0x2620/openmedialibrary_platform
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity
openmedialibrary_platform/Darwin/lib/python3.5/_markupbase.py

396 lines
14 KiB
Python
Raw Normal View History

Open Media Library Platform
2013-10-11 17:28:32 +00:00
"""Shared support for scanning document type declarations in HTML and XHTML.
Switch to python3
2014-09-30 16:15:32 +00:00
This module is used as a foundation for the html.parser module. It has no
documented public API and should not be used directly.
Open Media Library Platform
2013-10-11 17:28:32 +00:00
"""
import re
_declname_match = re.compile(r'[a-zA-Z][-_.a-zA-Z0-9]*\s*').match
_declstringlit_match = re.compile(r'(\'[^\']*\'|"[^"]*")\s*').match
_commentclose = re.compile(r'--\s*>')
_markedsectionclose = re.compile(r']\s*]\s*>')
# An analysis of the MS-Word extensions is available at
# http://www.planetpublish.com/xmlarena/xap/Thursday/WordtoXML.pdf
_msmarkedsectionclose = re.compile(r']\s*>')
del re
class ParserBase:
"""Parser base class which provides some common support methods used
by the SGML/HTML and XHTML parsers."""
def __init__(self):
if self.__class__ is ParserBase:
raise RuntimeError(
Switch to python3
2014-09-30 16:15:32 +00:00
"_markupbase.ParserBase must be subclassed")
Open Media Library Platform
2013-10-11 17:28:32 +00:00
def error(self, message):
raise NotImplementedError(
"subclasses of ParserBase must override error()")
def reset(self):
self.lineno = 1
self.offset = 0
def getpos(self):
"""Return current line number and offset."""
return self.lineno, self.offset
# Internal -- update line number and offset. This should be
# called for each piece of data exactly once, in order -- in other
# words the concatenation of all the input strings to this
# function should be exactly the entire input.
def updatepos(self, i, j):
if i >= j:
return j
rawdata = self.rawdata
nlines = rawdata.count("\n", i, j)
if nlines:
self.lineno = self.lineno + nlines
pos = rawdata.rindex("\n", i, j) # Should not fail
self.offset = j-(pos+1)
else:
self.offset = self.offset + j-i
return j
_decl_otherchars = ''
# Internal -- parse declaration (for use by subclasses).
def parse_declaration(self, i):
# This is some sort of declaration; in "HTML as
# deployed," this should only be the document type
# declaration ("<!DOCTYPE html...>").
# ISO 8879:1986, however, has more complex
# declaration syntax for elements in <!...>, including:
# --comment--
# [marked section]
# name in the following list: ENTITY, DOCTYPE, ELEMENT,
# ATTLIST, NOTATION, SHORTREF, USEMAP,
# LINKTYPE, LINK, IDLINK, USELINK, SYSTEM
rawdata = self.rawdata
j = i + 2
assert rawdata[i:j] == "<!", "unexpected call to parse_declaration"
if rawdata[j:j+1] == ">":
# the empty comment <!>
return j + 1
if rawdata[j:j+1] in ("-", ""):
# Start of comment followed by buffer boundary,
# or just a buffer boundary.
return -1
# A simple, practical version could look like: ((name|stringlit) S*) + '>'
n = len(rawdata)
if rawdata[j:j+2] == '--': #comment
# Locate --.*-- as the body of the comment
return self.parse_comment(i)
elif rawdata[j] == '[': #marked section
# Locate [statusWord [...arbitrary SGML...]] as the body of the marked section
# Where statusWord is one of TEMP, CDATA, IGNORE, INCLUDE, RCDATA
# Note that this is extended by Microsoft Office "Save as Web" function
# to include [if...] and [endif].
return self.parse_marked_section(i)
else: #all other declaration elements
decltype, j = self._scan_name(j, i)
if j < 0:
return j
if decltype == "doctype":
self._decl_otherchars = ''
while j < n:
c = rawdata[j]
if c == ">":
# end of declaration syntax
data = rawdata[i+2:j]
if decltype == "doctype":
self.handle_decl(data)
else:
# According to the HTML5 specs sections "8.2.4.44 Bogus
# comment state" and "8.2.4.45 Markup declaration open
# state", a comment token should be emitted.
# Calling unknown_decl provides more flexibility though.
self.unknown_decl(data)
return j + 1
if c in "\"'":
m = _declstringlit_match(rawdata, j)
if not m:
return -1 # incomplete
j = m.end()
elif c in "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ":
name, j = self._scan_name(j, i)
elif c in self._decl_otherchars:
j = j + 1
elif c == "[":
# this could be handled in a separate doctype parser
if decltype == "doctype":
j = self._parse_doctype_subset(j + 1, i)
Switch to python3
2014-09-30 16:15:32 +00:00
elif decltype in {"attlist", "linktype", "link", "element"}:
Open Media Library Platform
2013-10-11 17:28:32 +00:00
# must tolerate []'d groups in a content model in an element declaration
# also in data attribute specifications of attlist declaration
# also link type declaration subsets in linktype declarations
# also link attribute specification lists in link declarations
self.error("unsupported '[' char in %s declaration" % decltype)
else:
self.error("unexpected '[' char in declaration")
else:
self.error(
"unexpected %r char in declaration" % rawdata[j])
if j < 0:
return j
return -1 # incomplete
# Internal -- parse a marked section
# Override this to handle MS-word extension syntax <![if word]>content<![endif]>
def parse_marked_section(self, i, report=1):
rawdata= self.rawdata
assert rawdata[i:i+3] == '<![', "unexpected call to parse_marked_section()"
sectName, j = self._scan_name( i+3, i )
if j < 0:
return j
Switch to python3
2014-09-30 16:15:32 +00:00
if sectName in {"temp", "cdata", "ignore", "include", "rcdata"}:
Open Media Library Platform
2013-10-11 17:28:32 +00:00
# look for standard ]]> ending
match= _markedsectionclose.search(rawdata, i+3)
Switch to python3
2014-09-30 16:15:32 +00:00
elif sectName in {"if", "else", "endif"}:
Open Media Library Platform
2013-10-11 17:28:32 +00:00
# look for MS Office ]> ending
match= _msmarkedsectionclose.search(rawdata, i+3)
else:
self.error('unknown status keyword %r in marked section' % rawdata[i+3:j])
if not match:
return -1
if report:
j = match.start(0)
self.unknown_decl(rawdata[i+3: j])
return match.end(0)
# Internal -- parse comment, return length or -1 if not terminated
def parse_comment(self, i, report=1):
rawdata = self.rawdata
if rawdata[i:i+4] != '<!--':
self.error('unexpected call to parse_comment()')
match = _commentclose.search(rawdata, i+4)
if not match:
return -1
if report:
j = match.start(0)
self.handle_comment(rawdata[i+4: j])
return match.end(0)
# Internal -- scan past the internal subset in a <!DOCTYPE declaration,
# returning the index just past any whitespace following the trailing ']'.
def _parse_doctype_subset(self, i, declstartpos):
rawdata = self.rawdata
n = len(rawdata)
j = i
while j < n:
c = rawdata[j]
if c == "<":
s = rawdata[j:j+2]
if s == "<":
# end of buffer; incomplete
return -1
if s != "<!":
self.updatepos(declstartpos, j + 1)
self.error("unexpected char in internal subset (in %r)" % s)
if (j + 2) == n:
# end of buffer; incomplete
return -1
if (j + 4) > n:
# end of buffer; incomplete
return -1
if rawdata[j:j+4] == "<!--":
j = self.parse_comment(j, report=0)
if j < 0:
return j
continue
name, j = self._scan_name(j + 2, declstartpos)
if j == -1:
return -1
Switch to python3
2014-09-30 16:15:32 +00:00
if name not in {"attlist", "element", "entity", "notation"}:
Open Media Library Platform
2013-10-11 17:28:32 +00:00
self.updatepos(declstartpos, j + 2)
self.error(
"unknown declaration %r in internal subset" % name)
# handle the individual names
meth = getattr(self, "_parse_doctype_" + name)
j = meth(j, declstartpos)
if j < 0:
return j
elif c == "%":
# parameter entity reference
if (j + 1) == n:
# end of buffer; incomplete
return -1
s, j = self._scan_name(j + 1, declstartpos)
if j < 0:
return j
if rawdata[j] == ";":
j = j + 1
elif c == "]":
j = j + 1
while j < n and rawdata[j].isspace():
j = j + 1
if j < n:
if rawdata[j] == ">":
return j
self.updatepos(declstartpos, j)
self.error("unexpected char after internal subset")
else:
return -1
elif c.isspace():
j = j + 1
else:
self.updatepos(declstartpos, j)
self.error("unexpected char %r in internal subset" % c)
# end of buffer reached
return -1
# Internal -- scan past <!ELEMENT declarations
def _parse_doctype_element(self, i, declstartpos):
name, j = self._scan_name(i, declstartpos)
if j == -1:
return -1
# style content model; just skip until '>'
rawdata = self.rawdata
if '>' in rawdata[j:]:
return rawdata.find(">", j) + 1
return -1
# Internal -- scan past <!ATTLIST declarations
def _parse_doctype_attlist(self, i, declstartpos):
rawdata = self.rawdata
name, j = self._scan_name(i, declstartpos)
c = rawdata[j:j+1]
if c == "":
return -1
if c == ">":
return j + 1
while 1:
# scan a series of attribute descriptions; simplified:
# name type [value] [#constraint]
name, j = self._scan_name(j, declstartpos)
if j < 0:
return j
c = rawdata[j:j+1]
if c == "":
return -1
if c == "(":
# an enumerated type; look for ')'
if ")" in rawdata[j:]:
j = rawdata.find(")", j) + 1
else:
return -1
while rawdata[j:j+1].isspace():
j = j + 1
if not rawdata[j:]:
# end of buffer, incomplete
return -1
else:
name, j = self._scan_name(j, declstartpos)
c = rawdata[j:j+1]
if not c:
return -1
if c in "'\"":
m = _declstringlit_match(rawdata, j)
if m:
j = m.end()
else:
return -1
c = rawdata[j:j+1]
if not c:
return -1
if c == "#":
if rawdata[j:] == "#":
# end of buffer
return -1
name, j = self._scan_name(j + 1, declstartpos)
if j < 0:
return j
c = rawdata[j:j+1]
if not c:
return -1
if c == '>':
# all done
return j + 1
# Internal -- scan past <!NOTATION declarations
def _parse_doctype_notation(self, i, declstartpos):
name, j = self._scan_name(i, declstartpos)
if j < 0:
return j
rawdata = self.rawdata
while 1:
c = rawdata[j:j+1]
if not c:
# end of buffer; incomplete
return -1
if c == '>':
return j + 1
if c in "'\"":
m = _declstringlit_match(rawdata, j)
if not m:
return -1
j = m.end()
else:
name, j = self._scan_name(j, declstartpos)
if j < 0:
return j
# Internal -- scan past <!ENTITY declarations
def _parse_doctype_entity(self, i, declstartpos):
rawdata = self.rawdata
if rawdata[i:i+1] == "%":
j = i + 1
while 1:
c = rawdata[j:j+1]
if not c:
return -1
if c.isspace():
j = j + 1
else:
break
else:
j = i
name, j = self._scan_name(j, declstartpos)
if j < 0:
return j
while 1:
c = self.rawdata[j:j+1]
if not c:
return -1
if c in "'\"":
m = _declstringlit_match(rawdata, j)
if m:
j = m.end()
else:
return -1 # incomplete
elif c == ">":
return j + 1
else:
name, j = self._scan_name(j, declstartpos)
if j < 0:
return j
# Internal -- scan a name token and the new position and the token, or
# return -1 if we've reached the end of the buffer.
def _scan_name(self, i, declstartpos):
rawdata = self.rawdata
n = len(rawdata)
if i == n:
return None, -1
m = _declname_match(rawdata, i)
if m:
s = m.group()
name = s.strip()
if (i + len(s)) == n:
return None, -1 # end of buffer
return name.lower(), m.end()
else:
self.updatepos(declstartpos, i)
self.error("expected name token at %r"
% rawdata[declstartpos:declstartpos+20])
# To be overridden -- handlers for unknown objects
def unknown_decl(self, data):
pass
Reference in a new issue Copy permalink