Menu
▾
▴
[Jython-checkins] SF.net SVN: jython:[5899] branches/jy3k
|
From: <fwi...@us...> - 2009-01-09 04:50:29
|
Revision: 5899
http://jython.svn.sourceforge.net/jython/?rev=5899&view=rev
Author: fwierzbicki
Date: 2009-01-09 04:50:22 +0000 (Fri, 09 Jan 2009)
Log Message:
-----------
Merged revisions 5889-5893 via svnmerge from
https://jython.svn.sourceforge.net/svnroot/jython/trunk/jython
........
r5889 | pjenvey | 2009-01-08 16:23:29 -0500 (Thu, 08 Jan 2009) | 5 lines
jython-elementtree from: http://jython-elementtree.googlecode.com/svn/trunk@69
provides a partial emulation of pyexpat via xerces 2.9.1 and extra tests in
test_xml_etree_jy
from Sebastien Boisgerault
........
r5890 | pjenvey | 2009-01-08 16:26:19 -0500 (Thu, 08 Jan 2009) | 2 lines
xerces 2.9.1 for elementtree
........
r5891 | pjenvey | 2009-01-08 16:49:36 -0500 (Thu, 08 Jan 2009) | 2 lines
jarjar xerces into jython-complete and check for the mangled name
........
r5892 | pjenvey | 2009-01-08 17:05:28 -0500 (Thu, 08 Jan 2009) | 2 lines
unused import, coding standards
........
r5893 | otmarhumbel | 2009-01-08 17:54:04 -0500 (Thu, 08 Jan 2009) | 10 lines
rename the jython*.jar files:
jython.jar is now called jython-dev.jar
jython-complete.jar is now called jython.jar
the one we distribute is jython.jar,
containing the necessary external libraries, mangled
jython-dev.jar is intended for local developer usage,
containing no external libraries,
referencing the real external package names
........
Modified Paths:
--------------
branches/jy3k/CPythonLib.includes
branches/jy3k/Lib/test/regrtest.py
branches/jy3k/Lib/test/test_xml_etree.py
branches/jy3k/Lib/test/test_xml_etree_c.py
branches/jy3k/bugtests/README.txt
branches/jy3k/bugtests/test386.py
branches/jy3k/bugtests/test394.py
branches/jy3k/bugtests/test394jar/MANIFEST.MF
branches/jy3k/build.xml
branches/jy3k/src/org/python/core/PySystemState.java
branches/jy3k/src/org/python/util/JythoncAntTask.java
branches/jy3k/src/shell/jython
branches/jy3k/src/shell/jython.bat
Added Paths:
-----------
branches/jy3k/Lib/pyexpat.py
branches/jy3k/Lib/test/test_xml_etree_jy.py
branches/jy3k/Lib/xml/parsers/
branches/jy3k/Lib/xml/parsers/__init__.py
branches/jy3k/Lib/xml/parsers/expat.py
branches/jy3k/extlibs/xercesImpl.jar
Removed Paths:
-------------
branches/jy3k/Lib/xml/parsers/__init__.py
branches/jy3k/Lib/xml/parsers/expat.py
Property Changed:
----------------
branches/jy3k/
Property changes on: branches/jy3k
___________________________________________________________________
Modified: svnmerge-integrated
- /trunk/jython:1-5885
+ /trunk/jython:1-5898
Modified: branches/jy3k/CPythonLib.includes
===================================================================
--- branches/jy3k/CPythonLib.includes 2009-01-09 04:32:35 UTC (rev 5898)
+++ branches/jy3k/CPythonLib.includes 2009-01-09 04:50:22 UTC (rev 5899)
@@ -8,6 +8,7 @@
encodings/**
logging/*
test/**
+xml/etree/**
# Lib files, in alphabetical order:
__future__.py
Copied: branches/jy3k/Lib/pyexpat.py (from rev 5893, trunk/jython/Lib/pyexpat.py)
===================================================================
--- branches/jy3k/Lib/pyexpat.py (rev 0)
+++ branches/jy3k/Lib/pyexpat.py 2009-01-09 04:50:22 UTC (rev 5899)
@@ -0,0 +1 @@
+from xml.parsers.expat import *
Modified: branches/jy3k/Lib/test/regrtest.py
===================================================================
--- branches/jy3k/Lib/test/regrtest.py 2009-01-09 04:32:35 UTC (rev 5898)
+++ branches/jy3k/Lib/test/regrtest.py 2009-01-09 04:50:22 UTC (rev 5899)
@@ -1449,7 +1449,6 @@
test_wave
test_winreg
test_winsound
- test_xml_etree_c
test_zipfile64
"""
}
@@ -1487,7 +1486,6 @@
test_ucn
test_unicode
test_unicodedata
- test_xml_etree
test_zipimport
""",
}
Modified: branches/jy3k/Lib/test/test_xml_etree.py
===================================================================
--- branches/jy3k/Lib/test/test_xml_etree.py 2009-01-09 04:32:35 UTC (rev 5898)
+++ branches/jy3k/Lib/test/test_xml_etree.py 2009-01-09 04:50:22 UTC (rev 5899)
@@ -209,7 +209,7 @@
>>> check_encoding(ET, "iso-8859-1")
>>> check_encoding(ET, "iso-8859-15")
>>> check_encoding(ET, "cp437")
- >>> check_encoding(ET, "mac-roman")
+ >>> #check_encoding(ET, "mac-roman")
"""
ET.XML("<?xml version='1.0' encoding='%s'?><xml />" % encoding)
Modified: branches/jy3k/Lib/test/test_xml_etree_c.py
===================================================================
--- branches/jy3k/Lib/test/test_xml_etree_c.py 2009-01-09 04:32:35 UTC (rev 5898)
+++ branches/jy3k/Lib/test/test_xml_etree_c.py 2009-01-09 04:50:22 UTC (rev 5899)
@@ -198,7 +198,7 @@
>>> check_encoding("iso-8859-1")
>>> check_encoding("iso-8859-15")
>>> check_encoding("cp437")
- >>> check_encoding("mac-roman")
+ >>> #check_encoding("mac-roman")
"""
ET.XML(
"<?xml version='1.0' encoding='%s'?><xml />" % encoding
Copied: branches/jy3k/Lib/test/test_xml_etree_jy.py (from rev 5893, trunk/jython/Lib/test/test_xml_etree_jy.py)
===================================================================
--- branches/jy3k/Lib/test/test_xml_etree_jy.py (rev 0)
+++ branches/jy3k/Lib/test/test_xml_etree_jy.py 2009-01-09 04:50:22 UTC (rev 5899)
@@ -0,0 +1,754 @@
+# encoding: utf-8
+
+import sys
+JYTHON = sys.platform.startswith("java")
+
+import doctest
+
+import xml.parsers.expat as expat
+from xml.etree.ElementTree import *
+
+def jython(function):
+ if JYTHON:
+ return function
+ else:
+ return None
+
+class sortdict(dict):
+ def __repr__(self):
+ items = self.items()
+ items.sort()
+ pairs = ["%r: %r" % pair for pair in items]
+ return "{%s}" % ", ".join(pairs)
+ __str__ = __repr__
+
+
+class Outputter:
+ def StartElementHandler(self, name, attrs):
+ print 'Start element:\n ', repr(name), sortdict(attrs)
+
+ def EndElementHandler(self, name):
+ print 'End element:\n ', repr(name)
+
+ def CharacterDataHandler(self, data):
+ data = data.strip()
+ if data:
+ print 'Character data:'
+ print ' ', repr(data)
+
+ def ProcessingInstructionHandler(self, target, data):
+ print 'PI:\n ', repr(target), repr(data)
+
+ def StartNamespaceDeclHandler(self, prefix, uri):
+ print 'NS decl:\n ', repr(prefix), repr(uri)
+
+ def EndNamespaceDeclHandler(self, prefix):
+ print 'End of NS decl:\n ', repr(prefix)
+
+ def StartCdataSectionHandler(self):
+ print 'Start of CDATA section'
+
+ def EndCdataSectionHandler(self):
+ print 'End of CDATA section'
+
+ def CommentHandler(self, text):
+ print 'Comment:\n ', repr(text)
+
+ def NotationDeclHandler(self, *args):
+ name, base, sysid, pubid = args
+ print 'Notation declared:', args
+
+ def UnparsedEntityDeclHandler(self, *args):
+ entityName, base, systemId, publicId, notationName = args
+ print 'Unparsed entity decl:\n ', args
+
+ def NotStandaloneHandler(self, userData):
+ print 'Not standalone'
+ return 1
+
+ def ExternalEntityRefHandler(self, *args):
+ context, base, sysId, pubId = args
+ print 'External entity ref:', args[1:]
+ return 1
+
+ def DefaultHandler(self, userData):
+ pass
+
+ def DefaultHandlerExpand(self, userData):
+ pass
+
+_= """
+ >>> data = '''\
+ ... <?xml version="1.0" encoding="iso-8859-1" standalone="no"?>
+ ... <?xml-stylesheet href="stylesheet.css"?>
+ ... <!-- comment data -->
+ ... <!DOCTYPE quotations SYSTEM "quotations.dtd" [
+ ... <!ELEMENT root ANY>
+ ... <!NOTATION notation SYSTEM "notation.jpeg">
+ ... <!ENTITY acirc "â">
+ ... <!ENTITY external_entity SYSTEM "entity.file">
+ ... <!ENTITY unparsed_entity SYSTEM "entity.file" NDATA notation>
+ ... %unparsed_entity;
+ ... ]>
+ ...
+ ... <root attr1="value1" attr2="value2ὀ">
+ ... <myns:subelement xmlns:myns="http://www.python.org/namespace">
+ ... Contents of subelements
+ ... </myns:subelement>
+ ... <sub2><![CDATA[contents of CDATA section]]></sub2>
+ ... &external_entity;
+ ... </root>
+ ... '''
+ """
+
+def test_utf8():
+ """
+ Source: test_pyexpat.py
+ Changes: replaced tabs with spaces in Outputter to ease doctest integration
+
+ >>> out = Outputter()
+ >>> parser = expat.ParserCreate(namespace_separator='!')
+ >>> HANDLER_NAMES = [
+ ... 'StartElementHandler', 'EndElementHandler',
+ ... 'CharacterDataHandler',
+ ... 'ProcessingInstructionHandler',
+ ... 'UnparsedEntityDeclHandler', 'NotationDeclHandler',
+ ... 'StartNamespaceDeclHandler', 'EndNamespaceDeclHandler',
+ ... 'CommentHandler', 'StartCdataSectionHandler',
+ ... 'EndCdataSectionHandler',
+ ... 'DefaultHandler', 'DefaultHandlerExpand',
+ ... #'NotStandaloneHandler',
+ ... 'ExternalEntityRefHandler'
+ ... ]
+ >>> for name in HANDLER_NAMES:
+ ... setattr(parser, name, getattr(out, name))
+
+ >>> data = '''\\
+ ... <?xml version="1.0" encoding="iso-8859-1" standalone="no"?>
+ ... <?xml-stylesheet href="stylesheet.css"?>
+ ... <!-- comment data -->
+ ... <!DOCTYPE quotations SYSTEM "quotations.dtd" [
+ ... <!ELEMENT root ANY>
+ ... <!NOTATION notation SYSTEM "notation.jpeg">
+ ... <!ENTITY acirc "â">
+ ... <!ENTITY external_entity SYSTEM "entity.file">
+ ... <!ENTITY unparsed_entity SYSTEM "entity.file" NDATA notation>
+ ... %unparsed_entity;
+ ... ]>
+ ...
+ ... <root attr1="value1" attr2="value2ὀ">
+ ... <myns:subelement xmlns:myns="http://www.python.org/namespace">
+ ... Contents of subelements
+ ... </myns:subelement>
+ ... <sub2><![CDATA[contents of CDATA section]]></sub2>
+ ... &external_entity;
+ ... </root>
+ ... '''
+
+ #Produce UTF-8 output
+ #>>> parser.returns_unicode = 0
+ #>>> try:
+ #... parser.Parse(data, 1)
+ #... except expat.error:
+ #... print '** Error', parser.ErrorCode, expat.ErrorString(parser.ErrorCode)
+ #... print '** Line', parser.ErrorLineNumber
+ #... print '** Column', parser.ErrorColumnNumber
+ #... print '** Byte', parser.ErrorByteIndex
+ #PI:
+ #'xml-stylesheet' 'href="stylesheet.css"'
+ #Comment:
+ #' comment data '
+ #Notation declared: ('notation', None, 'notation.jpeg', None)
+ #Unparsed entity decl:
+ #('unparsed_entity', None, 'entity.file', None, 'notation')
+ #Start element:
+ #'root' {'attr1': 'value1', 'attr2': 'value2\\xe1\\xbd\\x80'}
+ #NS decl:
+ #'myns' 'http://www.python.org/namespace'
+ #Start element:
+ #'http://www.python.org/namespace!subelement' {}
+ #Character data:
+ #'Contents of subelements'
+ #End element:
+ #'http://www.python.org/namespace!subelement'
+ #End of NS decl:
+ #'myns'
+ #Start element:
+ #'sub2' {}
+ #Start of CDATA section
+ #Character data:
+ #'contents of CDATA section'
+ #End of CDATA section
+ #End element:
+ #'sub2'
+ #External entity ref: (None, 'entity.file', None)
+ #End element:
+ #'root'
+ #1
+
+ >>> parser = expat.ParserCreate(namespace_separator='!')
+ >>> parser.returns_unicode = 1
+ >>> for name in HANDLER_NAMES:
+ ... setattr(parser, name, getattr(out, name))
+ >>> try:
+ ... parser.Parse(data, 1)
+ ... except expat.error:
+ ... print '** Line', parser.ErrorLineNumber
+ ... print '** Column', parser.ErrorColumnNumber
+ ... print '** Byte', parser.ErrorByteIndex #doctest: +REPORT_UDIFF
+ PI:
+ u'xml-stylesheet' u'href="stylesheet.css"'
+ Comment:
+ u' comment data '
+ Notation declared: (u'notation', None, u'notation.jpeg', None)
+ Unparsed entity decl:
+ (u'unparsed_entity', None, u'entity.file', None, u'notation')
+ Start element:
+ u'root' {u'attr1': u'value1', u'attr2': u'value2\u1f40'}
+ NS decl:
+ u'myns' u'http://www.python.org/namespace'
+ Start element:
+ u'http://www.python.org/namespace!subelement' {}
+ Character data:
+ u'Contents of subelements'
+ End element:
+ u'http://www.python.org/namespace!subelement'
+ End of NS decl:
+ u'myns'
+ Start element:
+ u'sub2' {}
+ Start of CDATA section
+ Character data:
+ u'contents of CDATA section'
+ End of CDATA section
+ End element:
+ u'sub2'
+ External entity ref: (None, u'entity.file', None)
+ End element:
+ u'root'
+ 1
+ """
+
+
+def test_import_as_pyexpat():
+ """
+ >>> import pyexpat as expat
+ >>> expat #doctest: +ELLIPSIS
+ <module 'pyexpat' from ...>
+ """
+
+
+def test_errors_submodule():
+ """
+ >>> import xml.parsers.expat as expat
+ >>> expat.errors
+ <module 'pyexpat.errors' (built-in)>
+ >>> dir(expat.errors) #doctest: +ELLIPSIS
+ ['XML_ERROR_ABORTED', ..., 'XML_ERROR_XML_DECL', '__doc__', '__name__']
+ >>> expat.errors.XML_ERROR_ABORTED
+ 'parsing aborted'
+ >>> expat.errors.XML_ERROR_XML_DECL
+ 'XML declaration not well-formed'
+ """
+
+def test_model_submodule():
+ """
+ >>> import xml.parsers.expat as expat
+ >>> expat.model
+ <module 'pyexpat.model' (built-in)>
+ >>> print sortdict(expat.model.__dict__)
+ {'XML_CQUANT_NONE': 0, 'XML_CQUANT_OPT': 1, 'XML_CQUANT_PLUS': 3, 'XML_CQUANT_REP': 2, 'XML_CTYPE_ANY': 2, 'XML_CTYPE_CHOICE': 5, 'XML_CTYPE_EMPTY': 1, 'XML_CTYPE_MIXED': 3, 'XML_CTYPE_NAME': 4, 'XML_CTYPE_SEQ': 6, '__doc__': 'Constants used to interpret content model information.', '__name__': 'pyexpat.model'}
+ """
+
+def test_parse_only_xml_data():
+ """
+ Source: test_pyexpat.py, see also: http://python.org/sf/1296433
+ Changes:
+ - replaced 'iso8859' encoding with 'ISO-8859-1',
+ - added isfinal=True keyword argument to Parse call (as in this port,
+ the data is not processed until it is fully available).
+ With these changes, the test still crashes CPython 2.5.
+
+ >>> import xml.parsers.expat as expat
+ >>> # xml = "<?xml version='1.0' encoding='iso8859'?><s>%s</s>" % ('a' * 1025)
+
+ This one doesn't crash:
+ >>> xml = "<?xml version='1.0'?><s>%s</s>" % ('a' * 10000)
+
+ >>> def handler(text):
+ ... raise Exception
+ >>> parser = expat.ParserCreate()
+ >>> parser.CharacterDataHandler = handler
+ >>> try:
+ ... parser.Parse(xml, True)
+ ... except:
+ ... pass
+ """
+
+
+def test_namespace_separator():
+ """
+ Source: test_pyexpat.py
+
+ Tests that make sure we get errors when the namespace_separator value
+ is illegal, and that we don't for good values:
+
+ >>> from xml.parsers.expat import ParserCreate
+
+ >>> p = ParserCreate()
+ >>> p = ParserCreate(namespace_separator=None)
+ >>> p = ParserCreate(namespace_separator=' ')
+ >>> p = ParserCreate(namespace_separator=42) #doctest: +ELLIPSIS
+ Traceback (most recent call last):
+ ...
+ TypeError: ...
+ >>> p = ParserCreate(namespace_separator='too long') #doctest: +ELLIPSIS
+ Traceback (most recent call last):
+ ...
+ ValueError: ...
+
+ ParserCreate() needs to accept a namespace_separator of zero length
+ to satisfy the requirements of RDF applications that are required
+ to simply glue together the namespace URI and the localname. Though
+ considered a wart of the RDF specifications, it needs to be supported.
+
+ See XML-SIG mailing list thread starting with
+ http://mail.python.org/pipermail/xml-sig/2001-April/005202.html
+
+ >>> p = ParserCreate(namespace_separator='') # too short
+"""
+
+
+def test_interning_machinery():
+ """
+ Source: test_pyexpat.py
+
+ >>> from xml.parsers.expat import ParserCreate
+
+ >>> p = ParserCreate()
+ >>> L = []
+ >>> def collector(name, *args):
+ ... L.append(name)
+ >>> p.StartElementHandler = collector
+ >>> p.EndElementHandler = collector
+ >>> p.Parse("<e> <e/> <e></e> </e>", 1)
+ 1
+ >>> tag = L[0]
+ >>> len(L)
+ 6
+ >>> all(tag is entry for entry in L)
+ True
+ """
+
+
+def test_exception_from_callback():
+ """
+ Source: test_pyexpat.py
+
+ >>> from xml.parsers.expat import ParserCreate
+
+ >>> def StartElementHandler(name, attrs):
+ ... raise RuntimeError(name)
+
+ >>> parser = ParserCreate()
+ >>> parser.StartElementHandler = StartElementHandler
+ >>> try:
+ ... parser.Parse("<a><b><c/></b></a>", 1)
+ ... except RuntimeError, e:
+ ... pass
+ >>> e.args[0] == "a"
+ True
+ """
+
+
+def test_with_and_without_namespace():
+ """
+ >>> from xml.parsers.expat import ParserCreate
+
+ >>> xml = '''<root
+ ... xmlns="http://www.python.org"
+ ... xmlns:python="http://www.python.org"
+ ... python:a="1" b="2">
+ ... <python:sub1/>
+ ... <sub2 xmlns=""/>
+ ... </root>'''
+ >>> def handler(name, attributes):
+ ... attributes = sorted(attributes.items())
+ ... print name
+ ... for attr in attributes:
+ ... print " %s = %r" % attr
+
+ >>> parser = ParserCreate()
+ >>> parser.StartElementHandler = handler
+ >>> _ = parser.Parse(xml, True)
+ root
+ b = u'2'
+ python:a = u'1'
+ xmlns = u'http://www.python.org'
+ xmlns:python = u'http://www.python.org'
+ python:sub1
+ sub2
+ xmlns = u''
+
+ >>> parser = ParserCreate(namespace_separator="|")
+ >>> parser.StartElementHandler = handler
+ >>> _ = parser.Parse(xml, True)
+ http://www.python.org|root
+ b = u'2'
+ http://www.python.org|a = u'1'
+ http://www.python.org|sub1
+ sub2
+ """
+
+def test_unicode_bug():
+ """
+ Regression introduced by revision 28
+
+ >>> doc = XML("<doc>舰</doc>")
+ >>> doc.text
+ u'\u8230'
+ """
+
+def test_DTD():
+ """
+ >>> xml = '''<!DOCTYPE doc [
+ ... <!ELEMENT doc (any|empty|text|mixed|opt|many|plus)>
+ ... <!ELEMENT any ANY>
+ ... <!ELEMENT empty EMPTY>
+ ... <!ELEMENT text (#PCDATA)>
+ ... <!ELEMENT sequence (_sequence)>
+ ... <!ELEMENT _sequence (any,any)>
+ ... <!ELEMENT mixed (#PCDATA|any)*>
+ ... <!ELEMENT opt (empty)?>
+ ... <!ELEMENT many (empty)*>
+ ... <!ELEMENT plus (empty)+>
+ ... ]>
+ ... <doc><text>content</text></doc>
+ ... '''
+ >>> parser = expat.ParserCreate()
+ >>> def handler(header, *args):
+ ... def _handler(*args):
+ ... print header + ":", args
+ ... return _handler
+ >>> parser.ElementDeclHandler = handler("ELEMENT")
+ >>> parser.AttlistDeclHandler = handler("ATTRIBUTE")
+ >>> parser.EntityDeclHandler = handler("ENTITY")
+ >>> parser.NotationDeclHandler = handler("NOTATION")
+ >>> parser.UnparsedEntityDeclHandler = handler("UNPARSED")
+ >>> parser.Parse(xml, True)
+ ELEMENT: (u'doc', (5, 0, None, ((4, 0, u'any', ()), (4, 0, u'empty', ()), (4, 0, u'text', ()), (4, 0, u'mixed', ()), (4, 0, u'opt', ()), (4, 0, u'many', ()), (4, 0, u'plus', ()))))
+ ELEMENT: (u'any', (2, 0, None, ()))
+ ELEMENT: (u'empty', (1, 0, None, ()))
+ ELEMENT: (u'text', (3, 0, None, ()))
+ ELEMENT: (u'sequence', (6, 0, None, ((4, 0, u'_sequence', ()),)))
+ ELEMENT: (u'_sequence', (6, 0, None, ((4, 0, u'any', ()), (4, 0, u'any', ()))))
+ ELEMENT: (u'mixed', (3, 2, None, ((4, 0, u'any', ()),)))
+ ELEMENT: (u'opt', (6, 1, None, ((4, 0, u'empty', ()),)))
+ ELEMENT: (u'many', (6, 2, None, ((4, 0, u'empty', ()),)))
+ ELEMENT: (u'plus', (6, 3, None, ((4, 0, u'empty', ()),)))
+ 1
+ """
+
+def test_entity():
+ """
+
+ TODO: need a fallback for entity-resolver so that empty source is returned.
+
+ >>> xml = ''' <!DOCTYPE doc SYSTEM "external.dtd" [
+ ... <!ENTITY ext-entity SYSTEM "external-entity">
+ ... ]>
+ ... <doc>&ext-entity;&in-ext-dtd-entity;</doc>'''
+ >>> parser = expat.ParserCreate()
+ >>> parser.Parse(xml, True)
+ 1
+
+ EXPAT OH MY ! When applicable (internal entities), the CharacterDataHandler
+ callback will override DefaultHandlerExpand, but it WON'T override
+ DefaultHandler. On the other hand, the DefaultHandlerExpand callback WILL
+ override DefaultHandler ... More tests todo here ...
+
+ >>> xml = '''<!DOCTYPE doc SYSTEM "external.dtd" [
+ ... <!ENTITY ext-entity SYSTEM "external-entity">
+ ... <!ENTITY int-entity "internal">
+ ... ]>
+ ... <doc>&int-entity;&ext-entity;&in-ext-dtd-entity;</doc>'''
+ >>> parser = expat.ParserCreate()
+ >>> def handler(header):
+ ... def _handler(*args):
+ ... print header + ":", args
+ ... return 1
+ ... return _handler
+ >>> parser.CharacterDataHandler = handler("text")
+ >>> parser.DefaultHandler = handler("default")
+ >>> parser.Parse(xml, True) #doctest: +ELLIPSIS
+ default: ...
+ default: (u'&int-entity;',)
+ default: (u'&ext-entity;',)
+ default: (u'&in-ext-dtd-entity;',)
+ ...
+ 1
+
+ EXPAT OH MY ! When applicable (internal entities), the CharacterDataHandler
+ callback will override DefaultHandlerExpand, but it WON'T override
+ DefaultHandler. On the other hand, the DefaultHandlerExpand callback WILL
+ override DefaultHandler ... More tests todo here ...
+ """
+
+def test_resolve_entity_handlers():
+ """
+ >>> xml = '''<!DOCTYPE doc [
+ ... <!ENTITY entity SYSTEM "entity">
+ ... ]>
+ ... <doc>&entity;</doc>'''
+ >>> def handler(header):
+ ... def _handler(*args):
+ ... print header + ":", args
+ ... return 1
+ ... return _handler
+
+ >>> parser = expat.ParserCreate()
+ >>> parser.ExternalEntityRefHandler = handler("ExternalEntityRefHandler")
+ >>> parser.Parse(xml, True)
+ ExternalEntityRefHandler: (u'entity', None, u'entity', None)
+ 1
+ """
+
+def handler(name, header="XML>", returns=None):
+ def _handler(*args):
+ if len(args) == 1:
+ args = "(%r)" % args[0]
+ else:
+ args = str(args)
+ print header, name + "%s" % args
+ return returns
+ return _handler
+
+def parse(xml, *handlers):
+ parser = expat.ParserCreate()
+ for name in handlers:
+ if name == "ExternalEntityRefHandler":
+ returns = 1
+ else:
+ returns = None
+ setattr(parser, name, handler(name, returns=returns))
+ parser.Parse(xml, True)
+
+def test_internal_entities():
+ """
+ >>> xml = '''<!DOCTYPE doc [
+ ... <!ENTITY entity "entity-content">
+ ... ]>
+ ... <doc>&entity;</doc>'''
+
+ >>> parse(xml)
+
+ >>> parse(xml, "CharacterDataHandler")
+ XML> CharacterDataHandler(u'entity-content')
+
+ >>> parse(xml, "DefaultHandler") #doctest: +ELLIPSIS
+ XML> ...DefaultHandler(u'&entity;')...
+
+ >>> parse(xml, "DefaultHandlerExpand") #doctest: +ELLIPSIS
+ XML> ...DefaultHandlerExpand(u'entity-content')...
+
+ # Uhu ?
+ >>> parse(xml, "CharacterDataHandler",
+ ... "DefaultHandler") #doctest: +ELLIPSIS
+ XML> ...DefaultHandler(u'&entity;')...
+
+ >>> parse(xml, "CharacterDataHandler",
+ ... "DefaultHandlerExpand") #doctest: +ELLIPSIS
+ XML> ...CharacterDataHandler(u'entity-content')...
+
+ >>> parse(xml, "DefaultHandler",
+ ... "DefaultHandlerExpand") #doctest: +ELLIPSIS
+ XML> ...DefaultHandlerExpand(u'entity-content')...
+
+ >>> parse(xml, "CharacterDataHandler",
+ ... "DefaultHandler",
+ ... "DefaultHandlerExpand") #doctest: +ELLIPSIS
+ XML> ...CharacterDataHandler(u'entity-content')...
+ """
+
+def test_external_entities():
+ """
+ >>> xml = '''<!DOCTYPE doc [
+ ... <!ENTITY entity PUBLIC "http://entity-web" "entity-file">
+ ... ]>
+ ... <doc>&entity;</doc>'''
+
+ >>> parse(xml)
+
+ >>> parse(xml, "ExternalEntityRefHandler")
+ XML> ExternalEntityRefHandler(u'entity', None, u'entity-file', u'http://entity-web')
+
+ >>> parse(xml, "DefaultHandler") #doctest: +ELLIPSIS
+ XML> ...DefaultHandler(u'&entity;')...
+
+ >>> parse(xml, "DefaultHandlerExpand") #doctest: +ELLIPSIS
+ XML> ...DefaultHandlerExpand(u'&entity;')...
+
+ >>> parse(xml, "ExternalEntityRefHandler",
+ ... "DefaultHandler") #doctest: +ELLIPSIS
+ XML> ...ExternalEntityRefHandler(u'entity', None, u'entity-file', u'http://entity-web')...
+
+ >>> parse(xml, "ExternalEntityRefHandler",
+ ... "DefaultHandlerExpand") #doctest: +ELLIPSIS
+ XML> ...ExternalEntityRefHandler(u'entity', None, u'entity-file', u'http://entity-web')...
+
+ >>> parse(xml, "DefaultHandler",
+ ... "DefaultHandlerExpand") #doctest: +ELLIPSIS
+ XML> ...DefaultHandlerExpand(u'&entity;')...
+
+ >>> parse(xml, "ExternalEntityRefHandler",
+ ... "DefaultHandler",
+ ... "DefaultHandlerExpand") #doctest: +ELLIPSIS
+ XML> ...ExternalEntityRefHandler(u'entity', None, u'entity-file', u'http://entity-web')...
+ """
+
+def test_undefined_entities():
+ """
+ >>> xml = "<doc>&entity;</doc>"
+ >>> parse(xml)
+ Traceback (most recent call last):
+ ...
+ ExpatError: undefined entity: line 1, column 5
+ """
+
+def locate(parser, name):
+ def _handler(*args):
+ print name, parser.CurrentLineNumber, parser.CurrentColumnNumber
+ return _handler
+
+def test_current_location():
+ """
+ >>> xml = '''<doc>text<tag/>text<tag></tag>
+ ... <tag></tag>
+ ... text<tag/>
+ ... </doc>'''
+ >>> parser = expat.ParserCreate()
+ >>> parser.CharacterDataHandler = locate(parser, "TEXT:")
+ >>> parser.StartElementHandler = locate(parser, "START:")
+ >>> parser.EndElementHandler = locate(parser, "END:")
+ >>> _ = parser.Parse(xml, True) #doctest: +ELLIPSIS
+ START: 1 0
+ TEXT: 1 5...
+ START: 1 9
+ END: 1 15
+ TEXT: 1 15...
+ START: 1 19
+ END: 1 24
+ TEXT: 1 30...
+ START: 2 0
+ END: 2 5
+ TEXT: 2 11...
+ START: 3 4
+ END: 3 10
+ TEXT: 3 10...
+ END: 4 0
+
+ >>> xml = '''<doc>
+ ... start tag after some text<tag/>
+ ... <elt></elt><tag/>
+ ... <elt/><tag/>
+ ... </doc>'''
+ >>> parser = expat.ParserCreate()
+ >>> parser.CharacterDataHandler = locate(parser, "TEXT:")
+ >>> parser.StartElementHandler = locate(parser, "START:")
+ >>> parser.EndElementHandler = locate(parser, "END:")
+ >>> _ = parser.Parse(xml, True) #doctest: +ELLIPSIS
+ START: 1 0
+ TEXT: 1 5...
+ START: 2 25
+ END: 2 31
+ TEXT: 2 31...
+ START: 3 0
+ END: 3 5
+ START: 3 11
+ END: 3 17
+ TEXT: 3 17...
+ START: 4 0
+ END: 4 6
+ START: 4 6
+ END: 4 12
+ TEXT: 4 12...
+ END: 5 0
+ """
+
+
+def test_error_location():
+ """
+ Source: selftest.py, ElementTree 1.3a3
+ Changes: removed dependencies in ElementTree, added one extra test
+
+ >>> def error(xml):
+ ... p = expat.ParserCreate()
+ ... try:
+ ... p.Parse(xml, True)
+ ... except expat.ExpatError, e:
+ ... return e.lineno, e.offset
+
+ >>> error("foo")
+ (1, 0)
+ >>> error("<tag>&foo;</tag>")
+ (1, 5)
+ >>> error("foobar<")
+ (1, 6)
+ >>> error("<doc>text<doc")
+ (1, 9)
+ """
+
+@jython
+def test_resolveEntity():
+ """
+ # TODO: test that 'skipEntity' works.
+
+ >>> # Jython
+ >>> from org.python.core.util import StringUtil
+ >>> from jarray import array
+
+ >>> # Java Standard Edition
+ >>> from org.xml.sax import *
+ >>> from org.xml.sax.ext import *
+ >>> from org.xml.sax.helpers import *
+ >>> from java.io import ByteArrayInputStream
+
+ >>> xml = '''<!DOCTYPE doc
+ ... [<!ENTITY entity SYSTEM "entity-file">
+ ... ]>
+ ... <doc>&entity;</doc>
+ ... '''
+
+ >>> def empty_source():
+ ... _source = InputSource()
+ ... byte_stream = ByteArrayInputStream(array([], "b"))
+ ... _source.setByteStream(byte_stream)
+ ... return _source
+
+ >>> class Handler(EntityResolver2):
+ ... def getExternalSubset(self, name, baseURI):
+ ... return None
+ ... def resolveEntity(self, name, publicId, baseURI, systemId):
+ ... print "Entity name:", name
+ ... return empty_source()
+
+ >>> def main():
+ ... sax_parser = "org.apache.xerces.parsers.SAXParser"
+ ... reader = XMLReaderFactory.createXMLReader(sax_parser)
+ ... entity_resolver2 = "http://xml.org/sax/features/use-entity-resolver2"
+ ... enabled = reader.getFeature(entity_resolver2)
+ ... print "Entity-Resolver2 enabled:", enabled
+ ... handler = Handler()
+ ... reader.setEntityResolver(handler)
+ ... bytes = StringUtil.toBytes(xml)
+ ... byte_stream = ByteArrayInputStream(bytes)
+ ... source = InputSource(byte_stream)
+ ... reader.parse(source)
+
+ >>> main()
+ Entity-Resolver2 enabled: True
+ Entity name: entity
+ """
+
+if __name__ == "__main__":
+ doctest.testmod()
Deleted: branches/jy3k/Lib/xml/parsers/expat.py
===================================================================
--- trunk/jython/Lib/xml/parsers/expat.py 2009-01-08 22:54:04 UTC (rev 5893)
+++ branches/jy3k/Lib/xml/parsers/expat.py 2009-01-09 04:50:22 UTC (rev 5899)
@@ -1,617 +0,0 @@
-# coding: utf-8
-
-#------------------------------------------------------------------------------
-# Copyright (c) 2008 Sébastien Boisgérault
-#
-# 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.
-# -----------------------------------------------------------------------------
-
-__all__ = ["ExpatError", "ParserCreate", "XMLParserType", "error", "errors"]
-
-# Jython check
-import sys
-if not sys.platform.startswith('java'):
- raise ImportError("this version of expat requires the jython interpreter")
-
-# Standard Python Library
-import re
-import types
-
-# Jython
-from org.python.core import Py
-from org.python.core.util import StringUtil
-from jarray import array
-
-# Java Standard Edition
-from java.io import ByteArrayInputStream
-from java.lang import String, StringBuilder
-from org.xml.sax import InputSource
-from org.xml.sax import SAXNotRecognizedException, SAXParseException
-from org.xml.sax.helpers import XMLReaderFactory
-from org.xml.sax.ext import DefaultHandler2
-
-# Xerces
-try:
- # Name mangled by jarjar?
- import org.python.apache.xerces.parsers.SAXParser
- _xerces_parser = "org.python.apache.xerces.parsers.SAXParser"
-except ImportError:
- _xerces_parser = "org.apache.xerces.parsers.SAXParser"
-
-
-def ParserCreate(encoding=None, namespace_separator=None):
- return XMLParser(encoding, namespace_separator)
-
-
-class XMLParser(object):
-
- def __init__(self, encoding, namespace_separator):
- self.encoding = encoding
- self.CurrentLineNumber = 1
- self.CurrentColumnNumber = 0
- self._NextLineNumber = 1
- self._NextColumnNumber = 0
- self.ErrorLineNumber = -1
- self.ErrorColumnNumber = -1
- self.ErrorCode = None
-
- if namespace_separator is None:
- self.namespace_separator = namespace_separator
- elif isinstance(namespace_separator, basestring):
- self.namespace_separator = str(namespace_separator)
- if len(self.namespace_separator) > 1:
- error = ("namespace_separator must be at most one character, "
- "omitted, or None")
- raise ValueError(error)
- else:
- error = ("ParserCreate() argument 2 must be string or None, "
- "not %s" % type(namespace_separator).__name__)
- raise TypeError(error)
-
- self._reader = XMLReaderFactory.createXMLReader(_xerces_parser)
-
- if self.namespace_separator is None:
- try:
- feature = "http://xml.org/sax/features/namespaces"
- self._reader.setFeature(feature, False)
- except SAXNotRecognizedException:
- error = ("namespace support cannot be disabled; "
- "set namespace_separator to a string of length 1.")
- raise ValueError(error)
-
- self._base = None
- self._buffer_text = True
- self._returns_unicode = True
-
- self._data = StringBuilder()
-
- self._handler = XMLEventHandler(self)
- self._reader.setContentHandler(self._handler)
- self._reader.setErrorHandler(self._handler)
- self._reader.setDTDHandler(self._handler)
- self._reader.setEntityResolver(self._handler)
-
- sax_properties = ("lexical-handler", "declaration-handler")
- for name in sax_properties:
- try:
- name = "http://xml.org/sax/properties/" + name
- self._reader.setProperty(name, self._handler)
- except SAXNotRecognizedException:
- error = "can't set property %r" % name
- raise NotImplementedError(error)
-
- apache_features = (("nonvalidating/load-external-dtd", False),)
- for name, value in apache_features:
- try:
- name = "http://apache.org/xml/features/" + name
- self._reader.setFeature(name, value)
- except SAXNotRecognizedException:
- error = "can't set feature %r" % name
- raise NotImplementedError(error)
-
- # experimental
- #f = "http://xml.org/sax/features/external-general-entities"
- f = "http://xml.org/sax/features/external-parameter-entities"
- #self._reader.setFeature(f, False)
-
- # check
- f = "http://xml.org/sax/features/use-entity-resolver2"
- assert self._reader.getFeature(f)
-
- def GetBase(self):
- return self._base
-
- def SetBase(self, base):
- self._base = base
-
- def _error(self, value=None):
- raise AttributeError("'XMLParser' has no such attribute")
-
- def _get_buffer_text(self):
- return self._buffer_text
-
- def _set_buffer_text(self, value):
- self._buffer_text = bool(value)
-
- def _get_returns_unicode(self):
- return bool(self._returns_unicode)
-
- def _set_returns_unicode(self, value):
- self._returns_unicode = value
-
- # 'ordered' and 'specified' attributes are not supported
- ordered_attributes = property(_error, _error)
- specified_attributes = property(_error, _error)
- # any setting is allowed, but it won't make a difference
- buffer_text = property(_get_buffer_text, _set_buffer_text)
- # non-significant read-only values
- buffer_used = property(lambda self: None)
- buffer_size = property(lambda self: None)
- # 'returns_unicode' attribute is properly supported
- returns_unicode = property(_get_returns_unicode, _set_returns_unicode)
-
- def _expat_error(self, sax_error):
- sax_message = sax_error.getMessage()
- pattern = 'The entity ".*" was referenced, but not declared\.'
- if re.match(pattern, sax_message):
- expat_message = "undefined entity: line %s, column %s" % \
- (self.ErrorLineNumber, self.ErrorColumnNumber)
- else:
- expat_message = sax_message
- error = ExpatError(expat_message)
- error.lineno = self.ErrorLineNumber
- error.offset = self.ErrorColumnNumber
- error.code = self.ErrorCode
- return error
-
- def Parse(self, data, isfinal=False):
- # The 'data' argument should be an encoded text: a str instance that
- # represents an array of bytes. If instead it is a unicode string,
- # only the us-ascii range is considered safe enough to be silently
- # converted.
- if isinstance(data, unicode):
- data = data.encode(sys.getdefaultencoding())
-
- self._data.append(data)
-
- if isfinal:
- bytes = StringUtil.toBytes(self._data.toString())
- byte_stream = ByteArrayInputStream(bytes)
- source = InputSource(byte_stream)
- if self.encoding is not None:
- source.setEncoding(self.encoding)
- try:
- self._reader.parse(source)
- except SAXParseException, sax_error:
- # Experiments tend to show that the '_Next*' parser locations
- # match more closely expat behavior than the 'Current*' or sax
- # error locations.
- self.ErrorLineNumber = self._NextLineNumber
- self.ErrorColumnNumber = self._NextColumnNumber
- self.ErrorCode = None
- raise self._expat_error(sax_error)
- return 1
-
- def ParseFile(self, file):
- # TODO: pseudo-buffering if a read without argument is not supported.
- # document parse / parsefile usage.
- return self.Parse(file.read(), isfinal=True)
-
-
-XMLParserType = XMLParser
-
-
-def _encode(arg, encoding):
- if isinstance(arg, unicode):
- return arg.encode(encoding)
- else:
- if isinstance(arg, dict):
- iterator = arg.iteritems()
- else:
- iterator = iter(arg)
- return type(arg)(_encode(_arg, encoding) for _arg in iterator)
-
-
-def expat(callback=None, guard="True", force=False, returns="None"):
- global _register
- try:
- _ = _register
- except NameError:
- _register = {}
-
- def _expat(method):
- name = method.__name__
- context = id(sys._getframe(1))
- key = name, context
- append = _register.setdefault(key, []).append
- append((method, callback, guard, force, returns))
-
- def new_method(*args):
- self = args[0]
- parser = self.parser
- self._update_location(event=name) # bug if multiple method def
- for (method, callback, guard, force, returns) in _register[key]:
- _callback = callback and eval(guard) and \
- getattr(parser, callback, None)
- if _callback or force:
- results = method(*args)
- if _callback:
- if not isinstance(results, tuple):
- results = (results,)
- if not parser.returns_unicode:
- results = _encode(results, "utf-8")
- _callback(*results)
- return_ = eval(returns)
- if callable(return_):
- return return_(*args[1:])
- else:
- return return_
- break
- new_method.__name__ = name
- #new_method.__doc__ = method.__doc__ # what to do with multiple docs ?
- return new_method
- return _expat
-
-
-class XMLEventHandler(DefaultHandler2):
-
- def __init__(self, parser):
- self.parser = parser
- self._tags = {}
- self.dtd = False
- self._entity = {}
- self._previous_event = None
-
- # --- Helpers -------------------------------------------------------------
-
- def _intern(self, tag):
- return self._tags.setdefault(tag, tag)
-
- def _qualify(self, local_name, qname, namespace=None):
- namespace_separator = self.parser.namespace_separator
- if namespace_separator is None:
- return qname
- if not namespace:
- return local_name
- else:
- return namespace + namespace_separator + local_name
-
- def _char_slice_to_unicode(self, characters, start, length):
- """Convert a char[] slice to a PyUnicode instance"""
- text = Py.newUnicode(String(characters[start:start + length]))
- return text
-
- def _expat_content_model(self, name, model_):
- # TODO : implement a model parser
- return (name, model_) # does not fit expat conventions
-
- def _update_location(self, event=None):
- parser = self.parser
- locator = self._locator
-
- # ugly hack that takes care of a xerces-specific (?) locator issue:
- # locate start and end elements at the '<' instead of the first tag
- # type character.
- if event == "startElement" and self._previous_event == "characters":
- parser._NextColumnNumber = max(parser._NextColumnNumber - 1, 0)
- if event == "endElement" and self._previous_event == "characters":
- parser._NextColumnNumber = max(parser._NextColumnNumber - 2, 0)
- # TODO: use the same trick to report accurate error locations ?
-
- parser.CurrentLineNumber = parser._NextLineNumber
- parser.CurrentColumnNumber = parser._NextColumnNumber
- parser._NextLineNumber = locator.getLineNumber()
- parser._NextColumnNumber = locator.getColumnNumber() - 1
-
- self._previous_event = event
-
- # --- ContentHandler Interface --------------------------------------------
-
- @expat("ProcessingInstructionHandler")
- def processingInstruction(self, target, data):
- return target, data
-
- @expat("StartElementHandler")
- def startElement(self, namespace, local_name, qname, attributes):
- tag = self._qualify(local_name, qname, namespace)
- attribs = {}
- length = attributes.getLength()
- for index in range(length):
- local_name = attributes.getLocalName(index)
- qname = attributes.getQName(index)
- namespace = attributes.getURI(index)
- name = self._qualify(local_name, qname, namespace)
- value = attributes.getValue(index)
- attribs[name] = value
- return self._intern(tag), attribs
-
- @expat("EndElementHandler")
- def endElement(self, namespace, local_name, qname):
- return self._intern(self._qualify(local_name, qname, namespace))
-
- @expat("CharacterDataHandler")
- def characters(self, characters, start, length):
- return self._char_slice_to_unicode(characters, start, length)
-
- @expat("DefaultHandlerExpand")
- def characters(self, characters, start, length):
- return self._char_slice_to_unicode(characters, start, length)
-
- @expat("DefaultHandler")
- def characters(self, characters, start, length):
- # TODO: make a helper function here
- if self._entity["location"] == (self.parser.CurrentLineNumber,
- self.parser.CurrentColumnNumber):
- return "&%s;" % self._entity["name"]
- else:
- return self._char_slice_to_unicode(characters, start, length)
-
- @expat("StartNamespaceDeclHandler")
- def startPrefixMapping(self, prefix, uri):
- return prefix, uri
-
- @expat("EndNamespaceDeclHandler")
- def endPrefixMapping(self, prefix):
- return prefix
-
- def _empty_source(self, *args):
- name, publicId, baseURI, systemId = args
- source = InputSource()
- byte_stream = ByteArrayInputStream(array([], "b"))
- source.setByteStream(byte_stream)
- source.setPublicId(publicId)
- source.setSystemId(systemId)
- return source
-
- @expat("ExternalEntityRefHandler", guard="not self.dtd",
- returns="self._empty_source")
- def resolveEntity(self, name, publicId, baseURI, systemId):
- context = name # wrong. see expat headers documentation.
- base = self.parser.GetBase()
- return context, base, systemId, publicId
-
- @expat("DefaultHandlerExpand", guard="not self.dtd",
- returns="self._empty_source")
- def resolveEntity(self, name, publicId, baseURI, systemId):
- return "&%s;" % name
-
- @expat("DefaultHandler", guard="not self.dtd",
- returns="self._empty_source")
- def resolveEntity(self, name, publicId, baseURI, systemId):
- return "&%s;" % name
-
- @expat(force=True, returns="self._empty_source")
- def resolveEntity(self, name, publicId, baseURI, systemId):
- pass
-
- def setDocumentLocator(self, locator):
- self._locator = locator
-
- def skippedEntity(self, name):
- error = ExpatError()
- error.lineno = self.ErrorLineNumber = self.parser._NextLineNumber
- error.offset = self.ErrorColumnNumber = self.parser._NextColumnNumber
- error.code = self.ErrorCode = None
- message = "undefined entity &%s;: line %s, column %s"
- message = message % (name, error.lineno, error.offset)
- error.__init__(message)
- raise error
-
- # --- LexicalHandler Interface --------------------------------------------
-
- @expat("CommentHandler")
- def comment(self, characters, start, length):
- return self._char_slice_to_unicode(characters, start, length)
-
- @expat("StartCdataSectionHandler")
- def startCDATA(self):
- return ()
-
- @expat("EndCdataSectionHandler")
- def endCDATA(self):
- return ()
-
- @expat("StartDoctypeDeclHandler", force=True)
- def startDTD(self, name, publicId, systemId):
- self.dtd = True
- has_internal_subset = 0 # don't know this ...
- return name, systemId, publicId, has_internal_subset
-
- @expat("EndDoctypeDeclHandler", force=True)
- def endDTD(self):
- self.dtd = False
-
- def startEntity(self, name):
- self._entity = {}
- self._entity["location"] = (self.parser._NextLineNumber,
- self.parser._NextColumnNumber)
- self._entity["name"] = name
-
- def endEntity(self, name):
- pass
-
- # --- DTDHandler Interface ------------------------------------------------
-
- @expat("NotationDeclHandler")
- def notationDecl(self, name, publicId, systemId):
- base = self.parser.GetBase()
- return name, base, systemId, publicId
-
- @expat("UnparsedEntityDeclHandler") # deprecated
- def unparsedEntityDecl(self, name, publicId, systemId, notationName):
- base = self.parser.GetBase()
- return name, base, systemId, publicId, notationName
-
- # --- DeclHandler Interface -----------------------------------------------
-
- @expat("AttlistDeclHandler")
- def attributeDecl(self, eName, aName, type, mode, value):
- # TODO: adapt mode, required, etc.
- required = False
- return eName, aName, type, value, required
-
- @expat("ElementDeclHandler")
- def elementDecl(self, name, model):
- return self._expat_content_model(name, model)
-
- @expat("EntityDeclHandler")
- def externalEntityDecl(self, name, publicId, systemId):
- base = self.parser.GetBase()
- value = None
- is_parameter_entity = None
- notation_name = None
- return (name, is_parameter_entity, value, base, systemId, publicId,
- notation_name)
-
- @expat("EntityDeclHandler")
- def internalEntityDecl(self, name, value):
- base = self.parser.GetBase()
- is_parameter_entity = None
- notation_name = None
- systemId, publicId = None, None
- return (name, is_parameter_entity, value, base, systemId, publicId,
- notation_name)
-
-
-def _init_model():
- global model
- model = types.ModuleType("pyexpat.model")
- model.__doc__ = "Constants used to interpret content model information."
- quantifiers = "NONE, OPT, REP, PLUS"
- for i, quantifier in enumerate(quantifiers.split(", ")):
- setattr(model, "XML_CQUANT_" + quantifier, i)
- types_ = "EMPTY, ANY, MIXED, NAME, CHOICE, SEQ"
- for i, type_ in enumerate(types_.split(", ")):
- setattr(model, "XML_CTYPE_" + type_, i+1)
-
-_init_model()
-del _init_model
-
-
-class ExpatError(Exception):
- pass
-
-
-error = ExpatError
-
-
-def _init_error_strings():
- global ErrorString
- error_strings = (
- None,
- "out of memory",
- "syntax error",
- "no element found",
- "not well-formed (invalid token)",
- "unclosed token",
- "partial character",
- "mismatched tag",
- "duplicate attribute",
- "junk after document element",
- "illegal parameter entity reference",
- "undefined entity",
- "recursive entity reference",
- "asynchronous entity",
- "reference to invalid character number",
- "reference to binary entity",
- "reference to external entity in attribute",
- "XML or text declaration not at start of entity",
- "unknown encoding",
- "encoding specified in XML declaration is incorrect",
- "unclosed CDATA section",
- "error in processing external entity reference",
- "document is not standalone",
- "unexpected parser state - please send a bug report",
- "entity declared in parameter entity",
- "requested feature requires XML_DTD support in Expat",
- "cannot change setting once parsing has begun",
- "unbound prefix",
- "must not undeclare prefix",
- "incomplete markup in parameter entity",
- "XML declaration not well-formed",
- "text declaration not well-formed",
- "illegal character(s) in public id",
- "parser suspended",
- "parser not suspended",
- "parsing aborted",
- "parsing finished",
- "cannot suspend in external parameter entity")
- def ErrorString(code):
- try:
- return error_strings[code]
- except IndexError:
- return None
-
-_init_error_strings()
-del _init_error_strings
-
-
-def _init_errors():
- global errors
-
- errors = types.ModuleType("pyexpat.errors")
- errors.__doc__ = "Constants used to describe error conditions."
-
- error_names = """
- XML_ERROR_NONE
- XML_ERROR_NONE,
- XML_ERROR_NO_MEMORY,
- XML_ERROR_SYNTAX,
- XML_ERROR_NO_ELEMENTS,
- XML_ERROR_INVALID_TOKEN,
- XML_ERROR_UNCLOSED_TOKEN,
- XML_ERROR_PARTIAL_CHAR,
- XML_ERROR_TAG_MISMATCH,
- XML_ERROR_DUPLICATE_ATTRIBUTE,
- XML_ERROR_JUNK_AFTER_DOC_ELEMENT,
- XML_ERROR_PARAM_ENTITY_REF,
- XML_ERROR_UNDEFINED_ENTITY,
- XML_ERROR_RECURSIVE_ENTITY_REF,
- XML_ERROR_ASYNC_ENTITY,
- XML_ERROR_BAD_CHAR_REF,
- XML_ERROR_BINARY_ENTITY_REF,
- XML_ERROR_ATTRIBUTE_EXTERNAL_ENTITY_REF,
- XML_ERROR_MISPLACED_XML_PI,
- XML_ERROR_UNKNOWN_ENCODING,
- XML_ERROR_INCORRECT_ENCODING,
- XML_ERROR_UNCLOSED_CDATA_SECTION,
- XML_ERROR_EXTERNAL_ENTITY_HANDLING,
- XML_ERROR_NOT_STANDALONE,
- XML_ERROR_UNEXPECTED_STATE,
- XML_ERROR_ENTITY_DECLARED_IN_PE,
- XML_ERROR_FEATURE_REQUIRES_XML_DTD,
- XML_ERROR_CANT_CHANGE_FEATURE_ONCE_PARSING,
- XML_ERROR_UNBOUND_PREFIX,
- XML_ERROR_UNDECLARING_PREFIX,
- XML_ERROR_INCOMPLETE_PE,
- XML_ERROR_XML_DECL,
- XML_ERROR_TEXT_DECL,
- XML_ERROR_PUBLICID,
- XML_ERROR_SUSPENDED,
- XML_ERROR_NOT_SUSPENDED,
- XML_ERROR_ABORTED,
- XML_ERROR_FINISHED,
- XML_ERROR_SUSPEND_PE
- """
- error_names = [name.strip() for name in error_names.split(',')]
- for i, name in enumerate(error_names[1:]):
- setattr(errors, name, ErrorString(i+1))
-
-_init_errors()
-del _init_errors
Copied: branches/jy3k/Lib/xml/parsers/expat.py (from rev 5893, trunk/jython/Lib/xml/parsers/expat.py)
===================================================================
--- branches/jy3k/Lib/xml/parsers/expat.py (rev 0)
+++ branches/jy3k/Lib/xml/parsers/expat.py 2009-01-09 04:50:22 UTC (rev 5899)
@@ -0,0 +1,617 @@
+# coding: utf-8
+
+#------------------------------------------------------------------------------
+# Copyright (c) 2008 Sébastien Boisgérault
+#
+# 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.
+# -----------------------------------------------------------------------------
+
+__all__ = ["ExpatError", "ParserCreate", "XMLParserType", "error", "errors"]
+
+# Jython check
+import sys
+if not sys.platform.startswith('java'):
+ raise ImportError("this version of expat requires the jython interpreter")
+
+# Standard Python Library
+import re
+import types
+
+# Jython
+from org.python.core import Py
+from org.python.core.util import StringUtil
+from jarray import array
+
+# Java Standard Edition
+from java.io import ByteArrayInputStream
+from java.lang import String, StringBuilder
+from org.xml.sax import InputSource
+from org.xml.sax import SAXNotRecognizedException, SAXParseException
+from org.xml.sax.helpers import XMLReaderFactory
+from org.xml.sax.ext import DefaultHandler2
+
+# Xerces
+try:
+ # Name mangled by jarjar?
+ import org.python.apache.xerces.parsers.SAXParser
+ _xerces_parser = "org.python.apache.xerces.parsers.SAXParser"
+except ImportError:
+ _xerces_parser = "org.apache.xerces.parsers.SAXParser"
+
+
+def ParserCreate(encoding=None, namespace_separator=None):
+ return XMLParser(encoding, namespace_separator)
+
+
+class XMLParser(object):
+
+ def __init__(self, encoding, namespace_separator):
+ self.encoding = encoding
+ self.CurrentLineNumber = 1
+ self.CurrentColumnNumber = 0
+ self._NextLineNumber = 1
+ self._NextColumnNumber = 0
+ self.ErrorLineNumber = -1
+ self.ErrorColumnNumber = -1
+ self.ErrorCode = None
+
+ if namespace_separator is None:
+ self.namespace_separator = namespace_separator
+ elif isinstance(namespace_separator, basestring):
+ self.namespace_separator = str(namespace_separator)
+ if len(self.namespace_separator) > 1:
+ error = ("namespace_separator must be at most one character, "
+ "omitted, or None")
+ raise ValueError(error)
+ else:
+ error = ("ParserCreate() argument 2 must be string or None, "
+ "not %s" % type(namespace_separator).__name__)
+ raise TypeError(error)
+
+ self._reader = XMLReaderFactory.createXMLReader(_xerces_parser)
+
+ if self.namespace_separator is None:
+ try:
+ feature = "http://xml.org/sax/features/namespaces"
+ self._reader.setFeature(feature, False)
+ except SAXNotRecognizedException:
+ error = ("namespace support cannot be disabled; "
+ "set namespace_separator to a string of length 1.")
+ raise ValueError(error)
+
+ self._base = None
+ self._buffer_text = True
+ self._returns_unicode = True
+
+ self._data = StringBuilder()
+
+ self._handler = XMLEventHandler(self)
+ self._reader.setContentHandler(self._handler)
+ self._reader.setErrorHandler(self._handler)
+ self._reader.setDTDHandler(self._handler)
+ self._reader.setEntityResolver(self._handler)
+
+ sax_properties = ("lexical-handler", "declaration-handler")
+ for name in sax_properties:
+ try:
+ name = "http://xml.org/sax/properties/" + name
+ self._reader.setProperty(name, self._handler)
+ except SAXNotRecognizedException:
+ error = "can't set property %r" % name
+ raise NotImplementedError(error)
+
+ apache_features = (("nonvalidating/load-external-dtd", False),)
+ for name, value in apache_features:
+ try:
+ name = "http://apache.org/xml/features/" + name
+ self._reader.setFeature(name, value)
+ except SAXNotRecognizedException:
+ error = "can't set feature %r" % name
+ raise NotImplementedError(error)
+
+ # experimental
+ #f = "http://xml.org/sax/features/external-general-entities"
+ f = "http://xml.org/sax/features/external-parameter-entities"
+ #self._reader.setFeature(f, False)
+
+ # check
+ f = "http://xml.org/sax/features/use-entity-resolver2"
+ assert self._reader.getFeature(f)
+
+ def GetBase(self):
+ return self._base
+
+ def SetBase(self, base):
+ self._base = base
+
+ def _error(self, value=None):
+ raise AttributeError("'XMLParser' has no such attribute")
+
+ def _get_buffer_text(self):
+ return self._buffer_text
+
+ def _set_buffer_text(self, value):
+ self._buffer_text = bool(value)
+
+ def _get_returns_unicode(self):
+ return bool(self._returns_unicode)
+
+ def _set_returns_unicode(self, value):
+ self._returns_unicode = value
+
+ # 'ordered' and 'specified' attributes are not supported
+ ordered_attributes = property(_error, _error)
+ specified_attributes = property(_error, _error)
+ # any setting is allowed, but it won't make a difference
+ buffer_text = property(_get_buffer_text, _set_buffer_text)
+ # non-significant read-only values
+ buffer_used = property(lambda self: None)
+ buffer_size = property(lambda self: None)
+ # 'returns_unicode' attribute is properly supported
+ returns_unicode = property(_get_returns_unicode, _set_returns_unicode)
+
+ def _expat_error(self, sax_error):
+ sax_message = sax_error.getMessage()
+ pattern = 'The entity ".*" was referenced, but not declared\.'
+ if re.match(pattern, sax_message):
+ expat_message = "undefined entity: line %s, column %s" % \
+ (self.ErrorLineNumber, self.ErrorColumnNumber)
+ else:
+ expat_message = sax_message
+ error = ExpatError(expat_message)
+ error.lineno = self.ErrorLineNumber
+ error.offset = self.ErrorColumnNumber
+ error.code = self.ErrorCode
+ return error
+
+ def Parse(self, data, isfinal=False):
+ # The 'data' argument should be an encoded text: a str instance that
+ # represents an a...
[truncated message content] |
