From ianb at codespeak.net Tue Oct 2 00:24:09 2007
From: ianb at codespeak.net (ianb at codespeak.net)
Date: Tue, 2 Oct 2007 00:24:09 +0200 (CEST)
Subject: [Lxml-checkins] r47079 - lxml/trunk/src/lxml/html
Message-ID: <20071001222409.DD3168111@code0.codespeak.net>
Author: ianb
Date: Tue Oct 2 00:24:07 2007
New Revision: 47079
Modified:
lxml/trunk/src/lxml/html/setmixin.py
Log:
fix the in-place operators in SetMixin
Modified: lxml/trunk/src/lxml/html/setmixin.py
==============================================================================
--- lxml/trunk/src/lxml/html/setmixin.py (original)
+++ lxml/trunk/src/lxml/html/setmixin.py Tue Oct 2 00:24:07 2007
@@ -71,21 +71,27 @@
for item in other:
self.add(item)
- __ior__ = update
+ def __ior__(self, other):
+ self.update(other)
+ return self
def intersection_update(self, other):
for item in self:
if item not in other:
self.remove(item)
- __iand__ = intersection_update
+ def __iand__(self, other):
+ self.intersection_update(other)
+ return self
def difference_update(self, other):
for item in other:
if item in self:
self.remove(item)
- __isub__ = difference_update
+ def __isub__(self, other):
+ self.difference_update(other)
+ return self
def symmetric_difference_update(self, other):
for item in other:
@@ -94,7 +100,9 @@
else:
self.add(item)
- __ixor__ = symmetric_difference_update
+ def __ixor__(self, other):
+ self.symmetric_difference_update(other)
+ return self
def discard(self, item):
try:
From lxml-checkins at codespeak.net Thu Oct 4 23:42:44 2007
From: lxml-checkins at codespeak.net (VIAGRA ® Official Site)
Date: Thu, 4 Oct 2007 23:42:44 +0200 (CEST)
Subject: [Lxml-checkins] October 75% OFF
Message-ID: <20071004034331.7317.qmail@host75.201-252-1.telecom.net.ar>
An HTML attachment was scrubbed...
URL: http://codespeak.net/pipermail/lxml-checkins/attachments/20071004/e946f154/attachment.htm
From lxml-checkins at codespeak.net Fri Oct 5 17:54:08 2007
From: lxml-checkins at codespeak.net (lxml-checkins at codespeak.net)
Date: Fri, 5 Oct 2007 17:54:08 +0200 (CEST)
Subject: [Lxml-checkins] Check out what's new
Message-ID: <74047053679.3673357686918@delivery.net>
An HTML attachment was scrubbed...
URL: http://codespeak.net/pipermail/lxml-checkins/attachments/20071005/e44a8a2b/attachment.htm
From scoder at codespeak.net Sun Oct 7 06:30:36 2007
From: scoder at codespeak.net (scoder at codespeak.net)
Date: Sun, 7 Oct 2007 06:30:36 +0200 (CEST)
Subject: [Lxml-checkins] r47250 - in lxml/trunk: . src/lxml src/lxml/tests
Message-ID: <20071007043036.BD7A380FB@code0.codespeak.net>
Author: scoder
Date: Sun Oct 7 06:30:34 2007
New Revision: 47250
Modified:
lxml/trunk/CHANGES.txt
lxml/trunk/src/lxml/apihelpers.pxi
lxml/trunk/src/lxml/etree.pyx
lxml/trunk/src/lxml/tests/test_htmlparser.py
lxml/trunk/src/lxml/tests/test_unicode.py
Log:
let tag name validation distinguish HTML/XML tags based on the related parser, allow ':' in HTML tags
Modified: lxml/trunk/CHANGES.txt
==============================================================================
--- lxml/trunk/CHANGES.txt (original)
+++ lxml/trunk/CHANGES.txt Sun Oct 7 06:30:34 2007
@@ -16,9 +16,11 @@
Other changes
-------------
-* lxml.etree no longer validates unicode characters in tag names to
- avoid rejecting HTML tags. Only special characters like ':' and '>'
- are rejected.
+* Tag name validation in lxml.etree (and lxml.html) now distinguishes
+ between HTML tags and XML tags based on the parser that was used to
+ parse or create them. HTML tags no longer reject any non-ASCII
+ characters in tag names but only spaces and the special characters
+ '<>&/'.
2.0alpha3 (2007-09-26)
Modified: lxml/trunk/src/lxml/apihelpers.pxi
==============================================================================
--- lxml/trunk/src/lxml/apihelpers.pxi (original)
+++ lxml/trunk/src/lxml/apihelpers.pxi Sun Oct 7 06:30:34 2007
@@ -99,7 +99,10 @@
"""
cdef xmlNode* c_node
ns_utf, name_utf = _getNsTag(tag)
- _tagValidOrRaise(name_utf)
+ if parser is not None and parser._for_html:
+ _htmlTagValidOrRaise(name_utf)
+ else:
+ _tagValidOrRaise(name_utf)
if doc is not None:
c_doc = doc._c_doc
elif c_doc is NULL:
@@ -147,16 +150,22 @@
If 'c_doc' is also NULL, a new xmlDoc will be created.
"""
+ cdef _BaseParser parser
cdef _Document doc
cdef xmlNode* c_node
cdef xmlDoc* c_doc
if parent is None or parent._doc is None:
return None
ns_utf, name_utf = _getNsTag(tag)
- _tagValidOrRaise(name_utf)
doc = parent._doc
c_doc = doc._c_doc
+ parser = doc._parser
+ if parser is not None and parser._for_html:
+ _htmlTagValidOrRaise(name_utf)
+ else:
+ _tagValidOrRaise(name_utf)
+
c_node = _createElement(c_doc, name_utf)
if c_node is NULL:
python.PyErr_NoMemory()
@@ -175,6 +184,7 @@
cdef _initNodeAttributes(xmlNode* c_node, _Document doc, attrib, extra):
"""Initialise the attributes of an element node.
"""
+ cdef bint is_html
cdef xmlNs* c_ns
# 'extra' is not checked here (expected to be a keyword dict)
if attrib is not None and not hasattr(attrib, 'items'):
@@ -185,9 +195,11 @@
else:
attrib.update(extra)
if attrib:
+ is_html = doc._parser._for_html
for name, value in attrib.items():
attr_ns_utf, attr_name_utf = _getNsTag(name)
- _attributeValidOrRaise(attr_name_utf)
+ if not is_html:
+ _attributeValidOrRaise(attr_name_utf)
value_utf = _utf8(value)
if attr_ns_utf is None:
tree.xmlNewProp(c_node, _cstr(attr_name_utf), _cstr(value_utf))
@@ -242,7 +254,8 @@
cdef char* c_value
cdef char* c_tag
ns, tag = _getNsTag(key)
- _attributeValidOrRaise(tag)
+ if not element._doc._parser._for_html:
+ _attributeValidOrRaise(tag)
c_tag = _cstr(tag)
if isinstance(value, QName):
value = _resolveQNameText(element, value)
@@ -790,13 +803,17 @@
cdef int _pyXmlNameIsValid(name_utf8):
return _xmlNameIsValid(_cstr(name_utf8))
+cdef int _pyHtmlNameIsValid(name_utf8):
+ return _htmlNameIsValid(_cstr(name_utf8))
+
cdef int _xmlNameIsValid(char* c_name):
- #return tree.xmlValidateNCName(c_name, 0) == 0
+ return tree.xmlValidateNCName(c_name, 0) == 0
+
+cdef int _htmlNameIsValid(char* c_name):
if c_name is NULL or c_name[0] == c'\0':
return 0
while c_name[0] != c'\0':
- if c_name[0] == c':' or \
- c_name[0] == c'&' or \
+ if c_name[0] == c'&' or \
c_name[0] == c'<' or \
c_name[0] == c'>' or \
c_name[0] == c'/' or \
@@ -815,6 +832,12 @@
python.PyUnicode_FromEncodedObject(tag_utf, 'UTF-8', 'strict')
return 0
+cdef int _htmlTagValidOrRaise(tag_utf) except -1:
+ if not _pyHtmlNameIsValid(tag_utf):
+ raise ValueError, "Invalid HTML tag name %r" % \
+ python.PyUnicode_FromEncodedObject(tag_utf, 'UTF-8', 'strict')
+ return 0
+
cdef int _attributeValidOrRaise(name_utf) except -1:
if not _pyXmlNameIsValid(name_utf):
raise ValueError, "Invalid attribute name %r" % \
Modified: lxml/trunk/src/lxml/etree.pyx
==============================================================================
--- lxml/trunk/src/lxml/etree.pyx (original)
+++ lxml/trunk/src/lxml/etree.pyx Sun Oct 7 06:30:34 2007
@@ -707,8 +707,13 @@
return self._tag
def __set__(self, value):
+ cdef _BaseParser parser
ns, name = _getNsTag(value)
- _tagValidOrRaise(name)
+ parser = self._doc._parser
+ if parser is not None and parser._for_html:
+ _htmlTagValidOrRaise(name)
+ else:
+ _tagValidOrRaise(name)
self._tag = value
tree.xmlNodeSetName(self._c_node, _cstr(name))
if ns is None:
Modified: lxml/trunk/src/lxml/tests/test_htmlparser.py
==============================================================================
--- lxml/trunk/src/lxml/tests/test_htmlparser.py (original)
+++ lxml/trunk/src/lxml/tests/test_htmlparser.py Sun Oct 7 06:30:34 2007
@@ -39,6 +39,74 @@
self.assertRaises(self.etree.XMLSyntaxError,
parse, f, parser)
+ def test_html_element_name_empty(self):
+ parser = self.etree.HTMLParser()
+ Element = parser.makeelement
+
+ el = Element('name')
+ self.assertRaises(ValueError, Element, '{}')
+ self.assertRaises(ValueError, setattr, el, 'tag', '{}')
+
+ self.assertRaises(ValueError, Element, '{test}')
+ self.assertRaises(ValueError, setattr, el, 'tag', '{test}')
+
+ def test_html_element_name_colon(self):
+ parser = self.etree.HTMLParser()
+ Element = parser.makeelement
+
+ pname = Element('p:name')
+ self.assertEquals(pname.tag, 'p:name')
+
+ pname = Element('{test}p:name')
+ self.assertEquals(pname.tag, '{test}p:name')
+
+ pname = Element('name')
+ pname.tag = 'p:name'
+ self.assertEquals(pname.tag, 'p:name')
+
+ def test_html_element_name_space(self):
+ parser = self.etree.HTMLParser()
+ Element = parser.makeelement
+
+ self.assertRaises(ValueError, Element, ' name ')
+ self.assertRaises(ValueError, Element, 'na me')
+ self.assertRaises(ValueError, Element, '{test} name')
+
+ el = Element('name')
+ self.assertRaises(ValueError, setattr, el, 'tag', ' name ')
+
+ def test_html_subelement_name_empty(self):
+ parser = self.etree.HTMLParser()
+ Element = parser.makeelement
+
+ SubElement = self.etree.SubElement
+
+ el = Element('name')
+ self.assertRaises(ValueError, SubElement, el, '{}')
+ self.assertRaises(ValueError, SubElement, el, '{test}')
+
+ def test_html_subelement_name_colon(self):
+ parser = self.etree.HTMLParser()
+ Element = parser.makeelement
+ SubElement = self.etree.SubElement
+
+ el = Element('name')
+ pname = SubElement(el, 'p:name')
+ self.assertEquals(pname.tag, 'p:name')
+
+ pname = SubElement(el, '{test}p:name')
+ self.assertEquals(pname.tag, '{test}p:name')
+
+ def test_html_subelement_name_space(self):
+ parser = self.etree.HTMLParser()
+ Element = parser.makeelement
+ SubElement = self.etree.SubElement
+
+ el = Element('name')
+ self.assertRaises(ValueError, SubElement, el, ' name ')
+ self.assertRaises(ValueError, SubElement, el, 'na me')
+ self.assertRaises(ValueError, SubElement, el, '{test} name')
+
def test_module_parse_html_norecover(self):
parser = self.etree.HTMLParser(recover=False)
parse = self.etree.parse
Modified: lxml/trunk/src/lxml/tests/test_unicode.py
==============================================================================
--- lxml/trunk/src/lxml/tests/test_unicode.py (original)
+++ lxml/trunk/src/lxml/tests/test_unicode.py Sun Oct 7 06:30:34 2007
@@ -5,9 +5,9 @@
ascii_uni = u'a'
-# klingon = u"\uF8D2" # not valid for XML names
+klingon = u"\uF8D2" # not valid for XML names
-invalid_tag = "\u0680:\u3120"
+invalid_tag = "test" + klingon
uni = u'?\u0680\u3120' # some non-ASCII characters
From scoder at codespeak.net Sun Oct 7 06:32:49 2007
From: scoder at codespeak.net (scoder at codespeak.net)
Date: Sun, 7 Oct 2007 06:32:49 +0200 (CEST)
Subject: [Lxml-checkins] r47251 - in lxml/trunk: . doc
Message-ID: <20071007043249.5136B80FB@code0.codespeak.net>
Author: scoder
Date: Sun Oct 7 06:32:49 2007
New Revision: 47251
Modified:
lxml/trunk/CHANGES.txt
lxml/trunk/doc/main.txt
lxml/trunk/version.txt
Log:
2.0alpha4
Modified: lxml/trunk/CHANGES.txt
==============================================================================
--- lxml/trunk/CHANGES.txt (original)
+++ lxml/trunk/CHANGES.txt Sun Oct 7 06:32:49 2007
@@ -2,8 +2,9 @@
lxml changelog
==============
-Under development
-=================
+
+2.0alpha3 (2007-10-07)
+======================
Features added
--------------
Modified: lxml/trunk/doc/main.txt
==============================================================================
--- lxml/trunk/doc/main.txt (original)
+++ lxml/trunk/doc/main.txt Sun Oct 7 06:32:49 2007
@@ -138,8 +138,8 @@
.. _`lxml at the Python Package Index`: http://pypi.python.org/pypi/lxml/
.. _`this key`: pubkey.asc
-The latest version is `lxml 2.0alpha3`_, released 2007-09-26
-(`changes for 2.0alpha3`_). `Older versions`_ are listed below.
+The latest version is `lxml 2.0alpha4`_, released 2007-10-07
+(`changes for 2.0alpha4`_). `Older versions`_ are listed below.
.. _`Older versions`: #old-versions
@@ -199,6 +199,8 @@
Old Versions
------------
+* `lxml 2.0alpha3`_, released 2007-09-26 (`changes for 2.0alpha3`_)
+
* `lxml 2.0alpha2`_, released 2007-09-15 (`changes for 2.0alpha2`_)
* `lxml 2.0alpha1`_, released 2007-09-02 (`changes for 2.0alpha1`_)
Modified: lxml/trunk/version.txt
==============================================================================
--- lxml/trunk/version.txt (original)
+++ lxml/trunk/version.txt Sun Oct 7 06:32:49 2007
@@ -1 +1 @@
-2.0alpha3
+2.0alpha4
From scoder at codespeak.net Sun Oct 7 06:34:18 2007
From: scoder at codespeak.net (scoder at codespeak.net)
Date: Sun, 7 Oct 2007 06:34:18 +0200 (CEST)
Subject: [Lxml-checkins] r47252 - lxml/trunk/doc
Message-ID: <20071007043418.0354580FB@code0.codespeak.net>
Author: scoder
Date: Sun Oct 7 06:34:18 2007
New Revision: 47252
Modified:
lxml/trunk/doc/main.txt
Log:
2.0alpha4
Modified: lxml/trunk/doc/main.txt
==============================================================================
--- lxml/trunk/doc/main.txt (original)
+++ lxml/trunk/doc/main.txt Sun Oct 7 06:34:18 2007
@@ -251,6 +251,7 @@
* `lxml 0.5`_, released 2005-04-08
+.. _`lxml 2.0alpha4`: lxml-2.0alpha4.tgz
.. _`lxml 2.0alpha3`: lxml-2.0alpha3.tgz
.. _`lxml 2.0alpha2`: lxml-2.0alpha2.tgz
.. _`lxml 2.0alpha1`: lxml-2.0alpha1.tgz
@@ -277,6 +278,7 @@
.. _`lxml 0.5.1`: lxml-0.5.1.tgz
.. _`lxml 0.5`: lxml-0.5.tgz
+.. _`changes for 2.0alpha4`: changes-2.0alpha4.html
.. _`changes for 2.0alpha3`: changes-2.0alpha3.html
.. _`changes for 2.0alpha2`: changes-2.0alpha2.html
.. _`changes for 2.0alpha1`: changes-2.0alpha1.html
From scoder at codespeak.net Sun Oct 7 06:34:44 2007
From: scoder at codespeak.net (scoder at codespeak.net)
Date: Sun, 7 Oct 2007 06:34:44 +0200 (CEST)
Subject: [Lxml-checkins] r47253 - lxml/trunk
Message-ID: <20071007043444.51E6E80FB@code0.codespeak.net>
Author: scoder
Date: Sun Oct 7 06:34:44 2007
New Revision: 47253
Modified:
lxml/trunk/CHANGES.txt
Log:
2.0alpha4
Modified: lxml/trunk/CHANGES.txt
==============================================================================
--- lxml/trunk/CHANGES.txt (original)
+++ lxml/trunk/CHANGES.txt Sun Oct 7 06:34:44 2007
@@ -3,7 +3,7 @@
==============
-2.0alpha3 (2007-10-07)
+2.0alpha4 (2007-10-07)
======================
Features added
From scoder at codespeak.net Sun Oct 7 07:03:33 2007
From: scoder at codespeak.net (scoder at codespeak.net)
Date: Sun, 7 Oct 2007 07:03:33 +0200 (CEST)
Subject: [Lxml-checkins] r47254 - in lxml/trunk: . src/lxml src/lxml/tests
Message-ID: <20071007050333.809498113@code0.codespeak.net>
Author: scoder
Date: Sun Oct 7 07:03:32 2007
New Revision: 47254
Modified:
lxml/trunk/CHANGES.txt
lxml/trunk/src/lxml/apihelpers.pxi
lxml/trunk/src/lxml/tests/test_etree.py
lxml/trunk/src/lxml/tests/test_htmlparser.py
Log:
added " and ' to the list of invalid HTML tag characters
Modified: lxml/trunk/CHANGES.txt
==============================================================================
--- lxml/trunk/CHANGES.txt (original)
+++ lxml/trunk/CHANGES.txt Sun Oct 7 07:03:32 2007
@@ -21,7 +21,7 @@
between HTML tags and XML tags based on the parser that was used to
parse or create them. HTML tags no longer reject any non-ASCII
characters in tag names but only spaces and the special characters
- '<>&/'.
+ ``<>&/"'``.
2.0alpha3 (2007-09-26)
Modified: lxml/trunk/src/lxml/apihelpers.pxi
==============================================================================
--- lxml/trunk/src/lxml/apihelpers.pxi (original)
+++ lxml/trunk/src/lxml/apihelpers.pxi Sun Oct 7 07:03:32 2007
@@ -817,6 +817,8 @@
c_name[0] == c'<' or \
c_name[0] == c'>' or \
c_name[0] == c'/' or \
+ c_name[0] == c'"' or \
+ c_name[0] == c"'" or \
c_name[0] == c'\x09' or \
c_name[0] == c'\x0A' or \
c_name[0] == c'\x0B' or \
Modified: lxml/trunk/src/lxml/tests/test_etree.py
==============================================================================
--- lxml/trunk/src/lxml/tests/test_etree.py (original)
+++ lxml/trunk/src/lxml/tests/test_etree.py Sun Oct 7 07:03:32 2007
@@ -74,6 +74,18 @@
el = Element('name')
self.assertRaises(ValueError, setattr, el, 'tag', 'p:name')
+ def test_element_name_quote(self):
+ Element = self.etree.Element
+ self.assertRaises(ValueError, Element, "p'name")
+ self.assertRaises(ValueError, Element, 'p"name')
+
+ self.assertRaises(ValueError, Element, "{test}p'name")
+ self.assertRaises(ValueError, Element, '{test}p"name')
+
+ el = Element('name')
+ self.assertRaises(ValueError, setattr, el, 'tag', "p'name")
+ self.assertRaises(ValueError, setattr, el, 'tag', 'p"name')
+
def test_element_name_space(self):
Element = self.etree.Element
self.assertRaises(ValueError, Element, ' name ')
@@ -99,6 +111,17 @@
self.assertRaises(ValueError, SubElement, el, 'p:name')
self.assertRaises(ValueError, SubElement, el, '{test}p:name')
+ def test_subelement_name_quote(self):
+ Element = self.etree.Element
+ SubElement = self.etree.SubElement
+
+ el = Element('name')
+ self.assertRaises(ValueError, SubElement, el, "p'name")
+ self.assertRaises(ValueError, SubElement, el, "{test}p'name")
+
+ self.assertRaises(ValueError, SubElement, el, 'p"name')
+ self.assertRaises(ValueError, SubElement, el, '{test}p"name')
+
def test_subelement_name_space(self):
Element = self.etree.Element
SubElement = self.etree.SubElement
Modified: lxml/trunk/src/lxml/tests/test_htmlparser.py
==============================================================================
--- lxml/trunk/src/lxml/tests/test_htmlparser.py (original)
+++ lxml/trunk/src/lxml/tests/test_htmlparser.py Sun Oct 7 07:03:32 2007
@@ -64,6 +64,20 @@
pname.tag = 'p:name'
self.assertEquals(pname.tag, 'p:name')
+ def test_html_element_name_quote(self):
+ parser = self.etree.HTMLParser()
+ Element = parser.makeelement
+
+ self.assertRaises(ValueError, Element, 'p"name')
+ self.assertRaises(ValueError, Element, "na'me")
+ self.assertRaises(ValueError, Element, '{test}"name')
+ self.assertRaises(ValueError, Element, "{test}name'")
+
+ el = Element('name')
+ self.assertRaises(ValueError, setattr, el, 'tag', "pname'")
+ self.assertRaises(ValueError, setattr, el, 'tag', '"pname')
+ self.assertEquals(el.tag, "name")
+
def test_html_element_name_space(self):
parser = self.etree.HTMLParser()
Element = parser.makeelement
@@ -74,6 +88,7 @@
el = Element('name')
self.assertRaises(ValueError, setattr, el, 'tag', ' name ')
+ self.assertEquals(el.tag, "name")
def test_html_subelement_name_empty(self):
parser = self.etree.HTMLParser()
@@ -97,6 +112,17 @@
pname = SubElement(el, '{test}p:name')
self.assertEquals(pname.tag, '{test}p:name')
+ def test_html_subelement_name_quote(self):
+ parser = self.etree.HTMLParser()
+ Element = parser.makeelement
+ SubElement = self.etree.SubElement
+
+ el = Element('name')
+ self.assertRaises(ValueError, SubElement, el, "name'")
+ self.assertRaises(ValueError, SubElement, el, 'na"me')
+ self.assertRaises(ValueError, SubElement, el, "{test}na'me")
+ self.assertRaises(ValueError, SubElement, el, '{test}"name')
+
def test_html_subelement_name_space(self):
parser = self.etree.HTMLParser()
Element = parser.makeelement
From scoder at codespeak.net Sun Oct 7 22:12:25 2007
From: scoder at codespeak.net (scoder at codespeak.net)
Date: Sun, 7 Oct 2007 22:12:25 +0200 (CEST)
Subject: [Lxml-checkins] r47270 - lxml/trunk/doc
Message-ID: <20071007201225.4C1318188@code0.codespeak.net>
Author: scoder
Date: Sun Oct 7 22:12:23 2007
New Revision: 47270
Modified:
lxml/trunk/doc/lxml2.txt
Log:
docs
Modified: lxml/trunk/doc/lxml2.txt
==============================================================================
--- lxml/trunk/doc/lxml2.txt (original)
+++ lxml/trunk/doc/lxml2.txt Sun Oct 7 22:12:23 2007
@@ -78,7 +78,7 @@
type annotation on serialisation, you can use the ``deannotate()`` function.
* The C-API function ``findOrBuildNodeNs()`` was replaced by the more generic
- ``findOrBuildNodeNsPrefix()``
+ ``findOrBuildNodeNsPrefix()`` that accepts an additional default prefix.
Enhancements
From scoder at codespeak.net Mon Oct 8 21:57:08 2007
From: scoder at codespeak.net (scoder at codespeak.net)
Date: Mon, 8 Oct 2007 21:57:08 +0200 (CEST)
Subject: [Lxml-checkins] r47317 - lxml/trunk/src/lxml
Message-ID: <20071008195708.A49C3815A@code0.codespeak.net>
Author: scoder
Date: Mon Oct 8 21:57:08 2007
New Revision: 47317
Modified:
lxml/trunk/src/lxml/apihelpers.pxi
Log:
handle exceptions in subelement creation
Modified: lxml/trunk/src/lxml/apihelpers.pxi
==============================================================================
--- lxml/trunk/src/lxml/apihelpers.pxi (original)
+++ lxml/trunk/src/lxml/apihelpers.pxi Mon Oct 8 21:57:08 2007
@@ -171,15 +171,24 @@
python.PyErr_NoMemory()
tree.xmlAddChild(parent._c_node, c_node)
- if text is not None:
- _setNodeText(c_node, text)
- if tail is not None:
- _setTailText(c_node, tail)
-
- # add namespaces to node if necessary
- doc._setNodeNamespaces(c_node, ns_utf, nsmap)
- _initNodeAttributes(c_node, doc, attrib, extra_attrs)
- return _elementFactory(doc, c_node)
+ try:
+ if text is not None:
+ _setNodeText(c_node, text)
+ if tail is not None:
+ _setTailText(c_node, tail)
+
+ # add namespaces to node if necessary
+ doc._setNodeNamespaces(c_node, ns_utf, nsmap)
+ _initNodeAttributes(c_node, doc, attrib, extra_attrs)
+ return _elementFactory(doc, c_node)
+ except:
+ # free allocated c_node/c_doc unless Python does it for us
+ if c_node.doc is not c_doc:
+ # node not yet in document => will not be freed by document
+ if tail is not None:
+ _removeText(c_node.next) # tail
+ tree.xmlFreeNode(c_node)
+ raise
cdef _initNodeAttributes(xmlNode* c_node, _Document doc, attrib, extra):
"""Initialise the attributes of an element node.
From scoder at codespeak.net Mon Oct 8 22:00:20 2007
From: scoder at codespeak.net (scoder at codespeak.net)
Date: Mon, 8 Oct 2007 22:00:20 +0200 (CEST)
Subject: [Lxml-checkins] r47318 - in lxml/trunk: . src/lxml
Message-ID: <20071008200020.C380F80C9@code0.codespeak.net>
Author: scoder
Date: Mon Oct 8 22:00:20 2007
New Revision: 47318
Modified:
lxml/trunk/CHANGES.txt
lxml/trunk/src/lxml/etree.pyx
Log:
make namespace prefix counter a Python long to avoid crashes by counter overflow
Modified: lxml/trunk/CHANGES.txt
==============================================================================
--- lxml/trunk/CHANGES.txt (original)
+++ lxml/trunk/CHANGES.txt Mon Oct 8 22:00:20 2007
@@ -2,6 +2,21 @@
lxml changelog
==============
+Under development
+=================
+
+Features added
+--------------
+
+Bugs fixed
+----------
+
+* lxml.etree could crash when adding more than 10000 namespaces to a
+ document
+
+Other changes
+-------------
+
2.0alpha4 (2007-10-07)
======================
Modified: lxml/trunk/src/lxml/etree.pyx
==============================================================================
--- lxml/trunk/src/lxml/etree.pyx (original)
+++ lxml/trunk/src/lxml/etree.pyx Mon Oct 8 22:00:20 2007
@@ -229,7 +229,7 @@
When instances of this class are garbage collected, the libxml
document is cleaned up.
"""
- cdef int _ns_counter
+ cdef object _ns_counter
cdef xmlDoc* _c_doc
cdef _BaseParser _parser
@@ -295,7 +295,7 @@
return self._c_doc.URL
cdef buildNewPrefix(self):
- ns = python.PyString_FromFormat("ns%d", self._ns_counter)
+ ns = "ns%d" % self._ns_counter
self._ns_counter = self._ns_counter + 1
return ns
@@ -304,7 +304,6 @@
"""Get or create namespace structure for a node. Reuses the prefix if
possible.
"""
- cdef int i
cdef xmlNs* c_ns
cdef xmlNs* c_doc_ns
# look for existing ns
@@ -315,15 +314,12 @@
if c_prefix is NULL or \
tree.xmlSearchNs(self._c_doc, c_node, c_prefix) is not NULL:
# try to simulate ElementTree's namespace prefix creation
- for i from 0 <= i < 10000:
+ while 1:
prefix = self.buildNewPrefix()
c_prefix = _cstr(prefix)
# make sure it's not used already
if tree.xmlSearchNs(self._c_doc, c_node, c_prefix) is NULL:
break
- if i >= 10000:
- # XXX too many prefixes in use - this is pretty bad!
- return NULL
return tree.xmlNewNs(c_node, c_href, c_prefix)
@@ -333,8 +329,8 @@
c_ns = self._findOrBuildNodeNs(c_node, href, NULL)
tree.xmlSetNs(c_node, c_ns)
- cdef void _setNodeNamespaces(self, xmlNode* c_node,
- object node_ns_utf, object nsmap):
+ cdef int _setNodeNamespaces(self, xmlNode* c_node,
+ object node_ns_utf, object nsmap) except -1:
"""Lookup current namespace prefixes, then set namespace structure for
node and register new ns-prefix mappings.
@@ -347,7 +343,7 @@
if not nsmap:
if node_ns_utf is not None:
self._setNodeNs(c_node, _cstr(node_ns_utf))
- return
+ return 0
c_doc = self._c_doc
for prefix, href in nsmap.items():
@@ -368,6 +364,7 @@
if node_ns_utf is not None:
self._setNodeNs(c_node, _cstr(node_ns_utf))
+ return 0
cdef extern from "etree_defs.h":
# macro call to 't->tp_new()' for fast instantiation
@@ -377,7 +374,7 @@
cdef _Document result
result = NEW_DOCUMENT(_Document)
result._c_doc = c_doc
- result._ns_counter = 0
+ result._ns_counter = 0L
if parser is None:
parser = __GLOBAL_PARSER_CONTEXT.getDefaultParser()
result._parser = parser
From scoder at codespeak.net Mon Oct 8 22:59:19 2007
From: scoder at codespeak.net (scoder at codespeak.net)
Date: Mon, 8 Oct 2007 22:59:19 +0200 (CEST)
Subject: [Lxml-checkins] r47319 - in lxml/branch/lxml-1.3: . src/lxml
Message-ID: <20071008205919.961DE812D@code0.codespeak.net>
Author: scoder
Date: Mon Oct 8 22:59:18 2007
New Revision: 47319
Modified:
lxml/branch/lxml-1.3/CHANGES.txt
lxml/branch/lxml-1.3/src/lxml/etree.pyx
Log:
make namespace prefix counter a Python long to avoid crashes by counter overflow
Modified: lxml/branch/lxml-1.3/CHANGES.txt
==============================================================================
--- lxml/branch/lxml-1.3/CHANGES.txt (original)
+++ lxml/branch/lxml-1.3/CHANGES.txt Mon Oct 8 22:59:18 2007
@@ -11,6 +11,9 @@
Bugs fixed
----------
+* lxml.etree could crash when adding more than 10000 namespaces to a
+ document
+
* lxml failed to serialise namespace declarations of elements other than the
root node of a tree
Modified: lxml/branch/lxml-1.3/src/lxml/etree.pyx
==============================================================================
--- lxml/branch/lxml-1.3/src/lxml/etree.pyx (original)
+++ lxml/branch/lxml-1.3/src/lxml/etree.pyx Mon Oct 8 22:59:18 2007
@@ -231,7 +231,7 @@
When instances of this class are garbage collected, the libxml
document is cleaned up.
"""
- cdef int _ns_counter
+ cdef object _ns_counter
cdef xmlDoc* _c_doc
cdef _BaseParser _parser
@@ -297,7 +297,7 @@
return self._c_doc.URL
cdef buildNewPrefix(self):
- ns = python.PyString_FromFormat("ns%d", self._ns_counter)
+ ns = "ns%d" % self._ns_counter
self._ns_counter = self._ns_counter + 1
return ns
@@ -306,7 +306,6 @@
"""Get or create namespace structure for a node. Reuses the prefix if
possible.
"""
- cdef int i
cdef xmlNs* c_ns
cdef xmlNs* c_doc_ns
# look for existing ns
@@ -317,15 +316,12 @@
if c_prefix is NULL or \
tree.xmlSearchNs(self._c_doc, c_node, c_prefix) is not NULL:
# try to simulate ElementTree's namespace prefix creation
- for i from 0 <= i < 10000:
+ while 1:
prefix = self.buildNewPrefix()
c_prefix = _cstr(prefix)
# make sure it's not used already
if tree.xmlSearchNs(self._c_doc, c_node, c_prefix) is NULL:
break
- if i >= 10000:
- # XXX too many prefixes in use - this is pretty bad!
- return NULL
return tree.xmlNewNs(c_node, c_href, c_prefix)
@@ -335,8 +331,8 @@
c_ns = self._findOrBuildNodeNs(c_node, href, NULL)
tree.xmlSetNs(c_node, c_ns)
- cdef void _setNodeNamespaces(self, xmlNode* c_node,
- object node_ns_utf, object nsmap):
+ cdef int _setNodeNamespaces(self, xmlNode* c_node,
+ object node_ns_utf, object nsmap) except -1:
"""Lookup current namespace prefixes, then set namespace structure for
node and register new ns-prefix mappings.
@@ -349,7 +345,7 @@
if not nsmap:
if node_ns_utf is not None:
self._setNodeNs(c_node, _cstr(node_ns_utf))
- return
+ return 0
c_doc = self._c_doc
for prefix, href in nsmap.items():
@@ -370,12 +366,13 @@
if node_ns_utf is not None:
self._setNodeNs(c_node, _cstr(node_ns_utf))
+ return 0
cdef _Document _documentFactory(xmlDoc* c_doc, _BaseParser parser):
cdef _Document result
result = _Document()
result._c_doc = c_doc
- result._ns_counter = 0
+ result._ns_counter = 0L
if parser is None:
parser = __GLOBAL_PARSER_CONTEXT.getDefaultParser()
result._parser = parser
From scoder at codespeak.net Tue Oct 9 11:20:55 2007
From: scoder at codespeak.net (scoder at codespeak.net)
Date: Tue, 9 Oct 2007 11:20:55 +0200 (CEST)
Subject: [Lxml-checkins] r47326 - lxml/trunk/src/lxml
Message-ID: <20071009092055.7A8F080DA@code0.codespeak.net>
Author: scoder
Date: Tue Oct 9 11:20:53 2007
New Revision: 47326
Modified:
lxml/trunk/src/lxml/apihelpers.pxi
lxml/trunk/src/lxml/config.pxd
lxml/trunk/src/lxml/etree.pyx
lxml/trunk/src/lxml/etreepublic.pxd
lxml/trunk/src/lxml/iterparse.pxi
lxml/trunk/src/lxml/objectify.pyx
lxml/trunk/src/lxml/objectpath.pxi
lxml/trunk/src/lxml/parser.pxi
lxml/trunk/src/lxml/public-api.pxi
lxml/trunk/src/lxml/serializer.pxi
lxml/trunk/src/lxml/tree.pxd
lxml/trunk/src/lxml/xmlerror.pxi
Log:
use 'bint' instead of 'int' Pyrex type where appropriate
Modified: lxml/trunk/src/lxml/apihelpers.pxi
==============================================================================
--- lxml/trunk/src/lxml/apihelpers.pxi (original)
+++ lxml/trunk/src/lxml/apihelpers.pxi Tue Oct 9 11:20:53 2007
@@ -448,7 +448,7 @@
element._c_node, _cstr(ns), NULL)
return '%s:%s' % (c_ns.prefix, tag)
-cdef int _hasChild(xmlNode* c_node):
+cdef bint _hasChild(xmlNode* c_node):
return c_node is not NULL and _findChildForwards(c_node, 0) is not NULL
cdef xmlNode* _findChild(xmlNode* c_node, Py_ssize_t index):
@@ -534,7 +534,7 @@
return NULL
return c_node
-cdef int _tagMatches(xmlNode* c_node, char* c_href, char* c_name):
+cdef bint _tagMatches(xmlNode* c_node, char* c_href, char* c_name):
"""Tests if the node matches namespace URI and tag name.
A node matches if it matches both c_href and c_name.
@@ -697,7 +697,7 @@
cdef char* s
cdef char* c_end
cdef char c
- cdef int is_non_ascii
+ cdef bint is_non_ascii
s = _cstr(pystring)
c_end = s + python.PyString_GET_SIZE(pystring)
is_non_ascii = 0
Modified: lxml/trunk/src/lxml/config.pxd
==============================================================================
--- lxml/trunk/src/lxml/config.pxd (original)
+++ lxml/trunk/src/lxml/config.pxd Tue Oct 9 11:20:53 2007
@@ -1,3 +1,3 @@
cdef extern from "etree_defs.h":
- cdef int ENABLE_THREADING
- cdef int ENABLE_SCHEMATRON
+ cdef bint ENABLE_THREADING
+ cdef bint ENABLE_SCHEMATRON
Modified: lxml/trunk/src/lxml/etree.pyx
==============================================================================
--- lxml/trunk/src/lxml/etree.pyx (original)
+++ lxml/trunk/src/lxml/etree.pyx Tue Oct 9 11:20:53 2007
@@ -853,7 +853,6 @@
return c
def __nonzero__(self):
- cdef xmlNode* c_node
import warnings
warnings.warn(
"The behavior of this method will change in future versions. "
@@ -861,7 +860,7 @@
FutureWarning
)
# emulate old behaviour
- return bool(_hasChild(self._c_node))
+ return _hasChild(self._c_node)
def __contains__(self, element):
cdef xmlNode* c_node
@@ -1384,22 +1383,22 @@
The keyword argument 'method' selects the output method: 'xml' or
'html'.
"""
- cdef int c_write_declaration
+ cdef bint write_declaration
self._assertHasRoot()
# suppress decl. in default case (purely for ElementTree compatibility)
if xml_declaration is not None:
- c_write_declaration = bool(xml_declaration)
+ write_declaration = xml_declaration
if encoding is None:
encoding = 'ASCII'
elif encoding is None:
encoding = 'ASCII'
- c_write_declaration = 0
+ write_declaration = 0
else:
encoding = encoding.upper()
- c_write_declaration = encoding not in \
+ write_declaration = encoding not in \
('US-ASCII', 'ASCII', 'UTF8', 'UTF-8')
_tofilelike(file, self._context_node, encoding, method,
- c_write_declaration, 1, bool(pretty_print))
+ write_declaration, 1, pretty_print)
def getpath(self, _Element element not None):
"""Returns a structural, absolute XPath expression to find that element.
@@ -2164,7 +2163,7 @@
"""Writes an element tree or element structure to sys.stdout. This function
should be used for debugging only.
"""
- _dumpToFile(sys.stdout, elem._c_node, bool(pretty_print))
+ _dumpToFile(sys.stdout, elem._c_node, pretty_print)
def tostring(element_or_tree, encoding=None, method="xml",
xml_declaration=None, pretty_print=False):
@@ -2178,26 +2177,25 @@
The keyword argument 'pretty_print' (bool) enables formatted XML.
- The keyword argument 'method' selects the output method: 'xml' or 'html'.
+ The keyword argument 'method' selects the output method: 'xml',
+ 'html' or plain 'text'.
"""
- cdef int write_declaration
- cdef int c_pretty_print
- c_pretty_print = bool(pretty_print)
+ cdef bint write_declaration
if xml_declaration is None:
# by default, write an XML declaration only for non-standard encodings
write_declaration = encoding is not None and encoding.upper() not in \
('ASCII', 'UTF-8', 'UTF8', 'US-ASCII')
else:
- write_declaration = bool(xml_declaration)
+ write_declaration = xml_declaration
if encoding is None:
encoding = 'ASCII'
if isinstance(element_or_tree, _Element):
return _tostring(<_Element>element_or_tree, encoding, method,
- write_declaration, 0, c_pretty_print)
+ write_declaration, 0, pretty_print)
elif isinstance(element_or_tree, _ElementTree):
return _tostring((<_ElementTree>element_or_tree)._context_node,
- encoding, method, write_declaration, 1, c_pretty_print)
+ encoding, method, write_declaration, 1, pretty_print)
else:
raise TypeError, "Type '%s' cannot be serialized." % type(element_or_tree)
@@ -2218,17 +2216,16 @@
therefore not necessarily suited for serialization to byte streams without
further treatment.
- The keyword argument 'pretty_print' (bool) enables formatted XML.
+ The boolean keyword argument 'pretty_print' enables formatted XML.
- The keyword argument 'method' selects the output method: 'xml' or 'html'.
+ The keyword argument 'method' selects the output method: 'xml',
+ 'html' or plain 'text'.
"""
- cdef int c_pretty_print
- c_pretty_print = bool(pretty_print)
if isinstance(element_or_tree, _Element):
- return _tounicode(<_Element>element_or_tree, method, 0, c_pretty_print)
+ return _tounicode(<_Element>element_or_tree, method, 0, pretty_print)
elif isinstance(element_or_tree, _ElementTree):
return _tounicode((<_ElementTree>element_or_tree)._context_node,
- method, 1, c_pretty_print)
+ method, 1, pretty_print)
else:
raise TypeError, "Type '%s' cannot be serialized." % type(element_or_tree)
Modified: lxml/trunk/src/lxml/etreepublic.pxd
==============================================================================
--- lxml/trunk/src/lxml/etreepublic.pxd (original)
+++ lxml/trunk/src/lxml/etreepublic.pxd Tue Oct 9 11:20:53 2007
@@ -5,7 +5,7 @@
cdef extern from "etree_defs.h":
# test if c_node is considered an Element (i.e. Element, Comment, etc.)
- cdef int _isElement(tree.xmlNode* c_node)
+ cdef bint _isElement(tree.xmlNode* c_node)
# return the namespace URI of the node or NULL
cdef char* _getNs(tree.xmlNode* node)
@@ -129,7 +129,7 @@
# XML node helper functions
# check if the element has at least one child
- cdef int hasChild(tree.xmlNode* c_node)
+ cdef bint hasChild(tree.xmlNode* c_node)
# find child element number 'index' (supports negative indexes)
cdef tree.xmlNode* findChild(tree.xmlNode* c_node,
@@ -191,10 +191,10 @@
cdef object namespacedNameFromNsName(char* c_ns, char* c_tag)
# check if the node has a text value (which may be '')
- cdef int hasText(tree.xmlNode* c_node)
+ cdef bint hasText(tree.xmlNode* c_node)
# check if the node has a tail value (which may be '')
- cdef int hasTail(tree.xmlNode* c_node)
+ cdef bint hasTail(tree.xmlNode* c_node)
# get the text content of an element (or None)
cdef object textOf(tree.xmlNode* c_node)
Modified: lxml/trunk/src/lxml/iterparse.pxi
==============================================================================
--- lxml/trunk/src/lxml/iterparse.pxi (original)
+++ lxml/trunk/src/lxml/iterparse.pxi Tue Oct 9 11:20:53 2007
@@ -292,7 +292,6 @@
filename = _encodeFilename(filename)
self._source = source
- html = bool(html)
if html:
# make sure we're not looking for namespaces
if 'start' in events:
Modified: lxml/trunk/src/lxml/objectify.pyx
==============================================================================
--- lxml/trunk/src/lxml/objectify.pyx (original)
+++ lxml/trunk/src/lxml/objectify.pyx Tue Oct 9 11:20:53 2007
@@ -1045,7 +1045,7 @@
cdef object _makeelement
cdef object _namespace
cdef object _nsmap
- cdef int _annotate
+ cdef bint _annotate
def __init__(self, namespace=None, nsmap=None, annotate=True,
makeelement=None):
if nsmap is None:
@@ -1055,7 +1055,7 @@
self._namespace = None
else:
self._namespace = "{%s}" % namespace
- self._annotate = bool(annotate)
+ self._annotate = annotate
if makeelement is not None:
assert callable(makeelement)
self._makeelement = makeelement
@@ -1077,15 +1077,15 @@
cdef object _tag
cdef object _nsmap
cdef object _element_factory
- cdef int _annotate
+ cdef bint _annotate
def __call__(self, *children, **attrib):
cdef _ObjectifyElementMakerCaller elementMaker
cdef python.PyObject* pytype
cdef _Element element
cdef _Element childElement
- cdef int has_children
- cdef int has_string_value
+ cdef bint has_children
+ cdef bint has_string_value
if self._element_factory is None:
element = _makeElement(self._tag, None, attrib, self._nsmap)
else:
@@ -1153,7 +1153,7 @@
################################################################################
# Recursive element dumping
-cdef int __RECURSIVE_STR
+cdef bint __RECURSIVE_STR
__RECURSIVE_STR = 0 # default: off
def enableRecursiveStr(on=True):
@@ -1161,7 +1161,7 @@
based on objectify.dump(element).
"""
global __RECURSIVE_STR
- __RECURSIVE_STR = bool(on)
+ __RECURSIVE_STR = on
def dump(_Element element not None):
"""Return a recursively generated string representation of an element.
@@ -1323,8 +1323,7 @@
"""
cdef _Element element
element = cetree.rootNodeOrRaise(element_or_tree)
- _annotate(element, 0, 1, bool(ignore_xsi), bool(ignore_old),
- None, empty_pytype)
+ _annotate(element, 0, 1, ignore_xsi, ignore_old, None, empty_pytype)
def xsiannotate(element_or_tree, ignore_old=False, ignore_pytype=False,
empty_type=None):
@@ -1350,8 +1349,7 @@
"""
cdef _Element element
element = cetree.rootNodeOrRaise(element_or_tree)
- _annotate(element, 1, 0, bool(ignore_old), bool(ignore_pytype),
- empty_type, None)
+ _annotate(element, 1, 0, ignore_old, ignore_pytype, empty_type, None)
def annotate(element_or_tree, ignore_old=True, ignore_xsi=False,
empty_pytype=None, empty_type=None, annotate_xsi=0,
@@ -1386,12 +1384,12 @@
"""
cdef _Element element
element = cetree.rootNodeOrRaise(element_or_tree)
- _annotate(element, annotate_xsi, annotate_pytype, bool(ignore_xsi),
- bool(ignore_old), empty_type, empty_pytype)
+ _annotate(element, annotate_xsi, annotate_pytype, ignore_xsi,
+ ignore_old, empty_type, empty_pytype)
-cdef _annotate(_Element element, int annotate_xsi, int annotate_pytype,
- int ignore_xsi, int ignore_pytype,
+cdef _annotate(_Element element, bint annotate_xsi, bint annotate_pytype,
+ bint ignore_xsi, bint ignore_pytype,
empty_type_name, empty_pytype_name):
cdef _Document doc
cdef tree.xmlNode* c_node
Modified: lxml/trunk/src/lxml/objectpath.pxi
==============================================================================
--- lxml/trunk/src/lxml/objectpath.pxi (original)
+++ lxml/trunk/src/lxml/objectpath.pxi Tue Oct 9 11:20:53 2007
@@ -86,7 +86,7 @@
"""Parse object path string into a 'hrefOnameOhrefOnameOOO' string and an
index list. The index list is None if no index was used in the path.
"""
- cdef int has_dot
+ cdef bint has_dot
new_path = []
path = cetree.utf8(path.strip())
if path == '.':
Modified: lxml/trunk/src/lxml/parser.pxi
==============================================================================
--- lxml/trunk/src/lxml/parser.pxi (original)
+++ lxml/trunk/src/lxml/parser.pxi Tue Oct 9 11:20:53 2007
@@ -431,7 +431,7 @@
cdef object _handleParseResult(self, _BaseParser parser,
xmlDoc* result, filename):
cdef xmlDoc* c_doc
- cdef int recover
+ cdef bint recover
recover = parser._parse_options & xmlparser.XML_PARSE_RECOVER
c_doc = _handleParseResult(self, self._c_ctxt, result,
filename, recover)
@@ -439,7 +439,7 @@
cdef xmlDoc* _handleParseResultDoc(self, _BaseParser parser,
xmlDoc* result, filename) except NULL:
- cdef int recover
+ cdef bint recover
recover = parser._parse_options & xmlparser.XML_PARSE_RECOVER
return _handleParseResult(self, self._c_ctxt, result,
filename, recover)
@@ -481,8 +481,8 @@
cdef xmlDoc* _handleParseResult(_ParserContext context,
xmlparser.xmlParserCtxt* c_ctxt,
xmlDoc* result, filename,
- int recover) except NULL:
- cdef int well_formed
+ bint recover) except NULL:
+ cdef bint well_formed
if c_ctxt.myDoc is not NULL:
if c_ctxt.myDoc != result:
tree.xmlFreeDoc(c_ctxt.myDoc)
@@ -556,8 +556,8 @@
self._filename = filename
self._target = target
self._for_html = for_html
- self._remove_comments = bool(remove_comments)
- self._remove_pis = bool(remove_pis)
+ self._remove_comments = remove_comments
+ self._remove_pis = remove_pis
self._resolvers = _ResolverRegistry()
@@ -711,7 +711,6 @@
cdef python.PyThreadState* state
cdef xmlDoc* result
cdef xmlparser.xmlParserCtxt* pctxt
- cdef int recover
cdef Py_ssize_t py_buffer_len
cdef int buffer_len
cdef char* c_text
@@ -752,7 +751,6 @@
cdef python.PyThreadState* state
cdef xmlDoc* result
cdef xmlparser.xmlParserCtxt* pctxt
- cdef int recover
cdef char* c_encoding
if c_len > python.INT_MAX:
raise ParserError, "string is too long to parse it with libxml2"
@@ -788,7 +786,6 @@
cdef python.PyThreadState* state
cdef xmlDoc* result
cdef xmlparser.xmlParserCtxt* pctxt
- cdef int recover
cdef int orig_options
cdef char* c_encoding
result = NULL
@@ -825,7 +822,6 @@
cdef xmlDoc* result
cdef xmlparser.xmlParserCtxt* pctxt
cdef char* c_filename
- cdef int recover
if not filename:
filename = None
@@ -884,7 +880,6 @@
cdef char* c_encoding
cdef int buffer_len
cdef int error
- cdef int recover
if python.PyString_Check(data):
c_encoding = NULL
c_data = _cstr(data)
Modified: lxml/trunk/src/lxml/public-api.pxi
==============================================================================
--- lxml/trunk/src/lxml/public-api.pxi (original)
+++ lxml/trunk/src/lxml/public-api.pxi Tue Oct 9 11:20:53 2007
@@ -54,10 +54,10 @@
cdef public _Element rootNodeOrRaise(object input):
return _rootNodeOrRaise(input)
-cdef public int hasText(xmlNode* c_node):
+cdef public bint hasText(xmlNode* c_node):
return _hasText(c_node)
-cdef public int hasTail(xmlNode* c_node):
+cdef public bint hasTail(xmlNode* c_node):
return _hasTail(c_node)
cdef public object textOf(xmlNode* c_node):
@@ -106,7 +106,7 @@
char* c_href, char* c_name):
return _delAttributeFromNsName(c_element, c_href, c_name)
-cdef public int hasChild(xmlNode* c_node):
+cdef public bint hasChild(xmlNode* c_node):
return _hasChild(c_node)
cdef public xmlNode* findChild(xmlNode* c_node, Py_ssize_t index):
Modified: lxml/trunk/src/lxml/serializer.pxi
==============================================================================
--- lxml/trunk/src/lxml/serializer.pxi (original)
+++ lxml/trunk/src/lxml/serializer.pxi Tue Oct 9 11:20:53 2007
@@ -44,8 +44,8 @@
return python.PyUnicode_AsEncodedString(text, encoding, 'strict')
cdef _tostring(_Element element, encoding, method,
- int write_xml_declaration, int write_complete_document,
- int pretty_print):
+ bint write_xml_declaration, bint write_complete_document,
+ bint pretty_print):
"""Serialize an element to an encoded string representation of its XML
tree.
"""
@@ -96,7 +96,7 @@
return result
cdef _tounicode(_Element element, method,
- int write_complete_document, int pretty_print):
+ bint write_complete_document, bint pretty_print):
"""Serialize an element to the Python unicode representation of its XML
tree.
"""
@@ -133,9 +133,9 @@
cdef void _writeNodeToBuffer(tree.xmlOutputBuffer* c_buffer,
xmlNode* c_node, char* encoding, int c_method,
- int write_xml_declaration,
- int write_complete_document,
- int pretty_print):
+ bint write_xml_declaration,
+ bint write_complete_document,
+ bint pretty_print):
cdef xmlDoc* c_doc
cdef xmlNode* c_nsdecl_node
c_doc = c_node.doc
@@ -222,7 +222,7 @@
tree.xmlOutputBufferWrite(c_buffer, 3, "]>\n")
cdef void _writeTail(tree.xmlOutputBuffer* c_buffer, xmlNode* c_node,
- char* encoding, int pretty_print):
+ char* encoding, bint pretty_print):
"Write the element tail."
c_node = c_node.next
while c_node is not NULL and c_node.type == tree.XML_TEXT_NODE:
@@ -231,7 +231,7 @@
c_node = c_node.next
cdef void _writePrevSiblings(tree.xmlOutputBuffer* c_buffer, xmlNode* c_node,
- char* encoding, int pretty_print):
+ char* encoding, bint pretty_print):
cdef xmlNode* c_sibling
if c_node.parent is not NULL and _isElement(c_node.parent):
return
@@ -247,7 +247,7 @@
c_sibling = c_sibling.next
cdef void _writeNextSiblings(tree.xmlOutputBuffer* c_buffer, xmlNode* c_node,
- char* encoding, int pretty_print):
+ char* encoding, bint pretty_print):
cdef xmlNode* c_sibling
if c_node.parent is not NULL and _isElement(c_node.parent):
return
@@ -307,8 +307,8 @@
return (<_FilelikeWriter>ctxt).close()
cdef _tofilelike(f, _Element element, encoding, method,
- int write_xml_declaration, int write_doctype,
- int pretty_print):
+ bint write_xml_declaration, bint write_doctype,
+ bint pretty_print):
cdef python.PyThreadState* state
cdef _FilelikeWriter writer
cdef tree.xmlOutputBuffer* c_buffer
@@ -400,7 +400,7 @@
# dump node to file (mainly for debug)
-cdef _dumpToFile(f, xmlNode* c_node, int pretty_print):
+cdef _dumpToFile(f, xmlNode* c_node, bint pretty_print):
cdef tree.xmlOutputBuffer* c_buffer
if not python.PyFile_Check(f):
raise ValueError, "Not a file"
Modified: lxml/trunk/src/lxml/tree.pxd
==============================================================================
--- lxml/trunk/src/lxml/tree.pxd (original)
+++ lxml/trunk/src/lxml/tree.pxd Tue Oct 9 11:20:53 2007
@@ -300,9 +300,9 @@
cdef void* xmlMalloc(size_t size)
cdef extern from "etree_defs.h":
- cdef int _isElement(xmlNode* node)
- cdef int _isElementOrXInclude(xmlNode* node)
+ cdef bint _isElement(xmlNode* node)
+ cdef bint _isElementOrXInclude(xmlNode* node)
cdef char* _getNs(xmlNode* node)
cdef void BEGIN_FOR_EACH_ELEMENT_FROM(xmlNode* tree_top,
- xmlNode* start_node, int inclusive)
+ xmlNode* start_node, bint inclusive)
cdef void END_FOR_EACH_ELEMENT_FROM(xmlNode* start_node)
Modified: lxml/trunk/src/lxml/xmlerror.pxi
==============================================================================
--- lxml/trunk/src/lxml/xmlerror.pxi (original)
+++ lxml/trunk/src/lxml/xmlerror.pxi Tue Oct 9 11:20:53 2007
@@ -98,7 +98,7 @@
return ''
cdef void _receive(self, xmlerror.xmlError* error):
- cdef int is_error
+ cdef bint is_error
cdef _LogEntry entry
entry = _LogEntry()
entry._setError(error)
@@ -114,6 +114,7 @@
cdef void _receiveGeneric(self, int domain, int type, int level, int line,
message, filename):
+ cdef bint is_error
cdef _LogEntry entry
entry = _LogEntry()
entry._setGeneric(domain, type, level, line, message, filename)
@@ -184,7 +185,9 @@
return False
def __nonzero__(self):
- return bool(self._entries)
+ cdef bint result
+ result = self._entries
+ return result
def filter_domains(self, domains):
"""Filter the errors by the given domains and return a new error log
From scoder at codespeak.net Tue Oct 9 12:02:21 2007
From: scoder at codespeak.net (scoder at codespeak.net)
Date: Tue, 9 Oct 2007 12:02:21 +0200 (CEST)
Subject: [Lxml-checkins] r47330 - lxml/trunk/src/lxml
Message-ID: <20071009100221.2483081A8@code0.codespeak.net>
Author: scoder
Date: Tue Oct 9 12:02:20 2007
New Revision: 47330
Modified:
lxml/trunk/src/lxml/etree.pyx
Log:
keep prefix counter a C integer, change formatting string instead
Modified: lxml/trunk/src/lxml/etree.pyx
==============================================================================
--- lxml/trunk/src/lxml/etree.pyx (original)
+++ lxml/trunk/src/lxml/etree.pyx Tue Oct 9 12:02:20 2007
@@ -229,7 +229,8 @@
When instances of this class are garbage collected, the libxml
document is cleaned up.
"""
- cdef object _ns_counter
+ cdef unsigned int _ns_counter
+ cdef object _prefix_format
cdef xmlDoc* _c_doc
cdef _BaseParser _parser
@@ -295,8 +296,12 @@
return self._c_doc.URL
cdef buildNewPrefix(self):
- ns = "ns%d" % self._ns_counter
+ ns = python.PyString_FromFormat(
+ _cstr(self._prefix_format), self._ns_counter)
self._ns_counter = self._ns_counter + 1
+ if self._ns_counter == 0:
+ # overflow!
+ self._prefix_format = self._prefix_format + "A"
return ns
cdef xmlNs* _findOrBuildNodeNs(self, xmlNode* c_node,
@@ -374,7 +379,8 @@
cdef _Document result
result = NEW_DOCUMENT(_Document)
result._c_doc = c_doc
- result._ns_counter = 0L
+ result._ns_counter = 0
+ result._prefix_format = "ns%lu"
if parser is None:
parser = __GLOBAL_PARSER_CONTEXT.getDefaultParser()
result._parser = parser
From scoder at codespeak.net Tue Oct 9 12:02:54 2007
From: scoder at codespeak.net (scoder at codespeak.net)
Date: Tue, 9 Oct 2007 12:02:54 +0200 (CEST)
Subject: [Lxml-checkins] r47331 - lxml/branch/lxml-1.3/src/lxml
Message-ID: <20071009100254.4B17581A8@code0.codespeak.net>
Author: scoder
Date: Tue Oct 9 12:02:53 2007
New Revision: 47331
Modified:
lxml/branch/lxml-1.3/src/lxml/etree.pyx
Log:
keep prefix counter a C integer, change formatting string instead
Modified: lxml/branch/lxml-1.3/src/lxml/etree.pyx
==============================================================================
--- lxml/branch/lxml-1.3/src/lxml/etree.pyx (original)
+++ lxml/branch/lxml-1.3/src/lxml/etree.pyx Tue Oct 9 12:02:53 2007
@@ -231,7 +231,8 @@
When instances of this class are garbage collected, the libxml
document is cleaned up.
"""
- cdef object _ns_counter
+ cdef unsigned int _ns_counter
+ cdef object _prefix_format
cdef xmlDoc* _c_doc
cdef _BaseParser _parser
@@ -297,8 +298,12 @@
return self._c_doc.URL
cdef buildNewPrefix(self):
- ns = "ns%d" % self._ns_counter
+ ns = python.PyString_FromFormat(
+ _cstr(self._prefix_format), self._ns_counter)
self._ns_counter = self._ns_counter + 1
+ if self._ns_counter == 0:
+ # overflow!
+ self._prefix_format = self._prefix_format + "A"
return ns
cdef xmlNs* _findOrBuildNodeNs(self, xmlNode* c_node,
@@ -372,7 +377,8 @@
cdef _Document result
result = _Document()
result._c_doc = c_doc
- result._ns_counter = 0L
+ result._ns_counter = 0
+ result._prefix_format = "ns%lu"
if parser is None:
parser = __GLOBAL_PARSER_CONTEXT.getDefaultParser()
result._parser = parser
From scoder at codespeak.net Tue Oct 9 14:56:29 2007
From: scoder at codespeak.net (scoder at codespeak.net)
Date: Tue, 9 Oct 2007 14:56:29 +0200 (CEST)
Subject: [Lxml-checkins] r47343 - lxml/trunk/doc
Message-ID: <20071009125629.8F4DE81B1@code0.codespeak.net>
Author: scoder
Date: Tue Oct 9 14:56:29 2007
New Revision: 47343
Modified:
lxml/trunk/doc/build.txt
Log:
typo
Modified: lxml/trunk/doc/build.txt
==============================================================================
--- lxml/trunk/doc/build.txt (original)
+++ lxml/trunk/doc/build.txt Tue Oct 9 14:56:29 2007
@@ -223,7 +223,7 @@
version numbers::
STATIC_INCLUDE_DIRS = [
- "..\\libxml2-2.6.23.win32\\include ",
+ "..\\libxml2-2.6.23.win32\\include",
"..\\libxslt-1.1.15.win32\\include",
"..\\zlib-1.2.3.win32\\include",
"..\\iconv-1.9.1.win32\\include"
From scoder at codespeak.net Tue Oct 9 14:57:07 2007
From: scoder at codespeak.net (scoder at codespeak.net)
Date: Tue, 9 Oct 2007 14:57:07 +0200 (CEST)
Subject: [Lxml-checkins] r47344 - lxml/branch/lxml-1.3/doc
Message-ID: <20071009125707.98E2280C7@code0.codespeak.net>
Author: scoder
Date: Tue Oct 9 14:57:07 2007
New Revision: 47344
Modified:
lxml/branch/lxml-1.3/doc/build.txt
Log:
typo
Modified: lxml/branch/lxml-1.3/doc/build.txt
==============================================================================
--- lxml/branch/lxml-1.3/doc/build.txt (original)
+++ lxml/branch/lxml-1.3/doc/build.txt Tue Oct 9 14:57:07 2007
@@ -250,7 +250,7 @@
version numbers::
STATIC_INCLUDE_DIRS = [
- "..\\libxml2-2.6.23.win32\\include ",
+ "..\\libxml2-2.6.23.win32\\include",
"..\\libxslt-1.1.15.win32\\include",
"..\\zlib-1.2.3.win32\\include",
"..\\iconv-1.9.1.win32\\include"
From scoder at codespeak.net Tue Oct 9 15:03:40 2007
From: scoder at codespeak.net (scoder at codespeak.net)
Date: Tue, 9 Oct 2007 15:03:40 +0200 (CEST)
Subject: [Lxml-checkins] r47346 - lxml/trunk/doc
Message-ID: <20071009130340.0048481B1@code0.codespeak.net>
Author: scoder
Date: Tue Oct 9 15:03:40 2007
New Revision: 47346
Modified:
lxml/trunk/doc/build.txt
Log:
removed doc leftover
Modified: lxml/trunk/doc/build.txt
==============================================================================
--- lxml/trunk/doc/build.txt (original)
+++ lxml/trunk/doc/build.txt Tue Oct 9 15:03:40 2007
@@ -232,7 +232,6 @@
STATIC_LIBRARY_DIRS = [
"..\\libxml2-2.6.23.win32\\lib",
"..\\libxslt-1.1.15.win32\\lib",
- "..\\libxslt-1.1.15.win32\\lib",
"..\\zlib-1.2.3.win32\\lib",
"..\\iconv-1.9.1.win32\\lib"
]
From scoder at codespeak.net Tue Oct 9 15:03:54 2007
From: scoder at codespeak.net (scoder at codespeak.net)
Date: Tue, 9 Oct 2007 15:03:54 +0200 (CEST)
Subject: [Lxml-checkins] r47347 - lxml/branch/lxml-1.3/doc
Message-ID: <20071009130354.9DF7381B1@code0.codespeak.net>
Author: scoder
Date: Tue Oct 9 15:03:54 2007
New Revision: 47347
Modified:
lxml/branch/lxml-1.3/doc/build.txt
Log:
removed doc leftover
Modified: lxml/branch/lxml-1.3/doc/build.txt
==============================================================================
--- lxml/branch/lxml-1.3/doc/build.txt (original)
+++ lxml/branch/lxml-1.3/doc/build.txt Tue Oct 9 15:03:54 2007
@@ -259,7 +259,6 @@
STATIC_LIBRARY_DIRS = [
"..\\libxml2-2.6.23.win32\\lib",
"..\\libxslt-1.1.15.win32\\lib",
- "..\\libxslt-1.1.15.win32\\lib",
"..\\zlib-1.2.3.win32\\lib",
"..\\iconv-1.9.1.win32\\lib"
]
From scoder at codespeak.net Wed Oct 10 09:13:13 2007
From: scoder at codespeak.net (scoder at codespeak.net)
Date: Wed, 10 Oct 2007 09:13:13 +0200 (CEST)
Subject: [Lxml-checkins] r47366 - lxml/trunk/doc
Message-ID: <20071010071313.983FC81E0@code0.codespeak.net>
Author: scoder
Date: Wed Oct 10 09:13:10 2007
New Revision: 47366
Modified:
lxml/trunk/doc/lxmlhtml.txt
Log:
doc fix
Modified: lxml/trunk/doc/lxmlhtml.txt
==============================================================================
--- lxml/trunk/doc/lxmlhtml.txt (original)
+++ lxml/trunk/doc/lxmlhtml.txt Wed Oct 10 09:13:10 2007
@@ -2,9 +2,9 @@
lxml.html
=========
-Since version 2.0, lxml provides a dedicated package for dealing with HTML:
-``lxml.html``. It provides a special Element API for HTML elements, as well
-as a number of utilities for common tasks.
+Since version 2.0, lxml comes with a dedicated package for dealing
+with HTML: ``lxml.html``. It provides a special Element API for HTML
+elements, as well as a number of utilities for common tasks.
.. contents::
..
From scoder at codespeak.net Wed Oct 10 09:19:28 2007
From: scoder at codespeak.net (scoder at codespeak.net)
Date: Wed, 10 Oct 2007 09:19:28 +0200 (CEST)
Subject: [Lxml-checkins] r47367 - lxml/trunk/doc
Message-ID: <20071010071928.8AA9181E5@code0.codespeak.net>
Author: scoder
Date: Wed Oct 10 09:19:28 2007
New Revision: 47367
Modified:
lxml/trunk/doc/lxmlhtml.txt
Log:
doc fix
Modified: lxml/trunk/doc/lxmlhtml.txt
==============================================================================
--- lxml/trunk/doc/lxmlhtml.txt (original)
+++ lxml/trunk/doc/lxmlhtml.txt Wed Oct 10 09:19:28 2007
@@ -37,7 +37,8 @@
If you give a URL, or if the object has a ``.geturl()`` method (as
file-like objects from ``urllib.urlopen()`` have), then that URL
- is used as the base URL.
+ is used as the base URL. You can also provide an explicit
+ ``base_url`` keyword argument.
``document_fromstring(string)``:
Parses a document from the given string. This always creates a
From scoder at codespeak.net Wed Oct 10 11:22:38 2007
From: scoder at codespeak.net (scoder at codespeak.net)
Date: Wed, 10 Oct 2007 11:22:38 +0200 (CEST)
Subject: [Lxml-checkins] r47375 - lxml/trunk
Message-ID: <20071010092238.D7EDD81E6@code0.codespeak.net>
Author: scoder
Date: Wed Oct 10 11:22:37 2007
New Revision: 47375
Modified:
lxml/trunk/setup.py
lxml/trunk/setupinfo.py
lxml/trunk/versioninfo.py
Log:
Py3 syntax fixes in build scripts
Modified: lxml/trunk/setup.py
==============================================================================
--- lxml/trunk/setup.py (original)
+++ lxml/trunk/setup.py Wed Oct 10 11:22:37 2007
@@ -38,7 +38,7 @@
# create lxml-version.h file
svn_version = versioninfo.svn_version()
versioninfo.create_version_h(svn_version)
-print "Building lxml version", svn_version
+print("Building lxml version %s." % svn_version)
branch_link = """
Modified: lxml/trunk/setupinfo.py
==============================================================================
--- lxml/trunk/setupinfo.py (original)
+++ lxml/trunk/setupinfo.py Wed Oct 10 11:22:37 2007
@@ -3,7 +3,7 @@
try:
from Cython.Distutils import build_ext as build_pyx
- print "Building with Cython."
+ print("Building with Cython.")
CYTHON_INSTALLED = True
except ImportError:
CYTHON_INSTALLED = False
@@ -131,13 +131,21 @@
return macros
def flags(cmd):
- wf, rf, ef = os.popen3(cmd)
+ try:
+ import subprocess
+ except ImportError:
+ # Python 2.3
+ _, rf, ef = os.popen3(cmd)
+ else:
+ # Python 2.4+
+ p = subprocess.Popen(cmd, shell=True, close_fds=True,
+ stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+ rf, ef = p.stdout, p.stderr
errors = ef.read()
if errors:
- print "ERROR:", errors
- print "** make sure the development packages of libxml2 and libxslt are installed **"
- print
- return rf.read().split()
+ print("ERROR: %s" % errors)
+ print("** make sure the development packages of libxml2 and libxslt are installed **\n")
+ return str(rf.read()).split()
def has_option(name):
try:
Modified: lxml/trunk/versioninfo.py
==============================================================================
--- lxml/trunk/versioninfo.py (original)
+++ lxml/trunk/versioninfo.py Wed Oct 10 11:22:37 2007
@@ -35,7 +35,7 @@
if data.startswith('8'):
# SVN >= 1.4
- data = map(str.splitlines, data.split('\n\x0c\n'))
+ data = [ d.splitlines() for d in data.split('\n\x0c\n') ]
del data[0][0] # get rid of the '8'
dirurl = data[0][3]
try:
From ianb at codespeak.net Sun Oct 14 02:12:32 2007
From: ianb at codespeak.net (ianb at codespeak.net)
Date: Sun, 14 Oct 2007 02:12:32 +0200 (CEST)
Subject: [Lxml-checkins] r47440 - in lxml/trunk: . src/lxml
Message-ID: <20071014001232.1B0708165@code0.codespeak.net>
Author: ianb
Date: Sun Oct 14 02:12:31 2007
New Revision: 47440
Modified:
lxml/trunk/CHANGES.txt
lxml/trunk/src/lxml/doctestcompare.py
Log:
Improve doctestcompare a little: NOPARSE_MARKUP option to suppress its behavior, and xmlns=... now works
Modified: lxml/trunk/CHANGES.txt
==============================================================================
--- lxml/trunk/CHANGES.txt (original)
+++ lxml/trunk/CHANGES.txt Sun Oct 14 02:12:31 2007
@@ -8,12 +8,20 @@
Features added
--------------
+* When using ``lxml.doctestcompare`` you can give the doctest option
+ ``NOPARSE_MARKUP`` (like ``# doctest: +NOPARSE_MARKUP``) to suppress
+ the special checking for one test.
+
Bugs fixed
----------
* lxml.etree could crash when adding more than 10000 namespaces to a
document
+* With ``lxml.doctestcompare`` if you do ```` in your
+ output, it will then be namespace-neutral (before the ellipsis was
+ treated as a real namespace).
+
Other changes
-------------
Modified: lxml/trunk/src/lxml/doctestcompare.py
==============================================================================
--- lxml/trunk/src/lxml/doctestcompare.py (original)
+++ lxml/trunk/src/lxml/doctestcompare.py Sun Oct 14 02:12:31 2007
@@ -23,6 +23,8 @@
displayed (indented), and a rough diff-like output is given. Anything
marked with ``-`` is in the output but wasn't supposed to be, and
similarly ``+`` means its in the example but wasn't in the output.
+
+You can disable parsing on one line with ``# doctest:+NOPARSE_MARKUP``
"""
from lxml import etree
@@ -36,6 +38,7 @@
PARSE_HTML = doctest.register_optionflag('PARSE_HTML')
PARSE_XML = doctest.register_optionflag('PARSE_XML')
+NOPARSE_MARKUP = doctest.register_optionflag('NOPARSE_MARKUP')
OutputChecker = doctest.OutputChecker
@@ -84,6 +87,8 @@
def get_parser(self, want, got, optionflags):
parser = None
+ if NOPARSE_MARKUP & optionflags:
+ return None
if PARSE_HTML & optionflags:
parser = document_fromstring
elif PARSE_XML & optionflags:
@@ -102,7 +107,7 @@
and not _repr_re.search(s))
def compare_docs(self, want, got):
- if want.tag != got.tag and want.tag != 'any':
+ if not self.tag_compare(want.tag, got.tag):
return False
if not self.text_compare(want.text, got.text, True):
return False
@@ -143,6 +148,17 @@
else:
return False
+ def tag_compare(self, want, got):
+ if want == 'any':
+ return True
+ want = want or ''
+ got = got or ''
+ if want.startswith('{...}'):
+ # Ellipsis on the namespace
+ return want.split('}')[-1] == got.split('}')[-1]
+ else:
+ return want == got
+
def output_difference(self, example, got, optionflags):
want = example.want
parser = self.get_parser(want, got, optionflags)
@@ -282,7 +298,7 @@
return ''.join(parts)
def collect_diff_tag(self, want, got):
- if want.tag != got.tag and want.tag != 'any':
+ if not self.tag_compare(want.tag, got.tag):
tag = '%s (got: %s)' % (want.tag, got.tag)
else:
tag = got.tag
@@ -431,3 +447,21 @@
raise LookupError(
"Could not find doctest (only use this function *inside* a doctest)")
+__test__ = {
+ 'basic': '''
+ >>> temp_install()
+ >>> print """stuff"""
+ ...
+ >>> print """"""
+
+
+
+ >>> print """blahblahblah""" # doctest: +NOPARSE_MARKUP, +ELLIPSIS
+ ...foo />
+ '''}
+
+if __name__ == '__main__':
+ import doctest
+ doctest.testmod()
+
+
From scoder at codespeak.net Mon Oct 15 18:28:00 2007
From: scoder at codespeak.net (scoder at codespeak.net)
Date: Mon, 15 Oct 2007 18:28:00 +0200 (CEST)
Subject: [Lxml-checkins] r47468 - lxml/trunk/src/lxml
Message-ID: <20071015162800.944FE8102@code0.codespeak.net>
Author: scoder
Date: Mon Oct 15 18:27:59 2007
New Revision: 47468
Modified:
lxml/trunk/src/lxml/apihelpers.pxi
Log:
faster attribute collecting, _countElements() helper function
Modified: lxml/trunk/src/lxml/apihelpers.pxi
==============================================================================
--- lxml/trunk/src/lxml/apihelpers.pxi (original)
+++ lxml/trunk/src/lxml/apihelpers.pxi Mon Oct 15 18:27:59 2007
@@ -307,9 +307,21 @@
"""Collect all attributes of a node in a list. Depending on collecttype,
it collects either the name (1), the value (2) or the name-value tuples.
"""
+ cdef Py_ssize_t count
cdef xmlAttr* c_attr
c_attr = c_node.properties
- attributes = []
+ count = 0
+ while c_attr is not NULL:
+ if c_attr.type == tree.XML_ATTRIBUTE_NODE:
+ count = count + 1
+ c_attr = c_attr.next
+
+ if count == 0:
+ return []
+
+ attributes = python.PyList_New(count)
+ c_attr = c_node.properties
+ count = 0
while c_attr is not NULL:
if c_attr.type == tree.XML_ATTRIBUTE_NODE:
if collecttype == 1:
@@ -320,9 +332,9 @@
item = (_namespacedName(c_attr),
_attributeValue(c_node, c_attr))
- ret = python.PyList_Append(attributes, item)
- if ret:
- raise
+ python.Py_INCREF(item)
+ python.PyList_SET_ITEM(attributes, count, item)
+ count = count + 1
c_attr = c_attr.next
return attributes
@@ -451,6 +463,16 @@
cdef bint _hasChild(xmlNode* c_node):
return c_node is not NULL and _findChildForwards(c_node, 0) is not NULL
+cdef Py_ssize_t _countElements(xmlNode* c_node):
+ "Counts the elements within the following siblings and the node itself."
+ cdef Py_ssize_t count
+ count = 0
+ while c_node is not NULL:
+ if _isElement(c_node):
+ count = count + 1
+ c_node = c_node.next
+ return count
+
cdef xmlNode* _findChild(xmlNode* c_node, Py_ssize_t index):
if index < 0:
return _findChildBackwards(c_node, -index - 1)
From scoder at codespeak.net Mon Oct 15 18:28:26 2007
From: scoder at codespeak.net (scoder at codespeak.net)
Date: Mon, 15 Oct 2007 18:28:26 +0200 (CEST)
Subject: [Lxml-checkins] r47469 - lxml/trunk/src/lxml
Message-ID: <20071015162826.D27038102@code0.codespeak.net>
Author: scoder
Date: Mon Oct 15 18:28:26 2007
New Revision: 47469
Modified:
lxml/trunk/src/lxml/python.pxd
Log:
forgotten PyAPI declarations
Modified: lxml/trunk/src/lxml/python.pxd
==============================================================================
--- lxml/trunk/src/lxml/python.pxd (original)
+++ lxml/trunk/src/lxml/python.pxd Mon Oct 15 18:28:26 2007
@@ -41,8 +41,10 @@
cdef Py_ssize_t PyTuple_GET_SIZE(object t)
cdef object PyTuple_GET_ITEM(object o, Py_ssize_t pos)
+ cdef object PyList_New(Py_ssize_t index)
cdef Py_ssize_t PyList_GET_SIZE(object l)
cdef object PyList_GET_ITEM(object l, Py_ssize_t index)
+ cdef void PyList_SET_ITEM(object l, Py_ssize_t index, object value)
cdef int PyList_Append(object l, object obj) except -1
cdef int PyList_Reverse(object l) except -1
cdef int PyList_Insert(object l, Py_ssize_t index, object o) except -1
@@ -61,14 +63,15 @@
cdef object PySequence_List(object o)
cdef object PySequence_Tuple(object o)
- cdef int PyDict_Check(object instance)
- cdef int PyList_Check(object instance)
- cdef int PyTuple_Check(object instance)
- cdef int PyNumber_Check(object instance)
- cdef int PyBool_Check(object instance)
- cdef int PySequence_Check(object instance)
- cdef int PyType_Check(object instance)
- cdef int PyTuple_CheckExact(object instance)
+ cdef bint PyDict_Check(object instance)
+ cdef bint PyList_Check(object instance)
+ cdef bint PyTuple_Check(object instance)
+ cdef bint PyNumber_Check(object instance)
+ cdef bint PyBool_Check(object instance)
+ cdef bint PySequence_Check(object instance)
+ cdef bint PyType_Check(object instance)
+ cdef bint PyTuple_CheckExact(object instance)
+ cdef bint PySlice_Check(object instance)
cdef int PyObject_SetAttr(object o, object name, object value)
cdef object PyObject_RichCompare(object o1, object o2, int op)
From ianb at codespeak.net Tue Oct 16 05:35:34 2007
From: ianb at codespeak.net (ianb at codespeak.net)
Date: Tue, 16 Oct 2007 05:35:34 +0200 (CEST)
Subject: [Lxml-checkins] r47483 - lxml/trunk/src/lxml
Message-ID: <20071016033534.43F7D80C2@code0.codespeak.net>
Author: ianb
Date: Tue Oct 16 05:35:33 2007
New Revision: 47483
Modified:
lxml/trunk/src/lxml/doctestcompare.py
Log:
Oops, sometimes the tag we're comparing is a comment
Modified: lxml/trunk/src/lxml/doctestcompare.py
==============================================================================
--- lxml/trunk/src/lxml/doctestcompare.py (original)
+++ lxml/trunk/src/lxml/doctestcompare.py Tue Oct 16 05:35:33 2007
@@ -151,6 +151,9 @@
def tag_compare(self, want, got):
if want == 'any':
return True
+ if (not isinstance(want, basestring)
+ or not isinstance(got, basestring)):
+ return want == got
want = want or ''
got = got or ''
if want.startswith('{...}'):
From scoder at codespeak.net Fri Oct 19 11:45:23 2007
From: scoder at codespeak.net (scoder at codespeak.net)
Date: Fri, 19 Oct 2007 11:45:23 +0200 (CEST)
Subject: [Lxml-checkins] r47573 - lxml/tag/lxml-1.3.4
Message-ID: <20071019094523.8E94B8121@code0.codespeak.net>
Author: scoder
Date: Fri Oct 19 11:45:22 2007
New Revision: 47573
Added:
lxml/tag/lxml-1.3.4/
- copied from r46182, lxml/branch/lxml-1.3/
Log:
lxml 1.3.4 tag
From scoder at codespeak.net Fri Oct 19 12:54:43 2007
From: scoder at codespeak.net (scoder at codespeak.net)
Date: Fri, 19 Oct 2007 12:54:43 +0200 (CEST)
Subject: [Lxml-checkins] r47574 - lxml/trunk
Message-ID: <20071019105443.BB72D811F@code0.codespeak.net>
Author: scoder
Date: Fri Oct 19 12:54:42 2007
New Revision: 47574
Modified:
lxml/trunk/CREDITS.txt
Log:
Holger
Modified: lxml/trunk/CREDITS.txt
==============================================================================
--- lxml/trunk/CREDITS.txt (original)
+++ lxml/trunk/CREDITS.txt Fri Oct 19 12:54:42 2007
@@ -7,6 +7,8 @@
Ian Bicking - lxml.html
+Holger Joukl - bug reports, feedback and development on lxml.objectify
+
Marc-Antoine Parent - XPath extension function help and patches
Olivier Grisel - improved (c)ElementTree compatibility patches,
From scoder at codespeak.net Fri Oct 19 16:42:20 2007
From: scoder at codespeak.net (scoder at codespeak.net)
Date: Fri, 19 Oct 2007 16:42:20 +0200 (CEST)
Subject: [Lxml-checkins] r47591 - lxml/trunk/src/lxml
Message-ID: <20071019144220.DE82D8145@code0.codespeak.net>
Author: scoder
Date: Fri Oct 19 16:42:18 2007
New Revision: 47591
Modified:
lxml/trunk/src/lxml/etree.pyx
Log:
fix prefix name creation also for Python <= 2.4
Modified: lxml/trunk/src/lxml/etree.pyx
==============================================================================
--- lxml/trunk/src/lxml/etree.pyx (original)
+++ lxml/trunk/src/lxml/etree.pyx Fri Oct 19 16:42:18 2007
@@ -229,8 +229,8 @@
When instances of this class are garbage collected, the libxml
document is cleaned up.
"""
- cdef unsigned int _ns_counter
- cdef object _prefix_format
+ cdef int _ns_counter
+ cdef object _prefix_tail
cdef xmlDoc* _c_doc
cdef _BaseParser _parser
@@ -296,12 +296,17 @@
return self._c_doc.URL
cdef buildNewPrefix(self):
- ns = python.PyString_FromFormat(
- _cstr(self._prefix_format), self._ns_counter)
+ ns = python.PyString_FromFormat("ns%d", self._ns_counter)
+ if self._prefix_tail is not None:
+ ns = ns + self._prefix_tail
self._ns_counter = self._ns_counter + 1
- if self._ns_counter == 0:
+ if self._ns_counter < 0:
# overflow!
- self._prefix_format = self._prefix_format + "A"
+ self._ns_counter = 0
+ if self._prefix_tail is None:
+ self._prefix_tail = "A"
+ else:
+ self._prefix_tail = self._prefix_tail + "A"
return ns
cdef xmlNs* _findOrBuildNodeNs(self, xmlNode* c_node,
@@ -380,7 +385,7 @@
result = NEW_DOCUMENT(_Document)
result._c_doc = c_doc
result._ns_counter = 0
- result._prefix_format = "ns%lu"
+ result._prefix_tail = None
if parser is None:
parser = __GLOBAL_PARSER_CONTEXT.getDefaultParser()
result._parser = parser
From scoder at codespeak.net Fri Oct 19 16:45:14 2007
From: scoder at codespeak.net (scoder at codespeak.net)
Date: Fri, 19 Oct 2007 16:45:14 +0200 (CEST)
Subject: [Lxml-checkins] r47592 - lxml/branch/lxml-1.3/src/lxml
Message-ID: <20071019144514.4626E813C@code0.codespeak.net>
Author: scoder
Date: Fri Oct 19 16:45:13 2007
New Revision: 47592
Modified:
lxml/branch/lxml-1.3/src/lxml/etree.pyx
Log:
fix prefix name creation also for Python <= 2.4
Modified: lxml/branch/lxml-1.3/src/lxml/etree.pyx
==============================================================================
--- lxml/branch/lxml-1.3/src/lxml/etree.pyx (original)
+++ lxml/branch/lxml-1.3/src/lxml/etree.pyx Fri Oct 19 16:45:13 2007
@@ -231,8 +231,8 @@
When instances of this class are garbage collected, the libxml
document is cleaned up.
"""
- cdef unsigned int _ns_counter
- cdef object _prefix_format
+ cdef int _ns_counter
+ cdef object _prefix_tail
cdef xmlDoc* _c_doc
cdef _BaseParser _parser
@@ -298,12 +298,17 @@
return self._c_doc.URL
cdef buildNewPrefix(self):
- ns = python.PyString_FromFormat(
- _cstr(self._prefix_format), self._ns_counter)
+ ns = python.PyString_FromFormat("ns%d", self._ns_counter)
+ if self._prefix_tail is not None:
+ ns = ns + self._prefix_tail
self._ns_counter = self._ns_counter + 1
- if self._ns_counter == 0:
+ if self._ns_counter < 0:
# overflow!
- self._prefix_format = self._prefix_format + "A"
+ self._ns_counter = 0
+ if self._prefix_tail is None:
+ self._prefix_tail = "A"
+ else:
+ self._prefix_tail = self._prefix_tail + "A"
return ns
cdef xmlNs* _findOrBuildNodeNs(self, xmlNode* c_node,
@@ -378,7 +383,7 @@
result = _Document()
result._c_doc = c_doc
result._ns_counter = 0
- result._prefix_format = "ns%lu"
+ result._prefix_tail = None
if parser is None:
parser = __GLOBAL_PARSER_CONTEXT.getDefaultParser()
result._parser = parser
From scoder at codespeak.net Sat Oct 20 14:44:51 2007
From: scoder at codespeak.net (scoder at codespeak.net)
Date: Sat, 20 Oct 2007 14:44:51 +0200 (CEST)
Subject: [Lxml-checkins] r47636 - lxml/trunk
Message-ID: <20071020124451.A9E0B8143@code0.codespeak.net>
Author: scoder
Date: Sat Oct 20 14:44:50 2007
New Revision: 47636
Modified:
lxml/trunk/setupinfo.py
Log:
print Cython version in setup.py
Modified: lxml/trunk/setupinfo.py
==============================================================================
--- lxml/trunk/setupinfo.py (original)
+++ lxml/trunk/setupinfo.py Sat Oct 20 14:44:50 2007
@@ -3,7 +3,8 @@
try:
from Cython.Distutils import build_ext as build_pyx
- print("Building with Cython.")
+ import Cython.Compiler.Version
+ print("Building with Cython %s." % Cython.Compiler.Version.version)
CYTHON_INSTALLED = True
except ImportError:
CYTHON_INSTALLED = False
From scoder at codespeak.net Sat Oct 20 14:46:30 2007
From: scoder at codespeak.net (scoder at codespeak.net)
Date: Sat, 20 Oct 2007 14:46:30 +0200 (CEST)
Subject: [Lxml-checkins] r47637 - in lxml/trunk: . src/lxml
Message-ID: <20071020124630.E3081814B@code0.codespeak.net>
Author: scoder
Date: Sat Oct 20 14:46:30 2007
New Revision: 47637
Modified:
lxml/trunk/CHANGES.txt
lxml/trunk/src/lxml/docloader.pxi
lxml/trunk/src/lxml/etree.pyx
lxml/trunk/src/lxml/xslt.pxi
Log:
improved interaction of custom resolvers and XSLT
Modified: lxml/trunk/CHANGES.txt
==============================================================================
--- lxml/trunk/CHANGES.txt (original)
+++ lxml/trunk/CHANGES.txt Sat Oct 20 14:46:30 2007
@@ -8,6 +8,9 @@
Features added
--------------
+* Resolvers can now provide a ``base_url`` keyword argument when
+ resolving a document as string data.
+
* When using ``lxml.doctestcompare`` you can give the doctest option
``NOPARSE_MARKUP`` (like ``# doctest: +NOPARSE_MARKUP``) to suppress
the special checking for one test.
@@ -15,6 +18,9 @@
Bugs fixed
----------
+* Using custom resolvers on XSLT stylesheets parsed from a string
+ could request ill-formed URLs.
+
* lxml.etree could crash when adding more than 10000 namespaces to a
document
Modified: lxml/trunk/src/lxml/docloader.pxi
==============================================================================
--- lxml/trunk/src/lxml/docloader.pxi (original)
+++ lxml/trunk/src/lxml/docloader.pxi Sat Oct 20 14:46:30 2007
@@ -9,43 +9,69 @@
cdef class _InputDocument:
cdef _InputDocumentDataType _type
cdef object _data_bytes
+ cdef object _filename
cdef object _file
cdef class Resolver:
"This is the base class of all resolvers."
def resolve(self, system_url, public_id, context):
+ """Override this method to resolve an external source by
+ ``system_url`` and ``public_id``. The third argument is an
+ opaque context object.
+
+ Return the result of one of the ``resolve_*()`` methods.
+ """
return None
def resolve_empty(self, context):
- "Return an empty input document."
+ """Return an empty input document.
+
+ Pass context as parameter.
+ """
cdef _InputDocument doc_ref
doc_ref = _InputDocument()
doc_ref._type = PARSER_DATA_EMPTY
return doc_ref
- def resolve_string(self, string, context):
- "Return a parsable string as input document."
+ def resolve_string(self, string, context, base_url=None):
+ """Return a parsable string as input document.
+
+ Pass data string and context as parameters.
+
+ You can pass the source URL as 'base_url' keyword.
+ """
cdef _InputDocument doc_ref
doc_ref = _InputDocument()
doc_ref._type = PARSER_DATA_STRING
doc_ref._data_bytes = _utf8(string)
+ if base_url is not None:
+ doc_ref._filename = _encodeFilename(base_url)
return doc_ref
def resolve_filename(self, filename, context):
- "Return the name of a parsable file as input document."
+ """Return the name of a parsable file as input document.
+
+ Pass filename and context as parameters.
+ """
cdef _InputDocument doc_ref
doc_ref = _InputDocument()
doc_ref._type = PARSER_DATA_FILENAME
- doc_ref._data_bytes = _encodeFilename(filename)
+ doc_ref._filename = _encodeFilename(filename)
return doc_ref
def resolve_file(self, f, context):
- "Return an open file-like object as input document."
+ """Return an open file-like object as input document.
+
+ Pass open file and context as parameters.
+ """
cdef _InputDocument doc_ref
- if not hasattr(f, 'read'):
+ try:
+ f.read
+ except AttributeError:
raise TypeError, "Argument is not a file-like object"
doc_ref = _InputDocument()
doc_ref._type = PARSER_DATA_FILE
+ doc_ref._filename = _getFilenameForFile(f)
doc_ref._file = f
return doc_ref
Modified: lxml/trunk/src/lxml/etree.pyx
==============================================================================
--- lxml/trunk/src/lxml/etree.pyx (original)
+++ lxml/trunk/src/lxml/etree.pyx Sat Oct 20 14:46:30 2007
@@ -16,6 +16,9 @@
del __builtin__
+cdef object os_path_join
+from os.path import join as os_path_join
+
cdef object _elementpath
import _elementpath
Modified: lxml/trunk/src/lxml/xslt.pxi
==============================================================================
--- lxml/trunk/src/lxml/xslt.pxi (original)
+++ lxml/trunk/src/lxml/xslt.pxi Sat Oct 20 14:46:30 2007
@@ -84,25 +84,26 @@
context = <_XSLTResolverContext>c_context
try:
resolvers = context._resolvers
- uri = funicode(c_uri)
+ if cstd.strncmp('string://', c_uri, 9) == 0:
+ uri = funicode(c_uri + 9)
+ if cstd.strncmp('string://', context._c_style_doc.URL, 9) != 0 and \
+ cstd.strcmp('', context._c_style_doc.URL) != 0:
+ # stylesheet URL known => make the target URL absolute
+ uri = os_path_join(context._c_style_doc.URL, uri)
+ else:
+ uri = funicode(c_uri)
doc_ref = resolvers.resolve(uri, None, context)
c_doc = NULL
if doc_ref is not None:
if doc_ref._type == PARSER_DATA_STRING:
c_doc = _parseDoc(
- doc_ref._data_bytes, None, context._parser)
+ doc_ref._data_bytes, doc_ref._filename, context._parser)
elif doc_ref._type == PARSER_DATA_FILENAME:
- if python.PyUnicode_Check(doc_ref._data_bytes):
- filename = _utf8(doc_ref._data_bytes)
- else:
- filename = doc_ref._data_bytes
- c_doc = _parseDocFromFile(filename, context._parser)
+ c_doc = _parseDocFromFile(doc_ref._filename, context._parser)
elif doc_ref._type == PARSER_DATA_FILE:
- filename = _getFilenameForFile(doc_ref._file)
- data = doc_ref._file.read()
- c_doc = _parseDoc(
- data, filename, context._parser)
+ c_doc = _parseDocFromFilelike(
+ doc_ref._file, doc_ref._filename, context._parser)
elif doc_ref._type == PARSER_DATA_EMPTY:
c_doc = _newDoc()
if c_doc is not NULL and c_doc.URL is NULL:
@@ -115,7 +116,7 @@
cdef void _xslt_store_resolver_exception(char* c_uri, void* context,
xslt.xsltLoadType c_type):
- message = "Cannot resolve URI %s" % funicode(c_uri)
+ message = "Cannot resolve URI %s" % c_uri
if c_type == xslt.XSLT_LOAD_DOCUMENT:
exception = XSLTApplyError(message)
else:
@@ -299,7 +300,7 @@
# make sure we always have a stylesheet URL
if c_doc.URL is NULL:
- doc_url_utf = "XSLT:__STRING__XSLT__%s" % id(self)
+ doc_url_utf = "string://__STRING__XSLT__%s" % id(self)
c_doc.URL = tree.xmlStrdup(_cstr(doc_url_utf))
self._error_log = _ErrorLog()
From scoder at codespeak.net Sat Oct 20 14:50:20 2007
From: scoder at codespeak.net (scoder at codespeak.net)
Date: Sat, 20 Oct 2007 14:50:20 +0200 (CEST)
Subject: [Lxml-checkins] r47638 - lxml/trunk/src/lxml
Message-ID: <20071020125020.4842B80A4@code0.codespeak.net>
Author: scoder
Date: Sat Oct 20 14:50:19 2007
New Revision: 47638
Modified:
lxml/trunk/src/lxml/etree.pyx
lxml/trunk/src/lxml/objectify.pyx
Log:
fix error handling on PyList_Append()
Modified: lxml/trunk/src/lxml/etree.pyx
==============================================================================
--- lxml/trunk/src/lxml/etree.pyx (original)
+++ lxml/trunk/src/lxml/etree.pyx Sat Oct 20 14:50:19 2007
@@ -845,10 +845,8 @@
result = []
while c_node is not NULL and c < stop:
if _isElement(c_node):
- ret = python.PyList_Append(
+ python.PyList_Append(
result, _elementFactory(self._doc, c_node))
- if ret:
- raise
c = c + 1
c_node = c_node.next
return result
@@ -992,15 +990,12 @@
code should use ``list(element)`` or simply iterate over elements.
"""
cdef xmlNode* c_node
- cdef int ret
result = []
c_node = self._c_node.children
while c_node is not NULL:
if _isElement(c_node):
- ret = python.PyList_Append(
+ python.PyList_Append(
result, _elementFactory(self._doc, c_node))
- if ret:
- raise
c_node = c_node.next
return result
Modified: lxml/trunk/src/lxml/objectify.pyx
==============================================================================
--- lxml/trunk/src/lxml/objectify.pyx (original)
+++ lxml/trunk/src/lxml/objectify.pyx Sat Oct 20 14:50:19 2007
@@ -193,15 +193,12 @@
returned in document order.
"""
cdef tree.xmlNode* c_node
- cdef int ret
result = []
c_node = self._c_node.children
while c_node is not NULL:
if tree._isElement(c_node):
- ret = python.PyList_Append(
+ python.PyList_Append(
result, cetree.elementFactory(self._doc, c_node))
- if ret:
- raise
c_node = c_node.next
return result
From scoder at codespeak.net Sat Oct 20 14:52:33 2007
From: scoder at codespeak.net (scoder at codespeak.net)
Date: Sat, 20 Oct 2007 14:52:33 +0200 (CEST)
Subject: [Lxml-checkins] r47639 - lxml/branch/lxml-1.3/src/lxml
Message-ID: <20071020125233.676AE814E@code0.codespeak.net>
Author: scoder
Date: Sat Oct 20 14:52:33 2007
New Revision: 47639
Modified:
lxml/branch/lxml-1.3/src/lxml/etree.pyx
Log:
fix error handling on PyList_Append()
Modified: lxml/branch/lxml-1.3/src/lxml/etree.pyx
==============================================================================
--- lxml/branch/lxml-1.3/src/lxml/etree.pyx (original)
+++ lxml/branch/lxml-1.3/src/lxml/etree.pyx Sat Oct 20 14:52:33 2007
@@ -829,10 +829,8 @@
result = []
while c_node is not NULL and c < stop:
if _isElement(c_node):
- ret = python.PyList_Append(
+ python.PyList_Append(
result, _elementFactory(self._doc, c_node))
- if ret:
- raise
c = c + 1
c_node = c_node.next
return result
@@ -967,15 +965,12 @@
"""Returns all subelements. The elements are returned in document order.
"""
cdef xmlNode* c_node
- cdef int ret
result = []
c_node = self._c_node.children
while c_node is not NULL:
if _isElement(c_node):
- ret = python.PyList_Append(
+ python.PyList_Append(
result, _elementFactory(self._doc, c_node))
- if ret:
- raise
c_node = c_node.next
return result
From scoder at codespeak.net Sat Oct 20 14:53:53 2007
From: scoder at codespeak.net (scoder at codespeak.net)
Date: Sat, 20 Oct 2007 14:53:53 +0200 (CEST)
Subject: [Lxml-checkins] r47640 - lxml/trunk/src/lxml
Message-ID: <20071020125353.547B28152@code0.codespeak.net>
Author: scoder
Date: Sat Oct 20 14:53:53 2007
New Revision: 47640
Modified:
lxml/trunk/src/lxml/pyclasslookup.pyx
Log:
fix error handling on PyList_Append()
Modified: lxml/trunk/src/lxml/pyclasslookup.pyx
==============================================================================
--- lxml/trunk/src/lxml/pyclasslookup.pyx (original)
+++ lxml/trunk/src/lxml/pyclasslookup.pyx Sat Oct 20 14:53:53 2007
@@ -103,10 +103,8 @@
result = []
while c_node is not NULL and c < stop:
if tree._isElement(c_node):
- ret = python.PyList_Append(
+ python.PyList_Append(
result, _newProxy(self._source_proxy, c_node))
- if ret:
- raise
c = c + 1
c_node = c_node.next
return result
@@ -163,16 +161,13 @@
order.
"""
cdef tree.xmlNode* c_node
- cdef int ret
self._assertNode()
result = []
c_node = self._c_node.children
while c_node is not NULL:
if tree._isElement(c_node):
- ret = python.PyList_Append(
+ python.PyList_Append(
result, _newProxy(self._source_proxy, c_node))
- if ret:
- raise
c_node = c_node.next
return result
From scoder at codespeak.net Sat Oct 20 14:54:25 2007
From: scoder at codespeak.net (scoder at codespeak.net)
Date: Sat, 20 Oct 2007 14:54:25 +0200 (CEST)
Subject: [Lxml-checkins] r47641 - lxml/branch/lxml-1.3/src/lxml
Message-ID: <20071020125425.2153C8154@code0.codespeak.net>
Author: scoder
Date: Sat Oct 20 14:54:24 2007
New Revision: 47641
Modified:
lxml/branch/lxml-1.3/src/lxml/pyclasslookup.pyx
Log:
fix error handling on PyList_Append()
Modified: lxml/branch/lxml-1.3/src/lxml/pyclasslookup.pyx
==============================================================================
--- lxml/branch/lxml-1.3/src/lxml/pyclasslookup.pyx (original)
+++ lxml/branch/lxml-1.3/src/lxml/pyclasslookup.pyx Sat Oct 20 14:54:24 2007
@@ -103,10 +103,8 @@
result = []
while c_node is not NULL and c < stop:
if tree._isElement(c_node):
- ret = python.PyList_Append(
+ python.PyList_Append(
result, _newProxy(self._source_proxy, c_node))
- if ret:
- raise
c = c + 1
c_node = c_node.next
return result
@@ -163,16 +161,13 @@
order.
"""
cdef tree.xmlNode* c_node
- cdef int ret
self._assertNode()
result = []
c_node = self._c_node.children
while c_node is not NULL:
if tree._isElement(c_node):
- ret = python.PyList_Append(
+ python.PyList_Append(
result, _newProxy(self._source_proxy, c_node))
- if ret:
- raise
c_node = c_node.next
return result
From scoder at codespeak.net Sun Oct 21 09:22:42 2007
From: scoder at codespeak.net (scoder at codespeak.net)
Date: Sun, 21 Oct 2007 09:22:42 +0200 (CEST)
Subject: [Lxml-checkins] r47664 - lxml/trunk/doc
Message-ID: <20071021072242.63FC88160@code0.codespeak.net>
Author: scoder
Date: Sun Oct 21 09:22:40 2007
New Revision: 47664
Modified:
lxml/trunk/doc/tutorial.txt
Log:
tutorial section on serialisation
Modified: lxml/trunk/doc/tutorial.txt
==============================================================================
--- lxml/trunk/doc/tutorial.txt (original)
+++ lxml/trunk/doc/tutorial.txt Sun Oct 21 09:22:40 2007
@@ -334,13 +334,74 @@
.. _`further iterators`: api.html#iteration
+Serialisation
+-------------
+
+Serialisation commonly uses with the ``tostring()`` function that
+returns a string, or the ``ElementTree.write()`` method that writes to
+a file or file-like object. Both accept the same keyword arguments
+like ``pretty_print`` for formatted output or ``encoding`` to select a
+specific output encoding other than plain ASCII::
+
+ >>> root = etree.XML('')
+
+ >>> print etree.tostring(root)
+
+
+ >>> print etree.tostring(root, xml_declaration=True)
+
+
+
+ >>> print etree.tostring(root, encoding='iso-8859-1')
+
+
+
+ >>> print etree.tostring(root, pretty_print=True)
+
+
+
+
+
+
+
+Since lxml 2.0 (and ElementTree 1.3), the serialisation functions can
+do more than XML serialisation and optional pretty printing. You can
+serialise to HTML or extract the text content by passing the
+``method`` keyword::
+
+ >>> root = etree.XML('Hello
World
')
+
+ >>> print etree.tostring(root) # default: method = 'xml'
+ Hello
World
+
+ >>> print etree.tostring(root, method='xml') # same as above
+ Hello
World
+
+ >>> print etree.tostring(root, method='html')
+ Hello
World
+
+ >>> print etree.tostring(root, method='html', pretty_print=True)
+
+
+ Hello
World
+
+
+ >>> print etree.tostring(root, method='text')
+ HelloWorld
+
+For the plain text output, the ``tounicode()`` function might become handy::
+
+ >>> etree.tounicode(root, method='text')
+ u'HelloWorld'
+
+
The ElementTree class
=====================
An ``ElementTree`` is mainly a document wrapper around a tree with a root
node. It provides a couple of methods for parsing, serialisation and general
document handling. One of the bigger differences is that it serialises as a
-complete document, as opposed to a single Element. This includes top-level
+complete document, as opposed to a single ``Element``. This includes top-level
processing instructions and comments, as well as a DOCTYPE and other DTD
content in the document::
From scoder at codespeak.net Sun Oct 21 09:23:56 2007
From: scoder at codespeak.net (scoder at codespeak.net)
Date: Sun, 21 Oct 2007 09:23:56 +0200 (CEST)
Subject: [Lxml-checkins] r47665 - in lxml/trunk: doc src/lxml src/lxml/tests
Message-ID: <20071021072356.BF8D88160@code0.codespeak.net>
Author: scoder
Date: Sun Oct 21 09:23:56 2007
New Revision: 47665
Modified:
lxml/trunk/doc/parsing.txt
lxml/trunk/src/lxml/docloader.pxi
lxml/trunk/src/lxml/etree.pyx
lxml/trunk/src/lxml/objectify.pyx
lxml/trunk/src/lxml/parser.pxi
lxml/trunk/src/lxml/tests/test_elementtree.py
lxml/trunk/src/lxml/tests/test_etree.py
lxml/trunk/src/lxml/tests/test_htmlparser.py
Log:
use keyword-only arguments in API
Modified: lxml/trunk/doc/parsing.txt
==============================================================================
--- lxml/trunk/doc/parsing.txt (original)
+++ lxml/trunk/doc/parsing.txt Sun Oct 21 09:23:56 2007
@@ -495,7 +495,7 @@
>>> etree.tostring(root)
' + '
- >>> etree.tostring(root, 'UTF-8', xml_declaration=False)
+ >>> etree.tostring(root, encoding='UTF-8', xml_declaration=False)
' \xef\xa3\x91 + \xef\xa3\x92 '
As an extension, lxml.etree has a new ``tounicode()`` function that you can
Modified: lxml/trunk/src/lxml/docloader.pxi
==============================================================================
--- lxml/trunk/src/lxml/docloader.pxi (original)
+++ lxml/trunk/src/lxml/docloader.pxi Sun Oct 21 09:23:56 2007
@@ -33,7 +33,7 @@
doc_ref._type = PARSER_DATA_EMPTY
return doc_ref
- def resolve_string(self, string, context, base_url=None):
+ def resolve_string(self, string, context, *, base_url=None):
"""Return a parsable string as input document.
Pass data string and context as parameters.
Modified: lxml/trunk/src/lxml/etree.pyx
==============================================================================
--- lxml/trunk/src/lxml/etree.pyx (original)
+++ lxml/trunk/src/lxml/etree.pyx Sun Oct 21 09:23:56 2007
@@ -1383,7 +1383,7 @@
return self._doc._parser
return None
- def write(self, file, encoding=None, method="xml",
+ def write(self, file, *, encoding=None, method="xml",
pretty_print=False, xml_declaration=None):
"""Write the tree to a file or file-like object.
@@ -2061,7 +2061,7 @@
"""
return _makeSubElement(_parent, _tag, None, None, attrib, nsmap, _extra)
-def ElementTree(_Element element=None, file=None, _BaseParser parser=None):
+def ElementTree(_Element element=None, *, file=None, _BaseParser parser=None):
"""ElementTree wrapper class.
"""
cdef xmlNode* c_next
@@ -2084,7 +2084,7 @@
return _elementTreeFactory(doc, element)
-def HTML(text, _BaseParser parser=None, base_url=None):
+def HTML(text, _BaseParser parser=None, *, base_url=None):
"""Parses an HTML document from a string constant. This function can be used
to embed "HTML literals" in Python code.
@@ -2106,7 +2106,7 @@
except _TargetParserResult, result_container:
return result_container.result
-def XML(text, _BaseParser parser=None, base_url=None):
+def XML(text, _BaseParser parser=None, *, base_url=None):
"""Parses an XML document from a string constant. This function can be used
to embed "XML literals" in Python code, like in
@@ -2130,7 +2130,7 @@
except _TargetParserResult, result_container:
return result_container.result
-def fromstring(text, _BaseParser parser=None, base_url=None):
+def fromstring(text, _BaseParser parser=None, *, base_url=None):
"""Parses an XML document from a string.
To override the default parser with a different parser you can pass it to
@@ -2168,13 +2168,13 @@
"""
return isinstance(element, _Element)
-def dump(_Element elem not None, pretty_print=True):
+def dump(_Element elem not None, *, pretty_print=True):
"""Writes an element tree or element structure to sys.stdout. This function
should be used for debugging only.
"""
_dumpToFile(sys.stdout, elem._c_node, pretty_print)
-def tostring(element_or_tree, encoding=None, method="xml",
+def tostring(element_or_tree, *, encoding=None, method="xml",
xml_declaration=None, pretty_print=False):
"""Serialize an element to an encoded string representation of its XML
tree.
@@ -2217,7 +2217,7 @@
"""
return [tostring(element_or_tree, *args, **kwargs)]
-def tounicode(element_or_tree, method="xml", pretty_print=False):
+def tounicode(element_or_tree, *, method="xml", pretty_print=False):
"""Serialize an element to the Python unicode representation of its XML
tree.
Modified: lxml/trunk/src/lxml/objectify.pyx
==============================================================================
--- lxml/trunk/src/lxml/objectify.pyx (original)
+++ lxml/trunk/src/lxml/objectify.pyx Sun Oct 21 09:23:56 2007
@@ -1043,7 +1043,7 @@
cdef object _namespace
cdef object _nsmap
cdef bint _annotate
- def __init__(self, namespace=None, nsmap=None, annotate=True,
+ def __init__(self, *, namespace=None, nsmap=None, annotate=True,
makeelement=None):
if nsmap is None:
nsmap = _DEFAULT_NSMAP
@@ -1301,7 +1301,7 @@
pass
return None
-def pyannotate(element_or_tree, ignore_old=False, ignore_xsi=False,
+def pyannotate(element_or_tree, *, ignore_old=False, ignore_xsi=False,
empty_pytype=None):
"""Recursively annotates the elements of an XML tree with 'pytype'
attributes.
@@ -1322,7 +1322,7 @@
element = cetree.rootNodeOrRaise(element_or_tree)
_annotate(element, 0, 1, ignore_xsi, ignore_old, None, empty_pytype)
-def xsiannotate(element_or_tree, ignore_old=False, ignore_pytype=False,
+def xsiannotate(element_or_tree, *, ignore_old=False, ignore_pytype=False,
empty_type=None):
"""Recursively annotates the elements of an XML tree with 'xsi:type'
attributes.
@@ -1348,7 +1348,7 @@
element = cetree.rootNodeOrRaise(element_or_tree)
_annotate(element, 1, 0, ignore_old, ignore_pytype, empty_type, None)
-def annotate(element_or_tree, ignore_old=True, ignore_xsi=False,
+def annotate(element_or_tree, *, ignore_old=True, ignore_xsi=False,
empty_pytype=None, empty_type=None, annotate_xsi=0,
annotate_pytype=1):
"""Recursively annotates the elements of an XML tree with 'xsi:type'
@@ -1536,7 +1536,7 @@
tree.xmlSetNsProp(c_node, c_ns, "nil", "true")
tree.END_FOR_EACH_ELEMENT_FROM(c_node)
-def deannotate(element_or_tree, pytype=True, xsi=True):
+def deannotate(element_or_tree, *, pytype=True, xsi=True):
"""Recursively de-annotate the elements of an XML tree by removing 'pytype'
and/or 'type' attributes.
@@ -1640,7 +1640,7 @@
E = ElementMaker()
-def Element(_tag, attrib=None, nsmap=None, _pytype=None, **_attributes):
+def Element(_tag, attrib=None, nsmap=None, *, _pytype=None, **_attributes):
"""Objectify specific version of the lxml.etree Element() factory that
always creates a structural (tree) element.
@@ -1657,7 +1657,7 @@
_attributes[PYTYPE_ATTRIBUTE] = _pytype
return _makeElement(_tag, None, _attributes, nsmap)
-def DataElement(_value, attrib=None, nsmap=None, _pytype=None, _xsi=None,
+def DataElement(_value, attrib=None, nsmap=None, *, _pytype=None, _xsi=None,
**_attributes):
"""Create a new element from a Python value and XML attributes taken from
keyword arguments or a dictionary passed as second argument.
Modified: lxml/trunk/src/lxml/parser.pxi
==============================================================================
--- lxml/trunk/src/lxml/parser.pxi (original)
+++ lxml/trunk/src/lxml/parser.pxi Sun Oct 21 09:23:56 2007
@@ -1037,7 +1037,7 @@
not harmful, it is more efficient to use separate parsers. This does not
apply to the default parser.
"""
- def __init__(self, attribute_defaults=False, dtd_validation=False,
+ def __init__(self, *, attribute_defaults=False, dtd_validation=False,
load_dtd=False, no_network=True, ns_clean=False,
recover=False, remove_blank_text=False, compact=True,
resolve_entities=True, remove_comments=False,
@@ -1076,7 +1076,7 @@
This parser has ``remove_comments`` and ``remove_pis`` enabled by default
and thus ignores comments and processing instructions.
"""
- def __init__(self, attribute_defaults=False, dtd_validation=False,
+ def __init__(self, *, attribute_defaults=False, dtd_validation=False,
load_dtd=False, no_network=True, ns_clean=False,
recover=False, remove_blank_text=False, compact=True,
resolve_entities=True, remove_comments=True,
Modified: lxml/trunk/src/lxml/tests/test_elementtree.py
==============================================================================
--- lxml/trunk/src/lxml/tests/test_elementtree.py (original)
+++ lxml/trunk/src/lxml/tests/test_elementtree.py Sun Oct 21 09:23:56 2007
@@ -43,13 +43,13 @@
tree = ElementTree(element)
self.buildNodes(element, 10, 3)
f = open(self.getTestFilePath('testdump.xml'), 'w')
- tree.write(f, 'UTF-8')
+ tree.write(f, encoding='UTF-8')
f.close()
f = open(self.getTestFilePath('testdump.xml'), 'r')
tree = ElementTree(file=f)
f.close()
f = open(self.getTestFilePath('testdump2.xml'), 'w')
- tree.write(f, 'UTF-8')
+ tree.write(f, encoding='UTF-8')
f.close()
f = open(self.getTestFilePath('testdump.xml'), 'r')
data1 = f.read()
@@ -2358,7 +2358,7 @@
f = StringIO()
tree = ElementTree(element=a)
- tree.write(f, 'utf-8')
+ tree.write(f, encoding='utf-8')
self.assertEquals(u'S?k p? nettet'.encode('UTF-8'),
f.getvalue())
@@ -2389,7 +2389,7 @@
f = StringIO()
tree = ElementTree(element=a)
- tree.write(f, 'iso-8859-1')
+ tree.write(f, encoding='iso-8859-1')
result = f.getvalue()
declaration = ""
self.assertEncodingDeclaration(result,'iso-8859-1')
@@ -2460,7 +2460,7 @@
a = Element('a')
a.text = u'S?k p? nettet'
self.assertEquals(u'S?k p? nettet'.encode('UTF-8'),
- tostring(a, 'utf-8'))
+ tostring(a, encoding='utf-8'))
def test_encoding_tostring_unknown(self):
Element = self.etree.Element
@@ -2468,7 +2468,8 @@
a = Element('a')
a.text = u'S?k p? nettet'
- self.assertRaises(LookupError, tostring, a, 'Invalid Encoding')
+ self.assertRaises(LookupError, tostring, a,
+ encoding='Invalid Encoding')
def test_encoding_tostring_sub(self):
Element = self.etree.Element
@@ -2479,7 +2480,7 @@
b = SubElement(a, 'b')
b.text = u'S?k p? nettet'
self.assertEquals(u'S?k p? nettet'.encode('UTF-8'),
- tostring(b, 'utf-8'))
+ tostring(b, encoding='utf-8'))
def test_encoding_tostring_sub_tail(self):
Element = self.etree.Element
@@ -2491,7 +2492,7 @@
b.text = u'S?k p? nettet'
b.tail = u'S?k'
self.assertEquals(u'S?k p? nettetS?k'.encode('UTF-8'),
- tostring(b, 'utf-8'))
+ tostring(b, encoding='utf-8'))
def test_encoding_tostring_default_encoding(self):
Element = self.etree.Element
@@ -2919,7 +2920,7 @@
try:
f = open(filename, 'wb')
tree = ElementTree(element=element)
- tree.write(f, encoding)
+ tree.write(f, encoding=encoding)
f.close()
f = open(filename, 'rb')
data = f.read()
Modified: lxml/trunk/src/lxml/tests/test_etree.py
==============================================================================
--- lxml/trunk/src/lxml/tests/test_etree.py (original)
+++ lxml/trunk/src/lxml/tests/test_etree.py Sun Oct 21 09:23:56 2007
@@ -1777,7 +1777,7 @@
b = SubElement(a, 'b')
c = SubElement(a, 'c')
- result = unicode(tostring(a, 'UTF-16'), 'UTF-16')
+ result = unicode(tostring(a, encoding='UTF-16'), 'UTF-16')
self.assertEquals('',
canonicalize(result))
Modified: lxml/trunk/src/lxml/tests/test_htmlparser.py
==============================================================================
--- lxml/trunk/src/lxml/tests/test_htmlparser.py (original)
+++ lxml/trunk/src/lxml/tests/test_htmlparser.py Sun Oct 21 09:23:56 2007
@@ -16,6 +16,11 @@
etree = etree
html_str = "testpage title
"
+ html_str_pretty = """\
+
+test
+page title
+"""
broken_html_str = "test<body><h1>page title</h3></p></html>"
uhtml_str = u"<html><head><title>test ??\uF8D2page ??\uF8D2 title
"
@@ -29,9 +34,14 @@
def test_module_HTML_unicode(self):
element = self.etree.HTML(self.uhtml_str)
- self.assertEqual(unicode(self.etree.tostring(element, 'UTF8'), 'UTF8'),
+ self.assertEqual(unicode(self.etree.tostring(element, encoding='UTF8'), 'UTF8'),
unicode(self.uhtml_str.encode('UTF8'), 'UTF8'))
+ def test_module_HTML_pretty_print(self):
+ element = self.etree.HTML(self.html_str)
+ self.assertEqual(self.etree.tostring(element, method="html", pretty_print=True),
+ self.html_str_pretty)
+
def test_module_parse_html_error(self):
parser = self.etree.HTMLParser(recover=False)
parse = self.etree.parse
@@ -202,14 +212,14 @@
parser = self.etree.HTMLParser()
f = SillyFileLike(self.html_str)
tree = self.etree.parse(f, parser)
- html = self.etree.tostring(tree.getroot(), 'UTF-8')
+ html = self.etree.tostring(tree.getroot(), encoding='UTF-8')
self.assertEqual(html, self.html_str)
## def test_module_parse_html_filelike_unicode(self):
## parser = self.etree.HTMLParser()
## f = SillyFileLike(self.uhtml_str)
## tree = self.etree.parse(f, parser)
-## html = self.etree.tostring(tree.getroot(), 'UTF-8')
+## html = self.etree.tostring(tree.getroot(), encoding='UTF-8')
## self.assertEqual(unicode(html, 'UTF-8'), self.uhtml_str)
def test_html_file_error(self):
From scoder at codespeak.net Sun Oct 21 14:25:47 2007
From: scoder at codespeak.net (scoder at codespeak.net)
Date: Sun, 21 Oct 2007 14:25:47 +0200 (CEST)
Subject: [Lxml-checkins] r47669 - lxml/branch/pyrex-0.9.6.2-fixes
Message-ID: <20071021122547.DB301814E@code0.codespeak.net>
Author: scoder
Date: Sun Oct 21 14:25:46 2007
New Revision: 47669
Added:
lxml/branch/pyrex-0.9.6.2-fixes/
- copied from r47668, lxml/trunk/
Log:
new branch for fixes to build with Pyrex 0.9.6
From scoder at codespeak.net Sun Oct 21 14:27:46 2007
From: scoder at codespeak.net (scoder at codespeak.net)
Date: Sun, 21 Oct 2007 14:27:46 +0200 (CEST)
Subject: [Lxml-checkins] r47670 - lxml/branch/pyrex-0.9.6.2-fixes/src/lxml
Message-ID: <20071021122746.1C6D08159@code0.codespeak.net>
Author: scoder
Date: Sun Oct 21 14:27:45 2007
New Revision: 47670
Modified:
lxml/branch/pyrex-0.9.6.2-fixes/src/lxml/classlookup.pxi
lxml/branch/pyrex-0.9.6.2-fixes/src/lxml/etree.pyx
lxml/branch/pyrex-0.9.6.2-fixes/src/lxml/etreepublic.pxd
lxml/branch/pyrex-0.9.6.2-fixes/src/lxml/extensions.pxi
lxml/branch/pyrex-0.9.6.2-fixes/src/lxml/objectify.pyx
lxml/branch/pyrex-0.9.6.2-fixes/src/lxml/parser.pxi
lxml/branch/pyrex-0.9.6.2-fixes/src/lxml/parsertarget.pxi
lxml/branch/pyrex-0.9.6.2-fixes/src/lxml/public-api.pxi
lxml/branch/pyrex-0.9.6.2-fixes/src/lxml/pyclasslookup.pyx
Log:
lower case 'gil', public API and import changes
Modified: lxml/branch/pyrex-0.9.6.2-fixes/src/lxml/classlookup.pxi
==============================================================================
--- lxml/branch/pyrex-0.9.6.2-fixes/src/lxml/classlookup.pxi (original)
+++ lxml/branch/pyrex-0.9.6.2-fixes/src/lxml/classlookup.pxi Sun Oct 21 14:27:45 2007
@@ -48,7 +48,7 @@
################################################################################
# Element class lookup
-ctypedef object (*_element_class_lookup_function)(object, _Document, xmlNode*)
+ctypedef public object (*_element_class_lookup_function)(object, _Document, xmlNode*)
# class to store element class lookup functions
cdef public class ElementClassLookup [ type LxmlElementClassLookupType,
Modified: lxml/branch/pyrex-0.9.6.2-fixes/src/lxml/etree.pyx
==============================================================================
--- lxml/branch/pyrex-0.9.6.2-fixes/src/lxml/etree.pyx (original)
+++ lxml/branch/pyrex-0.9.6.2-fixes/src/lxml/etree.pyx Sun Oct 21 14:27:45 2007
@@ -1769,7 +1769,7 @@
return attribs
-ctypedef xmlNode* (*_node_to_node_function)(xmlNode*)
+ctypedef public xmlNode* (*_node_to_node_function)(xmlNode*)
cdef public class _ElementTagMatcher [ object LxmlElementTagMatcher,
type LxmlElementTagMatcherType ]:
Modified: lxml/branch/pyrex-0.9.6.2-fixes/src/lxml/etreepublic.pxd
==============================================================================
--- lxml/branch/pyrex-0.9.6.2-fixes/src/lxml/etreepublic.pxd (original)
+++ lxml/branch/pyrex-0.9.6.2-fixes/src/lxml/etreepublic.pxd Sun Oct 21 14:27:45 2007
@@ -16,10 +16,10 @@
int start_node_inclusive)
cdef void END_FOR_EACH_ELEMENT_FROM(tree.xmlNode* start_node)
-cdef extern from "etree.h":
+cdef extern from "etree_api.h":
# first function to call!
- cdef int import_etree(etree_module) except -1
+ cdef int import_etree() except -1
##########################################################################
# public ElementTree API classes
Modified: lxml/branch/pyrex-0.9.6.2-fixes/src/lxml/extensions.pxi
==============================================================================
--- lxml/branch/pyrex-0.9.6.2-fixes/src/lxml/extensions.pxi (original)
+++ lxml/branch/pyrex-0.9.6.2-fixes/src/lxml/extensions.pxi Sun Oct 21 14:27:45 2007
@@ -583,7 +583,7 @@
# lookup the function by name and call it
cdef void _xpath_function_call(xpath.xmlXPathParserContext* ctxt,
- int nargs) with GIL:
+ int nargs) with gil:
cdef xpath.xmlXPathContext* rctxt
cdef _BaseContext context
rctxt = ctxt.context
Modified: lxml/branch/pyrex-0.9.6.2-fixes/src/lxml/objectify.pyx
==============================================================================
--- lxml/branch/pyrex-0.9.6.2-fixes/src/lxml/objectify.pyx (original)
+++ lxml/branch/pyrex-0.9.6.2-fixes/src/lxml/objectify.pyx Sun Oct 21 14:27:45 2007
@@ -10,7 +10,7 @@
cdef object etree
from lxml import etree
# initialize C-API of lxml.etree
-import_etree(etree)
+import_etree()
__version__ = etree.__version__
Modified: lxml/branch/pyrex-0.9.6.2-fixes/src/lxml/parser.pxi
==============================================================================
--- lxml/branch/pyrex-0.9.6.2-fixes/src/lxml/parser.pxi (original)
+++ lxml/branch/pyrex-0.9.6.2-fixes/src/lxml/parser.pxi Sun Oct 21 14:27:45 2007
@@ -288,7 +288,7 @@
self._exc_context._store_raised()
return -1
-cdef int _readFilelikeParser(void* ctxt, char* c_buffer, int c_size) with GIL:
+cdef int _readFilelikeParser(void* ctxt, char* c_buffer, int c_size) with gil:
return (<_FileReaderContext>ctxt).copyToBuffer(c_buffer, c_size)
############################################################
@@ -297,7 +297,7 @@
cdef xmlparser.xmlParserInput* _parser_resolve_from_python(
char* c_url, char* c_pubid, xmlparser.xmlParserCtxt* c_context,
- int* error) with GIL:
+ int* error) with gil:
# call the Python document loaders
cdef xmlparser.xmlParserInput* c_input
cdef _ResolverContext context
Modified: lxml/branch/pyrex-0.9.6.2-fixes/src/lxml/parsertarget.pxi
==============================================================================
--- lxml/branch/pyrex-0.9.6.2-fixes/src/lxml/parsertarget.pxi (original)
+++ lxml/branch/pyrex-0.9.6.2-fixes/src/lxml/parsertarget.pxi Sun Oct 21 14:27:45 2007
@@ -87,7 +87,7 @@
char* c_namespace, int c_nb_namespaces,
char** c_namespaces,
int c_nb_attributes, int c_nb_defaulted,
- char** c_attributes) with GIL:
+ char** c_attributes) with gil:
cdef _TargetParserContext context
cdef xmlparser.xmlParserCtxt* c_ctxt
cdef int i
@@ -118,7 +118,7 @@
_handleSaxTargetException(context, c_ctxt)
cdef void _targetSaxEnd(void* ctxt, char* c_localname, char* c_prefix,
- char* c_namespace) with GIL:
+ char* c_namespace) with gil:
cdef _TargetParserContext context
cdef xmlparser.xmlParserCtxt* c_ctxt
c_ctxt = ctxt
@@ -131,7 +131,7 @@
except:
_handleSaxTargetException(context, c_ctxt)
-cdef void _targetSaxData(void* ctxt, char* c_data, int data_len) with GIL:
+cdef void _targetSaxData(void* ctxt, char* c_data, int data_len) with gil:
cdef _TargetParserContext context
cdef xmlparser.xmlParserCtxt* c_ctxt
c_ctxt = ctxt
@@ -145,7 +145,7 @@
_handleSaxTargetException(context, c_ctxt)
cdef void _targetSaxDoctype(void* ctxt, char* c_name, char* c_public,
- char* c_system) with GIL:
+ char* c_system) with gil:
cdef _TargetParserContext context
cdef xmlparser.xmlParserCtxt* c_ctxt
c_ctxt = ctxt
@@ -162,7 +162,7 @@
except:
_handleSaxTargetException(context, c_ctxt)
-cdef void _targetSaxPI(void* ctxt, char* c_target, char* c_data) with GIL:
+cdef void _targetSaxPI(void* ctxt, char* c_target, char* c_data) with gil:
cdef _TargetParserContext context
cdef xmlparser.xmlParserCtxt* c_ctxt
c_ctxt = ctxt
@@ -176,7 +176,7 @@
except:
_handleSaxTargetException(context, c_ctxt)
-cdef void _targetSaxComment(void* ctxt, char* c_data, int data_len) with GIL:
+cdef void _targetSaxComment(void* ctxt, char* c_data, int data_len) with gil:
cdef _TargetParserContext context
cdef xmlparser.xmlParserCtxt* c_ctxt
c_ctxt = ctxt
Modified: lxml/branch/pyrex-0.9.6.2-fixes/src/lxml/public-api.pxi
==============================================================================
--- lxml/branch/pyrex-0.9.6.2-fixes/src/lxml/public-api.pxi (original)
+++ lxml/branch/pyrex-0.9.6.2-fixes/src/lxml/public-api.pxi Sun Oct 21 14:27:45 2007
@@ -1,156 +1,156 @@
# Public C API for lxml.etree
-cdef public _Element deepcopyNodeToDocument(_Document doc, xmlNode* c_root):
+cdef api _Element deepcopyNodeToDocument(_Document doc, xmlNode* c_root):
"Recursively copy the element into the document. doc is not modified."
cdef xmlNode* c_node
c_node = _copyNodeToDoc(c_root, doc._c_doc)
return _elementFactory(doc, c_node)
-cdef public _ElementTree elementTreeFactory(_Element context_node):
+cdef api _ElementTree elementTreeFactory(_Element context_node):
return newElementTree(context_node, _ElementTree)
-cdef public _ElementTree newElementTree(_Element context_node,
+cdef api _ElementTree newElementTree(_Element context_node,
object subclass):
if context_node is NULL or context_node is None:
raise TypeError
return _newElementTree(context_node._doc, context_node, subclass)
-cdef public _Element elementFactory(_Document doc, xmlNode* c_node):
+cdef api _Element elementFactory(_Document doc, xmlNode* c_node):
if c_node is NULL or doc is None:
raise TypeError
return _elementFactory(doc, c_node)
-cdef public _Element makeElement(tag, _Document doc, parser,
+cdef api _Element makeElement(tag, _Document doc, parser,
text, tail, attrib, nsmap):
return _makeElement(tag, NULL, doc, parser, text, tail, attrib, nsmap, None)
-cdef public _Element makeSubElement(_Element parent, tag, text, tail,
+cdef api _Element makeSubElement(_Element parent, tag, text, tail,
attrib, nsmap):
return _makeSubElement(parent, tag, text, tail, attrib, nsmap, None)
-cdef public void setElementClassLookupFunction(
+cdef api void setElementClassLookupFunction(
_element_class_lookup_function function, state):
_setElementClassLookupFunction(function, state)
-cdef public object lookupDefaultElementClass(state, doc, xmlNode* c_node):
+cdef api object lookupDefaultElementClass(state, doc, xmlNode* c_node):
return _lookupDefaultElementClass(state, doc, c_node)
-cdef public object lookupNamespaceElementClass(state, doc, xmlNode* c_node):
+cdef api object lookupNamespaceElementClass(state, doc, xmlNode* c_node):
return _find_nselement_class(state, doc, c_node)
-cdef public object callLookupFallback(FallbackElementClassLookup lookup,
+cdef api object callLookupFallback(FallbackElementClassLookup lookup,
_Document doc, xmlNode* c_node):
return lookup._callFallback(doc, c_node)
-cdef public int tagMatches(xmlNode* c_node, char* c_href, char* c_name):
+cdef api int tagMatches(xmlNode* c_node, char* c_href, char* c_name):
if c_node is NULL:
return -1
return _tagMatches(c_node, c_href, c_name)
-cdef public _Document documentOrRaise(object input):
+cdef api _Document documentOrRaise(object input):
return _documentOrRaise(input)
-cdef public _Element rootNodeOrRaise(object input):
+cdef api _Element rootNodeOrRaise(object input):
return _rootNodeOrRaise(input)
-cdef public bint hasText(xmlNode* c_node):
+cdef api bint hasText(xmlNode* c_node):
return _hasText(c_node)
-cdef public bint hasTail(xmlNode* c_node):
+cdef api bint hasTail(xmlNode* c_node):
return _hasTail(c_node)
-cdef public object textOf(xmlNode* c_node):
+cdef api object textOf(xmlNode* c_node):
if c_node is NULL:
return None
return _collectText(c_node.children)
-cdef public object tailOf(xmlNode* c_node):
+cdef api object tailOf(xmlNode* c_node):
if c_node is NULL:
return None
return _collectText(c_node.next)
-cdef public int setNodeText(xmlNode* c_node, text) except -1:
+cdef api int setNodeText(xmlNode* c_node, text) except -1:
if c_node is NULL:
raise ValueError
return _setNodeText(c_node, text)
-cdef public int setTailText(xmlNode* c_node, text) except -1:
+cdef api int setTailText(xmlNode* c_node, text) except -1:
if c_node is NULL:
raise ValueError
return _setTailText(c_node, text)
-cdef public object attributeValue(xmlNode* c_element, xmlAttr* c_attrib_node):
+cdef api object attributeValue(xmlNode* c_element, xmlAttr* c_attrib_node):
return _attributeValue(c_element, c_attrib_node)
-cdef public object attributeValueFromNsName(xmlNode* c_element,
+cdef api object attributeValueFromNsName(xmlNode* c_element,
char* ns, char* name):
return _attributeValueFromNsName(c_element, ns, name)
-cdef public object getAttributeValue(_Element element, key, default):
+cdef api object getAttributeValue(_Element element, key, default):
return _getAttributeValue(element, key, default)
-cdef public object iterattributes(_Element element, int keysvalues):
+cdef api object iterattributes(_Element element, int keysvalues):
return _attributeIteratorFactory(element, keysvalues)
-cdef public object collectAttributes(xmlNode* c_element, int keysvalues):
+cdef api object collectAttributes(xmlNode* c_element, int keysvalues):
return _collectAttributes(c_element, keysvalues)
-cdef public int setAttributeValue(_Element element, key, value) except -1:
+cdef api int setAttributeValue(_Element element, key, value) except -1:
return _setAttributeValue(element, key, value)
-cdef public int delAttribute(_Element element, key) except -1:
+cdef api int delAttribute(_Element element, key) except -1:
return _delAttribute(element, key)
-cdef public int delAttributeFromNsName(tree.xmlNode* c_element,
+cdef api int delAttributeFromNsName(tree.xmlNode* c_element,
char* c_href, char* c_name):
return _delAttributeFromNsName(c_element, c_href, c_name)
-cdef public bint hasChild(xmlNode* c_node):
+cdef api bint hasChild(xmlNode* c_node):
return _hasChild(c_node)
-cdef public xmlNode* findChild(xmlNode* c_node, Py_ssize_t index):
+cdef api xmlNode* findChild(xmlNode* c_node, Py_ssize_t index):
return _findChild(c_node, index)
-cdef public xmlNode* findChildForwards(xmlNode* c_node, Py_ssize_t index):
+cdef api xmlNode* findChildForwards(xmlNode* c_node, Py_ssize_t index):
return _findChildForwards(c_node, index)
-cdef public xmlNode* findChildBackwards(xmlNode* c_node, Py_ssize_t index):
+cdef api xmlNode* findChildBackwards(xmlNode* c_node, Py_ssize_t index):
return _findChildBackwards(c_node, index)
-cdef public xmlNode* nextElement(xmlNode* c_node):
+cdef api xmlNode* nextElement(xmlNode* c_node):
return _nextElement(c_node)
-cdef public xmlNode* previousElement(xmlNode* c_node):
+cdef api xmlNode* previousElement(xmlNode* c_node):
return _previousElement(c_node)
-cdef public void appendChild(_Element parent, _Element child):
+cdef api void appendChild(_Element parent, _Element child):
_appendChild(parent, child)
-cdef