rebuild for 10.11+

This commit is contained in:
j 2019-01-10 14:33:55 +05:30
commit 901b731582
234 changed files with 1522 additions and 927 deletions

Binary file not shown.

View file

@ -1,3 +1,5 @@
# cython: language_level=2
#
# ElementTree
# $Id: ElementPath.py 3375 2008-02-13 08:05:08Z fredrik $
@ -53,6 +55,8 @@
# you, if needed.
##
from __future__ import absolute_import
import re
xpath_tokenizer_re = re.compile(

Binary file not shown.

View file

@ -1,3 +1,5 @@
# cython: language_level=2
#
# Element generator factory by Fredrik Lundh.
#
@ -37,6 +39,8 @@
The ``E`` Element factory for generating XML documents.
"""
from __future__ import absolute_import
import lxml.etree as ET
from functools import partial

View file

@ -209,13 +209,12 @@ class LXMLOutputChecker(OutputChecker):
else:
return value
html = parser is html_fromstring
diff_parts = []
diff_parts.append('Expected:')
diff_parts.append(self.format_doc(want_doc, html, 2))
diff_parts.append('Got:')
diff_parts.append(self.format_doc(got_doc, html, 2))
diff_parts.append('Diff:')
diff_parts.append(self.collect_diff(want_doc, got_doc, html, 2))
diff_parts = ['Expected:',
self.format_doc(want_doc, html, 2),
'Got:',
self.format_doc(got_doc, html, 2),
'Diff:',
self.collect_diff(want_doc, got_doc, html, 2)]
return '\n'.join(diff_parts)
def html_empty_tag(self, el, html=True):

Binary file not shown.

View file

@ -1,4 +1,4 @@
/* Generated by Cython 0.28.5 */
/* Generated by Cython 0.29.2 */
#ifndef __PYX_HAVE__lxml__etree
#define __PYX_HAVE__lxml__etree
@ -12,7 +12,7 @@ struct LxmlElementBase;
struct LxmlElementClassLookup;
struct LxmlFallbackElementClassLookup;
/* "lxml/etree.pyx":320
/* "lxml/etree.pyx":318
*
* # type of a function that steps from node to node
* ctypedef public xmlNode* (*_node_to_node_function)(xmlNode*) # <<<<<<<<<<<<<<
@ -21,7 +21,7 @@ struct LxmlFallbackElementClassLookup;
*/
typedef xmlNode *(*_node_to_node_function)(xmlNode *);
/* "lxml/etree.pyx":336
/* "lxml/etree.pyx":334
* @cython.final
* @cython.freelist(8)
* cdef public class _Document [ type LxmlDocumentType, object LxmlDocument ]: # <<<<<<<<<<<<<<
@ -37,7 +37,7 @@ struct LxmlDocument {
struct __pyx_obj_4lxml_5etree__BaseParser *_parser;
};
/* "lxml/etree.pyx":685
/* "lxml/etree.pyx":683
*
* @cython.no_gc_clear
* cdef public class _Element [ type LxmlElementType, object LxmlElement ]: # <<<<<<<<<<<<<<
@ -51,7 +51,7 @@ struct LxmlElement {
PyObject *_tag;
};
/* "lxml/etree.pyx":1849
/* "lxml/etree.pyx":1847
*
*
* cdef public class _ElementTree [ type LxmlElementTreeType, # <<<<<<<<<<<<<<
@ -65,7 +65,7 @@ struct LxmlElementTree {
struct LxmlElement *_context_node;
};
/* "lxml/etree.pyx":2576
/* "lxml/etree.pyx":2574
*
*
* cdef public class _ElementTagMatcher [ object LxmlElementTagMatcher, # <<<<<<<<<<<<<<
@ -81,7 +81,7 @@ struct LxmlElementTagMatcher {
char *_name;
};
/* "lxml/etree.pyx":2607
/* "lxml/etree.pyx":2605
* self._name = NULL
*
* cdef public class _ElementIterator(_ElementTagMatcher) [ # <<<<<<<<<<<<<<

View file

@ -1,7 +1,10 @@
/* Generated by Cython 0.28.5 */
/* Generated by Cython 0.29.2 */
#ifndef __PYX_HAVE_API__lxml__etree
#define __PYX_HAVE_API__lxml__etree
#ifdef __MINGW64__
#define MS_WIN64
#endif
#include "Python.h"
#include "etree.h"
@ -103,23 +106,6 @@ static xmlNs *(*__pyx_api_f_4lxml_5etree_findOrBuildNodeNsPrefix)(struct LxmlDoc
#endif
#endif
#ifndef __PYX_HAVE_RT_ImportModule
#define __PYX_HAVE_RT_ImportModule
static PyObject *__Pyx_ImportModule(const char *name) {
PyObject *py_name = 0;
PyObject *py_module = 0;
py_name = __Pyx_PyIdentifier_FromString(name);
if (!py_name)
goto bad;
py_module = PyImport_Import(py_name);
Py_DECREF(py_name);
return py_module;
bad:
Py_XDECREF(py_name);
return 0;
}
#endif
#ifndef __PYX_HAVE_RT_ImportFunction
#define __PYX_HAVE_RT_ImportFunction
static int __Pyx_ImportFunction(PyObject *module, const char *funcname, void (**f)(void), const char *sig) {
@ -176,7 +162,7 @@ bad:
static int import_lxml__etree(void) {
PyObject *module = 0;
module = __Pyx_ImportModule("lxml.etree");
module = PyImport_ImportModule("lxml.etree");
if (!module) goto bad;
if (__Pyx_ImportFunction(module, "deepcopyNodeToDocument", (void (**)(void))&__pyx_api_f_4lxml_5etree_deepcopyNodeToDocument, "struct LxmlElement *(struct LxmlDocument *, xmlNode *)") < 0) goto bad;
if (__Pyx_ImportFunction(module, "elementTreeFactory", (void (**)(void))&__pyx_api_f_4lxml_5etree_elementTreeFactory, "struct LxmlElementTree *(struct LxmlElement *)") < 0) goto bad;

View file

@ -46,7 +46,6 @@ import re
from functools import partial
try:
# while unnecessary, importing from 'collections.abc' is the right way to do it
from collections.abc import MutableMapping, MutableSet
except ImportError:
from collections import MutableMapping, MutableSet

View file

@ -1,4 +1,8 @@
from collections import MutableSet
try:
from collections.abc import MutableSet
except ImportError:
from collections import MutableSet
class SetMixin(MutableSet):

Binary file not shown.

View file

@ -1,9 +1,13 @@
# cython: language_level=2
"""A cleanup tool for HTML.
Removes unwanted tags and content. See the `Cleaner` class for
details.
"""
from __future__ import absolute_import
import re
import copy
try:
@ -27,11 +31,6 @@ try:
except NameError:
# Python 3
unicode = str
try:
bytes
except NameError:
# Python < 2.6
bytes = str
try:
basestring
except NameError:
@ -213,7 +212,7 @@ class Cleaner(object):
safe_attrs = defs.safe_attrs
add_nofollow = False
host_whitelist = ()
whitelist_tags = set(['iframe', 'embed'])
whitelist_tags = {'iframe', 'embed'}
def __init__(self, **kw):
for name, value in kw.items():

Binary file not shown.

View file

@ -1,3 +1,7 @@
# cython: language_level=3
from __future__ import absolute_import
import difflib
from lxml import etree
from lxml.html import fragment_fromstring
@ -621,7 +625,7 @@ def fixup_chunks(chunks):
% (cur_word, result, chunk, chunks))
cur_word.post_tags.append(chunk)
else:
assert(0)
assert False
if not result:
return [token('', pre_tags=tag_accum)]
@ -799,7 +803,6 @@ def _move_el_inside_block(el, tag):
if _contains_block_level_tag(child):
break
else:
import sys
# No block-level tags in any child
children_tag = etree.Element(tag)
children_tag.text = el.text

View file

@ -6,8 +6,8 @@
#ifndef PY_VERSION_HEX
# error the development package of Python (header files etc.) is not installed correctly
#else
# if PY_VERSION_HEX < 0x02060000 || PY_MAJOR_VERSION >= 3 && PY_VERSION_HEX < 0x03020000
# error this version of lxml requires Python 2.6, 2.7, 3.2 or later
# if PY_VERSION_HEX < 0x02070000 || PY_MAJOR_VERSION >= 3 && PY_VERSION_HEX < 0x03030000
# error this version of lxml requires Python 2.7, 3.3 or later
# endif
#endif
@ -262,8 +262,6 @@ long _ftol2( double dblSource ) { return _ftol( dblSource ); }
(((c_node)->ns == 0) ? 0 : ((c_node)->ns->href))
/* PyCapsule was added in Py2.7 */
#if PY_VERSION_HEX >= 0x02070000
#include "string.h"
static void* lxml_unpack_xmldoc_capsule(PyObject* capsule, int* is_owned) {
xmlDoc *c_doc;
@ -301,9 +299,6 @@ static void* lxml_unpack_xmldoc_capsule(PyObject* capsule, int* is_owned) {
}
return c_doc;
}
#else
# define lxml_unpack_xmldoc_capsule(capsule, is_owned) ((((void)capsule, 0) || ((void)is_owned, 0)) ? NULL : NULL)
#endif
/* Macro pair implementation of a depth first tree walker
*

View file

@ -17,7 +17,6 @@
#include <libxml/xmlversion.h>
#include <libxml/parser.h>
#include <libxml/xmlerror.h>
#include <libxml/SAX.h>
#include <libxml/SAX2.h>
#include <libxml/xmlmemory.h>

View file

@ -575,7 +575,7 @@ struct _xmlDoc {
void *ids; /* Hash table for ID attributes if any */
void *refs; /* Hash table for IDREFs attributes if any */
const xmlChar *URL; /* The URI for that document */
int charset; /* encoding of the in-memory content
int charset; /* Internal flag for charset handling,
actually an xmlCharEncoding */
struct _xmlDict *dict; /* dict used to allocate names or NULL */
void *psvi; /* for type/PSVI informations */

View file

@ -131,8 +131,8 @@
#endif
#endif
/* Cygwin platform, GNU compiler */
#if defined(_WIN32) && defined(__CYGWIN__)
/* Cygwin platform (does not define _WIN32), GNU compiler */
#if defined(__CYGWIN__)
#undef XMLPUBFUN
#undef XMLPUBVAR
#undef XMLCALL
@ -145,7 +145,7 @@
#if !defined(LIBXML_STATIC)
#define XMLPUBVAR __declspec(dllimport) extern
#else
#define XMLPUBVAR
#define XMLPUBVAR extern
#endif
#endif
#define XMLCALL __cdecl

View file

@ -29,21 +29,21 @@ XMLPUBFUN void XMLCALL xmlCheckVersion(int version);
*
* the version string like "1.2.3"
*/
#define LIBXML_DOTTED_VERSION "2.9.8"
#define LIBXML_DOTTED_VERSION "2.9.9"
/**
* LIBXML_VERSION:
*
* the version number: 1.2.3 value is 10203
*/
#define LIBXML_VERSION 20908
#define LIBXML_VERSION 20909
/**
* LIBXML_VERSION_STRING:
*
* the version number string, 1.2.3 value is "10203"
*/
#define LIBXML_VERSION_STRING "20908"
#define LIBXML_VERSION_STRING "20909"
/**
* LIBXML_VERSION_EXTRA:
@ -58,7 +58,7 @@ XMLPUBFUN void XMLCALL xmlCheckVersion(int version);
* Macro to check that the libxml version in use is compatible with
* the version the software has been compiled against
*/
#define LIBXML_TEST_VERSION xmlCheckVersion(20908);
#define LIBXML_TEST_VERSION xmlCheckVersion(20909);
#ifndef VMS
#if 0

View file

@ -1,3 +1,3 @@
#ifndef LXML_VERSION_STRING
#define LXML_VERSION_STRING "4.2.5"
#define LXML_VERSION_STRING "4.3.0"
#endif

View file

@ -63,8 +63,8 @@ svrl_validation_errors = _etree.XPath(
# RelaxNG validator for schematron schemas
schematron_schema_valid = _etree.RelaxNG(_etree.parse(
os.path.join(_resources_dir, 'rng', 'iso-schematron.rng')))
schematron_schema_valid = _etree.RelaxNG(
file=os.path.join(_resources_dir, 'rng', 'iso-schematron.rng'))
def stylesheet_params(**kwargs):

View file

@ -1,9 +1,29 @@
<?xml version="1.0" encoding="UTF-8"?>
<!-- Copyright © ISO/IEC 2015 -->
<!--
(c) International Organization for Standardization 2005.
Permission to copy in any form is granted for use with conforming
SGML systems and applications as defined in ISO 8879,
provided this notice is included in all copies.
The following permission notice and disclaimer shall be included in all
copies of this XML schema ("the Schema"), and derivations of the Schema:
Permission is hereby granted, free of charge in perpetuity, to any
person obtaining a copy of the Schema, to use, copy, modify, merge and
distribute free of charge, copies of the Schema for the purposes of
developing, implementing, installing and using software based on the
Schema, and to permit persons to whom the Schema is furnished to do so,
subject to the following conditions:
THE SCHEMA IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
ARISING FROM, OUT OF OR IN CONNECTION WITH THE SCHEMA OR THE USE OR
OTHER DEALINGS IN THE SCHEMA.
In addition, any modified copy of the Schema shall include the following
notice:
"THIS SCHEMA HAS BEEN MODIFIED FROM THE SCHEMA DEFINED IN ISO/IEC 19757-3,
AND SHOULD NOT BE INTERPRETED AS COMPLYING WITH THAT STANDARD".
-->
<grammar ns="http://purl.oclc.org/dsdl/schematron" xmlns="http://relaxng.org/ns/structure/1.0" datatypeLibrary="http://www.w3.org/2001/XMLSchema-datatypes">
<start>
@ -63,6 +83,10 @@
<optional>
<ref name="diagnostics"/>
</optional>
<optional>
<!-- edited (lxml): required in standard, optional here (since it can be empty anyway) -->
<ref name="properties"/>
</optional>
</group>
</interleave>
</element>
@ -105,6 +129,11 @@
<data type="IDREFS"/>
</attribute>
</optional>
<optional>
<attribute name="properties">
<data type="IDREFS"/>
</attribute>
</optional>
<ref name="rich"/>
<ref name="linkable"/>
<interleave>
@ -178,9 +207,14 @@
</define>
<define name="extends">
<element name="extends">
<attribute name="rule">
<data type="IDREF"/>
</attribute>
<choice>
<attribute name="rule">
<data type="IDREF"/>
</attribute>
<attribute name="href">
<ref name="uriValue"/>
</attribute>
</choice>
<ref name="foreign-empty"/>
</element>
</define>
@ -189,9 +223,14 @@
<attribute name="name">
<ref name="nameValue"/>
</attribute>
<attribute name="value">
<data type="string" datatypeLibrary=""/>
</attribute>
<choice>
<attribute name="value">
<data type="string" datatypeLibrary=""/>
</attribute>
<oneOrMore>
<ref name="foreign-element"/>
</oneOrMore>
</choice>
</element>
</define>
<define name="name">
@ -257,6 +296,11 @@
</define>
<define name="pattern">
<element name="pattern">
<optional>
<attribute name="documents">
<ref name="pathValue"/>
</attribute>
</optional>
<ref name="rich"/>
<interleave>
<ref name="foreign"/>
@ -367,6 +411,41 @@
</interleave>
</element>
</define>
<define name="properties">
<element name="properties">
<zeroOrMore>
<ref name="property"/>
</zeroOrMore>
</element>
</define>
<define name="property">
<element name="property">
<attribute name="id">
<data type="ID"/>
</attribute>
<optional>
<attribute name="role">
<ref name="roleValue"/>
</attribute>
</optional>
<optional>
<attribute name="scheme"/>
</optional>
<interleave>
<ref name="foreign"/>
<zeroOrMore>
<choice>
<text/>
<ref name="name"/>
<ref name="value-of"/>
<ref name="emph"/>
<ref name="dir"/>
<ref name="span"/>
</choice>
</zeroOrMore>
</interleave>
</element>
</define>
<define name="report">
<element name="report">
<attribute name="test">
@ -387,6 +466,11 @@
<data type="IDREFS"/>
</attribute>
</optional>
<optional>
<attribute name="properties">
<data type="IDREFS"/>
</attribute>
</optional>
<ref name="rich"/>
<ref name="linkable"/>
<interleave>
@ -434,6 +518,7 @@
<ref name="assert"/>
<ref name="report"/>
<ref name="extends"/>
<ref name="p"/>
</choice>
</oneOrMore>
</group>
@ -459,6 +544,7 @@
<ref name="assert"/>
<ref name="report"/>
<ref name="extends"/>
<ref name="p"/>
</choice>
</oneOrMore>
</group>
@ -501,6 +587,7 @@
<attribute name="href">
<ref name="uriValue"/>
</attribute>
<ref name="foreign-empty"/>
</element>
</define>
<define name="rich">

View file

@ -6,10 +6,11 @@
This is a preprocessor for ISO Schematron, which implements abstract patterns.
It also
* extracts a particular schema using an ID, where there are multiple
schemas, such as when they are embedded in the same NVDL script
* experimentally, allows parameter recognition and substitution inside
text as well as @context, @test, & @select.
schemas, such as when they are embedded in the same NVDL script
* allows parameter substitution inside @context, @test, @select, @path
* experimentally, allows parameter recognition and substitution inside
text (NOTE: to be removed, for compataibility with other implementations,
please do not use this)
This should be used after iso-dsdl-include.xsl and before the skeleton or
meta-stylesheet (e.g. iso-svrl.xsl) . It only requires XSLT 1.
@ -17,8 +18,45 @@
Each kind of inclusion can be turned off (or on) on the command line.
-->
<!--
VERSION INFORMATION
<!--
Open Source Initiative OSI - The MIT License:Licensing
[OSI Approved License]
This source code was previously available under the zlib/libpng license.
Attribution is polite.
The MIT License
Copyright (c) 2004-2010 Rick Jellife and Academia Sinica Computing Centre, Taiwan
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in
all copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
THE SOFTWARE.
-->
<!--
VERSION INFORMATION
2013-09-19 RJ
* Allow macro expansion in @path attributes, eg. for sch:name/@path
2010-07-10 RJ
* Move to MIT license
2008-09-18 RJ
* move out param test from iso:schema template to work with XSLT 1. (Noah Fontes)
@ -40,35 +78,11 @@
* Original written for old namespace
* http://www.topologi.com/resources/iso-pre-pro.xsl
-->
<!--
LEGAL INFORMATION
Copyright (c) 2000-2008 Rick Jelliffe and Academia Sinica Computing Center, Taiwan
This software is provided 'as-is', without any express or implied warranty.
In no event will the authors be held liable for any damages arising from
the use of this software.
Permission is granted to anyone to use this software for any purpose,
including commercial applications, and to alter it and redistribute it freely,
subject to the following restrictions:
1. The origin of this software must not be misrepresented; you must not claim
that you wrote the original software. If you use this software in a product,
an acknowledgment in the product documentation would be appreciated but is
not required.
2. Altered source versions must be plainly marked as such, and must not be
misrepresented as being the original software.
3. This notice may not be removed or altered from any source distribution.
-->
<xslt:stylesheet version="1.0" xmlns:xslt="http://www.w3.org/1999/XSL/Transform"
xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
xmlns:iso="http://purl.oclc.org/dsdl/schematron"
xmlns:nvdl="http://purl.oclc.org/dsdl/nvdl"
xmlns:iae="http://www.schematron.com/namespace/iae"
>
@ -231,7 +245,7 @@
<xslt:template mode="iae:do-pattern" match="*">
<xslt:param name="caller"/>
<xslt:copy>
<xslt:for-each select="@*[name()='test' or name()='context' or name()='select']">
<xslt:for-each select="@*[name()='test' or name()='context' or name()='select' or name()='path' ]">
<xslt:attribute name="{name()}">
<xslt:call-template name="iae:macro-expand">
<xslt:with-param name="text"><xslt:value-of select="."/></xslt:with-param>
@ -239,12 +253,13 @@
</xslt:call-template>
</xslt:attribute>
</xslt:for-each>
<xslt:copy-of select="@*[name()!='test'][name()!='context'][name()!='select']" />
<xslt:copy-of select="@*[name()!='test'][name()!='context'][name()!='select'][name()!='path']" />
<xsl:for-each select="node()">
<xsl:choose>
<!-- Experiment: replace macros in text as well, to allow parameterized assertions
and so on, without having to have spurious <iso:value-of> calls and multiple
delimiting -->
delimiting.
NOTE: THIS FUNCTIONALITY WILL BE REMOVED IN THE FUTURE -->
<xsl:when test="self::text()">
<xslt:call-template name="iae:macro-expand">
<xslt:with-param name="text"><xslt:value-of select="."/></xslt:with-param>
@ -293,4 +308,6 @@
</xsl:choose>
</xslt:template>
</xslt:stylesheet>

View file

@ -1,83 +1,84 @@
ISO SCHEMATRON 2009
XSLT implementation by Rick Jelliffe with assistance from members of Schematron-love-in maillist.
2009-03-18
Two distributions are available. One is for XSLT1 engines.
The other is for XSLT2 engines, such as SAXON 9.
This version of Schematron splits the process into a pipeline of several different XSLT stages.
1) First, preprocess your Schematron schema with iso_dsdl_include.xsl.
This is a macro processor to assemble the schema from various parts.
If your schema is not in separate parts, you can skip this stage.
2) Second, preprocess the output from stage 1 with iso_abstract_expand.xsl.
This is a macro processor to convert abstract patterns to real patterns.
If your schema does not use abstract patterns, you can skip this
stage.
3) Third, compile the Schematron schema into an XSLT script.
This will typically use iso_svrl_for_xslt1.xsl or iso_svrl_for_xslt2.xsl
(which in turn invoke iso_schematron_skeleton_for_xslt1.xsl or iso_schematron_skeleton_for_saxon.xsl)
However, other "meta-styleseets" are also in common use; the principle of operation is the same.
If your schema uses Schematron phases, supply these as command line/invocation parameters
to this process.
4) Fourth, run the script generated by stage 3 against the document being validated.
If you are using the SVRL script, then the output of validation will be an XML document.
If your schema uses Schematron parameters, supply these as command line/invocation parameters
to this process.
The XSLT2 distribution also features several next generation features,
such as validating multiple documents. See the source code for details.
Schematron assertions can be written in any language, of course; the file
sch-messages-en.xhtml contains the diagnostics messages from the XSLT2 skeleton
in English, and this can be used as template to localize the skeleton's
error messages. Note that typically programming errors in Schematron are XPath
errors, which requires localized messages from the XSLT engine.
ANT
---
To give an example of how to process a document, here is a sample ANT task.
<target name="schematron-compile-test" >
<!-- expand inclusions -->
<xslt basedir="test/schematron"
style="iso_dsdl_include.xsl" in="test.sch" out="test1.sch">
<classpath>
<pathelement location="${lib.dir}/saxon9.jar"/>
</classpath>
</xslt>
<!-- expand abstract patterns -->
<xslt basedir="test/schematron"
style="iso_abstract_expand.xsl" in="test1.sch" out="test2.sch">
<classpath>
<pathelement location="${lib.dir}/saxon9.jar"/>
</classpath>
</xslt>
<!-- compile it -->
<xslt basedir="test/schematron"
style="iso_svrl_for_xslt2.xsl" in="test2.sch" out="test.xsl">
<classpath>
<pathelement location="${lib.dir}/saxon9.jar"/>
</classpath>
</xslt>
<!-- validate -->
<xslt basedir="test/schematron"
style="test.xsl" in="instance.xml" out="instance.svrlt">
<classpath>
<pathelement location="${lib.dir}/saxon9.jar"/>
</classpath>
</xslt>
</target>
ISO SCHEMATRON 2010
XSLT implementation by Rick Jelliffe with assistance from members of Schematron-love-in maillist.
2010-04-21
Two distributions are available. One is for XSLT1 engines.
The other is for XSLT2 engines, such as SAXON 9.
This version of Schematron splits the process into a pipeline of several different XSLT stages.
1) First, preprocess your Schematron schema with iso_dsdl_include.xsl.
This is a macro processor to assemble the schema from various parts.
If your schema is not in separate parts, you can skip this stage.
This stage also generates error messages for some common XPath syntax problems.
2) Second, preprocess the output from stage 1 with iso_abstract_expand.xsl.
This is a macro processor to convert abstract patterns to real patterns.
If your schema does not use abstract patterns, you can skip this
stage.
3) Third, compile the Schematron schema into an XSLT script.
This will typically use iso_svrl_for_xslt1.xsl or iso_svrl_for_xslt2.xsl
(which in turn invoke iso_schematron_skeleton_for_xslt1.xsl or iso_schematron_skeleton_for_saxon.xsl)
However, other "meta-stylesheets" are also in common use; the principle of operation is the same.
If your schema uses Schematron phases, supply these as command line/invocation parameters
to this process.
4) Fourth, run the script generated by stage 3 against the document being validated.
If you are using the SVRL script, then the output of validation will be an XML document.
If your schema uses Schematron parameters, supply these as command line/invocation parameters
to this process.
The XSLT2 distribution also features several next generation features,
such as validating multiple documents. See the source code for details.
Schematron assertions can be written in any language, of course; the file
sch-messages-en.xhtml contains the diagnostics messages from the XSLT2 skeleton
in English, and this can be used as template to localize the skeleton's
error messages. Note that typically programming errors in Schematron are XPath
errors, which requires localized messages from the XSLT engine.
ANT
---
To give an example of how to process a document, here is a sample ANT task.
<target name="schematron-compile-test" >
<!-- expand inclusions -->
<xslt basedir="test/schematron"
style="iso_dsdl_include.xsl" in="test.sch" out="test1.sch">
<classpath>
<pathelement location="${lib.dir}/saxon9.jar"/>
</classpath>
</xslt>
<!-- expand abstract patterns -->
<xslt basedir="test/schematron"
style="iso_abstract_expand.xsl" in="test1.sch" out="test2.sch">
<classpath>
<pathelement location="${lib.dir}/saxon9.jar"/>
</classpath>
</xslt>
<!-- compile it -->
<xslt basedir="test/schematron"
style="iso_svrl_for_xslt2.xsl" in="test2.sch" out="test.xsl">
<classpath>
<pathelement location="${lib.dir}/saxon9.jar"/>
</classpath>
</xslt>
<!-- validate -->
<xslt basedir="test/schematron"
style="test.xsl" in="instance.xml" out="instance.svrlt">
<classpath>
<pathelement location="${lib.dir}/saxon9.jar"/>
</classpath>
</xslt>
</target>

View file

@ -1,4 +1,4 @@
/* Generated by Cython 0.28.5 */
/* Generated by Cython 0.29.2 */
#ifndef __PYX_HAVE__lxml__etree
#define __PYX_HAVE__lxml__etree
@ -12,7 +12,7 @@ struct LxmlElementBase;
struct LxmlElementClassLookup;
struct LxmlFallbackElementClassLookup;
/* "lxml/etree.pyx":320
/* "lxml/etree.pyx":318
*
* # type of a function that steps from node to node
* ctypedef public xmlNode* (*_node_to_node_function)(xmlNode*) # <<<<<<<<<<<<<<
@ -21,7 +21,7 @@ struct LxmlFallbackElementClassLookup;
*/
typedef xmlNode *(*_node_to_node_function)(xmlNode *);
/* "lxml/etree.pyx":336
/* "lxml/etree.pyx":334
* @cython.final
* @cython.freelist(8)
* cdef public class _Document [ type LxmlDocumentType, object LxmlDocument ]: # <<<<<<<<<<<<<<
@ -37,7 +37,7 @@ struct LxmlDocument {
struct __pyx_obj_4lxml_5etree__BaseParser *_parser;
};
/* "lxml/etree.pyx":685
/* "lxml/etree.pyx":683
*
* @cython.no_gc_clear
* cdef public class _Element [ type LxmlElementType, object LxmlElement ]: # <<<<<<<<<<<<<<
@ -51,7 +51,7 @@ struct LxmlElement {
PyObject *_tag;
};
/* "lxml/etree.pyx":1849
/* "lxml/etree.pyx":1847
*
*
* cdef public class _ElementTree [ type LxmlElementTreeType, # <<<<<<<<<<<<<<
@ -65,7 +65,7 @@ struct LxmlElementTree {
struct LxmlElement *_context_node;
};
/* "lxml/etree.pyx":2576
/* "lxml/etree.pyx":2574
*
*
* cdef public class _ElementTagMatcher [ object LxmlElementTagMatcher, # <<<<<<<<<<<<<<
@ -81,7 +81,7 @@ struct LxmlElementTagMatcher {
char *_name;
};
/* "lxml/etree.pyx":2607
/* "lxml/etree.pyx":2605
* self._name = NULL
*
* cdef public class _ElementIterator(_ElementTagMatcher) [ # <<<<<<<<<<<<<<

View file

@ -1,7 +1,10 @@
/* Generated by Cython 0.28.5 */
/* Generated by Cython 0.29.2 */
#ifndef __PYX_HAVE_API__lxml__etree
#define __PYX_HAVE_API__lxml__etree
#ifdef __MINGW64__
#define MS_WIN64
#endif
#include "Python.h"
#include "lxml.etree.h"
@ -103,23 +106,6 @@ static xmlNs *(*__pyx_api_f_4lxml_5etree_findOrBuildNodeNsPrefix)(struct LxmlDoc
#endif
#endif
#ifndef __PYX_HAVE_RT_ImportModule
#define __PYX_HAVE_RT_ImportModule
static PyObject *__Pyx_ImportModule(const char *name) {
PyObject *py_name = 0;
PyObject *py_module = 0;
py_name = __Pyx_PyIdentifier_FromString(name);
if (!py_name)
goto bad;
py_module = PyImport_Import(py_name);
Py_DECREF(py_name);
return py_module;
bad:
Py_XDECREF(py_name);
return 0;
}
#endif
#ifndef __PYX_HAVE_RT_ImportFunction
#define __PYX_HAVE_RT_ImportFunction
static int __Pyx_ImportFunction(PyObject *module, const char *funcname, void (**f)(void), const char *sig) {
@ -176,7 +162,7 @@ bad:
static int import_lxml__etree(void) {
PyObject *module = 0;
module = __Pyx_ImportModule("lxml.etree");
module = PyImport_ImportModule("lxml.etree");
if (!module) goto bad;
if (__Pyx_ImportFunction(module, "deepcopyNodeToDocument", (void (**)(void))&__pyx_api_f_4lxml_5etree_deepcopyNodeToDocument, "struct LxmlElement *(struct LxmlDocument *, xmlNode *)") < 0) goto bad;
if (__Pyx_ImportFunction(module, "elementTreeFactory", (void (**)(void))&__pyx_api_f_4lxml_5etree_elementTreeFactory, "struct LxmlElementTree *(struct LxmlElement *)") < 0) goto bad;

Binary file not shown.

View file

@ -1,3 +1,5 @@
# cython: language_level=2
"""
SAX-based adapter to copy trees from/to the Python standard library.
@ -10,6 +12,8 @@ the SAX events of an ElementTree against a SAX ContentHandler.
See http://codespeak.net/lxml/sax.html
"""
from __future__ import absolute_import
from xml.sax.handler import ContentHandler
from lxml import etree
from lxml.etree import ElementTree, SubElement
@ -25,7 +29,7 @@ def _getNsTag(tag):
if tag[0] == '{':
return tuple(tag[1:].split('}', 1))
else:
return (None, tag)
return None, tag
class ElementTreeContentHandler(ContentHandler):
@ -189,19 +193,26 @@ class ElementTreeProducer(object):
self._content_handler.endDocument()
def _recursive_saxify(self, element, prefixes):
def _recursive_saxify(self, element, parent_nsmap):
content_handler = self._content_handler
tag = element.tag
if tag is Comment or tag is ProcessingInstruction:
if tag is ProcessingInstruction:
content_handler.processingInstruction(
element.target, element.text)
if element.tail:
content_handler.characters(element.tail)
tail = element.tail
if tail:
content_handler.characters(tail)
return
element_nsmap = element.nsmap
new_prefixes = []
build_qname = self._build_qname
if element_nsmap != parent_nsmap:
# There have been updates to the namespace
for prefix, ns_uri in element_nsmap.items():
if parent_nsmap.get(prefix) != ns_uri:
new_prefixes.append( (prefix, ns_uri) )
attribs = element.items()
if attribs:
attr_values = {}
@ -209,39 +220,57 @@ class ElementTreeProducer(object):
for attr_ns_name, value in attribs:
attr_ns_tuple = _getNsTag(attr_ns_name)
attr_values[attr_ns_tuple] = value
attr_qnames[attr_ns_tuple] = build_qname(
attr_ns_tuple[0], attr_ns_tuple[1], prefixes, new_prefixes)
attr_qnames[attr_ns_tuple] = self._build_qname(
attr_ns_tuple[0], attr_ns_tuple[1], element_nsmap,
preferred_prefix=None, is_attribute=True)
sax_attributes = self._attr_class(attr_values, attr_qnames)
else:
sax_attributes = self._empty_attributes
ns_uri, local_name = _getNsTag(tag)
qname = build_qname(ns_uri, local_name, prefixes, new_prefixes)
qname = self._build_qname(
ns_uri, local_name, element_nsmap, element.prefix, is_attribute=False)
for prefix, uri in new_prefixes:
content_handler.startPrefixMapping(prefix, uri)
content_handler.startElementNS((ns_uri, local_name),
qname, sax_attributes)
if element.text:
content_handler.characters(element.text)
content_handler.startElementNS(
(ns_uri, local_name), qname, sax_attributes)
text = element.text
if text:
content_handler.characters(text)
for child in element:
self._recursive_saxify(child, prefixes)
self._recursive_saxify(child, element_nsmap)
content_handler.endElementNS((ns_uri, local_name), qname)
for prefix, uri in new_prefixes:
content_handler.endPrefixMapping(prefix)
if element.tail:
content_handler.characters(element.tail)
tail = element.tail
if tail:
content_handler.characters(tail)
def _build_qname(self, ns_uri, local_name, prefixes, new_prefixes):
def _build_qname(self, ns_uri, local_name, nsmap, preferred_prefix, is_attribute):
if ns_uri is None:
return local_name
try:
prefix = prefixes[ns_uri]
except KeyError:
prefix = prefixes[ns_uri] = 'ns%02d' % len(prefixes)
new_prefixes.append( (prefix, ns_uri) )
if not is_attribute and nsmap.get(preferred_prefix) == ns_uri:
prefix = preferred_prefix
else:
# Pick the first matching prefix, in alphabetical order.
candidates = [
pfx for (pfx, uri) in nsmap.items()
if pfx is not None and uri == ns_uri
]
prefix = (
candidates[0] if len(candidates) == 1
else min(candidates) if candidates
else None
)
if prefix is None:
# Default namespace
return local_name
return prefix + ':' + local_name
def saxify(element_or_tree, content_handler):
"""One-shot helper to generate SAX events from an XML tree and fire
them against a SAX ContentHandler.