggable', 'dynsrc', 'enctype', 'end',
|
||||
'face', 'for', 'form', 'frame', 'galleryimg', 'gutter', 'headers',
|
||||
'height', 'hidefocus', 'hidden', 'high', 'href', 'hreflang', 'hspace',
|
||||
'icon', 'id', 'inputmode', 'ismap', 'keytype', 'label', 'leftspacing',
|
||||
'lang', 'list', 'longdesc', 'loop', 'loopcount', 'loopend',
|
||||
'loopstart', 'low', 'lowsrc', 'max', 'maxlength', 'media', 'method',
|
||||
'min', 'multiple', 'name', 'nohref', 'noshade', 'nowrap', 'open',
|
||||
'optimum', 'pattern', 'ping', 'point-size', 'poster', 'pqg', 'preload',
|
||||
'prompt', 'radiogroup', 'readonly', 'rel', 'repeat-max', 'repeat-min',
|
||||
'replace', 'required', 'rev', 'rightspacing', 'rows', 'rowspan',
|
||||
'rules', 'scope', 'selected', 'shape', 'size', 'span', 'src', 'start',
|
||||
'step', 'style', 'summary', 'suppress', 'tabindex', 'target',
|
||||
'template', 'title', 'toppadding', 'type', 'unselectable', 'usemap',
|
||||
'urn', 'valign', 'value', 'variable', 'volume', 'vspace', 'vrml',
|
||||
'width', 'wrap', 'xml:lang']
|
||||
|
||||
mathml_attributes = ['actiontype', 'align', 'columnalign', 'columnalign',
|
||||
'columnalign', 'columnlines', 'columnspacing', 'columnspan', 'depth',
|
||||
'display', 'displaystyle', 'equalcolumns', 'equalrows', 'fence',
|
||||
'fontstyle', 'fontweight', 'frame', 'height', 'linethickness', 'lspace',
|
||||
'mathbackground', 'mathcolor', 'mathvariant', 'mathvariant', 'maxsize',
|
||||
'minsize', 'other', 'rowalign', 'rowalign', 'rowalign', 'rowlines',
|
||||
'rowspacing', 'rowspan', 'rspace', 'scriptlevel', 'selection',
|
||||
'separator', 'stretchy', 'width', 'width', 'xlink:href', 'xlink:show',
|
||||
'xlink:type', 'xmlns', 'xmlns:xlink']
|
||||
|
||||
svg_attributes = ['accent-height', 'accumulate', 'additive', 'alphabetic',
|
||||
'arabic-form', 'ascent', 'attributeName', 'attributeType',
|
||||
'baseProfile', 'bbox', 'begin', 'by', 'calcMode', 'cap-height',
|
||||
'class', 'clip-path', 'color', 'color-rendering', 'content', 'cx',
|
||||
'cy', 'd', 'dx', 'dy', 'descent', 'display', 'dur', 'end', 'fill',
|
||||
'fill-opacity', 'fill-rule', 'font-family', 'font-size',
|
||||
'font-stretch', 'font-style', 'font-variant', 'font-weight', 'from',
|
||||
'fx', 'fy', 'g1', 'g2', 'glyph-name', 'gradientUnits', 'hanging',
|
||||
'height', 'horiz-adv-x', 'horiz-origin-x', 'id', 'ideographic', 'k',
|
||||
'keyPoints', 'keySplines', 'keyTimes', 'lang', 'marker-end',
|
||||
'marker-mid', 'marker-start', 'markerHeight', 'markerUnits',
|
||||
'markerWidth', 'mathematical', 'max', 'min', 'name', 'offset',
|
||||
'opacity', 'orient', 'origin', 'overline-position',
|
||||
'overline-thickness', 'panose-1', 'path', 'pathLength', 'points',
|
||||
'preserveAspectRatio', 'r', 'refX', 'refY', 'repeatCount',
|
||||
'repeatDur', 'requiredExtensions', 'requiredFeatures', 'restart',
|
||||
'rotate', 'rx', 'ry', 'slope', 'stemh', 'stemv', 'stop-color',
|
||||
'stop-opacity', 'strikethrough-position', 'strikethrough-thickness',
|
||||
'stroke', 'stroke-dasharray', 'stroke-dashoffset', 'stroke-linecap',
|
||||
'stroke-linejoin', 'stroke-miterlimit', 'stroke-opacity',
|
||||
'stroke-width', 'systemLanguage', 'target', 'text-anchor', 'to',
|
||||
'transform', 'type', 'u1', 'u2', 'underline-position',
|
||||
'underline-thickness', 'unicode', 'unicode-range', 'units-per-em',
|
||||
'values', 'version', 'viewBox', 'visibility', 'width', 'widths', 'x',
|
||||
'x-height', 'x1', 'x2', 'xlink:actuate', 'xlink:arcrole',
|
||||
'xlink:href', 'xlink:role', 'xlink:show', 'xlink:title', 'xlink:type',
|
||||
'xml:base', 'xml:lang', 'xml:space', 'xmlns', 'xmlns:xlink', 'y',
|
||||
'y1', 'y2', 'zoomAndPan']
|
||||
|
||||
attr_val_is_uri = ['href', 'src', 'cite', 'action', 'longdesc', 'poster',
|
||||
'xlink:href', 'xml:base']
|
||||
|
||||
svg_attr_val_allows_ref = ['clip-path', 'color-profile', 'cursor', 'fill',
|
||||
'filter', 'marker', 'marker-start', 'marker-mid', 'marker-end',
|
||||
'mask', 'stroke']
|
||||
|
||||
svg_allow_local_href = ['altGlyph', 'animate', 'animateColor',
|
||||
'animateMotion', 'animateTransform', 'cursor', 'feImage', 'filter',
|
||||
'linearGradient', 'pattern', 'radialGradient', 'textpath', 'tref',
|
||||
'set', 'use']
|
||||
|
||||
acceptable_css_properties = ['azimuth', 'background-color',
|
||||
'border-bottom-color', 'border-collapse', 'border-color',
|
||||
'border-left-color', 'border-right-color', 'border-top-color', 'clear',
|
||||
'color', 'cursor', 'direction', 'display', 'elevation', 'float', 'font',
|
||||
'font-family', 'font-size', 'font-style', 'font-variant', 'font-weight',
|
||||
'height', 'letter-spacing', 'line-height', 'overflow', 'pause',
|
||||
'pause-after', 'pause-before', 'pitch', 'pitch-range', 'richness',
|
||||
'speak', 'speak-header', 'speak-numeral', 'speak-punctuation',
|
||||
'speech-rate', 'stress', 'text-align', 'text-decoration', 'text-indent',
|
||||
'unicode-bidi', 'vertical-align', 'voice-family', 'volume',
|
||||
'white-space', 'width']
|
||||
|
||||
acceptable_css_keywords = ['auto', 'aqua', 'black', 'block', 'blue',
|
||||
'bold', 'both', 'bottom', 'brown', 'center', 'collapse', 'dashed',
|
||||
'dotted', 'fuchsia', 'gray', 'green', '!important', 'italic', 'left',
|
||||
'lime', 'maroon', 'medium', 'none', 'navy', 'normal', 'nowrap', 'olive',
|
||||
'pointer', 'purple', 'red', 'right', 'solid', 'silver', 'teal', 'top',
|
||||
'transparent', 'underline', 'white', 'yellow']
|
||||
|
||||
acceptable_svg_properties = ['fill', 'fill-opacity', 'fill-rule',
|
||||
'stroke', 'stroke-width', 'stroke-linecap', 'stroke-linejoin',
|
||||
'stroke-opacity']
|
||||
|
||||
acceptable_protocols = ['ed2k', 'ftp', 'http', 'https', 'irc',
|
||||
'mailto', 'news', 'gopher', 'nntp', 'telnet', 'webcal',
|
||||
'xmpp', 'callto', 'feed', 'urn', 'aim', 'rsync', 'tag',
|
||||
'ssh', 'sftp', 'rtsp', 'afs']
|
||||
|
||||
# subclasses may define their own versions of these constants
|
||||
allowed_elements = acceptable_elements + mathml_elements + svg_elements
|
||||
allowed_attributes = acceptable_attributes + mathml_attributes + svg_attributes
|
||||
allowed_css_properties = acceptable_css_properties
|
||||
allowed_css_keywords = acceptable_css_keywords
|
||||
allowed_svg_properties = acceptable_svg_properties
|
||||
allowed_protocols = acceptable_protocols
|
||||
|
||||
# Sanitize the +html+, escaping all elements not in ALLOWED_ELEMENTS, and
|
||||
# stripping out all # attributes not in ALLOWED_ATTRIBUTES. Style
|
||||
# attributes are parsed, and a restricted set, # specified by
|
||||
# ALLOWED_CSS_PROPERTIES and ALLOWED_CSS_KEYWORDS, are allowed through.
|
||||
# attributes in ATTR_VAL_IS_URI are scanned, and only URI schemes specified
|
||||
# in ALLOWED_PROTOCOLS are allowed.
|
||||
#
|
||||
# sanitize_html('<script> do_nasty_stuff() </script>')
|
||||
# => <script> do_nasty_stuff() </script>
|
||||
# sanitize_html('<a href="javascript: sucker();">Click here for $100</a>')
|
||||
# => <a>Click here for $100</a>
|
||||
def sanitize_token(self, token):
|
||||
|
||||
# accommodate filters which use token_type differently
|
||||
token_type = token["type"]
|
||||
if token_type in list(tokenTypes.keys()):
|
||||
token_type = tokenTypes[token_type]
|
||||
|
||||
if token_type in (tokenTypes["StartTag"], tokenTypes["EndTag"],
|
||||
tokenTypes["EmptyTag"]):
|
||||
if token["name"] in self.allowed_elements:
|
||||
return self.allowed_token(token, token_type)
|
||||
else:
|
||||
return self.disallowed_token(token, token_type)
|
||||
elif token_type == tokenTypes["Comment"]:
|
||||
pass
|
||||
else:
|
||||
return token
|
||||
|
||||
def allowed_token(self, token, token_type):
|
||||
if "data" in token:
|
||||
attrs = dict([(name, val) for name, val in
|
||||
token["data"][::-1]
|
||||
if name in self.allowed_attributes])
|
||||
for attr in self.attr_val_is_uri:
|
||||
if attr not in attrs:
|
||||
continue
|
||||
val_unescaped = re.sub("[`\000-\040\177-\240\s]+", '',
|
||||
unescape(attrs[attr])).lower()
|
||||
# remove replacement characters from unescaped characters
|
||||
val_unescaped = val_unescaped.replace("\ufffd", "")
|
||||
if (re.match("^[a-z0-9][-+.a-z0-9]*:", val_unescaped) and
|
||||
(val_unescaped.split(':')[0] not in
|
||||
self.allowed_protocols)):
|
||||
del attrs[attr]
|
||||
for attr in self.svg_attr_val_allows_ref:
|
||||
if attr in attrs:
|
||||
attrs[attr] = re.sub(r'url\s*\(\s*[^#\s][^)]+?\)',
|
||||
' ',
|
||||
unescape(attrs[attr]))
|
||||
if (token["name"] in self.svg_allow_local_href and
|
||||
'xlink:href' in attrs and re.search('^\s*[^#\s].*',
|
||||
attrs['xlink:href'])):
|
||||
del attrs['xlink:href']
|
||||
if 'style' in attrs:
|
||||
attrs['style'] = self.sanitize_css(attrs['style'])
|
||||
token["data"] = [[name, val] for name, val in list(attrs.items())]
|
||||
return token
|
||||
|
||||
def disallowed_token(self, token, token_type):
|
||||
if token_type == tokenTypes["EndTag"]:
|
||||
token["data"] = "</%s>" % token["name"]
|
||||
elif token["data"]:
|
||||
attrs = ''.join([' %s="%s"' % (k, escape(v)) for k, v in token["data"]])
|
||||
token["data"] = "<%s%s>" % (token["name"], attrs)
|
||||
else:
|
||||
token["data"] = "<%s>" % token["name"]
|
||||
if token.get("selfClosing"):
|
||||
token["data"] = token["data"][:-1] + "/>"
|
||||
|
||||
if token["type"] in list(tokenTypes.keys()):
|
||||
token["type"] = "Characters"
|
||||
else:
|
||||
token["type"] = tokenTypes["Characters"]
|
||||
|
||||
del token["name"]
|
||||
return token
|
||||
|
||||
def sanitize_css(self, style):
|
||||
# disallow urls
|
||||
style = re.compile('url\s*\(\s*[^\s)]+?\s*\)\s*').sub(' ', style)
|
||||
|
||||
# gauntlet
|
||||
if not re.match("""^([:,;#%.\sa-zA-Z0-9!]|\w-\w|'[\s\w]+'|"[\s\w]+"|\([\d,\s]+\))*$""", style):
|
||||
return ''
|
||||
if not re.match("^\s*([-\w]+\s*:[^:;]*(;\s*|$))*$", style):
|
||||
return ''
|
||||
|
||||
clean = []
|
||||
for prop, value in re.findall("([-\w]+)\s*:\s*([^:;]*)", style):
|
||||
if not value:
|
||||
continue
|
||||
if prop.lower() in self.allowed_css_properties:
|
||||
clean.append(prop + ': ' + value + ';')
|
||||
elif prop.split('-')[0].lower() in ['background', 'border', 'margin',
|
||||
'padding']:
|
||||
for keyword in value.split():
|
||||
if not keyword in self.acceptable_css_keywords and \
|
||||
not re.match("^(#[0-9a-f]+|rgb\(\d+%?,\d*%?,?\d*%?\)?|\d{0,2}\.?\d{0,2}(cm|em|ex|in|mm|pc|pt|px|%|,|\))?)$", keyword):
|
||||
break
|
||||
else:
|
||||
clean.append(prop + ': ' + value + ';')
|
||||
elif prop.lower() in self.allowed_svg_properties:
|
||||
clean.append(prop + ': ' + value + ';')
|
||||
|
||||
return ' '.join(clean)
|
||||
|
||||
|
||||
class HTMLSanitizer(HTMLTokenizer, HTMLSanitizerMixin):
|
||||
def __init__(self, stream, encoding=None, parseMeta=True, useChardet=True,
|
||||
lowercaseElementName=False, lowercaseAttrName=False, parser=None):
|
||||
# Change case matching defaults as we only output lowercase html anyway
|
||||
# This solution doesn't seem ideal...
|
||||
HTMLTokenizer.__init__(self, stream, encoding, parseMeta, useChardet,
|
||||
lowercaseElementName, lowercaseAttrName, parser=parser)
|
||||
|
||||
def __iter__(self):
|
||||
for token in HTMLTokenizer.__iter__(self):
|
||||
token = self.sanitize_token(token)
|
||||
if token:
|
||||
yield token
|
||||
|
|
@ -0,0 +1,16 @@
|
|||
from __future__ import absolute_import, division, unicode_literals
|
||||
|
||||
from .. import treewalkers
|
||||
|
||||
from .htmlserializer import HTMLSerializer
|
||||
|
||||
|
||||
def serialize(input, tree="etree", format="html", encoding=None,
|
||||
**serializer_opts):
|
||||
# XXX: Should we cache this?
|
||||
walker = treewalkers.getTreeWalker(tree)
|
||||
if format == "html":
|
||||
s = HTMLSerializer(**serializer_opts)
|
||||
else:
|
||||
raise ValueError("type must be html")
|
||||
return s.render(walker(input), encoding)
|
||||
|
|
@ -0,0 +1,320 @@
|
|||
from __future__ import absolute_import, division, unicode_literals
|
||||
from pip._vendor.six import text_type
|
||||
|
||||
import gettext
|
||||
_ = gettext.gettext
|
||||
|
||||
try:
|
||||
from functools import reduce
|
||||
except ImportError:
|
||||
pass
|
||||
|
||||
from ..constants import voidElements, booleanAttributes, spaceCharacters
|
||||
from ..constants import rcdataElements, entities, xmlEntities
|
||||
from .. import utils
|
||||
from xml.sax.saxutils import escape
|
||||
|
||||
spaceCharacters = "".join(spaceCharacters)
|
||||
|
||||
try:
|
||||
from codecs import register_error, xmlcharrefreplace_errors
|
||||
except ImportError:
|
||||
unicode_encode_errors = "strict"
|
||||
else:
|
||||
unicode_encode_errors = "htmlentityreplace"
|
||||
|
||||
encode_entity_map = {}
|
||||
is_ucs4 = len("\U0010FFFF") == 1
|
||||
for k, v in list(entities.items()):
|
||||
# skip multi-character entities
|
||||
if ((is_ucs4 and len(v) > 1) or
|
||||
(not is_ucs4 and len(v) > 2)):
|
||||
continue
|
||||
if v != "&":
|
||||
if len(v) == 2:
|
||||
v = utils.surrogatePairToCodepoint(v)
|
||||
else:
|
||||
v = ord(v)
|
||||
if not v in encode_entity_map or k.islower():
|
||||
# prefer < over < and similarly for &, >, etc.
|
||||
encode_entity_map[v] = k
|
||||
|
||||
def htmlentityreplace_errors(exc):
|
||||
if isinstance(exc, (UnicodeEncodeError, UnicodeTranslateError)):
|
||||
res = []
|
||||
codepoints = []
|
||||
skip = False
|
||||
for i, c in enumerate(exc.object[exc.start:exc.end]):
|
||||
if skip:
|
||||
skip = False
|
||||
continue
|
||||
index = i + exc.start
|
||||
if utils.isSurrogatePair(exc.object[index:min([exc.end, index + 2])]):
|
||||
codepoint = utils.surrogatePairToCodepoint(exc.object[index:index + 2])
|
||||
skip = True
|
||||
else:
|
||||
codepoint = ord(c)
|
||||
codepoints.append(codepoint)
|
||||
for cp in codepoints:
|
||||
e = encode_entity_map.get(cp)
|
||||
if e:
|
||||
res.append("&")
|
||||
res.append(e)
|
||||
if not e.endswith(";"):
|
||||
res.append(";")
|
||||
else:
|
||||
res.append("&#x%s;" % (hex(cp)[2:]))
|
||||
return ("".join(res), exc.end)
|
||||
else:
|
||||
return xmlcharrefreplace_errors(exc)
|
||||
|
||||
register_error(unicode_encode_errors, htmlentityreplace_errors)
|
||||
|
||||
del register_error
|
||||
|
||||
|
||||
class HTMLSerializer(object):
|
||||
|
||||
# attribute quoting options
|
||||
quote_attr_values = False
|
||||
quote_char = '"'
|
||||
use_best_quote_char = True
|
||||
|
||||
# tag syntax options
|
||||
omit_optional_tags = True
|
||||
minimize_boolean_attributes = True
|
||||
use_trailing_solidus = False
|
||||
space_before_trailing_solidus = True
|
||||
|
||||
# escaping options
|
||||
escape_lt_in_attrs = False
|
||||
escape_rcdata = False
|
||||
resolve_entities = True
|
||||
|
||||
# miscellaneous options
|
||||
alphabetical_attributes = False
|
||||
inject_meta_charset = True
|
||||
strip_whitespace = False
|
||||
sanitize = False
|
||||
|
||||
options = ("quote_attr_values", "quote_char", "use_best_quote_char",
|
||||
"omit_optional_tags", "minimize_boolean_attributes",
|
||||
"use_trailing_solidus", "space_before_trailing_solidus",
|
||||
"escape_lt_in_attrs", "escape_rcdata", "resolve_entities",
|
||||
"alphabetical_attributes", "inject_meta_charset",
|
||||
"strip_whitespace", "sanitize")
|
||||
|
||||
def __init__(self, **kwargs):
|
||||
"""Initialize HTMLSerializer.
|
||||
|
||||
Keyword options (default given first unless specified) include:
|
||||
|
||||
inject_meta_charset=True|False
|
||||
Whether it insert a meta element to define the character set of the
|
||||
document.
|
||||
quote_attr_values=True|False
|
||||
Whether to quote attribute values that don't require quoting
|
||||
per HTML5 parsing rules.
|
||||
quote_char=u'"'|u"'"
|
||||
Use given quote character for attribute quoting. Default is to
|
||||
use double quote unless attribute value contains a double quote,
|
||||
in which case single quotes are used instead.
|
||||
escape_lt_in_attrs=False|True
|
||||
Whether to escape < in attribute values.
|
||||
escape_rcdata=False|True
|
||||
Whether to escape characters that need to be escaped within normal
|
||||
elements within rcdata elements such as style.
|
||||
resolve_entities=True|False
|
||||
Whether to resolve named character entities that appear in the
|
||||
source tree. The XML predefined entities < > & " '
|
||||
are unaffected by this setting.
|
||||
strip_whitespace=False|True
|
||||
Whether to remove semantically meaningless whitespace. (This
|
||||
compresses all whitespace to a single space except within pre.)
|
||||
minimize_boolean_attributes=True|False
|
||||
Shortens boolean attributes to give just the attribute value,
|
||||
for example <input disabled="disabled"> becomes <input disabled>.
|
||||
use_trailing_solidus=False|True
|
||||
Includes a close-tag slash at the end of the start tag of void
|
||||
elements (empty elements whose end tag is forbidden). E.g. <hr/>.
|
||||
space_before_trailing_solidus=True|False
|
||||
Places a space immediately before the closing slash in a tag
|
||||
using a trailing solidus. E.g. <hr />. Requires use_trailing_solidus.
|
||||
sanitize=False|True
|
||||
Strip all unsafe or unknown constructs from output.
|
||||
See `html5lib user documentation`_
|
||||
omit_optional_tags=True|False
|
||||
Omit start/end tags that are optional.
|
||||
alphabetical_attributes=False|True
|
||||
Reorder attributes to be in alphabetical order.
|
||||
|
||||
.. _html5lib user documentation: http://code.google.com/p/html5lib/wiki/UserDocumentation
|
||||
"""
|
||||
if 'quote_char' in kwargs:
|
||||
self.use_best_quote_char = False
|
||||
for attr in self.options:
|
||||
setattr(self, attr, kwargs.get(attr, getattr(self, attr)))
|
||||
self.errors = []
|
||||
self.strict = False
|
||||
|
||||
def encode(self, string):
|
||||
assert(isinstance(string, text_type))
|
||||
if self.encoding:
|
||||
return string.encode(self.encoding, unicode_encode_errors)
|
||||
else:
|
||||
return string
|
||||
|
||||
def encodeStrict(self, string):
|
||||
assert(isinstance(string, text_type))
|
||||
if self.encoding:
|
||||
return string.encode(self.encoding, "strict")
|
||||
else:
|
||||
return string
|
||||
|
||||
def serialize(self, treewalker, encoding=None):
|
||||
self.encoding = encoding
|
||||
in_cdata = False
|
||||
self.errors = []
|
||||
|
||||
if encoding and self.inject_meta_charset:
|
||||
from ..filters.inject_meta_charset import Filter
|
||||
treewalker = Filter(treewalker, encoding)
|
||||
# WhitespaceFilter should be used before OptionalTagFilter
|
||||
# for maximum efficiently of this latter filter
|
||||
if self.strip_whitespace:
|
||||
from ..filters.whitespace import Filter
|
||||
treewalker = Filter(treewalker)
|
||||
if self.sanitize:
|
||||
from ..filters.sanitizer import Filter
|
||||
treewalker = Filter(treewalker)
|
||||
if self.omit_optional_tags:
|
||||
from ..filters.optionaltags import Filter
|
||||
treewalker = Filter(treewalker)
|
||||
# Alphabetical attributes must be last, as other filters
|
||||
# could add attributes and alter the order
|
||||
if self.alphabetical_attributes:
|
||||
from ..filters.alphabeticalattributes import Filter
|
||||
treewalker = Filter(treewalker)
|
||||
|
||||
for token in treewalker:
|
||||
type = token["type"]
|
||||
if type == "Doctype":
|
||||
doctype = "<!DOCTYPE %s" % token["name"]
|
||||
|
||||
if token["publicId"]:
|
||||
doctype += ' PUBLIC "%s"' % token["publicId"]
|
||||
elif token["systemId"]:
|
||||
doctype += " SYSTEM"
|
||||
if token["systemId"]:
|
||||
if token["systemId"].find('"') >= 0:
|
||||
if token["systemId"].find("'") >= 0:
|
||||
self.serializeError(_("System identifer contains both single and double quote characters"))
|
||||
quote_char = "'"
|
||||
else:
|
||||
quote_char = '"'
|
||||
doctype += " %s%s%s" % (quote_char, token["systemId"], quote_char)
|
||||
|
||||
doctype += ">"
|
||||
yield self.encodeStrict(doctype)
|
||||
|
||||
elif type in ("Characters", "SpaceCharacters"):
|
||||
if type == "SpaceCharacters" or in_cdata:
|
||||
if in_cdata and token["data"].find("</") >= 0:
|
||||
self.serializeError(_("Unexpected </ in CDATA"))
|
||||
yield self.encode(token["data"])
|
||||
else:
|
||||
yield self.encode(escape(token["data"]))
|
||||
|
||||
elif type in ("StartTag", "EmptyTag"):
|
||||
name = token["name"]
|
||||
yield self.encodeStrict("<%s" % name)
|
||||
if name in rcdataElements and not self.escape_rcdata:
|
||||
in_cdata = True
|
||||
elif in_cdata:
|
||||
self.serializeError(_("Unexpected child element of a CDATA element"))
|
||||
for (attr_namespace, attr_name), attr_value in token["data"].items():
|
||||
# TODO: Add namespace support here
|
||||
k = attr_name
|
||||
v = attr_value
|
||||
yield self.encodeStrict(' ')
|
||||
|
||||
yield self.encodeStrict(k)
|
||||
if not self.minimize_boolean_attributes or \
|
||||
(k not in booleanAttributes.get(name, tuple())
|
||||
and k not in booleanAttributes.get("", tuple())):
|
||||
yield self.encodeStrict("=")
|
||||
if self.quote_attr_values or not v:
|
||||
quote_attr = True
|
||||
else:
|
||||
quote_attr = reduce(lambda x, y: x or (y in v),
|
||||
spaceCharacters + ">\"'=", False)
|
||||
v = v.replace("&", "&")
|
||||
if self.escape_lt_in_attrs:
|
||||
v = v.replace("<", "<")
|
||||
if quote_attr:
|
||||
quote_char = self.quote_char
|
||||
if self.use_best_quote_char:
|
||||
if "'" in v and '"' not in v:
|
||||
quote_char = '"'
|
||||
elif '"' in v and "'" not in v:
|
||||
quote_char = "'"
|
||||
if quote_char == "'":
|
||||
v = v.replace("'", "'")
|
||||
else:
|
||||
v = v.replace('"', """)
|
||||
yield self.encodeStrict(quote_char)
|
||||
yield self.encode(v)
|
||||
yield self.encodeStrict(quote_char)
|
||||
else:
|
||||
yield self.encode(v)
|
||||
if name in voidElements and self.use_trailing_solidus:
|
||||
if self.space_before_trailing_solidus:
|
||||
yield self.encodeStrict(" /")
|
||||
else:
|
||||
yield self.encodeStrict("/")
|
||||
yield self.encode(">")
|
||||
|
||||
elif type == "EndTag":
|
||||
name = token["name"]
|
||||
if name in rcdataElements:
|
||||
in_cdata = False
|
||||
elif in_cdata:
|
||||
self.serializeError(_("Unexpected child element of a CDATA element"))
|
||||
yield self.encodeStrict("</%s>" % name)
|
||||
|
||||
elif type == "Comment":
|
||||
data = token["data"]
|
||||
if data.find("--") >= 0:
|
||||
self.serializeError(_("Comment contains --"))
|
||||
yield self.encodeStrict("<!--%s-->" % token["data"])
|
||||
|
||||
elif type == "Entity":
|
||||
name = token["name"]
|
||||
key = name + ";"
|
||||
if not key in entities:
|
||||
self.serializeError(_("Entity %s not recognized" % name))
|
||||
if self.resolve_entities and key not in xmlEntities:
|
||||
data = entities[key]
|
||||
else:
|
||||
data = "&%s;" % name
|
||||
yield self.encodeStrict(data)
|
||||
|
||||
else:
|
||||
self.serializeError(token["data"])
|
||||
|
||||
def render(self, treewalker, encoding=None):
|
||||
if encoding:
|
||||
return b"".join(list(self.serialize(treewalker, encoding)))
|
||||
else:
|
||||
return "".join(list(self.serialize(treewalker)))
|
||||
|
||||
def serializeError(self, data="XXX ERROR MESSAGE NEEDED"):
|
||||
# XXX The idea is to make data mandatory.
|
||||
self.errors.append(data)
|
||||
if self.strict:
|
||||
raise SerializeError
|
||||
|
||||
|
||||
def SerializeError(Exception):
|
||||
"""Error in serialized tree"""
|
||||
pass
|
||||
1731
Darwin/lib/python3.4/site-packages/pip/_vendor/html5lib/tokenizer.py
Normal file
1731
Darwin/lib/python3.4/site-packages/pip/_vendor/html5lib/tokenizer.py
Normal file
File diff suppressed because it is too large
Load diff
|
|
@ -0,0 +1,44 @@
|
|||
from __future__ import absolute_import, division, unicode_literals
|
||||
|
||||
from xml.sax.xmlreader import AttributesNSImpl
|
||||
|
||||
from ..constants import adjustForeignAttributes, unadjustForeignAttributes
|
||||
|
||||
prefix_mapping = {}
|
||||
for prefix, localName, namespace in adjustForeignAttributes.values():
|
||||
if prefix is not None:
|
||||
prefix_mapping[prefix] = namespace
|
||||
|
||||
|
||||
def to_sax(walker, handler):
|
||||
"""Call SAX-like content handler based on treewalker walker"""
|
||||
handler.startDocument()
|
||||
for prefix, namespace in prefix_mapping.items():
|
||||
handler.startPrefixMapping(prefix, namespace)
|
||||
|
||||
for token in walker:
|
||||
type = token["type"]
|
||||
if type == "Doctype":
|
||||
continue
|
||||
elif type in ("StartTag", "EmptyTag"):
|
||||
attrs = AttributesNSImpl(token["data"],
|
||||
unadjustForeignAttributes)
|
||||
handler.startElementNS((token["namespace"], token["name"]),
|
||||
token["name"],
|
||||
attrs)
|
||||
if type == "EmptyTag":
|
||||
handler.endElementNS((token["namespace"], token["name"]),
|
||||
token["name"])
|
||||
elif type == "EndTag":
|
||||
handler.endElementNS((token["namespace"], token["name"]),
|
||||
token["name"])
|
||||
elif type in ("Characters", "SpaceCharacters"):
|
||||
handler.characters(token["data"])
|
||||
elif type == "Comment":
|
||||
pass
|
||||
else:
|
||||
assert False, "Unknown token type"
|
||||
|
||||
for prefix, namespace in prefix_mapping.items():
|
||||
handler.endPrefixMapping(prefix)
|
||||
handler.endDocument()
|
||||
|
|
@ -0,0 +1,76 @@
|
|||
"""A collection of modules for building different kinds of tree from
|
||||
HTML documents.
|
||||
|
||||
To create a treebuilder for a new type of tree, you need to do
|
||||
implement several things:
|
||||
|
||||
1) A set of classes for various types of elements: Document, Doctype,
|
||||
Comment, Element. These must implement the interface of
|
||||
_base.treebuilders.Node (although comment nodes have a different
|
||||
signature for their constructor, see treebuilders.etree.Comment)
|
||||
Textual content may also be implemented as another node type, or not, as
|
||||
your tree implementation requires.
|
||||
|
||||
2) A treebuilder object (called TreeBuilder by convention) that
|
||||
inherits from treebuilders._base.TreeBuilder. This has 4 required attributes:
|
||||
documentClass - the class to use for the bottommost node of a document
|
||||
elementClass - the class to use for HTML Elements
|
||||
commentClass - the class to use for comments
|
||||
doctypeClass - the class to use for doctypes
|
||||
It also has one required method:
|
||||
getDocument - Returns the root node of the complete document tree
|
||||
|
||||
3) If you wish to run the unit tests, you must also create a
|
||||
testSerializer method on your treebuilder which accepts a node and
|
||||
returns a string containing Node and its children serialized according
|
||||
to the format used in the unittests
|
||||
"""
|
||||
|
||||
from __future__ import absolute_import, division, unicode_literals
|
||||
|
||||
from ..utils import default_etree
|
||||
|
||||
treeBuilderCache = {}
|
||||
|
||||
|
||||
def getTreeBuilder(treeType, implementation=None, **kwargs):
|
||||
"""Get a TreeBuilder class for various types of tree with built-in support
|
||||
|
||||
treeType - the name of the tree type required (case-insensitive). Supported
|
||||
values are:
|
||||
|
||||
"dom" - A generic builder for DOM implementations, defaulting to
|
||||
a xml.dom.minidom based implementation.
|
||||
"etree" - A generic builder for tree implementations exposing an
|
||||
ElementTree-like interface, defaulting to
|
||||
xml.etree.cElementTree if available and
|
||||
xml.etree.ElementTree if not.
|
||||
"lxml" - A etree-based builder for lxml.etree, handling
|
||||
limitations of lxml's implementation.
|
||||
|
||||
implementation - (Currently applies to the "etree" and "dom" tree types). A
|
||||
module implementing the tree type e.g.
|
||||
xml.etree.ElementTree or xml.etree.cElementTree."""
|
||||
|
||||
treeType = treeType.lower()
|
||||
if treeType not in treeBuilderCache:
|
||||
if treeType == "dom":
|
||||
from . import dom
|
||||
# Come up with a sane default (pref. from the stdlib)
|
||||
if implementation is None:
|
||||
from xml.dom import minidom
|
||||
implementation = minidom
|
||||
# NEVER cache here, caching is done in the dom submodule
|
||||
return dom.getDomModule(implementation, **kwargs).TreeBuilder
|
||||
elif treeType == "lxml":
|
||||
from . import etree_lxml
|
||||
treeBuilderCache[treeType] = etree_lxml.TreeBuilder
|
||||
elif treeType == "etree":
|
||||
from . import etree
|
||||
if implementation is None:
|
||||
implementation = default_etree
|
||||
# NEVER cache here, caching is done in the etree submodule
|
||||
return etree.getETreeModule(implementation, **kwargs).TreeBuilder
|
||||
else:
|
||||
raise ValueError("""Unrecognised treebuilder "%s" """ % treeType)
|
||||
return treeBuilderCache.get(treeType)
|
||||
|
|
@ -0,0 +1,377 @@
|
|||
from __future__ import absolute_import, division, unicode_literals
|
||||
from pip._vendor.six import text_type
|
||||
|
||||
from ..constants import scopingElements, tableInsertModeElements, namespaces
|
||||
|
||||
# The scope markers are inserted when entering object elements,
|
||||
# marquees, table cells, and table captions, and are used to prevent formatting
|
||||
# from "leaking" into tables, object elements, and marquees.
|
||||
Marker = None
|
||||
|
||||
listElementsMap = {
|
||||
None: (frozenset(scopingElements), False),
|
||||
"button": (frozenset(scopingElements | set([(namespaces["html"], "button")])), False),
|
||||
"list": (frozenset(scopingElements | set([(namespaces["html"], "ol"),
|
||||
(namespaces["html"], "ul")])), False),
|
||||
"table": (frozenset([(namespaces["html"], "html"),
|
||||
(namespaces["html"], "table")]), False),
|
||||
"select": (frozenset([(namespaces["html"], "optgroup"),
|
||||
(namespaces["html"], "option")]), True)
|
||||
}
|
||||
|
||||
|
||||
class Node(object):
|
||||
def __init__(self, name):
|
||||
"""Node representing an item in the tree.
|
||||
name - The tag name associated with the node
|
||||
parent - The parent of the current node (or None for the document node)
|
||||
value - The value of the current node (applies to text nodes and
|
||||
comments
|
||||
attributes - a dict holding name, value pairs for attributes of the node
|
||||
childNodes - a list of child nodes of the current node. This must
|
||||
include all elements but not necessarily other node types
|
||||
_flags - A list of miscellaneous flags that can be set on the node
|
||||
"""
|
||||
self.name = name
|
||||
self.parent = None
|
||||
self.value = None
|
||||
self.attributes = {}
|
||||
self.childNodes = []
|
||||
self._flags = []
|
||||
|
||||
def __str__(self):
|
||||
attributesStr = " ".join(["%s=\"%s\"" % (name, value)
|
||||
for name, value in
|
||||
self.attributes.items()])
|
||||
if attributesStr:
|
||||
return "<%s %s>" % (self.name, attributesStr)
|
||||
else:
|
||||
return "<%s>" % (self.name)
|
||||
|
||||
def __repr__(self):
|
||||
return "<%s>" % (self.name)
|
||||
|
||||
def appendChild(self, node):
|
||||
"""Insert node as a child of the current node
|
||||
"""
|
||||
raise NotImplementedError
|
||||
|
||||
def insertText(self, data, insertBefore=None):
|
||||
"""Insert data as text in the current node, positioned before the
|
||||
start of node insertBefore or to the end of the node's text.
|
||||
"""
|
||||
raise NotImplementedError
|
||||
|
||||
def insertBefore(self, node, refNode):
|
||||
"""Insert node as a child of the current node, before refNode in the
|
||||
list of child nodes. Raises ValueError if refNode is not a child of
|
||||
the current node"""
|
||||
raise NotImplementedError
|
||||
|
||||
def removeChild(self, node):
|
||||
"""Remove node from the children of the current node
|
||||
"""
|
||||
raise NotImplementedError
|
||||
|
||||
def reparentChildren(self, newParent):
|
||||
"""Move all the children of the current node to newParent.
|
||||
This is needed so that trees that don't store text as nodes move the
|
||||
text in the correct way
|
||||
"""
|
||||
# XXX - should this method be made more general?
|
||||
for child in self.childNodes:
|
||||
newParent.appendChild(child)
|
||||
self.childNodes = []
|
||||
|
||||
def cloneNode(self):
|
||||
"""Return a shallow copy of the current node i.e. a node with the same
|
||||
name and attributes but with no parent or child nodes
|
||||
"""
|
||||
raise NotImplementedError
|
||||
|
||||
def hasContent(self):
|
||||
"""Return true if the node has children or text, false otherwise
|
||||
"""
|
||||
raise NotImplementedError
|
||||
|
||||
|
||||
class ActiveFormattingElements(list):
|
||||
def append(self, node):
|
||||
equalCount = 0
|
||||
if node != Marker:
|
||||
for element in self[::-1]:
|
||||
if element == Marker:
|
||||
break
|
||||
if self.nodesEqual(element, node):
|
||||
equalCount += 1
|
||||
if equalCount == 3:
|
||||
self.remove(element)
|
||||
break
|
||||
list.append(self, node)
|
||||
|
||||
def nodesEqual(self, node1, node2):
|
||||
if not node1.nameTuple == node2.nameTuple:
|
||||
return False
|
||||
|
||||
if not node1.attributes == node2.attributes:
|
||||
return False
|
||||
|
||||
return True
|
||||
|
||||
|
||||
class TreeBuilder(object):
|
||||
"""Base treebuilder implementation
|
||||
documentClass - the class to use for the bottommost node of a document
|
||||
elementClass - the class to use for HTML Elements
|
||||
commentClass - the class to use for comments
|
||||
doctypeClass - the class to use for doctypes
|
||||
"""
|
||||
|
||||
# Document class
|
||||
documentClass = None
|
||||
|
||||
# The class to use for creating a node
|
||||
elementClass = None
|
||||
|
||||
# The class to use for creating comments
|
||||
commentClass = None
|
||||
|
||||
# The class to use for creating doctypes
|
||||
doctypeClass = None
|
||||
|
||||
# Fragment class
|
||||
fragmentClass = None
|
||||
|
||||
def __init__(self, namespaceHTMLElements):
|
||||
if namespaceHTMLElements:
|
||||
self.defaultNamespace = "http://www.w3.org/1999/xhtml"
|
||||
else:
|
||||
self.defaultNamespace = None
|
||||
self.reset()
|
||||
|
||||
def reset(self):
|
||||
self.openElements = []
|
||||
self.activeFormattingElements = ActiveFormattingElements()
|
||||
|
||||
# XXX - rename these to headElement, formElement
|
||||
self.headPointer = None
|
||||
self.formPointer = None
|
||||
|
||||
self.insertFromTable = False
|
||||
|
||||
self.document = self.documentClass()
|
||||
|
||||
def elementInScope(self, target, variant=None):
|
||||
|
||||
# If we pass a node in we match that. if we pass a string
|
||||
# match any node with that name
|
||||
exactNode = hasattr(target, "nameTuple")
|
||||
|
||||
listElements, invert = listElementsMap[variant]
|
||||
|
||||
for node in reversed(self.openElements):
|
||||
if (node.name == target and not exactNode or
|
||||
node == target and exactNode):
|
||||
return True
|
||||
elif (invert ^ (node.nameTuple in listElements)):
|
||||
return False
|
||||
|
||||
assert False # We should never reach this point
|
||||
|
||||
def reconstructActiveFormattingElements(self):
|
||||
# Within this algorithm the order of steps described in the
|
||||
# specification is not quite the same as the order of steps in the
|
||||
# code. It should still do the same though.
|
||||
|
||||
# Step 1: stop the algorithm when there's nothing to do.
|
||||
if not self.activeFormattingElements:
|
||||
return
|
||||
|
||||
# Step 2 and step 3: we start with the last element. So i is -1.
|
||||
i = len(self.activeFormattingElements) - 1
|
||||
entry = self.activeFormattingElements[i]
|
||||
if entry == Marker or entry in self.openElements:
|
||||
return
|
||||
|
||||
# Step 6
|
||||
while entry != Marker and entry not in self.openElements:
|
||||
if i == 0:
|
||||
# This will be reset to 0 below
|
||||
i = -1
|
||||
break
|
||||
i -= 1
|
||||
# Step 5: let entry be one earlier in the list.
|
||||
entry = self.activeFormattingElements[i]
|
||||
|
||||
while True:
|
||||
# Step 7
|
||||
i += 1
|
||||
|
||||
# Step 8
|
||||
entry = self.activeFormattingElements[i]
|
||||
clone = entry.cloneNode() # Mainly to get a new copy of the attributes
|
||||
|
||||
# Step 9
|
||||
element = self.insertElement({"type": "StartTag",
|
||||
"name": clone.name,
|
||||
"namespace": clone.namespace,
|
||||
"data": clone.attributes})
|
||||
|
||||
# Step 10
|
||||
self.activeFormattingElements[i] = element
|
||||
|
||||
# Step 11
|
||||
if element == self.activeFormattingElements[-1]:
|
||||
break
|
||||
|
||||
def clearActiveFormattingElements(self):
|
||||
entry = self.activeFormattingElements.pop()
|
||||
while self.activeFormattingElements and entry != Marker:
|
||||
entry = self.activeFormattingElements.pop()
|
||||
|
||||
def elementInActiveFormattingElements(self, name):
|
||||
"""Check if an element exists between the end of the active
|
||||
formatting elements and the last marker. If it does, return it, else
|
||||
return false"""
|
||||
|
||||
for item in self.activeFormattingElements[::-1]:
|
||||
# Check for Marker first because if it's a Marker it doesn't have a
|
||||
# name attribute.
|
||||
if item == Marker:
|
||||
break
|
||||
elif item.name == name:
|
||||
return item
|
||||
return False
|
||||
|
||||
def insertRoot(self, token):
|
||||
element = self.createElement(token)
|
||||
self.openElements.append(element)
|
||||
self.document.appendChild(element)
|
||||
|
||||
def insertDoctype(self, token):
|
||||
name = token["name"]
|
||||
publicId = token["publicId"]
|
||||
systemId = token["systemId"]
|
||||
|
||||
doctype = self.doctypeClass(name, publicId, systemId)
|
||||
self.document.appendChild(doctype)
|
||||
|
||||
def insertComment(self, token, parent=None):
|
||||
if parent is None:
|
||||
parent = self.openElements[-1]
|
||||
parent.appendChild(self.commentClass(token["data"]))
|
||||
|
||||
def createElement(self, token):
|
||||
"""Create an element but don't insert it anywhere"""
|
||||
name = token["name"]
|
||||
namespace = token.get("namespace", self.defaultNamespace)
|
||||
element = self.elementClass(name, namespace)
|
||||
element.attributes = token["data"]
|
||||
return element
|
||||
|
||||
def _getInsertFromTable(self):
|
||||
return self._insertFromTable
|
||||
|
||||
def _setInsertFromTable(self, value):
|
||||
"""Switch the function used to insert an element from the
|
||||
normal one to the misnested table one and back again"""
|
||||
self._insertFromTable = value
|
||||
if value:
|
||||
self.insertElement = self.insertElementTable
|
||||
else:
|
||||
self.insertElement = self.insertElementNormal
|
||||
|
||||
insertFromTable = property(_getInsertFromTable, _setInsertFromTable)
|
||||
|
||||
def insertElementNormal(self, token):
|
||||
name = token["name"]
|
||||
assert isinstance(name, text_type), "Element %s not unicode" % name
|
||||
namespace = token.get("namespace", self.defaultNamespace)
|
||||
element = self.elementClass(name, namespace)
|
||||
element.attributes = token["data"]
|
||||
self.openElements[-1].appendChild(element)
|
||||
self.openElements.append(element)
|
||||
return element
|
||||
|
||||
def insertElementTable(self, token):
|
||||
"""Create an element and insert it into the tree"""
|
||||
element = self.createElement(token)
|
||||
if self.openElements[-1].name not in tableInsertModeElements:
|
||||
return self.insertElementNormal(token)
|
||||
else:
|
||||
# We should be in the InTable mode. This means we want to do
|
||||
# special magic element rearranging
|
||||
parent, insertBefore = self.getTableMisnestedNodePosition()
|
||||
if insertBefore is None:
|
||||
parent.appendChild(element)
|
||||
else:
|
||||
parent.insertBefore(element, insertBefore)
|
||||
self.openElements.append(element)
|
||||
return element
|
||||
|
||||
def insertText(self, data, parent=None):
|
||||
"""Insert text data."""
|
||||
if parent is None:
|
||||
parent = self.openElements[-1]
|
||||
|
||||
if (not self.insertFromTable or (self.insertFromTable and
|
||||
self.openElements[-1].name
|
||||
not in tableInsertModeElements)):
|
||||
parent.insertText(data)
|
||||
else:
|
||||
# We should be in the InTable mode. This means we want to do
|
||||
# special magic element rearranging
|
||||
parent, insertBefore = self.getTableMisnestedNodePosition()
|
||||
parent.insertText(data, insertBefore)
|
||||
|
||||
def getTableMisnestedNodePosition(self):
|
||||
"""Get the foster parent element, and sibling to insert before
|
||||
(or None) when inserting a misnested table node"""
|
||||
# The foster parent element is the one which comes before the most
|
||||
# recently opened table element
|
||||
# XXX - this is really inelegant
|
||||
lastTable = None
|
||||
fosterParent = None
|
||||
insertBefore = None
|
||||
for elm in self.openElements[::-1]:
|
||||
if elm.name == "table":
|
||||
lastTable = elm
|
||||
break
|
||||
if lastTable:
|
||||
# XXX - we should really check that this parent is actually a
|
||||
# node here
|
||||
if lastTable.parent:
|
||||
fosterParent = lastTable.parent
|
||||
insertBefore = lastTable
|
||||
else:
|
||||
fosterParent = self.openElements[
|
||||
self.openElements.index(lastTable) - 1]
|
||||
else:
|
||||
fosterParent = self.openElements[0]
|
||||
return fosterParent, insertBefore
|
||||
|
||||
def generateImpliedEndTags(self, exclude=None):
|
||||
name = self.openElements[-1].name
|
||||
# XXX td, th and tr are not actually needed
|
||||
if (name in frozenset(("dd", "dt", "li", "option", "optgroup", "p", "rp", "rt"))
|
||||
and name != exclude):
|
||||
self.openElements.pop()
|
||||
# XXX This is not entirely what the specification says. We should
|
||||
# investigate it more closely.
|
||||
self.generateImpliedEndTags(exclude)
|
||||
|
||||
def getDocument(self):
|
||||
"Return the final tree"
|
||||
return self.document
|
||||
|
||||
def getFragment(self):
|
||||
"Return the final fragment"
|
||||
# assert self.innerHTML
|
||||
fragment = self.fragmentClass()
|
||||
self.openElements[0].reparentChildren(fragment)
|
||||
return fragment
|
||||
|
||||
def testSerializer(self, node):
|
||||
"""Serialize the subtree of node in the format required by unit tests
|
||||
node - the node from which to start serializing"""
|
||||
raise NotImplementedError
|
||||
|
|
@ -0,0 +1,227 @@
|
|||
from __future__ import absolute_import, division, unicode_literals
|
||||
|
||||
|
||||
from xml.dom import minidom, Node
|
||||
import weakref
|
||||
|
||||
from . import _base
|
||||
from .. import constants
|
||||
from ..constants import namespaces
|
||||
from ..utils import moduleFactoryFactory
|
||||
|
||||
|
||||
def getDomBuilder(DomImplementation):
|
||||
Dom = DomImplementation
|
||||
|
||||
class AttrList(object):
|
||||
def __init__(self, element):
|
||||
self.element = element
|
||||
|
||||
def __iter__(self):
|
||||
return list(self.element.attributes.items()).__iter__()
|
||||
|
||||
def __setitem__(self, name, value):
|
||||
self.element.setAttribute(name, value)
|
||||
|
||||
def __len__(self):
|
||||
return len(list(self.element.attributes.items()))
|
||||
|
||||
def items(self):
|
||||
return [(item[0], item[1]) for item in
|
||||
list(self.element.attributes.items())]
|
||||
|
||||
def keys(self):
|
||||
return list(self.element.attributes.keys())
|
||||
|
||||
def __getitem__(self, name):
|
||||
return self.element.getAttribute(name)
|
||||
|
||||
def __contains__(self, name):
|
||||
if isinstance(name, tuple):
|
||||
raise NotImplementedError
|
||||
else:
|
||||
return self.element.hasAttribute(name)
|
||||
|
||||
class NodeBuilder(_base.Node):
|
||||
def __init__(self, element):
|
||||
_base.Node.__init__(self, element.nodeName)
|
||||
self.element = element
|
||||
|
||||
namespace = property(lambda self: hasattr(self.element, "namespaceURI")
|
||||
and self.element.namespaceURI or None)
|
||||
|
||||
def appendChild(self, node):
|
||||
node.parent = self
|
||||
self.element.appendChild(node.element)
|
||||
|
||||
def insertText(self, data, insertBefore=None):
|
||||
text = self.element.ownerDocument.createTextNode(data)
|
||||
if insertBefore:
|
||||
self.element.insertBefore(text, insertBefore.element)
|
||||
else:
|
||||
self.element.appendChild(text)
|
||||
|
||||
def insertBefore(self, node, refNode):
|
||||
self.element.insertBefore(node.element, refNode.element)
|
||||
node.parent = self
|
||||
|
||||
def removeChild(self, node):
|
||||
if node.element.parentNode == self.element:
|
||||
self.element.removeChild(node.element)
|
||||
node.parent = None
|
||||
|
||||
def reparentChildren(self, newParent):
|
||||
while self.element.hasChildNodes():
|
||||
child = self.element.firstChild
|
||||
self.element.removeChild(child)
|
||||
newParent.element.appendChild(child)
|
||||
self.childNodes = []
|
||||
|
||||
def getAttributes(self):
|
||||
return AttrList(self.element)
|
||||
|
||||
def setAttributes(self, attributes):
|
||||
if attributes:
|
||||
for name, value in list(attributes.items()):
|
||||
if isinstance(name, tuple):
|
||||
if name[0] is not None:
|
||||
qualifiedName = (name[0] + ":" + name[1])
|
||||
else:
|
||||
qualifiedName = name[1]
|
||||
self.element.setAttributeNS(name[2], qualifiedName,
|
||||
value)
|
||||
else:
|
||||
self.element.setAttribute(
|
||||
name, value)
|
||||
attributes = property(getAttributes, setAttributes)
|
||||
|
||||
def cloneNode(self):
|
||||
return NodeBuilder(self.element.cloneNode(False))
|
||||
|
||||
def hasContent(self):
|
||||
return self.element.hasChildNodes()
|
||||
|
||||
def getNameTuple(self):
|
||||
if self.namespace is None:
|
||||
return namespaces["html"], self.name
|
||||
else:
|
||||
return self.namespace, self.name
|
||||
|
||||
nameTuple = property(getNameTuple)
|
||||
|
||||
class TreeBuilder(_base.TreeBuilder):
|
||||
def documentClass(self):
|
||||
self.dom = Dom.getDOMImplementation().createDocument(None, None, None)
|
||||
return weakref.proxy(self)
|
||||
|
||||
def insertDoctype(self, token):
|
||||
name = token["name"]
|
||||
publicId = token["publicId"]
|
||||
systemId = token["systemId"]
|
||||
|
||||
domimpl = Dom.getDOMImplementation()
|
||||
doctype = domimpl.createDocumentType(name, publicId, systemId)
|
||||
self.document.appendChild(NodeBuilder(doctype))
|
||||
if Dom == minidom:
|
||||
doctype.ownerDocument = self.dom
|
||||
|
||||
def elementClass(self, name, namespace=None):
|
||||
if namespace is None and self.defaultNamespace is None:
|
||||
node = self.dom.createElement(name)
|
||||
else:
|
||||
node = self.dom.createElementNS(namespace, name)
|
||||
|
||||
return NodeBuilder(node)
|
||||
|
||||
def commentClass(self, data):
|
||||
return NodeBuilder(self.dom.createComment(data))
|
||||
|
||||
def fragmentClass(self):
|
||||
return NodeBuilder(self.dom.createDocumentFragment())
|
||||
|
||||
def appendChild(self, node):
|
||||
self.dom.appendChild(node.element)
|
||||
|
||||
def testSerializer(self, element):
|
||||
return testSerializer(element)
|
||||
|
||||
def getDocument(self):
|
||||
return self.dom
|
||||
|
||||
def getFragment(self):
|
||||
return _base.TreeBuilder.getFragment(self).element
|
||||
|
||||
def insertText(self, data, parent=None):
|
||||
data = data
|
||||
if parent != self:
|
||||
_base.TreeBuilder.insertText(self, data, parent)
|
||||
else:
|
||||
# HACK: allow text nodes as children of the document node
|
||||
if hasattr(self.dom, '_child_node_types'):
|
||||
if not Node.TEXT_NODE in self.dom._child_node_types:
|
||||
self.dom._child_node_types = list(self.dom._child_node_types)
|
||||
self.dom._child_node_types.append(Node.TEXT_NODE)
|
||||
self.dom.appendChild(self.dom.createTextNode(data))
|
||||
|
||||
implementation = DomImplementation
|
||||
name = None
|
||||
|
||||
def testSerializer(element):
|
||||
element.normalize()
|
||||
rv = []
|
||||
|
||||
def serializeElement(element, indent=0):
|
||||
if element.nodeType == Node.DOCUMENT_TYPE_NODE:
|
||||
if element.name:
|
||||
if element.publicId or element.systemId:
|
||||
publicId = element.publicId or ""
|
||||
systemId = element.systemId or ""
|
||||
rv.append("""|%s<!DOCTYPE %s "%s" "%s">""" %
|
||||
(' ' * indent, element.name, publicId, systemId))
|
||||
else:
|
||||
rv.append("|%s<!DOCTYPE %s>" % (' ' * indent, element.name))
|
||||
else:
|
||||
rv.append("|%s<!DOCTYPE >" % (' ' * indent,))
|
||||
elif element.nodeType == Node.DOCUMENT_NODE:
|
||||
rv.append("#document")
|
||||
elif element.nodeType == Node.DOCUMENT_FRAGMENT_NODE:
|
||||
rv.append("#document-fragment")
|
||||
elif element.nodeType == Node.COMMENT_NODE:
|
||||
rv.append("|%s<!-- %s -->" % (' ' * indent, element.nodeValue))
|
||||
elif element.nodeType == Node.TEXT_NODE:
|
||||
rv.append("|%s\"%s\"" % (' ' * indent, element.nodeValue))
|
||||
else:
|
||||
if (hasattr(element, "namespaceURI") and
|
||||
element.namespaceURI is not None):
|
||||
name = "%s %s" % (constants.prefixes[element.namespaceURI],
|
||||
element.nodeName)
|
||||
else:
|
||||
name = element.nodeName
|
||||
rv.append("|%s<%s>" % (' ' * indent, name))
|
||||
if element.hasAttributes():
|
||||
attributes = []
|
||||
for i in range(len(element.attributes)):
|
||||
attr = element.attributes.item(i)
|
||||
name = attr.nodeName
|
||||
value = attr.value
|
||||
ns = attr.namespaceURI
|
||||
if ns:
|
||||
name = "%s %s" % (constants.prefixes[ns], attr.localName)
|
||||
else:
|
||||
name = attr.nodeName
|
||||
attributes.append((name, value))
|
||||
|
||||
for name, value in sorted(attributes):
|
||||
rv.append('|%s%s="%s"' % (' ' * (indent + 2), name, value))
|
||||
indent += 2
|
||||
for child in element.childNodes:
|
||||
serializeElement(child, indent)
|
||||
serializeElement(element, 0)
|
||||
|
||||
return "\n".join(rv)
|
||||
|
||||
return locals()
|
||||
|
||||
|
||||
# The actual means to get a module!
|
||||
getDomModule = moduleFactoryFactory(getDomBuilder)
|
||||
|
|
@ -0,0 +1,337 @@
|
|||
from __future__ import absolute_import, division, unicode_literals
|
||||
from pip._vendor.six import text_type
|
||||
|
||||
import re
|
||||
|
||||
from . import _base
|
||||
from .. import ihatexml
|
||||
from .. import constants
|
||||
from ..constants import namespaces
|
||||
from ..utils import moduleFactoryFactory
|
||||
|
||||
tag_regexp = re.compile("{([^}]*)}(.*)")
|
||||
|
||||
|
||||
def getETreeBuilder(ElementTreeImplementation, fullTree=False):
|
||||
ElementTree = ElementTreeImplementation
|
||||
ElementTreeCommentType = ElementTree.Comment("asd").tag
|
||||
|
||||
class Element(_base.Node):
|
||||
def __init__(self, name, namespace=None):
|
||||
self._name = name
|
||||
self._namespace = namespace
|
||||
self._element = ElementTree.Element(self._getETreeTag(name,
|
||||
namespace))
|
||||
if namespace is None:
|
||||
self.nameTuple = namespaces["html"], self._name
|
||||
else:
|
||||
self.nameTuple = self._namespace, self._name
|
||||
self.parent = None
|
||||
self._childNodes = []
|
||||
self._flags = []
|
||||
|
||||
def _getETreeTag(self, name, namespace):
|
||||
if namespace is None:
|
||||
etree_tag = name
|
||||
else:
|
||||
etree_tag = "{%s}%s" % (namespace, name)
|
||||
return etree_tag
|
||||
|
||||
def _setName(self, name):
|
||||
self._name = name
|
||||
self._element.tag = self._getETreeTag(self._name, self._namespace)
|
||||
|
||||
def _getName(self):
|
||||
return self._name
|
||||
|
||||
name = property(_getName, _setName)
|
||||
|
||||
def _setNamespace(self, namespace):
|
||||
self._namespace = namespace
|
||||
self._element.tag = self._getETreeTag(self._name, self._namespace)
|
||||
|
||||
def _getNamespace(self):
|
||||
return self._namespace
|
||||
|
||||
namespace = property(_getNamespace, _setNamespace)
|
||||
|
||||
def _getAttributes(self):
|
||||
return self._element.attrib
|
||||
|
||||
def _setAttributes(self, attributes):
|
||||
# Delete existing attributes first
|
||||
# XXX - there may be a better way to do this...
|
||||
for key in list(self._element.attrib.keys()):
|
||||
del self._element.attrib[key]
|
||||
for key, value in attributes.items():
|
||||
if isinstance(key, tuple):
|
||||
name = "{%s}%s" % (key[2], key[1])
|
||||
else:
|
||||
name = key
|
||||
self._element.set(name, value)
|
||||
|
||||
attributes = property(_getAttributes, _setAttributes)
|
||||
|
||||
def _getChildNodes(self):
|
||||
return self._childNodes
|
||||
|
||||
def _setChildNodes(self, value):
|
||||
del self._element[:]
|
||||
self._childNodes = []
|
||||
for element in value:
|
||||
self.insertChild(element)
|
||||
|
||||
childNodes = property(_getChildNodes, _setChildNodes)
|
||||
|
||||
def hasContent(self):
|
||||
"""Return true if the node has children or text"""
|
||||
return bool(self._element.text or len(self._element))
|
||||
|
||||
def appendChild(self, node):
|
||||
self._childNodes.append(node)
|
||||
self._element.append(node._element)
|
||||
node.parent = self
|
||||
|
||||
def insertBefore(self, node, refNode):
|
||||
index = list(self._element).index(refNode._element)
|
||||
self._element.insert(index, node._element)
|
||||
node.parent = self
|
||||
|
||||
def removeChild(self, node):
|
||||
self._element.remove(node._element)
|
||||
node.parent = None
|
||||
|
||||
def insertText(self, data, insertBefore=None):
|
||||
if not(len(self._element)):
|
||||
if not self._element.text:
|
||||
self._element.text = ""
|
||||
self._element.text += data
|
||||
elif insertBefore is None:
|
||||
# Insert the text as the tail of the last child element
|
||||
if not self._element[-1].tail:
|
||||
self._element[-1].tail = ""
|
||||
self._element[-1].tail += data
|
||||
else:
|
||||
# Insert the text before the specified node
|
||||
children = list(self._element)
|
||||
index = children.index(insertBefore._element)
|
||||
if index > 0:
|
||||
if not self._element[index - 1].tail:
|
||||
self._element[index - 1].tail = ""
|
||||
self._element[index - 1].tail += data
|
||||
else:
|
||||
if not self._element.text:
|
||||
self._element.text = ""
|
||||
self._element.text += data
|
||||
|
||||
def cloneNode(self):
|
||||
element = type(self)(self.name, self.namespace)
|
||||
for name, value in self.attributes.items():
|
||||
element.attributes[name] = value
|
||||
return element
|
||||
|
||||
def reparentChildren(self, newParent):
|
||||
if newParent.childNodes:
|
||||
newParent.childNodes[-1]._element.tail += self._element.text
|
||||
else:
|
||||
if not newParent._element.text:
|
||||
newParent._element.text = ""
|
||||
if self._element.text is not None:
|
||||
newParent._element.text += self._element.text
|
||||
self._element.text = ""
|
||||
_base.Node.reparentChildren(self, newParent)
|
||||
|
||||
class Comment(Element):
|
||||
def __init__(self, data):
|
||||
# Use the superclass constructor to set all properties on the
|
||||
# wrapper element
|
||||
self._element = ElementTree.Comment(data)
|
||||
self.parent = None
|
||||
self._childNodes = []
|
||||
self._flags = []
|
||||
|
||||
def _getData(self):
|
||||
return self._element.text
|
||||
|
||||
def _setData(self, value):
|
||||
self._element.text = value
|
||||
|
||||
data = property(_getData, _setData)
|
||||
|
||||
class DocumentType(Element):
|
||||
def __init__(self, name, publicId, systemId):
|
||||
Element.__init__(self, "<!DOCTYPE>")
|
||||
self._element.text = name
|
||||
self.publicId = publicId
|
||||
self.systemId = systemId
|
||||
|
||||
def _getPublicId(self):
|
||||
return self._element.get("publicId", "")
|
||||
|
||||
def _setPublicId(self, value):
|
||||
if value is not None:
|
||||
self._element.set("publicId", value)
|
||||
|
||||
publicId = property(_getPublicId, _setPublicId)
|
||||
|
||||
def _getSystemId(self):
|
||||
return self._element.get("systemId", "")
|
||||
|
||||
def _setSystemId(self, value):
|
||||
if value is not None:
|
||||
self._element.set("systemId", value)
|
||||
|
||||
systemId = property(_getSystemId, _setSystemId)
|
||||
|
||||
class Document(Element):
|
||||
def __init__(self):
|
||||
Element.__init__(self, "DOCUMENT_ROOT")
|
||||
|
||||
class DocumentFragment(Element):
|
||||
def __init__(self):
|
||||
Element.__init__(self, "DOCUMENT_FRAGMENT")
|
||||
|
||||
def testSerializer(element):
|
||||
rv = []
|
||||
|
||||
def serializeElement(element, indent=0):
|
||||
if not(hasattr(element, "tag")):
|
||||
element = element.getroot()
|
||||
if element.tag == "<!DOCTYPE>":
|
||||
if element.get("publicId") or element.get("systemId"):
|
||||
publicId = element.get("publicId") or ""
|
||||
systemId = element.get("systemId") or ""
|
||||
rv.append("""<!DOCTYPE %s "%s" "%s">""" %
|
||||
(element.text, publicId, systemId))
|
||||
else:
|
||||
rv.append("<!DOCTYPE %s>" % (element.text,))
|
||||
elif element.tag == "DOCUMENT_ROOT":
|
||||
rv.append("#document")
|
||||
if element.text is not None:
|
||||
rv.append("|%s\"%s\"" % (' ' * (indent + 2), element.text))
|
||||
if element.tail is not None:
|
||||
raise TypeError("Document node cannot have tail")
|
||||
if hasattr(element, "attrib") and len(element.attrib):
|
||||
raise TypeError("Document node cannot have attributes")
|
||||
elif element.tag == ElementTreeCommentType:
|
||||
rv.append("|%s<!-- %s -->" % (' ' * indent, element.text))
|
||||
else:
|
||||
assert isinstance(element.tag, text_type), \
|
||||
"Expected unicode, got %s, %s" % (type(element.tag), element.tag)
|
||||
nsmatch = tag_regexp.match(element.tag)
|
||||
|
||||
if nsmatch is None:
|
||||
name = element.tag
|
||||
else:
|
||||
ns, name = nsmatch.groups()
|
||||
prefix = constants.prefixes[ns]
|
||||
name = "%s %s" % (prefix, name)
|
||||
rv.append("|%s<%s>" % (' ' * indent, name))
|
||||
|
||||
if hasattr(element, "attrib"):
|
||||
attributes = []
|
||||
for name, value in element.attrib.items():
|
||||
nsmatch = tag_regexp.match(name)
|
||||
if nsmatch is not None:
|
||||
ns, name = nsmatch.groups()
|
||||
prefix = constants.prefixes[ns]
|
||||
attr_string = "%s %s" % (prefix, name)
|
||||
else:
|
||||
attr_string = name
|
||||
attributes.append((attr_string, value))
|
||||
|
||||
for name, value in sorted(attributes):
|
||||
rv.append('|%s%s="%s"' % (' ' * (indent + 2), name, value))
|
||||
if element.text:
|
||||
rv.append("|%s\"%s\"" % (' ' * (indent + 2), element.text))
|
||||
indent += 2
|
||||
for child in element:
|
||||
serializeElement(child, indent)
|
||||
if element.tail:
|
||||
rv.append("|%s\"%s\"" % (' ' * (indent - 2), element.tail))
|
||||
serializeElement(element, 0)
|
||||
|
||||
return "\n".join(rv)
|
||||
|
||||
def tostring(element):
|
||||
"""Serialize an element and its child nodes to a string"""
|
||||
rv = []
|
||||
filter = ihatexml.InfosetFilter()
|
||||
|
||||
def serializeElement(element):
|
||||
if isinstance(element, ElementTree.ElementTree):
|
||||
element = element.getroot()
|
||||
|
||||
if element.tag == "<!DOCTYPE>":
|
||||
if element.get("publicId") or element.get("systemId"):
|
||||
publicId = element.get("publicId") or ""
|
||||
systemId = element.get("systemId") or ""
|
||||
rv.append("""<!DOCTYPE %s PUBLIC "%s" "%s">""" %
|
||||
(element.text, publicId, systemId))
|
||||
else:
|
||||
rv.append("<!DOCTYPE %s>" % (element.text,))
|
||||
elif element.tag == "DOCUMENT_ROOT":
|
||||
if element.text is not None:
|
||||
rv.append(element.text)
|
||||
if element.tail is not None:
|
||||
raise TypeError("Document node cannot have tail")
|
||||
if hasattr(element, "attrib") and len(element.attrib):
|
||||
raise TypeError("Document node cannot have attributes")
|
||||
|
||||
for child in element:
|
||||
serializeElement(child)
|
||||
|
||||
elif element.tag == ElementTreeCommentType:
|
||||
rv.append("<!--%s-->" % (element.text,))
|
||||
else:
|
||||
# This is assumed to be an ordinary element
|
||||
if not element.attrib:
|
||||
rv.append("<%s>" % (filter.fromXmlName(element.tag),))
|
||||
else:
|
||||
attr = " ".join(["%s=\"%s\"" % (
|
||||
filter.fromXmlName(name), value)
|
||||
for name, value in element.attrib.items()])
|
||||
rv.append("<%s %s>" % (element.tag, attr))
|
||||
if element.text:
|
||||
rv.append(element.text)
|
||||
|
||||
for child in element:
|
||||
serializeElement(child)
|
||||
|
||||
rv.append("</%s>" % (element.tag,))
|
||||
|
||||
if element.tail:
|
||||
rv.append(element.tail)
|
||||
|
||||
serializeElement(element)
|
||||
|
||||
return "".join(rv)
|
||||
|
||||
class TreeBuilder(_base.TreeBuilder):
|
||||
documentClass = Document
|
||||
doctypeClass = DocumentType
|
||||
elementClass = Element
|
||||
commentClass = Comment
|
||||
fragmentClass = DocumentFragment
|
||||
implementation = ElementTreeImplementation
|
||||
|
||||
def testSerializer(self, element):
|
||||
return testSerializer(element)
|
||||
|
||||
def getDocument(self):
|
||||
if fullTree:
|
||||
return self.document._element
|
||||
else:
|
||||
if self.defaultNamespace is not None:
|
||||
return self.document._element.find(
|
||||
"{%s}html" % self.defaultNamespace)
|
||||
else:
|
||||
return self.document._element.find("html")
|
||||
|
||||
def getFragment(self):
|
||||
return _base.TreeBuilder.getFragment(self)._element
|
||||
|
||||
return locals()
|
||||
|
||||
|
||||
getETreeModule = moduleFactoryFactory(getETreeBuilder)
|
||||
|
|
@ -0,0 +1,369 @@
|
|||
"""Module for supporting the lxml.etree library. The idea here is to use as much
|
||||
of the native library as possible, without using fragile hacks like custom element
|
||||
names that break between releases. The downside of this is that we cannot represent
|
||||
all possible trees; specifically the following are known to cause problems:
|
||||
|
||||
Text or comments as siblings of the root element
|
||||
Docypes with no name
|
||||
|
||||
When any of these things occur, we emit a DataLossWarning
|
||||
"""
|
||||
|
||||
from __future__ import absolute_import, division, unicode_literals
|
||||
|
||||
import warnings
|
||||
import re
|
||||
import sys
|
||||
|
||||
from . import _base
|
||||
from ..constants import DataLossWarning
|
||||
from .. import constants
|
||||
from . import etree as etree_builders
|
||||
from .. import ihatexml
|
||||
|
||||
import lxml.etree as etree
|
||||
|
||||
|
||||
fullTree = True
|
||||
tag_regexp = re.compile("{([^}]*)}(.*)")
|
||||
|
||||
comment_type = etree.Comment("asd").tag
|
||||
|
||||
|
||||
class DocumentType(object):
|
||||
def __init__(self, name, publicId, systemId):
|
||||
self.name = name
|
||||
self.publicId = publicId
|
||||
self.systemId = systemId
|
||||
|
||||
|
||||
class Document(object):
|
||||
def __init__(self):
|
||||
self._elementTree = None
|
||||
self._childNodes = []
|
||||
|
||||
def appendChild(self, element):
|
||||
self._elementTree.getroot().addnext(element._element)
|
||||
|
||||
def _getChildNodes(self):
|
||||
return self._childNodes
|
||||
|
||||
childNodes = property(_getChildNodes)
|
||||
|
||||
|
||||
def testSerializer(element):
|
||||
rv = []
|
||||
finalText = None
|
||||
infosetFilter = ihatexml.InfosetFilter()
|
||||
|
||||
def serializeElement(element, indent=0):
|
||||
if not hasattr(element, "tag"):
|
||||
if hasattr(element, "getroot"):
|
||||
# Full tree case
|
||||
rv.append("#document")
|
||||
if element.docinfo.internalDTD:
|
||||
if not (element.docinfo.public_id or
|
||||
element.docinfo.system_url):
|
||||
dtd_str = "<!DOCTYPE %s>" % element.docinfo.root_name
|
||||
else:
|
||||
dtd_str = """<!DOCTYPE %s "%s" "%s">""" % (
|
||||
element.docinfo.root_name,
|
||||
element.docinfo.public_id,
|
||||
element.docinfo.system_url)
|
||||
rv.append("|%s%s" % (' ' * (indent + 2), dtd_str))
|
||||
next_element = element.getroot()
|
||||
while next_element.getprevious() is not None:
|
||||
next_element = next_element.getprevious()
|
||||
while next_element is not None:
|
||||
serializeElement(next_element, indent + 2)
|
||||
next_element = next_element.getnext()
|
||||
elif isinstance(element, str) or isinstance(element, bytes):
|
||||
# Text in a fragment
|
||||
assert isinstance(element, str) or sys.version_info.major == 2
|
||||
rv.append("|%s\"%s\"" % (' ' * indent, element))
|
||||
else:
|
||||
# Fragment case
|
||||
rv.append("#document-fragment")
|
||||
for next_element in element:
|
||||
serializeElement(next_element, indent + 2)
|
||||
elif element.tag == comment_type:
|
||||
rv.append("|%s<!-- %s -->" % (' ' * indent, element.text))
|
||||
if hasattr(element, "tail") and element.tail:
|
||||
rv.append("|%s\"%s\"" % (' ' * indent, element.tail))
|
||||
else:
|
||||
assert isinstance(element, etree._Element)
|
||||
nsmatch = etree_builders.tag_regexp.match(element.tag)
|
||||
if nsmatch is not None:
|
||||
ns = nsmatch.group(1)
|
||||
tag = nsmatch.group(2)
|
||||
prefix = constants.prefixes[ns]
|
||||
rv.append("|%s<%s %s>" % (' ' * indent, prefix,
|
||||
infosetFilter.fromXmlName(tag)))
|
||||
else:
|
||||
rv.append("|%s<%s>" % (' ' * indent,
|
||||
infosetFilter.fromXmlName(element.tag)))
|
||||
|
||||
if hasattr(element, "attrib"):
|
||||
attributes = []
|
||||
for name, value in element.attrib.items():
|
||||
nsmatch = tag_regexp.match(name)
|
||||
if nsmatch is not None:
|
||||
ns, name = nsmatch.groups()
|
||||
name = infosetFilter.fromXmlName(name)
|
||||
prefix = constants.prefixes[ns]
|
||||
attr_string = "%s %s" % (prefix, name)
|
||||
else:
|
||||
attr_string = infosetFilter.fromXmlName(name)
|
||||
attributes.append((attr_string, value))
|
||||
|
||||
for name, value in sorted(attributes):
|
||||
rv.append('|%s%s="%s"' % (' ' * (indent + 2), name, value))
|
||||
|
||||
if element.text:
|
||||
rv.append("|%s\"%s\"" % (' ' * (indent + 2), element.text))
|
||||
indent += 2
|
||||
for child in element:
|
||||
serializeElement(child, indent)
|
||||
if hasattr(element, "tail") and element.tail:
|
||||
rv.append("|%s\"%s\"" % (' ' * (indent - 2), element.tail))
|
||||
serializeElement(element, 0)
|
||||
|
||||
if finalText is not None:
|
||||
rv.append("|%s\"%s\"" % (' ' * 2, finalText))
|
||||
|
||||
return "\n".join(rv)
|
||||
|
||||
|
||||
def tostring(element):
|
||||
"""Serialize an element and its child nodes to a string"""
|
||||
rv = []
|
||||
finalText = None
|
||||
|
||||
def serializeElement(element):
|
||||
if not hasattr(element, "tag"):
|
||||
if element.docinfo.internalDTD:
|
||||
if element.docinfo.doctype:
|
||||
dtd_str = element.docinfo.doctype
|
||||
else:
|
||||
dtd_str = "<!DOCTYPE %s>" % element.docinfo.root_name
|
||||
rv.append(dtd_str)
|
||||
serializeElement(element.getroot())
|
||||
|
||||
elif element.tag == comment_type:
|
||||
rv.append("<!--%s-->" % (element.text,))
|
||||
|
||||
else:
|
||||
# This is assumed to be an ordinary element
|
||||
if not element.attrib:
|
||||
rv.append("<%s>" % (element.tag,))
|
||||
else:
|
||||
attr = " ".join(["%s=\"%s\"" % (name, value)
|
||||
for name, value in element.attrib.items()])
|
||||
rv.append("<%s %s>" % (element.tag, attr))
|
||||
if element.text:
|
||||
rv.append(element.text)
|
||||
|
||||
for child in element:
|
||||
serializeElement(child)
|
||||
|
||||
rv.append("</%s>" % (element.tag,))
|
||||
|
||||
if hasattr(element, "tail") and element.tail:
|
||||
rv.append(element.tail)
|
||||
|
||||
serializeElement(element)
|
||||
|
||||
if finalText is not None:
|
||||
rv.append("%s\"" % (' ' * 2, finalText))
|
||||
|
||||
return "".join(rv)
|
||||
|
||||
|
||||
class TreeBuilder(_base.TreeBuilder):
|
||||
documentClass = Document
|
||||
doctypeClass = DocumentType
|
||||
elementClass = None
|
||||
commentClass = None
|
||||
fragmentClass = Document
|
||||
implementation = etree
|
||||
|
||||
def __init__(self, namespaceHTMLElements, fullTree=False):
|
||||
builder = etree_builders.getETreeModule(etree, fullTree=fullTree)
|
||||
infosetFilter = self.infosetFilter = ihatexml.InfosetFilter()
|
||||
self.namespaceHTMLElements = namespaceHTMLElements
|
||||
|
||||
class Attributes(dict):
|
||||
def __init__(self, element, value={}):
|
||||
self._element = element
|
||||
dict.__init__(self, value)
|
||||
for key, value in self.items():
|
||||
if isinstance(key, tuple):
|
||||
name = "{%s}%s" % (key[2], infosetFilter.coerceAttribute(key[1]))
|
||||
else:
|
||||
name = infosetFilter.coerceAttribute(key)
|
||||
self._element._element.attrib[name] = value
|
||||
|
||||
def __setitem__(self, key, value):
|
||||
dict.__setitem__(self, key, value)
|
||||
if isinstance(key, tuple):
|
||||
name = "{%s}%s" % (key[2], infosetFilter.coerceAttribute(key[1]))
|
||||
else:
|
||||
name = infosetFilter.coerceAttribute(key)
|
||||
self._element._element.attrib[name] = value
|
||||
|
||||
class Element(builder.Element):
|
||||
def __init__(self, name, namespace):
|
||||
name = infosetFilter.coerceElement(name)
|
||||
builder.Element.__init__(self, name, namespace=namespace)
|
||||
self._attributes = Attributes(self)
|
||||
|
||||
def _setName(self, name):
|
||||
self._name = infosetFilter.coerceElement(name)
|
||||
self._element.tag = self._getETreeTag(
|
||||
self._name, self._namespace)
|
||||
|
||||
def _getName(self):
|
||||
return infosetFilter.fromXmlName(self._name)
|
||||
|
||||
name = property(_getName, _setName)
|
||||
|
||||
def _getAttributes(self):
|
||||
return self._attributes
|
||||
|
||||
def _setAttributes(self, attributes):
|
||||
self._attributes = Attributes(self, attributes)
|
||||
|
||||
attributes = property(_getAttributes, _setAttributes)
|
||||
|
||||
def insertText(self, data, insertBefore=None):
|
||||
data = infosetFilter.coerceCharacters(data)
|
||||
builder.Element.insertText(self, data, insertBefore)
|
||||
|
||||
def appendChild(self, child):
|
||||
builder.Element.appendChild(self, child)
|
||||
|
||||
class Comment(builder.Comment):
|
||||
def __init__(self, data):
|
||||
data = infosetFilter.coerceComment(data)
|
||||
builder.Comment.__init__(self, data)
|
||||
|
||||
def _setData(self, data):
|
||||
data = infosetFilter.coerceComment(data)
|
||||
self._element.text = data
|
||||
|
||||
def _getData(self):
|
||||
return self._element.text
|
||||
|
||||
data = property(_getData, _setData)
|
||||
|
||||
self.elementClass = Element
|
||||
self.commentClass = builder.Comment
|
||||
# self.fragmentClass = builder.DocumentFragment
|
||||
_base.TreeBuilder.__init__(self, namespaceHTMLElements)
|
||||
|
||||
def reset(self):
|
||||
_base.TreeBuilder.reset(self)
|
||||
self.insertComment = self.insertCommentInitial
|
||||
self.initial_comments = []
|
||||
self.doctype = None
|
||||
|
||||
def testSerializer(self, element):
|
||||
return testSerializer(element)
|
||||
|
||||
def getDocument(self):
|
||||
if fullTree:
|
||||
return self.document._elementTree
|
||||
else:
|
||||
return self.document._elementTree.getroot()
|
||||
|
||||
def getFragment(self):
|
||||
fragment = []
|
||||
element = self.openElements[0]._element
|
||||
if element.text:
|
||||
fragment.append(element.text)
|
||||
fragment.extend(list(element))
|
||||
if element.tail:
|
||||
fragment.append(element.tail)
|
||||
return fragment
|
||||
|
||||
def insertDoctype(self, token):
|
||||
name = token["name"]
|
||||
publicId = token["publicId"]
|
||||
systemId = token["systemId"]
|
||||
|
||||
if not name:
|
||||
warnings.warn("lxml cannot represent empty doctype", DataLossWarning)
|
||||
self.doctype = None
|
||||
else:
|
||||
coercedName = self.infosetFilter.coerceElement(name)
|
||||
if coercedName != name:
|
||||
warnings.warn("lxml cannot represent non-xml doctype", DataLossWarning)
|
||||
|
||||
doctype = self.doctypeClass(coercedName, publicId, systemId)
|
||||
self.doctype = doctype
|
||||
|
||||
def insertCommentInitial(self, data, parent=None):
|
||||
self.initial_comments.append(data)
|
||||
|
||||
def insertCommentMain(self, data, parent=None):
|
||||
if (parent == self.document and
|
||||
self.document._elementTree.getroot()[-1].tag == comment_type):
|
||||
warnings.warn("lxml cannot represent adjacent comments beyond the root elements", DataLossWarning)
|
||||
super(TreeBuilder, self).insertComment(data, parent)
|
||||
|
||||
def insertRoot(self, token):
|
||||
"""Create the document root"""
|
||||
# Because of the way libxml2 works, it doesn't seem to be possible to
|
||||
# alter information like the doctype after the tree has been parsed.
|
||||
# Therefore we need to use the built-in parser to create our iniial
|
||||
# tree, after which we can add elements like normal
|
||||
docStr = ""
|
||||
if self.doctype:
|
||||
assert self.doctype.name
|
||||
docStr += "<!DOCTYPE %s" % self.doctype.name
|
||||
if (self.doctype.publicId is not None or
|
||||
self.doctype.systemId is not None):
|
||||
docStr += (' PUBLIC "%s" ' %
|
||||
(self.infosetFilter.coercePubid(self.doctype.publicId or "")))
|
||||
if self.doctype.systemId:
|
||||
sysid = self.doctype.systemId
|
||||
if sysid.find("'") >= 0 and sysid.find('"') >= 0:
|
||||
warnings.warn("DOCTYPE system cannot contain single and double quotes", DataLossWarning)
|
||||
sysid = sysid.replace("'", 'U00027')
|
||||
if sysid.find("'") >= 0:
|
||||
docStr += '"%s"' % sysid
|
||||
else:
|
||||
docStr += "'%s'" % sysid
|
||||
else:
|
||||
docStr += "''"
|
||||
docStr += ">"
|
||||
if self.doctype.name != token["name"]:
|
||||
warnings.warn("lxml cannot represent doctype with a different name to the root element", DataLossWarning)
|
||||
docStr += "<THIS_SHOULD_NEVER_APPEAR_PUBLICLY/>"
|
||||
root = etree.fromstring(docStr)
|
||||
|
||||
# Append the initial comments:
|
||||
for comment_token in self.initial_comments:
|
||||
root.addprevious(etree.Comment(comment_token["data"]))
|
||||
|
||||
# Create the root document and add the ElementTree to it
|
||||
self.document = self.documentClass()
|
||||
self.document._elementTree = root.getroottree()
|
||||
|
||||
# Give the root element the right name
|
||||
name = token["name"]
|
||||
namespace = token.get("namespace", self.defaultNamespace)
|
||||
if namespace is None:
|
||||
etree_tag = name
|
||||
else:
|
||||
etree_tag = "{%s}%s" % (namespace, name)
|
||||
root.tag = etree_tag
|
||||
|
||||
# Add the root element to the internal child/open data structures
|
||||
root_element = self.elementClass(name, namespace)
|
||||
root_element._element = root
|
||||
self.document._childNodes.append(root_element)
|
||||
self.openElements.append(root_element)
|
||||
|
||||
# Reset to the default insert comment function
|
||||
self.insertComment = self.insertCommentMain
|
||||
|
|
@ -0,0 +1,57 @@
|
|||
"""A collection of modules for iterating through different kinds of
|
||||
tree, generating tokens identical to those produced by the tokenizer
|
||||
module.
|
||||
|
||||
To create a tree walker for a new type of tree, you need to do
|
||||
implement a tree walker object (called TreeWalker by convention) that
|
||||
implements a 'serialize' method taking a tree as sole argument and
|
||||
returning an iterator generating tokens.
|
||||
"""
|
||||
|
||||
from __future__ import absolute_import, division, unicode_literals
|
||||
|
||||
import sys
|
||||
|
||||
from ..utils import default_etree
|
||||
|
||||
treeWalkerCache = {}
|
||||
|
||||
|
||||
def getTreeWalker(treeType, implementation=None, **kwargs):
|
||||
"""Get a TreeWalker class for various types of tree with built-in support
|
||||
|
||||
treeType - the name of the tree type required (case-insensitive). Supported
|
||||
values are:
|
||||
|
||||
"dom" - The xml.dom.minidom DOM implementation
|
||||
"pulldom" - The xml.dom.pulldom event stream
|
||||
"etree" - A generic walker for tree implementations exposing an
|
||||
elementtree-like interface (known to work with
|
||||
ElementTree, cElementTree and lxml.etree).
|
||||
"lxml" - Optimized walker for lxml.etree
|
||||
"genshi" - a Genshi stream
|
||||
|
||||
implementation - (Currently applies to the "etree" tree type only). A module
|
||||
implementing the tree type e.g. xml.etree.ElementTree or
|
||||
cElementTree."""
|
||||
|
||||
treeType = treeType.lower()
|
||||
if treeType not in treeWalkerCache:
|
||||
if treeType in ("dom", "pulldom"):
|
||||
name = "%s.%s" % (__name__, treeType)
|
||||
__import__(name)
|
||||
mod = sys.modules[name]
|
||||
treeWalkerCache[treeType] = mod.TreeWalker
|
||||
elif treeType == "genshi":
|
||||
from . import genshistream
|
||||
treeWalkerCache[treeType] = genshistream.TreeWalker
|
||||
elif treeType == "lxml":
|
||||
from . import lxmletree
|
||||
treeWalkerCache[treeType] = lxmletree.TreeWalker
|
||||
elif treeType == "etree":
|
||||
from . import etree
|
||||
if implementation is None:
|
||||
implementation = default_etree
|
||||
# XXX: NEVER cache here, caching is done in the etree submodule
|
||||
return etree.getETreeModule(implementation, **kwargs).TreeWalker
|
||||
return treeWalkerCache.get(treeType)
|
||||
|
|
@ -0,0 +1,200 @@
|
|||
from __future__ import absolute_import, division, unicode_literals
|
||||
from pip._vendor.six import text_type, string_types
|
||||
|
||||
import gettext
|
||||
_ = gettext.gettext
|
||||
|
||||
from xml.dom import Node
|
||||
|
||||
DOCUMENT = Node.DOCUMENT_NODE
|
||||
DOCTYPE = Node.DOCUMENT_TYPE_NODE
|
||||
TEXT = Node.TEXT_NODE
|
||||
ELEMENT = Node.ELEMENT_NODE
|
||||
COMMENT = Node.COMMENT_NODE
|
||||
ENTITY = Node.ENTITY_NODE
|
||||
UNKNOWN = "<#UNKNOWN#>"
|
||||
|
||||
from ..constants import voidElements, spaceCharacters
|
||||
spaceCharacters = "".join(spaceCharacters)
|
||||
|
||||
|
||||
def to_text(s, blank_if_none=True):
|
||||
"""Wrapper around six.text_type to convert None to empty string"""
|
||||
if s is None:
|
||||
if blank_if_none:
|
||||
return ""
|
||||
else:
|
||||
return None
|
||||
elif isinstance(s, text_type):
|
||||
return s
|
||||
else:
|
||||
return text_type(s)
|
||||
|
||||
|
||||
def is_text_or_none(string):
|
||||
"""Wrapper around isinstance(string_types) or is None"""
|
||||
return string is None or isinstance(string, string_types)
|
||||
|
||||
|
||||
class TreeWalker(object):
|
||||
def __init__(self, tree):
|
||||
self.tree = tree
|
||||
|
||||
def __iter__(self):
|
||||
raise NotImplementedError
|
||||
|
||||
def error(self, msg):
|
||||
return {"type": "SerializeError", "data": msg}
|
||||
|
||||
def emptyTag(self, namespace, name, attrs, hasChildren=False):
|
||||
assert namespace is None or isinstance(namespace, string_types), type(namespace)
|
||||
assert isinstance(name, string_types), type(name)
|
||||
assert all((namespace is None or isinstance(namespace, string_types)) and
|
||||
isinstance(name, string_types) and
|
||||
isinstance(value, string_types)
|
||||
for (namespace, name), value in attrs.items())
|
||||
|
||||
yield {"type": "EmptyTag", "name": to_text(name, False),
|
||||
"namespace": to_text(namespace),
|
||||
"data": attrs}
|
||||
if hasChildren:
|
||||
yield self.error(_("Void element has children"))
|
||||
|
||||
def startTag(self, namespace, name, attrs):
|
||||
assert namespace is None or isinstance(namespace, string_types), type(namespace)
|
||||
assert isinstance(name, string_types), type(name)
|
||||
assert all((namespace is None or isinstance(namespace, string_types)) and
|
||||
isinstance(name, string_types) and
|
||||
isinstance(value, string_types)
|
||||
for (namespace, name), value in attrs.items())
|
||||
|
||||
return {"type": "StartTag",
|
||||
"name": text_type(name),
|
||||
"namespace": to_text(namespace),
|
||||
"data": dict(((to_text(namespace, False), to_text(name)),
|
||||
to_text(value, False))
|
||||
for (namespace, name), value in attrs.items())}
|
||||
|
||||
def endTag(self, namespace, name):
|
||||
assert namespace is None or isinstance(namespace, string_types), type(namespace)
|
||||
assert isinstance(name, string_types), type(namespace)
|
||||
|
||||
return {"type": "EndTag",
|
||||
"name": to_text(name, False),
|
||||
"namespace": to_text(namespace),
|
||||
"data": {}}
|
||||
|
||||
def text(self, data):
|
||||
assert isinstance(data, string_types), type(data)
|
||||
|
||||
data = to_text(data)
|
||||
middle = data.lstrip(spaceCharacters)
|
||||
left = data[:len(data) - len(middle)]
|
||||
if left:
|
||||
yield {"type": "SpaceCharacters", "data": left}
|
||||
data = middle
|
||||
middle = data.rstrip(spaceCharacters)
|
||||
right = data[len(middle):]
|
||||
if middle:
|
||||
yield {"type": "Characters", "data": middle}
|
||||
if right:
|
||||
yield {"type": "SpaceCharacters", "data": right}
|
||||
|
||||
def comment(self, data):
|
||||
assert isinstance(data, string_types), type(data)
|
||||
|
||||
return {"type": "Comment", "data": text_type(data)}
|
||||
|
||||
def doctype(self, name, publicId=None, systemId=None, correct=True):
|
||||
assert is_text_or_none(name), type(name)
|
||||
assert is_text_or_none(publicId), type(publicId)
|
||||
assert is_text_or_none(systemId), type(systemId)
|
||||
|
||||
return {"type": "Doctype",
|
||||
"name": to_text(name),
|
||||
"publicId": to_text(publicId),
|
||||
"systemId": to_text(systemId),
|
||||
"correct": to_text(correct)}
|
||||
|
||||
def entity(self, name):
|
||||
assert isinstance(name, string_types), type(name)
|
||||
|
||||
return {"type": "Entity", "name": text_type(name)}
|
||||
|
||||
def unknown(self, nodeType):
|
||||
return self.error(_("Unknown node type: ") + nodeType)
|
||||
|
||||
|
||||
class NonRecursiveTreeWalker(TreeWalker):
|
||||
def getNodeDetails(self, node):
|
||||
raise NotImplementedError
|
||||
|
||||
def getFirstChild(self, node):
|
||||
raise NotImplementedError
|
||||
|
||||
def getNextSibling(self, node):
|
||||
raise NotImplementedError
|
||||
|
||||
def getParentNode(self, node):
|
||||
raise NotImplementedError
|
||||
|
||||
def __iter__(self):
|
||||
currentNode = self.tree
|
||||
while currentNode is not None:
|
||||
details = self.getNodeDetails(currentNode)
|
||||
type, details = details[0], details[1:]
|
||||
hasChildren = False
|
||||
|
||||
if type == DOCTYPE:
|
||||
yield self.doctype(*details)
|
||||
|
||||
elif type == TEXT:
|
||||
for token in self.text(*details):
|
||||
yield token
|
||||
|
||||
elif type == ELEMENT:
|
||||
namespace, name, attributes, hasChildren = details
|
||||
if name in voidElements:
|
||||
for token in self.emptyTag(namespace, name, attributes,
|
||||
hasChildren):
|
||||
yield token
|
||||
hasChildren = False
|
||||
else:
|
||||
yield self.startTag(namespace, name, attributes)
|
||||
|
||||
elif type == COMMENT:
|
||||
yield self.comment(details[0])
|
||||
|
||||
elif type == ENTITY:
|
||||
yield self.entity(details[0])
|
||||
|
||||
elif type == DOCUMENT:
|
||||
hasChildren = True
|
||||
|
||||
else:
|
||||
yield self.unknown(details[0])
|
||||
|
||||
if hasChildren:
|
||||
firstChild = self.getFirstChild(currentNode)
|
||||
else:
|
||||
firstChild = None
|
||||
|
||||
if firstChild is not None:
|
||||
currentNode = firstChild
|
||||
else:
|
||||
while currentNode is not None:
|
||||
details = self.getNodeDetails(currentNode)
|
||||
type, details = details[0], details[1:]
|
||||
if type == ELEMENT:
|
||||
namespace, name, attributes, hasChildren = details
|
||||
if name not in voidElements:
|
||||
yield self.endTag(namespace, name)
|
||||
if self.tree is currentNode:
|
||||
currentNode = None
|
||||
break
|
||||
nextSibling = self.getNextSibling(currentNode)
|
||||
if nextSibling is not None:
|
||||
currentNode = nextSibling
|
||||
break
|
||||
else:
|
||||
currentNode = self.getParentNode(currentNode)
|
||||
|
|
@ -0,0 +1,46 @@
|
|||
from __future__ import absolute_import, division, unicode_literals
|
||||
|
||||
from xml.dom import Node
|
||||
|
||||
import gettext
|
||||
_ = gettext.gettext
|
||||
|
||||
from . import _base
|
||||
|
||||
|
||||
class TreeWalker(_base.NonRecursiveTreeWalker):
|
||||
def getNodeDetails(self, node):
|
||||
if node.nodeType == Node.DOCUMENT_TYPE_NODE:
|
||||
return _base.DOCTYPE, node.name, node.publicId, node.systemId
|
||||
|
||||
elif node.nodeType in (Node.TEXT_NODE, Node.CDATA_SECTION_NODE):
|
||||
return _base.TEXT, node.nodeValue
|
||||
|
||||
elif node.nodeType == Node.ELEMENT_NODE:
|
||||
attrs = {}
|
||||
for attr in list(node.attributes.keys()):
|
||||
attr = node.getAttributeNode(attr)
|
||||
if attr.namespaceURI:
|
||||
attrs[(attr.namespaceURI, attr.localName)] = attr.value
|
||||
else:
|
||||
attrs[(None, attr.name)] = attr.value
|
||||
return (_base.ELEMENT, node.namespaceURI, node.nodeName,
|
||||
attrs, node.hasChildNodes())
|
||||
|
||||
elif node.nodeType == Node.COMMENT_NODE:
|
||||
return _base.COMMENT, node.nodeValue
|
||||
|
||||
elif node.nodeType in (Node.DOCUMENT_NODE, Node.DOCUMENT_FRAGMENT_NODE):
|
||||
return (_base.DOCUMENT,)
|
||||
|
||||
else:
|
||||
return _base.UNKNOWN, node.nodeType
|
||||
|
||||
def getFirstChild(self, node):
|
||||
return node.firstChild
|
||||
|
||||
def getNextSibling(self, node):
|
||||
return node.nextSibling
|
||||
|
||||
def getParentNode(self, node):
|
||||
return node.parentNode
|
||||
|
|
@ -0,0 +1,138 @@
|
|||
from __future__ import absolute_import, division, unicode_literals
|
||||
|
||||
try:
|
||||
from collections import OrderedDict
|
||||
except ImportError:
|
||||
try:
|
||||
from ordereddict import OrderedDict
|
||||
except ImportError:
|
||||
OrderedDict = dict
|
||||
import gettext
|
||||
_ = gettext.gettext
|
||||
|
||||
import re
|
||||
|
||||
from pip._vendor.six import text_type
|
||||
|
||||
from . import _base
|
||||
from ..utils import moduleFactoryFactory
|
||||
|
||||
tag_regexp = re.compile("{([^}]*)}(.*)")
|
||||
|
||||
|
||||
def getETreeBuilder(ElementTreeImplementation):
|
||||
ElementTree = ElementTreeImplementation
|
||||
ElementTreeCommentType = ElementTree.Comment("asd").tag
|
||||
|
||||
class TreeWalker(_base.NonRecursiveTreeWalker):
|
||||
"""Given the particular ElementTree representation, this implementation,
|
||||
to avoid using recursion, returns "nodes" as tuples with the following
|
||||
content:
|
||||
|
||||
1. The current element
|
||||
|
||||
2. The index of the element relative to its parent
|
||||
|
||||
3. A stack of ancestor elements
|
||||
|
||||
4. A flag "text", "tail" or None to indicate if the current node is a
|
||||
text node; either the text or tail of the current element (1)
|
||||
"""
|
||||
def getNodeDetails(self, node):
|
||||
if isinstance(node, tuple): # It might be the root Element
|
||||
elt, key, parents, flag = node
|
||||
if flag in ("text", "tail"):
|
||||
return _base.TEXT, getattr(elt, flag)
|
||||
else:
|
||||
node = elt
|
||||
|
||||
if not(hasattr(node, "tag")):
|
||||
node = node.getroot()
|
||||
|
||||
if node.tag in ("DOCUMENT_ROOT", "DOCUMENT_FRAGMENT"):
|
||||
return (_base.DOCUMENT,)
|
||||
|
||||
elif node.tag == "<!DOCTYPE>":
|
||||
return (_base.DOCTYPE, node.text,
|
||||
node.get("publicId"), node.get("systemId"))
|
||||
|
||||
elif node.tag == ElementTreeCommentType:
|
||||
return _base.COMMENT, node.text
|
||||
|
||||
else:
|
||||
assert type(node.tag) == text_type, type(node.tag)
|
||||
# This is assumed to be an ordinary element
|
||||
match = tag_regexp.match(node.tag)
|
||||
if match:
|
||||
namespace, tag = match.groups()
|
||||
else:
|
||||
namespace = None
|
||||
tag = node.tag
|
||||
attrs = OrderedDict()
|
||||
for name, value in list(node.attrib.items()):
|
||||
match = tag_regexp.match(name)
|
||||
if match:
|
||||
attrs[(match.group(1), match.group(2))] = value
|
||||
else:
|
||||
attrs[(None, name)] = value
|
||||
return (_base.ELEMENT, namespace, tag,
|
||||
attrs, len(node) or node.text)
|
||||
|
||||
def getFirstChild(self, node):
|
||||
if isinstance(node, tuple):
|
||||
element, key, parents, flag = node
|
||||
else:
|
||||
element, key, parents, flag = node, None, [], None
|
||||
|
||||
if flag in ("text", "tail"):
|
||||
return None
|
||||
else:
|
||||
if element.text:
|
||||
return element, key, parents, "text"
|
||||
elif len(element):
|
||||
parents.append(element)
|
||||
return element[0], 0, parents, None
|
||||
else:
|
||||
return None
|
||||
|
||||
def getNextSibling(self, node):
|
||||
if isinstance(node, tuple):
|
||||
element, key, parents, flag = node
|
||||
else:
|
||||
return None
|
||||
|
||||
if flag == "text":
|
||||
if len(element):
|
||||
parents.append(element)
|
||||
return element[0], 0, parents, None
|
||||
else:
|
||||
return None
|
||||
else:
|
||||
if element.tail and flag != "tail":
|
||||
return element, key, parents, "tail"
|
||||
elif key < len(parents[-1]) - 1:
|
||||
return parents[-1][key + 1], key + 1, parents, None
|
||||
else:
|
||||
return None
|
||||
|
||||
def getParentNode(self, node):
|
||||
if isinstance(node, tuple):
|
||||
element, key, parents, flag = node
|
||||
else:
|
||||
return None
|
||||
|
||||
if flag == "text":
|
||||
if not parents:
|
||||
return element
|
||||
else:
|
||||
return element, key, parents, None
|
||||
else:
|
||||
parent = parents.pop()
|
||||
if not parents:
|
||||
return parent
|
||||
else:
|
||||
return parent, list(parents[-1]).index(parent), parents, None
|
||||
|
||||
return locals()
|
||||
|
||||
getETreeModule = moduleFactoryFactory(getETreeBuilder)
|
||||
|
|
@ -0,0 +1,69 @@
|
|||
from __future__ import absolute_import, division, unicode_literals
|
||||
|
||||
from genshi.core import QName
|
||||
from genshi.core import START, END, XML_NAMESPACE, DOCTYPE, TEXT
|
||||
from genshi.core import START_NS, END_NS, START_CDATA, END_CDATA, PI, COMMENT
|
||||
|
||||
from . import _base
|
||||
|
||||
from ..constants import voidElements, namespaces
|
||||
|
||||
|
||||
class TreeWalker(_base.TreeWalker):
|
||||
def __iter__(self):
|
||||
# Buffer the events so we can pass in the following one
|
||||
previous = None
|
||||
for event in self.tree:
|
||||
if previous is not None:
|
||||
for token in self.tokens(previous, event):
|
||||
yield token
|
||||
previous = event
|
||||
|
||||
# Don't forget the final event!
|
||||
if previous is not None:
|
||||
for token in self.tokens(previous, None):
|
||||
yield token
|
||||
|
||||
def tokens(self, event, next):
|
||||
kind, data, pos = event
|
||||
if kind == START:
|
||||
tag, attribs = data
|
||||
name = tag.localname
|
||||
namespace = tag.namespace
|
||||
converted_attribs = {}
|
||||
for k, v in attribs:
|
||||
if isinstance(k, QName):
|
||||
converted_attribs[(k.namespace, k.localname)] = v
|
||||
else:
|
||||
converted_attribs[(None, k)] = v
|
||||
|
||||
if namespace == namespaces["html"] and name in voidElements:
|
||||
for token in self.emptyTag(namespace, name, converted_attribs,
|
||||
not next or next[0] != END
|
||||
or next[1] != tag):
|
||||
yield token
|
||||
else:
|
||||
yield self.startTag(namespace, name, converted_attribs)
|
||||
|
||||
elif kind == END:
|
||||
name = data.localname
|
||||
namespace = data.namespace
|
||||
if name not in voidElements:
|
||||
yield self.endTag(namespace, name)
|
||||
|
||||
elif kind == COMMENT:
|
||||
yield self.comment(data)
|
||||
|
||||
elif kind == TEXT:
|
||||
for token in self.text(data):
|
||||
yield token
|
||||
|
||||
elif kind == DOCTYPE:
|
||||
yield self.doctype(*data)
|
||||
|
||||
elif kind in (XML_NAMESPACE, DOCTYPE, START_NS, END_NS,
|
||||
START_CDATA, END_CDATA, PI):
|
||||
pass
|
||||
|
||||
else:
|
||||
yield self.unknown(kind)
|
||||
|
|
@ -0,0 +1,208 @@
|
|||
from __future__ import absolute_import, division, unicode_literals
|
||||
from pip._vendor.six import text_type
|
||||
|
||||
from lxml import etree
|
||||
from ..treebuilders.etree import tag_regexp
|
||||
|
||||
from gettext import gettext
|
||||
_ = gettext
|
||||
|
||||
from . import _base
|
||||
|
||||
from .. import ihatexml
|
||||
|
||||
|
||||
def ensure_str(s):
|
||||
if s is None:
|
||||
return None
|
||||
elif isinstance(s, text_type):
|
||||
return s
|
||||
else:
|
||||
return s.decode("utf-8", "strict")
|
||||
|
||||
|
||||
class Root(object):
|
||||
def __init__(self, et):
|
||||
self.elementtree = et
|
||||
self.children = []
|
||||
if et.docinfo.internalDTD:
|
||||
self.children.append(Doctype(self,
|
||||
ensure_str(et.docinfo.root_name),
|
||||
ensure_str(et.docinfo.public_id),
|
||||
ensure_str(et.docinfo.system_url)))
|
||||
root = et.getroot()
|
||||
node = root
|
||||
|
||||
while node.getprevious() is not None:
|
||||
node = node.getprevious()
|
||||
while node is not None:
|
||||
self.children.append(node)
|
||||
node = node.getnext()
|
||||
|
||||
self.text = None
|
||||
self.tail = None
|
||||
|
||||
def __getitem__(self, key):
|
||||
return self.children[key]
|
||||
|
||||
def getnext(self):
|
||||
return None
|
||||
|
||||
def __len__(self):
|
||||
return 1
|
||||
|
||||
|
||||
class Doctype(object):
|
||||
def __init__(self, root_node, name, public_id, system_id):
|
||||
self.root_node = root_node
|
||||
self.name = name
|
||||
self.public_id = public_id
|
||||
self.system_id = system_id
|
||||
|
||||
self.text = None
|
||||
self.tail = None
|
||||
|
||||
def getnext(self):
|
||||
return self.root_node.children[1]
|
||||
|
||||
|
||||
class FragmentRoot(Root):
|
||||
def __init__(self, children):
|
||||
self.children = [FragmentWrapper(self, child) for child in children]
|
||||
self.text = self.tail = None
|
||||
|
||||
def getnext(self):
|
||||
return None
|
||||
|
||||
|
||||
class FragmentWrapper(object):
|
||||
def __init__(self, fragment_root, obj):
|
||||
self.root_node = fragment_root
|
||||
self.obj = obj
|
||||
if hasattr(self.obj, 'text'):
|
||||
self.text = ensure_str(self.obj.text)
|
||||
else:
|
||||
self.text = None
|
||||
if hasattr(self.obj, 'tail'):
|
||||
self.tail = ensure_str(self.obj.tail)
|
||||
else:
|
||||
self.tail = None
|
||||
self.isstring = isinstance(obj, str) or isinstance(obj, bytes)
|
||||
# Support for bytes here is Py2
|
||||
if self.isstring:
|
||||
self.obj = ensure_str(self.obj)
|
||||
|
||||
def __getattr__(self, name):
|
||||
return getattr(self.obj, name)
|
||||
|
||||
def getnext(self):
|
||||
siblings = self.root_node.children
|
||||
idx = siblings.index(self)
|
||||
if idx < len(siblings) - 1:
|
||||
return siblings[idx + 1]
|
||||
else:
|
||||
return None
|
||||
|
||||
def __getitem__(self, key):
|
||||
return self.obj[key]
|
||||
|
||||
def __bool__(self):
|
||||
return bool(self.obj)
|
||||
|
||||
def getparent(self):
|
||||
return None
|
||||
|
||||
def __str__(self):
|
||||
return str(self.obj)
|
||||
|
||||
def __unicode__(self):
|
||||
return str(self.obj)
|
||||
|
||||
def __len__(self):
|
||||
return len(self.obj)
|
||||
|
||||
|
||||
class TreeWalker(_base.NonRecursiveTreeWalker):
|
||||
def __init__(self, tree):
|
||||
if hasattr(tree, "getroot"):
|
||||
tree = Root(tree)
|
||||
elif isinstance(tree, list):
|
||||
tree = FragmentRoot(tree)
|
||||
_base.NonRecursiveTreeWalker.__init__(self, tree)
|
||||
self.filter = ihatexml.InfosetFilter()
|
||||
|
||||
def getNodeDetails(self, node):
|
||||
if isinstance(node, tuple): # Text node
|
||||
node, key = node
|
||||
assert key in ("text", "tail"), _("Text nodes are text or tail, found %s") % key
|
||||
return _base.TEXT, ensure_str(getattr(node, key))
|
||||
|
||||
elif isinstance(node, Root):
|
||||
return (_base.DOCUMENT,)
|
||||
|
||||
elif isinstance(node, Doctype):
|
||||
return _base.DOCTYPE, node.name, node.public_id, node.system_id
|
||||
|
||||
elif isinstance(node, FragmentWrapper) and node.isstring:
|
||||
return _base.TEXT, node.obj
|
||||
|
||||
elif node.tag == etree.Comment:
|
||||
return _base.COMMENT, ensure_str(node.text)
|
||||
|
||||
elif node.tag == etree.Entity:
|
||||
return _base.ENTITY, ensure_str(node.text)[1:-1] # strip &;
|
||||
|
||||
else:
|
||||
# This is assumed to be an ordinary element
|
||||
match = tag_regexp.match(ensure_str(node.tag))
|
||||
if match:
|
||||
namespace, tag = match.groups()
|
||||
else:
|
||||
namespace = None
|
||||
tag = ensure_str(node.tag)
|
||||
attrs = {}
|
||||
for name, value in list(node.attrib.items()):
|
||||
name = ensure_str(name)
|
||||
value = ensure_str(value)
|
||||
match = tag_regexp.match(name)
|
||||
if match:
|
||||
attrs[(match.group(1), match.group(2))] = value
|
||||
else:
|
||||
attrs[(None, name)] = value
|
||||
return (_base.ELEMENT, namespace, self.filter.fromXmlName(tag),
|
||||
attrs, len(node) > 0 or node.text)
|
||||
|
||||
def getFirstChild(self, node):
|
||||
assert not isinstance(node, tuple), _("Text nodes have no children")
|
||||
|
||||
assert len(node) or node.text, "Node has no children"
|
||||
if node.text:
|
||||
return (node, "text")
|
||||
else:
|
||||
return node[0]
|
||||
|
||||
def getNextSibling(self, node):
|
||||
if isinstance(node, tuple): # Text node
|
||||
node, key = node
|
||||
assert key in ("text", "tail"), _("Text nodes are text or tail, found %s") % key
|
||||
if key == "text":
|
||||
# XXX: we cannot use a "bool(node) and node[0] or None" construct here
|
||||
# because node[0] might evaluate to False if it has no child element
|
||||
if len(node):
|
||||
return node[0]
|
||||
else:
|
||||
return None
|
||||
else: # tail
|
||||
return node.getnext()
|
||||
|
||||
return (node, "tail") if node.tail else node.getnext()
|
||||
|
||||
def getParentNode(self, node):
|
||||
if isinstance(node, tuple): # Text node
|
||||
node, key = node
|
||||
assert key in ("text", "tail"), _("Text nodes are text or tail, found %s") % key
|
||||
if key == "text":
|
||||
return node
|
||||
# else: fallback to "normal" processing
|
||||
|
||||
return node.getparent()
|
||||
|
|
@ -0,0 +1,63 @@
|
|||
from __future__ import absolute_import, division, unicode_literals
|
||||
|
||||
from xml.dom.pulldom import START_ELEMENT, END_ELEMENT, \
|
||||
COMMENT, IGNORABLE_WHITESPACE, CHARACTERS
|
||||
|
||||
from . import _base
|
||||
|
||||
from ..constants import voidElements
|
||||
|
||||
|
||||
class TreeWalker(_base.TreeWalker):
|
||||
def __iter__(self):
|
||||
ignore_until = None
|
||||
previous = None
|
||||
for event in self.tree:
|
||||
if previous is not None and \
|
||||
(ignore_until is None or previous[1] is ignore_until):
|
||||
if previous[1] is ignore_until:
|
||||
ignore_until = None
|
||||
for token in self.tokens(previous, event):
|
||||
yield token
|
||||
if token["type"] == "EmptyTag":
|
||||
ignore_until = previous[1]
|
||||
previous = event
|
||||
if ignore_until is None or previous[1] is ignore_until:
|
||||
for token in self.tokens(previous, None):
|
||||
yield token
|
||||
elif ignore_until is not None:
|
||||
raise ValueError("Illformed DOM event stream: void element without END_ELEMENT")
|
||||
|
||||
def tokens(self, event, next):
|
||||
type, node = event
|
||||
if type == START_ELEMENT:
|
||||
name = node.nodeName
|
||||
namespace = node.namespaceURI
|
||||
attrs = {}
|
||||
for attr in list(node.attributes.keys()):
|
||||
attr = node.getAttributeNode(attr)
|
||||
attrs[(attr.namespaceURI, attr.localName)] = attr.value
|
||||
if name in voidElements:
|
||||
for token in self.emptyTag(namespace,
|
||||
name,
|
||||
attrs,
|
||||
not next or next[1] is not node):
|
||||
yield token
|
||||
else:
|
||||
yield self.startTag(namespace, name, attrs)
|
||||
|
||||
elif type == END_ELEMENT:
|
||||
name = node.nodeName
|
||||
namespace = node.namespaceURI
|
||||
if name not in voidElements:
|
||||
yield self.endTag(namespace, name)
|
||||
|
||||
elif type == COMMENT:
|
||||
yield self.comment(node.nodeValue)
|
||||
|
||||
elif type in (IGNORABLE_WHITESPACE, CHARACTERS):
|
||||
for token in self.text(node.nodeValue):
|
||||
yield token
|
||||
|
||||
else:
|
||||
yield self.unknown(type)
|
||||
|
|
@ -0,0 +1,12 @@
|
|||
from __future__ import absolute_import, division, unicode_literals
|
||||
|
||||
from .py import Trie as PyTrie
|
||||
|
||||
Trie = PyTrie
|
||||
|
||||
try:
|
||||
from .datrie import Trie as DATrie
|
||||
except ImportError:
|
||||
pass
|
||||
else:
|
||||
Trie = DATrie
|
||||
|
|
@ -0,0 +1,37 @@
|
|||
from __future__ import absolute_import, division, unicode_literals
|
||||
|
||||
from collections import Mapping
|
||||
|
||||
|
||||
class Trie(Mapping):
|
||||
"""Abstract base class for tries"""
|
||||
|
||||
def keys(self, prefix=None):
|
||||
keys = super().keys()
|
||||
|
||||
if prefix is None:
|
||||
return set(keys)
|
||||
|
||||
# Python 2.6: no set comprehensions
|
||||
return set([x for x in keys if x.startswith(prefix)])
|
||||
|
||||
def has_keys_with_prefix(self, prefix):
|
||||
for key in self.keys():
|
||||
if key.startswith(prefix):
|
||||
return True
|
||||
|
||||
return False
|
||||
|
||||
def longest_prefix(self, prefix):
|
||||
if prefix in self:
|
||||
return prefix
|
||||
|
||||
for i in range(1, len(prefix) + 1):
|
||||
if prefix[:-i] in self:
|
||||
return prefix[:-i]
|
||||
|
||||
raise KeyError(prefix)
|
||||
|
||||
def longest_prefix_item(self, prefix):
|
||||
lprefix = self.longest_prefix(prefix)
|
||||
return (lprefix, self[lprefix])
|
||||
|
|
@ -0,0 +1,44 @@
|
|||
from __future__ import absolute_import, division, unicode_literals
|
||||
|
||||
from datrie import Trie as DATrie
|
||||
from pip._vendor.six import text_type
|
||||
|
||||
from ._base import Trie as ABCTrie
|
||||
|
||||
|
||||
class Trie(ABCTrie):
|
||||
def __init__(self, data):
|
||||
chars = set()
|
||||
for key in data.keys():
|
||||
if not isinstance(key, text_type):
|
||||
raise TypeError("All keys must be strings")
|
||||
for char in key:
|
||||
chars.add(char)
|
||||
|
||||
self._data = DATrie("".join(chars))
|
||||
for key, value in data.items():
|
||||
self._data[key] = value
|
||||
|
||||
def __contains__(self, key):
|
||||
return key in self._data
|
||||
|
||||
def __len__(self):
|
||||
return len(self._data)
|
||||
|
||||
def __iter__(self):
|
||||
raise NotImplementedError()
|
||||
|
||||
def __getitem__(self, key):
|
||||
return self._data[key]
|
||||
|
||||
def keys(self, prefix=None):
|
||||
return self._data.keys(prefix)
|
||||
|
||||
def has_keys_with_prefix(self, prefix):
|
||||
return self._data.has_keys_with_prefix(prefix)
|
||||
|
||||
def longest_prefix(self, prefix):
|
||||
return self._data.longest_prefix(prefix)
|
||||
|
||||
def longest_prefix_item(self, prefix):
|
||||
return self._data.longest_prefix_item(prefix)
|
||||
|
|
@ -0,0 +1,67 @@
|
|||
from __future__ import absolute_import, division, unicode_literals
|
||||
from pip._vendor.six import text_type
|
||||
|
||||
from bisect import bisect_left
|
||||
|
||||
from ._base import Trie as ABCTrie
|
||||
|
||||
|
||||
class Trie(ABCTrie):
|
||||
def __init__(self, data):
|
||||
if not all(isinstance(x, text_type) for x in data.keys()):
|
||||
raise TypeError("All keys must be strings")
|
||||
|
||||
self._data = data
|
||||
self._keys = sorted(data.keys())
|
||||
self._cachestr = ""
|
||||
self._cachepoints = (0, len(data))
|
||||
|
||||
def __contains__(self, key):
|
||||
return key in self._data
|
||||
|
||||
def __len__(self):
|
||||
return len(self._data)
|
||||
|
||||
def __iter__(self):
|
||||
return iter(self._data)
|
||||
|
||||
def __getitem__(self, key):
|
||||
return self._data[key]
|
||||
|
||||
def keys(self, prefix=None):
|
||||
if prefix is None or prefix == "" or not self._keys:
|
||||
return set(self._keys)
|
||||
|
||||
if prefix.startswith(self._cachestr):
|
||||
lo, hi = self._cachepoints
|
||||
start = i = bisect_left(self._keys, prefix, lo, hi)
|
||||
else:
|
||||
start = i = bisect_left(self._keys, prefix)
|
||||
|
||||
keys = set()
|
||||
if start == len(self._keys):
|
||||
return keys
|
||||
|
||||
while self._keys[i].startswith(prefix):
|
||||
keys.add(self._keys[i])
|
||||
i += 1
|
||||
|
||||
self._cachestr = prefix
|
||||
self._cachepoints = (start, i)
|
||||
|
||||
return keys
|
||||
|
||||
def has_keys_with_prefix(self, prefix):
|
||||
if prefix in self._data:
|
||||
return True
|
||||
|
||||
if prefix.startswith(self._cachestr):
|
||||
lo, hi = self._cachepoints
|
||||
i = bisect_left(self._keys, prefix, lo, hi)
|
||||
else:
|
||||
i = bisect_left(self._keys, prefix)
|
||||
|
||||
if i == len(self._keys):
|
||||
return False
|
||||
|
||||
return self._keys[i].startswith(prefix)
|
||||
|
|
@ -0,0 +1,82 @@
|
|||
from __future__ import absolute_import, division, unicode_literals
|
||||
|
||||
from types import ModuleType
|
||||
|
||||
try:
|
||||
import xml.etree.cElementTree as default_etree
|
||||
except ImportError:
|
||||
import xml.etree.ElementTree as default_etree
|
||||
|
||||
|
||||
__all__ = ["default_etree", "MethodDispatcher", "isSurrogatePair",
|
||||
"surrogatePairToCodepoint", "moduleFactoryFactory"]
|
||||
|
||||
|
||||
class MethodDispatcher(dict):
|
||||
"""Dict with 2 special properties:
|
||||
|
||||
On initiation, keys that are lists, sets or tuples are converted to
|
||||
multiple keys so accessing any one of the items in the original
|
||||
list-like object returns the matching value
|
||||
|
||||
md = MethodDispatcher({("foo", "bar"):"baz"})
|
||||
md["foo"] == "baz"
|
||||
|
||||
A default value which can be set through the default attribute.
|
||||
"""
|
||||
|
||||
def __init__(self, items=()):
|
||||
# Using _dictEntries instead of directly assigning to self is about
|
||||
# twice as fast. Please do careful performance testing before changing
|
||||
# anything here.
|
||||
_dictEntries = []
|
||||
for name, value in items:
|
||||
if type(name) in (list, tuple, frozenset, set):
|
||||
for item in name:
|
||||
_dictEntries.append((item, value))
|
||||
else:
|
||||
_dictEntries.append((name, value))
|
||||
dict.__init__(self, _dictEntries)
|
||||
self.default = None
|
||||
|
||||
def __getitem__(self, key):
|
||||
return dict.get(self, key, self.default)
|
||||
|
||||
|
||||
# Some utility functions to dal with weirdness around UCS2 vs UCS4
|
||||
# python builds
|
||||
|
||||
def isSurrogatePair(data):
|
||||
return (len(data) == 2 and
|
||||
ord(data[0]) >= 0xD800 and ord(data[0]) <= 0xDBFF and
|
||||
ord(data[1]) >= 0xDC00 and ord(data[1]) <= 0xDFFF)
|
||||
|
||||
|
||||
def surrogatePairToCodepoint(data):
|
||||
char_val = (0x10000 + (ord(data[0]) - 0xD800) * 0x400 +
|
||||
(ord(data[1]) - 0xDC00))
|
||||
return char_val
|
||||
|
||||
# Module Factory Factory (no, this isn't Java, I know)
|
||||
# Here to stop this being duplicated all over the place.
|
||||
|
||||
|
||||
def moduleFactoryFactory(factory):
|
||||
moduleCache = {}
|
||||
|
||||
def moduleFactory(baseModule, *args, **kwargs):
|
||||
if isinstance(ModuleType.__name__, type("")):
|
||||
name = "_%s_factory" % baseModule.__name__
|
||||
else:
|
||||
name = b"_%s_factory" % baseModule.__name__
|
||||
|
||||
if name in moduleCache:
|
||||
return moduleCache[name]
|
||||
else:
|
||||
mod = ModuleType(name)
|
||||
objs = factory(baseModule, *args, **kwargs)
|
||||
mod.__dict__.update(objs)
|
||||
moduleCache[name] = mod
|
||||
return mod
|
||||
|
||||
return moduleFactory
|
||||
2762
Darwin/lib/python3.4/site-packages/pip/_vendor/pkg_resources.py
Normal file
2762
Darwin/lib/python3.4/site-packages/pip/_vendor/pkg_resources.py
Normal file
File diff suppressed because it is too large
Load diff
34
Darwin/lib/python3.4/site-packages/pip/_vendor/re-vendor.py
Normal file
34
Darwin/lib/python3.4/site-packages/pip/_vendor/re-vendor.py
Normal file
|
|
@ -0,0 +1,34 @@
|
|||
import os
|
||||
import sys
|
||||
import pip
|
||||
import glob
|
||||
import shutil
|
||||
|
||||
here = os.path.abspath(os.path.dirname(__file__))
|
||||
|
||||
def usage():
|
||||
print("Usage: re-vendor.py [clean|vendor]")
|
||||
sys.exit(1)
|
||||
|
||||
def clean():
|
||||
for fn in os.listdir(here):
|
||||
dirname = os.path.join(here, fn)
|
||||
if os.path.isdir(dirname):
|
||||
shutil.rmtree(dirname)
|
||||
# six is a single file, not a package
|
||||
os.unlink(os.path.join(here, 'six.py'))
|
||||
|
||||
def vendor():
|
||||
pip.main(['install', '-t', here, '-r', 'vendor.txt'])
|
||||
for dirname in glob.glob('*.egg-info'):
|
||||
shutil.rmtree(dirname)
|
||||
|
||||
if __name__ == '__main__':
|
||||
if len(sys.argv) != 2:
|
||||
usage()
|
||||
if sys.argv[1] == 'clean':
|
||||
clean()
|
||||
elif sys.argv[1] == 'vendor':
|
||||
vendor()
|
||||
else:
|
||||
usage()
|
||||
|
|
@ -0,0 +1,77 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
|
||||
# __
|
||||
# /__) _ _ _ _ _/ _
|
||||
# / ( (- (/ (/ (- _) / _)
|
||||
# /
|
||||
|
||||
"""
|
||||
requests HTTP library
|
||||
~~~~~~~~~~~~~~~~~~~~~
|
||||
|
||||
Requests is an HTTP library, written in Python, for human beings. Basic GET
|
||||
usage:
|
||||
|
||||
>>> import requests
|
||||
>>> r = requests.get('http://python.org')
|
||||
>>> r.status_code
|
||||
200
|
||||
>>> 'Python is a programming language' in r.content
|
||||
True
|
||||
|
||||
... or POST:
|
||||
|
||||
>>> payload = dict(key1='value1', key2='value2')
|
||||
>>> r = requests.post("http://httpbin.org/post", data=payload)
|
||||
>>> print(r.text)
|
||||
{
|
||||
...
|
||||
"form": {
|
||||
"key2": "value2",
|
||||
"key1": "value1"
|
||||
},
|
||||
...
|
||||
}
|
||||
|
||||
The other HTTP methods are supported - see `requests.api`. Full documentation
|
||||
is at <http://python-requests.org>.
|
||||
|
||||
:copyright: (c) 2014 by Kenneth Reitz.
|
||||
:license: Apache 2.0, see LICENSE for more details.
|
||||
|
||||
"""
|
||||
|
||||
__title__ = 'requests'
|
||||
__version__ = '2.3.0'
|
||||
__build__ = 0x020300
|
||||
__author__ = 'Kenneth Reitz'
|
||||
__license__ = 'Apache 2.0'
|
||||
__copyright__ = 'Copyright 2014 Kenneth Reitz'
|
||||
|
||||
# Attempt to enable urllib3's SNI support, if possible
|
||||
try:
|
||||
from .packages.urllib3.contrib import pyopenssl
|
||||
pyopenssl.inject_into_urllib3()
|
||||
except ImportError:
|
||||
pass
|
||||
|
||||
from . import utils
|
||||
from .models import Request, Response, PreparedRequest
|
||||
from .api import request, get, head, post, patch, put, delete, options
|
||||
from .sessions import session, Session
|
||||
from .status_codes import codes
|
||||
from .exceptions import (
|
||||
RequestException, Timeout, URLRequired,
|
||||
TooManyRedirects, HTTPError, ConnectionError
|
||||
)
|
||||
|
||||
# Set default logging handler to avoid "No handler found" warnings.
|
||||
import logging
|
||||
try: # Python 2.7+
|
||||
from logging import NullHandler
|
||||
except ImportError:
|
||||
class NullHandler(logging.Handler):
|
||||
def emit(self, record):
|
||||
pass
|
||||
|
||||
logging.getLogger(__name__).addHandler(NullHandler())
|
||||
|
|
@ -0,0 +1,388 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
|
||||
"""
|
||||
requests.adapters
|
||||
~~~~~~~~~~~~~~~~~
|
||||
|
||||
This module contains the transport adapters that Requests uses to define
|
||||
and maintain connections.
|
||||
"""
|
||||
|
||||
import socket
|
||||
|
||||
from .models import Response
|
||||
from .packages.urllib3.poolmanager import PoolManager, proxy_from_url
|
||||
from .packages.urllib3.response import HTTPResponse
|
||||
from .packages.urllib3.util import Timeout as TimeoutSauce
|
||||
from .compat import urlparse, basestring, urldefrag, unquote
|
||||
from .utils import (DEFAULT_CA_BUNDLE_PATH, get_encoding_from_headers,
|
||||
prepend_scheme_if_needed, get_auth_from_url)
|
||||
from .structures import CaseInsensitiveDict
|
||||
from .packages.urllib3.exceptions import MaxRetryError
|
||||
from .packages.urllib3.exceptions import TimeoutError
|
||||
from .packages.urllib3.exceptions import SSLError as _SSLError
|
||||
from .packages.urllib3.exceptions import HTTPError as _HTTPError
|
||||
from .packages.urllib3.exceptions import ProxyError as _ProxyError
|
||||
from .cookies import extract_cookies_to_jar
|
||||
from .exceptions import ConnectionError, Timeout, SSLError, ProxyError
|
||||
from .auth import _basic_auth_str
|
||||
|
||||
DEFAULT_POOLBLOCK = False
|
||||
DEFAULT_POOLSIZE = 10
|
||||
DEFAULT_RETRIES = 0
|
||||
|
||||
|
||||
class BaseAdapter(object):
|
||||
"""The Base Transport Adapter"""
|
||||
|
||||
def __init__(self):
|
||||
super(BaseAdapter, self).__init__()
|
||||
|
||||
def send(self):
|
||||
raise NotImplementedError
|
||||
|
||||
def close(self):
|
||||
raise NotImplementedError
|
||||
|
||||
|
||||
class HTTPAdapter(BaseAdapter):
|
||||
"""The built-in HTTP Adapter for urllib3.
|
||||
|
||||
Provides a general-case interface for Requests sessions to contact HTTP and
|
||||
HTTPS urls by implementing the Transport Adapter interface. This class will
|
||||
usually be created by the :class:`Session <Session>` class under the
|
||||
covers.
|
||||
|
||||
:param pool_connections: The number of urllib3 connection pools to cache.
|
||||
:param pool_maxsize: The maximum number of connections to save in the pool.
|
||||
:param int max_retries: The maximum number of retries each connection
|
||||
should attempt. Note, this applies only to failed connections and
|
||||
timeouts, never to requests where the server returns a response.
|
||||
:param pool_block: Whether the connection pool should block for connections.
|
||||
|
||||
Usage::
|
||||
|
||||
>>> import requests
|
||||
>>> s = requests.Session()
|
||||
>>> a = requests.adapters.HTTPAdapter(max_retries=3)
|
||||
>>> s.mount('http://', a)
|
||||
"""
|
||||
__attrs__ = ['max_retries', 'config', '_pool_connections', '_pool_maxsize',
|
||||
'_pool_block']
|
||||
|
||||
def __init__(self, pool_connections=DEFAULT_POOLSIZE,
|
||||
pool_maxsize=DEFAULT_POOLSIZE, max_retries=DEFAULT_RETRIES,
|
||||
pool_block=DEFAULT_POOLBLOCK):
|
||||
self.max_retries = max_retries
|
||||
self.config = {}
|
||||
self.proxy_manager = {}
|
||||
|
||||
super(HTTPAdapter, self).__init__()
|
||||
|
||||
self._pool_connections = pool_connections
|
||||
self._pool_maxsize = pool_maxsize
|
||||
self._pool_block = pool_block
|
||||
|
||||
self.init_poolmanager(pool_connections, pool_maxsize, block=pool_block)
|
||||
|
||||
def __getstate__(self):
|
||||
return dict((attr, getattr(self, attr, None)) for attr in
|
||||
self.__attrs__)
|
||||
|
||||
def __setstate__(self, state):
|
||||
# Can't handle by adding 'proxy_manager' to self.__attrs__ because
|
||||
# because self.poolmanager uses a lambda function, which isn't pickleable.
|
||||
self.proxy_manager = {}
|
||||
self.config = {}
|
||||
|
||||
for attr, value in state.items():
|
||||
setattr(self, attr, value)
|
||||
|
||||
self.init_poolmanager(self._pool_connections, self._pool_maxsize,
|
||||
block=self._pool_block)
|
||||
|
||||
def init_poolmanager(self, connections, maxsize, block=DEFAULT_POOLBLOCK):
|
||||
"""Initializes a urllib3 PoolManager. This method should not be called
|
||||
from user code, and is only exposed for use when subclassing the
|
||||
:class:`HTTPAdapter <requests.adapters.HTTPAdapter>`.
|
||||
|
||||
:param connections: The number of urllib3 connection pools to cache.
|
||||
:param maxsize: The maximum number of connections to save in the pool.
|
||||
:param block: Block when no free connections are available.
|
||||
"""
|
||||
# save these values for pickling
|
||||
self._pool_connections = connections
|
||||
self._pool_maxsize = maxsize
|
||||
self._pool_block = block
|
||||
|
||||
self.poolmanager = PoolManager(num_pools=connections, maxsize=maxsize,
|
||||
block=block)
|
||||
|
||||
def cert_verify(self, conn, url, verify, cert):
|
||||
"""Verify a SSL certificate. This method should not be called from user
|
||||
code, and is only exposed for use when subclassing the
|
||||
:class:`HTTPAdapter <requests.adapters.HTTPAdapter>`.
|
||||
|
||||
:param conn: The urllib3 connection object associated with the cert.
|
||||
:param url: The requested URL.
|
||||
:param verify: Whether we should actually verify the certificate.
|
||||
:param cert: The SSL certificate to verify.
|
||||
"""
|
||||
if url.lower().startswith('https') and verify:
|
||||
|
||||
cert_loc = None
|
||||
|
||||
# Allow self-specified cert location.
|
||||
if verify is not True:
|
||||
cert_loc = verify
|
||||
|
||||
if not cert_loc:
|
||||
cert_loc = DEFAULT_CA_BUNDLE_PATH
|
||||
|
||||
if not cert_loc:
|
||||
raise Exception("Could not find a suitable SSL CA certificate bundle.")
|
||||
|
||||
conn.cert_reqs = 'CERT_REQUIRED'
|
||||
conn.ca_certs = cert_loc
|
||||
else:
|
||||
conn.cert_reqs = 'CERT_NONE'
|
||||
conn.ca_certs = None
|
||||
|
||||
if cert:
|
||||
if not isinstance(cert, basestring):
|
||||
conn.cert_file = cert[0]
|
||||
conn.key_file = cert[1]
|
||||
else:
|
||||
conn.cert_file = cert
|
||||
|
||||
def build_response(self, req, resp):
|
||||
"""Builds a :class:`Response <requests.Response>` object from a urllib3
|
||||
response. This should not be called from user code, and is only exposed
|
||||
for use when subclassing the
|
||||
:class:`HTTPAdapter <requests.adapters.HTTPAdapter>`
|
||||
|
||||
:param req: The :class:`PreparedRequest <PreparedRequest>` used to generate the response.
|
||||
:param resp: The urllib3 response object.
|
||||
"""
|
||||
response = Response()
|
||||
|
||||
# Fallback to None if there's no status_code, for whatever reason.
|
||||
response.status_code = getattr(resp, 'status', None)
|
||||
|
||||
# Make headers case-insensitive.
|
||||
response.headers = CaseInsensitiveDict(getattr(resp, 'headers', {}))
|
||||
|
||||
# Set encoding.
|
||||
response.encoding = get_encoding_from_headers(response.headers)
|
||||
response.raw = resp
|
||||
response.reason = response.raw.reason
|
||||
|
||||
if isinstance(req.url, bytes):
|
||||
response.url = req.url.decode('utf-8')
|
||||
else:
|
||||
response.url = req.url
|
||||
|
||||
# Add new cookies from the server.
|
||||
extract_cookies_to_jar(response.cookies, req, resp)
|
||||
|
||||
# Give the Response some context.
|
||||
response.request = req
|
||||
response.connection = self
|
||||
|
||||
return response
|
||||
|
||||
def get_connection(self, url, proxies=None):
|
||||
"""Returns a urllib3 connection for the given URL. This should not be
|
||||
called from user code, and is only exposed for use when subclassing the
|
||||
:class:`HTTPAdapter <requests.adapters.HTTPAdapter>`.
|
||||
|
||||
:param url: The URL to connect to.
|
||||
:param proxies: (optional) A Requests-style dictionary of proxies used on this request.
|
||||
"""
|
||||
proxies = proxies or {}
|
||||
proxy = proxies.get(urlparse(url.lower()).scheme)
|
||||
|
||||
if proxy:
|
||||
proxy = prepend_scheme_if_needed(proxy, 'http')
|
||||
proxy_headers = self.proxy_headers(proxy)
|
||||
|
||||
if not proxy in self.proxy_manager:
|
||||
self.proxy_manager[proxy] = proxy_from_url(
|
||||
proxy,
|
||||
proxy_headers=proxy_headers,
|
||||
num_pools=self._pool_connections,
|
||||
maxsize=self._pool_maxsize,
|
||||
block=self._pool_block)
|
||||
|
||||
conn = self.proxy_manager[proxy].connection_from_url(url)
|
||||
else:
|
||||
# Only scheme should be lower case
|
||||
parsed = urlparse(url)
|
||||
url = parsed.geturl()
|
||||
conn = self.poolmanager.connection_from_url(url)
|
||||
|
||||
return conn
|
||||
|
||||
def close(self):
|
||||
"""Disposes of any internal state.
|
||||
|
||||
Currently, this just closes the PoolManager, which closes pooled
|
||||
connections.
|
||||
"""
|
||||
self.poolmanager.clear()
|
||||
|
||||
def request_url(self, request, proxies):
|
||||
"""Obtain the url to use when making the final request.
|
||||
|
||||
If the message is being sent through a HTTP proxy, the full URL has to
|
||||
be used. Otherwise, we should only use the path portion of the URL.
|
||||
|
||||
This should not be called from user code, and is only exposed for use
|
||||
when subclassing the
|
||||
:class:`HTTPAdapter <requests.adapters.HTTPAdapter>`.
|
||||
|
||||
:param request: The :class:`PreparedRequest <PreparedRequest>` being sent.
|
||||
:param proxies: A dictionary of schemes to proxy URLs.
|
||||
"""
|
||||
proxies = proxies or {}
|
||||
scheme = urlparse(request.url).scheme
|
||||
proxy = proxies.get(scheme)
|
||||
|
||||
if proxy and scheme != 'https':
|
||||
url, _ = urldefrag(request.url)
|
||||
else:
|
||||
url = request.path_url
|
||||
|
||||
return url
|
||||
|
||||
def add_headers(self, request, **kwargs):
|
||||
"""Add any headers needed by the connection. As of v2.0 this does
|
||||
nothing by default, but is left for overriding by users that subclass
|
||||
the :class:`HTTPAdapter <requests.adapters.HTTPAdapter>`.
|
||||
|
||||
This should not be called from user code, and is only exposed for use
|
||||
when subclassing the
|
||||
:class:`HTTPAdapter <requests.adapters.HTTPAdapter>`.
|
||||
|
||||
:param request: The :class:`PreparedRequest <PreparedRequest>` to add headers to.
|
||||
:param kwargs: The keyword arguments from the call to send().
|
||||
"""
|
||||
pass
|
||||
|
||||
def proxy_headers(self, proxy):
|
||||
"""Returns a dictionary of the headers to add to any request sent
|
||||
through a proxy. This works with urllib3 magic to ensure that they are
|
||||
correctly sent to the proxy, rather than in a tunnelled request if
|
||||
CONNECT is being used.
|
||||
|
||||
This should not be called from user code, and is only exposed for use
|
||||
when subclassing the
|
||||
:class:`HTTPAdapter <requests.adapters.HTTPAdapter>`.
|
||||
|
||||
:param proxies: The url of the proxy being used for this request.
|
||||
:param kwargs: Optional additional keyword arguments.
|
||||
"""
|
||||
headers = {}
|
||||
username, password = get_auth_from_url(proxy)
|
||||
|
||||
if username and password:
|
||||
headers['Proxy-Authorization'] = _basic_auth_str(username,
|
||||
password)
|
||||
|
||||
return headers
|
||||
|
||||
def send(self, request, stream=False, timeout=None, verify=True, cert=None, proxies=None):
|
||||
"""Sends PreparedRequest object. Returns Response object.
|
||||
|
||||
:param request: The :class:`PreparedRequest <PreparedRequest>` being sent.
|
||||
:param stream: (optional) Whether to stream the request content.
|
||||
:param timeout: (optional) The timeout on the request.
|
||||
:param verify: (optional) Whether to verify SSL certificates.
|
||||
:param cert: (optional) Any user-provided SSL certificate to be trusted.
|
||||
:param proxies: (optional) The proxies dictionary to apply to the request.
|
||||
"""
|
||||
|
||||
conn = self.get_connection(request.url, proxies)
|
||||
|
||||
self.cert_verify(conn, request.url, verify, cert)
|
||||
url = self.request_url(request, proxies)
|
||||
self.add_headers(request)
|
||||
|
||||
chunked = not (request.body is None or 'Content-Length' in request.headers)
|
||||
|
||||
timeout = TimeoutSauce(connect=timeout, read=timeout)
|
||||
|
||||
try:
|
||||
if not chunked:
|
||||
resp = conn.urlopen(
|
||||
method=request.method,
|
||||
url=url,
|
||||
body=request.body,
|
||||
headers=request.headers,
|
||||
redirect=False,
|
||||
assert_same_host=False,
|
||||
preload_content=False,
|
||||
decode_content=False,
|
||||
retries=self.max_retries,
|
||||
timeout=timeout
|
||||
)
|
||||
|
||||
# Send the request.
|
||||
else:
|
||||
if hasattr(conn, 'proxy_pool'):
|
||||
conn = conn.proxy_pool
|
||||
|
||||
low_conn = conn._get_conn(timeout=timeout)
|
||||
|
||||
try:
|
||||
low_conn.putrequest(request.method,
|
||||
url,
|
||||
skip_accept_encoding=True)
|
||||
|
||||
for header, value in request.headers.items():
|
||||
low_conn.putheader(header, value)
|
||||
|
||||
low_conn.endheaders()
|
||||
|
||||
for i in request.body:
|
||||
low_conn.send(hex(len(i))[2:].encode('utf-8'))
|
||||
low_conn.send(b'\r\n')
|
||||
low_conn.send(i)
|
||||
low_conn.send(b'\r\n')
|
||||
low_conn.send(b'0\r\n\r\n')
|
||||
|
||||
r = low_conn.getresponse()
|
||||
resp = HTTPResponse.from_httplib(
|
||||
r,
|
||||
pool=conn,
|
||||
connection=low_conn,
|
||||
preload_content=False,
|
||||
decode_content=False
|
||||
)
|
||||
except:
|
||||
# If we hit any problems here, clean up the connection.
|
||||
# Then, reraise so that we can handle the actual exception.
|
||||
low_conn.close()
|
||||
raise
|
||||
else:
|
||||
# All is well, return the connection to the pool.
|
||||
conn._put_conn(low_conn)
|
||||
|
||||
except socket.error as sockerr:
|
||||
raise ConnectionError(sockerr, request=request)
|
||||
|
||||
except MaxRetryError as e:
|
||||
raise ConnectionError(e, request=request)
|
||||
|
||||
except _ProxyError as e:
|
||||
raise ProxyError(e)
|
||||
|
||||
except (_SSLError, _HTTPError) as e:
|
||||
if isinstance(e, _SSLError):
|
||||
raise SSLError(e, request=request)
|
||||
elif isinstance(e, TimeoutError):
|
||||
raise Timeout(e, request=request)
|
||||
else:
|
||||
raise
|
||||
|
||||
return self.build_response(request, resp)
|
||||
120
Darwin/lib/python3.4/site-packages/pip/_vendor/requests/api.py
Normal file
120
Darwin/lib/python3.4/site-packages/pip/_vendor/requests/api.py
Normal file
|
|
@ -0,0 +1,120 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
|
||||
"""
|
||||
requests.api
|
||||
~~~~~~~~~~~~
|
||||
|
||||
This module implements the Requests API.
|
||||
|
||||
:copyright: (c) 2012 by Kenneth Reitz.
|
||||
:license: Apache2, see LICENSE for more details.
|
||||
|
||||
"""
|
||||
|
||||
from . import sessions
|
||||
|
||||
|
||||
def request(method, url, **kwargs):
|
||||
"""Constructs and sends a :class:`Request <Request>`.
|
||||
Returns :class:`Response <Response>` object.
|
||||
|
||||
:param method: method for the new :class:`Request` object.
|
||||
:param url: URL for the new :class:`Request` object.
|
||||
:param params: (optional) Dictionary or bytes to be sent in the query string for the :class:`Request`.
|
||||
:param data: (optional) Dictionary, bytes, or file-like object to send in the body of the :class:`Request`.
|
||||
:param headers: (optional) Dictionary of HTTP Headers to send with the :class:`Request`.
|
||||
:param cookies: (optional) Dict or CookieJar object to send with the :class:`Request`.
|
||||
:param files: (optional) Dictionary of 'name': file-like-objects (or {'name': ('filename', fileobj)}) for multipart encoding upload.
|
||||
:param auth: (optional) Auth tuple to enable Basic/Digest/Custom HTTP Auth.
|
||||
:param timeout: (optional) Float describing the timeout of the request in seconds.
|
||||
:param allow_redirects: (optional) Boolean. Set to True if POST/PUT/DELETE redirect following is allowed.
|
||||
:param proxies: (optional) Dictionary mapping protocol to the URL of the proxy.
|
||||
:param verify: (optional) if ``True``, the SSL cert will be verified. A CA_BUNDLE path can also be provided.
|
||||
:param stream: (optional) if ``False``, the response content will be immediately downloaded.
|
||||
:param cert: (optional) if String, path to ssl client cert file (.pem). If Tuple, ('cert', 'key') pair.
|
||||
|
||||
Usage::
|
||||
|
||||
>>> import requests
|
||||
>>> req = requests.request('GET', 'http://httpbin.org/get')
|
||||
<Response [200]>
|
||||
"""
|
||||
|
||||
session = sessions.Session()
|
||||
return session.request(method=method, url=url, **kwargs)
|
||||
|
||||
|
||||
def get(url, **kwargs):
|
||||
"""Sends a GET request. Returns :class:`Response` object.
|
||||
|
||||
:param url: URL for the new :class:`Request` object.
|
||||
:param \*\*kwargs: Optional arguments that ``request`` takes.
|
||||
"""
|
||||
|
||||
kwargs.setdefault('allow_redirects', True)
|
||||
return request('get', url, **kwargs)
|
||||
|
||||
|
||||
def options(url, **kwargs):
|
||||
"""Sends a OPTIONS request. Returns :class:`Response` object.
|
||||
|
||||
:param url: URL for the new :class:`Request` object.
|
||||
:param \*\*kwargs: Optional arguments that ``request`` takes.
|
||||
"""
|
||||
|
||||
kwargs.setdefault('allow_redirects', True)
|
||||
return request('options', url, **kwargs)
|
||||
|
||||
|
||||
def head(url, **kwargs):
|
||||
"""Sends a HEAD request. Returns :class:`Response` object.
|
||||
|
||||
:param url: URL for the new :class:`Request` object.
|
||||
:param \*\*kwargs: Optional arguments that ``request`` takes.
|
||||
"""
|
||||
|
||||
kwargs.setdefault('allow_redirects', False)
|
||||
return request('head', url, **kwargs)
|
||||
|
||||
|
||||
def post(url, data=None, **kwargs):
|
||||
"""Sends a POST request. Returns :class:`Response` object.
|
||||
|
||||
:param url: URL for the new :class:`Request` object.
|
||||
:param data: (optional) Dictionary, bytes, or file-like object to send in the body of the :class:`Request`.
|
||||
:param \*\*kwargs: Optional arguments that ``request`` takes.
|
||||
"""
|
||||
|
||||
return request('post', url, data=data, **kwargs)
|
||||
|
||||
|
||||
def put(url, data=None, **kwargs):
|
||||
"""Sends a PUT request. Returns :class:`Response` object.
|
||||
|
||||
:param url: URL for the new :class:`Request` object.
|
||||
:param data: (optional) Dictionary, bytes, or file-like object to send in the body of the :class:`Request`.
|
||||
:param \*\*kwargs: Optional arguments that ``request`` takes.
|
||||
"""
|
||||
|
||||
return request('put', url, data=data, **kwargs)
|
||||
|
||||
|
||||
def patch(url, data=None, **kwargs):
|
||||
"""Sends a PATCH request. Returns :class:`Response` object.
|
||||
|
||||
:param url: URL for the new :class:`Request` object.
|
||||
:param data: (optional) Dictionary, bytes, or file-like object to send in the body of the :class:`Request`.
|
||||
:param \*\*kwargs: Optional arguments that ``request`` takes.
|
||||
"""
|
||||
|
||||
return request('patch', url, data=data, **kwargs)
|
||||
|
||||
|
||||
def delete(url, **kwargs):
|
||||
"""Sends a DELETE request. Returns :class:`Response` object.
|
||||
|
||||
:param url: URL for the new :class:`Request` object.
|
||||
:param \*\*kwargs: Optional arguments that ``request`` takes.
|
||||
"""
|
||||
|
||||
return request('delete', url, **kwargs)
|
||||
193
Darwin/lib/python3.4/site-packages/pip/_vendor/requests/auth.py
Normal file
193
Darwin/lib/python3.4/site-packages/pip/_vendor/requests/auth.py
Normal file
|
|
@ -0,0 +1,193 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
|
||||
"""
|
||||
requests.auth
|
||||
~~~~~~~~~~~~~
|
||||
|
||||
This module contains the authentication handlers for Requests.
|
||||
"""
|
||||
|
||||
import os
|
||||
import re
|
||||
import time
|
||||
import hashlib
|
||||
|
||||
from base64 import b64encode
|
||||
|
||||
from .compat import urlparse, str
|
||||
from .cookies import extract_cookies_to_jar
|
||||
from .utils import parse_dict_header
|
||||
|
||||
CONTENT_TYPE_FORM_URLENCODED = 'application/x-www-form-urlencoded'
|
||||
CONTENT_TYPE_MULTI_PART = 'multipart/form-data'
|
||||
|
||||
|
||||
def _basic_auth_str(username, password):
|
||||
"""Returns a Basic Auth string."""
|
||||
|
||||
return 'Basic ' + b64encode(('%s:%s' % (username, password)).encode('latin1')).strip().decode('latin1')
|
||||
|
||||
|
||||
class AuthBase(object):
|
||||
"""Base class that all auth implementations derive from"""
|
||||
|
||||
def __call__(self, r):
|
||||
raise NotImplementedError('Auth hooks must be callable.')
|
||||
|
||||
|
||||
class HTTPBasicAuth(AuthBase):
|
||||
"""Attaches HTTP Basic Authentication to the given Request object."""
|
||||
def __init__(self, username, password):
|
||||
self.username = username
|
||||
self.password = password
|
||||
|
||||
def __call__(self, r):
|
||||
r.headers['Authorization'] = _basic_auth_str(self.username, self.password)
|
||||
return r
|
||||
|
||||
|
||||
class HTTPProxyAuth(HTTPBasicAuth):
|
||||
"""Attaches HTTP Proxy Authentication to a given Request object."""
|
||||
def __call__(self, r):
|
||||
r.headers['Proxy-Authorization'] = _basic_auth_str(self.username, self.password)
|
||||
return r
|
||||
|
||||
|
||||
class HTTPDigestAuth(AuthBase):
|
||||
"""Attaches HTTP Digest Authentication to the given Request object."""
|
||||
def __init__(self, username, password):
|
||||
self.username = username
|
||||
self.password = password
|
||||
self.last_nonce = ''
|
||||
self.nonce_count = 0
|
||||
self.chal = {}
|
||||
self.pos = None
|
||||
|
||||
def build_digest_header(self, method, url):
|
||||
|
||||
realm = self.chal['realm']
|
||||
nonce = self.chal['nonce']
|
||||
qop = self.chal.get('qop')
|
||||
algorithm = self.chal.get('algorithm')
|
||||
opaque = self.chal.get('opaque')
|
||||
|
||||
if algorithm is None:
|
||||
_algorithm = 'MD5'
|
||||
else:
|
||||
_algorithm = algorithm.upper()
|
||||
# lambdas assume digest modules are imported at the top level
|
||||
if _algorithm == 'MD5' or _algorithm == 'MD5-SESS':
|
||||
def md5_utf8(x):
|
||||
if isinstance(x, str):
|
||||
x = x.encode('utf-8')
|
||||
return hashlib.md5(x).hexdigest()
|
||||
hash_utf8 = md5_utf8
|
||||
elif _algorithm == 'SHA':
|
||||
def sha_utf8(x):
|
||||
if isinstance(x, str):
|
||||
x = x.encode('utf-8')
|
||||
return hashlib.sha1(x).hexdigest()
|
||||
hash_utf8 = sha_utf8
|
||||
|
||||
KD = lambda s, d: hash_utf8("%s:%s" % (s, d))
|
||||
|
||||
if hash_utf8 is None:
|
||||
return None
|
||||
|
||||
# XXX not implemented yet
|
||||
entdig = None
|
||||
p_parsed = urlparse(url)
|
||||
path = p_parsed.path
|
||||
if p_parsed.query:
|
||||
path += '?' + p_parsed.query
|
||||
|
||||
A1 = '%s:%s:%s' % (self.username, realm, self.password)
|
||||
A2 = '%s:%s' % (method, path)
|
||||
|
||||
HA1 = hash_utf8(A1)
|
||||
HA2 = hash_utf8(A2)
|
||||
|
||||
if nonce == self.last_nonce:
|
||||
self.nonce_count += 1
|
||||
else:
|
||||
self.nonce_count = 1
|
||||
ncvalue = '%08x' % self.nonce_count
|
||||
s = str(self.nonce_count).encode('utf-8')
|
||||
s += nonce.encode('utf-8')
|
||||
s += time.ctime().encode('utf-8')
|
||||
s += os.urandom(8)
|
||||
|
||||
cnonce = (hashlib.sha1(s).hexdigest()[:16])
|
||||
noncebit = "%s:%s:%s:%s:%s" % (nonce, ncvalue, cnonce, qop, HA2)
|
||||
if _algorithm == 'MD5-SESS':
|
||||
HA1 = hash_utf8('%s:%s:%s' % (HA1, nonce, cnonce))
|
||||
|
||||
if qop is None:
|
||||
respdig = KD(HA1, "%s:%s" % (nonce, HA2))
|
||||
elif qop == 'auth' or 'auth' in qop.split(','):
|
||||
respdig = KD(HA1, noncebit)
|
||||
else:
|
||||
# XXX handle auth-int.
|
||||
return None
|
||||
|
||||
self.last_nonce = nonce
|
||||
|
||||
# XXX should the partial digests be encoded too?
|
||||
base = 'username="%s", realm="%s", nonce="%s", uri="%s", ' \
|
||||
'response="%s"' % (self.username, realm, nonce, path, respdig)
|
||||
if opaque:
|
||||
base += ', opaque="%s"' % opaque
|
||||
if algorithm:
|
||||
base += ', algorithm="%s"' % algorithm
|
||||
if entdig:
|
||||
base += ', digest="%s"' % entdig
|
||||
if qop:
|
||||
base += ', qop="auth", nc=%s, cnonce="%s"' % (ncvalue, cnonce)
|
||||
|
||||
return 'Digest %s' % (base)
|
||||
|
||||
def handle_401(self, r, **kwargs):
|
||||
"""Takes the given response and tries digest-auth, if needed."""
|
||||
|
||||
if self.pos is not None:
|
||||
# Rewind the file position indicator of the body to where
|
||||
# it was to resend the request.
|
||||
r.request.body.seek(self.pos)
|
||||
num_401_calls = getattr(self, 'num_401_calls', 1)
|
||||
s_auth = r.headers.get('www-authenticate', '')
|
||||
|
||||
if 'digest' in s_auth.lower() and num_401_calls < 2:
|
||||
|
||||
setattr(self, 'num_401_calls', num_401_calls + 1)
|
||||
pat = re.compile(r'digest ', flags=re.IGNORECASE)
|
||||
self.chal = parse_dict_header(pat.sub('', s_auth, count=1))
|
||||
|
||||
# Consume content and release the original connection
|
||||
# to allow our new request to reuse the same one.
|
||||
r.content
|
||||
r.raw.release_conn()
|
||||
prep = r.request.copy()
|
||||
extract_cookies_to_jar(prep._cookies, r.request, r.raw)
|
||||
prep.prepare_cookies(prep._cookies)
|
||||
|
||||
prep.headers['Authorization'] = self.build_digest_header(
|
||||
prep.method, prep.url)
|
||||
_r = r.connection.send(prep, **kwargs)
|
||||
_r.history.append(r)
|
||||
_r.request = prep
|
||||
|
||||
return _r
|
||||
|
||||
setattr(self, 'num_401_calls', 1)
|
||||
return r
|
||||
|
||||
def __call__(self, r):
|
||||
# If we have a saved nonce, skip the 401
|
||||
if self.last_nonce:
|
||||
r.headers['Authorization'] = self.build_digest_header(r.method, r.url)
|
||||
try:
|
||||
self.pos = r.body.tell()
|
||||
except AttributeError:
|
||||
pass
|
||||
r.register_hook('response', self.handle_401)
|
||||
return r
|
||||
5026
Darwin/lib/python3.4/site-packages/pip/_vendor/requests/cacert.pem
Normal file
5026
Darwin/lib/python3.4/site-packages/pip/_vendor/requests/cacert.pem
Normal file
File diff suppressed because it is too large
Load diff
|
|
@ -0,0 +1,24 @@
|
|||
#!/usr/bin/env python
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
"""
|
||||
certs.py
|
||||
~~~~~~~~
|
||||
|
||||
This module returns the preferred default CA certificate bundle.
|
||||
|
||||
If you are packaging Requests, e.g., for a Linux distribution or a managed
|
||||
environment, you can change the definition of where() to return a separately
|
||||
packaged CA bundle.
|
||||
"""
|
||||
|
||||
import os.path
|
||||
|
||||
|
||||
def where():
|
||||
"""Return the preferred certificate bundle."""
|
||||
# vendored bundle inside Requests
|
||||
return os.path.join(os.path.dirname(__file__), 'cacert.pem')
|
||||
|
||||
if __name__ == '__main__':
|
||||
print(where())
|
||||
|
|
@ -0,0 +1,115 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
|
||||
"""
|
||||
pythoncompat
|
||||
"""
|
||||
|
||||
from .packages import chardet
|
||||
|
||||
import sys
|
||||
|
||||
# -------
|
||||
# Pythons
|
||||
# -------
|
||||
|
||||
# Syntax sugar.
|
||||
_ver = sys.version_info
|
||||
|
||||
#: Python 2.x?
|
||||
is_py2 = (_ver[0] == 2)
|
||||
|
||||
#: Python 3.x?
|
||||
is_py3 = (_ver[0] == 3)
|
||||
|
||||
#: Python 3.0.x
|
||||
is_py30 = (is_py3 and _ver[1] == 0)
|
||||
|
||||
#: Python 3.1.x
|
||||
is_py31 = (is_py3 and _ver[1] == 1)
|
||||
|
||||
#: Python 3.2.x
|
||||
is_py32 = (is_py3 and _ver[1] == 2)
|
||||
|
||||
#: Python 3.3.x
|
||||
is_py33 = (is_py3 and _ver[1] == 3)
|
||||
|
||||
#: Python 3.4.x
|
||||
is_py34 = (is_py3 and _ver[1] == 4)
|
||||
|
||||
#: Python 2.7.x
|
||||
is_py27 = (is_py2 and _ver[1] == 7)
|
||||
|
||||
#: Python 2.6.x
|
||||
is_py26 = (is_py2 and _ver[1] == 6)
|
||||
|
||||
#: Python 2.5.x
|
||||
is_py25 = (is_py2 and _ver[1] == 5)
|
||||
|
||||
#: Python 2.4.x
|
||||
is_py24 = (is_py2 and _ver[1] == 4) # I'm assuming this is not by choice.
|
||||
|
||||
|
||||
# ---------
|
||||
# Platforms
|
||||
# ---------
|
||||
|
||||
|
||||
# Syntax sugar.
|
||||
_ver = sys.version.lower()
|
||||
|
||||
is_pypy = ('pypy' in _ver)
|
||||
is_jython = ('jython' in _ver)
|
||||
is_ironpython = ('iron' in _ver)
|
||||
|
||||
# Assume CPython, if nothing else.
|
||||
is_cpython = not any((is_pypy, is_jython, is_ironpython))
|
||||
|
||||
# Windows-based system.
|
||||
is_windows = 'win32' in str(sys.platform).lower()
|
||||
|
||||
# Standard Linux 2+ system.
|
||||
is_linux = ('linux' in str(sys.platform).lower())
|
||||
is_osx = ('darwin' in str(sys.platform).lower())
|
||||
is_hpux = ('hpux' in str(sys.platform).lower()) # Complete guess.
|
||||
is_solaris = ('solar==' in str(sys.platform).lower()) # Complete guess.
|
||||
|
||||
try:
|
||||
import simplejson as json
|
||||
except ImportError:
|
||||
import json
|
||||
|
||||
# ---------
|
||||
# Specifics
|
||||
# ---------
|
||||
|
||||
if is_py2:
|
||||
from urllib import quote, unquote, quote_plus, unquote_plus, urlencode, getproxies, proxy_bypass
|
||||
from urlparse import urlparse, urlunparse, urljoin, urlsplit, urldefrag
|
||||
from urllib2 import parse_http_list
|
||||
import cookielib
|
||||
from Cookie import Morsel
|
||||
from StringIO import StringIO
|
||||
from .packages.urllib3.packages.ordered_dict import OrderedDict
|
||||
from httplib import IncompleteRead
|
||||
|
||||
builtin_str = str
|
||||
bytes = str
|
||||
str = unicode
|
||||
basestring = basestring
|
||||
numeric_types = (int, long, float)
|
||||
|
||||
|
||||
elif is_py3:
|
||||
from urllib.parse import urlparse, urlunparse, urljoin, urlsplit, urlencode, quote, unquote, quote_plus, unquote_plus, urldefrag
|
||||
from urllib.request import parse_http_list, getproxies, proxy_bypass
|
||||
from http import cookiejar as cookielib
|
||||
from http.cookies import Morsel
|
||||
from io import StringIO
|
||||
from collections import OrderedDict
|
||||
from http.client import IncompleteRead
|
||||
|
||||
builtin_str = str
|
||||
str = str
|
||||
bytes = bytes
|
||||
basestring = (str, bytes)
|
||||
numeric_types = (int, float)
|
||||
|
|
@ -0,0 +1,454 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
|
||||
"""
|
||||
Compatibility code to be able to use `cookielib.CookieJar` with requests.
|
||||
|
||||
requests.utils imports from here, so be careful with imports.
|
||||
"""
|
||||
|
||||
import time
|
||||
import collections
|
||||
from .compat import cookielib, urlparse, urlunparse, Morsel
|
||||
|
||||
try:
|
||||
import threading
|
||||
# grr, pyflakes: this fixes "redefinition of unused 'threading'"
|
||||
threading
|
||||
except ImportError:
|
||||
import dummy_threading as threading
|
||||
|
||||
|
||||
class MockRequest(object):
|
||||
"""Wraps a `requests.Request` to mimic a `urllib2.Request`.
|
||||
|
||||
The code in `cookielib.CookieJar` expects this interface in order to correctly
|
||||
manage cookie policies, i.e., determine whether a cookie can be set, given the
|
||||
domains of the request and the cookie.
|
||||
|
||||
The original request object is read-only. The client is responsible for collecting
|
||||
the new headers via `get_new_headers()` and interpreting them appropriately. You
|
||||
probably want `get_cookie_header`, defined below.
|
||||
"""
|
||||
|
||||
def __init__(self, request):
|
||||
self._r = request
|
||||
self._new_headers = {}
|
||||
self.type = urlparse(self._r.url).scheme
|
||||
|
||||
def get_type(self):
|
||||
return self.type
|
||||
|
||||
def get_host(self):
|
||||
return urlparse(self._r.url).netloc
|
||||
|
||||
def get_origin_req_host(self):
|
||||
return self.get_host()
|
||||
|
||||
def get_full_url(self):
|
||||
# Only return the response's URL if the user hadn't set the Host
|
||||
# header
|
||||
if not self._r.headers.get('Host'):
|
||||
return self._r.url
|
||||
# If they did set it, retrieve it and reconstruct the expected domain
|
||||
host = self._r.headers['Host']
|
||||
parsed = urlparse(self._r.url)
|
||||
# Reconstruct the URL as we expect it
|
||||
return urlunparse([
|
||||
parsed.scheme, host, parsed.path, parsed.params, parsed.query,
|
||||
parsed.fragment
|
||||
])
|
||||
|
||||
def is_unverifiable(self):
|
||||
return True
|
||||
|
||||
def has_header(self, name):
|
||||
return name in self._r.headers or name in self._new_headers
|
||||
|
||||
def get_header(self, name, default=None):
|
||||
return self._r.headers.get(name, self._new_headers.get(name, default))
|
||||
|
||||
def add_header(self, key, val):
|
||||
"""cookielib has no legitimate use for this method; add it back if you find one."""
|
||||
raise NotImplementedError("Cookie headers should be added with add_unredirected_header()")
|
||||
|
||||
def add_unredirected_header(self, name, value):
|
||||
self._new_headers[name] = value
|
||||
|
||||
def get_new_headers(self):
|
||||
return self._new_headers
|
||||
|
||||
@property
|
||||
def unverifiable(self):
|
||||
return self.is_unverifiable()
|
||||
|
||||
@property
|
||||
def origin_req_host(self):
|
||||
return self.get_origin_req_host()
|
||||
|
||||
@property
|
||||
def host(self):
|
||||
return self.get_host()
|
||||
|
||||
|
||||
class MockResponse(object):
|
||||
"""Wraps a `httplib.HTTPMessage` to mimic a `urllib.addinfourl`.
|
||||
|
||||
...what? Basically, expose the parsed HTTP headers from the server response
|
||||
the way `cookielib` expects to see them.
|
||||
"""
|
||||
|
||||
def __init__(self, headers):
|
||||
"""Make a MockResponse for `cookielib` to read.
|
||||
|
||||
:param headers: a httplib.HTTPMessage or analogous carrying the headers
|
||||
"""
|
||||
self._headers = headers
|
||||
|
||||
def info(self):
|
||||
return self._headers
|
||||
|
||||
def getheaders(self, name):
|
||||
self._headers.getheaders(name)
|
||||
|
||||
|
||||
def extract_cookies_to_jar(jar, request, response):
|
||||
"""Extract the cookies from the response into a CookieJar.
|
||||
|
||||
:param jar: cookielib.CookieJar (not necessarily a RequestsCookieJar)
|
||||
:param request: our own requests.Request object
|
||||
:param response: urllib3.HTTPResponse object
|
||||
"""
|
||||
if not (hasattr(response, '_original_response') and
|
||||
response._original_response):
|
||||
return
|
||||
# the _original_response field is the wrapped httplib.HTTPResponse object,
|
||||
req = MockRequest(request)
|
||||
# pull out the HTTPMessage with the headers and put it in the mock:
|
||||
res = MockResponse(response._original_response.msg)
|
||||
jar.extract_cookies(res, req)
|
||||
|
||||
|
||||
def get_cookie_header(jar, request):
|
||||
"""Produce an appropriate Cookie header string to be sent with `request`, or None."""
|
||||
r = MockRequest(request)
|
||||
jar.add_cookie_header(r)
|
||||
return r.get_new_headers().get('Cookie')
|
||||
|
||||
|
||||
def remove_cookie_by_name(cookiejar, name, domain=None, path=None):
|
||||
"""Unsets a cookie by name, by default over all domains and paths.
|
||||
|
||||
Wraps CookieJar.clear(), is O(n).
|
||||
"""
|
||||
clearables = []
|
||||
for cookie in cookiejar:
|
||||
if cookie.name == name:
|
||||
if domain is None or domain == cookie.domain:
|
||||
if path is None or path == cookie.path:
|
||||
clearables.append((cookie.domain, cookie.path, cookie.name))
|
||||
|
||||
for domain, path, name in clearables:
|
||||
cookiejar.clear(domain, path, name)
|
||||
|
||||
|
||||
class CookieConflictError(RuntimeError):
|
||||
"""There are two cookies that meet the criteria specified in the cookie jar.
|
||||
Use .get and .set and include domain and path args in order to be more specific."""
|
||||
|
||||
|
||||
class RequestsCookieJar(cookielib.CookieJar, collections.MutableMapping):
|
||||
"""Compatibility class; is a cookielib.CookieJar, but exposes a dict interface.
|
||||
|
||||
This is the CookieJar we create by default for requests and sessions that
|
||||
don't specify one, since some clients may expect response.cookies and
|
||||
session.cookies to support dict operations.
|
||||
|
||||
Don't use the dict interface internally; it's just for compatibility with
|
||||
with external client code. All `requests` code should work out of the box
|
||||
with externally provided instances of CookieJar, e.g., LWPCookieJar and
|
||||
FileCookieJar.
|
||||
|
||||
Caution: dictionary operations that are normally O(1) may be O(n).
|
||||
|
||||
Unlike a regular CookieJar, this class is pickleable.
|
||||
"""
|
||||
|
||||
def get(self, name, default=None, domain=None, path=None):
|
||||
"""Dict-like get() that also supports optional domain and path args in
|
||||
order to resolve naming collisions from using one cookie jar over
|
||||
multiple domains. Caution: operation is O(n), not O(1)."""
|
||||
try:
|
||||
return self._find_no_duplicates(name, domain, path)
|
||||
except KeyError:
|
||||
return default
|
||||
|
||||
def set(self, name, value, **kwargs):
|
||||
"""Dict-like set() that also supports optional domain and path args in
|
||||
order to resolve naming collisions from using one cookie jar over
|
||||
multiple domains."""
|
||||
# support client code that unsets cookies by assignment of a None value:
|
||||
if value is None:
|
||||
remove_cookie_by_name(self, name, domain=kwargs.get('domain'), path=kwargs.get('path'))
|
||||
return
|
||||
|
||||
if isinstance(value, Morsel):
|
||||
c = morsel_to_cookie(value)
|
||||
else:
|
||||
c = create_cookie(name, value, **kwargs)
|
||||
self.set_cookie(c)
|
||||
return c
|
||||
|
||||
def iterkeys(self):
|
||||
"""Dict-like iterkeys() that returns an iterator of names of cookies from the jar.
|
||||
See itervalues() and iteritems()."""
|
||||
for cookie in iter(self):
|
||||
yield cookie.name
|
||||
|
||||
def keys(self):
|
||||
"""Dict-like keys() that returns a list of names of cookies from the jar.
|
||||
See values() and items()."""
|
||||
return list(self.iterkeys())
|
||||
|
||||
def itervalues(self):
|
||||
"""Dict-like itervalues() that returns an iterator of values of cookies from the jar.
|
||||
See iterkeys() and iteritems()."""
|
||||
for cookie in iter(self):
|
||||
yield cookie.value
|
||||
|
||||
def values(self):
|
||||
"""Dict-like values() that returns a list of values of cookies from the jar.
|
||||
See keys() and items()."""
|
||||
return list(self.itervalues())
|
||||
|
||||
def iteritems(self):
|
||||
"""Dict-like iteritems() that returns an iterator of name-value tuples from the jar.
|
||||
See iterkeys() and itervalues()."""
|
||||
for cookie in iter(self):
|
||||
yield cookie.name, cookie.value
|
||||
|
||||
def items(self):
|
||||
"""Dict-like items() that returns a list of name-value tuples from the jar.
|
||||
See keys() and values(). Allows client-code to call "dict(RequestsCookieJar)
|
||||
and get a vanilla python dict of key value pairs."""
|
||||
return list(self.iteritems())
|
||||
|
||||
def list_domains(self):
|
||||
"""Utility method to list all the domains in the jar."""
|
||||
domains = []
|
||||
for cookie in iter(self):
|
||||
if cookie.domain not in domains:
|
||||
domains.append(cookie.domain)
|
||||
return domains
|
||||
|
||||
def list_paths(self):
|
||||
"""Utility method to list all the paths in the jar."""
|
||||
paths = []
|
||||
for cookie in iter(self):
|
||||
if cookie.path not in paths:
|
||||
paths.append(cookie.path)
|
||||
return paths
|
||||
|
||||
def multiple_domains(self):
|
||||
"""Returns True if there are multiple domains in the jar.
|
||||
Returns False otherwise."""
|
||||
domains = []
|
||||
for cookie in iter(self):
|
||||
if cookie.domain is not None and cookie.domain in domains:
|
||||
return True
|
||||
domains.append(cookie.domain)
|
||||
return False # there is only one domain in jar
|
||||
|
||||
def get_dict(self, domain=None, path=None):
|
||||
"""Takes as an argument an optional domain and path and returns a plain old
|
||||
Python dict of name-value pairs of cookies that meet the requirements."""
|
||||
dictionary = {}
|
||||
for cookie in iter(self):
|
||||
if (domain is None or cookie.domain == domain) and (path is None
|
||||
or cookie.path == path):
|
||||
dictionary[cookie.name] = cookie.value
|
||||
return dictionary
|
||||
|
||||
def __getitem__(self, name):
|
||||
"""Dict-like __getitem__() for compatibility with client code. Throws exception
|
||||
if there are more than one cookie with name. In that case, use the more
|
||||
explicit get() method instead. Caution: operation is O(n), not O(1)."""
|
||||
|
||||
return self._find_no_duplicates(name)
|
||||
|
||||
def __setitem__(self, name, value):
|
||||
"""Dict-like __setitem__ for compatibility with client code. Throws exception
|
||||
if there is already a cookie of that name in the jar. In that case, use the more
|
||||
explicit set() method instead."""
|
||||
|
||||
self.set(name, value)
|
||||
|
||||
def __delitem__(self, name):
|
||||
"""Deletes a cookie given a name. Wraps cookielib.CookieJar's remove_cookie_by_name()."""
|
||||
remove_cookie_by_name(self, name)
|
||||
|
||||
def set_cookie(self, cookie, *args, **kwargs):
|
||||
if hasattr(cookie.value, 'startswith') and cookie.value.startswith('"') and cookie.value.endswith('"'):
|
||||
cookie.value = cookie.value.replace('\\"', '')
|
||||
return super(RequestsCookieJar, self).set_cookie(cookie, *args, **kwargs)
|
||||
|
||||
def update(self, other):
|
||||
"""Updates this jar with cookies from another CookieJar or dict-like"""
|
||||
if isinstance(other, cookielib.CookieJar):
|
||||
for cookie in other:
|
||||
self.set_cookie(cookie)
|
||||
else:
|
||||
super(RequestsCookieJar, self).update(other)
|
||||
|
||||
def _find(self, name, domain=None, path=None):
|
||||
"""Requests uses this method internally to get cookie values. Takes as args name
|
||||
and optional domain and path. Returns a cookie.value. If there are conflicting cookies,
|
||||
_find arbitrarily chooses one. See _find_no_duplicates if you want an exception thrown
|
||||
if there are conflicting cookies."""
|
||||
for cookie in iter(self):
|
||||
if cookie.name == name:
|
||||
if domain is None or cookie.domain == domain:
|
||||
if path is None or cookie.path == path:
|
||||
return cookie.value
|
||||
|
||||
raise KeyError('name=%r, domain=%r, path=%r' % (name, domain, path))
|
||||
|
||||
def _find_no_duplicates(self, name, domain=None, path=None):
|
||||
"""__get_item__ and get call _find_no_duplicates -- never used in Requests internally.
|
||||
Takes as args name and optional domain and path. Returns a cookie.value.
|
||||
Throws KeyError if cookie is not found and CookieConflictError if there are
|
||||
multiple cookies that match name and optionally domain and path."""
|
||||
toReturn = None
|
||||
for cookie in iter(self):
|
||||
if cookie.name == name:
|
||||
if domain is None or cookie.domain == domain:
|
||||
if path is None or cookie.path == path:
|
||||
if toReturn is not None: # if there are multiple cookies that meet passed in criteria
|
||||
raise CookieConflictError('There are multiple cookies with name, %r' % (name))
|
||||
toReturn = cookie.value # we will eventually return this as long as no cookie conflict
|
||||
|
||||
if toReturn:
|
||||
return toReturn
|
||||
raise KeyError('name=%r, domain=%r, path=%r' % (name, domain, path))
|
||||
|
||||
def __getstate__(self):
|
||||
"""Unlike a normal CookieJar, this class is pickleable."""
|
||||
state = self.__dict__.copy()
|
||||
# remove the unpickleable RLock object
|
||||
state.pop('_cookies_lock')
|
||||
return state
|
||||
|
||||
def __setstate__(self, state):
|
||||
"""Unlike a normal CookieJar, this class is pickleable."""
|
||||
self.__dict__.update(state)
|
||||
if '_cookies_lock' not in self.__dict__:
|
||||
self._cookies_lock = threading.RLock()
|
||||
|
||||
def copy(self):
|
||||
"""Return a copy of this RequestsCookieJar."""
|
||||
new_cj = RequestsCookieJar()
|
||||
new_cj.update(self)
|
||||
return new_cj
|
||||
|
||||
|
||||
def create_cookie(name, value, **kwargs):
|
||||
"""Make a cookie from underspecified parameters.
|
||||
|
||||
By default, the pair of `name` and `value` will be set for the domain ''
|
||||
and sent on every request (this is sometimes called a "supercookie").
|
||||
"""
|
||||
result = dict(
|
||||
version=0,
|
||||
name=name,
|
||||
value=value,
|
||||
port=None,
|
||||
domain='',
|
||||
path='/',
|
||||
secure=False,
|
||||
expires=None,
|
||||
discard=True,
|
||||
comment=None,
|
||||
comment_url=None,
|
||||
rest={'HttpOnly': None},
|
||||
rfc2109=False,)
|
||||
|
||||
badargs = set(kwargs) - set(result)
|
||||
if badargs:
|
||||
err = 'create_cookie() got unexpected keyword arguments: %s'
|
||||
raise TypeError(err % list(badargs))
|
||||
|
||||
result.update(kwargs)
|
||||
result['port_specified'] = bool(result['port'])
|
||||
result['domain_specified'] = bool(result['domain'])
|
||||
result['domain_initial_dot'] = result['domain'].startswith('.')
|
||||
result['path_specified'] = bool(result['path'])
|
||||
|
||||
return cookielib.Cookie(**result)
|
||||
|
||||
|
||||
def morsel_to_cookie(morsel):
|
||||
"""Convert a Morsel object into a Cookie containing the one k/v pair."""
|
||||
|
||||
expires = None
|
||||
if morsel['max-age']:
|
||||
expires = time.time() + morsel['max-age']
|
||||
elif morsel['expires']:
|
||||
time_template = '%a, %d-%b-%Y %H:%M:%S GMT'
|
||||
expires = time.mktime(
|
||||
time.strptime(morsel['expires'], time_template)) - time.timezone
|
||||
return create_cookie(
|
||||
comment=morsel['comment'],
|
||||
comment_url=bool(morsel['comment']),
|
||||
discard=False,
|
||||
domain=morsel['domain'],
|
||||
expires=expires,
|
||||
name=morsel.key,
|
||||
path=morsel['path'],
|
||||
port=None,
|
||||
rest={'HttpOnly': morsel['httponly']},
|
||||
rfc2109=False,
|
||||
secure=bool(morsel['secure']),
|
||||
value=morsel.value,
|
||||
version=morsel['version'] or 0,
|
||||
)
|
||||
|
||||
|
||||
def cookiejar_from_dict(cookie_dict, cookiejar=None, overwrite=True):
|
||||
"""Returns a CookieJar from a key/value dictionary.
|
||||
|
||||
:param cookie_dict: Dict of key/values to insert into CookieJar.
|
||||
:param cookiejar: (optional) A cookiejar to add the cookies to.
|
||||
:param overwrite: (optional) If False, will not replace cookies
|
||||
already in the jar with new ones.
|
||||
"""
|
||||
if cookiejar is None:
|
||||
cookiejar = RequestsCookieJar()
|
||||
|
||||
if cookie_dict is not None:
|
||||
names_from_jar = [cookie.name for cookie in cookiejar]
|
||||
for name in cookie_dict:
|
||||
if overwrite or (name not in names_from_jar):
|
||||
cookiejar.set_cookie(create_cookie(name, cookie_dict[name]))
|
||||
|
||||
return cookiejar
|
||||
|
||||
|
||||
def merge_cookies(cookiejar, cookies):
|
||||
"""Add cookies to cookiejar and returns a merged CookieJar.
|
||||
|
||||
:param cookiejar: CookieJar object to add the cookies to.
|
||||
:param cookies: Dictionary or CookieJar object to be added.
|
||||
"""
|
||||
if not isinstance(cookiejar, cookielib.CookieJar):
|
||||
raise ValueError('You can only merge into CookieJar')
|
||||
|
||||
if isinstance(cookies, dict):
|
||||
cookiejar = cookiejar_from_dict(
|
||||
cookies, cookiejar=cookiejar, overwrite=False)
|
||||
elif isinstance(cookies, cookielib.CookieJar):
|
||||
try:
|
||||
cookiejar.update(cookies)
|
||||
except AttributeError:
|
||||
for cookie_in_jar in cookies:
|
||||
cookiejar.set_cookie(cookie_in_jar)
|
||||
|
||||
return cookiejar
|
||||
|
|
@ -0,0 +1,75 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
|
||||
"""
|
||||
requests.exceptions
|
||||
~~~~~~~~~~~~~~~~~~~
|
||||
|
||||
This module contains the set of Requests' exceptions.
|
||||
|
||||
"""
|
||||
from .packages.urllib3.exceptions import HTTPError as BaseHTTPError
|
||||
|
||||
|
||||
class RequestException(IOError):
|
||||
"""There was an ambiguous exception that occurred while handling your
|
||||
request."""
|
||||
|
||||
def __init__(self, *args, **kwargs):
|
||||
"""
|
||||
Initialize RequestException with `request` and `response` objects.
|
||||
"""
|
||||
response = kwargs.pop('response', None)
|
||||
self.response = response
|
||||
self.request = kwargs.pop('request', None)
|
||||
if (response is not None and not self.request and
|
||||
hasattr(response, 'request')):
|
||||
self.request = self.response.request
|
||||
super(RequestException, self).__init__(*args, **kwargs)
|
||||
|
||||
|
||||
class HTTPError(RequestException):
|
||||
"""An HTTP error occurred."""
|
||||
|
||||
|
||||
class ConnectionError(RequestException):
|
||||
"""A Connection error occurred."""
|
||||
|
||||
|
||||
class ProxyError(ConnectionError):
|
||||
"""A proxy error occurred."""
|
||||
|
||||
|
||||
class SSLError(ConnectionError):
|
||||
"""An SSL error occurred."""
|
||||
|
||||
|
||||
class Timeout(RequestException):
|
||||
"""The request timed out."""
|
||||
|
||||
|
||||
class URLRequired(RequestException):
|
||||
"""A valid URL is required to make a request."""
|
||||
|
||||
|
||||
class TooManyRedirects(RequestException):
|
||||
"""Too many redirects."""
|
||||
|
||||
|
||||
class MissingSchema(RequestException, ValueError):
|
||||
"""The URL schema (e.g. http or https) is missing."""
|
||||
|
||||
|
||||
class InvalidSchema(RequestException, ValueError):
|
||||
"""See defaults.py for valid schemas."""
|
||||
|
||||
|
||||
class InvalidURL(RequestException, ValueError):
|
||||
""" The URL provided was somehow invalid. """
|
||||
|
||||
|
||||
class ChunkedEncodingError(RequestException):
|
||||
"""The server declared chunked encoding but sent an invalid chunk."""
|
||||
|
||||
|
||||
class ContentDecodingError(RequestException, BaseHTTPError):
|
||||
"""Failed to decode response content"""
|
||||
|
|
@ -0,0 +1,45 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
|
||||
"""
|
||||
requests.hooks
|
||||
~~~~~~~~~~~~~~
|
||||
|
||||
This module provides the capabilities for the Requests hooks system.
|
||||
|
||||
Available hooks:
|
||||
|
||||
``response``:
|
||||
The response generated from a Request.
|
||||
|
||||
"""
|
||||
|
||||
|
||||
HOOKS = ['response']
|
||||
|
||||
|
||||
def default_hooks():
|
||||
hooks = {}
|
||||
for event in HOOKS:
|
||||
hooks[event] = []
|
||||
return hooks
|
||||
|
||||
# TODO: response is the only one
|
||||
|
||||
|
||||
def dispatch_hook(key, hooks, hook_data, **kwargs):
|
||||
"""Dispatches a hook dictionary on a given piece of data."""
|
||||
|
||||
hooks = hooks or dict()
|
||||
|
||||
if key in hooks:
|
||||
hooks = hooks.get(key)
|
||||
|
||||
if hasattr(hooks, '__call__'):
|
||||
hooks = [hooks]
|
||||
|
||||
for hook in hooks:
|
||||
_hook_data = hook(hook_data, **kwargs)
|
||||
if _hook_data is not None:
|
||||
hook_data = _hook_data
|
||||
|
||||
return hook_data
|
||||
|
|
@ -0,0 +1,803 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
|
||||
"""
|
||||
requests.models
|
||||
~~~~~~~~~~~~~~~
|
||||
|
||||
This module contains the primary objects that power Requests.
|
||||
"""
|
||||
|
||||
import collections
|
||||
import datetime
|
||||
|
||||
from io import BytesIO, UnsupportedOperation
|
||||
from .hooks import default_hooks
|
||||
from .structures import CaseInsensitiveDict
|
||||
|
||||
from .auth import HTTPBasicAuth
|
||||
from .cookies import cookiejar_from_dict, get_cookie_header
|
||||
from .packages.urllib3.fields import RequestField
|
||||
from .packages.urllib3.filepost import encode_multipart_formdata
|
||||
from .packages.urllib3.util import parse_url
|
||||
from .packages.urllib3.exceptions import DecodeError
|
||||
from .exceptions import (
|
||||
HTTPError, RequestException, MissingSchema, InvalidURL,
|
||||
ChunkedEncodingError, ContentDecodingError)
|
||||
from .utils import (
|
||||
guess_filename, get_auth_from_url, requote_uri,
|
||||
stream_decode_response_unicode, to_key_val_list, parse_header_links,
|
||||
iter_slices, guess_json_utf, super_len, to_native_string)
|
||||
from .compat import (
|
||||
cookielib, urlunparse, urlsplit, urlencode, str, bytes, StringIO,
|
||||
is_py2, chardet, json, builtin_str, basestring, IncompleteRead)
|
||||
from .status_codes import codes
|
||||
|
||||
#: The set of HTTP status codes that indicate an automatically
|
||||
#: processable redirect.
|
||||
REDIRECT_STATI = (
|
||||
codes.moved, # 301
|
||||
codes.found, # 302
|
||||
codes.other, # 303
|
||||
codes.temporary_moved, # 307
|
||||
)
|
||||
DEFAULT_REDIRECT_LIMIT = 30
|
||||
CONTENT_CHUNK_SIZE = 10 * 1024
|
||||
ITER_CHUNK_SIZE = 512
|
||||
|
||||
|
||||
class RequestEncodingMixin(object):
|
||||
@property
|
||||
def path_url(self):
|
||||
"""Build the path URL to use."""
|
||||
|
||||
url = []
|
||||
|
||||
p = urlsplit(self.url)
|
||||
|
||||
path = p.path
|
||||
if not path:
|
||||
path = '/'
|
||||
|
||||
url.append(path)
|
||||
|
||||
query = p.query
|
||||
if query:
|
||||
url.append('?')
|
||||
url.append(query)
|
||||
|
||||
return ''.join(url)
|
||||
|
||||
@staticmethod
|
||||
def _encode_params(data):
|
||||
"""Encode parameters in a piece of data.
|
||||
|
||||
Will successfully encode parameters when passed as a dict or a list of
|
||||
2-tuples. Order is retained if data is a list of 2-tuples but arbitrary
|
||||
if parameters are supplied as a dict.
|
||||
"""
|
||||
|
||||
if isinstance(data, (str, bytes)):
|
||||
return data
|
||||
elif hasattr(data, 'read'):
|
||||
return data
|
||||
elif hasattr(data, '__iter__'):
|
||||
result = []
|
||||
for k, vs in to_key_val_list(data):
|
||||
if isinstance(vs, basestring) or not hasattr(vs, '__iter__'):
|
||||
vs = [vs]
|
||||
for v in vs:
|
||||
if v is not None:
|
||||
result.append(
|
||||
(k.encode('utf-8') if isinstance(k, str) else k,
|
||||
v.encode('utf-8') if isinstance(v, str) else v))
|
||||
return urlencode(result, doseq=True)
|
||||
else:
|
||||
return data
|
||||
|
||||
@staticmethod
|
||||
def _encode_files(files, data):
|
||||
"""Build the body for a multipart/form-data request.
|
||||
|
||||
Will successfully encode files when passed as a dict or a list of
|
||||
2-tuples. Order is retained if data is a list of 2-tuples but arbitrary
|
||||
if parameters are supplied as a dict.
|
||||
|
||||
"""
|
||||
if (not files):
|
||||
raise ValueError("Files must be provided.")
|
||||
elif isinstance(data, basestring):
|
||||
raise ValueError("Data must not be a string.")
|
||||
|
||||
new_fields = []
|
||||
fields = to_key_val_list(data or {})
|
||||
files = to_key_val_list(files or {})
|
||||
|
||||
for field, val in fields:
|
||||
if isinstance(val, basestring) or not hasattr(val, '__iter__'):
|
||||
val = [val]
|
||||
for v in val:
|
||||
if v is not None:
|
||||
# Don't call str() on bytestrings: in Py3 it all goes wrong.
|
||||
if not isinstance(v, bytes):
|
||||
v = str(v)
|
||||
|
||||
new_fields.append(
|
||||
(field.decode('utf-8') if isinstance(field, bytes) else field,
|
||||
v.encode('utf-8') if isinstance(v, str) else v))
|
||||
|
||||
for (k, v) in files:
|
||||
# support for explicit filename
|
||||
ft = None
|
||||
fh = None
|
||||
if isinstance(v, (tuple, list)):
|
||||
if len(v) == 2:
|
||||
fn, fp = v
|
||||
elif len(v) == 3:
|
||||
fn, fp, ft = v
|
||||
else:
|
||||
fn, fp, ft, fh = v
|
||||
else:
|
||||
fn = guess_filename(v) or k
|
||||
fp = v
|
||||
if isinstance(fp, str):
|
||||
fp = StringIO(fp)
|
||||
if isinstance(fp, bytes):
|
||||
fp = BytesIO(fp)
|
||||
|
||||
rf = RequestField(name=k, data=fp.read(),
|
||||
filename=fn, headers=fh)
|
||||
rf.make_multipart(content_type=ft)
|
||||
new_fields.append(rf)
|
||||
|
||||
body, content_type = encode_multipart_formdata(new_fields)
|
||||
|
||||
return body, content_type
|
||||
|
||||
|
||||
class RequestHooksMixin(object):
|
||||
def register_hook(self, event, hook):
|
||||
"""Properly register a hook."""
|
||||
|
||||
if event not in self.hooks:
|
||||
raise ValueError('Unsupported event specified, with event name "%s"' % (event))
|
||||
|
||||
if isinstance(hook, collections.Callable):
|
||||
self.hooks[event].append(hook)
|
||||
elif hasattr(hook, '__iter__'):
|
||||
self.hooks[event].extend(h for h in hook if isinstance(h, collections.Callable))
|
||||
|
||||
def deregister_hook(self, event, hook):
|
||||
"""Deregister a previously registered hook.
|
||||
Returns True if the hook existed, False if not.
|
||||
"""
|
||||
|
||||
try:
|
||||
self.hooks[event].remove(hook)
|
||||
return True
|
||||
except ValueError:
|
||||
return False
|
||||
|
||||
|
||||
class Request(RequestHooksMixin):
|
||||
"""A user-created :class:`Request <Request>` object.
|
||||
|
||||
Used to prepare a :class:`PreparedRequest <PreparedRequest>`, which is sent to the server.
|
||||
|
||||
:param method: HTTP method to use.
|
||||
:param url: URL to send.
|
||||
:param headers: dictionary of headers to send.
|
||||
:param files: dictionary of {filename: fileobject} files to multipart upload.
|
||||
:param data: the body to attach the request. If a dictionary is provided, form-encoding will take place.
|
||||
:param params: dictionary of URL parameters to append to the URL.
|
||||
:param auth: Auth handler or (user, pass) tuple.
|
||||
:param cookies: dictionary or CookieJar of cookies to attach to this request.
|
||||
:param hooks: dictionary of callback hooks, for internal usage.
|
||||
|
||||
Usage::
|
||||
|
||||
>>> import requests
|
||||
>>> req = requests.Request('GET', 'http://httpbin.org/get')
|
||||
>>> req.prepare()
|
||||
<PreparedRequest [GET]>
|
||||
|
||||
"""
|
||||
def __init__(self,
|
||||
method=None,
|
||||
url=None,
|
||||
headers=None,
|
||||
files=None,
|
||||
data=None,
|
||||
params=None,
|
||||
auth=None,
|
||||
cookies=None,
|
||||
hooks=None):
|
||||
|
||||
# Default empty dicts for dict params.
|
||||
data = [] if data is None else data
|
||||
files = [] if files is None else files
|
||||
headers = {} if headers is None else headers
|
||||
params = {} if params is None else params
|
||||
hooks = {} if hooks is None else hooks
|
||||
|
||||
self.hooks = default_hooks()
|
||||
for (k, v) in list(hooks.items()):
|
||||
self.register_hook(event=k, hook=v)
|
||||
|
||||
self.method = method
|
||||
self.url = url
|
||||
self.headers = headers
|
||||
self.files = files
|
||||
self.data = data
|
||||
self.params = params
|
||||
self.auth = auth
|
||||
self.cookies = cookies
|
||||
|
||||
def __repr__(self):
|
||||
return '<Request [%s]>' % (self.method)
|
||||
|
||||
def prepare(self):
|
||||
"""Constructs a :class:`PreparedRequest <PreparedRequest>` for transmission and returns it."""
|
||||
p = PreparedRequest()
|
||||
p.prepare(
|
||||
method=self.method,
|
||||
url=self.url,
|
||||
headers=self.headers,
|
||||
files=self.files,
|
||||
data=self.data,
|
||||
params=self.params,
|
||||
auth=self.auth,
|
||||
cookies=self.cookies,
|
||||
hooks=self.hooks,
|
||||
)
|
||||
return p
|
||||
|
||||
|
||||
class PreparedRequest(RequestEncodingMixin, RequestHooksMixin):
|
||||
"""The fully mutable :class:`PreparedRequest <PreparedRequest>` object,
|
||||
containing the exact bytes that will be sent to the server.
|
||||
|
||||
Generated from either a :class:`Request <Request>` object or manually.
|
||||
|
||||
Usage::
|
||||
|
||||
>>> import requests
|
||||
>>> req = requests.Request('GET', 'http://httpbin.org/get')
|
||||
>>> r = req.prepare()
|
||||
<PreparedRequest [GET]>
|
||||
|
||||
>>> s = requests.Session()
|
||||
>>> s.send(r)
|
||||
<Response [200]>
|
||||
|
||||
"""
|
||||
|
||||
def __init__(self):
|
||||
#: HTTP verb to send to the server.
|
||||
self.method = None
|
||||
#: HTTP URL to send the request to.
|
||||
self.url = None
|
||||
#: dictionary of HTTP headers.
|
||||
self.headers = None
|
||||
# The `CookieJar` used to create the Cookie header will be stored here
|
||||
# after prepare_cookies is called
|
||||
self._cookies = None
|
||||
#: request body to send to the server.
|
||||
self.body = None
|
||||
#: dictionary of callback hooks, for internal usage.
|
||||
self.hooks = default_hooks()
|
||||
|
||||
def prepare(self, method=None, url=None, headers=None, files=None,
|
||||
data=None, params=None, auth=None, cookies=None, hooks=None):
|
||||
"""Prepares the entire request with the given parameters."""
|
||||
|
||||
self.prepare_method(method)
|
||||
self.prepare_url(url, params)
|
||||
self.prepare_headers(headers)
|
||||
self.prepare_cookies(cookies)
|
||||
self.prepare_body(data, files)
|
||||
self.prepare_auth(auth, url)
|
||||
# Note that prepare_auth must be last to enable authentication schemes
|
||||
# such as OAuth to work on a fully prepared request.
|
||||
|
||||
# This MUST go after prepare_auth. Authenticators could add a hook
|
||||
self.prepare_hooks(hooks)
|
||||
|
||||
def __repr__(self):
|
||||
return '<PreparedRequest [%s]>' % (self.method)
|
||||
|
||||
def copy(self):
|
||||
p = PreparedRequest()
|
||||
p.method = self.method
|
||||
p.url = self.url
|
||||
p.headers = self.headers.copy()
|
||||
p._cookies = self._cookies.copy()
|
||||
p.body = self.body
|
||||
p.hooks = self.hooks
|
||||
return p
|
||||
|
||||
def prepare_method(self, method):
|
||||
"""Prepares the given HTTP method."""
|
||||
self.method = method
|
||||
if self.method is not None:
|
||||
self.method = self.method.upper()
|
||||
|
||||
def prepare_url(self, url, params):
|
||||
"""Prepares the given HTTP URL."""
|
||||
#: Accept objects that have string representations.
|
||||
try:
|
||||
url = unicode(url)
|
||||
except NameError:
|
||||
# We're on Python 3.
|
||||
url = str(url)
|
||||
except UnicodeDecodeError:
|
||||
pass
|
||||
|
||||
# Don't do any URL preparation for oddball schemes
|
||||
if ':' in url and not url.lower().startswith('http'):
|
||||
self.url = url
|
||||
return
|
||||
|
||||
# Support for unicode domain names and paths.
|
||||
scheme, auth, host, port, path, query, fragment = parse_url(url)
|
||||
|
||||
if not scheme:
|
||||
raise MissingSchema("Invalid URL {0!r}: No schema supplied. "
|
||||
"Perhaps you meant http://{0}?".format(url))
|
||||
|
||||
if not host:
|
||||
raise InvalidURL("Invalid URL %r: No host supplied" % url)
|
||||
|
||||
# Only want to apply IDNA to the hostname
|
||||
try:
|
||||
host = host.encode('idna').decode('utf-8')
|
||||
except UnicodeError:
|
||||
raise InvalidURL('URL has an invalid label.')
|
||||
|
||||
# Carefully reconstruct the network location
|
||||
netloc = auth or ''
|
||||
if netloc:
|
||||
netloc += '@'
|
||||
netloc += host
|
||||
if port:
|
||||
netloc += ':' + str(port)
|
||||
|
||||
# Bare domains aren't valid URLs.
|
||||
if not path:
|
||||
path = '/'
|
||||
|
||||
if is_py2:
|
||||
if isinstance(scheme, str):
|
||||
scheme = scheme.encode('utf-8')
|
||||
if isinstance(netloc, str):
|
||||
netloc = netloc.encode('utf-8')
|
||||
if isinstance(path, str):
|
||||
path = path.encode('utf-8')
|
||||
if isinstance(query, str):
|
||||
query = query.encode('utf-8')
|
||||
if isinstance(fragment, str):
|
||||
fragment = fragment.encode('utf-8')
|
||||
|
||||
enc_params = self._encode_params(params)
|
||||
if enc_params:
|
||||
if query:
|
||||
query = '%s&%s' % (query, enc_params)
|
||||
else:
|
||||
query = enc_params
|
||||
|
||||
url = requote_uri(urlunparse([scheme, netloc, path, None, query, fragment]))
|
||||
self.url = url
|
||||
|
||||
def prepare_headers(self, headers):
|
||||
"""Prepares the given HTTP headers."""
|
||||
|
||||
if headers:
|
||||
self.headers = CaseInsensitiveDict((to_native_string(name), value) for name, value in headers.items())
|
||||
else:
|
||||
self.headers = CaseInsensitiveDict()
|
||||
|
||||
def prepare_body(self, data, files):
|
||||
"""Prepares the given HTTP body data."""
|
||||
|
||||
# Check if file, fo, generator, iterator.
|
||||
# If not, run through normal process.
|
||||
|
||||
# Nottin' on you.
|
||||
body = None
|
||||
content_type = None
|
||||
length = None
|
||||
|
||||
is_stream = all([
|
||||
hasattr(data, '__iter__'),
|
||||
not isinstance(data, (basestring, list, tuple, dict))
|
||||
])
|
||||
|
||||
try:
|
||||
length = super_len(data)
|
||||
except (TypeError, AttributeError, UnsupportedOperation):
|
||||
length = None
|
||||
|
||||
if is_stream:
|
||||
body = data
|
||||
|
||||
if files:
|
||||
raise NotImplementedError('Streamed bodies and files are mutually exclusive.')
|
||||
|
||||
if length is not None:
|
||||
self.headers['Content-Length'] = builtin_str(length)
|
||||
else:
|
||||
self.headers['Transfer-Encoding'] = 'chunked'
|
||||
else:
|
||||
# Multi-part file uploads.
|
||||
if files:
|
||||
(body, content_type) = self._encode_files(files, data)
|
||||
else:
|
||||
if data:
|
||||
body = self._encode_params(data)
|
||||
if isinstance(data, str) or isinstance(data, builtin_str) or hasattr(data, 'read'):
|
||||
content_type = None
|
||||
else:
|
||||
content_type = 'application/x-www-form-urlencoded'
|
||||
|
||||
self.prepare_content_length(body)
|
||||
|
||||
# Add content-type if it wasn't explicitly provided.
|
||||
if (content_type) and (not 'content-type' in self.headers):
|
||||
self.headers['Content-Type'] = content_type
|
||||
|
||||
self.body = body
|
||||
|
||||
def prepare_content_length(self, body):
|
||||
if hasattr(body, 'seek') and hasattr(body, 'tell'):
|
||||
body.seek(0, 2)
|
||||
self.headers['Content-Length'] = builtin_str(body.tell())
|
||||
body.seek(0, 0)
|
||||
elif body is not None:
|
||||
l = super_len(body)
|
||||
if l:
|
||||
self.headers['Content-Length'] = builtin_str(l)
|
||||
elif self.method not in ('GET', 'HEAD'):
|
||||
self.headers['Content-Length'] = '0'
|
||||
|
||||
def prepare_auth(self, auth, url=''):
|
||||
"""Prepares the given HTTP auth data."""
|
||||
|
||||
# If no Auth is explicitly provided, extract it from the URL first.
|
||||
if auth is None:
|
||||
url_auth = get_auth_from_url(self.url)
|
||||
auth = url_auth if any(url_auth) else None
|
||||
|
||||
if auth:
|
||||
if isinstance(auth, tuple) and len(auth) == 2:
|
||||
# special-case basic HTTP auth
|
||||
auth = HTTPBasicAuth(*auth)
|
||||
|
||||
# Allow auth to make its changes.
|
||||
r = auth(self)
|
||||
|
||||
# Update self to reflect the auth changes.
|
||||
self.__dict__.update(r.__dict__)
|
||||
|
||||
# Recompute Content-Length
|
||||
self.prepare_content_length(self.body)
|
||||
|
||||
def prepare_cookies(self, cookies):
|
||||
"""Prepares the given HTTP cookie data."""
|
||||
|
||||
if isinstance(cookies, cookielib.CookieJar):
|
||||
self._cookies = cookies
|
||||
else:
|
||||
self._cookies = cookiejar_from_dict(cookies)
|
||||
|
||||
cookie_header = get_cookie_header(self._cookies, self)
|
||||
if cookie_header is not None:
|
||||
self.headers['Cookie'] = cookie_header
|
||||
|
||||
def prepare_hooks(self, hooks):
|
||||
"""Prepares the given hooks."""
|
||||
for event in hooks:
|
||||
self.register_hook(event, hooks[event])
|
||||
|
||||
|
||||
class Response(object):
|
||||
"""The :class:`Response <Response>` object, which contains a
|
||||
server's response to an HTTP request.
|
||||
"""
|
||||
|
||||
__attrs__ = [
|
||||
'_content',
|
||||
'status_code',
|
||||
'headers',
|
||||
'url',
|
||||
'history',
|
||||
'encoding',
|
||||
'reason',
|
||||
'cookies',
|
||||
'elapsed',
|
||||
'request',
|
||||
]
|
||||
|
||||
def __init__(self):
|
||||
super(Response, self).__init__()
|
||||
|
||||
self._content = False
|
||||
self._content_consumed = False
|
||||
|
||||
#: Integer Code of responded HTTP Status, e.g. 404 or 200.
|
||||
self.status_code = None
|
||||
|
||||
#: Case-insensitive Dictionary of Response Headers.
|
||||
#: For example, ``headers['content-encoding']`` will return the
|
||||
#: value of a ``'Content-Encoding'`` response header.
|
||||
self.headers = CaseInsensitiveDict()
|
||||
|
||||
#: File-like object representation of response (for advanced usage).
|
||||
#: Use of ``raw`` requires that ``stream=True`` be set on the request.
|
||||
# This requirement does not apply for use internally to Requests.
|
||||
self.raw = None
|
||||
|
||||
#: Final URL location of Response.
|
||||
self.url = None
|
||||
|
||||
#: Encoding to decode with when accessing r.text.
|
||||
self.encoding = None
|
||||
|
||||
#: A list of :class:`Response <Response>` objects from
|
||||
#: the history of the Request. Any redirect responses will end
|
||||
#: up here. The list is sorted from the oldest to the most recent request.
|
||||
self.history = []
|
||||
|
||||
#: Textual reason of responded HTTP Status, e.g. "Not Found" or "OK".
|
||||
self.reason = None
|
||||
|
||||
#: A CookieJar of Cookies the server sent back.
|
||||
self.cookies = cookiejar_from_dict({})
|
||||
|
||||
#: The amount of time elapsed between sending the request
|
||||
#: and the arrival of the response (as a timedelta)
|
||||
self.elapsed = datetime.timedelta(0)
|
||||
|
||||
def __getstate__(self):
|
||||
# Consume everything; accessing the content attribute makes
|
||||
# sure the content has been fully read.
|
||||
if not self._content_consumed:
|
||||
self.content
|
||||
|
||||
return dict(
|
||||
(attr, getattr(self, attr, None))
|
||||
for attr in self.__attrs__
|
||||
)
|
||||
|
||||
def __setstate__(self, state):
|
||||
for name, value in state.items():
|
||||
setattr(self, name, value)
|
||||
|
||||
# pickled objects do not have .raw
|
||||
setattr(self, '_content_consumed', True)
|
||||
setattr(self, 'raw', None)
|
||||
|
||||
def __repr__(self):
|
||||
return '<Response [%s]>' % (self.status_code)
|
||||
|
||||
def __bool__(self):
|
||||
"""Returns true if :attr:`status_code` is 'OK'."""
|
||||
return self.ok
|
||||
|
||||
def __nonzero__(self):
|
||||
"""Returns true if :attr:`status_code` is 'OK'."""
|
||||
return self.ok
|
||||
|
||||
def __iter__(self):
|
||||
"""Allows you to use a response as an iterator."""
|
||||
return self.iter_content(128)
|
||||
|
||||
@property
|
||||
def ok(self):
|
||||
try:
|
||||
self.raise_for_status()
|
||||
except RequestException:
|
||||
return False
|
||||
return True
|
||||
|
||||
@property
|
||||
def is_redirect(self):
|
||||
"""True if this Response is a well-formed HTTP redirect that could have
|
||||
been processed automatically (by :meth:`Session.resolve_redirects`).
|
||||
"""
|
||||
return ('location' in self.headers and self.status_code in REDIRECT_STATI)
|
||||
|
||||
@property
|
||||
def apparent_encoding(self):
|
||||
"""The apparent encoding, provided by the chardet library"""
|
||||
return chardet.detect(self.content)['encoding']
|
||||
|
||||
def iter_content(self, chunk_size=1, decode_unicode=False):
|
||||
"""Iterates over the response data. When stream=True is set on the
|
||||
request, this avoids reading the content at once into memory for
|
||||
large responses. The chunk size is the number of bytes it should
|
||||
read into memory. This is not necessarily the length of each item
|
||||
returned as decoding can take place.
|
||||
|
||||
If decode_unicode is True, content will be decoded using the best
|
||||
available encoding based on the response.
|
||||
"""
|
||||
def generate():
|
||||
try:
|
||||
# Special case for urllib3.
|
||||
try:
|
||||
for chunk in self.raw.stream(chunk_size, decode_content=True):
|
||||
yield chunk
|
||||
except IncompleteRead as e:
|
||||
raise ChunkedEncodingError(e)
|
||||
except DecodeError as e:
|
||||
raise ContentDecodingError(e)
|
||||
except AttributeError:
|
||||
# Standard file-like object.
|
||||
while True:
|
||||
chunk = self.raw.read(chunk_size)
|
||||
if not chunk:
|
||||
break
|
||||
yield chunk
|
||||
|
||||
self._content_consumed = True
|
||||
|
||||
# simulate reading small chunks of the content
|
||||
reused_chunks = iter_slices(self._content, chunk_size)
|
||||
|
||||
stream_chunks = generate()
|
||||
|
||||
chunks = reused_chunks if self._content_consumed else stream_chunks
|
||||
|
||||
if decode_unicode:
|
||||
chunks = stream_decode_response_unicode(chunks, self)
|
||||
|
||||
return chunks
|
||||
|
||||
def iter_lines(self, chunk_size=ITER_CHUNK_SIZE, decode_unicode=None):
|
||||
"""Iterates over the response data, one line at a time. When
|
||||
stream=True is set on the request, this avoids reading the
|
||||
content at once into memory for large responses.
|
||||
"""
|
||||
|
||||
pending = None
|
||||
|
||||
for chunk in self.iter_content(chunk_size=chunk_size, decode_unicode=decode_unicode):
|
||||
|
||||
if pending is not None:
|
||||
chunk = pending + chunk
|
||||
lines = chunk.splitlines()
|
||||
|
||||
if lines and lines[-1] and chunk and lines[-1][-1] == chunk[-1]:
|
||||
pending = lines.pop()
|
||||
else:
|
||||
pending = None
|
||||
|
||||
for line in lines:
|
||||
yield line
|
||||
|
||||
if pending is not None:
|
||||
yield pending
|
||||
|
||||
@property
|
||||
def content(self):
|
||||
"""Content of the response, in bytes."""
|
||||
|
||||
if self._content is False:
|
||||
# Read the contents.
|
||||
try:
|
||||
if self._content_consumed:
|
||||
raise RuntimeError(
|
||||
'The content for this response was already consumed')
|
||||
|
||||
if self.status_code == 0:
|
||||
self._content = None
|
||||
else:
|
||||
self._content = bytes().join(self.iter_content(CONTENT_CHUNK_SIZE)) or bytes()
|
||||
|
||||
except AttributeError:
|
||||
self._content = None
|
||||
|
||||
self._content_consumed = True
|
||||
# don't need to release the connection; that's been handled by urllib3
|
||||
# since we exhausted the data.
|
||||
return self._content
|
||||
|
||||
@property
|
||||
def text(self):
|
||||
"""Content of the response, in unicode.
|
||||
|
||||
If Response.encoding is None, encoding will be guessed using
|
||||
``chardet``.
|
||||
|
||||
The encoding of the response content is determined based solely on HTTP
|
||||
headers, following RFC 2616 to the letter. If you can take advantage of
|
||||
non-HTTP knowledge to make a better guess at the encoding, you should
|
||||
set ``r.encoding`` appropriately before accessing this property.
|
||||
"""
|
||||
|
||||
# Try charset from content-type
|
||||
content = None
|
||||
encoding = self.encoding
|
||||
|
||||
if not self.content:
|
||||
return str('')
|
||||
|
||||
# Fallback to auto-detected encoding.
|
||||
if self.encoding is None:
|
||||
encoding = self.apparent_encoding
|
||||
|
||||
# Decode unicode from given encoding.
|
||||
try:
|
||||
content = str(self.content, encoding, errors='replace')
|
||||
except (LookupError, TypeError):
|
||||
# A LookupError is raised if the encoding was not found which could
|
||||
# indicate a misspelling or similar mistake.
|
||||
#
|
||||
# A TypeError can be raised if encoding is None
|
||||
#
|
||||
# So we try blindly encoding.
|
||||
content = str(self.content, errors='replace')
|
||||
|
||||
return content
|
||||
|
||||
def json(self, **kwargs):
|
||||
"""Returns the json-encoded content of a response, if any.
|
||||
|
||||
:param \*\*kwargs: Optional arguments that ``json.loads`` takes.
|
||||
"""
|
||||
|
||||
if not self.encoding and len(self.content) > 3:
|
||||
# No encoding set. JSON RFC 4627 section 3 states we should expect
|
||||
# UTF-8, -16 or -32. Detect which one to use; If the detection or
|
||||
# decoding fails, fall back to `self.text` (using chardet to make
|
||||
# a best guess).
|
||||
encoding = guess_json_utf(self.content)
|
||||
if encoding is not None:
|
||||
try:
|
||||
return json.loads(self.content.decode(encoding), **kwargs)
|
||||
except UnicodeDecodeError:
|
||||
# Wrong UTF codec detected; usually because it's not UTF-8
|
||||
# but some other 8-bit codec. This is an RFC violation,
|
||||
# and the server didn't bother to tell us what codec *was*
|
||||
# used.
|
||||
pass
|
||||
return json.loads(self.text, **kwargs)
|
||||
|
||||
@property
|
||||
def links(self):
|
||||
"""Returns the parsed header links of the response, if any."""
|
||||
|
||||
header = self.headers.get('link')
|
||||
|
||||
# l = MultiDict()
|
||||
l = {}
|
||||
|
||||
if header:
|
||||
links = parse_header_links(header)
|
||||
|
||||
for link in links:
|
||||
key = link.get('rel') or link.get('url')
|
||||
l[key] = link
|
||||
|
||||
return l
|
||||
|
||||
def raise_for_status(self):
|
||||
"""Raises stored :class:`HTTPError`, if one occurred."""
|
||||
|
||||
http_error_msg = ''
|
||||
|
||||
if 400 <= self.status_code < 500:
|
||||
http_error_msg = '%s Client Error: %s' % (self.status_code, self.reason)
|
||||
|
||||
elif 500 <= self.status_code < 600:
|
||||
http_error_msg = '%s Server Error: %s' % (self.status_code, self.reason)
|
||||
|
||||
if http_error_msg:
|
||||
raise HTTPError(http_error_msg, response=self)
|
||||
|
||||
def close(self):
|
||||
"""Releases the connection back to the pool. Once this method has been
|
||||
called the underlying ``raw`` object must not be accessed again.
|
||||
|
||||
*Note: Should not normally need to be called explicitly.*
|
||||
"""
|
||||
return self.raw.release_conn()
|
||||
|
|
@ -0,0 +1,3 @@
|
|||
from __future__ import absolute_import
|
||||
|
||||
from . import urllib3
|
||||
|
|
@ -0,0 +1,32 @@
|
|||
######################## BEGIN LICENSE BLOCK ########################
|
||||
# This library is free software; you can redistribute it and/or
|
||||
# modify it under the terms of the GNU Lesser General Public
|
||||
# License as published by the Free Software Foundation; either
|
||||
# version 2.1 of the License, or (at your option) any later version.
|
||||
#
|
||||
# This library is distributed in the hope that it will be useful,
|
||||
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
||||
# Lesser General Public License for more details.
|
||||
#
|
||||
# You should have received a copy of the GNU Lesser General Public
|
||||
# License along with this library; if not, write to the Free Software
|
||||
# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
|
||||
# 02110-1301 USA
|
||||
######################### END LICENSE BLOCK #########################
|
||||
|
||||
__version__ = "2.2.1"
|
||||
from sys import version_info
|
||||
|
||||
|
||||
def detect(aBuf):
|
||||
if ((version_info < (3, 0) and isinstance(aBuf, unicode)) or
|
||||
(version_info >= (3, 0) and not isinstance(aBuf, bytes))):
|
||||
raise ValueError('Expected a bytes object, not a unicode object')
|
||||
|
||||
from . import universaldetector
|
||||
u = universaldetector.UniversalDetector()
|
||||
u.reset()
|
||||
u.feed(aBuf)
|
||||
u.close()
|
||||
return u.result
|
||||
|
|
@ -0,0 +1,925 @@
|
|||
######################## BEGIN LICENSE BLOCK ########################
|
||||
# The Original Code is Mozilla Communicator client code.
|
||||
#
|
||||
# The Initial Developer of the Original Code is
|
||||
# Netscape Communications Corporation.
|
||||
# Portions created by the Initial Developer are Copyright (C) 1998
|
||||
# the Initial Developer. All Rights Reserved.
|
||||
#
|
||||
# Contributor(s):
|
||||
# Mark Pilgrim - port to Python
|
||||
#
|
||||
# This library is free software; you can redistribute it and/or
|
||||
# modify it under the terms of the GNU Lesser General Public
|
||||
# License as published by the Free Software Foundation; either
|
||||
# version 2.1 of the License, or (at your option) any later version.
|
||||
#
|
||||
# This library is distributed in the hope that it will be useful,
|
||||
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
||||
# Lesser General Public License for more details.
|
||||
#
|
||||
# You should have received a copy of the GNU Lesser General Public
|
||||
# License along with this library; if not, write to the Free Software
|
||||
# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
|
||||
# 02110-1301 USA
|
||||
######################### END LICENSE BLOCK #########################
|
||||
|
||||
# Big5 frequency table
|
||||
# by Taiwan's Mandarin Promotion Council
|
||||
# <http://www.edu.tw:81/mandr/>
|
||||
#
|
||||
# 128 --> 0.42261
|
||||
# 256 --> 0.57851
|
||||
# 512 --> 0.74851
|
||||
# 1024 --> 0.89384
|
||||
# 2048 --> 0.97583
|
||||
#
|
||||
# Ideal Distribution Ratio = 0.74851/(1-0.74851) =2.98
|
||||
# Random Distribution Ration = 512/(5401-512)=0.105
|
||||
#
|
||||
# Typical Distribution Ratio about 25% of Ideal one, still much higher than RDR
|
||||
|
||||
BIG5_TYPICAL_DISTRIBUTION_RATIO = 0.75
|
||||
|
||||
#Char to FreqOrder table
|
||||
BIG5_TABLE_SIZE = 5376
|
||||
|
||||
Big5CharToFreqOrder = (
|
||||
1,1801,1506, 255,1431, 198, 9, 82, 6,5008, 177, 202,3681,1256,2821, 110, # 16
|
||||
3814, 33,3274, 261, 76, 44,2114, 16,2946,2187,1176, 659,3971, 26,3451,2653, # 32
|
||||
1198,3972,3350,4202, 410,2215, 302, 590, 361,1964, 8, 204, 58,4510,5009,1932, # 48
|
||||
63,5010,5011, 317,1614, 75, 222, 159,4203,2417,1480,5012,3555,3091, 224,2822, # 64
|
||||
3682, 3, 10,3973,1471, 29,2787,1135,2866,1940, 873, 130,3275,1123, 312,5013, # 80
|
||||
4511,2052, 507, 252, 682,5014, 142,1915, 124, 206,2947, 34,3556,3204, 64, 604, # 96
|
||||
5015,2501,1977,1978, 155,1991, 645, 641,1606,5016,3452, 337, 72, 406,5017, 80, # 112
|
||||
630, 238,3205,1509, 263, 939,1092,2654, 756,1440,1094,3453, 449, 69,2987, 591, # 128
|
||||
179,2096, 471, 115,2035,1844, 60, 50,2988, 134, 806,1869, 734,2036,3454, 180, # 144
|
||||
995,1607, 156, 537,2907, 688,5018, 319,1305, 779,2145, 514,2379, 298,4512, 359, # 160
|
||||
2502, 90,2716,1338, 663, 11, 906,1099,2553, 20,2441, 182, 532,1716,5019, 732, # 176
|
||||
1376,4204,1311,1420,3206, 25,2317,1056, 113, 399, 382,1950, 242,3455,2474, 529, # 192
|
||||
3276, 475,1447,3683,5020, 117, 21, 656, 810,1297,2300,2334,3557,5021, 126,4205, # 208
|
||||
706, 456, 150, 613,4513, 71,1118,2037,4206, 145,3092, 85, 835, 486,2115,1246, # 224
|
||||
1426, 428, 727,1285,1015, 800, 106, 623, 303,1281,5022,2128,2359, 347,3815, 221, # 240
|
||||
3558,3135,5023,1956,1153,4207, 83, 296,1199,3093, 192, 624, 93,5024, 822,1898, # 256
|
||||
2823,3136, 795,2065, 991,1554,1542,1592, 27, 43,2867, 859, 139,1456, 860,4514, # 272
|
||||
437, 712,3974, 164,2397,3137, 695, 211,3037,2097, 195,3975,1608,3559,3560,3684, # 288
|
||||
3976, 234, 811,2989,2098,3977,2233,1441,3561,1615,2380, 668,2077,1638, 305, 228, # 304
|
||||
1664,4515, 467, 415,5025, 262,2099,1593, 239, 108, 300, 200,1033, 512,1247,2078, # 320
|
||||
5026,5027,2176,3207,3685,2682, 593, 845,1062,3277, 88,1723,2038,3978,1951, 212, # 336
|
||||
266, 152, 149, 468,1899,4208,4516, 77, 187,5028,3038, 37, 5,2990,5029,3979, # 352
|
||||
5030,5031, 39,2524,4517,2908,3208,2079, 55, 148, 74,4518, 545, 483,1474,1029, # 368
|
||||
1665, 217,1870,1531,3138,1104,2655,4209, 24, 172,3562, 900,3980,3563,3564,4519, # 384
|
||||
32,1408,2824,1312, 329, 487,2360,2251,2717, 784,2683, 4,3039,3351,1427,1789, # 400
|
||||
188, 109, 499,5032,3686,1717,1790, 888,1217,3040,4520,5033,3565,5034,3352,1520, # 416
|
||||
3687,3981, 196,1034, 775,5035,5036, 929,1816, 249, 439, 38,5037,1063,5038, 794, # 432
|
||||
3982,1435,2301, 46, 178,3278,2066,5039,2381,5040, 214,1709,4521, 804, 35, 707, # 448
|
||||
324,3688,1601,2554, 140, 459,4210,5041,5042,1365, 839, 272, 978,2262,2580,3456, # 464
|
||||
2129,1363,3689,1423, 697, 100,3094, 48, 70,1231, 495,3139,2196,5043,1294,5044, # 480
|
||||
2080, 462, 586,1042,3279, 853, 256, 988, 185,2382,3457,1698, 434,1084,5045,3458, # 496
|
||||
314,2625,2788,4522,2335,2336, 569,2285, 637,1817,2525, 757,1162,1879,1616,3459, # 512
|
||||
287,1577,2116, 768,4523,1671,2868,3566,2526,1321,3816, 909,2418,5046,4211, 933, # 528
|
||||
3817,4212,2053,2361,1222,4524, 765,2419,1322, 786,4525,5047,1920,1462,1677,2909, # 544
|
||||
1699,5048,4526,1424,2442,3140,3690,2600,3353,1775,1941,3460,3983,4213, 309,1369, # 560
|
||||
1130,2825, 364,2234,1653,1299,3984,3567,3985,3986,2656, 525,1085,3041, 902,2001, # 576
|
||||
1475, 964,4527, 421,1845,1415,1057,2286, 940,1364,3141, 376,4528,4529,1381, 7, # 592
|
||||
2527, 983,2383, 336,1710,2684,1846, 321,3461, 559,1131,3042,2752,1809,1132,1313, # 608
|
||||
265,1481,1858,5049, 352,1203,2826,3280, 167,1089, 420,2827, 776, 792,1724,3568, # 624
|
||||
4214,2443,3281,5050,4215,5051, 446, 229, 333,2753, 901,3818,1200,1557,4530,2657, # 640
|
||||
1921, 395,2754,2685,3819,4216,1836, 125, 916,3209,2626,4531,5052,5053,3820,5054, # 656
|
||||
5055,5056,4532,3142,3691,1133,2555,1757,3462,1510,2318,1409,3569,5057,2146, 438, # 672
|
||||
2601,2910,2384,3354,1068, 958,3043, 461, 311,2869,2686,4217,1916,3210,4218,1979, # 688
|
||||
383, 750,2755,2627,4219, 274, 539, 385,1278,1442,5058,1154,1965, 384, 561, 210, # 704
|
||||
98,1295,2556,3570,5059,1711,2420,1482,3463,3987,2911,1257, 129,5060,3821, 642, # 720
|
||||
523,2789,2790,2658,5061, 141,2235,1333, 68, 176, 441, 876, 907,4220, 603,2602, # 736
|
||||
710, 171,3464, 404, 549, 18,3143,2398,1410,3692,1666,5062,3571,4533,2912,4534, # 752
|
||||
5063,2991, 368,5064, 146, 366, 99, 871,3693,1543, 748, 807,1586,1185, 22,2263, # 768
|
||||
379,3822,3211,5065,3212, 505,1942,2628,1992,1382,2319,5066, 380,2362, 218, 702, # 784
|
||||
1818,1248,3465,3044,3572,3355,3282,5067,2992,3694, 930,3283,3823,5068, 59,5069, # 800
|
||||
585, 601,4221, 497,3466,1112,1314,4535,1802,5070,1223,1472,2177,5071, 749,1837, # 816
|
||||
690,1900,3824,1773,3988,1476, 429,1043,1791,2236,2117, 917,4222, 447,1086,1629, # 832
|
||||
5072, 556,5073,5074,2021,1654, 844,1090, 105, 550, 966,1758,2828,1008,1783, 686, # 848
|
||||
1095,5075,2287, 793,1602,5076,3573,2603,4536,4223,2948,2302,4537,3825, 980,2503, # 864
|
||||
544, 353, 527,4538, 908,2687,2913,5077, 381,2629,1943,1348,5078,1341,1252, 560, # 880
|
||||
3095,5079,3467,2870,5080,2054, 973, 886,2081, 143,4539,5081,5082, 157,3989, 496, # 896
|
||||
4224, 57, 840, 540,2039,4540,4541,3468,2118,1445, 970,2264,1748,1966,2082,4225, # 912
|
||||
3144,1234,1776,3284,2829,3695, 773,1206,2130,1066,2040,1326,3990,1738,1725,4226, # 928
|
||||
279,3145, 51,1544,2604, 423,1578,2131,2067, 173,4542,1880,5083,5084,1583, 264, # 944
|
||||
610,3696,4543,2444, 280, 154,5085,5086,5087,1739, 338,1282,3096, 693,2871,1411, # 960
|
||||
1074,3826,2445,5088,4544,5089,5090,1240, 952,2399,5091,2914,1538,2688, 685,1483, # 976
|
||||
4227,2475,1436, 953,4228,2055,4545, 671,2400, 79,4229,2446,3285, 608, 567,2689, # 992
|
||||
3469,4230,4231,1691, 393,1261,1792,2401,5092,4546,5093,5094,5095,5096,1383,1672, # 1008
|
||||
3827,3213,1464, 522,1119, 661,1150, 216, 675,4547,3991,1432,3574, 609,4548,2690, # 1024
|
||||
2402,5097,5098,5099,4232,3045, 0,5100,2476, 315, 231,2447, 301,3356,4549,2385, # 1040
|
||||
5101, 233,4233,3697,1819,4550,4551,5102, 96,1777,1315,2083,5103, 257,5104,1810, # 1056
|
||||
3698,2718,1139,1820,4234,2022,1124,2164,2791,1778,2659,5105,3097, 363,1655,3214, # 1072
|
||||
5106,2993,5107,5108,5109,3992,1567,3993, 718, 103,3215, 849,1443, 341,3357,2949, # 1088
|
||||
1484,5110,1712, 127, 67, 339,4235,2403, 679,1412, 821,5111,5112, 834, 738, 351, # 1104
|
||||
2994,2147, 846, 235,1497,1881, 418,1993,3828,2719, 186,1100,2148,2756,3575,1545, # 1120
|
||||
1355,2950,2872,1377, 583,3994,4236,2581,2995,5113,1298,3699,1078,2557,3700,2363, # 1136
|
||||
78,3829,3830, 267,1289,2100,2002,1594,4237, 348, 369,1274,2197,2178,1838,4552, # 1152
|
||||
1821,2830,3701,2757,2288,2003,4553,2951,2758, 144,3358, 882,4554,3995,2759,3470, # 1168
|
||||
4555,2915,5114,4238,1726, 320,5115,3996,3046, 788,2996,5116,2831,1774,1327,2873, # 1184
|
||||
3997,2832,5117,1306,4556,2004,1700,3831,3576,2364,2660, 787,2023, 506, 824,3702, # 1200
|
||||
534, 323,4557,1044,3359,2024,1901, 946,3471,5118,1779,1500,1678,5119,1882,4558, # 1216
|
||||
165, 243,4559,3703,2528, 123, 683,4239, 764,4560, 36,3998,1793, 589,2916, 816, # 1232
|
||||
626,1667,3047,2237,1639,1555,1622,3832,3999,5120,4000,2874,1370,1228,1933, 891, # 1248
|
||||
2084,2917, 304,4240,5121, 292,2997,2720,3577, 691,2101,4241,1115,4561, 118, 662, # 1264
|
||||
5122, 611,1156, 854,2386,1316,2875, 2, 386, 515,2918,5123,5124,3286, 868,2238, # 1280
|
||||
1486, 855,2661, 785,2216,3048,5125,1040,3216,3578,5126,3146, 448,5127,1525,5128, # 1296
|
||||
2165,4562,5129,3833,5130,4242,2833,3579,3147, 503, 818,4001,3148,1568, 814, 676, # 1312
|
||||
1444, 306,1749,5131,3834,1416,1030, 197,1428, 805,2834,1501,4563,5132,5133,5134, # 1328
|
||||
1994,5135,4564,5136,5137,2198, 13,2792,3704,2998,3149,1229,1917,5138,3835,2132, # 1344
|
||||
5139,4243,4565,2404,3580,5140,2217,1511,1727,1120,5141,5142, 646,3836,2448, 307, # 1360
|
||||
5143,5144,1595,3217,5145,5146,5147,3705,1113,1356,4002,1465,2529,2530,5148, 519, # 1376
|
||||
5149, 128,2133, 92,2289,1980,5150,4003,1512, 342,3150,2199,5151,2793,2218,1981, # 1392
|
||||
3360,4244, 290,1656,1317, 789, 827,2365,5152,3837,4566, 562, 581,4004,5153, 401, # 1408
|
||||
4567,2252, 94,4568,5154,1399,2794,5155,1463,2025,4569,3218,1944,5156, 828,1105, # 1424
|
||||
4245,1262,1394,5157,4246, 605,4570,5158,1784,2876,5159,2835, 819,2102, 578,2200, # 1440
|
||||
2952,5160,1502, 436,3287,4247,3288,2836,4005,2919,3472,3473,5161,2721,2320,5162, # 1456
|
||||
5163,2337,2068, 23,4571, 193, 826,3838,2103, 699,1630,4248,3098, 390,1794,1064, # 1472
|
||||
3581,5164,1579,3099,3100,1400,5165,4249,1839,1640,2877,5166,4572,4573, 137,4250, # 1488
|
||||
598,3101,1967, 780, 104, 974,2953,5167, 278, 899, 253, 402, 572, 504, 493,1339, # 1504
|
||||
5168,4006,1275,4574,2582,2558,5169,3706,3049,3102,2253, 565,1334,2722, 863, 41, # 1520
|
||||
5170,5171,4575,5172,1657,2338, 19, 463,2760,4251, 606,5173,2999,3289,1087,2085, # 1536
|
||||
1323,2662,3000,5174,1631,1623,1750,4252,2691,5175,2878, 791,2723,2663,2339, 232, # 1552
|
||||
2421,5176,3001,1498,5177,2664,2630, 755,1366,3707,3290,3151,2026,1609, 119,1918, # 1568
|
||||
3474, 862,1026,4253,5178,4007,3839,4576,4008,4577,2265,1952,2477,5179,1125, 817, # 1584
|
||||
4254,4255,4009,1513,1766,2041,1487,4256,3050,3291,2837,3840,3152,5180,5181,1507, # 1600
|
||||
5182,2692, 733, 40,1632,1106,2879, 345,4257, 841,2531, 230,4578,3002,1847,3292, # 1616
|
||||
3475,5183,1263, 986,3476,5184, 735, 879, 254,1137, 857, 622,1300,1180,1388,1562, # 1632
|
||||
4010,4011,2954, 967,2761,2665,1349, 592,2134,1692,3361,3003,1995,4258,1679,4012, # 1648
|
||||
1902,2188,5185, 739,3708,2724,1296,1290,5186,4259,2201,2202,1922,1563,2605,2559, # 1664
|
||||
1871,2762,3004,5187, 435,5188, 343,1108, 596, 17,1751,4579,2239,3477,3709,5189, # 1680
|
||||
4580, 294,3582,2955,1693, 477, 979, 281,2042,3583, 643,2043,3710,2631,2795,2266, # 1696
|
||||
1031,2340,2135,2303,3584,4581, 367,1249,2560,5190,3585,5191,4582,1283,3362,2005, # 1712
|
||||
240,1762,3363,4583,4584, 836,1069,3153, 474,5192,2149,2532, 268,3586,5193,3219, # 1728
|
||||
1521,1284,5194,1658,1546,4260,5195,3587,3588,5196,4261,3364,2693,1685,4262, 961, # 1744
|
||||
1673,2632, 190,2006,2203,3841,4585,4586,5197, 570,2504,3711,1490,5198,4587,2633, # 1760
|
||||
3293,1957,4588, 584,1514, 396,1045,1945,5199,4589,1968,2449,5200,5201,4590,4013, # 1776
|
||||
619,5202,3154,3294, 215,2007,2796,2561,3220,4591,3221,4592, 763,4263,3842,4593, # 1792
|
||||
5203,5204,1958,1767,2956,3365,3712,1174, 452,1477,4594,3366,3155,5205,2838,1253, # 1808
|
||||
2387,2189,1091,2290,4264, 492,5206, 638,1169,1825,2136,1752,4014, 648, 926,1021, # 1824
|
||||
1324,4595, 520,4596, 997, 847,1007, 892,4597,3843,2267,1872,3713,2405,1785,4598, # 1840
|
||||
1953,2957,3103,3222,1728,4265,2044,3714,4599,2008,1701,3156,1551, 30,2268,4266, # 1856
|
||||
5207,2027,4600,3589,5208, 501,5209,4267, 594,3478,2166,1822,3590,3479,3591,3223, # 1872
|
||||
829,2839,4268,5210,1680,3157,1225,4269,5211,3295,4601,4270,3158,2341,5212,4602, # 1888
|
||||
4271,5213,4015,4016,5214,1848,2388,2606,3367,5215,4603, 374,4017, 652,4272,4273, # 1904
|
||||
375,1140, 798,5216,5217,5218,2366,4604,2269, 546,1659, 138,3051,2450,4605,5219, # 1920
|
||||
2254, 612,1849, 910, 796,3844,1740,1371, 825,3845,3846,5220,2920,2562,5221, 692, # 1936
|
||||
444,3052,2634, 801,4606,4274,5222,1491, 244,1053,3053,4275,4276, 340,5223,4018, # 1952
|
||||
1041,3005, 293,1168, 87,1357,5224,1539, 959,5225,2240, 721, 694,4277,3847, 219, # 1968
|
||||
1478, 644,1417,3368,2666,1413,1401,1335,1389,4019,5226,5227,3006,2367,3159,1826, # 1984
|
||||
730,1515, 184,2840, 66,4607,5228,1660,2958, 246,3369, 378,1457, 226,3480, 975, # 2000
|
||||
4020,2959,1264,3592, 674, 696,5229, 163,5230,1141,2422,2167, 713,3593,3370,4608, # 2016
|
||||
4021,5231,5232,1186, 15,5233,1079,1070,5234,1522,3224,3594, 276,1050,2725, 758, # 2032
|
||||
1126, 653,2960,3296,5235,2342, 889,3595,4022,3104,3007, 903,1250,4609,4023,3481, # 2048
|
||||
3596,1342,1681,1718, 766,3297, 286, 89,2961,3715,5236,1713,5237,2607,3371,3008, # 2064
|
||||
5238,2962,2219,3225,2880,5239,4610,2505,2533, 181, 387,1075,4024, 731,2190,3372, # 2080
|
||||
5240,3298, 310, 313,3482,2304, 770,4278, 54,3054, 189,4611,3105,3848,4025,5241, # 2096
|
||||
1230,1617,1850, 355,3597,4279,4612,3373, 111,4280,3716,1350,3160,3483,3055,4281, # 2112
|
||||
2150,3299,3598,5242,2797,4026,4027,3009, 722,2009,5243,1071, 247,1207,2343,2478, # 2128
|
||||
1378,4613,2010, 864,1437,1214,4614, 373,3849,1142,2220, 667,4615, 442,2763,2563, # 2144
|
||||
3850,4028,1969,4282,3300,1840, 837, 170,1107, 934,1336,1883,5244,5245,2119,4283, # 2160
|
||||
2841, 743,1569,5246,4616,4284, 582,2389,1418,3484,5247,1803,5248, 357,1395,1729, # 2176
|
||||
3717,3301,2423,1564,2241,5249,3106,3851,1633,4617,1114,2086,4285,1532,5250, 482, # 2192
|
||||
2451,4618,5251,5252,1492, 833,1466,5253,2726,3599,1641,2842,5254,1526,1272,3718, # 2208
|
||||
4286,1686,1795, 416,2564,1903,1954,1804,5255,3852,2798,3853,1159,2321,5256,2881, # 2224
|
||||
4619,1610,1584,3056,2424,2764, 443,3302,1163,3161,5257,5258,4029,5259,4287,2506, # 2240
|
||||
3057,4620,4030,3162,2104,1647,3600,2011,1873,4288,5260,4289, 431,3485,5261, 250, # 2256
|
||||
97, 81,4290,5262,1648,1851,1558, 160, 848,5263, 866, 740,1694,5264,2204,2843, # 2272
|
||||
3226,4291,4621,3719,1687, 950,2479, 426, 469,3227,3720,3721,4031,5265,5266,1188, # 2288
|
||||
424,1996, 861,3601,4292,3854,2205,2694, 168,1235,3602,4293,5267,2087,1674,4622, # 2304
|
||||
3374,3303, 220,2565,1009,5268,3855, 670,3010, 332,1208, 717,5269,5270,3603,2452, # 2320
|
||||
4032,3375,5271, 513,5272,1209,2882,3376,3163,4623,1080,5273,5274,5275,5276,2534, # 2336
|
||||
3722,3604, 815,1587,4033,4034,5277,3605,3486,3856,1254,4624,1328,3058,1390,4035, # 2352
|
||||
1741,4036,3857,4037,5278, 236,3858,2453,3304,5279,5280,3723,3859,1273,3860,4625, # 2368
|
||||
5281, 308,5282,4626, 245,4627,1852,2480,1307,2583, 430, 715,2137,2454,5283, 270, # 2384
|
||||
199,2883,4038,5284,3606,2727,1753, 761,1754, 725,1661,1841,4628,3487,3724,5285, # 2400
|
||||
5286, 587, 14,3305, 227,2608, 326, 480,2270, 943,2765,3607, 291, 650,1884,5287, # 2416
|
||||
1702,1226, 102,1547, 62,3488, 904,4629,3489,1164,4294,5288,5289,1224,1548,2766, # 2432
|
||||
391, 498,1493,5290,1386,1419,5291,2056,1177,4630, 813, 880,1081,2368, 566,1145, # 2448
|
||||
4631,2291,1001,1035,2566,2609,2242, 394,1286,5292,5293,2069,5294, 86,1494,1730, # 2464
|
||||
4039, 491,1588, 745, 897,2963, 843,3377,4040,2767,2884,3306,1768, 998,2221,2070, # 2480
|
||||
397,1827,1195,1970,3725,3011,3378, 284,5295,3861,2507,2138,2120,1904,5296,4041, # 2496
|
||||
2151,4042,4295,1036,3490,1905, 114,2567,4296, 209,1527,5297,5298,2964,2844,2635, # 2512
|
||||
2390,2728,3164, 812,2568,5299,3307,5300,1559, 737,1885,3726,1210, 885, 28,2695, # 2528
|
||||
3608,3862,5301,4297,1004,1780,4632,5302, 346,1982,2222,2696,4633,3863,1742, 797, # 2544
|
||||
1642,4043,1934,1072,1384,2152, 896,4044,3308,3727,3228,2885,3609,5303,2569,1959, # 2560
|
||||
4634,2455,1786,5304,5305,5306,4045,4298,1005,1308,3728,4299,2729,4635,4636,1528, # 2576
|
||||
2610, 161,1178,4300,1983, 987,4637,1101,4301, 631,4046,1157,3229,2425,1343,1241, # 2592
|
||||
1016,2243,2570, 372, 877,2344,2508,1160, 555,1935, 911,4047,5307, 466,1170, 169, # 2608
|
||||
1051,2921,2697,3729,2481,3012,1182,2012,2571,1251,2636,5308, 992,2345,3491,1540, # 2624
|
||||
2730,1201,2071,2406,1997,2482,5309,4638, 528,1923,2191,1503,1874,1570,2369,3379, # 2640
|
||||
3309,5310, 557,1073,5311,1828,3492,2088,2271,3165,3059,3107, 767,3108,2799,4639, # 2656
|
||||
1006,4302,4640,2346,1267,2179,3730,3230, 778,4048,3231,2731,1597,2667,5312,4641, # 2672
|
||||
5313,3493,5314,5315,5316,3310,2698,1433,3311, 131, 95,1504,4049, 723,4303,3166, # 2688
|
||||
1842,3610,2768,2192,4050,2028,2105,3731,5317,3013,4051,1218,5318,3380,3232,4052, # 2704
|
||||
4304,2584, 248,1634,3864, 912,5319,2845,3732,3060,3865, 654, 53,5320,3014,5321, # 2720
|
||||
1688,4642, 777,3494,1032,4053,1425,5322, 191, 820,2121,2846, 971,4643, 931,3233, # 2736
|
||||
135, 664, 783,3866,1998, 772,2922,1936,4054,3867,4644,2923,3234, 282,2732, 640, # 2752
|
||||
1372,3495,1127, 922, 325,3381,5323,5324, 711,2045,5325,5326,4055,2223,2800,1937, # 2768
|
||||
4056,3382,2224,2255,3868,2305,5327,4645,3869,1258,3312,4057,3235,2139,2965,4058, # 2784
|
||||
4059,5328,2225, 258,3236,4646, 101,1227,5329,3313,1755,5330,1391,3314,5331,2924, # 2800
|
||||
2057, 893,5332,5333,5334,1402,4305,2347,5335,5336,3237,3611,5337,5338, 878,1325, # 2816
|
||||
1781,2801,4647, 259,1385,2585, 744,1183,2272,4648,5339,4060,2509,5340, 684,1024, # 2832
|
||||
4306,5341, 472,3612,3496,1165,3315,4061,4062, 322,2153, 881, 455,1695,1152,1340, # 2848
|
||||
660, 554,2154,4649,1058,4650,4307, 830,1065,3383,4063,4651,1924,5342,1703,1919, # 2864
|
||||
5343, 932,2273, 122,5344,4652, 947, 677,5345,3870,2637, 297,1906,1925,2274,4653, # 2880
|
||||
2322,3316,5346,5347,4308,5348,4309, 84,4310, 112, 989,5349, 547,1059,4064, 701, # 2896
|
||||
3613,1019,5350,4311,5351,3497, 942, 639, 457,2306,2456, 993,2966, 407, 851, 494, # 2912
|
||||
4654,3384, 927,5352,1237,5353,2426,3385, 573,4312, 680, 921,2925,1279,1875, 285, # 2928
|
||||
790,1448,1984, 719,2168,5354,5355,4655,4065,4066,1649,5356,1541, 563,5357,1077, # 2944
|
||||
5358,3386,3061,3498, 511,3015,4067,4068,3733,4069,1268,2572,3387,3238,4656,4657, # 2960
|
||||
5359, 535,1048,1276,1189,2926,2029,3167,1438,1373,2847,2967,1134,2013,5360,4313, # 2976
|
||||
1238,2586,3109,1259,5361, 700,5362,2968,3168,3734,4314,5363,4315,1146,1876,1907, # 2992
|
||||
4658,2611,4070, 781,2427, 132,1589, 203, 147, 273,2802,2407, 898,1787,2155,4071, # 3008
|
||||
4072,5364,3871,2803,5365,5366,4659,4660,5367,3239,5368,1635,3872, 965,5369,1805, # 3024
|
||||
2699,1516,3614,1121,1082,1329,3317,4073,1449,3873, 65,1128,2848,2927,2769,1590, # 3040
|
||||
3874,5370,5371, 12,2668, 45, 976,2587,3169,4661, 517,2535,1013,1037,3240,5372, # 3056
|
||||
3875,2849,5373,3876,5374,3499,5375,2612, 614,1999,2323,3877,3110,2733,2638,5376, # 3072
|
||||
2588,4316, 599,1269,5377,1811,3735,5378,2700,3111, 759,1060, 489,1806,3388,3318, # 3088
|
||||
1358,5379,5380,2391,1387,1215,2639,2256, 490,5381,5382,4317,1759,2392,2348,5383, # 3104
|
||||
4662,3878,1908,4074,2640,1807,3241,4663,3500,3319,2770,2349, 874,5384,5385,3501, # 3120
|
||||
3736,1859, 91,2928,3737,3062,3879,4664,5386,3170,4075,2669,5387,3502,1202,1403, # 3136
|
||||
3880,2969,2536,1517,2510,4665,3503,2511,5388,4666,5389,2701,1886,1495,1731,4076, # 3152
|
||||
2370,4667,5390,2030,5391,5392,4077,2702,1216, 237,2589,4318,2324,4078,3881,4668, # 3168
|
||||
4669,2703,3615,3504, 445,4670,5393,5394,5395,5396,2771, 61,4079,3738,1823,4080, # 3184
|
||||
5397, 687,2046, 935, 925, 405,2670, 703,1096,1860,2734,4671,4081,1877,1367,2704, # 3200
|
||||
3389, 918,2106,1782,2483, 334,3320,1611,1093,4672, 564,3171,3505,3739,3390, 945, # 3216
|
||||
2641,2058,4673,5398,1926, 872,4319,5399,3506,2705,3112, 349,4320,3740,4082,4674, # 3232
|
||||
3882,4321,3741,2156,4083,4675,4676,4322,4677,2408,2047, 782,4084, 400, 251,4323, # 3248
|
||||
1624,5400,5401, 277,3742, 299,1265, 476,1191,3883,2122,4324,4325,1109, 205,5402, # 3264
|
||||
2590,1000,2157,3616,1861,5403,5404,5405,4678,5406,4679,2573, 107,2484,2158,4085, # 3280
|
||||
3507,3172,5407,1533, 541,1301, 158, 753,4326,2886,3617,5408,1696, 370,1088,4327, # 3296
|
||||
4680,3618, 579, 327, 440, 162,2244, 269,1938,1374,3508, 968,3063, 56,1396,3113, # 3312
|
||||
2107,3321,3391,5409,1927,2159,4681,3016,5410,3619,5411,5412,3743,4682,2485,5413, # 3328
|
||||
2804,5414,1650,4683,5415,2613,5416,5417,4086,2671,3392,1149,3393,4087,3884,4088, # 3344
|
||||
5418,1076, 49,5419, 951,3242,3322,3323, 450,2850, 920,5420,1812,2805,2371,4328, # 3360
|
||||
1909,1138,2372,3885,3509,5421,3243,4684,1910,1147,1518,2428,4685,3886,5422,4686, # 3376
|
||||
2393,2614, 260,1796,3244,5423,5424,3887,3324, 708,5425,3620,1704,5426,3621,1351, # 3392
|
||||
1618,3394,3017,1887, 944,4329,3395,4330,3064,3396,4331,5427,3744, 422, 413,1714, # 3408
|
||||
3325, 500,2059,2350,4332,2486,5428,1344,1911, 954,5429,1668,5430,5431,4089,2409, # 3424
|
||||
4333,3622,3888,4334,5432,2307,1318,2512,3114, 133,3115,2887,4687, 629, 31,2851, # 3440
|
||||
2706,3889,4688, 850, 949,4689,4090,2970,1732,2089,4335,1496,1853,5433,4091, 620, # 3456
|
||||
3245, 981,1242,3745,3397,1619,3746,1643,3326,2140,2457,1971,1719,3510,2169,5434, # 3472
|
||||
3246,5435,5436,3398,1829,5437,1277,4690,1565,2048,5438,1636,3623,3116,5439, 869, # 3488
|
||||
2852, 655,3890,3891,3117,4092,3018,3892,1310,3624,4691,5440,5441,5442,1733, 558, # 3504
|
||||
4692,3747, 335,1549,3065,1756,4336,3748,1946,3511,1830,1291,1192, 470,2735,2108, # 3520
|
||||
2806, 913,1054,4093,5443,1027,5444,3066,4094,4693, 982,2672,3399,3173,3512,3247, # 3536
|
||||
3248,1947,2807,5445, 571,4694,5446,1831,5447,3625,2591,1523,2429,5448,2090, 984, # 3552
|
||||
4695,3749,1960,5449,3750, 852, 923,2808,3513,3751, 969,1519, 999,2049,2325,1705, # 3568
|
||||
5450,3118, 615,1662, 151, 597,4095,2410,2326,1049, 275,4696,3752,4337, 568,3753, # 3584
|
||||
3626,2487,4338,3754,5451,2430,2275, 409,3249,5452,1566,2888,3514,1002, 769,2853, # 3600
|
||||
194,2091,3174,3755,2226,3327,4339, 628,1505,5453,5454,1763,2180,3019,4096, 521, # 3616
|
||||
1161,2592,1788,2206,2411,4697,4097,1625,4340,4341, 412, 42,3119, 464,5455,2642, # 3632
|
||||
4698,3400,1760,1571,2889,3515,2537,1219,2207,3893,2643,2141,2373,4699,4700,3328, # 3648
|
||||
1651,3401,3627,5456,5457,3628,2488,3516,5458,3756,5459,5460,2276,2092, 460,5461, # 3664
|
||||
4701,5462,3020, 962, 588,3629, 289,3250,2644,1116, 52,5463,3067,1797,5464,5465, # 3680
|
||||
5466,1467,5467,1598,1143,3757,4342,1985,1734,1067,4702,1280,3402, 465,4703,1572, # 3696
|
||||
510,5468,1928,2245,1813,1644,3630,5469,4704,3758,5470,5471,2673,1573,1534,5472, # 3712
|
||||
5473, 536,1808,1761,3517,3894,3175,2645,5474,5475,5476,4705,3518,2929,1912,2809, # 3728
|
||||
5477,3329,1122, 377,3251,5478, 360,5479,5480,4343,1529, 551,5481,2060,3759,1769, # 3744
|
||||
2431,5482,2930,4344,3330,3120,2327,2109,2031,4706,1404, 136,1468,1479, 672,1171, # 3760
|
||||
3252,2308, 271,3176,5483,2772,5484,2050, 678,2736, 865,1948,4707,5485,2014,4098, # 3776
|
||||
2971,5486,2737,2227,1397,3068,3760,4708,4709,1735,2931,3403,3631,5487,3895, 509, # 3792
|
||||
2854,2458,2890,3896,5488,5489,3177,3178,4710,4345,2538,4711,2309,1166,1010, 552, # 3808
|
||||
681,1888,5490,5491,2972,2973,4099,1287,1596,1862,3179, 358, 453, 736, 175, 478, # 3824
|
||||
1117, 905,1167,1097,5492,1854,1530,5493,1706,5494,2181,3519,2292,3761,3520,3632, # 3840
|
||||
4346,2093,4347,5495,3404,1193,2489,4348,1458,2193,2208,1863,1889,1421,3331,2932, # 3856
|
||||
3069,2182,3521, 595,2123,5496,4100,5497,5498,4349,1707,2646, 223,3762,1359, 751, # 3872
|
||||
3121, 183,3522,5499,2810,3021, 419,2374, 633, 704,3897,2394, 241,5500,5501,5502, # 3888
|
||||
838,3022,3763,2277,2773,2459,3898,1939,2051,4101,1309,3122,2246,1181,5503,1136, # 3904
|
||||
2209,3899,2375,1446,4350,2310,4712,5504,5505,4351,1055,2615, 484,3764,5506,4102, # 3920
|
||||
625,4352,2278,3405,1499,4353,4103,5507,4104,4354,3253,2279,2280,3523,5508,5509, # 3936
|
||||
2774, 808,2616,3765,3406,4105,4355,3123,2539, 526,3407,3900,4356, 955,5510,1620, # 3952
|
||||
4357,2647,2432,5511,1429,3766,1669,1832, 994, 928,5512,3633,1260,5513,5514,5515, # 3968
|
||||
1949,2293, 741,2933,1626,4358,2738,2460, 867,1184, 362,3408,1392,5516,5517,4106, # 3984
|
||||
4359,1770,1736,3254,2934,4713,4714,1929,2707,1459,1158,5518,3070,3409,2891,1292, # 4000
|
||||
1930,2513,2855,3767,1986,1187,2072,2015,2617,4360,5519,2574,2514,2170,3768,2490, # 4016
|
||||
3332,5520,3769,4715,5521,5522, 666,1003,3023,1022,3634,4361,5523,4716,1814,2257, # 4032
|
||||
574,3901,1603, 295,1535, 705,3902,4362, 283, 858, 417,5524,5525,3255,4717,4718, # 4048
|
||||
3071,1220,1890,1046,2281,2461,4107,1393,1599, 689,2575, 388,4363,5526,2491, 802, # 4064
|
||||
5527,2811,3903,2061,1405,2258,5528,4719,3904,2110,1052,1345,3256,1585,5529, 809, # 4080
|
||||
5530,5531,5532, 575,2739,3524, 956,1552,1469,1144,2328,5533,2329,1560,2462,3635, # 4096
|
||||
3257,4108, 616,2210,4364,3180,2183,2294,5534,1833,5535,3525,4720,5536,1319,3770, # 4112
|
||||
3771,1211,3636,1023,3258,1293,2812,5537,5538,5539,3905, 607,2311,3906, 762,2892, # 4128
|
||||
1439,4365,1360,4721,1485,3072,5540,4722,1038,4366,1450,2062,2648,4367,1379,4723, # 4144
|
||||
2593,5541,5542,4368,1352,1414,2330,2935,1172,5543,5544,3907,3908,4724,1798,1451, # 4160
|
||||
5545,5546,5547,5548,2936,4109,4110,2492,2351, 411,4111,4112,3637,3333,3124,4725, # 4176
|
||||
1561,2674,1452,4113,1375,5549,5550, 47,2974, 316,5551,1406,1591,2937,3181,5552, # 4192
|
||||
1025,2142,3125,3182, 354,2740, 884,2228,4369,2412, 508,3772, 726,3638, 996,2433, # 4208
|
||||
3639, 729,5553, 392,2194,1453,4114,4726,3773,5554,5555,2463,3640,2618,1675,2813, # 4224
|
||||
919,2352,2975,2353,1270,4727,4115, 73,5556,5557, 647,5558,3259,2856,2259,1550, # 4240
|
||||
1346,3024,5559,1332, 883,3526,5560,5561,5562,5563,3334,2775,5564,1212, 831,1347, # 4256
|
||||
4370,4728,2331,3909,1864,3073, 720,3910,4729,4730,3911,5565,4371,5566,5567,4731, # 4272
|
||||
5568,5569,1799,4732,3774,2619,4733,3641,1645,2376,4734,5570,2938, 669,2211,2675, # 4288
|
||||
2434,5571,2893,5572,5573,1028,3260,5574,4372,2413,5575,2260,1353,5576,5577,4735, # 4304
|
||||
3183, 518,5578,4116,5579,4373,1961,5580,2143,4374,5581,5582,3025,2354,2355,3912, # 4320
|
||||
516,1834,1454,4117,2708,4375,4736,2229,2620,1972,1129,3642,5583,2776,5584,2976, # 4336
|
||||
1422, 577,1470,3026,1524,3410,5585,5586, 432,4376,3074,3527,5587,2594,1455,2515, # 4352
|
||||
2230,1973,1175,5588,1020,2741,4118,3528,4737,5589,2742,5590,1743,1361,3075,3529, # 4368
|
||||
2649,4119,4377,4738,2295, 895, 924,4378,2171, 331,2247,3076, 166,1627,3077,1098, # 4384
|
||||
5591,1232,2894,2231,3411,4739, 657, 403,1196,2377, 542,3775,3412,1600,4379,3530, # 4400
|
||||
5592,4740,2777,3261, 576, 530,1362,4741,4742,2540,2676,3776,4120,5593, 842,3913, # 4416
|
||||
5594,2814,2032,1014,4121, 213,2709,3413, 665, 621,4380,5595,3777,2939,2435,5596, # 4432
|
||||
2436,3335,3643,3414,4743,4381,2541,4382,4744,3644,1682,4383,3531,1380,5597, 724, # 4448
|
||||
2282, 600,1670,5598,1337,1233,4745,3126,2248,5599,1621,4746,5600, 651,4384,5601, # 4464
|
||||
1612,4385,2621,5602,2857,5603,2743,2312,3078,5604, 716,2464,3079, 174,1255,2710, # 4480
|
||||
4122,3645, 548,1320,1398, 728,4123,1574,5605,1891,1197,3080,4124,5606,3081,3082, # 4496
|
||||
3778,3646,3779, 747,5607, 635,4386,4747,5608,5609,5610,4387,5611,5612,4748,5613, # 4512
|
||||
3415,4749,2437, 451,5614,3780,2542,2073,4388,2744,4389,4125,5615,1764,4750,5616, # 4528
|
||||
4390, 350,4751,2283,2395,2493,5617,4391,4126,2249,1434,4127, 488,4752, 458,4392, # 4544
|
||||
4128,3781, 771,1330,2396,3914,2576,3184,2160,2414,1553,2677,3185,4393,5618,2494, # 4560
|
||||
2895,2622,1720,2711,4394,3416,4753,5619,2543,4395,5620,3262,4396,2778,5621,2016, # 4576
|
||||
2745,5622,1155,1017,3782,3915,5623,3336,2313, 201,1865,4397,1430,5624,4129,5625, # 4592
|
||||
5626,5627,5628,5629,4398,1604,5630, 414,1866, 371,2595,4754,4755,3532,2017,3127, # 4608
|
||||
4756,1708, 960,4399, 887, 389,2172,1536,1663,1721,5631,2232,4130,2356,2940,1580, # 4624
|
||||
5632,5633,1744,4757,2544,4758,4759,5634,4760,5635,2074,5636,4761,3647,3417,2896, # 4640
|
||||
4400,5637,4401,2650,3418,2815, 673,2712,2465, 709,3533,4131,3648,4402,5638,1148, # 4656
|
||||
502, 634,5639,5640,1204,4762,3649,1575,4763,2623,3783,5641,3784,3128, 948,3263, # 4672
|
||||
121,1745,3916,1110,5642,4403,3083,2516,3027,4132,3785,1151,1771,3917,1488,4133, # 4688
|
||||
1987,5643,2438,3534,5644,5645,2094,5646,4404,3918,1213,1407,2816, 531,2746,2545, # 4704
|
||||
3264,1011,1537,4764,2779,4405,3129,1061,5647,3786,3787,1867,2897,5648,2018, 120, # 4720
|
||||
4406,4407,2063,3650,3265,2314,3919,2678,3419,1955,4765,4134,5649,3535,1047,2713, # 4736
|
||||
1266,5650,1368,4766,2858, 649,3420,3920,2546,2747,1102,2859,2679,5651,5652,2000, # 4752
|
||||
5653,1111,3651,2977,5654,2495,3921,3652,2817,1855,3421,3788,5655,5656,3422,2415, # 4768
|
||||
2898,3337,3266,3653,5657,2577,5658,3654,2818,4135,1460, 856,5659,3655,5660,2899, # 4784
|
||||
2978,5661,2900,3922,5662,4408, 632,2517, 875,3923,1697,3924,2296,5663,5664,4767, # 4800
|
||||
3028,1239, 580,4768,4409,5665, 914, 936,2075,1190,4136,1039,2124,5666,5667,5668, # 4816
|
||||
5669,3423,1473,5670,1354,4410,3925,4769,2173,3084,4137, 915,3338,4411,4412,3339, # 4832
|
||||
1605,1835,5671,2748, 398,3656,4413,3926,4138, 328,1913,2860,4139,3927,1331,4414, # 4848
|
||||
3029, 937,4415,5672,3657,4140,4141,3424,2161,4770,3425, 524, 742, 538,3085,1012, # 4864
|
||||
5673,5674,3928,2466,5675, 658,1103, 225,3929,5676,5677,4771,5678,4772,5679,3267, # 4880
|
||||
1243,5680,4142, 963,2250,4773,5681,2714,3658,3186,5682,5683,2596,2332,5684,4774, # 4896
|
||||
5685,5686,5687,3536, 957,3426,2547,2033,1931,2941,2467, 870,2019,3659,1746,2780, # 4912
|
||||
2781,2439,2468,5688,3930,5689,3789,3130,3790,3537,3427,3791,5690,1179,3086,5691, # 4928
|
||||
3187,2378,4416,3792,2548,3188,3131,2749,4143,5692,3428,1556,2549,2297, 977,2901, # 4944
|
||||
2034,4144,1205,3429,5693,1765,3430,3189,2125,1271, 714,1689,4775,3538,5694,2333, # 4960
|
||||
3931, 533,4417,3660,2184, 617,5695,2469,3340,3539,2315,5696,5697,3190,5698,5699, # 4976
|
||||
3932,1988, 618, 427,2651,3540,3431,5700,5701,1244,1690,5702,2819,4418,4776,5703, # 4992
|
||||
3541,4777,5704,2284,1576, 473,3661,4419,3432, 972,5705,3662,5706,3087,5707,5708, # 5008
|
||||
4778,4779,5709,3793,4145,4146,5710, 153,4780, 356,5711,1892,2902,4420,2144, 408, # 5024
|
||||
803,2357,5712,3933,5713,4421,1646,2578,2518,4781,4782,3934,5714,3935,4422,5715, # 5040
|
||||
2416,3433, 752,5716,5717,1962,3341,2979,5718, 746,3030,2470,4783,4423,3794, 698, # 5056
|
||||
4784,1893,4424,3663,2550,4785,3664,3936,5719,3191,3434,5720,1824,1302,4147,2715, # 5072
|
||||
3937,1974,4425,5721,4426,3192, 823,1303,1288,1236,2861,3542,4148,3435, 774,3938, # 5088
|
||||
5722,1581,4786,1304,2862,3939,4787,5723,2440,2162,1083,3268,4427,4149,4428, 344, # 5104
|
||||
1173, 288,2316, 454,1683,5724,5725,1461,4788,4150,2597,5726,5727,4789, 985, 894, # 5120
|
||||
5728,3436,3193,5729,1914,2942,3795,1989,5730,2111,1975,5731,4151,5732,2579,1194, # 5136
|
||||
425,5733,4790,3194,1245,3796,4429,5734,5735,2863,5736, 636,4791,1856,3940, 760, # 5152
|
||||
1800,5737,4430,2212,1508,4792,4152,1894,1684,2298,5738,5739,4793,4431,4432,2213, # 5168
|
||||
479,5740,5741, 832,5742,4153,2496,5743,2980,2497,3797, 990,3132, 627,1815,2652, # 5184
|
||||
4433,1582,4434,2126,2112,3543,4794,5744, 799,4435,3195,5745,4795,2113,1737,3031, # 5200
|
||||
1018, 543, 754,4436,3342,1676,4796,4797,4154,4798,1489,5746,3544,5747,2624,2903, # 5216
|
||||
4155,5748,5749,2981,5750,5751,5752,5753,3196,4799,4800,2185,1722,5754,3269,3270, # 5232
|
||||
1843,3665,1715, 481, 365,1976,1857,5755,5756,1963,2498,4801,5757,2127,3666,3271, # 5248
|
||||
433,1895,2064,2076,5758, 602,2750,5759,5760,5761,5762,5763,3032,1628,3437,5764, # 5264
|
||||
3197,4802,4156,2904,4803,2519,5765,2551,2782,5766,5767,5768,3343,4804,2905,5769, # 5280
|
||||
4805,5770,2864,4806,4807,1221,2982,4157,2520,5771,5772,5773,1868,1990,5774,5775, # 5296
|
||||
5776,1896,5777,5778,4808,1897,4158, 318,5779,2095,4159,4437,5780,5781, 485,5782, # 5312
|
||||
938,3941, 553,2680, 116,5783,3942,3667,5784,3545,2681,2783,3438,3344,2820,5785, # 5328
|
||||
3668,2943,4160,1747,2944,2983,5786,5787, 207,5788,4809,5789,4810,2521,5790,3033, # 5344
|
||||
890,3669,3943,5791,1878,3798,3439,5792,2186,2358,3440,1652,5793,5794,5795, 941, # 5360
|
||||
2299, 208,3546,4161,2020, 330,4438,3944,2906,2499,3799,4439,4811,5796,5797,5798, # 5376 #last 512
|
||||
#Everything below is of no interest for detection purpose
|
||||
2522,1613,4812,5799,3345,3945,2523,5800,4162,5801,1637,4163,2471,4813,3946,5802, # 5392
|
||||
2500,3034,3800,5803,5804,2195,4814,5805,2163,5806,5807,5808,5809,5810,5811,5812, # 5408
|
||||
5813,5814,5815,5816,5817,5818,5819,5820,5821,5822,5823,5824,5825,5826,5827,5828, # 5424
|
||||
5829,5830,5831,5832,5833,5834,5835,5836,5837,5838,5839,5840,5841,5842,5843,5844, # 5440
|
||||
5845,5846,5847,5848,5849,5850,5851,5852,5853,5854,5855,5856,5857,5858,5859,5860, # 5456
|
||||
5861,5862,5863,5864,5865,5866,5867,5868,5869,5870,5871,5872,5873,5874,5875,5876, # 5472
|
||||
5877,5878,5879,5880,5881,5882,5883,5884,5885,5886,5887,5888,5889,5890,5891,5892, # 5488
|
||||
5893,5894,5895,5896,5897,5898,5899,5900,5901,5902,5903,5904,5905,5906,5907,5908, # 5504
|
||||
5909,5910,5911,5912,5913,5914,5915,5916,5917,5918,5919,5920,5921,5922,5923,5924, # 5520
|
||||
5925,5926,5927,5928,5929,5930,5931,5932,5933,5934,5935,5936,5937,5938,5939,5940, # 5536
|
||||
5941,5942,5943,5944,5945,5946,5947,5948,5949,5950,5951,5952,5953,5954,5955,5956, # 5552
|
||||
5957,5958,5959,5960,5961,5962,5963,5964,5965,5966,5967,5968,5969,5970,5971,5972, # 5568
|
||||
5973,5974,5975,5976,5977,5978,5979,5980,5981,5982,5983,5984,5985,5986,5987,5988, # 5584
|
||||
5989,5990,5991,5992,5993,5994,5995,5996,5997,5998,5999,6000,6001,6002,6003,6004, # 5600
|
||||
6005,6006,6007,6008,6009,6010,6011,6012,6013,6014,6015,6016,6017,6018,6019,6020, # 5616
|
||||
6021,6022,6023,6024,6025,6026,6027,6028,6029,6030,6031,6032,6033,6034,6035,6036, # 5632
|
||||
6037,6038,6039,6040,6041,6042,6043,6044,6045,6046,6047,6048,6049,6050,6051,6052, # 5648
|
||||
6053,6054,6055,6056,6057,6058,6059,6060,6061,6062,6063,6064,6065,6066,6067,6068, # 5664
|
||||
6069,6070,6071,6072,6073,6074,6075,6076,6077,6078,6079,6080,6081,6082,6083,6084, # 5680
|
||||
6085,6086,6087,6088,6089,6090,6091,6092,6093,6094,6095,6096,6097,6098,6099,6100, # 5696
|
||||
6101,6102,6103,6104,6105,6106,6107,6108,6109,6110,6111,6112,6113,6114,6115,6116, # 5712
|
||||
6117,6118,6119,6120,6121,6122,6123,6124,6125,6126,6127,6128,6129,6130,6131,6132, # 5728
|
||||
6133,6134,6135,6136,6137,6138,6139,6140,6141,6142,6143,6144,6145,6146,6147,6148, # 5744
|
||||
6149,6150,6151,6152,6153,6154,6155,6156,6157,6158,6159,6160,6161,6162,6163,6164, # 5760
|
||||
6165,6166,6167,6168,6169,6170,6171,6172,6173,6174,6175,6176,6177,6178,6179,6180, # 5776
|
||||
6181,6182,6183,6184,6185,6186,6187,6188,6189,6190,6191,6192,6193,6194,6195,6196, # 5792
|
||||
6197,6198,6199,6200,6201,6202,6203,6204,6205,6206,6207,6208,6209,6210,6211,6212, # 5808
|
||||
6213,6214,6215,6216,6217,6218,6219,6220,6221,6222,6223,3670,6224,6225,6226,6227, # 5824
|
||||
6228,6229,6230,6231,6232,6233,6234,6235,6236,6237,6238,6239,6240,6241,6242,6243, # 5840
|
||||
6244,6245,6246,6247,6248,6249,6250,6251,6252,6253,6254,6255,6256,6257,6258,6259, # 5856
|
||||
6260,6261,6262,6263,6264,6265,6266,6267,6268,6269,6270,6271,6272,6273,6274,6275, # 5872
|
||||
6276,6277,6278,6279,6280,6281,6282,6283,6284,6285,4815,6286,6287,6288,6289,6290, # 5888
|
||||
6291,6292,4816,6293,6294,6295,6296,6297,6298,6299,6300,6301,6302,6303,6304,6305, # 5904
|
||||
6306,6307,6308,6309,6310,6311,4817,4818,6312,6313,6314,6315,6316,6317,6318,4819, # 5920
|
||||
6319,6320,6321,6322,6323,6324,6325,6326,6327,6328,6329,6330,6331,6332,6333,6334, # 5936
|
||||
6335,6336,6337,4820,6338,6339,6340,6341,6342,6343,6344,6345,6346,6347,6348,6349, # 5952
|
||||
6350,6351,6352,6353,6354,6355,6356,6357,6358,6359,6360,6361,6362,6363,6364,6365, # 5968
|
||||
6366,6367,6368,6369,6370,6371,6372,6373,6374,6375,6376,6377,6378,6379,6380,6381, # 5984
|
||||
6382,6383,6384,6385,6386,6387,6388,6389,6390,6391,6392,6393,6394,6395,6396,6397, # 6000
|
||||
6398,6399,6400,6401,6402,6403,6404,6405,6406,6407,6408,6409,6410,3441,6411,6412, # 6016
|
||||
6413,6414,6415,6416,6417,6418,6419,6420,6421,6422,6423,6424,6425,4440,6426,6427, # 6032
|
||||
6428,6429,6430,6431,6432,6433,6434,6435,6436,6437,6438,6439,6440,6441,6442,6443, # 6048
|
||||
6444,6445,6446,6447,6448,6449,6450,6451,6452,6453,6454,4821,6455,6456,6457,6458, # 6064
|
||||
6459,6460,6461,6462,6463,6464,6465,6466,6467,6468,6469,6470,6471,6472,6473,6474, # 6080
|
||||
6475,6476,6477,3947,3948,6478,6479,6480,6481,3272,4441,6482,6483,6484,6485,4442, # 6096
|
||||
6486,6487,6488,6489,6490,6491,6492,6493,6494,6495,6496,4822,6497,6498,6499,6500, # 6112
|
||||
6501,6502,6503,6504,6505,6506,6507,6508,6509,6510,6511,6512,6513,6514,6515,6516, # 6128
|
||||
6517,6518,6519,6520,6521,6522,6523,6524,6525,6526,6527,6528,6529,6530,6531,6532, # 6144
|
||||
6533,6534,6535,6536,6537,6538,6539,6540,6541,6542,6543,6544,6545,6546,6547,6548, # 6160
|
||||
6549,6550,6551,6552,6553,6554,6555,6556,2784,6557,4823,6558,6559,6560,6561,6562, # 6176
|
||||
6563,6564,6565,6566,6567,6568,6569,3949,6570,6571,6572,4824,6573,6574,6575,6576, # 6192
|
||||
6577,6578,6579,6580,6581,6582,6583,4825,6584,6585,6586,3950,2785,6587,6588,6589, # 6208
|
||||
6590,6591,6592,6593,6594,6595,6596,6597,6598,6599,6600,6601,6602,6603,6604,6605, # 6224
|
||||
6606,6607,6608,6609,6610,6611,6612,4826,6613,6614,6615,4827,6616,6617,6618,6619, # 6240
|
||||
6620,6621,6622,6623,6624,6625,4164,6626,6627,6628,6629,6630,6631,6632,6633,6634, # 6256
|
||||
3547,6635,4828,6636,6637,6638,6639,6640,6641,6642,3951,2984,6643,6644,6645,6646, # 6272
|
||||
6647,6648,6649,4165,6650,4829,6651,6652,4830,6653,6654,6655,6656,6657,6658,6659, # 6288
|
||||
6660,6661,6662,4831,6663,6664,6665,6666,6667,6668,6669,6670,6671,4166,6672,4832, # 6304
|
||||
3952,6673,6674,6675,6676,4833,6677,6678,6679,4167,6680,6681,6682,3198,6683,6684, # 6320
|
||||
6685,6686,6687,6688,6689,6690,6691,6692,6693,6694,6695,6696,6697,4834,6698,6699, # 6336
|
||||
6700,6701,6702,6703,6704,6705,6706,6707,6708,6709,6710,6711,6712,6713,6714,6715, # 6352
|
||||
6716,6717,6718,6719,6720,6721,6722,6723,6724,6725,6726,6727,6728,6729,6730,6731, # 6368
|
||||
6732,6733,6734,4443,6735,6736,6737,6738,6739,6740,6741,6742,6743,6744,6745,4444, # 6384
|
||||
6746,6747,6748,6749,6750,6751,6752,6753,6754,6755,6756,6757,6758,6759,6760,6761, # 6400
|
||||
6762,6763,6764,6765,6766,6767,6768,6769,6770,6771,6772,6773,6774,6775,6776,6777, # 6416
|
||||
6778,6779,6780,6781,4168,6782,6783,3442,6784,6785,6786,6787,6788,6789,6790,6791, # 6432
|
||||
4169,6792,6793,6794,6795,6796,6797,6798,6799,6800,6801,6802,6803,6804,6805,6806, # 6448
|
||||
6807,6808,6809,6810,6811,4835,6812,6813,6814,4445,6815,6816,4446,6817,6818,6819, # 6464
|
||||
6820,6821,6822,6823,6824,6825,6826,6827,6828,6829,6830,6831,6832,6833,6834,6835, # 6480
|
||||
3548,6836,6837,6838,6839,6840,6841,6842,6843,6844,6845,6846,4836,6847,6848,6849, # 6496
|
||||
6850,6851,6852,6853,6854,3953,6855,6856,6857,6858,6859,6860,6861,6862,6863,6864, # 6512
|
||||
6865,6866,6867,6868,6869,6870,6871,6872,6873,6874,6875,6876,6877,3199,6878,6879, # 6528
|
||||
6880,6881,6882,4447,6883,6884,6885,6886,6887,6888,6889,6890,6891,6892,6893,6894, # 6544
|
||||
6895,6896,6897,6898,6899,6900,6901,6902,6903,6904,4170,6905,6906,6907,6908,6909, # 6560
|
||||
6910,6911,6912,6913,6914,6915,6916,6917,6918,6919,6920,6921,6922,6923,6924,6925, # 6576
|
||||
6926,6927,4837,6928,6929,6930,6931,6932,6933,6934,6935,6936,3346,6937,6938,4838, # 6592
|
||||
6939,6940,6941,4448,6942,6943,6944,6945,6946,4449,6947,6948,6949,6950,6951,6952, # 6608
|
||||
6953,6954,6955,6956,6957,6958,6959,6960,6961,6962,6963,6964,6965,6966,6967,6968, # 6624
|
||||
6969,6970,6971,6972,6973,6974,6975,6976,6977,6978,6979,6980,6981,6982,6983,6984, # 6640
|
||||
6985,6986,6987,6988,6989,6990,6991,6992,6993,6994,3671,6995,6996,6997,6998,4839, # 6656
|
||||
6999,7000,7001,7002,3549,7003,7004,7005,7006,7007,7008,7009,7010,7011,7012,7013, # 6672
|
||||
7014,7015,7016,7017,7018,7019,7020,7021,7022,7023,7024,7025,7026,7027,7028,7029, # 6688
|
||||
7030,4840,7031,7032,7033,7034,7035,7036,7037,7038,4841,7039,7040,7041,7042,7043, # 6704
|
||||
7044,7045,7046,7047,7048,7049,7050,7051,7052,7053,7054,7055,7056,7057,7058,7059, # 6720
|
||||
7060,7061,7062,7063,7064,7065,7066,7067,7068,7069,7070,2985,7071,7072,7073,7074, # 6736
|
||||
7075,7076,7077,7078,7079,7080,4842,7081,7082,7083,7084,7085,7086,7087,7088,7089, # 6752
|
||||
7090,7091,7092,7093,7094,7095,7096,7097,7098,7099,7100,7101,7102,7103,7104,7105, # 6768
|
||||
7106,7107,7108,7109,7110,7111,7112,7113,7114,7115,7116,7117,7118,4450,7119,7120, # 6784
|
||||
7121,7122,7123,7124,7125,7126,7127,7128,7129,7130,7131,7132,7133,7134,7135,7136, # 6800
|
||||
7137,7138,7139,7140,7141,7142,7143,4843,7144,7145,7146,7147,7148,7149,7150,7151, # 6816
|
||||
7152,7153,7154,7155,7156,7157,7158,7159,7160,7161,7162,7163,7164,7165,7166,7167, # 6832
|
||||
7168,7169,7170,7171,7172,7173,7174,7175,7176,7177,7178,7179,7180,7181,7182,7183, # 6848
|
||||
7184,7185,7186,7187,7188,4171,4172,7189,7190,7191,7192,7193,7194,7195,7196,7197, # 6864
|
||||
7198,7199,7200,7201,7202,7203,7204,7205,7206,7207,7208,7209,7210,7211,7212,7213, # 6880
|
||||
7214,7215,7216,7217,7218,7219,7220,7221,7222,7223,7224,7225,7226,7227,7228,7229, # 6896
|
||||
7230,7231,7232,7233,7234,7235,7236,7237,7238,7239,7240,7241,7242,7243,7244,7245, # 6912
|
||||
7246,7247,7248,7249,7250,7251,7252,7253,7254,7255,7256,7257,7258,7259,7260,7261, # 6928
|
||||
7262,7263,7264,7265,7266,7267,7268,7269,7270,7271,7272,7273,7274,7275,7276,7277, # 6944
|
||||
7278,7279,7280,7281,7282,7283,7284,7285,7286,7287,7288,7289,7290,7291,7292,7293, # 6960
|
||||
7294,7295,7296,4844,7297,7298,7299,7300,7301,7302,7303,7304,7305,7306,7307,7308, # 6976
|
||||
7309,7310,7311,7312,7313,7314,7315,7316,4451,7317,7318,7319,7320,7321,7322,7323, # 6992
|
||||
7324,7325,7326,7327,7328,7329,7330,7331,7332,7333,7334,7335,7336,7337,7338,7339, # 7008
|
||||
7340,7341,7342,7343,7344,7345,7346,7347,7348,7349,7350,7351,7352,7353,4173,7354, # 7024
|
||||
7355,4845,7356,7357,7358,7359,7360,7361,7362,7363,7364,7365,7366,7367,7368,7369, # 7040
|
||||
7370,7371,7372,7373,7374,7375,7376,7377,7378,7379,7380,7381,7382,7383,7384,7385, # 7056
|
||||
7386,7387,7388,4846,7389,7390,7391,7392,7393,7394,7395,7396,7397,7398,7399,7400, # 7072
|
||||
7401,7402,7403,7404,7405,3672,7406,7407,7408,7409,7410,7411,7412,7413,7414,7415, # 7088
|
||||
7416,7417,7418,7419,7420,7421,7422,7423,7424,7425,7426,7427,7428,7429,7430,7431, # 7104
|
||||
7432,7433,7434,7435,7436,7437,7438,7439,7440,7441,7442,7443,7444,7445,7446,7447, # 7120
|
||||
7448,7449,7450,7451,7452,7453,4452,7454,3200,7455,7456,7457,7458,7459,7460,7461, # 7136
|
||||
7462,7463,7464,7465,7466,7467,7468,7469,7470,7471,7472,7473,7474,4847,7475,7476, # 7152
|
||||
7477,3133,7478,7479,7480,7481,7482,7483,7484,7485,7486,7487,7488,7489,7490,7491, # 7168
|
||||
7492,7493,7494,7495,7496,7497,7498,7499,7500,7501,7502,3347,7503,7504,7505,7506, # 7184
|
||||
7507,7508,7509,7510,7511,7512,7513,7514,7515,7516,7517,7518,7519,7520,7521,4848, # 7200
|
||||
7522,7523,7524,7525,7526,7527,7528,7529,7530,7531,7532,7533,7534,7535,7536,7537, # 7216
|
||||
7538,7539,7540,7541,7542,7543,7544,7545,7546,7547,7548,7549,3801,4849,7550,7551, # 7232
|
||||
7552,7553,7554,7555,7556,7557,7558,7559,7560,7561,7562,7563,7564,7565,7566,7567, # 7248
|
||||
7568,7569,3035,7570,7571,7572,7573,7574,7575,7576,7577,7578,7579,7580,7581,7582, # 7264
|
||||
7583,7584,7585,7586,7587,7588,7589,7590,7591,7592,7593,7594,7595,7596,7597,7598, # 7280
|
||||
7599,7600,7601,7602,7603,7604,7605,7606,7607,7608,7609,7610,7611,7612,7613,7614, # 7296
|
||||
7615,7616,4850,7617,7618,3802,7619,7620,7621,7622,7623,7624,7625,7626,7627,7628, # 7312
|
||||
7629,7630,7631,7632,4851,7633,7634,7635,7636,7637,7638,7639,7640,7641,7642,7643, # 7328
|
||||
7644,7645,7646,7647,7648,7649,7650,7651,7652,7653,7654,7655,7656,7657,7658,7659, # 7344
|
||||
7660,7661,7662,7663,7664,7665,7666,7667,7668,7669,7670,4453,7671,7672,7673,7674, # 7360
|
||||
7675,7676,7677,7678,7679,7680,7681,7682,7683,7684,7685,7686,7687,7688,7689,7690, # 7376
|
||||
7691,7692,7693,7694,7695,7696,7697,3443,7698,7699,7700,7701,7702,4454,7703,7704, # 7392
|
||||
7705,7706,7707,7708,7709,7710,7711,7712,7713,2472,7714,7715,7716,7717,7718,7719, # 7408
|
||||
7720,7721,7722,7723,7724,7725,7726,7727,7728,7729,7730,7731,3954,7732,7733,7734, # 7424
|
||||
7735,7736,7737,7738,7739,7740,7741,7742,7743,7744,7745,7746,7747,7748,7749,7750, # 7440
|
||||
3134,7751,7752,4852,7753,7754,7755,4853,7756,7757,7758,7759,7760,4174,7761,7762, # 7456
|
||||
7763,7764,7765,7766,7767,7768,7769,7770,7771,7772,7773,7774,7775,7776,7777,7778, # 7472
|
||||
7779,7780,7781,7782,7783,7784,7785,7786,7787,7788,7789,7790,7791,7792,7793,7794, # 7488
|
||||
7795,7796,7797,7798,7799,7800,7801,7802,7803,7804,7805,4854,7806,7807,7808,7809, # 7504
|
||||
7810,7811,7812,7813,7814,7815,7816,7817,7818,7819,7820,7821,7822,7823,7824,7825, # 7520
|
||||
4855,7826,7827,7828,7829,7830,7831,7832,7833,7834,7835,7836,7837,7838,7839,7840, # 7536
|
||||
7841,7842,7843,7844,7845,7846,7847,3955,7848,7849,7850,7851,7852,7853,7854,7855, # 7552
|
||||
7856,7857,7858,7859,7860,3444,7861,7862,7863,7864,7865,7866,7867,7868,7869,7870, # 7568
|
||||
7871,7872,7873,7874,7875,7876,7877,7878,7879,7880,7881,7882,7883,7884,7885,7886, # 7584
|
||||
7887,7888,7889,7890,7891,4175,7892,7893,7894,7895,7896,4856,4857,7897,7898,7899, # 7600
|
||||
7900,2598,7901,7902,7903,7904,7905,7906,7907,7908,4455,7909,7910,7911,7912,7913, # 7616
|
||||
7914,3201,7915,7916,7917,7918,7919,7920,7921,4858,7922,7923,7924,7925,7926,7927, # 7632
|
||||
7928,7929,7930,7931,7932,7933,7934,7935,7936,7937,7938,7939,7940,7941,7942,7943, # 7648
|
||||
7944,7945,7946,7947,7948,7949,7950,7951,7952,7953,7954,7955,7956,7957,7958,7959, # 7664
|
||||
7960,7961,7962,7963,7964,7965,7966,7967,7968,7969,7970,7971,7972,7973,7974,7975, # 7680
|
||||
7976,7977,7978,7979,7980,7981,4859,7982,7983,7984,7985,7986,7987,7988,7989,7990, # 7696
|
||||
7991,7992,7993,7994,7995,7996,4860,7997,7998,7999,8000,8001,8002,8003,8004,8005, # 7712
|
||||
8006,8007,8008,8009,8010,8011,8012,8013,8014,8015,8016,4176,8017,8018,8019,8020, # 7728
|
||||
8021,8022,8023,4861,8024,8025,8026,8027,8028,8029,8030,8031,8032,8033,8034,8035, # 7744
|
||||
8036,4862,4456,8037,8038,8039,8040,4863,8041,8042,8043,8044,8045,8046,8047,8048, # 7760
|
||||
8049,8050,8051,8052,8053,8054,8055,8056,8057,8058,8059,8060,8061,8062,8063,8064, # 7776
|
||||
8065,8066,8067,8068,8069,8070,8071,8072,8073,8074,8075,8076,8077,8078,8079,8080, # 7792
|
||||
8081,8082,8083,8084,8085,8086,8087,8088,8089,8090,8091,8092,8093,8094,8095,8096, # 7808
|
||||
8097,8098,8099,4864,4177,8100,8101,8102,8103,8104,8105,8106,8107,8108,8109,8110, # 7824
|
||||
8111,8112,8113,8114,8115,8116,8117,8118,8119,8120,4178,8121,8122,8123,8124,8125, # 7840
|
||||
8126,8127,8128,8129,8130,8131,8132,8133,8134,8135,8136,8137,8138,8139,8140,8141, # 7856
|
||||
8142,8143,8144,8145,4865,4866,8146,8147,8148,8149,8150,8151,8152,8153,8154,8155, # 7872
|
||||
8156,8157,8158,8159,8160,8161,8162,8163,8164,8165,4179,8166,8167,8168,8169,8170, # 7888
|
||||
8171,8172,8173,8174,8175,8176,8177,8178,8179,8180,8181,4457,8182,8183,8184,8185, # 7904
|
||||
8186,8187,8188,8189,8190,8191,8192,8193,8194,8195,8196,8197,8198,8199,8200,8201, # 7920
|
||||
8202,8203,8204,8205,8206,8207,8208,8209,8210,8211,8212,8213,8214,8215,8216,8217, # 7936
|
||||
8218,8219,8220,8221,8222,8223,8224,8225,8226,8227,8228,8229,8230,8231,8232,8233, # 7952
|
||||
8234,8235,8236,8237,8238,8239,8240,8241,8242,8243,8244,8245,8246,8247,8248,8249, # 7968
|
||||
8250,8251,8252,8253,8254,8255,8256,3445,8257,8258,8259,8260,8261,8262,4458,8263, # 7984
|
||||
8264,8265,8266,8267,8268,8269,8270,8271,8272,4459,8273,8274,8275,8276,3550,8277, # 8000
|
||||
8278,8279,8280,8281,8282,8283,8284,8285,8286,8287,8288,8289,4460,8290,8291,8292, # 8016
|
||||
8293,8294,8295,8296,8297,8298,8299,8300,8301,8302,8303,8304,8305,8306,8307,4867, # 8032
|
||||
8308,8309,8310,8311,8312,3551,8313,8314,8315,8316,8317,8318,8319,8320,8321,8322, # 8048
|
||||
8323,8324,8325,8326,4868,8327,8328,8329,8330,8331,8332,8333,8334,8335,8336,8337, # 8064
|
||||
8338,8339,8340,8341,8342,8343,8344,8345,8346,8347,8348,8349,8350,8351,8352,8353, # 8080
|
||||
8354,8355,8356,8357,8358,8359,8360,8361,8362,8363,4869,4461,8364,8365,8366,8367, # 8096
|
||||
8368,8369,8370,4870,8371,8372,8373,8374,8375,8376,8377,8378,8379,8380,8381,8382, # 8112
|
||||
8383,8384,8385,8386,8387,8388,8389,8390,8391,8392,8393,8394,8395,8396,8397,8398, # 8128
|
||||
8399,8400,8401,8402,8403,8404,8405,8406,8407,8408,8409,8410,4871,8411,8412,8413, # 8144
|
||||
8414,8415,8416,8417,8418,8419,8420,8421,8422,4462,8423,8424,8425,8426,8427,8428, # 8160
|
||||
8429,8430,8431,8432,8433,2986,8434,8435,8436,8437,8438,8439,8440,8441,8442,8443, # 8176
|
||||
8444,8445,8446,8447,8448,8449,8450,8451,8452,8453,8454,8455,8456,8457,8458,8459, # 8192
|
||||
8460,8461,8462,8463,8464,8465,8466,8467,8468,8469,8470,8471,8472,8473,8474,8475, # 8208
|
||||
8476,8477,8478,4180,8479,8480,8481,8482,8483,8484,8485,8486,8487,8488,8489,8490, # 8224
|
||||
8491,8492,8493,8494,8495,8496,8497,8498,8499,8500,8501,8502,8503,8504,8505,8506, # 8240
|
||||
8507,8508,8509,8510,8511,8512,8513,8514,8515,8516,8517,8518,8519,8520,8521,8522, # 8256
|
||||
8523,8524,8525,8526,8527,8528,8529,8530,8531,8532,8533,8534,8535,8536,8537,8538, # 8272
|
||||
8539,8540,8541,8542,8543,8544,8545,8546,8547,8548,8549,8550,8551,8552,8553,8554, # 8288
|
||||
8555,8556,8557,8558,8559,8560,8561,8562,8563,8564,4872,8565,8566,8567,8568,8569, # 8304
|
||||
8570,8571,8572,8573,4873,8574,8575,8576,8577,8578,8579,8580,8581,8582,8583,8584, # 8320
|
||||
8585,8586,8587,8588,8589,8590,8591,8592,8593,8594,8595,8596,8597,8598,8599,8600, # 8336
|
||||
8601,8602,8603,8604,8605,3803,8606,8607,8608,8609,8610,8611,8612,8613,4874,3804, # 8352
|
||||
8614,8615,8616,8617,8618,8619,8620,8621,3956,8622,8623,8624,8625,8626,8627,8628, # 8368
|
||||
8629,8630,8631,8632,8633,8634,8635,8636,8637,8638,2865,8639,8640,8641,8642,8643, # 8384
|
||||
8644,8645,8646,8647,8648,8649,8650,8651,8652,8653,8654,8655,8656,4463,8657,8658, # 8400
|
||||
8659,4875,4876,8660,8661,8662,8663,8664,8665,8666,8667,8668,8669,8670,8671,8672, # 8416
|
||||
8673,8674,8675,8676,8677,8678,8679,8680,8681,4464,8682,8683,8684,8685,8686,8687, # 8432
|
||||
8688,8689,8690,8691,8692,8693,8694,8695,8696,8697,8698,8699,8700,8701,8702,8703, # 8448
|
||||
8704,8705,8706,8707,8708,8709,2261,8710,8711,8712,8713,8714,8715,8716,8717,8718, # 8464
|
||||
8719,8720,8721,8722,8723,8724,8725,8726,8727,8728,8729,8730,8731,8732,8733,4181, # 8480
|
||||
8734,8735,8736,8737,8738,8739,8740,8741,8742,8743,8744,8745,8746,8747,8748,8749, # 8496
|
||||
8750,8751,8752,8753,8754,8755,8756,8757,8758,8759,8760,8761,8762,8763,4877,8764, # 8512
|
||||
8765,8766,8767,8768,8769,8770,8771,8772,8773,8774,8775,8776,8777,8778,8779,8780, # 8528
|
||||
8781,8782,8783,8784,8785,8786,8787,8788,4878,8789,4879,8790,8791,8792,4880,8793, # 8544
|
||||
8794,8795,8796,8797,8798,8799,8800,8801,4881,8802,8803,8804,8805,8806,8807,8808, # 8560
|
||||
8809,8810,8811,8812,8813,8814,8815,3957,8816,8817,8818,8819,8820,8821,8822,8823, # 8576
|
||||
8824,8825,8826,8827,8828,8829,8830,8831,8832,8833,8834,8835,8836,8837,8838,8839, # 8592
|
||||
8840,8841,8842,8843,8844,8845,8846,8847,4882,8848,8849,8850,8851,8852,8853,8854, # 8608
|
||||
8855,8856,8857,8858,8859,8860,8861,8862,8863,8864,8865,8866,8867,8868,8869,8870, # 8624
|
||||
8871,8872,8873,8874,8875,8876,8877,8878,8879,8880,8881,8882,8883,8884,3202,8885, # 8640
|
||||
8886,8887,8888,8889,8890,8891,8892,8893,8894,8895,8896,8897,8898,8899,8900,8901, # 8656
|
||||
8902,8903,8904,8905,8906,8907,8908,8909,8910,8911,8912,8913,8914,8915,8916,8917, # 8672
|
||||
8918,8919,8920,8921,8922,8923,8924,4465,8925,8926,8927,8928,8929,8930,8931,8932, # 8688
|
||||
4883,8933,8934,8935,8936,8937,8938,8939,8940,8941,8942,8943,2214,8944,8945,8946, # 8704
|
||||
8947,8948,8949,8950,8951,8952,8953,8954,8955,8956,8957,8958,8959,8960,8961,8962, # 8720
|
||||
8963,8964,8965,4884,8966,8967,8968,8969,8970,8971,8972,8973,8974,8975,8976,8977, # 8736
|
||||
8978,8979,8980,8981,8982,8983,8984,8985,8986,8987,8988,8989,8990,8991,8992,4885, # 8752
|
||||
8993,8994,8995,8996,8997,8998,8999,9000,9001,9002,9003,9004,9005,9006,9007,9008, # 8768
|
||||
9009,9010,9011,9012,9013,9014,9015,9016,9017,9018,9019,9020,9021,4182,9022,9023, # 8784
|
||||
9024,9025,9026,9027,9028,9029,9030,9031,9032,9033,9034,9035,9036,9037,9038,9039, # 8800
|
||||
9040,9041,9042,9043,9044,9045,9046,9047,9048,9049,9050,9051,9052,9053,9054,9055, # 8816
|
||||
9056,9057,9058,9059,9060,9061,9062,9063,4886,9064,9065,9066,9067,9068,9069,4887, # 8832
|
||||
9070,9071,9072,9073,9074,9075,9076,9077,9078,9079,9080,9081,9082,9083,9084,9085, # 8848
|
||||
9086,9087,9088,9089,9090,9091,9092,9093,9094,9095,9096,9097,9098,9099,9100,9101, # 8864
|
||||
9102,9103,9104,9105,9106,9107,9108,9109,9110,9111,9112,9113,9114,9115,9116,9117, # 8880
|
||||
9118,9119,9120,9121,9122,9123,9124,9125,9126,9127,9128,9129,9130,9131,9132,9133, # 8896
|
||||
9134,9135,9136,9137,9138,9139,9140,9141,3958,9142,9143,9144,9145,9146,9147,9148, # 8912
|
||||
9149,9150,9151,4888,9152,9153,9154,9155,9156,9157,9158,9159,9160,9161,9162,9163, # 8928
|
||||
9164,9165,9166,9167,9168,9169,9170,9171,9172,9173,9174,9175,4889,9176,9177,9178, # 8944
|
||||
9179,9180,9181,9182,9183,9184,9185,9186,9187,9188,9189,9190,9191,9192,9193,9194, # 8960
|
||||
9195,9196,9197,9198,9199,9200,9201,9202,9203,4890,9204,9205,9206,9207,9208,9209, # 8976
|
||||
9210,9211,9212,9213,9214,9215,9216,9217,9218,9219,9220,9221,9222,4466,9223,9224, # 8992
|
||||
9225,9226,9227,9228,9229,9230,9231,9232,9233,9234,9235,9236,9237,9238,9239,9240, # 9008
|
||||
9241,9242,9243,9244,9245,4891,9246,9247,9248,9249,9250,9251,9252,9253,9254,9255, # 9024
|
||||
9256,9257,4892,9258,9259,9260,9261,4893,4894,9262,9263,9264,9265,9266,9267,9268, # 9040
|
||||
9269,9270,9271,9272,9273,4467,9274,9275,9276,9277,9278,9279,9280,9281,9282,9283, # 9056
|
||||
9284,9285,3673,9286,9287,9288,9289,9290,9291,9292,9293,9294,9295,9296,9297,9298, # 9072
|
||||
9299,9300,9301,9302,9303,9304,9305,9306,9307,9308,9309,9310,9311,9312,9313,9314, # 9088
|
||||
9315,9316,9317,9318,9319,9320,9321,9322,4895,9323,9324,9325,9326,9327,9328,9329, # 9104
|
||||
9330,9331,9332,9333,9334,9335,9336,9337,9338,9339,9340,9341,9342,9343,9344,9345, # 9120
|
||||
9346,9347,4468,9348,9349,9350,9351,9352,9353,9354,9355,9356,9357,9358,9359,9360, # 9136
|
||||
9361,9362,9363,9364,9365,9366,9367,9368,9369,9370,9371,9372,9373,4896,9374,4469, # 9152
|
||||
9375,9376,9377,9378,9379,4897,9380,9381,9382,9383,9384,9385,9386,9387,9388,9389, # 9168
|
||||
9390,9391,9392,9393,9394,9395,9396,9397,9398,9399,9400,9401,9402,9403,9404,9405, # 9184
|
||||
9406,4470,9407,2751,9408,9409,3674,3552,9410,9411,9412,9413,9414,9415,9416,9417, # 9200
|
||||
9418,9419,9420,9421,4898,9422,9423,9424,9425,9426,9427,9428,9429,3959,9430,9431, # 9216
|
||||
9432,9433,9434,9435,9436,4471,9437,9438,9439,9440,9441,9442,9443,9444,9445,9446, # 9232
|
||||
9447,9448,9449,9450,3348,9451,9452,9453,9454,9455,9456,9457,9458,9459,9460,9461, # 9248
|
||||
9462,9463,9464,9465,9466,9467,9468,9469,9470,9471,9472,4899,9473,9474,9475,9476, # 9264
|
||||
9477,4900,9478,9479,9480,9481,9482,9483,9484,9485,9486,9487,9488,3349,9489,9490, # 9280
|
||||
9491,9492,9493,9494,9495,9496,9497,9498,9499,9500,9501,9502,9503,9504,9505,9506, # 9296
|
||||
9507,9508,9509,9510,9511,9512,9513,9514,9515,9516,9517,9518,9519,9520,4901,9521, # 9312
|
||||
9522,9523,9524,9525,9526,4902,9527,9528,9529,9530,9531,9532,9533,9534,9535,9536, # 9328
|
||||
9537,9538,9539,9540,9541,9542,9543,9544,9545,9546,9547,9548,9549,9550,9551,9552, # 9344
|
||||
9553,9554,9555,9556,9557,9558,9559,9560,9561,9562,9563,9564,9565,9566,9567,9568, # 9360
|
||||
9569,9570,9571,9572,9573,9574,9575,9576,9577,9578,9579,9580,9581,9582,9583,9584, # 9376
|
||||
3805,9585,9586,9587,9588,9589,9590,9591,9592,9593,9594,9595,9596,9597,9598,9599, # 9392
|
||||
9600,9601,9602,4903,9603,9604,9605,9606,9607,4904,9608,9609,9610,9611,9612,9613, # 9408
|
||||
9614,4905,9615,9616,9617,9618,9619,9620,9621,9622,9623,9624,9625,9626,9627,9628, # 9424
|
||||
9629,9630,9631,9632,4906,9633,9634,9635,9636,9637,9638,9639,9640,9641,9642,9643, # 9440
|
||||
4907,9644,9645,9646,9647,9648,9649,9650,9651,9652,9653,9654,9655,9656,9657,9658, # 9456
|
||||
9659,9660,9661,9662,9663,9664,9665,9666,9667,9668,9669,9670,9671,9672,4183,9673, # 9472
|
||||
9674,9675,9676,9677,4908,9678,9679,9680,9681,4909,9682,9683,9684,9685,9686,9687, # 9488
|
||||
9688,9689,9690,4910,9691,9692,9693,3675,9694,9695,9696,2945,9697,9698,9699,9700, # 9504
|
||||
9701,9702,9703,9704,9705,4911,9706,9707,9708,9709,9710,9711,9712,9713,9714,9715, # 9520
|
||||
9716,9717,9718,9719,9720,9721,9722,9723,9724,9725,9726,9727,9728,9729,9730,9731, # 9536
|
||||
9732,9733,9734,9735,4912,9736,9737,9738,9739,9740,4913,9741,9742,9743,9744,9745, # 9552
|
||||
9746,9747,9748,9749,9750,9751,9752,9753,9754,9755,9756,9757,9758,4914,9759,9760, # 9568
|
||||
9761,9762,9763,9764,9765,9766,9767,9768,9769,9770,9771,9772,9773,9774,9775,9776, # 9584
|
||||
9777,9778,9779,9780,9781,9782,4915,9783,9784,9785,9786,9787,9788,9789,9790,9791, # 9600
|
||||
9792,9793,4916,9794,9795,9796,9797,9798,9799,9800,9801,9802,9803,9804,9805,9806, # 9616
|
||||
9807,9808,9809,9810,9811,9812,9813,9814,9815,9816,9817,9818,9819,9820,9821,9822, # 9632
|
||||
9823,9824,9825,9826,9827,9828,9829,9830,9831,9832,9833,9834,9835,9836,9837,9838, # 9648
|
||||
9839,9840,9841,9842,9843,9844,9845,9846,9847,9848,9849,9850,9851,9852,9853,9854, # 9664
|
||||
9855,9856,9857,9858,9859,9860,9861,9862,9863,9864,9865,9866,9867,9868,4917,9869, # 9680
|
||||
9870,9871,9872,9873,9874,9875,9876,9877,9878,9879,9880,9881,9882,9883,9884,9885, # 9696
|
||||
9886,9887,9888,9889,9890,9891,9892,4472,9893,9894,9895,9896,9897,3806,9898,9899, # 9712
|
||||
9900,9901,9902,9903,9904,9905,9906,9907,9908,9909,9910,9911,9912,9913,9914,4918, # 9728
|
||||
9915,9916,9917,4919,9918,9919,9920,9921,4184,9922,9923,9924,9925,9926,9927,9928, # 9744
|
||||
9929,9930,9931,9932,9933,9934,9935,9936,9937,9938,9939,9940,9941,9942,9943,9944, # 9760
|
||||
9945,9946,4920,9947,9948,9949,9950,9951,9952,9953,9954,9955,4185,9956,9957,9958, # 9776
|
||||
9959,9960,9961,9962,9963,9964,9965,4921,9966,9967,9968,4473,9969,9970,9971,9972, # 9792
|
||||
9973,9974,9975,9976,9977,4474,9978,9979,9980,9981,9982,9983,9984,9985,9986,9987, # 9808
|
||||
9988,9989,9990,9991,9992,9993,9994,9995,9996,9997,9998,9999,10000,10001,10002,10003, # 9824
|
||||
10004,10005,10006,10007,10008,10009,10010,10011,10012,10013,10014,10015,10016,10017,10018,10019, # 9840
|
||||
10020,10021,4922,10022,4923,10023,10024,10025,10026,10027,10028,10029,10030,10031,10032,10033, # 9856
|
||||
10034,10035,10036,10037,10038,10039,10040,10041,10042,10043,10044,10045,10046,10047,10048,4924, # 9872
|
||||
10049,10050,10051,10052,10053,10054,10055,10056,10057,10058,10059,10060,10061,10062,10063,10064, # 9888
|
||||
10065,10066,10067,10068,10069,10070,10071,10072,10073,10074,10075,10076,10077,10078,10079,10080, # 9904
|
||||
10081,10082,10083,10084,10085,10086,10087,4475,10088,10089,10090,10091,10092,10093,10094,10095, # 9920
|
||||
10096,10097,4476,10098,10099,10100,10101,10102,10103,10104,10105,10106,10107,10108,10109,10110, # 9936
|
||||
10111,2174,10112,10113,10114,10115,10116,10117,10118,10119,10120,10121,10122,10123,10124,10125, # 9952
|
||||
10126,10127,10128,10129,10130,10131,10132,10133,10134,10135,10136,10137,10138,10139,10140,3807, # 9968
|
||||
4186,4925,10141,10142,10143,10144,10145,10146,10147,4477,4187,10148,10149,10150,10151,10152, # 9984
|
||||
10153,4188,10154,10155,10156,10157,10158,10159,10160,10161,4926,10162,10163,10164,10165,10166, #10000
|
||||
10167,10168,10169,10170,10171,10172,10173,10174,10175,10176,10177,10178,10179,10180,10181,10182, #10016
|
||||
10183,10184,10185,10186,10187,10188,10189,10190,10191,10192,3203,10193,10194,10195,10196,10197, #10032
|
||||
10198,10199,10200,4478,10201,10202,10203,10204,4479,10205,10206,10207,10208,10209,10210,10211, #10048
|
||||
10212,10213,10214,10215,10216,10217,10218,10219,10220,10221,10222,10223,10224,10225,10226,10227, #10064
|
||||
10228,10229,10230,10231,10232,10233,10234,4927,10235,10236,10237,10238,10239,10240,10241,10242, #10080
|
||||
10243,10244,10245,10246,10247,10248,10249,10250,10251,10252,10253,10254,10255,10256,10257,10258, #10096
|
||||
10259,10260,10261,10262,10263,10264,10265,10266,10267,10268,10269,10270,10271,10272,10273,4480, #10112
|
||||
4928,4929,10274,10275,10276,10277,10278,10279,10280,10281,10282,10283,10284,10285,10286,10287, #10128
|
||||
10288,10289,10290,10291,10292,10293,10294,10295,10296,10297,10298,10299,10300,10301,10302,10303, #10144
|
||||
10304,10305,10306,10307,10308,10309,10310,10311,10312,10313,10314,10315,10316,10317,10318,10319, #10160
|
||||
10320,10321,10322,10323,10324,10325,10326,10327,10328,10329,10330,10331,10332,10333,10334,4930, #10176
|
||||
10335,10336,10337,10338,10339,10340,10341,10342,4931,10343,10344,10345,10346,10347,10348,10349, #10192
|
||||
10350,10351,10352,10353,10354,10355,3088,10356,2786,10357,10358,10359,10360,4189,10361,10362, #10208
|
||||
10363,10364,10365,10366,10367,10368,10369,10370,10371,10372,10373,10374,10375,4932,10376,10377, #10224
|
||||
10378,10379,10380,10381,10382,10383,10384,10385,10386,10387,10388,10389,10390,10391,10392,4933, #10240
|
||||
10393,10394,10395,4934,10396,10397,10398,10399,10400,10401,10402,10403,10404,10405,10406,10407, #10256
|
||||
10408,10409,10410,10411,10412,3446,10413,10414,10415,10416,10417,10418,10419,10420,10421,10422, #10272
|
||||
10423,4935,10424,10425,10426,10427,10428,10429,10430,4936,10431,10432,10433,10434,10435,10436, #10288
|
||||
10437,10438,10439,10440,10441,10442,10443,4937,10444,10445,10446,10447,4481,10448,10449,10450, #10304
|
||||
10451,10452,10453,10454,10455,10456,10457,10458,10459,10460,10461,10462,10463,10464,10465,10466, #10320
|
||||
10467,10468,10469,10470,10471,10472,10473,10474,10475,10476,10477,10478,10479,10480,10481,10482, #10336
|
||||
10483,10484,10485,10486,10487,10488,10489,10490,10491,10492,10493,10494,10495,10496,10497,10498, #10352
|
||||
10499,10500,10501,10502,10503,10504,10505,4938,10506,10507,10508,10509,10510,2552,10511,10512, #10368
|
||||
10513,10514,10515,10516,3447,10517,10518,10519,10520,10521,10522,10523,10524,10525,10526,10527, #10384
|
||||
10528,10529,10530,10531,10532,10533,10534,10535,10536,10537,10538,10539,10540,10541,10542,10543, #10400
|
||||
4482,10544,4939,10545,10546,10547,10548,10549,10550,10551,10552,10553,10554,10555,10556,10557, #10416
|
||||
10558,10559,10560,10561,10562,10563,10564,10565,10566,10567,3676,4483,10568,10569,10570,10571, #10432
|
||||
10572,3448,10573,10574,10575,10576,10577,10578,10579,10580,10581,10582,10583,10584,10585,10586, #10448
|
||||
10587,10588,10589,10590,10591,10592,10593,10594,10595,10596,10597,10598,10599,10600,10601,10602, #10464
|
||||
10603,10604,10605,10606,10607,10608,10609,10610,10611,10612,10613,10614,10615,10616,10617,10618, #10480
|
||||
10619,10620,10621,10622,10623,10624,10625,10626,10627,4484,10628,10629,10630,10631,10632,4940, #10496
|
||||
10633,10634,10635,10636,10637,10638,10639,10640,10641,10642,10643,10644,10645,10646,10647,10648, #10512
|
||||
10649,10650,10651,10652,10653,10654,10655,10656,4941,10657,10658,10659,2599,10660,10661,10662, #10528
|
||||
10663,10664,10665,10666,3089,10667,10668,10669,10670,10671,10672,10673,10674,10675,10676,10677, #10544
|
||||
10678,10679,10680,4942,10681,10682,10683,10684,10685,10686,10687,10688,10689,10690,10691,10692, #10560
|
||||
10693,10694,10695,10696,10697,4485,10698,10699,10700,10701,10702,10703,10704,4943,10705,3677, #10576
|
||||
10706,10707,10708,10709,10710,10711,10712,4944,10713,10714,10715,10716,10717,10718,10719,10720, #10592
|
||||
10721,10722,10723,10724,10725,10726,10727,10728,4945,10729,10730,10731,10732,10733,10734,10735, #10608
|
||||
10736,10737,10738,10739,10740,10741,10742,10743,10744,10745,10746,10747,10748,10749,10750,10751, #10624
|
||||
10752,10753,10754,10755,10756,10757,10758,10759,10760,10761,4946,10762,10763,10764,10765,10766, #10640
|
||||
10767,4947,4948,10768,10769,10770,10771,10772,10773,10774,10775,10776,10777,10778,10779,10780, #10656
|
||||
10781,10782,10783,10784,10785,10786,10787,10788,10789,10790,10791,10792,10793,10794,10795,10796, #10672
|
||||
10797,10798,10799,10800,10801,10802,10803,10804,10805,10806,10807,10808,10809,10810,10811,10812, #10688
|
||||
10813,10814,10815,10816,10817,10818,10819,10820,10821,10822,10823,10824,10825,10826,10827,10828, #10704
|
||||
10829,10830,10831,10832,10833,10834,10835,10836,10837,10838,10839,10840,10841,10842,10843,10844, #10720
|
||||
10845,10846,10847,10848,10849,10850,10851,10852,10853,10854,10855,10856,10857,10858,10859,10860, #10736
|
||||
10861,10862,10863,10864,10865,10866,10867,10868,10869,10870,10871,10872,10873,10874,10875,10876, #10752
|
||||
10877,10878,4486,10879,10880,10881,10882,10883,10884,10885,4949,10886,10887,10888,10889,10890, #10768
|
||||
10891,10892,10893,10894,10895,10896,10897,10898,10899,10900,10901,10902,10903,10904,10905,10906, #10784
|
||||
10907,10908,10909,10910,10911,10912,10913,10914,10915,10916,10917,10918,10919,4487,10920,10921, #10800
|
||||
10922,10923,10924,10925,10926,10927,10928,10929,10930,10931,10932,4950,10933,10934,10935,10936, #10816
|
||||
10937,10938,10939,10940,10941,10942,10943,10944,10945,10946,10947,10948,10949,4488,10950,10951, #10832
|
||||
10952,10953,10954,10955,10956,10957,10958,10959,4190,10960,10961,10962,10963,10964,10965,10966, #10848
|
||||
10967,10968,10969,10970,10971,10972,10973,10974,10975,10976,10977,10978,10979,10980,10981,10982, #10864
|
||||
10983,10984,10985,10986,10987,10988,10989,10990,10991,10992,10993,10994,10995,10996,10997,10998, #10880
|
||||
10999,11000,11001,11002,11003,11004,11005,11006,3960,11007,11008,11009,11010,11011,11012,11013, #10896
|
||||
11014,11015,11016,11017,11018,11019,11020,11021,11022,11023,11024,11025,11026,11027,11028,11029, #10912
|
||||
11030,11031,11032,4951,11033,11034,11035,11036,11037,11038,11039,11040,11041,11042,11043,11044, #10928
|
||||
11045,11046,11047,4489,11048,11049,11050,11051,4952,11052,11053,11054,11055,11056,11057,11058, #10944
|
||||
4953,11059,11060,11061,11062,11063,11064,11065,11066,11067,11068,11069,11070,11071,4954,11072, #10960
|
||||
11073,11074,11075,11076,11077,11078,11079,11080,11081,11082,11083,11084,11085,11086,11087,11088, #10976
|
||||
11089,11090,11091,11092,11093,11094,11095,11096,11097,11098,11099,11100,11101,11102,11103,11104, #10992
|
||||
11105,11106,11107,11108,11109,11110,11111,11112,11113,11114,11115,3808,11116,11117,11118,11119, #11008
|
||||
11120,11121,11122,11123,11124,11125,11126,11127,11128,11129,11130,11131,11132,11133,11134,4955, #11024
|
||||
11135,11136,11137,11138,11139,11140,11141,11142,11143,11144,11145,11146,11147,11148,11149,11150, #11040
|
||||
11151,11152,11153,11154,11155,11156,11157,11158,11159,11160,11161,4956,11162,11163,11164,11165, #11056
|
||||
11166,11167,11168,11169,11170,11171,11172,11173,11174,11175,11176,11177,11178,11179,11180,4957, #11072
|
||||
11181,11182,11183,11184,11185,11186,4958,11187,11188,11189,11190,11191,11192,11193,11194,11195, #11088
|
||||
11196,11197,11198,11199,11200,3678,11201,11202,11203,11204,11205,11206,4191,11207,11208,11209, #11104
|
||||
11210,11211,11212,11213,11214,11215,11216,11217,11218,11219,11220,11221,11222,11223,11224,11225, #11120
|
||||
11226,11227,11228,11229,11230,11231,11232,11233,11234,11235,11236,11237,11238,11239,11240,11241, #11136
|
||||
11242,11243,11244,11245,11246,11247,11248,11249,11250,11251,4959,11252,11253,11254,11255,11256, #11152
|
||||
11257,11258,11259,11260,11261,11262,11263,11264,11265,11266,11267,11268,11269,11270,11271,11272, #11168
|
||||
11273,11274,11275,11276,11277,11278,11279,11280,11281,11282,11283,11284,11285,11286,11287,11288, #11184
|
||||
11289,11290,11291,11292,11293,11294,11295,11296,11297,11298,11299,11300,11301,11302,11303,11304, #11200
|
||||
11305,11306,11307,11308,11309,11310,11311,11312,11313,11314,3679,11315,11316,11317,11318,4490, #11216
|
||||
11319,11320,11321,11322,11323,11324,11325,11326,11327,11328,11329,11330,11331,11332,11333,11334, #11232
|
||||
11335,11336,11337,11338,11339,11340,11341,11342,11343,11344,11345,11346,11347,4960,11348,11349, #11248
|
||||
11350,11351,11352,11353,11354,11355,11356,11357,11358,11359,11360,11361,11362,11363,11364,11365, #11264
|
||||
11366,11367,11368,11369,11370,11371,11372,11373,11374,11375,11376,11377,3961,4961,11378,11379, #11280
|
||||
11380,11381,11382,11383,11384,11385,11386,11387,11388,11389,11390,11391,11392,11393,11394,11395, #11296
|
||||
11396,11397,4192,11398,11399,11400,11401,11402,11403,11404,11405,11406,11407,11408,11409,11410, #11312
|
||||
11411,4962,11412,11413,11414,11415,11416,11417,11418,11419,11420,11421,11422,11423,11424,11425, #11328
|
||||
11426,11427,11428,11429,11430,11431,11432,11433,11434,11435,11436,11437,11438,11439,11440,11441, #11344
|
||||
11442,11443,11444,11445,11446,11447,11448,11449,11450,11451,11452,11453,11454,11455,11456,11457, #11360
|
||||
11458,11459,11460,11461,11462,11463,11464,11465,11466,11467,11468,11469,4963,11470,11471,4491, #11376
|
||||
11472,11473,11474,11475,4964,11476,11477,11478,11479,11480,11481,11482,11483,11484,11485,11486, #11392
|
||||
11487,11488,11489,11490,11491,11492,4965,11493,11494,11495,11496,11497,11498,11499,11500,11501, #11408
|
||||
11502,11503,11504,11505,11506,11507,11508,11509,11510,11511,11512,11513,11514,11515,11516,11517, #11424
|
||||
11518,11519,11520,11521,11522,11523,11524,11525,11526,11527,11528,11529,3962,11530,11531,11532, #11440
|
||||
11533,11534,11535,11536,11537,11538,11539,11540,11541,11542,11543,11544,11545,11546,11547,11548, #11456
|
||||
11549,11550,11551,11552,11553,11554,11555,11556,11557,11558,11559,11560,11561,11562,11563,11564, #11472
|
||||
4193,4194,11565,11566,11567,11568,11569,11570,11571,11572,11573,11574,11575,11576,11577,11578, #11488
|
||||
11579,11580,11581,11582,11583,11584,11585,11586,11587,11588,11589,11590,11591,4966,4195,11592, #11504
|
||||
11593,11594,11595,11596,11597,11598,11599,11600,11601,11602,11603,11604,3090,11605,11606,11607, #11520
|
||||
11608,11609,11610,4967,11611,11612,11613,11614,11615,11616,11617,11618,11619,11620,11621,11622, #11536
|
||||
11623,11624,11625,11626,11627,11628,11629,11630,11631,11632,11633,11634,11635,11636,11637,11638, #11552
|
||||
11639,11640,11641,11642,11643,11644,11645,11646,11647,11648,11649,11650,11651,11652,11653,11654, #11568
|
||||
11655,11656,11657,11658,11659,11660,11661,11662,11663,11664,11665,11666,11667,11668,11669,11670, #11584
|
||||
11671,11672,11673,11674,4968,11675,11676,11677,11678,11679,11680,11681,11682,11683,11684,11685, #11600
|
||||
11686,11687,11688,11689,11690,11691,11692,11693,3809,11694,11695,11696,11697,11698,11699,11700, #11616
|
||||
11701,11702,11703,11704,11705,11706,11707,11708,11709,11710,11711,11712,11713,11714,11715,11716, #11632
|
||||
11717,11718,3553,11719,11720,11721,11722,11723,11724,11725,11726,11727,11728,11729,11730,4969, #11648
|
||||
11731,11732,11733,11734,11735,11736,11737,11738,11739,11740,4492,11741,11742,11743,11744,11745, #11664
|
||||
11746,11747,11748,11749,11750,11751,11752,4970,11753,11754,11755,11756,11757,11758,11759,11760, #11680
|
||||
11761,11762,11763,11764,11765,11766,11767,11768,11769,11770,11771,11772,11773,11774,11775,11776, #11696
|
||||
11777,11778,11779,11780,11781,11782,11783,11784,11785,11786,11787,11788,11789,11790,4971,11791, #11712
|
||||
11792,11793,11794,11795,11796,11797,4972,11798,11799,11800,11801,11802,11803,11804,11805,11806, #11728
|
||||
11807,11808,11809,11810,4973,11811,11812,11813,11814,11815,11816,11817,11818,11819,11820,11821, #11744
|
||||
11822,11823,11824,11825,11826,11827,11828,11829,11830,11831,11832,11833,11834,3680,3810,11835, #11760
|
||||
11836,4974,11837,11838,11839,11840,11841,11842,11843,11844,11845,11846,11847,11848,11849,11850, #11776
|
||||
11851,11852,11853,11854,11855,11856,11857,11858,11859,11860,11861,11862,11863,11864,11865,11866, #11792
|
||||
11867,11868,11869,11870,11871,11872,11873,11874,11875,11876,11877,11878,11879,11880,11881,11882, #11808
|
||||
11883,11884,4493,11885,11886,11887,11888,11889,11890,11891,11892,11893,11894,11895,11896,11897, #11824
|
||||
11898,11899,11900,11901,11902,11903,11904,11905,11906,11907,11908,11909,11910,11911,11912,11913, #11840
|
||||
11914,11915,4975,11916,11917,11918,11919,11920,11921,11922,11923,11924,11925,11926,11927,11928, #11856
|
||||
11929,11930,11931,11932,11933,11934,11935,11936,11937,11938,11939,11940,11941,11942,11943,11944, #11872
|
||||
11945,11946,11947,11948,11949,4976,11950,11951,11952,11953,11954,11955,11956,11957,11958,11959, #11888
|
||||
11960,11961,11962,11963,11964,11965,11966,11967,11968,11969,11970,11971,11972,11973,11974,11975, #11904
|
||||
11976,11977,11978,11979,11980,11981,11982,11983,11984,11985,11986,11987,4196,11988,11989,11990, #11920
|
||||
11991,11992,4977,11993,11994,11995,11996,11997,11998,11999,12000,12001,12002,12003,12004,12005, #11936
|
||||
12006,12007,12008,12009,12010,12011,12012,12013,12014,12015,12016,12017,12018,12019,12020,12021, #11952
|
||||
12022,12023,12024,12025,12026,12027,12028,12029,12030,12031,12032,12033,12034,12035,12036,12037, #11968
|
||||
12038,12039,12040,12041,12042,12043,12044,12045,12046,12047,12048,12049,12050,12051,12052,12053, #11984
|
||||
12054,12055,12056,12057,12058,12059,12060,12061,4978,12062,12063,12064,12065,12066,12067,12068, #12000
|
||||
12069,12070,12071,12072,12073,12074,12075,12076,12077,12078,12079,12080,12081,12082,12083,12084, #12016
|
||||
12085,12086,12087,12088,12089,12090,12091,12092,12093,12094,12095,12096,12097,12098,12099,12100, #12032
|
||||
12101,12102,12103,12104,12105,12106,12107,12108,12109,12110,12111,12112,12113,12114,12115,12116, #12048
|
||||
12117,12118,12119,12120,12121,12122,12123,4979,12124,12125,12126,12127,12128,4197,12129,12130, #12064
|
||||
12131,12132,12133,12134,12135,12136,12137,12138,12139,12140,12141,12142,12143,12144,12145,12146, #12080
|
||||
12147,12148,12149,12150,12151,12152,12153,12154,4980,12155,12156,12157,12158,12159,12160,4494, #12096
|
||||
12161,12162,12163,12164,3811,12165,12166,12167,12168,12169,4495,12170,12171,4496,12172,12173, #12112
|
||||
12174,12175,12176,3812,12177,12178,12179,12180,12181,12182,12183,12184,12185,12186,12187,12188, #12128
|
||||
12189,12190,12191,12192,12193,12194,12195,12196,12197,12198,12199,12200,12201,12202,12203,12204, #12144
|
||||
12205,12206,12207,12208,12209,12210,12211,12212,12213,12214,12215,12216,12217,12218,12219,12220, #12160
|
||||
12221,4981,12222,12223,12224,12225,12226,12227,12228,12229,12230,12231,12232,12233,12234,12235, #12176
|
||||
4982,12236,12237,12238,12239,12240,12241,12242,12243,12244,12245,4983,12246,12247,12248,12249, #12192
|
||||
4984,12250,12251,12252,12253,12254,12255,12256,12257,12258,12259,12260,12261,12262,12263,12264, #12208
|
||||
4985,12265,4497,12266,12267,12268,12269,12270,12271,12272,12273,12274,12275,12276,12277,12278, #12224
|
||||
12279,12280,12281,12282,12283,12284,12285,12286,12287,4986,12288,12289,12290,12291,12292,12293, #12240
|
||||
12294,12295,12296,2473,12297,12298,12299,12300,12301,12302,12303,12304,12305,12306,12307,12308, #12256
|
||||
12309,12310,12311,12312,12313,12314,12315,12316,12317,12318,12319,3963,12320,12321,12322,12323, #12272
|
||||
12324,12325,12326,12327,12328,12329,12330,12331,12332,4987,12333,12334,12335,12336,12337,12338, #12288
|
||||
12339,12340,12341,12342,12343,12344,12345,12346,12347,12348,12349,12350,12351,12352,12353,12354, #12304
|
||||
12355,12356,12357,12358,12359,3964,12360,12361,12362,12363,12364,12365,12366,12367,12368,12369, #12320
|
||||
12370,3965,12371,12372,12373,12374,12375,12376,12377,12378,12379,12380,12381,12382,12383,12384, #12336
|
||||
12385,12386,12387,12388,12389,12390,12391,12392,12393,12394,12395,12396,12397,12398,12399,12400, #12352
|
||||
12401,12402,12403,12404,12405,12406,12407,12408,4988,12409,12410,12411,12412,12413,12414,12415, #12368
|
||||
12416,12417,12418,12419,12420,12421,12422,12423,12424,12425,12426,12427,12428,12429,12430,12431, #12384
|
||||
12432,12433,12434,12435,12436,12437,12438,3554,12439,12440,12441,12442,12443,12444,12445,12446, #12400
|
||||
12447,12448,12449,12450,12451,12452,12453,12454,12455,12456,12457,12458,12459,12460,12461,12462, #12416
|
||||
12463,12464,4989,12465,12466,12467,12468,12469,12470,12471,12472,12473,12474,12475,12476,12477, #12432
|
||||
12478,12479,12480,4990,12481,12482,12483,12484,12485,12486,12487,12488,12489,4498,12490,12491, #12448
|
||||
12492,12493,12494,12495,12496,12497,12498,12499,12500,12501,12502,12503,12504,12505,12506,12507, #12464
|
||||
12508,12509,12510,12511,12512,12513,12514,12515,12516,12517,12518,12519,12520,12521,12522,12523, #12480
|
||||
12524,12525,12526,12527,12528,12529,12530,12531,12532,12533,12534,12535,12536,12537,12538,12539, #12496
|
||||
12540,12541,12542,12543,12544,12545,12546,12547,12548,12549,12550,12551,4991,12552,12553,12554, #12512
|
||||
12555,12556,12557,12558,12559,12560,12561,12562,12563,12564,12565,12566,12567,12568,12569,12570, #12528
|
||||
12571,12572,12573,12574,12575,12576,12577,12578,3036,12579,12580,12581,12582,12583,3966,12584, #12544
|
||||
12585,12586,12587,12588,12589,12590,12591,12592,12593,12594,12595,12596,12597,12598,12599,12600, #12560
|
||||
12601,12602,12603,12604,12605,12606,12607,12608,12609,12610,12611,12612,12613,12614,12615,12616, #12576
|
||||
12617,12618,12619,12620,12621,12622,12623,12624,12625,12626,12627,12628,12629,12630,12631,12632, #12592
|
||||
12633,12634,12635,12636,12637,12638,12639,12640,12641,12642,12643,12644,12645,12646,4499,12647, #12608
|
||||
12648,12649,12650,12651,12652,12653,12654,12655,12656,12657,12658,12659,12660,12661,12662,12663, #12624
|
||||
12664,12665,12666,12667,12668,12669,12670,12671,12672,12673,12674,12675,12676,12677,12678,12679, #12640
|
||||
12680,12681,12682,12683,12684,12685,12686,12687,12688,12689,12690,12691,12692,12693,12694,12695, #12656
|
||||
12696,12697,12698,4992,12699,12700,12701,12702,12703,12704,12705,12706,12707,12708,12709,12710, #12672
|
||||
12711,12712,12713,12714,12715,12716,12717,12718,12719,12720,12721,12722,12723,12724,12725,12726, #12688
|
||||
12727,12728,12729,12730,12731,12732,12733,12734,12735,12736,12737,12738,12739,12740,12741,12742, #12704
|
||||
12743,12744,12745,12746,12747,12748,12749,12750,12751,12752,12753,12754,12755,12756,12757,12758, #12720
|
||||
12759,12760,12761,12762,12763,12764,12765,12766,12767,12768,12769,12770,12771,12772,12773,12774, #12736
|
||||
12775,12776,12777,12778,4993,2175,12779,12780,12781,12782,12783,12784,12785,12786,4500,12787, #12752
|
||||
12788,12789,12790,12791,12792,12793,12794,12795,12796,12797,12798,12799,12800,12801,12802,12803, #12768
|
||||
12804,12805,12806,12807,12808,12809,12810,12811,12812,12813,12814,12815,12816,12817,12818,12819, #12784
|
||||
12820,12821,12822,12823,12824,12825,12826,4198,3967,12827,12828,12829,12830,12831,12832,12833, #12800
|
||||
12834,12835,12836,12837,12838,12839,12840,12841,12842,12843,12844,12845,12846,12847,12848,12849, #12816
|
||||
12850,12851,12852,12853,12854,12855,12856,12857,12858,12859,12860,12861,4199,12862,12863,12864, #12832
|
||||
12865,12866,12867,12868,12869,12870,12871,12872,12873,12874,12875,12876,12877,12878,12879,12880, #12848
|
||||
12881,12882,12883,12884,12885,12886,12887,4501,12888,12889,12890,12891,12892,12893,12894,12895, #12864
|
||||
12896,12897,12898,12899,12900,12901,12902,12903,12904,12905,12906,12907,12908,12909,12910,12911, #12880
|
||||
12912,4994,12913,12914,12915,12916,12917,12918,12919,12920,12921,12922,12923,12924,12925,12926, #12896
|
||||
12927,12928,12929,12930,12931,12932,12933,12934,12935,12936,12937,12938,12939,12940,12941,12942, #12912
|
||||
12943,12944,12945,12946,12947,12948,12949,12950,12951,12952,12953,12954,12955,12956,1772,12957, #12928
|
||||
12958,12959,12960,12961,12962,12963,12964,12965,12966,12967,12968,12969,12970,12971,12972,12973, #12944
|
||||
12974,12975,12976,12977,12978,12979,12980,12981,12982,12983,12984,12985,12986,12987,12988,12989, #12960
|
||||
12990,12991,12992,12993,12994,12995,12996,12997,4502,12998,4503,12999,13000,13001,13002,13003, #12976
|
||||
4504,13004,13005,13006,13007,13008,13009,13010,13011,13012,13013,13014,13015,13016,13017,13018, #12992
|
||||
13019,13020,13021,13022,13023,13024,13025,13026,13027,13028,13029,3449,13030,13031,13032,13033, #13008
|
||||
13034,13035,13036,13037,13038,13039,13040,13041,13042,13043,13044,13045,13046,13047,13048,13049, #13024
|
||||
13050,13051,13052,13053,13054,13055,13056,13057,13058,13059,13060,13061,13062,13063,13064,13065, #13040
|
||||
13066,13067,13068,13069,13070,13071,13072,13073,13074,13075,13076,13077,13078,13079,13080,13081, #13056
|
||||
13082,13083,13084,13085,13086,13087,13088,13089,13090,13091,13092,13093,13094,13095,13096,13097, #13072
|
||||
13098,13099,13100,13101,13102,13103,13104,13105,13106,13107,13108,13109,13110,13111,13112,13113, #13088
|
||||
13114,13115,13116,13117,13118,3968,13119,4995,13120,13121,13122,13123,13124,13125,13126,13127, #13104
|
||||
4505,13128,13129,13130,13131,13132,13133,13134,4996,4506,13135,13136,13137,13138,13139,4997, #13120
|
||||
13140,13141,13142,13143,13144,13145,13146,13147,13148,13149,13150,13151,13152,13153,13154,13155, #13136
|
||||
13156,13157,13158,13159,4998,13160,13161,13162,13163,13164,13165,13166,13167,13168,13169,13170, #13152
|
||||
13171,13172,13173,13174,13175,13176,4999,13177,13178,13179,13180,13181,13182,13183,13184,13185, #13168
|
||||
13186,13187,13188,13189,13190,13191,13192,13193,13194,13195,13196,13197,13198,13199,13200,13201, #13184
|
||||
13202,13203,13204,13205,13206,5000,13207,13208,13209,13210,13211,13212,13213,13214,13215,13216, #13200
|
||||
13217,13218,13219,13220,13221,13222,13223,13224,13225,13226,13227,4200,5001,13228,13229,13230, #13216
|
||||
13231,13232,13233,13234,13235,13236,13237,13238,13239,13240,3969,13241,13242,13243,13244,3970, #13232
|
||||
13245,13246,13247,13248,13249,13250,13251,13252,13253,13254,13255,13256,13257,13258,13259,13260, #13248
|
||||
13261,13262,13263,13264,13265,13266,13267,13268,3450,13269,13270,13271,13272,13273,13274,13275, #13264
|
||||
13276,5002,13277,13278,13279,13280,13281,13282,13283,13284,13285,13286,13287,13288,13289,13290, #13280
|
||||
13291,13292,13293,13294,13295,13296,13297,13298,13299,13300,13301,13302,3813,13303,13304,13305, #13296
|
||||
13306,13307,13308,13309,13310,13311,13312,13313,13314,13315,13316,13317,13318,13319,13320,13321, #13312
|
||||
13322,13323,13324,13325,13326,13327,13328,4507,13329,13330,13331,13332,13333,13334,13335,13336, #13328
|
||||
13337,13338,13339,13340,13341,5003,13342,13343,13344,13345,13346,13347,13348,13349,13350,13351, #13344
|
||||
13352,13353,13354,13355,13356,13357,13358,13359,13360,13361,13362,13363,13364,13365,13366,13367, #13360
|
||||
5004,13368,13369,13370,13371,13372,13373,13374,13375,13376,13377,13378,13379,13380,13381,13382, #13376
|
||||
13383,13384,13385,13386,13387,13388,13389,13390,13391,13392,13393,13394,13395,13396,13397,13398, #13392
|
||||
13399,13400,13401,13402,13403,13404,13405,13406,13407,13408,13409,13410,13411,13412,13413,13414, #13408
|
||||
13415,13416,13417,13418,13419,13420,13421,13422,13423,13424,13425,13426,13427,13428,13429,13430, #13424
|
||||
13431,13432,4508,13433,13434,13435,4201,13436,13437,13438,13439,13440,13441,13442,13443,13444, #13440
|
||||
13445,13446,13447,13448,13449,13450,13451,13452,13453,13454,13455,13456,13457,5005,13458,13459, #13456
|
||||
13460,13461,13462,13463,13464,13465,13466,13467,13468,13469,13470,4509,13471,13472,13473,13474, #13472
|
||||
13475,13476,13477,13478,13479,13480,13481,13482,13483,13484,13485,13486,13487,13488,13489,13490, #13488
|
||||
13491,13492,13493,13494,13495,13496,13497,13498,13499,13500,13501,13502,13503,13504,13505,13506, #13504
|
||||
13507,13508,13509,13510,13511,13512,13513,13514,13515,13516,13517,13518,13519,13520,13521,13522, #13520
|
||||
13523,13524,13525,13526,13527,13528,13529,13530,13531,13532,13533,13534,13535,13536,13537,13538, #13536
|
||||
13539,13540,13541,13542,13543,13544,13545,13546,13547,13548,13549,13550,13551,13552,13553,13554, #13552
|
||||
13555,13556,13557,13558,13559,13560,13561,13562,13563,13564,13565,13566,13567,13568,13569,13570, #13568
|
||||
13571,13572,13573,13574,13575,13576,13577,13578,13579,13580,13581,13582,13583,13584,13585,13586, #13584
|
||||
13587,13588,13589,13590,13591,13592,13593,13594,13595,13596,13597,13598,13599,13600,13601,13602, #13600
|
||||
13603,13604,13605,13606,13607,13608,13609,13610,13611,13612,13613,13614,13615,13616,13617,13618, #13616
|
||||
13619,13620,13621,13622,13623,13624,13625,13626,13627,13628,13629,13630,13631,13632,13633,13634, #13632
|
||||
13635,13636,13637,13638,13639,13640,13641,13642,5006,13643,13644,13645,13646,13647,13648,13649, #13648
|
||||
13650,13651,5007,13652,13653,13654,13655,13656,13657,13658,13659,13660,13661,13662,13663,13664, #13664
|
||||
13665,13666,13667,13668,13669,13670,13671,13672,13673,13674,13675,13676,13677,13678,13679,13680, #13680
|
||||
13681,13682,13683,13684,13685,13686,13687,13688,13689,13690,13691,13692,13693,13694,13695,13696, #13696
|
||||
13697,13698,13699,13700,13701,13702,13703,13704,13705,13706,13707,13708,13709,13710,13711,13712, #13712
|
||||
13713,13714,13715,13716,13717,13718,13719,13720,13721,13722,13723,13724,13725,13726,13727,13728, #13728
|
||||
13729,13730,13731,13732,13733,13734,13735,13736,13737,13738,13739,13740,13741,13742,13743,13744, #13744
|
||||
13745,13746,13747,13748,13749,13750,13751,13752,13753,13754,13755,13756,13757,13758,13759,13760, #13760
|
||||
13761,13762,13763,13764,13765,13766,13767,13768,13769,13770,13771,13772,13773,13774,3273,13775, #13776
|
||||
13776,13777,13778,13779,13780,13781,13782,13783,13784,13785,13786,13787,13788,13789,13790,13791, #13792
|
||||
13792,13793,13794,13795,13796,13797,13798,13799,13800,13801,13802,13803,13804,13805,13806,13807, #13808
|
||||
13808,13809,13810,13811,13812,13813,13814,13815,13816,13817,13818,13819,13820,13821,13822,13823, #13824
|
||||
13824,13825,13826,13827,13828,13829,13830,13831,13832,13833,13834,13835,13836,13837,13838,13839, #13840
|
||||
13840,13841,13842,13843,13844,13845,13846,13847,13848,13849,13850,13851,13852,13853,13854,13855, #13856
|
||||
13856,13857,13858,13859,13860,13861,13862,13863,13864,13865,13866,13867,13868,13869,13870,13871, #13872
|
||||
13872,13873,13874,13875,13876,13877,13878,13879,13880,13881,13882,13883,13884,13885,13886,13887, #13888
|
||||
13888,13889,13890,13891,13892,13893,13894,13895,13896,13897,13898,13899,13900,13901,13902,13903, #13904
|
||||
13904,13905,13906,13907,13908,13909,13910,13911,13912,13913,13914,13915,13916,13917,13918,13919, #13920
|
||||
13920,13921,13922,13923,13924,13925,13926,13927,13928,13929,13930,13931,13932,13933,13934,13935, #13936
|
||||
13936,13937,13938,13939,13940,13941,13942,13943,13944,13945,13946,13947,13948,13949,13950,13951, #13952
|
||||
13952,13953,13954,13955,13956,13957,13958,13959,13960,13961,13962,13963,13964,13965,13966,13967, #13968
|
||||
13968,13969,13970,13971,13972) #13973
|
||||
|
||||
# flake8: noqa
|
||||
|
|
@ -0,0 +1,42 @@
|
|||
######################## BEGIN LICENSE BLOCK ########################
|
||||
# The Original Code is Mozilla Communicator client code.
|
||||
#
|
||||
# The Initial Developer of the Original Code is
|
||||
# Netscape Communications Corporation.
|
||||
# Portions created by the Initial Developer are Copyright (C) 1998
|
||||
# the Initial Developer. All Rights Reserved.
|
||||
#
|
||||
# Contributor(s):
|
||||
# Mark Pilgrim - port to Python
|
||||
#
|
||||
# This library is free software; you can redistribute it and/or
|
||||
# modify it under the terms of the GNU Lesser General Public
|
||||
# License as published by the Free Software Foundation; either
|
||||
# version 2.1 of the License, or (at your option) any later version.
|
||||
#
|
||||
# This library is distributed in the hope that it will be useful,
|
||||
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
||||
# Lesser General Public License for more details.
|
||||
#
|
||||
# You should have received a copy of the GNU Lesser General Public
|
||||
# License along with this library; if not, write to the Free Software
|
||||
# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
|
||||
# 02110-1301 USA
|
||||
######################### END LICENSE BLOCK #########################
|
||||
|
||||
from .mbcharsetprober import MultiByteCharSetProber
|
||||
from .codingstatemachine import CodingStateMachine
|
||||
from .chardistribution import Big5DistributionAnalysis
|
||||
from .mbcssm import Big5SMModel
|
||||
|
||||
|
||||
class Big5Prober(MultiByteCharSetProber):
|
||||
def __init__(self):
|
||||
MultiByteCharSetProber.__init__(self)
|
||||
self._mCodingSM = CodingStateMachine(Big5SMModel)
|
||||
self._mDistributionAnalyzer = Big5DistributionAnalysis()
|
||||
self.reset()
|
||||
|
||||
def get_charset_name(self):
|
||||
return "Big5"
|
||||
|
|
@ -0,0 +1,46 @@
|
|||
#!/usr/bin/env python
|
||||
"""
|
||||
Script which takes one or more file paths and reports on their detected
|
||||
encodings
|
||||
|
||||
Example::
|
||||
|
||||
% chardetect somefile someotherfile
|
||||
somefile: windows-1252 with confidence 0.5
|
||||
someotherfile: ascii with confidence 1.0
|
||||
|
||||
If no paths are provided, it takes its input from stdin.
|
||||
|
||||
"""
|
||||
from io import open
|
||||
from sys import argv, stdin
|
||||
|
||||
from chardet.universaldetector import UniversalDetector
|
||||
|
||||
|
||||
def description_of(file, name='stdin'):
|
||||
"""Return a string describing the probable encoding of a file."""
|
||||
u = UniversalDetector()
|
||||
for line in file:
|
||||
u.feed(line)
|
||||
u.close()
|
||||
result = u.result
|
||||
if result['encoding']:
|
||||
return '%s: %s with confidence %s' % (name,
|
||||
result['encoding'],
|
||||
result['confidence'])
|
||||
else:
|
||||
return '%s: no result' % name
|
||||
|
||||
|
||||
def main():
|
||||
if len(argv) <= 1:
|
||||
print(description_of(stdin))
|
||||
else:
|
||||
for path in argv[1:]:
|
||||
with open(path, 'rb') as f:
|
||||
print(description_of(f, path))
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
main()
|
||||
|
|
@ -0,0 +1,231 @@
|
|||
######################## BEGIN LICENSE BLOCK ########################
|
||||
# The Original Code is Mozilla Communicator client code.
|
||||
#
|
||||
# The Initial Developer of the Original Code is
|
||||
# Netscape Communications Corporation.
|
||||
# Portions created by the Initial Developer are Copyright (C) 1998
|
||||
# the Initial Developer. All Rights Reserved.
|
||||
#
|
||||
# Contributor(s):
|
||||
# Mark Pilgrim - port to Python
|
||||
#
|
||||
# This library is free software; you can redistribute it and/or
|
||||
# modify it under the terms of the GNU Lesser General Public
|
||||
# License as published by the Free Software Foundation; either
|
||||
# version 2.1 of the License, or (at your option) any later version.
|
||||
#
|
||||
# This library is distributed in the hope that it will be useful,
|
||||
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
||||
# Lesser General Public License for more details.
|
||||
#
|
||||
# You should have received a copy of the GNU Lesser General Public
|
||||
# License along with this library; if not, write to the Free Software
|
||||
# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
|
||||
# 02110-1301 USA
|
||||
######################### END LICENSE BLOCK #########################
|
||||
|
||||
from .euctwfreq import (EUCTWCharToFreqOrder, EUCTW_TABLE_SIZE,
|
||||
EUCTW_TYPICAL_DISTRIBUTION_RATIO)
|
||||
from .euckrfreq import (EUCKRCharToFreqOrder, EUCKR_TABLE_SIZE,
|
||||
EUCKR_TYPICAL_DISTRIBUTION_RATIO)
|
||||
from .gb2312freq import (GB2312CharToFreqOrder, GB2312_TABLE_SIZE,
|
||||
GB2312_TYPICAL_DISTRIBUTION_RATIO)
|
||||
from .big5freq import (Big5CharToFreqOrder, BIG5_TABLE_SIZE,
|
||||
BIG5_TYPICAL_DISTRIBUTION_RATIO)
|
||||
from .jisfreq import (JISCharToFreqOrder, JIS_TABLE_SIZE,
|
||||
JIS_TYPICAL_DISTRIBUTION_RATIO)
|
||||
from .compat import wrap_ord
|
||||
|
||||
ENOUGH_DATA_THRESHOLD = 1024
|
||||
SURE_YES = 0.99
|
||||
SURE_NO = 0.01
|
||||
MINIMUM_DATA_THRESHOLD = 3
|
||||
|
||||
|
||||
class CharDistributionAnalysis:
|
||||
def __init__(self):
|
||||
# Mapping table to get frequency order from char order (get from
|
||||
# GetOrder())
|
||||
self._mCharToFreqOrder = None
|
||||
self._mTableSize = None # Size of above table
|
||||
# This is a constant value which varies from language to language,
|
||||
# used in calculating confidence. See
|
||||
# http://www.mozilla.org/projects/intl/UniversalCharsetDetection.html
|
||||
# for further detail.
|
||||
self._mTypicalDistributionRatio = None
|
||||
self.reset()
|
||||
|
||||
def reset(self):
|
||||
"""reset analyser, clear any state"""
|
||||
# If this flag is set to True, detection is done and conclusion has
|
||||
# been made
|
||||
self._mDone = False
|
||||
self._mTotalChars = 0 # Total characters encountered
|
||||
# The number of characters whose frequency order is less than 512
|
||||
self._mFreqChars = 0
|
||||
|
||||
def feed(self, aBuf, aCharLen):
|
||||
"""feed a character with known length"""
|
||||
if aCharLen == 2:
|
||||
# we only care about 2-bytes character in our distribution analysis
|
||||
order = self.get_order(aBuf)
|
||||
else:
|
||||
order = -1
|
||||
if order >= 0:
|
||||
self._mTotalChars += 1
|
||||
# order is valid
|
||||
if order < self._mTableSize:
|
||||
if 512 > self._mCharToFreqOrder[order]:
|
||||
self._mFreqChars += 1
|
||||
|
||||
def get_confidence(self):
|
||||
"""return confidence based on existing data"""
|
||||
# if we didn't receive any character in our consideration range,
|
||||
# return negative answer
|
||||
if self._mTotalChars <= 0 or self._mFreqChars <= MINIMUM_DATA_THRESHOLD:
|
||||
return SURE_NO
|
||||
|
||||
if self._mTotalChars != self._mFreqChars:
|
||||
r = (self._mFreqChars / ((self._mTotalChars - self._mFreqChars)
|
||||
* self._mTypicalDistributionRatio))
|
||||
if r < SURE_YES:
|
||||
return r
|
||||
|
||||
# normalize confidence (we don't want to be 100% sure)
|
||||
return SURE_YES
|
||||
|
||||
def got_enough_data(self):
|
||||
# It is not necessary to receive all data to draw conclusion.
|
||||
# For charset detection, certain amount of data is enough
|
||||
return self._mTotalChars > ENOUGH_DATA_THRESHOLD
|
||||
|
||||
def get_order(self, aBuf):
|
||||
# We do not handle characters based on the original encoding string,
|
||||
# but convert this encoding string to a number, here called order.
|
||||
# This allows multiple encodings of a language to share one frequency
|
||||
# table.
|
||||
return -1
|
||||
|
||||
|
||||
class EUCTWDistributionAnalysis(CharDistributionAnalysis):
|
||||
def __init__(self):
|
||||
CharDistributionAnalysis.__init__(self)
|
||||
self._mCharToFreqOrder = EUCTWCharToFreqOrder
|
||||
self._mTableSize = EUCTW_TABLE_SIZE
|
||||
self._mTypicalDistributionRatio = EUCTW_TYPICAL_DISTRIBUTION_RATIO
|
||||
|
||||
def get_order(self, aBuf):
|
||||
# for euc-TW encoding, we are interested
|
||||
# first byte range: 0xc4 -- 0xfe
|
||||
# second byte range: 0xa1 -- 0xfe
|
||||
# no validation needed here. State machine has done that
|
||||
first_char = wrap_ord(aBuf[0])
|
||||
if first_char >= 0xC4:
|
||||
return 94 * (first_char - 0xC4) + wrap_ord(aBuf[1]) - 0xA1
|
||||
else:
|
||||
return -1
|
||||
|
||||
|
||||
class EUCKRDistributionAnalysis(CharDistributionAnalysis):
|
||||
def __init__(self):
|
||||
CharDistributionAnalysis.__init__(self)
|
||||
self._mCharToFreqOrder = EUCKRCharToFreqOrder
|
||||
self._mTableSize = EUCKR_TABLE_SIZE
|
||||
self._mTypicalDistributionRatio = EUCKR_TYPICAL_DISTRIBUTION_RATIO
|
||||
|
||||
def get_order(self, aBuf):
|
||||
# for euc-KR encoding, we are interested
|
||||
# first byte range: 0xb0 -- 0xfe
|
||||
# second byte range: 0xa1 -- 0xfe
|
||||
# no validation needed here. State machine has done that
|
||||
first_char = wrap_ord(aBuf[0])
|
||||
if first_char >= 0xB0:
|
||||
return 94 * (first_char - 0xB0) + wrap_ord(aBuf[1]) - 0xA1
|
||||
else:
|
||||
return -1
|
||||
|
||||
|
||||
class GB2312DistributionAnalysis(CharDistributionAnalysis):
|
||||
def __init__(self):
|
||||
CharDistributionAnalysis.__init__(self)
|
||||
self._mCharToFreqOrder = GB2312CharToFreqOrder
|
||||
self._mTableSize = GB2312_TABLE_SIZE
|
||||
self._mTypicalDistributionRatio = GB2312_TYPICAL_DISTRIBUTION_RATIO
|
||||
|
||||
def get_order(self, aBuf):
|
||||
# for GB2312 encoding, we are interested
|
||||
# first byte range: 0xb0 -- 0xfe
|
||||
# second byte range: 0xa1 -- 0xfe
|
||||
# no validation needed here. State machine has done that
|
||||
first_char, second_char = wrap_ord(aBuf[0]), wrap_ord(aBuf[1])
|
||||
if (first_char >= 0xB0) and (second_char >= 0xA1):
|
||||
return 94 * (first_char - 0xB0) + second_char - 0xA1
|
||||
else:
|
||||
return -1
|
||||
|
||||
|
||||
class Big5DistributionAnalysis(CharDistributionAnalysis):
|
||||
def __init__(self):
|
||||
CharDistributionAnalysis.__init__(self)
|
||||
self._mCharToFreqOrder = Big5CharToFreqOrder
|
||||
self._mTableSize = BIG5_TABLE_SIZE
|
||||
self._mTypicalDistributionRatio = BIG5_TYPICAL_DISTRIBUTION_RATIO
|
||||
|
||||
def get_order(self, aBuf):
|
||||
# for big5 encoding, we are interested
|
||||
# first byte range: 0xa4 -- 0xfe
|
||||
# second byte range: 0x40 -- 0x7e , 0xa1 -- 0xfe
|
||||
# no validation needed here. State machine has done that
|
||||
first_char, second_char = wrap_ord(aBuf[0]), wrap_ord(aBuf[1])
|
||||
if first_char >= 0xA4:
|
||||
if second_char >= 0xA1:
|
||||
return 157 * (first_char - 0xA4) + second_char - 0xA1 + 63
|
||||
else:
|
||||
return 157 * (first_char - 0xA4) + second_char - 0x40
|
||||
else:
|
||||
return -1
|
||||
|
||||
|
||||
class SJISDistributionAnalysis(CharDistributionAnalysis):
|
||||
def __init__(self):
|
||||
CharDistributionAnalysis.__init__(self)
|
||||
self._mCharToFreqOrder = JISCharToFreqOrder
|
||||
self._mTableSize = JIS_TABLE_SIZE
|
||||
self._mTypicalDistributionRatio = JIS_TYPICAL_DISTRIBUTION_RATIO
|
||||
|
||||
def get_order(self, aBuf):
|
||||
# for sjis encoding, we are interested
|
||||
# first byte range: 0x81 -- 0x9f , 0xe0 -- 0xfe
|
||||
# second byte range: 0x40 -- 0x7e, 0x81 -- oxfe
|
||||
# no validation needed here. State machine has done that
|
||||
first_char, second_char = wrap_ord(aBuf[0]), wrap_ord(aBuf[1])
|
||||
if (first_char >= 0x81) and (first_char <= 0x9F):
|
||||
order = 188 * (first_char - 0x81)
|
||||
elif (first_char >= 0xE0) and (first_char <= 0xEF):
|
||||
order = 188 * (first_char - 0xE0 + 31)
|
||||
else:
|
||||
return -1
|
||||
order = order + second_char - 0x40
|
||||
if second_char > 0x7F:
|
||||
order = -1
|
||||
return order
|
||||
|
||||
|
||||
class EUCJPDistributionAnalysis(CharDistributionAnalysis):
|
||||
def __init__(self):
|
||||
CharDistributionAnalysis.__init__(self)
|
||||
self._mCharToFreqOrder = JISCharToFreqOrder
|
||||
self._mTableSize = JIS_TABLE_SIZE
|
||||
self._mTypicalDistributionRatio = JIS_TYPICAL_DISTRIBUTION_RATIO
|
||||
|
||||
def get_order(self, aBuf):
|
||||
# for euc-JP encoding, we are interested
|
||||
# first byte range: 0xa0 -- 0xfe
|
||||
# second byte range: 0xa1 -- 0xfe
|
||||
# no validation needed here. State machine has done that
|
||||
char = wrap_ord(aBuf[0])
|
||||
if char >= 0xA0:
|
||||
return 94 * (char - 0xA1) + wrap_ord(aBuf[1]) - 0xa1
|
||||
else:
|
||||
return -1
|
||||
|
|
@ -0,0 +1,106 @@
|
|||
######################## BEGIN LICENSE BLOCK ########################
|
||||
# The Original Code is Mozilla Communicator client code.
|
||||
#
|
||||
# The Initial Developer of the Original Code is
|
||||
# Netscape Communications Corporation.
|
||||
# Portions created by the Initial Developer are Copyright (C) 1998
|
||||
# the Initial Developer. All Rights Reserved.
|
||||
#
|
||||
# Contributor(s):
|
||||
# Mark Pilgrim - port to Python
|
||||
#
|
||||
# This library is free software; you can redistribute it and/or
|
||||
# modify it under the terms of the GNU Lesser General Public
|
||||
# License as published by the Free Software Foundation; either
|
||||
# version 2.1 of the License, or (at your option) any later version.
|
||||
#
|
||||
# This library is distributed in the hope that it will be useful,
|
||||
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
||||
# Lesser General Public License for more details.
|
||||
#
|
||||
# You should have received a copy of the GNU Lesser General Public
|
||||
# License along with this library; if not, write to the Free Software
|
||||
# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
|
||||
# 02110-1301 USA
|
||||
######################### END LICENSE BLOCK #########################
|
||||
|
||||
from . import constants
|
||||
import sys
|
||||
from .charsetprober import CharSetProber
|
||||
|
||||
|
||||
class CharSetGroupProber(CharSetProber):
|
||||
def __init__(self):
|
||||
CharSetProber.__init__(self)
|
||||
self._mActiveNum = 0
|
||||
self._mProbers = []
|
||||
self._mBestGuessProber = None
|
||||
|
||||
def reset(self):
|
||||
CharSetProber.reset(self)
|
||||
self._mActiveNum = 0
|
||||
for prober in self._mProbers:
|
||||
if prober:
|
||||
prober.reset()
|
||||
prober.active = True
|
||||
self._mActiveNum += 1
|
||||
self._mBestGuessProber = None
|
||||
|
||||
def get_charset_name(self):
|
||||
if not self._mBestGuessProber:
|
||||
self.get_confidence()
|
||||
if not self._mBestGuessProber:
|
||||
return None
|
||||
# self._mBestGuessProber = self._mProbers[0]
|
||||
return self._mBestGuessProber.get_charset_name()
|
||||
|
||||
def feed(self, aBuf):
|
||||
for prober in self._mProbers:
|
||||
if not prober:
|
||||
continue
|
||||
if not prober.active:
|
||||
continue
|
||||
st = prober.feed(aBuf)
|
||||
if not st:
|
||||
continue
|
||||
if st == constants.eFoundIt:
|
||||
self._mBestGuessProber = prober
|
||||
return self.get_state()
|
||||
elif st == constants.eNotMe:
|
||||
prober.active = False
|
||||
self._mActiveNum -= 1
|
||||
if self._mActiveNum <= 0:
|
||||
self._mState = constants.eNotMe
|
||||
return self.get_state()
|
||||
return self.get_state()
|
||||
|
||||
def get_confidence(self):
|
||||
st = self.get_state()
|
||||
if st == constants.eFoundIt:
|
||||
return 0.99
|
||||
elif st == constants.eNotMe:
|
||||
return 0.01
|
||||
bestConf = 0.0
|
||||
self._mBestGuessProber = None
|
||||
for prober in self._mProbers:
|
||||
if not prober:
|
||||
continue
|
||||
if not prober.active:
|
||||
if constants._debug:
|
||||
sys.stderr.write(prober.get_charset_name()
|
||||
+ ' not active\n')
|
||||
continue
|
||||
cf = prober.get_confidence()
|
||||
if constants._debug:
|
||||
sys.stderr.write('%s confidence = %s\n' %
|
||||
(prober.get_charset_name(), cf))
|
||||
if bestConf < cf:
|
||||
bestConf = cf
|
||||
self._mBestGuessProber = prober
|
||||
if not self._mBestGuessProber:
|
||||
return 0.0
|
||||
return bestConf
|
||||
# else:
|
||||
# self._mBestGuessProber = self._mProbers[0]
|
||||
# return self._mBestGuessProber.get_confidence()
|
||||
|
|
@ -0,0 +1,62 @@
|
|||
######################## BEGIN LICENSE BLOCK ########################
|
||||
# The Original Code is Mozilla Universal charset detector code.
|
||||
#
|
||||
# The Initial Developer of the Original Code is
|
||||
# Netscape Communications Corporation.
|
||||
# Portions created by the Initial Developer are Copyright (C) 2001
|
||||
# the Initial Developer. All Rights Reserved.
|
||||
#
|
||||
# Contributor(s):
|
||||
# Mark Pilgrim - port to Python
|
||||
# Shy Shalom - original C code
|
||||
#
|
||||
# This library is free software; you can redistribute it and/or
|
||||
# modify it under the terms of the GNU Lesser General Public
|
||||
# License as published by the Free Software Foundation; either
|
||||
# version 2.1 of the License, or (at your option) any later version.
|
||||
#
|
||||
# This library is distributed in the hope that it will be useful,
|
||||
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
||||
# Lesser General Public License for more details.
|
||||
#
|
||||
# You should have received a copy of the GNU Lesser General Public
|
||||
# License along with this library; if not, write to the Free Software
|
||||
# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
|
||||
# 02110-1301 USA
|
||||
######################### END LICENSE BLOCK #########################
|
||||
|
||||
from . import constants
|
||||
import re
|
||||
|
||||
|
||||
class CharSetProber:
|
||||
def __init__(self):
|
||||
pass
|
||||
|
||||
def reset(self):
|
||||
self._mState = constants.eDetecting
|
||||
|
||||
def get_charset_name(self):
|
||||
return None
|
||||
|
||||
def feed(self, aBuf):
|
||||
pass
|
||||
|
||||
def get_state(self):
|
||||
return self._mState
|
||||
|
||||
def get_confidence(self):
|
||||
return 0.0
|
||||
|
||||
def filter_high_bit_only(self, aBuf):
|
||||
aBuf = re.sub(b'([\x00-\x7F])+', b' ', aBuf)
|
||||
return aBuf
|
||||
|
||||
def filter_without_english_letters(self, aBuf):
|
||||
aBuf = re.sub(b'([A-Za-z])+', b' ', aBuf)
|
||||
return aBuf
|
||||
|
||||
def filter_with_english_letters(self, aBuf):
|
||||
# TODO
|
||||
return aBuf
|
||||
|
|
@ -0,0 +1,61 @@
|
|||
######################## BEGIN LICENSE BLOCK ########################
|
||||
# The Original Code is mozilla.org code.
|
||||
#
|
||||
# The Initial Developer of the Original Code is
|
||||
# Netscape Communications Corporation.
|
||||
# Portions created by the Initial Developer are Copyright (C) 1998
|
||||
# the Initial Developer. All Rights Reserved.
|
||||
#
|
||||
# Contributor(s):
|
||||
# Mark Pilgrim - port to Python
|
||||
#
|
||||
# This library is free software; you can redistribute it and/or
|
||||
# modify it under the terms of the GNU Lesser General Public
|
||||
# License as published by the Free Software Foundation; either
|
||||
# version 2.1 of the License, or (at your option) any later version.
|
||||
#
|
||||
# This library is distributed in the hope that it will be useful,
|
||||
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
||||
# Lesser General Public License for more details.
|
||||
#
|
||||
# You should have received a copy of the GNU Lesser General Public
|
||||
# License along with this library; if not, write to the Free Software
|
||||
# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
|
||||
# 02110-1301 USA
|
||||
######################### END LICENSE BLOCK #########################
|
||||
|
||||
from .constants import eStart
|
||||
from .compat import wrap_ord
|
||||
|
||||
|
||||
class CodingStateMachine:
|
||||
def __init__(self, sm):
|
||||
self._mModel = sm
|
||||
self._mCurrentBytePos = 0
|
||||
self._mCurrentCharLen = 0
|
||||
self.reset()
|
||||
|
||||
def reset(self):
|
||||
self._mCurrentState = eStart
|
||||
|
||||
def next_state(self, c):
|
||||
# for each byte we get its class
|
||||
# if it is first byte, we also get byte length
|
||||
# PY3K: aBuf is a byte stream, so c is an int, not a byte
|
||||
byteCls = self._mModel['classTable'][wrap_ord(c)]
|
||||
if self._mCurrentState == eStart:
|
||||
self._mCurrentBytePos = 0
|
||||
self._mCurrentCharLen = self._mModel['charLenTable'][byteCls]
|
||||
# from byte's class and stateTable, we get its next state
|
||||
curr_state = (self._mCurrentState * self._mModel['classFactor']
|
||||
+ byteCls)
|
||||
self._mCurrentState = self._mModel['stateTable'][curr_state]
|
||||
self._mCurrentBytePos += 1
|
||||
return self._mCurrentState
|
||||
|
||||
def get_current_charlen(self):
|
||||
return self._mCurrentCharLen
|
||||
|
||||
def get_coding_state_machine(self):
|
||||
return self._mModel['name']
|
||||
|
|
@ -0,0 +1,34 @@
|
|||
######################## BEGIN LICENSE BLOCK ########################
|
||||
# Contributor(s):
|
||||
# Ian Cordasco - port to Python
|
||||
#
|
||||
# This library is free software; you can redistribute it and/or
|
||||
# modify it under the terms of the GNU Lesser General Public
|
||||
# License as published by the Free Software Foundation; either
|
||||
# version 2.1 of the License, or (at your option) any later version.
|
||||
#
|
||||
# This library is distributed in the hope that it will be useful,
|
||||
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
||||
# Lesser General Public License for more details.
|
||||
#
|
||||
# You should have received a copy of the GNU Lesser General Public
|
||||
# License along with this library; if not, write to the Free Software
|
||||
# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
|
||||
# 02110-1301 USA
|
||||
######################### END LICENSE BLOCK #########################
|
||||
|
||||
import sys
|
||||
|
||||
|
||||
if sys.version_info < (3, 0):
|
||||
base_str = (str, unicode)
|
||||
else:
|
||||
base_str = (bytes, str)
|
||||
|
||||
|
||||
def wrap_ord(a):
|
||||
if sys.version_info < (3, 0) and isinstance(a, base_str):
|
||||
return ord(a)
|
||||
else:
|
||||
return a
|
||||
|
|
@ -0,0 +1,39 @@
|
|||
######################## BEGIN LICENSE BLOCK ########################
|
||||
# The Original Code is Mozilla Universal charset detector code.
|
||||
#
|
||||
# The Initial Developer of the Original Code is
|
||||
# Netscape Communications Corporation.
|
||||
# Portions created by the Initial Developer are Copyright (C) 2001
|
||||
# the Initial Developer. All Rights Reserved.
|
||||
#
|
||||
# Contributor(s):
|
||||
# Mark Pilgrim - port to Python
|
||||
# Shy Shalom - original C code
|
||||
#
|
||||
# This library is free software; you can redistribute it and/or
|
||||
# modify it under the terms of the GNU Lesser General Public
|
||||
# License as published by the Free Software Foundation; either
|
||||
# version 2.1 of the License, or (at your option) any later version.
|
||||
#
|
||||
# This library is distributed in the hope that it will be useful,
|
||||
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
||||
# Lesser General Public License for more details.
|
||||
#
|
||||
# You should have received a copy of the GNU Lesser General Public
|
||||
# License along with this library; if not, write to the Free Software
|
||||
# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
|
||||
# 02110-1301 USA
|
||||
######################### END LICENSE BLOCK #########################
|
||||
|
||||
_debug = 0
|
||||
|
||||
eDetecting = 0
|
||||
eFoundIt = 1
|
||||
eNotMe = 2
|
||||
|
||||
eStart = 0
|
||||
eError = 1
|
||||
eItsMe = 2
|
||||
|
||||
SHORTCUT_THRESHOLD = 0.95
|
||||
|
|
@ -0,0 +1,44 @@
|
|||
######################## BEGIN LICENSE BLOCK ########################
|
||||
# The Original Code is mozilla.org code.
|
||||
#
|
||||
# The Initial Developer of the Original Code is
|
||||
# Netscape Communications Corporation.
|
||||
# Portions created by the Initial Developer are Copyright (C) 1998
|
||||
# the Initial Developer. All Rights Reserved.
|
||||
#
|
||||
# Contributor(s):
|
||||
# Mark Pilgrim - port to Python
|
||||
#
|
||||
# This library is free software; you can redistribute it and/or
|
||||
# modify it under the terms of the GNU Lesser General Public
|
||||
# License as published by the Free Software Foundation; either
|
||||
# version 2.1 of the License, or (at your option) any later version.
|
||||
#
|
||||
# This library is distributed in the hope that it will be useful,
|
||||
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
||||
# Lesser General Public License for more details.
|
||||
#
|
||||
# You should have received a copy of the GNU Lesser General Public
|
||||
# License along with this library; if not, write to the Free Software
|
||||
# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
|
||||
# 02110-1301 USA
|
||||
######################### END LICENSE BLOCK #########################
|
||||
|
||||
from .mbcharsetprober import MultiByteCharSetProber
|
||||
from .codingstatemachine import CodingStateMachine
|
||||
from .chardistribution import EUCKRDistributionAnalysis
|
||||
from .mbcssm import CP949SMModel
|
||||
|
||||
|
||||
class CP949Prober(MultiByteCharSetProber):
|
||||
def __init__(self):
|
||||
MultiByteCharSetProber.__init__(self)
|
||||
self._mCodingSM = CodingStateMachine(CP949SMModel)
|
||||
# NOTE: CP949 is a superset of EUC-KR, so the distribution should be
|
||||
# not different.
|
||||
self._mDistributionAnalyzer = EUCKRDistributionAnalysis()
|
||||
self.reset()
|
||||
|
||||
def get_charset_name(self):
|
||||
return "CP949"
|
||||
|
|
@ -0,0 +1,86 @@
|
|||
######################## BEGIN LICENSE BLOCK ########################
|
||||
# The Original Code is mozilla.org code.
|
||||
#
|
||||
# The Initial Developer of the Original Code is
|
||||
# Netscape Communications Corporation.
|
||||
# Portions created by the Initial Developer are Copyright (C) 1998
|
||||
# the Initial Developer. All Rights Reserved.
|
||||
#
|
||||
# Contributor(s):
|
||||
# Mark Pilgrim - port to Python
|
||||
#
|
||||
# This library is free software; you can redistribute it and/or
|
||||
# modify it under the terms of the GNU Lesser General Public
|
||||
# License as published by the Free Software Foundation; either
|
||||
# version 2.1 of the License, or (at your option) any later version.
|
||||
#
|
||||
# This library is distributed in the hope that it will be useful,
|
||||
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
||||
# Lesser General Public License for more details.
|
||||
#
|
||||
# You should have received a copy of the GNU Lesser General Public
|
||||
# License along with this library; if not, write to the Free Software
|
||||
# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
|
||||
# 02110-1301 USA
|
||||
######################### END LICENSE BLOCK #########################
|
||||
|
||||
from . import constants
|
||||
from .escsm import (HZSMModel, ISO2022CNSMModel, ISO2022JPSMModel,
|
||||
ISO2022KRSMModel)
|
||||
from .charsetprober import CharSetProber
|
||||
from .codingstatemachine import CodingStateMachine
|
||||
from .compat import wrap_ord
|
||||
|
||||
|
||||
class EscCharSetProber(CharSetProber):
|
||||
def __init__(self):
|
||||
CharSetProber.__init__(self)
|
||||
self._mCodingSM = [
|
||||
CodingStateMachine(HZSMModel),
|
||||
CodingStateMachine(ISO2022CNSMModel),
|
||||
CodingStateMachine(ISO2022JPSMModel),
|
||||
CodingStateMachine(ISO2022KRSMModel)
|
||||
]
|
||||
self.reset()
|
||||
|
||||
def reset(self):
|
||||
CharSetProber.reset(self)
|
||||
for codingSM in self._mCodingSM:
|
||||
if not codingSM:
|
||||
continue
|
||||
codingSM.active = True
|
||||
codingSM.reset()
|
||||
self._mActiveSM = len(self._mCodingSM)
|
||||
self._mDetectedCharset = None
|
||||
|
||||
def get_charset_name(self):
|
||||
return self._mDetectedCharset
|
||||
|
||||
def get_confidence(self):
|
||||
if self._mDetectedCharset:
|
||||
return 0.99
|
||||
else:
|
||||
return 0.00
|
||||
|
||||
def feed(self, aBuf):
|
||||
for c in aBuf:
|
||||
# PY3K: aBuf is a byte array, so c is an int, not a byte
|
||||
for codingSM in self._mCodingSM:
|
||||
if not codingSM:
|
||||
continue
|
||||
if not codingSM.active:
|
||||
continue
|
||||
codingState = codingSM.next_state(wrap_ord(c))
|
||||
if codingState == constants.eError:
|
||||
codingSM.active = False
|
||||
self._mActiveSM -= 1
|
||||
if self._mActiveSM <= 0:
|
||||
self._mState = constants.eNotMe
|
||||
return self.get_state()
|
||||
elif codingState == constants.eItsMe:
|
||||
self._mState = constants.eFoundIt
|
||||
self._mDetectedCharset = codingSM.get_coding_state_machine() # nopep8
|
||||
return self.get_state()
|
||||
|
||||
return self.get_state()
|
||||
|
|
@ -0,0 +1,242 @@
|
|||
######################## BEGIN LICENSE BLOCK ########################
|
||||
# The Original Code is mozilla.org code.
|
||||
#
|
||||
# The Initial Developer of the Original Code is
|
||||
# Netscape Communications Corporation.
|
||||
# Portions created by the Initial Developer are Copyright (C) 1998
|
||||
# the Initial Developer. All Rights Reserved.
|
||||
#
|
||||
# Contributor(s):
|
||||
# Mark Pilgrim - port to Python
|
||||
#
|
||||
# This library is free software; you can redistribute it and/or
|
||||
# modify it under the terms of the GNU Lesser General Public
|
||||
# License as published by the Free Software Foundation; either
|
||||
# version 2.1 of the License, or (at your option) any later version.
|
||||
#
|
||||
# This library is distributed in the hope that it will be useful,
|
||||
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
||||
# Lesser General Public License for more details.
|
||||
#
|
||||
# You should have received a copy of the GNU Lesser General Public
|
||||
# License along with this library; if not, write to the Free Software
|
||||
# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
|
||||
# 02110-1301 USA
|
||||
######################### END LICENSE BLOCK #########################
|
||||
|
||||
from .constants import eStart, eError, eItsMe
|
||||
|
||||
HZ_cls = (
|
||||
1,0,0,0,0,0,0,0, # 00 - 07
|
||||
0,0,0,0,0,0,0,0, # 08 - 0f
|
||||
0,0,0,0,0,0,0,0, # 10 - 17
|
||||
0,0,0,1,0,0,0,0, # 18 - 1f
|
||||
0,0,0,0,0,0,0,0, # 20 - 27
|
||||
0,0,0,0,0,0,0,0, # 28 - 2f
|
||||
0,0,0,0,0,0,0,0, # 30 - 37
|
||||
0,0,0,0,0,0,0,0, # 38 - 3f
|
||||
0,0,0,0,0,0,0,0, # 40 - 47
|
||||
0,0,0,0,0,0,0,0, # 48 - 4f
|
||||
0,0,0,0,0,0,0,0, # 50 - 57
|
||||
0,0,0,0,0,0,0,0, # 58 - 5f
|
||||
0,0,0,0,0,0,0,0, # 60 - 67
|
||||
0,0,0,0,0,0,0,0, # 68 - 6f
|
||||
0,0,0,0,0,0,0,0, # 70 - 77
|
||||
0,0,0,4,0,5,2,0, # 78 - 7f
|
||||
1,1,1,1,1,1,1,1, # 80 - 87
|
||||
1,1,1,1,1,1,1,1, # 88 - 8f
|
||||
1,1,1,1,1,1,1,1, # 90 - 97
|
||||
1,1,1,1,1,1,1,1, # 98 - 9f
|
||||
1,1,1,1,1,1,1,1, # a0 - a7
|
||||
1,1,1,1,1,1,1,1, # a8 - af
|
||||
1,1,1,1,1,1,1,1, # b0 - b7
|
||||
1,1,1,1,1,1,1,1, # b8 - bf
|
||||
1,1,1,1,1,1,1,1, # c0 - c7
|
||||
1,1,1,1,1,1,1,1, # c8 - cf
|
||||
1,1,1,1,1,1,1,1, # d0 - d7
|
||||
1,1,1,1,1,1,1,1, # d8 - df
|
||||
1,1,1,1,1,1,1,1, # e0 - e7
|
||||
1,1,1,1,1,1,1,1, # e8 - ef
|
||||
1,1,1,1,1,1,1,1, # f0 - f7
|
||||
1,1,1,1,1,1,1,1, # f8 - ff
|
||||
)
|
||||
|
||||
HZ_st = (
|
||||
eStart,eError, 3,eStart,eStart,eStart,eError,eError,# 00-07
|
||||
eError,eError,eError,eError,eItsMe,eItsMe,eItsMe,eItsMe,# 08-0f
|
||||
eItsMe,eItsMe,eError,eError,eStart,eStart, 4,eError,# 10-17
|
||||
5,eError, 6,eError, 5, 5, 4,eError,# 18-1f
|
||||
4,eError, 4, 4, 4,eError, 4,eError,# 20-27
|
||||
4,eItsMe,eStart,eStart,eStart,eStart,eStart,eStart,# 28-2f
|
||||
)
|
||||
|
||||
HZCharLenTable = (0, 0, 0, 0, 0, 0)
|
||||
|
||||
HZSMModel = {'classTable': HZ_cls,
|
||||
'classFactor': 6,
|
||||
'stateTable': HZ_st,
|
||||
'charLenTable': HZCharLenTable,
|
||||
'name': "HZ-GB-2312"}
|
||||
|
||||
ISO2022CN_cls = (
|
||||
2,0,0,0,0,0,0,0, # 00 - 07
|
||||
0,0,0,0,0,0,0,0, # 08 - 0f
|
||||
0,0,0,0,0,0,0,0, # 10 - 17
|
||||
0,0,0,1,0,0,0,0, # 18 - 1f
|
||||
0,0,0,0,0,0,0,0, # 20 - 27
|
||||
0,3,0,0,0,0,0,0, # 28 - 2f
|
||||
0,0,0,0,0,0,0,0, # 30 - 37
|
||||
0,0,0,0,0,0,0,0, # 38 - 3f
|
||||
0,0,0,4,0,0,0,0, # 40 - 47
|
||||
0,0,0,0,0,0,0,0, # 48 - 4f
|
||||
0,0,0,0,0,0,0,0, # 50 - 57
|
||||
0,0,0,0,0,0,0,0, # 58 - 5f
|
||||
0,0,0,0,0,0,0,0, # 60 - 67
|
||||
0,0,0,0,0,0,0,0, # 68 - 6f
|
||||
0,0,0,0,0,0,0,0, # 70 - 77
|
||||
0,0,0,0,0,0,0,0, # 78 - 7f
|
||||
2,2,2,2,2,2,2,2, # 80 - 87
|
||||
2,2,2,2,2,2,2,2, # 88 - 8f
|
||||
2,2,2,2,2,2,2,2, # 90 - 97
|
||||
2,2,2,2,2,2,2,2, # 98 - 9f
|
||||
2,2,2,2,2,2,2,2, # a0 - a7
|
||||
2,2,2,2,2,2,2,2, # a8 - af
|
||||
2,2,2,2,2,2,2,2, # b0 - b7
|
||||
2,2,2,2,2,2,2,2, # b8 - bf
|
||||
2,2,2,2,2,2,2,2, # c0 - c7
|
||||
2,2,2,2,2,2,2,2, # c8 - cf
|
||||
2,2,2,2,2,2,2,2, # d0 - d7
|
||||
2,2,2,2,2,2,2,2, # d8 - df
|
||||
2,2,2,2,2,2,2,2, # e0 - e7
|
||||
2,2,2,2,2,2,2,2, # e8 - ef
|
||||
2,2,2,2,2,2,2,2, # f0 - f7
|
||||
2,2,2,2,2,2,2,2, # f8 - ff
|
||||
)
|
||||
|
||||
ISO2022CN_st = (
|
||||
eStart, 3,eError,eStart,eStart,eStart,eStart,eStart,# 00-07
|
||||
eStart,eError,eError,eError,eError,eError,eError,eError,# 08-0f
|
||||
eError,eError,eItsMe,eItsMe,eItsMe,eItsMe,eItsMe,eItsMe,# 10-17
|
||||
eItsMe,eItsMe,eItsMe,eError,eError,eError, 4,eError,# 18-1f
|
||||
eError,eError,eError,eItsMe,eError,eError,eError,eError,# 20-27
|
||||
5, 6,eError,eError,eError,eError,eError,eError,# 28-2f
|
||||
eError,eError,eError,eItsMe,eError,eError,eError,eError,# 30-37
|
||||
eError,eError,eError,eError,eError,eItsMe,eError,eStart,# 38-3f
|
||||
)
|
||||
|
||||
ISO2022CNCharLenTable = (0, 0, 0, 0, 0, 0, 0, 0, 0)
|
||||
|
||||
ISO2022CNSMModel = {'classTable': ISO2022CN_cls,
|
||||
'classFactor': 9,
|
||||
'stateTable': ISO2022CN_st,
|
||||
'charLenTable': ISO2022CNCharLenTable,
|
||||
'name': "ISO-2022-CN"}
|
||||
|
||||
ISO2022JP_cls = (
|
||||
2,0,0,0,0,0,0,0, # 00 - 07
|
||||
0,0,0,0,0,0,2,2, # 08 - 0f
|
||||
0,0,0,0,0,0,0,0, # 10 - 17
|
||||
0,0,0,1,0,0,0,0, # 18 - 1f
|
||||
0,0,0,0,7,0,0,0, # 20 - 27
|
||||
3,0,0,0,0,0,0,0, # 28 - 2f
|
||||
0,0,0,0,0,0,0,0, # 30 - 37
|
||||
0,0,0,0,0,0,0,0, # 38 - 3f
|
||||
6,0,4,0,8,0,0,0, # 40 - 47
|
||||
0,9,5,0,0,0,0,0, # 48 - 4f
|
||||
0,0,0,0,0,0,0,0, # 50 - 57
|
||||
0,0,0,0,0,0,0,0, # 58 - 5f
|
||||
0,0,0,0,0,0,0,0, # 60 - 67
|
||||
0,0,0,0,0,0,0,0, # 68 - 6f
|
||||
0,0,0,0,0,0,0,0, # 70 - 77
|
||||
0,0,0,0,0,0,0,0, # 78 - 7f
|
||||
2,2,2,2,2,2,2,2, # 80 - 87
|
||||
2,2,2,2,2,2,2,2, # 88 - 8f
|
||||
2,2,2,2,2,2,2,2, # 90 - 97
|
||||
2,2,2,2,2,2,2,2, # 98 - 9f
|
||||
2,2,2,2,2,2,2,2, # a0 - a7
|
||||
2,2,2,2,2,2,2,2, # a8 - af
|
||||
2,2,2,2,2,2,2,2, # b0 - b7
|
||||
2,2,2,2,2,2,2,2, # b8 - bf
|
||||
2,2,2,2,2,2,2,2, # c0 - c7
|
||||
2,2,2,2,2,2,2,2, # c8 - cf
|
||||
2,2,2,2,2,2,2,2, # d0 - d7
|
||||
2,2,2,2,2,2,2,2, # d8 - df
|
||||
2,2,2,2,2,2,2,2, # e0 - e7
|
||||
2,2,2,2,2,2,2,2, # e8 - ef
|
||||
2,2,2,2,2,2,2,2, # f0 - f7
|
||||
2,2,2,2,2,2,2,2, # f8 - ff
|
||||
)
|
||||
|
||||
ISO2022JP_st = (
|
||||
eStart, 3,eError,eStart,eStart,eStart,eStart,eStart,# 00-07
|
||||
eStart,eStart,eError,eError,eError,eError,eError,eError,# 08-0f
|
||||
eError,eError,eError,eError,eItsMe,eItsMe,eItsMe,eItsMe,# 10-17
|
||||
eItsMe,eItsMe,eItsMe,eItsMe,eItsMe,eItsMe,eError,eError,# 18-1f
|
||||
eError, 5,eError,eError,eError, 4,eError,eError,# 20-27
|
||||
eError,eError,eError, 6,eItsMe,eError,eItsMe,eError,# 28-2f
|
||||
eError,eError,eError,eError,eError,eError,eItsMe,eItsMe,# 30-37
|
||||
eError,eError,eError,eItsMe,eError,eError,eError,eError,# 38-3f
|
||||
eError,eError,eError,eError,eItsMe,eError,eStart,eStart,# 40-47
|
||||
)
|
||||
|
||||
ISO2022JPCharLenTable = (0, 0, 0, 0, 0, 0, 0, 0, 0, 0)
|
||||
|
||||
ISO2022JPSMModel = {'classTable': ISO2022JP_cls,
|
||||
'classFactor': 10,
|
||||
'stateTable': ISO2022JP_st,
|
||||
'charLenTable': ISO2022JPCharLenTable,
|
||||
'name': "ISO-2022-JP"}
|
||||
|
||||
ISO2022KR_cls = (
|
||||
2,0,0,0,0,0,0,0, # 00 - 07
|
||||
0,0,0,0,0,0,0,0, # 08 - 0f
|
||||
0,0,0,0,0,0,0,0, # 10 - 17
|
||||
0,0,0,1,0,0,0,0, # 18 - 1f
|
||||
0,0,0,0,3,0,0,0, # 20 - 27
|
||||
0,4,0,0,0,0,0,0, # 28 - 2f
|
||||
0,0,0,0,0,0,0,0, # 30 - 37
|
||||
0,0,0,0,0,0,0,0, # 38 - 3f
|
||||
0,0,0,5,0,0,0,0, # 40 - 47
|
||||
0,0,0,0,0,0,0,0, # 48 - 4f
|
||||
0,0,0,0,0,0,0,0, # 50 - 57
|
||||
0,0,0,0,0,0,0,0, # 58 - 5f
|
||||
0,0,0,0,0,0,0,0, # 60 - 67
|
||||
0,0,0,0,0,0,0,0, # 68 - 6f
|
||||
0,0,0,0,0,0,0,0, # 70 - 77
|
||||
0,0,0,0,0,0,0,0, # 78 - 7f
|
||||
2,2,2,2,2,2,2,2, # 80 - 87
|
||||
2,2,2,2,2,2,2,2, # 88 - 8f
|
||||
2,2,2,2,2,2,2,2, # 90 - 97
|
||||
2,2,2,2,2,2,2,2, # 98 - 9f
|
||||
2,2,2,2,2,2,2,2, # a0 - a7
|
||||
2,2,2,2,2,2,2,2, # a8 - af
|
||||
2,2,2,2,2,2,2,2, # b0 - b7
|
||||
2,2,2,2,2,2,2,2, # b8 - bf
|
||||
2,2,2,2,2,2,2,2, # c0 - c7
|
||||
2,2,2,2,2,2,2,2, # c8 - cf
|
||||
2,2,2,2,2,2,2,2, # d0 - d7
|
||||
2,2,2,2,2,2,2,2, # d8 - df
|
||||
2,2,2,2,2,2,2,2, # e0 - e7
|
||||
2,2,2,2,2,2,2,2, # e8 - ef
|
||||
2,2,2,2,2,2,2,2, # f0 - f7
|
||||
2,2,2,2,2,2,2,2, # f8 - ff
|
||||
)
|
||||
|
||||
ISO2022KR_st = (
|
||||
eStart, 3,eError,eStart,eStart,eStart,eError,eError,# 00-07
|
||||
eError,eError,eError,eError,eItsMe,eItsMe,eItsMe,eItsMe,# 08-0f
|
||||
eItsMe,eItsMe,eError,eError,eError, 4,eError,eError,# 10-17
|
||||
eError,eError,eError,eError, 5,eError,eError,eError,# 18-1f
|
||||
eError,eError,eError,eItsMe,eStart,eStart,eStart,eStart,# 20-27
|
||||
)
|
||||
|
||||
ISO2022KRCharLenTable = (0, 0, 0, 0, 0, 0)
|
||||
|
||||
ISO2022KRSMModel = {'classTable': ISO2022KR_cls,
|
||||
'classFactor': 6,
|
||||
'stateTable': ISO2022KR_st,
|
||||
'charLenTable': ISO2022KRCharLenTable,
|
||||
'name': "ISO-2022-KR"}
|
||||
|
||||
# flake8: noqa
|
||||
|
|
@ -0,0 +1,90 @@
|
|||
######################## BEGIN LICENSE BLOCK ########################
|
||||
# The Original Code is mozilla.org code.
|
||||
#
|
||||
# The Initial Developer of the Original Code is
|
||||
# Netscape Communications Corporation.
|
||||
# Portions created by the Initial Developer are Copyright (C) 1998
|
||||
# the Initial Developer. All Rights Reserved.
|
||||
#
|
||||
# Contributor(s):
|
||||
# Mark Pilgrim - port to Python
|
||||
#
|
||||
# This library is free software; you can redistribute it and/or
|
||||
# modify it under the terms of the GNU Lesser General Public
|
||||
# License as published by the Free Software Foundation; either
|
||||
# version 2.1 of the License, or (at your option) any later version.
|
||||
#
|
||||
# This library is distributed in the hope that it will be useful,
|
||||
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
||||
# Lesser General Public License for more details.
|
||||
#
|
||||
# You should have received a copy of the GNU Lesser General Public
|
||||
# License along with this library; if not, write to the Free Software
|
||||
# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
|
||||
# 02110-1301 USA
|
||||
######################### END LICENSE BLOCK #########################
|
||||
|
||||
import sys
|
||||
from . import constants
|
||||
from .mbcharsetprober import MultiByteCharSetProber
|
||||
from .codingstatemachine import CodingStateMachine
|
||||
from .chardistribution import EUCJPDistributionAnalysis
|
||||
from .jpcntx import EUCJPContextAnalysis
|
||||
from .mbcssm import EUCJPSMModel
|
||||
|
||||
|
||||
class EUCJPProber(MultiByteCharSetProber):
|
||||
def __init__(self):
|
||||
MultiByteCharSetProber.__init__(self)
|
||||
self._mCodingSM = CodingStateMachine(EUCJPSMModel)
|
||||
self._mDistributionAnalyzer = EUCJPDistributionAnalysis()
|
||||
self._mContextAnalyzer = EUCJPContextAnalysis()
|
||||
self.reset()
|
||||
|
||||
def reset(self):
|
||||
MultiByteCharSetProber.reset(self)
|
||||
self._mContextAnalyzer.reset()
|
||||
|
||||
def get_charset_name(self):
|
||||
return "EUC-JP"
|
||||
|
||||
def feed(self, aBuf):
|
||||
aLen = len(aBuf)
|
||||
for i in range(0, aLen):
|
||||
# PY3K: aBuf is a byte array, so aBuf[i] is an int, not a byte
|
||||
codingState = self._mCodingSM.next_state(aBuf[i])
|
||||
if codingState == constants.eError:
|
||||
if constants._debug:
|
||||
sys.stderr.write(self.get_charset_name()
|
||||
+ ' prober hit error at byte ' + str(i)
|
||||
+ '\n')
|
||||
self._mState = constants.eNotMe
|
||||
break
|
||||
elif codingState == constants.eItsMe:
|
||||
self._mState = constants.eFoundIt
|
||||
break
|
||||
elif codingState == constants.eStart:
|
||||
charLen = self._mCodingSM.get_current_charlen()
|
||||
if i == 0:
|
||||
self._mLastChar[1] = aBuf[0]
|
||||
self._mContextAnalyzer.feed(self._mLastChar, charLen)
|
||||
self._mDistributionAnalyzer.feed(self._mLastChar, charLen)
|
||||
else:
|
||||
self._mContextAnalyzer.feed(aBuf[i - 1:i + 1], charLen)
|
||||
self._mDistributionAnalyzer.feed(aBuf[i - 1:i + 1],
|
||||
charLen)
|
||||
|
||||
self._mLastChar[0] = aBuf[aLen - 1]
|
||||
|
||||
if self.get_state() == constants.eDetecting:
|
||||
if (self._mContextAnalyzer.got_enough_data() and
|
||||
(self.get_confidence() > constants.SHORTCUT_THRESHOLD)):
|
||||
self._mState = constants.eFoundIt
|
||||
|
||||
return self.get_state()
|
||||
|
||||
def get_confidence(self):
|
||||
contxtCf = self._mContextAnalyzer.get_confidence()
|
||||
distribCf = self._mDistributionAnalyzer.get_confidence()
|
||||
return max(contxtCf, distribCf)
|
||||
|
|
@ -0,0 +1,596 @@
|
|||
######################## BEGIN LICENSE BLOCK ########################
|
||||
# The Original Code is Mozilla Communicator client code.
|
||||
#
|
||||
# The Initial Developer of the Original Code is
|
||||
# Netscape Communications Corporation.
|
||||
# Portions created by the Initial Developer are Copyright (C) 1998
|
||||
# the Initial Developer. All Rights Reserved.
|
||||
#
|
||||
# Contributor(s):
|
||||
# Mark Pilgrim - port to Python
|
||||
#
|
||||
# This library is free software; you can redistribute it and/or
|
||||
# modify it under the terms of the GNU Lesser General Public
|
||||
# License as published by the Free Software Foundation; either
|
||||
# version 2.1 of the License, or (at your option) any later version.
|
||||
#
|
||||
# This library is distributed in the hope that it will be useful,
|
||||
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
||||
# Lesser General Public License for more details.
|
||||
#
|
||||
# You should have received a copy of the GNU Lesser General Public
|
||||
# License along with this library; if not, write to the Free Software
|
||||
# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
|
||||
# 02110-1301 USA
|
||||
######################### END LICENSE BLOCK #########################
|
||||
|
||||
# Sampling from about 20M text materials include literature and computer technology
|
||||
|
||||
# 128 --> 0.79
|
||||
# 256 --> 0.92
|
||||
# 512 --> 0.986
|
||||
# 1024 --> 0.99944
|
||||
# 2048 --> 0.99999
|
||||
#
|
||||
# Idea Distribution Ratio = 0.98653 / (1-0.98653) = 73.24
|
||||
# Random Distribution Ration = 512 / (2350-512) = 0.279.
|
||||
#
|
||||
# Typical Distribution Ratio
|
||||
|
||||
EUCKR_TYPICAL_DISTRIBUTION_RATIO = 6.0
|
||||
|
||||
EUCKR_TABLE_SIZE = 2352
|
||||
|
||||
# Char to FreqOrder table ,
|
||||
EUCKRCharToFreqOrder = ( \
|
||||
13, 130, 120,1396, 481,1719,1720, 328, 609, 212,1721, 707, 400, 299,1722, 87,
|
||||
1397,1723, 104, 536,1117,1203,1724,1267, 685,1268, 508,1725,1726,1727,1728,1398,
|
||||
1399,1729,1730,1731, 141, 621, 326,1057, 368,1732, 267, 488, 20,1733,1269,1734,
|
||||
945,1400,1735, 47, 904,1270,1736,1737, 773, 248,1738, 409, 313, 786, 429,1739,
|
||||
116, 987, 813,1401, 683, 75,1204, 145,1740,1741,1742,1743, 16, 847, 667, 622,
|
||||
708,1744,1745,1746, 966, 787, 304, 129,1747, 60, 820, 123, 676,1748,1749,1750,
|
||||
1751, 617,1752, 626,1753,1754,1755,1756, 653,1757,1758,1759,1760,1761,1762, 856,
|
||||
344,1763,1764,1765,1766, 89, 401, 418, 806, 905, 848,1767,1768,1769, 946,1205,
|
||||
709,1770,1118,1771, 241,1772,1773,1774,1271,1775, 569,1776, 999,1777,1778,1779,
|
||||
1780, 337, 751,1058, 28, 628, 254,1781, 177, 906, 270, 349, 891,1079,1782, 19,
|
||||
1783, 379,1784, 315,1785, 629, 754,1402, 559,1786, 636, 203,1206,1787, 710, 567,
|
||||
1788, 935, 814,1789,1790,1207, 766, 528,1791,1792,1208,1793,1794,1795,1796,1797,
|
||||
1403,1798,1799, 533,1059,1404,1405,1156,1406, 936, 884,1080,1800, 351,1801,1802,
|
||||
1803,1804,1805, 801,1806,1807,1808,1119,1809,1157, 714, 474,1407,1810, 298, 899,
|
||||
885,1811,1120, 802,1158,1812, 892,1813,1814,1408, 659,1815,1816,1121,1817,1818,
|
||||
1819,1820,1821,1822, 319,1823, 594, 545,1824, 815, 937,1209,1825,1826, 573,1409,
|
||||
1022,1827,1210,1828,1829,1830,1831,1832,1833, 556, 722, 807,1122,1060,1834, 697,
|
||||
1835, 900, 557, 715,1836,1410, 540,1411, 752,1159, 294, 597,1211, 976, 803, 770,
|
||||
1412,1837,1838, 39, 794,1413, 358,1839, 371, 925,1840, 453, 661, 788, 531, 723,
|
||||
544,1023,1081, 869, 91,1841, 392, 430, 790, 602,1414, 677,1082, 457,1415,1416,
|
||||
1842,1843, 475, 327,1024,1417, 795, 121,1844, 733, 403,1418,1845,1846,1847, 300,
|
||||
119, 711,1212, 627,1848,1272, 207,1849,1850, 796,1213, 382,1851, 519,1852,1083,
|
||||
893,1853,1854,1855, 367, 809, 487, 671,1856, 663,1857,1858, 956, 471, 306, 857,
|
||||
1859,1860,1160,1084,1861,1862,1863,1864,1865,1061,1866,1867,1868,1869,1870,1871,
|
||||
282, 96, 574,1872, 502,1085,1873,1214,1874, 907,1875,1876, 827, 977,1419,1420,
|
||||
1421, 268,1877,1422,1878,1879,1880, 308,1881, 2, 537,1882,1883,1215,1884,1885,
|
||||
127, 791,1886,1273,1423,1887, 34, 336, 404, 643,1888, 571, 654, 894, 840,1889,
|
||||
0, 886,1274, 122, 575, 260, 908, 938,1890,1275, 410, 316,1891,1892, 100,1893,
|
||||
1894,1123, 48,1161,1124,1025,1895, 633, 901,1276,1896,1897, 115, 816,1898, 317,
|
||||
1899, 694,1900, 909, 734,1424, 572, 866,1425, 691, 85, 524,1010, 543, 394, 841,
|
||||
1901,1902,1903,1026,1904,1905,1906,1907,1908,1909, 30, 451, 651, 988, 310,1910,
|
||||
1911,1426, 810,1216, 93,1912,1913,1277,1217,1914, 858, 759, 45, 58, 181, 610,
|
||||
269,1915,1916, 131,1062, 551, 443,1000, 821,1427, 957, 895,1086,1917,1918, 375,
|
||||
1919, 359,1920, 687,1921, 822,1922, 293,1923,1924, 40, 662, 118, 692, 29, 939,
|
||||
887, 640, 482, 174,1925, 69,1162, 728,1428, 910,1926,1278,1218,1279, 386, 870,
|
||||
217, 854,1163, 823,1927,1928,1929,1930, 834,1931, 78,1932, 859,1933,1063,1934,
|
||||
1935,1936,1937, 438,1164, 208, 595,1938,1939,1940,1941,1219,1125,1942, 280, 888,
|
||||
1429,1430,1220,1431,1943,1944,1945,1946,1947,1280, 150, 510,1432,1948,1949,1950,
|
||||
1951,1952,1953,1954,1011,1087,1955,1433,1043,1956, 881,1957, 614, 958,1064,1065,
|
||||
1221,1958, 638,1001, 860, 967, 896,1434, 989, 492, 553,1281,1165,1959,1282,1002,
|
||||
1283,1222,1960,1961,1962,1963, 36, 383, 228, 753, 247, 454,1964, 876, 678,1965,
|
||||
1966,1284, 126, 464, 490, 835, 136, 672, 529, 940,1088,1435, 473,1967,1968, 467,
|
||||
50, 390, 227, 587, 279, 378, 598, 792, 968, 240, 151, 160, 849, 882,1126,1285,
|
||||
639,1044, 133, 140, 288, 360, 811, 563,1027, 561, 142, 523,1969,1970,1971, 7,
|
||||
103, 296, 439, 407, 506, 634, 990,1972,1973,1974,1975, 645,1976,1977,1978,1979,
|
||||
1980,1981, 236,1982,1436,1983,1984,1089, 192, 828, 618, 518,1166, 333,1127,1985,
|
||||
818,1223,1986,1987,1988,1989,1990,1991,1992,1993, 342,1128,1286, 746, 842,1994,
|
||||
1995, 560, 223,1287, 98, 8, 189, 650, 978,1288,1996,1437,1997, 17, 345, 250,
|
||||
423, 277, 234, 512, 226, 97, 289, 42, 167,1998, 201,1999,2000, 843, 836, 824,
|
||||
532, 338, 783,1090, 182, 576, 436,1438,1439, 527, 500,2001, 947, 889,2002,2003,
|
||||
2004,2005, 262, 600, 314, 447,2006, 547,2007, 693, 738,1129,2008, 71,1440, 745,
|
||||
619, 688,2009, 829,2010,2011, 147,2012, 33, 948,2013,2014, 74, 224,2015, 61,
|
||||
191, 918, 399, 637,2016,1028,1130, 257, 902,2017,2018,2019,2020,2021,2022,2023,
|
||||
2024,2025,2026, 837,2027,2028,2029,2030, 179, 874, 591, 52, 724, 246,2031,2032,
|
||||
2033,2034,1167, 969,2035,1289, 630, 605, 911,1091,1168,2036,2037,2038,1441, 912,
|
||||
2039, 623,2040,2041, 253,1169,1290,2042,1442, 146, 620, 611, 577, 433,2043,1224,
|
||||
719,1170, 959, 440, 437, 534, 84, 388, 480,1131, 159, 220, 198, 679,2044,1012,
|
||||
819,1066,1443, 113,1225, 194, 318,1003,1029,2045,2046,2047,2048,1067,2049,2050,
|
||||
2051,2052,2053, 59, 913, 112,2054, 632,2055, 455, 144, 739,1291,2056, 273, 681,
|
||||
499,2057, 448,2058,2059, 760,2060,2061, 970, 384, 169, 245,1132,2062,2063, 414,
|
||||
1444,2064,2065, 41, 235,2066, 157, 252, 877, 568, 919, 789, 580,2067, 725,2068,
|
||||
2069,1292,2070,2071,1445,2072,1446,2073,2074, 55, 588, 66,1447, 271,1092,2075,
|
||||
1226,2076, 960,1013, 372,2077,2078,2079,2080,2081,1293,2082,2083,2084,2085, 850,
|
||||
2086,2087,2088,2089,2090, 186,2091,1068, 180,2092,2093,2094, 109,1227, 522, 606,
|
||||
2095, 867,1448,1093, 991,1171, 926, 353,1133,2096, 581,2097,2098,2099,1294,1449,
|
||||
1450,2100, 596,1172,1014,1228,2101,1451,1295,1173,1229,2102,2103,1296,1134,1452,
|
||||
949,1135,2104,2105,1094,1453,1454,1455,2106,1095,2107,2108,2109,2110,2111,2112,
|
||||
2113,2114,2115,2116,2117, 804,2118,2119,1230,1231, 805,1456, 405,1136,2120,2121,
|
||||
2122,2123,2124, 720, 701,1297, 992,1457, 927,1004,2125,2126,2127,2128,2129,2130,
|
||||
22, 417,2131, 303,2132, 385,2133, 971, 520, 513,2134,1174, 73,1096, 231, 274,
|
||||
962,1458, 673,2135,1459,2136, 152,1137,2137,2138,2139,2140,1005,1138,1460,1139,
|
||||
2141,2142,2143,2144, 11, 374, 844,2145, 154,1232, 46,1461,2146, 838, 830, 721,
|
||||
1233, 106,2147, 90, 428, 462, 578, 566,1175, 352,2148,2149, 538,1234, 124,1298,
|
||||
2150,1462, 761, 565,2151, 686,2152, 649,2153, 72, 173,2154, 460, 415,2155,1463,
|
||||
2156,1235, 305,2157,2158,2159,2160,2161,2162, 579,2163,2164,2165,2166,2167, 747,
|
||||
2168,2169,2170,2171,1464, 669,2172,2173,2174,2175,2176,1465,2177, 23, 530, 285,
|
||||
2178, 335, 729,2179, 397,2180,2181,2182,1030,2183,2184, 698,2185,2186, 325,2187,
|
||||
2188, 369,2189, 799,1097,1015, 348,2190,1069, 680,2191, 851,1466,2192,2193, 10,
|
||||
2194, 613, 424,2195, 979, 108, 449, 589, 27, 172, 81,1031, 80, 774, 281, 350,
|
||||
1032, 525, 301, 582,1176,2196, 674,1045,2197,2198,1467, 730, 762,2199,2200,2201,
|
||||
2202,1468,2203, 993,2204,2205, 266,1070, 963,1140,2206,2207,2208, 664,1098, 972,
|
||||
2209,2210,2211,1177,1469,1470, 871,2212,2213,2214,2215,2216,1471,2217,2218,2219,
|
||||
2220,2221,2222,2223,2224,2225,2226,2227,1472,1236,2228,2229,2230,2231,2232,2233,
|
||||
2234,2235,1299,2236,2237, 200,2238, 477, 373,2239,2240, 731, 825, 777,2241,2242,
|
||||
2243, 521, 486, 548,2244,2245,2246,1473,1300, 53, 549, 137, 875, 76, 158,2247,
|
||||
1301,1474, 469, 396,1016, 278, 712,2248, 321, 442, 503, 767, 744, 941,1237,1178,
|
||||
1475,2249, 82, 178,1141,1179, 973,2250,1302,2251, 297,2252,2253, 570,2254,2255,
|
||||
2256, 18, 450, 206,2257, 290, 292,1142,2258, 511, 162, 99, 346, 164, 735,2259,
|
||||
1476,1477, 4, 554, 343, 798,1099,2260,1100,2261, 43, 171,1303, 139, 215,2262,
|
||||
2263, 717, 775,2264,1033, 322, 216,2265, 831,2266, 149,2267,1304,2268,2269, 702,
|
||||
1238, 135, 845, 347, 309,2270, 484,2271, 878, 655, 238,1006,1478,2272, 67,2273,
|
||||
295,2274,2275, 461,2276, 478, 942, 412,2277,1034,2278,2279,2280, 265,2281, 541,
|
||||
2282,2283,2284,2285,2286, 70, 852,1071,2287,2288,2289,2290, 21, 56, 509, 117,
|
||||
432,2291,2292, 331, 980, 552,1101, 148, 284, 105, 393,1180,1239, 755,2293, 187,
|
||||
2294,1046,1479,2295, 340,2296, 63,1047, 230,2297,2298,1305, 763,1306, 101, 800,
|
||||
808, 494,2299,2300,2301, 903,2302, 37,1072, 14, 5,2303, 79, 675,2304, 312,
|
||||
2305,2306,2307,2308,2309,1480, 6,1307,2310,2311,2312, 1, 470, 35, 24, 229,
|
||||
2313, 695, 210, 86, 778, 15, 784, 592, 779, 32, 77, 855, 964,2314, 259,2315,
|
||||
501, 380,2316,2317, 83, 981, 153, 689,1308,1481,1482,1483,2318,2319, 716,1484,
|
||||
2320,2321,2322,2323,2324,2325,1485,2326,2327, 128, 57, 68, 261,1048, 211, 170,
|
||||
1240, 31,2328, 51, 435, 742,2329,2330,2331, 635,2332, 264, 456,2333,2334,2335,
|
||||
425,2336,1486, 143, 507, 263, 943,2337, 363, 920,1487, 256,1488,1102, 243, 601,
|
||||
1489,2338,2339,2340,2341,2342,2343,2344, 861,2345,2346,2347,2348,2349,2350, 395,
|
||||
2351,1490,1491, 62, 535, 166, 225,2352,2353, 668, 419,1241, 138, 604, 928,2354,
|
||||
1181,2355,1492,1493,2356,2357,2358,1143,2359, 696,2360, 387, 307,1309, 682, 476,
|
||||
2361,2362, 332, 12, 222, 156,2363, 232,2364, 641, 276, 656, 517,1494,1495,1035,
|
||||
416, 736,1496,2365,1017, 586,2366,2367,2368,1497,2369, 242,2370,2371,2372,1498,
|
||||
2373, 965, 713,2374,2375,2376,2377, 740, 982,1499, 944,1500,1007,2378,2379,1310,
|
||||
1501,2380,2381,2382, 785, 329,2383,2384,1502,2385,2386,2387, 932,2388,1503,2389,
|
||||
2390,2391,2392,1242,2393,2394,2395,2396,2397, 994, 950,2398,2399,2400,2401,1504,
|
||||
1311,2402,2403,2404,2405,1049, 749,2406,2407, 853, 718,1144,1312,2408,1182,1505,
|
||||
2409,2410, 255, 516, 479, 564, 550, 214,1506,1507,1313, 413, 239, 444, 339,1145,
|
||||
1036,1508,1509,1314,1037,1510,1315,2411,1511,2412,2413,2414, 176, 703, 497, 624,
|
||||
593, 921, 302,2415, 341, 165,1103,1512,2416,1513,2417,2418,2419, 376,2420, 700,
|
||||
2421,2422,2423, 258, 768,1316,2424,1183,2425, 995, 608,2426,2427,2428,2429, 221,
|
||||
2430,2431,2432,2433,2434,2435,2436,2437, 195, 323, 726, 188, 897, 983,1317, 377,
|
||||
644,1050, 879,2438, 452,2439,2440,2441,2442,2443,2444, 914,2445,2446,2447,2448,
|
||||
915, 489,2449,1514,1184,2450,2451, 515, 64, 427, 495,2452, 583,2453, 483, 485,
|
||||
1038, 562, 213,1515, 748, 666,2454,2455,2456,2457, 334,2458, 780, 996,1008, 705,
|
||||
1243,2459,2460,2461,2462,2463, 114,2464, 493,1146, 366, 163,1516, 961,1104,2465,
|
||||
291,2466,1318,1105,2467,1517, 365,2468, 355, 951,1244,2469,1319,2470, 631,2471,
|
||||
2472, 218,1320, 364, 320, 756,1518,1519,1321,1520,1322,2473,2474,2475,2476, 997,
|
||||
2477,2478,2479,2480, 665,1185,2481, 916,1521,2482,2483,2484, 584, 684,2485,2486,
|
||||
797,2487,1051,1186,2488,2489,2490,1522,2491,2492, 370,2493,1039,1187, 65,2494,
|
||||
434, 205, 463,1188,2495, 125, 812, 391, 402, 826, 699, 286, 398, 155, 781, 771,
|
||||
585,2496, 590, 505,1073,2497, 599, 244, 219, 917,1018, 952, 646,1523,2498,1323,
|
||||
2499,2500, 49, 984, 354, 741,2501, 625,2502,1324,2503,1019, 190, 357, 757, 491,
|
||||
95, 782, 868,2504,2505,2506,2507,2508,2509, 134,1524,1074, 422,1525, 898,2510,
|
||||
161,2511,2512,2513,2514, 769,2515,1526,2516,2517, 411,1325,2518, 472,1527,2519,
|
||||
2520,2521,2522,2523,2524, 985,2525,2526,2527,2528,2529,2530, 764,2531,1245,2532,
|
||||
2533, 25, 204, 311,2534, 496,2535,1052,2536,2537,2538,2539,2540,2541,2542, 199,
|
||||
704, 504, 468, 758, 657,1528, 196, 44, 839,1246, 272, 750,2543, 765, 862,2544,
|
||||
2545,1326,2546, 132, 615, 933,2547, 732,2548,2549,2550,1189,1529,2551, 283,1247,
|
||||
1053, 607, 929,2552,2553,2554, 930, 183, 872, 616,1040,1147,2555,1148,1020, 441,
|
||||
249,1075,2556,2557,2558, 466, 743,2559,2560,2561, 92, 514, 426, 420, 526,2562,
|
||||
2563,2564,2565,2566,2567,2568, 185,2569,2570,2571,2572, 776,1530, 658,2573, 362,
|
||||
2574, 361, 922,1076, 793,2575,2576,2577,2578,2579,2580,1531, 251,2581,2582,2583,
|
||||
2584,1532, 54, 612, 237,1327,2585,2586, 275, 408, 647, 111,2587,1533,1106, 465,
|
||||
3, 458, 9, 38,2588, 107, 110, 890, 209, 26, 737, 498,2589,1534,2590, 431,
|
||||
202, 88,1535, 356, 287,1107, 660,1149,2591, 381,1536, 986,1150, 445,1248,1151,
|
||||
974,2592,2593, 846,2594, 446, 953, 184,1249,1250, 727,2595, 923, 193, 883,2596,
|
||||
2597,2598, 102, 324, 539, 817,2599, 421,1041,2600, 832,2601, 94, 175, 197, 406,
|
||||
2602, 459,2603,2604,2605,2606,2607, 330, 555,2608,2609,2610, 706,1108, 389,2611,
|
||||
2612,2613,2614, 233,2615, 833, 558, 931, 954,1251,2616,2617,1537, 546,2618,2619,
|
||||
1009,2620,2621,2622,1538, 690,1328,2623, 955,2624,1539,2625,2626, 772,2627,2628,
|
||||
2629,2630,2631, 924, 648, 863, 603,2632,2633, 934,1540, 864, 865,2634, 642,1042,
|
||||
670,1190,2635,2636,2637,2638, 168,2639, 652, 873, 542,1054,1541,2640,2641,2642, # 512, 256
|
||||
#Everything below is of no interest for detection purpose
|
||||
2643,2644,2645,2646,2647,2648,2649,2650,2651,2652,2653,2654,2655,2656,2657,2658,
|
||||
2659,2660,2661,2662,2663,2664,2665,2666,2667,2668,2669,2670,2671,2672,2673,2674,
|
||||
2675,2676,2677,2678,2679,2680,2681,2682,2683,2684,2685,2686,2687,2688,2689,2690,
|
||||
2691,2692,2693,2694,2695,2696,2697,2698,2699,1542, 880,2700,2701,2702,2703,2704,
|
||||
2705,2706,2707,2708,2709,2710,2711,2712,2713,2714,2715,2716,2717,2718,2719,2720,
|
||||
2721,2722,2723,2724,2725,1543,2726,2727,2728,2729,2730,2731,2732,1544,2733,2734,
|
||||
2735,2736,2737,2738,2739,2740,2741,2742,2743,2744,2745,2746,2747,2748,2749,2750,
|
||||
2751,2752,2753,2754,1545,2755,2756,2757,2758,2759,2760,2761,2762,2763,2764,2765,
|
||||
2766,1546,2767,1547,2768,2769,2770,2771,2772,2773,2774,2775,2776,2777,2778,2779,
|
||||
2780,2781,2782,2783,2784,2785,2786,1548,2787,2788,2789,1109,2790,2791,2792,2793,
|
||||
2794,2795,2796,2797,2798,2799,2800,2801,2802,2803,2804,2805,2806,2807,2808,2809,
|
||||
2810,2811,2812,1329,2813,2814,2815,2816,2817,2818,2819,2820,2821,2822,2823,2824,
|
||||
2825,2826,2827,2828,2829,2830,2831,2832,2833,2834,2835,2836,2837,2838,2839,2840,
|
||||
2841,2842,2843,2844,2845,2846,2847,2848,2849,2850,2851,2852,2853,2854,2855,2856,
|
||||
1549,2857,2858,2859,2860,1550,2861,2862,1551,2863,2864,2865,2866,2867,2868,2869,
|
||||
2870,2871,2872,2873,2874,1110,1330,2875,2876,2877,2878,2879,2880,2881,2882,2883,
|
||||
2884,2885,2886,2887,2888,2889,2890,2891,2892,2893,2894,2895,2896,2897,2898,2899,
|
||||
2900,2901,2902,2903,2904,2905,2906,2907,2908,2909,2910,2911,2912,2913,2914,2915,
|
||||
2916,2917,2918,2919,2920,2921,2922,2923,2924,2925,2926,2927,2928,2929,2930,1331,
|
||||
2931,2932,2933,2934,2935,2936,2937,2938,2939,2940,2941,2942,2943,1552,2944,2945,
|
||||
2946,2947,2948,2949,2950,2951,2952,2953,2954,2955,2956,2957,2958,2959,2960,2961,
|
||||
2962,2963,2964,1252,2965,2966,2967,2968,2969,2970,2971,2972,2973,2974,2975,2976,
|
||||
2977,2978,2979,2980,2981,2982,2983,2984,2985,2986,2987,2988,2989,2990,2991,2992,
|
||||
2993,2994,2995,2996,2997,2998,2999,3000,3001,3002,3003,3004,3005,3006,3007,3008,
|
||||
3009,3010,3011,3012,1553,3013,3014,3015,3016,3017,1554,3018,1332,3019,3020,3021,
|
||||
3022,3023,3024,3025,3026,3027,3028,3029,3030,3031,3032,3033,3034,3035,3036,3037,
|
||||
3038,3039,3040,3041,3042,3043,3044,3045,3046,3047,3048,3049,3050,1555,3051,3052,
|
||||
3053,1556,1557,3054,3055,3056,3057,3058,3059,3060,3061,3062,3063,3064,3065,3066,
|
||||
3067,1558,3068,3069,3070,3071,3072,3073,3074,3075,3076,1559,3077,3078,3079,3080,
|
||||
3081,3082,3083,1253,3084,3085,3086,3087,3088,3089,3090,3091,3092,3093,3094,3095,
|
||||
3096,3097,3098,3099,3100,3101,3102,3103,3104,3105,3106,3107,3108,1152,3109,3110,
|
||||
3111,3112,3113,1560,3114,3115,3116,3117,1111,3118,3119,3120,3121,3122,3123,3124,
|
||||
3125,3126,3127,3128,3129,3130,3131,3132,3133,3134,3135,3136,3137,3138,3139,3140,
|
||||
3141,3142,3143,3144,3145,3146,3147,3148,3149,3150,3151,3152,3153,3154,3155,3156,
|
||||
3157,3158,3159,3160,3161,3162,3163,3164,3165,3166,3167,3168,3169,3170,3171,3172,
|
||||
3173,3174,3175,3176,1333,3177,3178,3179,3180,3181,3182,3183,3184,3185,3186,3187,
|
||||
3188,3189,1561,3190,3191,1334,3192,3193,3194,3195,3196,3197,3198,3199,3200,3201,
|
||||
3202,3203,3204,3205,3206,3207,3208,3209,3210,3211,3212,3213,3214,3215,3216,3217,
|
||||
3218,3219,3220,3221,3222,3223,3224,3225,3226,3227,3228,3229,3230,3231,3232,3233,
|
||||
3234,1562,3235,3236,3237,3238,3239,3240,3241,3242,3243,3244,3245,3246,3247,3248,
|
||||
3249,3250,3251,3252,3253,3254,3255,3256,3257,3258,3259,3260,3261,3262,3263,3264,
|
||||
3265,3266,3267,3268,3269,3270,3271,3272,3273,3274,3275,3276,3277,1563,3278,3279,
|
||||
3280,3281,3282,3283,3284,3285,3286,3287,3288,3289,3290,3291,3292,3293,3294,3295,
|
||||
3296,3297,3298,3299,3300,3301,3302,3303,3304,3305,3306,3307,3308,3309,3310,3311,
|
||||
3312,3313,3314,3315,3316,3317,3318,3319,3320,3321,3322,3323,3324,3325,3326,3327,
|
||||
3328,3329,3330,3331,3332,3333,3334,3335,3336,3337,3338,3339,3340,3341,3342,3343,
|
||||
3344,3345,3346,3347,3348,3349,3350,3351,3352,3353,3354,3355,3356,3357,3358,3359,
|
||||
3360,3361,3362,3363,3364,1335,3365,3366,3367,3368,3369,3370,3371,3372,3373,3374,
|
||||
3375,3376,3377,3378,3379,3380,3381,3382,3383,3384,3385,3386,3387,1336,3388,3389,
|
||||
3390,3391,3392,3393,3394,3395,3396,3397,3398,3399,3400,3401,3402,3403,3404,3405,
|
||||
3406,3407,3408,3409,3410,3411,3412,3413,3414,1337,3415,3416,3417,3418,3419,1338,
|
||||
3420,3421,3422,1564,1565,3423,3424,3425,3426,3427,3428,3429,3430,3431,1254,3432,
|
||||
3433,3434,1339,3435,3436,3437,3438,3439,1566,3440,3441,3442,3443,3444,3445,3446,
|
||||
3447,3448,3449,3450,3451,3452,3453,3454,1255,3455,3456,3457,3458,3459,1567,1191,
|
||||
3460,1568,1569,3461,3462,3463,1570,3464,3465,3466,3467,3468,1571,3469,3470,3471,
|
||||
3472,3473,1572,3474,3475,3476,3477,3478,3479,3480,3481,3482,3483,3484,3485,3486,
|
||||
1340,3487,3488,3489,3490,3491,3492,1021,3493,3494,3495,3496,3497,3498,1573,3499,
|
||||
1341,3500,3501,3502,3503,3504,3505,3506,3507,3508,3509,3510,3511,1342,3512,3513,
|
||||
3514,3515,3516,1574,1343,3517,3518,3519,1575,3520,1576,3521,3522,3523,3524,3525,
|
||||
3526,3527,3528,3529,3530,3531,3532,3533,3534,3535,3536,3537,3538,3539,3540,3541,
|
||||
3542,3543,3544,3545,3546,3547,3548,3549,3550,3551,3552,3553,3554,3555,3556,3557,
|
||||
3558,3559,3560,3561,3562,3563,3564,3565,3566,3567,3568,3569,3570,3571,3572,3573,
|
||||
3574,3575,3576,3577,3578,3579,3580,1577,3581,3582,1578,3583,3584,3585,3586,3587,
|
||||
3588,3589,3590,3591,3592,3593,3594,3595,3596,3597,3598,3599,3600,3601,3602,3603,
|
||||
3604,1579,3605,3606,3607,3608,3609,3610,3611,3612,3613,3614,3615,3616,3617,3618,
|
||||
3619,3620,3621,3622,3623,3624,3625,3626,3627,3628,3629,1580,3630,3631,1581,3632,
|
||||
3633,3634,3635,3636,3637,3638,3639,3640,3641,3642,3643,3644,3645,3646,3647,3648,
|
||||
3649,3650,3651,3652,3653,3654,3655,3656,1582,3657,3658,3659,3660,3661,3662,3663,
|
||||
3664,3665,3666,3667,3668,3669,3670,3671,3672,3673,3674,3675,3676,3677,3678,3679,
|
||||
3680,3681,3682,3683,3684,3685,3686,3687,3688,3689,3690,3691,3692,3693,3694,3695,
|
||||
3696,3697,3698,3699,3700,1192,3701,3702,3703,3704,1256,3705,3706,3707,3708,1583,
|
||||
1257,3709,3710,3711,3712,3713,3714,3715,3716,1584,3717,3718,3719,3720,3721,3722,
|
||||
3723,3724,3725,3726,3727,3728,3729,3730,3731,3732,3733,3734,3735,3736,3737,3738,
|
||||
3739,3740,3741,3742,3743,3744,3745,1344,3746,3747,3748,3749,3750,3751,3752,3753,
|
||||
3754,3755,3756,1585,3757,3758,3759,3760,3761,3762,3763,3764,3765,3766,1586,3767,
|
||||
3768,3769,3770,3771,3772,3773,3774,3775,3776,3777,3778,1345,3779,3780,3781,3782,
|
||||
3783,3784,3785,3786,3787,3788,3789,3790,3791,3792,3793,3794,3795,1346,1587,3796,
|
||||
3797,1588,3798,3799,3800,3801,3802,3803,3804,3805,3806,1347,3807,3808,3809,3810,
|
||||
3811,1589,3812,3813,3814,3815,3816,3817,3818,3819,3820,3821,1590,3822,3823,1591,
|
||||
1348,3824,3825,3826,3827,3828,3829,3830,1592,3831,3832,1593,3833,3834,3835,3836,
|
||||
3837,3838,3839,3840,3841,3842,3843,3844,1349,3845,3846,3847,3848,3849,3850,3851,
|
||||
3852,3853,3854,3855,3856,3857,3858,1594,3859,3860,3861,3862,3863,3864,3865,3866,
|
||||
3867,3868,3869,1595,3870,3871,3872,3873,1596,3874,3875,3876,3877,3878,3879,3880,
|
||||
3881,3882,3883,3884,3885,3886,1597,3887,3888,3889,3890,3891,3892,3893,3894,3895,
|
||||
1598,3896,3897,3898,1599,1600,3899,1350,3900,1351,3901,3902,1352,3903,3904,3905,
|
||||
3906,3907,3908,3909,3910,3911,3912,3913,3914,3915,3916,3917,3918,3919,3920,3921,
|
||||
3922,3923,3924,1258,3925,3926,3927,3928,3929,3930,3931,1193,3932,1601,3933,3934,
|
||||
3935,3936,3937,3938,3939,3940,3941,3942,3943,1602,3944,3945,3946,3947,3948,1603,
|
||||
3949,3950,3951,3952,3953,3954,3955,3956,3957,3958,3959,3960,3961,3962,3963,3964,
|
||||
3965,1604,3966,3967,3968,3969,3970,3971,3972,3973,3974,3975,3976,3977,1353,3978,
|
||||
3979,3980,3981,3982,3983,3984,3985,3986,3987,3988,3989,3990,3991,1354,3992,3993,
|
||||
3994,3995,3996,3997,3998,3999,4000,4001,4002,4003,4004,4005,4006,4007,4008,4009,
|
||||
4010,4011,4012,4013,4014,4015,4016,4017,4018,4019,4020,4021,4022,4023,1355,4024,
|
||||
4025,4026,4027,4028,4029,4030,4031,4032,4033,4034,4035,4036,4037,4038,4039,4040,
|
||||
1605,4041,4042,4043,4044,4045,4046,4047,4048,4049,4050,4051,4052,4053,4054,4055,
|
||||
4056,4057,4058,4059,4060,1606,4061,4062,4063,4064,1607,4065,4066,4067,4068,4069,
|
||||
4070,4071,4072,4073,4074,4075,4076,1194,4077,4078,1608,4079,4080,4081,4082,4083,
|
||||
4084,4085,4086,4087,1609,4088,4089,4090,4091,4092,4093,4094,4095,4096,4097,4098,
|
||||
4099,4100,4101,4102,4103,4104,4105,4106,4107,4108,1259,4109,4110,4111,4112,4113,
|
||||
4114,4115,4116,4117,4118,4119,4120,4121,4122,4123,4124,1195,4125,4126,4127,1610,
|
||||
4128,4129,4130,4131,4132,4133,4134,4135,4136,4137,1356,4138,4139,4140,4141,4142,
|
||||
4143,4144,1611,4145,4146,4147,4148,4149,4150,4151,4152,4153,4154,4155,4156,4157,
|
||||
4158,4159,4160,4161,4162,4163,4164,4165,4166,4167,4168,4169,4170,4171,4172,4173,
|
||||
4174,4175,4176,4177,4178,4179,4180,4181,4182,4183,4184,4185,4186,4187,4188,4189,
|
||||
4190,4191,4192,4193,4194,4195,4196,4197,4198,4199,4200,4201,4202,4203,4204,4205,
|
||||
4206,4207,4208,4209,4210,4211,4212,4213,4214,4215,4216,4217,4218,4219,1612,4220,
|
||||
4221,4222,4223,4224,4225,4226,4227,1357,4228,1613,4229,4230,4231,4232,4233,4234,
|
||||
4235,4236,4237,4238,4239,4240,4241,4242,4243,1614,4244,4245,4246,4247,4248,4249,
|
||||
4250,4251,4252,4253,4254,4255,4256,4257,4258,4259,4260,4261,4262,4263,4264,4265,
|
||||
4266,4267,4268,4269,4270,1196,1358,4271,4272,4273,4274,4275,4276,4277,4278,4279,
|
||||
4280,4281,4282,4283,4284,4285,4286,4287,1615,4288,4289,4290,4291,4292,4293,4294,
|
||||
4295,4296,4297,4298,4299,4300,4301,4302,4303,4304,4305,4306,4307,4308,4309,4310,
|
||||
4311,4312,4313,4314,4315,4316,4317,4318,4319,4320,4321,4322,4323,4324,4325,4326,
|
||||
4327,4328,4329,4330,4331,4332,4333,4334,1616,4335,4336,4337,4338,4339,4340,4341,
|
||||
4342,4343,4344,4345,4346,4347,4348,4349,4350,4351,4352,4353,4354,4355,4356,4357,
|
||||
4358,4359,4360,1617,4361,4362,4363,4364,4365,1618,4366,4367,4368,4369,4370,4371,
|
||||
4372,4373,4374,4375,4376,4377,4378,4379,4380,4381,4382,4383,4384,4385,4386,4387,
|
||||
4388,4389,4390,4391,4392,4393,4394,4395,4396,4397,4398,4399,4400,4401,4402,4403,
|
||||
4404,4405,4406,4407,4408,4409,4410,4411,4412,4413,4414,4415,4416,1619,4417,4418,
|
||||
4419,4420,4421,4422,4423,4424,4425,1112,4426,4427,4428,4429,4430,1620,4431,4432,
|
||||
4433,4434,4435,4436,4437,4438,4439,4440,4441,4442,1260,1261,4443,4444,4445,4446,
|
||||
4447,4448,4449,4450,4451,4452,4453,4454,4455,1359,4456,4457,4458,4459,4460,4461,
|
||||
4462,4463,4464,4465,1621,4466,4467,4468,4469,4470,4471,4472,4473,4474,4475,4476,
|
||||
4477,4478,4479,4480,4481,4482,4483,4484,4485,4486,4487,4488,4489,1055,4490,4491,
|
||||
4492,4493,4494,4495,4496,4497,4498,4499,4500,4501,4502,4503,4504,4505,4506,4507,
|
||||
4508,4509,4510,4511,4512,4513,4514,4515,4516,4517,4518,1622,4519,4520,4521,1623,
|
||||
4522,4523,4524,4525,4526,4527,4528,4529,4530,4531,4532,4533,4534,4535,1360,4536,
|
||||
4537,4538,4539,4540,4541,4542,4543, 975,4544,4545,4546,4547,4548,4549,4550,4551,
|
||||
4552,4553,4554,4555,4556,4557,4558,4559,4560,4561,4562,4563,4564,4565,4566,4567,
|
||||
4568,4569,4570,4571,1624,4572,4573,4574,4575,4576,1625,4577,4578,4579,4580,4581,
|
||||
4582,4583,4584,1626,4585,4586,4587,4588,4589,4590,4591,4592,4593,4594,4595,1627,
|
||||
4596,4597,4598,4599,4600,4601,4602,4603,4604,4605,4606,4607,4608,4609,4610,4611,
|
||||
4612,4613,4614,4615,1628,4616,4617,4618,4619,4620,4621,4622,4623,4624,4625,4626,
|
||||
4627,4628,4629,4630,4631,4632,4633,4634,4635,4636,4637,4638,4639,4640,4641,4642,
|
||||
4643,4644,4645,4646,4647,4648,4649,1361,4650,4651,4652,4653,4654,4655,4656,4657,
|
||||
4658,4659,4660,4661,1362,4662,4663,4664,4665,4666,4667,4668,4669,4670,4671,4672,
|
||||
4673,4674,4675,4676,4677,4678,4679,4680,4681,4682,1629,4683,4684,4685,4686,4687,
|
||||
1630,4688,4689,4690,4691,1153,4692,4693,4694,1113,4695,4696,4697,4698,4699,4700,
|
||||
4701,4702,4703,4704,4705,4706,4707,4708,4709,4710,4711,1197,4712,4713,4714,4715,
|
||||
4716,4717,4718,4719,4720,4721,4722,4723,4724,4725,4726,4727,4728,4729,4730,4731,
|
||||
4732,4733,4734,4735,1631,4736,1632,4737,4738,4739,4740,4741,4742,4743,4744,1633,
|
||||
4745,4746,4747,4748,4749,1262,4750,4751,4752,4753,4754,1363,4755,4756,4757,4758,
|
||||
4759,4760,4761,4762,4763,4764,4765,4766,4767,4768,1634,4769,4770,4771,4772,4773,
|
||||
4774,4775,4776,4777,4778,1635,4779,4780,4781,4782,4783,4784,4785,4786,4787,4788,
|
||||
4789,1636,4790,4791,4792,4793,4794,4795,4796,4797,4798,4799,4800,4801,4802,4803,
|
||||
4804,4805,4806,1637,4807,4808,4809,1638,4810,4811,4812,4813,4814,4815,4816,4817,
|
||||
4818,1639,4819,4820,4821,4822,4823,4824,4825,4826,4827,4828,4829,4830,4831,4832,
|
||||
4833,1077,4834,4835,4836,4837,4838,4839,4840,4841,4842,4843,4844,4845,4846,4847,
|
||||
4848,4849,4850,4851,4852,4853,4854,4855,4856,4857,4858,4859,4860,4861,4862,4863,
|
||||
4864,4865,4866,4867,4868,4869,4870,4871,4872,4873,4874,4875,4876,4877,4878,4879,
|
||||
4880,4881,4882,4883,1640,4884,4885,1641,4886,4887,4888,4889,4890,4891,4892,4893,
|
||||
4894,4895,4896,4897,4898,4899,4900,4901,4902,4903,4904,4905,4906,4907,4908,4909,
|
||||
4910,4911,1642,4912,4913,4914,1364,4915,4916,4917,4918,4919,4920,4921,4922,4923,
|
||||
4924,4925,4926,4927,4928,4929,4930,4931,1643,4932,4933,4934,4935,4936,4937,4938,
|
||||
4939,4940,4941,4942,4943,4944,4945,4946,4947,4948,4949,4950,4951,4952,4953,4954,
|
||||
4955,4956,4957,4958,4959,4960,4961,4962,4963,4964,4965,4966,4967,4968,4969,4970,
|
||||
4971,4972,4973,4974,4975,4976,4977,4978,4979,4980,1644,4981,4982,4983,4984,1645,
|
||||
4985,4986,1646,4987,4988,4989,4990,4991,4992,4993,4994,4995,4996,4997,4998,4999,
|
||||
5000,5001,5002,5003,5004,5005,1647,5006,1648,5007,5008,5009,5010,5011,5012,1078,
|
||||
5013,5014,5015,5016,5017,5018,5019,5020,5021,5022,5023,5024,5025,5026,5027,5028,
|
||||
1365,5029,5030,5031,5032,5033,5034,5035,5036,5037,5038,5039,1649,5040,5041,5042,
|
||||
5043,5044,5045,1366,5046,5047,5048,5049,5050,5051,5052,5053,5054,5055,1650,5056,
|
||||
5057,5058,5059,5060,5061,5062,5063,5064,5065,5066,5067,5068,5069,5070,5071,5072,
|
||||
5073,5074,5075,5076,5077,1651,5078,5079,5080,5081,5082,5083,5084,5085,5086,5087,
|
||||
5088,5089,5090,5091,5092,5093,5094,5095,5096,5097,5098,5099,5100,5101,5102,5103,
|
||||
5104,5105,5106,5107,5108,5109,5110,1652,5111,5112,5113,5114,5115,5116,5117,5118,
|
||||
1367,5119,5120,5121,5122,5123,5124,5125,5126,5127,5128,5129,1653,5130,5131,5132,
|
||||
5133,5134,5135,5136,5137,5138,5139,5140,5141,5142,5143,5144,5145,5146,5147,5148,
|
||||
5149,1368,5150,1654,5151,1369,5152,5153,5154,5155,5156,5157,5158,5159,5160,5161,
|
||||
5162,5163,5164,5165,5166,5167,5168,5169,5170,5171,5172,5173,5174,5175,5176,5177,
|
||||
5178,1370,5179,5180,5181,5182,5183,5184,5185,5186,5187,5188,5189,5190,5191,5192,
|
||||
5193,5194,5195,5196,5197,5198,1655,5199,5200,5201,5202,1656,5203,5204,5205,5206,
|
||||
1371,5207,1372,5208,5209,5210,5211,1373,5212,5213,1374,5214,5215,5216,5217,5218,
|
||||
5219,5220,5221,5222,5223,5224,5225,5226,5227,5228,5229,5230,5231,5232,5233,5234,
|
||||
5235,5236,5237,5238,5239,5240,5241,5242,5243,5244,5245,5246,5247,1657,5248,5249,
|
||||
5250,5251,1658,1263,5252,5253,5254,5255,5256,1375,5257,5258,5259,5260,5261,5262,
|
||||
5263,5264,5265,5266,5267,5268,5269,5270,5271,5272,5273,5274,5275,5276,5277,5278,
|
||||
5279,5280,5281,5282,5283,1659,5284,5285,5286,5287,5288,5289,5290,5291,5292,5293,
|
||||
5294,5295,5296,5297,5298,5299,5300,1660,5301,5302,5303,5304,5305,5306,5307,5308,
|
||||
5309,5310,5311,5312,5313,5314,5315,5316,5317,5318,5319,5320,5321,1376,5322,5323,
|
||||
5324,5325,5326,5327,5328,5329,5330,5331,5332,5333,1198,5334,5335,5336,5337,5338,
|
||||
5339,5340,5341,5342,5343,1661,5344,5345,5346,5347,5348,5349,5350,5351,5352,5353,
|
||||
5354,5355,5356,5357,5358,5359,5360,5361,5362,5363,5364,5365,5366,5367,5368,5369,
|
||||
5370,5371,5372,5373,5374,5375,5376,5377,5378,5379,5380,5381,5382,5383,5384,5385,
|
||||
5386,5387,5388,5389,5390,5391,5392,5393,5394,5395,5396,5397,5398,1264,5399,5400,
|
||||
5401,5402,5403,5404,5405,5406,5407,5408,5409,5410,5411,5412,1662,5413,5414,5415,
|
||||
5416,1663,5417,5418,5419,5420,5421,5422,5423,5424,5425,5426,5427,5428,5429,5430,
|
||||
5431,5432,5433,5434,5435,5436,5437,5438,1664,5439,5440,5441,5442,5443,5444,5445,
|
||||
5446,5447,5448,5449,5450,5451,5452,5453,5454,5455,5456,5457,5458,5459,5460,5461,
|
||||
5462,5463,5464,5465,5466,5467,5468,5469,5470,5471,5472,5473,5474,5475,5476,5477,
|
||||
5478,1154,5479,5480,5481,5482,5483,5484,5485,1665,5486,5487,5488,5489,5490,5491,
|
||||
5492,5493,5494,5495,5496,5497,5498,5499,5500,5501,5502,5503,5504,5505,5506,5507,
|
||||
5508,5509,5510,5511,5512,5513,5514,5515,5516,5517,5518,5519,5520,5521,5522,5523,
|
||||
5524,5525,5526,5527,5528,5529,5530,5531,5532,5533,5534,5535,5536,5537,5538,5539,
|
||||
5540,5541,5542,5543,5544,5545,5546,5547,5548,1377,5549,5550,5551,5552,5553,5554,
|
||||
5555,5556,5557,5558,5559,5560,5561,5562,5563,5564,5565,5566,5567,5568,5569,5570,
|
||||
1114,5571,5572,5573,5574,5575,5576,5577,5578,5579,5580,5581,5582,5583,5584,5585,
|
||||
5586,5587,5588,5589,5590,5591,5592,1378,5593,5594,5595,5596,5597,5598,5599,5600,
|
||||
5601,5602,5603,5604,5605,5606,5607,5608,5609,5610,5611,5612,5613,5614,1379,5615,
|
||||
5616,5617,5618,5619,5620,5621,5622,5623,5624,5625,5626,5627,5628,5629,5630,5631,
|
||||
5632,5633,5634,1380,5635,5636,5637,5638,5639,5640,5641,5642,5643,5644,5645,5646,
|
||||
5647,5648,5649,1381,1056,5650,5651,5652,5653,5654,5655,5656,5657,5658,5659,5660,
|
||||
1666,5661,5662,5663,5664,5665,5666,5667,5668,1667,5669,1668,5670,5671,5672,5673,
|
||||
5674,5675,5676,5677,5678,1155,5679,5680,5681,5682,5683,5684,5685,5686,5687,5688,
|
||||
5689,5690,5691,5692,5693,5694,5695,5696,5697,5698,1669,5699,5700,5701,5702,5703,
|
||||
5704,5705,1670,5706,5707,5708,5709,5710,1671,5711,5712,5713,5714,1382,5715,5716,
|
||||
5717,5718,5719,5720,5721,5722,5723,5724,5725,1672,5726,5727,1673,1674,5728,5729,
|
||||
5730,5731,5732,5733,5734,5735,5736,1675,5737,5738,5739,5740,5741,5742,5743,5744,
|
||||
1676,5745,5746,5747,5748,5749,5750,5751,1383,5752,5753,5754,5755,5756,5757,5758,
|
||||
5759,5760,5761,5762,5763,5764,5765,5766,5767,5768,1677,5769,5770,5771,5772,5773,
|
||||
1678,5774,5775,5776, 998,5777,5778,5779,5780,5781,5782,5783,5784,5785,1384,5786,
|
||||
5787,5788,5789,5790,5791,5792,5793,5794,5795,5796,5797,5798,5799,5800,1679,5801,
|
||||
5802,5803,1115,1116,5804,5805,5806,5807,5808,5809,5810,5811,5812,5813,5814,5815,
|
||||
5816,5817,5818,5819,5820,5821,5822,5823,5824,5825,5826,5827,5828,5829,5830,5831,
|
||||
5832,5833,5834,5835,5836,5837,5838,5839,5840,5841,5842,5843,5844,5845,5846,5847,
|
||||
5848,5849,5850,5851,5852,5853,5854,5855,1680,5856,5857,5858,5859,5860,5861,5862,
|
||||
5863,5864,1681,5865,5866,5867,1682,5868,5869,5870,5871,5872,5873,5874,5875,5876,
|
||||
5877,5878,5879,1683,5880,1684,5881,5882,5883,5884,1685,5885,5886,5887,5888,5889,
|
||||
5890,5891,5892,5893,5894,5895,5896,5897,5898,5899,5900,5901,5902,5903,5904,5905,
|
||||
5906,5907,1686,5908,5909,5910,5911,5912,5913,5914,5915,5916,5917,5918,5919,5920,
|
||||
5921,5922,5923,5924,5925,5926,5927,5928,5929,5930,5931,5932,5933,5934,5935,1687,
|
||||
5936,5937,5938,5939,5940,5941,5942,5943,5944,5945,5946,5947,5948,5949,5950,5951,
|
||||
5952,1688,1689,5953,1199,5954,5955,5956,5957,5958,5959,5960,5961,1690,5962,5963,
|
||||
5964,5965,5966,5967,5968,5969,5970,5971,5972,5973,5974,5975,5976,5977,5978,5979,
|
||||
5980,5981,1385,5982,1386,5983,5984,5985,5986,5987,5988,5989,5990,5991,5992,5993,
|
||||
5994,5995,5996,5997,5998,5999,6000,6001,6002,6003,6004,6005,6006,6007,6008,6009,
|
||||
6010,6011,6012,6013,6014,6015,6016,6017,6018,6019,6020,6021,6022,6023,6024,6025,
|
||||
6026,6027,1265,6028,6029,1691,6030,6031,6032,6033,6034,6035,6036,6037,6038,6039,
|
||||
6040,6041,6042,6043,6044,6045,6046,6047,6048,6049,6050,6051,6052,6053,6054,6055,
|
||||
6056,6057,6058,6059,6060,6061,6062,6063,6064,6065,6066,6067,6068,6069,6070,6071,
|
||||
6072,6073,6074,6075,6076,6077,6078,6079,6080,6081,6082,6083,6084,1692,6085,6086,
|
||||
6087,6088,6089,6090,6091,6092,6093,6094,6095,6096,6097,6098,6099,6100,6101,6102,
|
||||
6103,6104,6105,6106,6107,6108,6109,6110,6111,6112,6113,6114,6115,6116,6117,6118,
|
||||
6119,6120,6121,6122,6123,6124,6125,6126,6127,6128,6129,6130,6131,1693,6132,6133,
|
||||
6134,6135,6136,1694,6137,6138,6139,6140,6141,1695,6142,6143,6144,6145,6146,6147,
|
||||
6148,6149,6150,6151,6152,6153,6154,6155,6156,6157,6158,6159,6160,6161,6162,6163,
|
||||
6164,6165,6166,6167,6168,6169,6170,6171,6172,6173,6174,6175,6176,6177,6178,6179,
|
||||
6180,6181,6182,6183,6184,6185,1696,6186,6187,6188,6189,6190,6191,6192,6193,6194,
|
||||
6195,6196,6197,6198,6199,6200,6201,6202,6203,6204,6205,6206,6207,6208,6209,6210,
|
||||
6211,6212,6213,6214,6215,6216,6217,6218,6219,1697,6220,6221,6222,6223,6224,6225,
|
||||
6226,6227,6228,6229,6230,6231,6232,6233,6234,6235,6236,6237,6238,6239,6240,6241,
|
||||
6242,6243,6244,6245,6246,6247,6248,6249,6250,6251,6252,6253,1698,6254,6255,6256,
|
||||
6257,6258,6259,6260,6261,6262,6263,1200,6264,6265,6266,6267,6268,6269,6270,6271, #1024
|
||||
6272,6273,6274,6275,6276,6277,6278,6279,6280,6281,6282,6283,6284,6285,6286,6287,
|
||||
6288,6289,6290,6291,6292,6293,6294,6295,6296,6297,6298,6299,6300,6301,6302,1699,
|
||||
6303,6304,1700,6305,6306,6307,6308,6309,6310,6311,6312,6313,6314,6315,6316,6317,
|
||||
6318,6319,6320,6321,6322,6323,6324,6325,6326,6327,6328,6329,6330,6331,6332,6333,
|
||||
6334,6335,6336,6337,6338,6339,1701,6340,6341,6342,6343,6344,1387,6345,6346,6347,
|
||||
6348,6349,6350,6351,6352,6353,6354,6355,6356,6357,6358,6359,6360,6361,6362,6363,
|
||||
6364,6365,6366,6367,6368,6369,6370,6371,6372,6373,6374,6375,6376,6377,6378,6379,
|
||||
6380,6381,6382,6383,6384,6385,6386,6387,6388,6389,6390,6391,6392,6393,6394,6395,
|
||||
6396,6397,6398,6399,6400,6401,6402,6403,6404,6405,6406,6407,6408,6409,6410,6411,
|
||||
6412,6413,1702,6414,6415,6416,6417,6418,6419,6420,6421,6422,1703,6423,6424,6425,
|
||||
6426,6427,6428,6429,6430,6431,6432,6433,6434,6435,6436,6437,6438,1704,6439,6440,
|
||||
6441,6442,6443,6444,6445,6446,6447,6448,6449,6450,6451,6452,6453,6454,6455,6456,
|
||||
6457,6458,6459,6460,6461,6462,6463,6464,6465,6466,6467,6468,6469,6470,6471,6472,
|
||||
6473,6474,6475,6476,6477,6478,6479,6480,6481,6482,6483,6484,6485,6486,6487,6488,
|
||||
6489,6490,6491,6492,6493,6494,6495,6496,6497,6498,6499,6500,6501,6502,6503,1266,
|
||||
6504,6505,6506,6507,6508,6509,6510,6511,6512,6513,6514,6515,6516,6517,6518,6519,
|
||||
6520,6521,6522,6523,6524,6525,6526,6527,6528,6529,6530,6531,6532,6533,6534,6535,
|
||||
6536,6537,6538,6539,6540,6541,6542,6543,6544,6545,6546,6547,6548,6549,6550,6551,
|
||||
1705,1706,6552,6553,6554,6555,6556,6557,6558,6559,6560,6561,6562,6563,6564,6565,
|
||||
6566,6567,6568,6569,6570,6571,6572,6573,6574,6575,6576,6577,6578,6579,6580,6581,
|
||||
6582,6583,6584,6585,6586,6587,6588,6589,6590,6591,6592,6593,6594,6595,6596,6597,
|
||||
6598,6599,6600,6601,6602,6603,6604,6605,6606,6607,6608,6609,6610,6611,6612,6613,
|
||||
6614,6615,6616,6617,6618,6619,6620,6621,6622,6623,6624,6625,6626,6627,6628,6629,
|
||||
6630,6631,6632,6633,6634,6635,6636,6637,1388,6638,6639,6640,6641,6642,6643,6644,
|
||||
1707,6645,6646,6647,6648,6649,6650,6651,6652,6653,6654,6655,6656,6657,6658,6659,
|
||||
6660,6661,6662,6663,1708,6664,6665,6666,6667,6668,6669,6670,6671,6672,6673,6674,
|
||||
1201,6675,6676,6677,6678,6679,6680,6681,6682,6683,6684,6685,6686,6687,6688,6689,
|
||||
6690,6691,6692,6693,6694,6695,6696,6697,6698,6699,6700,6701,6702,6703,6704,6705,
|
||||
6706,6707,6708,6709,6710,6711,6712,6713,6714,6715,6716,6717,6718,6719,6720,6721,
|
||||
6722,6723,6724,6725,1389,6726,6727,6728,6729,6730,6731,6732,6733,6734,6735,6736,
|
||||
1390,1709,6737,6738,6739,6740,6741,6742,1710,6743,6744,6745,6746,1391,6747,6748,
|
||||
6749,6750,6751,6752,6753,6754,6755,6756,6757,1392,6758,6759,6760,6761,6762,6763,
|
||||
6764,6765,6766,6767,6768,6769,6770,6771,6772,6773,6774,6775,6776,6777,6778,6779,
|
||||
6780,1202,6781,6782,6783,6784,6785,6786,6787,6788,6789,6790,6791,6792,6793,6794,
|
||||
6795,6796,6797,6798,6799,6800,6801,6802,6803,6804,6805,6806,6807,6808,6809,1711,
|
||||
6810,6811,6812,6813,6814,6815,6816,6817,6818,6819,6820,6821,6822,6823,6824,6825,
|
||||
6826,6827,6828,6829,6830,6831,6832,6833,6834,6835,6836,1393,6837,6838,6839,6840,
|
||||
6841,6842,6843,6844,6845,6846,6847,6848,6849,6850,6851,6852,6853,6854,6855,6856,
|
||||
6857,6858,6859,6860,6861,6862,6863,6864,6865,6866,6867,6868,6869,6870,6871,6872,
|
||||
6873,6874,6875,6876,6877,6878,6879,6880,6881,6882,6883,6884,6885,6886,6887,6888,
|
||||
6889,6890,6891,6892,6893,6894,6895,6896,6897,6898,6899,6900,6901,6902,1712,6903,
|
||||
6904,6905,6906,6907,6908,6909,6910,1713,6911,6912,6913,6914,6915,6916,6917,6918,
|
||||
6919,6920,6921,6922,6923,6924,6925,6926,6927,6928,6929,6930,6931,6932,6933,6934,
|
||||
6935,6936,6937,6938,6939,6940,6941,6942,6943,6944,6945,6946,6947,6948,6949,6950,
|
||||
6951,6952,6953,6954,6955,6956,6957,6958,6959,6960,6961,6962,6963,6964,6965,6966,
|
||||
6967,6968,6969,6970,6971,6972,6973,6974,1714,6975,6976,6977,6978,6979,6980,6981,
|
||||
6982,6983,6984,6985,6986,6987,6988,1394,6989,6990,6991,6992,6993,6994,6995,6996,
|
||||
6997,6998,6999,7000,1715,7001,7002,7003,7004,7005,7006,7007,7008,7009,7010,7011,
|
||||
7012,7013,7014,7015,7016,7017,7018,7019,7020,7021,7022,7023,7024,7025,7026,7027,
|
||||
7028,1716,7029,7030,7031,7032,7033,7034,7035,7036,7037,7038,7039,7040,7041,7042,
|
||||
7043,7044,7045,7046,7047,7048,7049,7050,7051,7052,7053,7054,7055,7056,7057,7058,
|
||||
7059,7060,7061,7062,7063,7064,7065,7066,7067,7068,7069,7070,7071,7072,7073,7074,
|
||||
7075,7076,7077,7078,7079,7080,7081,7082,7083,7084,7085,7086,7087,7088,7089,7090,
|
||||
7091,7092,7093,7094,7095,7096,7097,7098,7099,7100,7101,7102,7103,7104,7105,7106,
|
||||
7107,7108,7109,7110,7111,7112,7113,7114,7115,7116,7117,7118,7119,7120,7121,7122,
|
||||
7123,7124,7125,7126,7127,7128,7129,7130,7131,7132,7133,7134,7135,7136,7137,7138,
|
||||
7139,7140,7141,7142,7143,7144,7145,7146,7147,7148,7149,7150,7151,7152,7153,7154,
|
||||
7155,7156,7157,7158,7159,7160,7161,7162,7163,7164,7165,7166,7167,7168,7169,7170,
|
||||
7171,7172,7173,7174,7175,7176,7177,7178,7179,7180,7181,7182,7183,7184,7185,7186,
|
||||
7187,7188,7189,7190,7191,7192,7193,7194,7195,7196,7197,7198,7199,7200,7201,7202,
|
||||
7203,7204,7205,7206,7207,1395,7208,7209,7210,7211,7212,7213,1717,7214,7215,7216,
|
||||
7217,7218,7219,7220,7221,7222,7223,7224,7225,7226,7227,7228,7229,7230,7231,7232,
|
||||
7233,7234,7235,7236,7237,7238,7239,7240,7241,7242,7243,7244,7245,7246,7247,7248,
|
||||
7249,7250,7251,7252,7253,7254,7255,7256,7257,7258,7259,7260,7261,7262,7263,7264,
|
||||
7265,7266,7267,7268,7269,7270,7271,7272,7273,7274,7275,7276,7277,7278,7279,7280,
|
||||
7281,7282,7283,7284,7285,7286,7287,7288,7289,7290,7291,7292,7293,7294,7295,7296,
|
||||
7297,7298,7299,7300,7301,7302,7303,7304,7305,7306,7307,7308,7309,7310,7311,7312,
|
||||
7313,1718,7314,7315,7316,7317,7318,7319,7320,7321,7322,7323,7324,7325,7326,7327,
|
||||
7328,7329,7330,7331,7332,7333,7334,7335,7336,7337,7338,7339,7340,7341,7342,7343,
|
||||
7344,7345,7346,7347,7348,7349,7350,7351,7352,7353,7354,7355,7356,7357,7358,7359,
|
||||
7360,7361,7362,7363,7364,7365,7366,7367,7368,7369,7370,7371,7372,7373,7374,7375,
|
||||
7376,7377,7378,7379,7380,7381,7382,7383,7384,7385,7386,7387,7388,7389,7390,7391,
|
||||
7392,7393,7394,7395,7396,7397,7398,7399,7400,7401,7402,7403,7404,7405,7406,7407,
|
||||
7408,7409,7410,7411,7412,7413,7414,7415,7416,7417,7418,7419,7420,7421,7422,7423,
|
||||
7424,7425,7426,7427,7428,7429,7430,7431,7432,7433,7434,7435,7436,7437,7438,7439,
|
||||
7440,7441,7442,7443,7444,7445,7446,7447,7448,7449,7450,7451,7452,7453,7454,7455,
|
||||
7456,7457,7458,7459,7460,7461,7462,7463,7464,7465,7466,7467,7468,7469,7470,7471,
|
||||
7472,7473,7474,7475,7476,7477,7478,7479,7480,7481,7482,7483,7484,7485,7486,7487,
|
||||
7488,7489,7490,7491,7492,7493,7494,7495,7496,7497,7498,7499,7500,7501,7502,7503,
|
||||
7504,7505,7506,7507,7508,7509,7510,7511,7512,7513,7514,7515,7516,7517,7518,7519,
|
||||
7520,7521,7522,7523,7524,7525,7526,7527,7528,7529,7530,7531,7532,7533,7534,7535,
|
||||
7536,7537,7538,7539,7540,7541,7542,7543,7544,7545,7546,7547,7548,7549,7550,7551,
|
||||
7552,7553,7554,7555,7556,7557,7558,7559,7560,7561,7562,7563,7564,7565,7566,7567,
|
||||
7568,7569,7570,7571,7572,7573,7574,7575,7576,7577,7578,7579,7580,7581,7582,7583,
|
||||
7584,7585,7586,7587,7588,7589,7590,7591,7592,7593,7594,7595,7596,7597,7598,7599,
|
||||
7600,7601,7602,7603,7604,7605,7606,7607,7608,7609,7610,7611,7612,7613,7614,7615,
|
||||
7616,7617,7618,7619,7620,7621,7622,7623,7624,7625,7626,7627,7628,7629,7630,7631,
|
||||
7632,7633,7634,7635,7636,7637,7638,7639,7640,7641,7642,7643,7644,7645,7646,7647,
|
||||
7648,7649,7650,7651,7652,7653,7654,7655,7656,7657,7658,7659,7660,7661,7662,7663,
|
||||
7664,7665,7666,7667,7668,7669,7670,7671,7672,7673,7674,7675,7676,7677,7678,7679,
|
||||
7680,7681,7682,7683,7684,7685,7686,7687,7688,7689,7690,7691,7692,7693,7694,7695,
|
||||
7696,7697,7698,7699,7700,7701,7702,7703,7704,7705,7706,7707,7708,7709,7710,7711,
|
||||
7712,7713,7714,7715,7716,7717,7718,7719,7720,7721,7722,7723,7724,7725,7726,7727,
|
||||
7728,7729,7730,7731,7732,7733,7734,7735,7736,7737,7738,7739,7740,7741,7742,7743,
|
||||
7744,7745,7746,7747,7748,7749,7750,7751,7752,7753,7754,7755,7756,7757,7758,7759,
|
||||
7760,7761,7762,7763,7764,7765,7766,7767,7768,7769,7770,7771,7772,7773,7774,7775,
|
||||
7776,7777,7778,7779,7780,7781,7782,7783,7784,7785,7786,7787,7788,7789,7790,7791,
|
||||
7792,7793,7794,7795,7796,7797,7798,7799,7800,7801,7802,7803,7804,7805,7806,7807,
|
||||
7808,7809,7810,7811,7812,7813,7814,7815,7816,7817,7818,7819,7820,7821,7822,7823,
|
||||
7824,7825,7826,7827,7828,7829,7830,7831,7832,7833,7834,7835,7836,7837,7838,7839,
|
||||
7840,7841,7842,7843,7844,7845,7846,7847,7848,7849,7850,7851,7852,7853,7854,7855,
|
||||
7856,7857,7858,7859,7860,7861,7862,7863,7864,7865,7866,7867,7868,7869,7870,7871,
|
||||
7872,7873,7874,7875,7876,7877,7878,7879,7880,7881,7882,7883,7884,7885,7886,7887,
|
||||
7888,7889,7890,7891,7892,7893,7894,7895,7896,7897,7898,7899,7900,7901,7902,7903,
|
||||
7904,7905,7906,7907,7908,7909,7910,7911,7912,7913,7914,7915,7916,7917,7918,7919,
|
||||
7920,7921,7922,7923,7924,7925,7926,7927,7928,7929,7930,7931,7932,7933,7934,7935,
|
||||
7936,7937,7938,7939,7940,7941,7942,7943,7944,7945,7946,7947,7948,7949,7950,7951,
|
||||
7952,7953,7954,7955,7956,7957,7958,7959,7960,7961,7962,7963,7964,7965,7966,7967,
|
||||
7968,7969,7970,7971,7972,7973,7974,7975,7976,7977,7978,7979,7980,7981,7982,7983,
|
||||
7984,7985,7986,7987,7988,7989,7990,7991,7992,7993,7994,7995,7996,7997,7998,7999,
|
||||
8000,8001,8002,8003,8004,8005,8006,8007,8008,8009,8010,8011,8012,8013,8014,8015,
|
||||
8016,8017,8018,8019,8020,8021,8022,8023,8024,8025,8026,8027,8028,8029,8030,8031,
|
||||
8032,8033,8034,8035,8036,8037,8038,8039,8040,8041,8042,8043,8044,8045,8046,8047,
|
||||
8048,8049,8050,8051,8052,8053,8054,8055,8056,8057,8058,8059,8060,8061,8062,8063,
|
||||
8064,8065,8066,8067,8068,8069,8070,8071,8072,8073,8074,8075,8076,8077,8078,8079,
|
||||
8080,8081,8082,8083,8084,8085,8086,8087,8088,8089,8090,8091,8092,8093,8094,8095,
|
||||
8096,8097,8098,8099,8100,8101,8102,8103,8104,8105,8106,8107,8108,8109,8110,8111,
|
||||
8112,8113,8114,8115,8116,8117,8118,8119,8120,8121,8122,8123,8124,8125,8126,8127,
|
||||
8128,8129,8130,8131,8132,8133,8134,8135,8136,8137,8138,8139,8140,8141,8142,8143,
|
||||
8144,8145,8146,8147,8148,8149,8150,8151,8152,8153,8154,8155,8156,8157,8158,8159,
|
||||
8160,8161,8162,8163,8164,8165,8166,8167,8168,8169,8170,8171,8172,8173,8174,8175,
|
||||
8176,8177,8178,8179,8180,8181,8182,8183,8184,8185,8186,8187,8188,8189,8190,8191,
|
||||
8192,8193,8194,8195,8196,8197,8198,8199,8200,8201,8202,8203,8204,8205,8206,8207,
|
||||
8208,8209,8210,8211,8212,8213,8214,8215,8216,8217,8218,8219,8220,8221,8222,8223,
|
||||
8224,8225,8226,8227,8228,8229,8230,8231,8232,8233,8234,8235,8236,8237,8238,8239,
|
||||
8240,8241,8242,8243,8244,8245,8246,8247,8248,8249,8250,8251,8252,8253,8254,8255,
|
||||
8256,8257,8258,8259,8260,8261,8262,8263,8264,8265,8266,8267,8268,8269,8270,8271,
|
||||
8272,8273,8274,8275,8276,8277,8278,8279,8280,8281,8282,8283,8284,8285,8286,8287,
|
||||
8288,8289,8290,8291,8292,8293,8294,8295,8296,8297,8298,8299,8300,8301,8302,8303,
|
||||
8304,8305,8306,8307,8308,8309,8310,8311,8312,8313,8314,8315,8316,8317,8318,8319,
|
||||
8320,8321,8322,8323,8324,8325,8326,8327,8328,8329,8330,8331,8332,8333,8334,8335,
|
||||
8336,8337,8338,8339,8340,8341,8342,8343,8344,8345,8346,8347,8348,8349,8350,8351,
|
||||
8352,8353,8354,8355,8356,8357,8358,8359,8360,8361,8362,8363,8364,8365,8366,8367,
|
||||
8368,8369,8370,8371,8372,8373,8374,8375,8376,8377,8378,8379,8380,8381,8382,8383,
|
||||
8384,8385,8386,8387,8388,8389,8390,8391,8392,8393,8394,8395,8396,8397,8398,8399,
|
||||
8400,8401,8402,8403,8404,8405,8406,8407,8408,8409,8410,8411,8412,8413,8414,8415,
|
||||
8416,8417,8418,8419,8420,8421,8422,8423,8424,8425,8426,8427,8428,8429,8430,8431,
|
||||
8432,8433,8434,8435,8436,8437,8438,8439,8440,8441,8442,8443,8444,8445,8446,8447,
|
||||
8448,8449,8450,8451,8452,8453,8454,8455,8456,8457,8458,8459,8460,8461,8462,8463,
|
||||
8464,8465,8466,8467,8468,8469,8470,8471,8472,8473,8474,8475,8476,8477,8478,8479,
|
||||
8480,8481,8482,8483,8484,8485,8486,8487,8488,8489,8490,8491,8492,8493,8494,8495,
|
||||
8496,8497,8498,8499,8500,8501,8502,8503,8504,8505,8506,8507,8508,8509,8510,8511,
|
||||
8512,8513,8514,8515,8516,8517,8518,8519,8520,8521,8522,8523,8524,8525,8526,8527,
|
||||
8528,8529,8530,8531,8532,8533,8534,8535,8536,8537,8538,8539,8540,8541,8542,8543,
|
||||
8544,8545,8546,8547,8548,8549,8550,8551,8552,8553,8554,8555,8556,8557,8558,8559,
|
||||
8560,8561,8562,8563,8564,8565,8566,8567,8568,8569,8570,8571,8572,8573,8574,8575,
|
||||
8576,8577,8578,8579,8580,8581,8582,8583,8584,8585,8586,8587,8588,8589,8590,8591,
|
||||
8592,8593,8594,8595,8596,8597,8598,8599,8600,8601,8602,8603,8604,8605,8606,8607,
|
||||
8608,8609,8610,8611,8612,8613,8614,8615,8616,8617,8618,8619,8620,8621,8622,8623,
|
||||
8624,8625,8626,8627,8628,8629,8630,8631,8632,8633,8634,8635,8636,8637,8638,8639,
|
||||
8640,8641,8642,8643,8644,8645,8646,8647,8648,8649,8650,8651,8652,8653,8654,8655,
|
||||
8656,8657,8658,8659,8660,8661,8662,8663,8664,8665,8666,8667,8668,8669,8670,8671,
|
||||
8672,8673,8674,8675,8676,8677,8678,8679,8680,8681,8682,8683,8684,8685,8686,8687,
|
||||
8688,8689,8690,8691,8692,8693,8694,8695,8696,8697,8698,8699,8700,8701,8702,8703,
|
||||
8704,8705,8706,8707,8708,8709,8710,8711,8712,8713,8714,8715,8716,8717,8718,8719,
|
||||
8720,8721,8722,8723,8724,8725,8726,8727,8728,8729,8730,8731,8732,8733,8734,8735,
|
||||
8736,8737,8738,8739,8740,8741)
|
||||
|
||||
# flake8: noqa
|
||||
|
|
@ -0,0 +1,42 @@
|
|||
######################## BEGIN LICENSE BLOCK ########################
|
||||
# The Original Code is mozilla.org code.
|
||||
#
|
||||
# The Initial Developer of the Original Code is
|
||||
# Netscape Communications Corporation.
|
||||
# Portions created by the Initial Developer are Copyright (C) 1998
|
||||
# the Initial Developer. All Rights Reserved.
|
||||
#
|
||||
# Contributor(s):
|
||||
# Mark Pilgrim - port to Python
|
||||
#
|
||||
# This library is free software; you can redistribute it and/or
|
||||
# modify it under the terms of the GNU Lesser General Public
|
||||
# License as published by the Free Software Foundation; either
|
||||
# version 2.1 of the License, or (at your option) any later version.
|
||||
#
|
||||
# This library is distributed in the hope that it will be useful,
|
||||
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
|
||||
# Lesser General Public License for more details.
|
||||
#
|
||||
# You should have received a copy of the GNU Lesser General Public
|
||||
# License along with this library; if not, write to the Free Software
|
||||
# Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
|
||||
# 02110-1301 USA
|
||||
######################### END LICENSE BLOCK #########################
|
||||
|
||||
from .mbcharsetprober import MultiByteCharSetProber
|
||||
from .codingstatemachine import CodingStateMachine
|
||||
from .chardistribution import EUCKRDistributionAnalysis
|
||||
from .mbcssm import EUCKRSMModel
|
||||
|
||||
|
||||
class EUCKRProber(MultiByteCharSetProber):
|
||||
def __init__(self):
|
||||
MultiByteCharSetProber.__init__(self)
|
||||
self._mCodingSM = CodingStateMachine(EUCKRSMModel)
|
||||
self._mDistributionAnalyzer = EUCKRDistributionAnalysis()
|
||||
self.reset()
|
||||
|
||||
def get_charset_name(self):
|
||||
return "EUC-KR"
|
||||
Some files were not shown because too many files have changed in this diff Show more
Loading…
Add table
Add a link
Reference in a new issue