From scoder at codespeak.net Thu Apr 1 22:28:41 2010
From: scoder at codespeak.net (scoder at codespeak.net)
Date: Thu, 1 Apr 2010 22:28:41 +0200 (CEST)
Subject: [Lxml-checkins] r73254 - in lxml/trunk: . src/lxml src/lxml/tests
Message-ID: <20100401202841.B98EF282BD8@codespeak.net>
Author: scoder
Date: Thu Apr 1 22:28:37 2010
New Revision: 73254
Modified:
lxml/trunk/ (props changed)
lxml/trunk/CHANGES.txt
lxml/trunk/src/lxml/lxml.etree.pyx
lxml/trunk/src/lxml/proxy.pxi
lxml/trunk/src/lxml/serializer.pxi
lxml/trunk/src/lxml/tests/test_etree.py
Log:
r5546 at lenny: sbehnel | 2010-04-01 22:28:22 +0200
support C14N serialisation through 'c14n' serialisation method, also in tostring()
Modified: lxml/trunk/CHANGES.txt
==============================================================================
--- lxml/trunk/CHANGES.txt (original)
+++ lxml/trunk/CHANGES.txt Thu Apr 1 22:28:37 2010
@@ -8,6 +8,12 @@
Features added
--------------
+* Support 'unicode' string name as encoding parameter in
+ ``tostring()``, following ElementTree 1.3.
+
+* Support 'c14n' serialisation method in ``ElementTree.write()`` and
+ ``tostring()``, following ElementTree 1.3.
+
* During regular XPath evaluation, various ESXLT functions are
available within their namespace when using libxslt 1.1.26 or later.
Modified: lxml/trunk/src/lxml/lxml.etree.pyx
==============================================================================
--- lxml/trunk/src/lxml/lxml.etree.pyx (original)
+++ lxml/trunk/src/lxml/lxml.etree.pyx Thu Apr 1 22:28:37 2010
@@ -1708,17 +1708,23 @@
def write(self, file, *, encoding=None, method=u"xml",
pretty_print=False, xml_declaration=None, with_tail=True,
- standalone=None, docstring=None, compression=0):
+ standalone=None, docstring=None, compression=0,
+ exclusive=False, with_comments=True):
u"""write(self, file, encoding=None, method="xml",
pretty_print=False, xml_declaration=None, with_tail=True,
- standalone=None, compression=0)
+ standalone=None, compression=0,
+ exclusive=False, with_comments=True)
Write the tree to a filename, file or file-like object.
Defaults to ASCII encoding and writing a declaration as needed.
- The keyword argument 'method' selects the output method: 'xml' or
- 'html'.
+ The keyword argument 'method' selects the output method:
+ 'xml', 'html', 'text' or 'c14n'. Default is 'xml'.
+
+ The ``exclusive`` and ``with_comments`` arguments are only
+ used with C14N output, where they request exclusive and
+ uncommented C14N serialisation respectively.
Passing a boolean value to the ``standalone`` option will
output an XML declaration with the corresponding
@@ -1729,6 +1735,19 @@
cdef bint write_declaration
cdef int is_standalone
self._assertHasRoot()
+ if compression is None or compression < 0:
+ compression = 0
+ # C14N serialisation
+ if method == 'c14n':
+ if encoding is not None:
+ raise ValueError("Cannot specify encoding with C14N")
+ if xml_declaration:
+ raise ValueError("Cannot enable XML declaration in C14N")
+ _tofilelikeC14N(file, self._context_node, exclusive, with_comments,
+ compression)
+ return
+ if not with_comments:
+ raise ValueError("Can only discard comments in C14N serialisation")
# suppress decl. in default case (purely for ElementTree compatibility)
if xml_declaration is not None:
write_declaration = xml_declaration
@@ -1749,8 +1768,6 @@
else:
write_declaration = 1
is_standalone = 0
- if compression is None or compression < 0:
- compression = 0
_tofilelike(file, self._context_node, encoding, docstring, method,
write_declaration, 1, pretty_print, with_tail,
is_standalone, compression)
@@ -2659,26 +2676,36 @@
def tostring(element_or_tree, *, encoding=None, method=u"xml",
xml_declaration=None, pretty_print=False, with_tail=True,
- standalone=None, doctype=None):
+ standalone=None, doctype=None,
+ exclusive=False, with_comments=True):
u"""tostring(element_or_tree, encoding=None, method="xml",
xml_declaration=None, pretty_print=False, with_tail=True,
- standalone=None, doctype=None)
+ standalone=None, doctype=None,
+ exclusive=False, with_comments=True)
Serialize an element to an encoded string representation of its XML
tree.
- Defaults to ASCII encoding without XML declaration. This behaviour can be
- configured with the keyword arguments 'encoding' (string) and
- 'xml_declaration' (bool). Note that changing the encoding to a non UTF-8
- compatible encoding will enable a declaration by default.
+ Defaults to ASCII encoding without XML declaration. This
+ behaviour can be configured with the keyword arguments 'encoding'
+ (string) and 'xml_declaration' (bool). Note that changing the
+ encoding to a non UTF-8 compatible encoding will enable a
+ declaration by default.
You can also serialise to a Unicode string without declaration by
- passing the ``unicode`` function as encoding (or ``str`` in Py3).
+ passing the ``unicode`` function as encoding (or ``str`` in Py3),
+ or the name 'unicode'. This changes the return value from a byte
+ string to an unencoded unicode string.
The keyword argument 'pretty_print' (bool) enables formatted XML.
The keyword argument 'method' selects the output method: 'xml',
- 'html' or plain 'text'.
+ 'html', plain 'text' (text content without tags) or 'c14n'.
+ Default is 'xml'.
+
+ The ``exclusive`` and ``with_comments`` arguments are only used
+ with C14N output, where they request exclusive and uncommented
+ C14N serialisation respectively.
Passing a boolean value to the ``standalone`` option will output
an XML declaration with the corresponding ``standalone`` flag.
@@ -2693,11 +2720,21 @@
"""
cdef bint write_declaration
cdef int is_standalone
- if encoding is _unicode:
+ # C14N serialisation
+ if method == 'c14n':
+ if encoding is not None:
+ raise ValueError("Cannot specify encoding with C14N")
+ if xml_declaration:
+ raise ValueError("Cannot enable XML declaration in C14N")
+ return _tostringC14N(element_or_tree, exclusive, with_comments)
+ if not with_comments:
+ raise ValueError("Can only discard comments in C14N serialisation")
+ if encoding is _unicode or (encoding is not None and encoding.upper() == 'UNICODE'):
if xml_declaration:
raise ValueError, \
u"Serialisation to unicode must not request an XML declaration"
write_declaration = 0
+ encoding = _unicode
elif 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 \
Modified: lxml/trunk/src/lxml/proxy.pxi
==============================================================================
--- lxml/trunk/src/lxml/proxy.pxi (original)
+++ lxml/trunk/src/lxml/proxy.pxi Thu Apr 1 22:28:37 2010
@@ -61,6 +61,10 @@
# temporarily make a node the root node of its document
cdef xmlDoc* _fakeRootDoc(xmlDoc* c_base_doc, xmlNode* c_node) except NULL:
+ return _plainFakeRootDoc(c_base_doc, c_node, 1)
+
+cdef xmlDoc* _plainFakeRootDoc(xmlDoc* c_base_doc, xmlNode* c_node,
+ bint with_siblings) except NULL:
# build a temporary document that has the given node as root node
# note that copy and original must not be modified during its lifetime!!
# always call _destroyFakeDoc() after use!
@@ -68,10 +72,11 @@
cdef xmlNode* c_root
cdef xmlNode* c_new_root
cdef xmlDoc* c_doc
- c_root = tree.xmlDocGetRootElement(c_base_doc)
- if c_root is c_node:
- # already the root node
- return c_base_doc
+ if with_siblings or (c_node.prev is NULL and c_node.next is NULL):
+ c_root = tree.xmlDocGetRootElement(c_base_doc)
+ if c_root is c_node:
+ # already the root node, no siblings
+ return c_base_doc
c_doc = _copyDoc(c_base_doc, 0) # non recursive!
c_new_root = tree.xmlDocCopyNode(c_node, c_doc, 2) # non recursive!
Modified: lxml/trunk/src/lxml/serializer.pxi
==============================================================================
--- lxml/trunk/src/lxml/serializer.pxi (original)
+++ lxml/trunk/src/lxml/serializer.pxi Thu Apr 1 22:28:37 2010
@@ -142,6 +142,37 @@
_raiseSerialisationError(error_result)
return result
+cdef bytes _tostringC14N(element_or_tree, bint exclusive, bint with_comments):
+ cdef xmlDoc* c_doc
+ cdef char* c_buffer = NULL
+ cdef int byte_count = -1
+ cdef bytes result
+ cdef _Document doc
+ cdef _Element element
+
+ if isinstance(element_or_tree, _Element):
+ doc = (<_Element>element_or_tree)._doc
+ c_doc = _plainFakeRootDoc(doc._c_doc, (<_Element>element_or_tree)._c_node, 0)
+ else:
+ doc = _documentOrRaise(element_or_tree)
+ c_doc = doc._c_doc
+
+ with nogil:
+ byte_count = c14n.xmlC14NDocDumpMemory(
+ c_doc, NULL, exclusive, NULL, with_comments, &c_buffer)
+
+ _destroyFakeDoc(doc._c_doc, c_doc)
+
+ if byte_count < 0 or c_buffer is NULL:
+ if c_buffer is not NULL:
+ tree.xmlFree(c_buffer)
+ raise C14NError, u"C14N failed"
+ try:
+ result = c_buffer[:byte_count]
+ finally:
+ tree.xmlFree(c_buffer)
+ return result
+
cdef _raiseSerialisationError(int error_result):
if error_result == xmlerror.XML_ERR_NO_MEMORY:
return python.PyErr_NoMemory()
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 Thu Apr 1 22:28:37 2010
@@ -3029,6 +3029,30 @@
self.assertEquals(_bytes(''),
s)
+ def test_c14n_tostring_with_comments(self):
+ tree = self.parse(_bytes(''))
+ s = etree.tostring(tree, method='c14n')
+ self.assertEquals(_bytes('\n\n'),
+ s)
+ s = etree.tostring(tree, method='c14n', with_comments=True)
+ self.assertEquals(_bytes('\n\n'),
+ s)
+ s = etree.tostring(tree, method='c14n', with_comments=False)
+ self.assertEquals(_bytes(''),
+ s)
+
+ def test_c14n_element_tostring_with_comments(self):
+ tree = self.parse(_bytes(''))
+ s = etree.tostring(tree.getroot(), method='c14n')
+ self.assertEquals(_bytes(''),
+ s)
+ s = etree.tostring(tree.getroot(), method='c14n', with_comments=True)
+ self.assertEquals(_bytes(''),
+ s)
+ s = etree.tostring(tree.getroot(), method='c14n', with_comments=False)
+ self.assertEquals(_bytes(''),
+ s)
+
def test_c14n_exclusive(self):
tree = self.parse(_bytes(
''))
@@ -3048,6 +3072,39 @@
self.assertEquals(_bytes(''),
s)
+ def test_c14n_tostring_exclusive(self):
+ tree = self.parse(_bytes(
+ ''))
+ s = etree.tostring(tree, method='c14n')
+ self.assertEquals(_bytes(''),
+ s)
+ s = etree.tostring(tree, method='c14n', exclusive=False)
+ self.assertEquals(_bytes(''),
+ s)
+ s = etree.tostring(tree, method='c14n', exclusive=True)
+ self.assertEquals(_bytes(''),
+ s)
+
+ def test_c14n_element_tostring_exclusive(self):
+ tree = self.parse(_bytes(
+ ''))
+ s = etree.tostring(tree.getroot(), method='c14n')
+ self.assertEquals(_bytes(''),
+ s)
+ s = etree.tostring(tree.getroot(), method='c14n', exclusive=False)
+ self.assertEquals(_bytes(''),
+ s)
+ s = etree.tostring(tree.getroot(), method='c14n', exclusive=True)
+ self.assertEquals(_bytes(''),
+ s)
+
+ s = etree.tostring(tree.getroot()[0], method='c14n', exclusive=False)
+ self.assertEquals(_bytes(''),
+ s)
+ s = etree.tostring(tree.getroot()[0], method='c14n', exclusive=True)
+ self.assertEquals(_bytes(''),
+ s)
+
class ETreeWriteTestCase(HelperTestCase):
def test_write(self):
From scoder at codespeak.net Thu Apr 1 22:30:03 2010
From: scoder at codespeak.net (scoder at codespeak.net)
Date: Thu, 1 Apr 2010 22:30:03 +0200 (CEST)
Subject: [Lxml-checkins] r73255 - lxml/trunk
Message-ID: <20100401203003.EB11F282BD8@codespeak.net>
Author: scoder
Date: Thu Apr 1 22:30:02 2010
New Revision: 73255
Modified:
lxml/trunk/ (props changed)
lxml/trunk/CHANGES.txt
Log:
r5548 at lenny: sbehnel | 2010-04-01 22:29:57 +0200
changelog
Modified: lxml/trunk/CHANGES.txt
==============================================================================
--- lxml/trunk/CHANGES.txt (original)
+++ lxml/trunk/CHANGES.txt Thu Apr 1 22:30:02 2010
@@ -14,6 +14,11 @@
* Support 'c14n' serialisation method in ``ElementTree.write()`` and
``tostring()``, following ElementTree 1.3.
+* The ElementPath expression syntax (``el.find*()``) was extended to
+ match the upcoming ElementTree 1.3 that will ship in the standard
+ library of Python 3.2/2.7. This includes extended support for
+ predicates as well as namespace prefixes (as known from XPath).
+
* During regular XPath evaluation, various ESXLT functions are
available within their namespace when using libxslt 1.1.26 or later.
From scoder at codespeak.net Thu Apr 1 23:09:26 2010
From: scoder at codespeak.net (scoder at codespeak.net)
Date: Thu, 1 Apr 2010 23:09:26 +0200 (CEST)
Subject: [Lxml-checkins] r73257 - in lxml/trunk: . src/lxml src/lxml/tests
Message-ID: <20100401210926.77C3B282BD8@codespeak.net>
Author: scoder
Date: Thu Apr 1 23:09:24 2010
New Revision: 73257
Modified:
lxml/trunk/ (props changed)
lxml/trunk/CHANGES.txt
lxml/trunk/src/lxml/lxml.etree.pyx
lxml/trunk/src/lxml/tests/test_elementtree.py
Log:
r5550 at lenny: sbehnel | 2010-04-01 23:09:19 +0200
allow user code to globally register namespace prefixes
Modified: lxml/trunk/CHANGES.txt
==============================================================================
--- lxml/trunk/CHANGES.txt (original)
+++ lxml/trunk/CHANGES.txt Thu Apr 1 23:09:24 2010
@@ -8,6 +8,11 @@
Features added
--------------
+* New function ``lxml.etree.register_namespace(prefix, uri)`` that
+ globally registers a namespace prefix for a namespace that newly
+ created Elements in that namespace will use automatically. Follows
+ ElementTree 1.3.
+
* Support 'unicode' string name as encoding parameter in
``tostring()``, following ElementTree 1.3.
Modified: lxml/trunk/src/lxml/lxml.etree.pyx
==============================================================================
--- lxml/trunk/src/lxml/lxml.etree.pyx (original)
+++ lxml/trunk/src/lxml/lxml.etree.pyx Thu Apr 1 23:09:24 2010
@@ -34,7 +34,7 @@
'iterparse', 'iterwalk', 'parse', 'parseid', 'set_default_parser',
'set_element_class_lookup', 'strip_attributes', 'strip_elements',
'strip_tags', 'tostring', 'tostringlist', 'tounicode',
- 'use_global_python_log'
+ 'use_global_python_log', 'register_namespace'
]
cimport tree, python, config
@@ -140,6 +140,25 @@
b"http://codespeak.net/lxml/objectify/pytype" : b"py",
}
+cdef object _check_internal_prefix = re.compile(b"ns\d+$").match
+
+def register_namespace(prefix, uri):
+ u"""Registers a namespace prefix that newly created Elements in that
+ namespace will use. The registry is global, and any existing
+ mapping for either the given prefix or the namespace URI will be
+ removed.
+ """
+ prefix_utf, uri_utf = _utf8(prefix), _utf8(uri)
+ if _check_internal_prefix(prefix_utf):
+ raise ValueError("Prefix format reserved for internal use")
+ _tagValidOrRaise(prefix_utf)
+ _uriValidOrRaise(uri_utf)
+ for k, v in _DEFAULT_NAMESPACE_PREFIXES.items():
+ if k == uri_utf or v == prefix_utf:
+ del _DEFAULT_NAMESPACE_PREFIXES[k]
+ _DEFAULT_NAMESPACE_PREFIXES[uri_utf] = prefix_utf
+
+
# Error superclass for ElementTree compatibility
class Error(Exception):
pass
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 Thu Apr 1 23:09:24 2010
@@ -2619,6 +2619,26 @@
root2 = fromstring(xml2)
self.assertEquals('TEST', root[0].get('{%s}a' % ns_href))
+ required_versions_ET['test_itertext'] = (1,3)
+ def test_register_namespace(self):
+ # ET 1.3+
+ Element = self.etree.Element
+ tostring = self.etree.tostring
+ prefix = 'TESTPREFIX'
+ namespace = 'http://seriously.unknown/namespace/URI'
+
+ el = Element('{%s}test' % namespace)
+ self.assertEquals(_bytes('' % namespace),
+ self._writeElement(el))
+
+ self.etree.register_namespace(prefix, namespace)
+ el = Element('{%s}test' % namespace)
+ self.assertEquals(_bytes('<%s:test xmlns:%s="%s">' % (
+ prefix, prefix, namespace, prefix)),
+ self._writeElement(el))
+
+ self.assertRaises(ValueError, self.etree.register_namespace, 'ns25', namespace)
+
def test_tostring(self):
tostring = self.etree.tostring
Element = self.etree.Element
From scoder at codespeak.net Thu Apr 1 23:34:15 2010
From: scoder at codespeak.net (scoder at codespeak.net)
Date: Thu, 1 Apr 2010 23:34:15 +0200 (CEST)
Subject: [Lxml-checkins] r73260 - in lxml/trunk: . doc
Message-ID: <20100401213415.13CCD282BD8@codespeak.net>
Author: scoder
Date: Thu Apr 1 23:34:13 2010
New Revision: 73260
Modified:
lxml/trunk/ (props changed)
lxml/trunk/doc/element_classes.txt
Log:
r5552 at lenny: sbehnel | 2010-04-01 23:34:05 +0200
doc update: proxy guaranteed to stay alive as long as referenced
Modified: lxml/trunk/doc/element_classes.txt
==============================================================================
--- lxml/trunk/doc/element_classes.txt (original)
+++ lxml/trunk/doc/element_classes.txt Thu Apr 1 23:34:13 2010
@@ -67,18 +67,44 @@
an ``__init___`` or ``__new__`` method. There should not be any
internal state either, except for the data stored in the underlying
XML tree. Element instances are created and garbage collected at
-need, so there is no way to predict when and how often a proxy is
-created for them. Even worse, when the ``__init__`` method is called,
-the object is not even initialized yet to represent the XML tag, so
-there is not much use in providing an ``__init__`` method in
+need, so there is normally no way to predict when and how often a
+proxy is created for them. Even worse, when the ``__init__`` method
+is called, the object is not even initialized yet to represent the XML
+tag, so there is not much use in providing an ``__init__`` method in
subclasses.
-Most use cases will not require any class initialisation, so you can content
-yourself with skipping to the next section for now. However, if you really
-need to set up your element class on instantiation, there is one possible way
-to do so. ElementBase classes have an ``_init()`` method that can be
-overridden. It can be used to modify the XML tree, e.g. to construct special
-children or verify and update attributes.
+Most use cases will not require any class initialisation or proxy
+state, so you can content yourself with skipping to the next section
+for now. However, if you really need to set up your element class on
+instantiation, or need a way to persistently store state in the proxy
+instances instead of the XML tree, here is a way to do so.
+
+There is one important guarantee regarding Element proxies. Once a
+proxy has been instantiated, it will keep alive as long as there is a
+Python reference to it, and any access to the XML element in the tree
+will return this very instance. Therefore, if you need to store local
+state in a custom Element class (which is generally discouraged), you
+can do so by keeping the Elements in a tree alive. If the tree
+doesn't change, you can simply do this:
+
+.. sourcecode:: python
+
+ proxy_cache = list(root.iter())
+
+or
+
+.. sourcecode:: python
+
+ proxy_cache = set(root.iter())
+
+or use any other suitable container. Note that you have to keep this
+cache manually up to date if the tree changes, which can get tricky in
+cases.
+
+For proxy initialisation, ElementBase classes have an ``_init()``
+method that can be overridden, as oppose to the normal ``__init__()``
+method. It can be used to modify the XML tree, e.g. to construct
+special children or verify and update attributes.
The semantics of ``_init()`` are as follows:
From scoder at codespeak.net Thu Apr 1 23:50:34 2010
From: scoder at codespeak.net (scoder at codespeak.net)
Date: Thu, 1 Apr 2010 23:50:34 +0200 (CEST)
Subject: [Lxml-checkins] r73261 - in lxml/trunk: . src/lxml
Message-ID: <20100401215034.77215282BD8@codespeak.net>
Author: scoder
Date: Thu Apr 1 23:50:32 2010
New Revision: 73261
Modified:
lxml/trunk/ (props changed)
lxml/trunk/CHANGES.txt
lxml/trunk/src/lxml/lxml.etree.pyx
lxml/trunk/src/lxml/parser.pxi
Log:
r5554 at lenny: sbehnel | 2010-04-01 23:50:28 +0200
export XMLParser as XMLTreeBuilder, as ET 1.2 calls it
Modified: lxml/trunk/CHANGES.txt
==============================================================================
--- lxml/trunk/CHANGES.txt (original)
+++ lxml/trunk/CHANGES.txt Thu Apr 1 23:50:32 2010
@@ -74,6 +74,9 @@
Bugs fixed
----------
+* Export ElementTree compatible XML parser class as
+ ``XMLTreeBuilder``, as it is called in ET 1.2.
+
* ObjectifiedDataElements in lxml.objectify were not hashable.
* Crash in XPath evaluation when reading smart strings from a document
Modified: lxml/trunk/src/lxml/lxml.etree.pyx
==============================================================================
--- lxml/trunk/src/lxml/lxml.etree.pyx (original)
+++ lxml/trunk/src/lxml/lxml.etree.pyx Thu Apr 1 23:50:32 2010
@@ -25,16 +25,16 @@
'SubElement', 'TreeBuilder', 'XInclude', 'XIncludeError', 'XML',
'XMLDTDID', 'XMLID', 'XMLParser', 'XMLSchema', 'XMLSchemaError',
'XMLSchemaParseError', 'XMLSchemaValidateError', 'XMLSyntaxError',
- 'XPath', 'XPathDocumentEvaluator', 'XPathError', 'XPathEvalError',
- 'XPathEvaluator', 'XPathFunctionError', 'XPathResultError',
+ 'XMLTreeBuilder', 'XPath', 'XPathDocumentEvaluator', 'XPathError',
+ 'XPathEvalError', 'XPathEvaluator', 'XPathFunctionError', 'XPathResultError',
'XPathSyntaxError', 'XSLT', 'XSLTAccessControl', 'XSLTApplyError',
'XSLTError', 'XSLTExtension', 'XSLTExtensionError', 'XSLTParseError',
'XSLTSaveError', 'cleanup_namespaces', 'clear_error_log', 'dump',
'fromstring', 'fromstringlist', 'get_default_parser', 'iselement',
- 'iterparse', 'iterwalk', 'parse', 'parseid', 'set_default_parser',
- 'set_element_class_lookup', 'strip_attributes', 'strip_elements',
- 'strip_tags', 'tostring', 'tostringlist', 'tounicode',
- 'use_global_python_log', 'register_namespace'
+ 'iterparse', 'iterwalk', 'parse', 'parseid', 'register_namespace',
+ 'set_default_parser', 'set_element_class_lookup', 'strip_attributes',
+ 'strip_elements', 'strip_tags', 'tostring', 'tostringlist', 'tounicode',
+ 'use_global_python_log'
]
cimport tree, python, config
Modified: lxml/trunk/src/lxml/parser.pxi
==============================================================================
--- lxml/trunk/src/lxml/parser.pxi (original)
+++ lxml/trunk/src/lxml/parser.pxi Thu Apr 1 23:50:32 2010
@@ -1306,6 +1306,9 @@
encoding=encoding,
schema=schema)
+# ET 1.2 compatible name
+XMLTreeBuilder = ETCompatXMLParser
+
cdef XMLParser __DEFAULT_XML_PARSER
__DEFAULT_XML_PARSER = XMLParser()
From lxml-checkins at codespeak.net Fri Apr 2 00:57:07 2010
From: lxml-checkins at codespeak.net (Selling Viagra on-line since 1997)
Date: Fri, 2 Apr 2010 01:57:07 +0300
Subject: [Lxml-checkins] Hot Sale,
lxml-checkins! 77% off on top goods Ahanuwayg
Message-ID: <20100401225706.BCBDA36C21E@codespeak.net>
An HTML attachment was scrubbed...
URL: http://codespeak.net/pipermail/lxml-checkins/attachments/20100402/d2523615/attachment.htm
From scoder at codespeak.net Fri Apr 2 07:43:44 2010
From: scoder at codespeak.net (scoder at codespeak.net)
Date: Fri, 2 Apr 2010 07:43:44 +0200 (CEST)
Subject: [Lxml-checkins] r73283 - lxml/trunk
Message-ID: <20100402054344.8E375282B9C@codespeak.net>
Author: scoder
Date: Fri Apr 2 07:43:43 2010
New Revision: 73283
Modified:
lxml/trunk/ (props changed)
lxml/trunk/CHANGES.txt
Log:
r5556 at lenny: sbehnel | 2010-04-02 07:43:38 +0200
changelog
Modified: lxml/trunk/CHANGES.txt
==============================================================================
--- lxml/trunk/CHANGES.txt (original)
+++ lxml/trunk/CHANGES.txt Fri Apr 2 07:43:43 2010
@@ -77,7 +77,9 @@
* Export ElementTree compatible XML parser class as
``XMLTreeBuilder``, as it is called in ET 1.2.
-* ObjectifiedDataElements in lxml.objectify were not hashable.
+* ObjectifiedDataElements in lxml.objectify were not hashable. They
+ now use the hash value of the underlying Python value (string,
+ number, etc.) to which they compare equal.
* Crash in XPath evaluation when reading smart strings from a document
other than the original context document.
From scoder at codespeak.net Tue Apr 6 22:14:46 2010
From: scoder at codespeak.net (scoder at codespeak.net)
Date: Tue, 6 Apr 2010 22:14:46 +0200 (CEST)
Subject: [Lxml-checkins] r73467 - in lxml/trunk: . src/lxml
Message-ID: <20100406201446.0D329282B9C@codespeak.net>
Author: scoder
Date: Tue Apr 6 22:14:45 2010
New Revision: 73467
Modified:
lxml/trunk/ (props changed)
lxml/trunk/src/lxml/parser.pxi
Log:
r5558 at lenny: sbehnel | 2010-04-02 18:01:37 +0200
docstring fix
Modified: lxml/trunk/src/lxml/parser.pxi
==============================================================================
--- lxml/trunk/src/lxml/parser.pxi (original)
+++ lxml/trunk/src/lxml/parser.pxi Tue Apr 6 22:14:45 2010
@@ -1271,7 +1271,7 @@
u"""ETCompatXMLParser(self, encoding=None, attribute_defaults=False, \
dtd_validation=False, load_dtd=False, no_network=True, \
ns_clean=False, recover=False, schema=None, \
- remove_blank_text=False, resolve_entities=True, \
+ huge_tree=False, remove_blank_text=False, resolve_entities=True, \
remove_comments=True, remove_pis=True, strip_cdata=True, \
target=None, compact=True)
From scoder at codespeak.net Tue Apr 6 22:15:14 2010
From: scoder at codespeak.net (scoder at codespeak.net)
Date: Tue, 6 Apr 2010 22:15:14 +0200 (CEST)
Subject: [Lxml-checkins] r73468 - in lxml/trunk: . src/lxml
Message-ID: <20100406201514.5A160282B9C@codespeak.net>
Author: scoder
Date: Tue Apr 6 22:15:12 2010
New Revision: 73468
Modified:
lxml/trunk/ (props changed)
lxml/trunk/CHANGES.txt
lxml/trunk/src/lxml/classlookup.pxi
Log:
r5559 at lenny: sbehnel | 2010-04-06 22:14:22 +0200
prevent crash when instantiating CommentBase and friends
Modified: lxml/trunk/CHANGES.txt
==============================================================================
--- lxml/trunk/CHANGES.txt (original)
+++ lxml/trunk/CHANGES.txt Tue Apr 6 22:15:12 2010
@@ -74,6 +74,8 @@
Bugs fixed
----------
+* Prevent crash when instantiating ``CommentBase`` and friends.
+
* Export ElementTree compatible XML parser class as
``XMLTreeBuilder``, as it is called in ET 1.2.
Modified: lxml/trunk/src/lxml/classlookup.pxi
==============================================================================
--- lxml/trunk/src/lxml/classlookup.pxi (original)
+++ lxml/trunk/src/lxml/classlookup.pxi Tue Apr 6 22:15:12 2010
@@ -101,8 +101,7 @@
cdef class CommentBase(_Comment):
u"""All custom Comment classes must inherit from this one.
- Note that you cannot (and must not) instantiate this class or its
- subclasses.
+ To create an XML Comment instance, use the ``Comment()`` factory.
Subclasses *must not* override __init__ or __new__ as it is
absolutely undefined when these objects will be created or
@@ -111,12 +110,24 @@
creation, you can implement an ``_init(self)`` method that will be
called after object creation.
"""
+ def __init__(self, text):
+ # copied from Comment() factory
+ cdef _Document doc
+ cdef xmlDoc* c_doc
+ if text is None:
+ text = b''
+ else:
+ text = _utf8(text)
+ c_doc = _newXMLDoc()
+ doc = _documentFactory(c_doc, None)
+ self._c_node = _createComment(c_doc, _cstr(text))
+ tree.xmlAddChild(c_doc, self._c_node)
cdef class PIBase(_ProcessingInstruction):
u"""All custom Processing Instruction classes must inherit from this one.
- Note that you cannot (and must not) instantiate this class or its
- subclasses.
+ To create an XML ProcessingInstruction instance, use the ``PI()``
+ factory.
Subclasses *must not* override __init__ or __new__ as it is
absolutely undefined when these objects will be created or
@@ -125,12 +136,24 @@
creation, you can implement an ``_init(self)`` method that will be
called after object creation.
"""
+ def __init__(self, target, text=None):
+ # copied from PI() factory
+ cdef _Document doc
+ cdef xmlDoc* c_doc
+ target = _utf8(target)
+ if text is None:
+ text = b''
+ else:
+ text = _utf8(text)
+ c_doc = _newXMLDoc()
+ doc = _documentFactory(c_doc, None)
+ self._c_node = _createPI(c_doc, _cstr(target), _cstr(text))
+ tree.xmlAddChild(c_doc, self._c_node)
cdef class EntityBase(_Entity):
u"""All custom Entity classes must inherit from this one.
- Note that you cannot (and must not) instantiate this class or its
- subclasses.
+ To create an XML Entity instance, use the ``Entity()`` factory.
Subclasses *must not* override __init__ or __new__ as it is
absolutely undefined when these objects will be created or
@@ -139,7 +162,21 @@
creation, you can implement an ``_init(self)`` method that will be
called after object creation.
"""
-
+ def __init__(self, name):
+ cdef _Document doc
+ cdef xmlDoc* c_doc
+ cdef char* c_name
+ name_utf = _utf8(name)
+ c_name = _cstr(name_utf)
+ if c_name[0] == c'#':
+ if not _characterReferenceIsValid(c_name + 1):
+ raise ValueError, u"Invalid character reference: '%s'" % name
+ elif not _xmlNameIsValid(c_name):
+ raise ValueError, u"Invalid entity reference: '%s'" % name
+ c_doc = _newXMLDoc()
+ doc = _documentFactory(c_doc, None)
+ self._c_node = _createEntity(c_doc, c_name)
+ tree.xmlAddChild(c_doc, self._c_node)
################################################################################
# Element class lookup
From scoder at codespeak.net Fri Apr 9 20:29:00 2010
From: scoder at codespeak.net (scoder at codespeak.net)
Date: Fri, 9 Apr 2010 20:29:00 +0200 (CEST)
Subject: [Lxml-checkins] r73601 - in lxml/trunk: . src/lxml
Message-ID: <20100409182900.54968282BAD@codespeak.net>
Author: scoder
Date: Fri Apr 9 20:28:57 2010
New Revision: 73601
Modified:
lxml/trunk/ (props changed)
lxml/trunk/src/lxml/iterparse.pxi
Log:
r5562 at lenny: sbehnel | 2010-04-09 20:28:51 +0200
docstring cleanup
Modified: lxml/trunk/src/lxml/iterparse.pxi
==============================================================================
--- lxml/trunk/src/lxml/iterparse.pxi (original)
+++ lxml/trunk/src/lxml/iterparse.pxi Fri Apr 9 20:28:57 2010
@@ -311,48 +311,48 @@
cdef class iterparse(_BaseParser):
u"""iterparse(self, source, events=("end",), tag=None, attribute_defaults=False, dtd_validation=False, load_dtd=False, no_network=True, remove_blank_text=False, remove_comments=False, remove_pis=False, encoding=None, html=False, huge_tree=False, schema=None)
-Incremental parser.
+ Incremental parser.
-Parses XML into a tree and generates tuples (event, element) in a
-SAX-like fashion. ``event`` is any of 'start', 'end', 'start-ns',
-'end-ns'.
-
-For 'start' and 'end', ``element`` is the Element that the parser just
-found opening or closing. For 'start-ns', it is a tuple (prefix, URI) of
-a new namespace declaration. For 'end-ns', it is simply None. Note that
-all start and end events are guaranteed to be properly nested.
-
-The keyword argument ``events`` specifies a sequence of event type names
-that should be generated. By default, only 'end' events will be
-generated.
-
-The additional ``tag`` argument restricts the 'start' and 'end' events to
-those elements that match the given tag. By default, events are generated
-for all elements. Note that the 'start-ns' and 'end-ns' events are not
-impacted by this restriction.
-
-The other keyword arguments in the constructor are mainly based on the
-libxml2 parser configuration. A DTD will also be loaded if validation or
-attribute default values are requested.
-
-Available boolean keyword arguments:
- - attribute_defaults: read default attributes from DTD
- - dtd_validation: validate (if DTD is available)
- - load_dtd: use DTD for parsing
- - no_network: prevent network access for related files
- - remove_blank_text: discard blank text nodes
- - remove_comments: discard comments
- - remove_pis: discard processing instructions
- - strip_cdata: replace CDATA sections by normal text content (default: True)
- - compact: safe memory for short text content (default: True)
- - resolve_entities: replace entities by their text value (default: True)
- - huge_tree: disable security restrictions and support very deep trees
- and very long text content (only affects libxml2 2.7+)
-
-Other keyword arguments:
- - encoding: override the document encoding
- - schema: an XMLSchema to validate against
-""" # stupid, stupid MSVC has a 2048 bytes limit for strings!!!
+ Parses XML into a tree and generates tuples (event, element) in a
+ SAX-like fashion. ``event`` is any of 'start', 'end', 'start-ns',
+ 'end-ns'.
+
+ For 'start' and 'end', ``element`` is the Element that the parser just
+ found opening or closing. For 'start-ns', it is a tuple (prefix, URI) of
+ a new namespace declaration. For 'end-ns', it is simply None. Note that
+ all start and end events are guaranteed to be properly nested.
+
+ The keyword argument ``events`` specifies a sequence of event type names
+ that should be generated. By default, only 'end' events will be
+ generated.
+
+ The additional ``tag`` argument restricts the 'start' and 'end' events to
+ those elements that match the given tag. By default, events are generated
+ for all elements. Note that the 'start-ns' and 'end-ns' events are not
+ impacted by this restriction.
+
+ The other keyword arguments in the constructor are mainly based on the
+ libxml2 parser configuration. A DTD will also be loaded if validation or
+ attribute default values are requested.
+
+ Available boolean keyword arguments:
+ - attribute_defaults: read default attributes from DTD
+ - dtd_validation: validate (if DTD is available)
+ - load_dtd: use DTD for parsing
+ - no_network: prevent network access for related files
+ - remove_blank_text: discard blank text nodes
+ - remove_comments: discard comments
+ - remove_pis: discard processing instructions
+ - strip_cdata: replace CDATA sections by normal text content (default: True)
+ - compact: safe memory for short text content (default: True)
+ - resolve_entities: replace entities by their text value (default: True)
+ - huge_tree: disable security restrictions and support very deep trees
+ and very long text content (only affects libxml2 2.7+)
+
+ Other keyword arguments:
+ - encoding: override the document encoding
+ - schema: an XMLSchema to validate against
+ """
cdef object _tag
cdef object _events
cdef readonly object root
From scoder at codespeak.net Sun Apr 11 19:34:59 2010
From: scoder at codespeak.net (scoder at codespeak.net)
Date: Sun, 11 Apr 2010 19:34:59 +0200 (CEST)
Subject: [Lxml-checkins] r73648 - in lxml/trunk: . src/lxml/tests
Message-ID: <20100411173459.DB527282B90@codespeak.net>
Author: scoder
Date: Sun Apr 11 19:34:58 2010
New Revision: 73648
Modified:
lxml/trunk/ (props changed)
lxml/trunk/src/lxml/tests/test_css.py
Log:
r5564 at lenny: sbehnel | 2010-04-11 19:31:29 +0200
execute doctests in cssselect.py
Modified: lxml/trunk/src/lxml/tests/test_css.py
==============================================================================
--- lxml/trunk/src/lxml/tests/test_css.py (original)
+++ lxml/trunk/src/lxml/tests/test_css.py Sun Apr 11 19:34:58 2010
@@ -129,5 +129,6 @@
if sys.version_info >= (2,4):
suite.addTests([make_doctest('test_css_select.txt')])
suite.addTests([make_doctest('test_css.txt')])
+ suite.addTests(doctest.DocTestSuite(cssselect))
suite.addTests(list(CSSTestCase.all()))
return suite
From scoder at codespeak.net Sun Apr 11 19:35:03 2010
From: scoder at codespeak.net (scoder at codespeak.net)
Date: Sun, 11 Apr 2010 19:35:03 +0200 (CEST)
Subject: [Lxml-checkins] r73649 - in lxml/trunk: . src/lxml
Message-ID: <20100411173503.3AB10282B90@codespeak.net>
Author: scoder
Date: Sun Apr 11 19:35:01 2010
New Revision: 73649
Modified:
lxml/trunk/ (props changed)
lxml/trunk/CHANGES.txt
lxml/trunk/src/lxml/cssselect.py
Log:
r5565 at lenny: sbehnel | 2010-04-11 19:34:52 +0200
ticket #560381: allow passing prefix-to-namespace mapping into CSSSelector()
Modified: lxml/trunk/CHANGES.txt
==============================================================================
--- lxml/trunk/CHANGES.txt (original)
+++ lxml/trunk/CHANGES.txt Sun Apr 11 19:35:01 2010
@@ -8,6 +8,9 @@
Features added
--------------
+* Keyword argument ``namespaces`` in ``lxml.cssselect.CSSSelector()``
+ to pass a prefix-to-namespace mapping for the selector.
+
* New function ``lxml.etree.register_namespace(prefix, uri)`` that
globally registers a namespace prefix for a namespace that newly
created Elements in that namespace will use automatically. Follows
Modified: lxml/trunk/src/lxml/cssselect.py
==============================================================================
--- lxml/trunk/src/lxml/cssselect.py (original)
+++ lxml/trunk/src/lxml/cssselect.py Sun Apr 11 19:35:01 2010
@@ -32,10 +32,24 @@
>>> root = etree.XML("TEXT")
>>> [ el.tag for el in select(root) ]
['child']
+
+ To use CSS namespaces, you need to pass a prefix-to-namespace
+ mapping as ``namespaces`` keyword argument::
+
+ >>> rdfns = 'http://www.w3.org/1999/02/22-rdf-syntax-ns#'
+ >>> select_ns = cssselect.CSSSelector('root > rdf|Description',
+ ... namespaces={'rdf': rdfns})
+
+ >>> rdf = etree.XML((
+ ... ''
+ ... 'blah'
+ ... '') % rdfns)
+ >>> [(el.tag, el.text) for el in select_ns(rdf)]
+ [('{http://www.w3.org/1999/02/22-rdf-syntax-ns#}Description', 'blah')]
"""
- def __init__(self, css):
+ def __init__(self, css, namespaces=None):
path = css_to_xpath(css)
- etree.XPath.__init__(self, path)
+ etree.XPath.__init__(self, path, namespaces=namespaces)
self.css = css
def __repr__(self):
From lxml-checkins at codespeak.net Fri Apr 16 08:50:26 2010
From: lxml-checkins at codespeak.net (© Pfizer Inc ® 1916-2010)
Date: Fri, 16 Apr 2010 08:50:26 +0200 (CEST)
Subject: [Lxml-checkins] 344 C-A-N-A-D-l-A-N P-H-A-R-M-A-C-Y
Message-ID: <20100416065026.DA3FA282B9D@codespeak.net>
Dear lxml-checkins at codespeak.net
Get ready to make her happy.
Discount price store: ID71040142
http://ugp.squareunit.ru?efa
We do guarantee high-quality medications, instant worldwide delivery and friendly support.
? 2001-2010 Pfizer Inc. All rights reserved.
From lxml-checkins at codespeak.net Mon Apr 19 14:49:40 2010
From: lxml-checkins at codespeak.net (Erectile Dysfunction Treatment - VIAGRA ® (ED))
Date: Mon, 19 Apr 2010 12:49:40 -0000
Subject: [Lxml-checkins] 19.4.2010 Pfizer 38% OFF.
Message-ID: <000301cadfbe$bb6bde54$425aa8c0@.dsl.telesp.net.br>
An HTML attachment was scrubbed...
URL: http://codespeak.net/pipermail/lxml-checkins/attachments/20100419/5d61bf70/attachment.htm
From lxml-checkins at codespeak.net Tue Apr 20 22:31:28 2010
From: lxml-checkins at codespeak.net (VIAGRA ® Official Seller)
Date: Tue, 20 Apr 2010 22:31:28 +0200 (CEST)
Subject: [Lxml-checkins] lxml-checkins@codespeak.net April 68% off
Message-ID: <20100420203128.C5077282BEC@codespeak.net>
An HTML attachment was scrubbed...
URL: http://codespeak.net/pipermail/lxml-checkins/attachments/20100420/0366e92e/attachment.htm
From scoder at codespeak.net Tue Apr 27 21:41:29 2010
From: scoder at codespeak.net (scoder at codespeak.net)
Date: Tue, 27 Apr 2010 21:41:29 +0200 (CEST)
Subject: [Lxml-checkins] r74122 - in lxml/trunk: . src/lxml/html
Message-ID: <20100427194129.1CB1C282B9D@codespeak.net>
Author: scoder
Date: Tue Apr 27 21:41:28 2010
New Revision: 74122
Modified:
lxml/trunk/ (props changed)
lxml/trunk/src/lxml/html/__init__.py
Log:
r5568 at lenny: sbehnel | 2010-04-13 20:33:51 +0200
lxml.html.tostring(): only drop tag when serialising as HTML
Modified: lxml/trunk/src/lxml/html/__init__.py
==============================================================================
--- lxml/trunk/src/lxml/html/__init__.py (original)
+++ lxml/trunk/src/lxml/html/__init__.py Tue Apr 27 21:41:28 2010
@@ -1491,7 +1491,7 @@
"""
html = etree.tostring(doc, method=method, pretty_print=pretty_print,
encoding=encoding)
- if not include_meta_content_type:
+ if method == 'html' and not include_meta_content_type:
if isinstance(html, str):
html = __str_replace_meta_content_type('', html)
else:
From scoder at codespeak.net Tue Apr 27 21:41:40 2010
From: scoder at codespeak.net (scoder at codespeak.net)
Date: Tue, 27 Apr 2010 21:41:40 +0200 (CEST)
Subject: [Lxml-checkins] r74123 - in lxml/trunk: . src/lxml
Message-ID: <20100427194140.81D41282B9D@codespeak.net>
Author: scoder
Date: Tue Apr 27 21:41:38 2010
New Revision: 74123
Modified:
lxml/trunk/ (props changed)
lxml/trunk/CHANGES.txt
lxml/trunk/src/lxml/apihelpers.pxi
lxml/trunk/src/lxml/docloader.pxi
lxml/trunk/src/lxml/dtd.pxi
lxml/trunk/src/lxml/extensions.pxi
lxml/trunk/src/lxml/iterparse.pxi
lxml/trunk/src/lxml/lxml.etree.pyx
lxml/trunk/src/lxml/parser.pxi
lxml/trunk/src/lxml/readonlytree.pxi
lxml/trunk/src/lxml/relaxng.pxi
lxml/trunk/src/lxml/saxparser.pxi
lxml/trunk/src/lxml/schematron.pxi
lxml/trunk/src/lxml/serializer.pxi
lxml/trunk/src/lxml/xinclude.pxi
lxml/trunk/src/lxml/xmlerror.pxi
lxml/trunk/src/lxml/xmlschema.pxi
lxml/trunk/src/lxml/xpath.pxi
lxml/trunk/src/lxml/xslt.pxi
lxml/trunk/src/lxml/xsltext.pxi
Log:
r5569 at lenny: sbehnel | 2010-04-27 21:41:20 +0200
API hardening against uninitialised proxies and missing __init__ calls
Modified: lxml/trunk/CHANGES.txt
==============================================================================
--- lxml/trunk/CHANGES.txt (original)
+++ lxml/trunk/CHANGES.txt Tue Apr 27 21:41:38 2010
@@ -77,6 +77,9 @@
Bugs fixed
----------
+* API is hardened against invalid proxy instances to prevent crashes
+ due to incorrectly instantiated Element instances.
+
* Prevent crash when instantiating ``CommentBase`` and friends.
* Export ElementTree compatible XML parser class as
Modified: lxml/trunk/src/lxml/apihelpers.pxi
==============================================================================
--- lxml/trunk/src/lxml/apihelpers.pxi (original)
+++ lxml/trunk/src/lxml/apihelpers.pxi Tue Apr 27 21:41:38 2010
@@ -11,6 +11,12 @@
displayNode(c_child, indent + 1)
c_child = c_child.next
+cdef inline int _assertValidNode(_Element element) except -1:
+ assert element._c_node is not NULL, u"invalid Element proxy at %s" % id(element)
+
+cdef inline int _assertValidDoc(_Document doc) except -1:
+ assert doc._c_doc is not NULL, u"invalid Document proxy at %s" % id(doc)
+
cdef _Document _documentOrRaise(object input):
u"""Call this to get the document of a _Document, _ElementTree or _Element
object, or to raise an exception if it can't be determined.
@@ -33,8 +39,8 @@
if doc is None:
raise ValueError, u"Input object has no document: %s" % \
python._fqtypename(input)
- else:
- return doc
+ _assertValidDoc(doc)
+ return doc
cdef _Element _rootNodeOrRaise(object input):
u"""Call this to get the root node of a _Document, _ElementTree or
@@ -55,36 +61,41 @@
if node is None:
raise ValueError, u"Input object has no element: %s" % \
python._fqtypename(input)
- else:
- return node
+ _assertValidNode(node)
+ return node
cdef _Document _documentOf(object input):
# call this to get the document of a
# _Document, _ElementTree or _Element object
# may return None!
cdef _Element element
+ cdef _Document doc = None
if isinstance(input, _ElementTree):
element = (<_ElementTree>input)._context_node
if element is not None:
- return element._doc
+ doc = element._doc
elif isinstance(input, _Element):
- return (<_Element>input)._doc
+ doc = (<_Element>input)._doc
elif isinstance(input, _Document):
- return <_Document>input
- return None
+ doc = <_Document>input
+ if doc is not None:
+ _assertValidDoc(doc)
+ return doc
cdef _Element _rootNodeOf(object input):
# call this to get the root node of a
# _Document, _ElementTree or _Element object
# may return None!
+ cdef _Element element = None
if isinstance(input, _ElementTree):
- return (<_ElementTree>input)._context_node
+ element = (<_ElementTree>input)._context_node
elif isinstance(input, _Element):
- return <_Element>input
+ element = <_Element>input
elif isinstance(input, _Document):
- return (<_Document>input).getroot()
- else:
- return None
+ element = (<_Document>input).getroot()
+ if element is not None:
+ _assertValidNode(element)
+ return element
cdef _Element _makeElement(tag, xmlDoc* c_doc, _Document doc,
_BaseParser parser, text, tail, attrib, nsmap,
@@ -183,6 +194,7 @@
cdef xmlDoc* c_doc
if parent is None or parent._doc is None:
return None
+ _assertValidNode(parent)
ns_utf, name_utf = _getNsTag(tag)
c_doc = parent._doc._c_doc
@@ -1181,6 +1193,7 @@
if c_node is not NULL:
for element in elements:
assert element is not None, u"Node must not be None"
+ _assertValidNode(element)
# move element and tail over
c_source_doc = element._c_node.doc
c_next = element._c_node.next
@@ -1205,10 +1218,12 @@
if left_to_right:
for element in elements:
assert element is not None, u"Node must not be None"
+ _assertValidNode(element)
_appendChild(parent, element)
else:
for element in elements:
assert element is not None, u"Node must not be None"
+ _assertValidNode(element)
_prependChild(parent, element)
return 0
Modified: lxml/trunk/src/lxml/docloader.pxi
==============================================================================
--- lxml/trunk/src/lxml/docloader.pxi (original)
+++ lxml/trunk/src/lxml/docloader.pxi Tue Apr 27 21:41:38 2010
@@ -1,6 +1,7 @@
# Custom resolver API
ctypedef enum _InputDocumentDataType:
+ PARSER_DATA_INVALID
PARSER_DATA_EMPTY
PARSER_DATA_STRING
PARSER_DATA_FILENAME
@@ -12,6 +13,10 @@
cdef object _filename
cdef object _file
+ def __cinit__(self):
+ self._type = PARSER_DATA_INVALID
+
+
cdef class Resolver:
u"This is the base class of all resolvers."
def resolve(self, system_url, public_id, context):
@@ -101,7 +106,7 @@
cdef class _ResolverRegistry:
cdef object _resolvers
cdef Resolver _default_resolver
- def __init__(self, Resolver default_resolver=None):
+ def __cinit__(self, Resolver default_resolver=None):
self._resolvers = set()
self._default_resolver = default_resolver
Modified: lxml/trunk/src/lxml/dtd.pxi
==============================================================================
--- lxml/trunk/src/lxml/dtd.pxi (original)
+++ lxml/trunk/src/lxml/dtd.pxi Tue Apr 27 21:41:38 2010
@@ -28,8 +28,10 @@
catalog.
"""
cdef tree.xmlDtd* _c_dtd
- def __init__(self, file=None, *, external_id=None):
+ def __cinit__(self):
self._c_dtd = NULL
+
+ def __init__(self, file=None, *, external_id=None):
_Validator.__init__(self)
if file is not None:
if _isString(file):
@@ -69,6 +71,7 @@
cdef dtdvalid.xmlValidCtxt* valid_ctxt
cdef int ret
+ assert self._c_dtd is not NULL, "DTD not initialised"
doc = _documentOrRaise(etree)
root_node = _rootNodeOrRaise(etree)
Modified: lxml/trunk/src/lxml/extensions.pxi
==============================================================================
--- lxml/trunk/src/lxml/extensions.pxi (original)
+++ lxml/trunk/src/lxml/extensions.pxi Tue Apr 27 21:41:38 2010
@@ -42,6 +42,8 @@
cdef _TempStore _temp_refs
cdef set _temp_documents
cdef _ExceptionContext _exc
+ def __cinit__(self):
+ self._xpathCtxt = NULL
def __init__(self, namespaces, extensions, enable_regexp,
build_smart_strings):
@@ -340,7 +342,7 @@
"""
cdef _Document doc
for doc in self._temp_documents:
- if doc._c_doc is c_node.doc:
+ if doc is not None and doc._c_doc is c_node.doc:
return doc
return None
@@ -374,7 +376,7 @@
cdef class _ExsltRegExp:
cdef dict _compile_map
- def __init__(self):
+ def __cinit__(self):
self._compile_map = {}
cdef _make_string(self, value):
Modified: lxml/trunk/src/lxml/iterparse.pxi
==============================================================================
--- lxml/trunk/src/lxml/iterparse.pxi (original)
+++ lxml/trunk/src/lxml/iterparse.pxi Tue Apr 27 21:41:38 2010
@@ -79,7 +79,7 @@
cdef char* _tag_href
cdef char* _tag_name
- def __init__(self):
+ def __cinit__(self):
self._ns_stack = []
self._pop_ns = self._ns_stack.pop
self._node_stack = []
@@ -581,7 +581,7 @@
cdef _Element node
cdef _Element next_node
cdef int ns_count
- if python.PyList_GET_SIZE(self._events):
+ if self._events:
return self._pop_event(0)
ns_count = 0
# find next node
@@ -597,7 +597,7 @@
next_node = None
while next_node is None:
# back off through parents
- self._index = self._index - 1
+ self._index -= 1
node = self._end_node()
if self._index < 0:
break
@@ -609,8 +609,8 @@
elif self._event_filter & ITERPARSE_FILTER_END_NS:
ns_count = _countNsDefs(next_node._c_node)
self._node_stack.append( (next_node, ns_count) )
- self._index = self._index + 1
- if python.PyList_GET_SIZE(self._events):
+ self._index += 1
+ if self._events:
return self._pop_event(0)
raise StopIteration
Modified: lxml/trunk/src/lxml/lxml.etree.pyx
==============================================================================
--- lxml/trunk/src/lxml/lxml.etree.pyx (original)
+++ lxml/trunk/src/lxml/lxml.etree.pyx Tue Apr 27 21:41:38 2010
@@ -171,7 +171,7 @@
def __init__(self, message, error_log=None):
if python.PY_VERSION_HEX >= 0x02050000:
# Python >= 2.5 uses new style class exceptions
- super(_LxmlError, self).__init__(message)
+ super(_Error, self).__init__(message)
else:
error_super_init(self, message)
if error_log is None:
@@ -179,7 +179,7 @@
else:
self.error_log = error_log.copy()
-cdef object _LxmlError = LxmlError
+cdef object _Error = Error
cdef object error_super_init = Error.__init__
@@ -326,7 +326,7 @@
cdef bint hasdoctype(self):
# DOCTYPE gets parsed into internal subset (xmlDTD*)
- return self._c_doc.intSubset is not NULL
+ return self._c_doc is not NULL and self._c_doc.intSubset is not NULL
cdef getdoctype(self):
# get doctype info: root tag, public/system ID (or None if not known)
@@ -355,8 +355,7 @@
cdef getxmlinfo(self):
# return XML version and encoding (or None if not known)
- cdef xmlDoc* c_doc
- c_doc = self._c_doc
+ cdef xmlDoc* c_doc = self._c_doc
if c_doc.version is NULL:
version = None
else:
@@ -377,8 +376,8 @@
cdef buildNewPrefix(self):
# get a new unique prefix ("nsX") for this document
- if self._ns_counter < python.PyTuple_GET_SIZE(_PREFIX_CACHE):
- ns = python.PyTuple_GET_ITEM(_PREFIX_CACHE, self._ns_counter)
+ if self._ns_counter < len(_PREFIX_CACHE):
+ ns = _PREFIX_CACHE[self._ns_counter]
python.Py_INCREF(ns)
else:
ns = python.PyBytes_FromFormat("ns%d", self._ns_counter)
@@ -444,12 +443,12 @@
c_ns = self._findOrBuildNodeNs(c_node, href, NULL, 0)
tree.xmlSetNs(c_node, c_ns)
-cdef __initPrefixCache():
+cdef tuple __initPrefixCache():
cdef int i
return tuple([ python.PyBytes_FromFormat("ns%d", i)
for i in range(30) ])
-cdef object _PREFIX_CACHE
+cdef tuple _PREFIX_CACHE
_PREFIX_CACHE = __initPrefixCache()
cdef extern from "etree_defs.h":
@@ -607,6 +606,7 @@
cdef _Element element
cdef bint left_to_right
cdef Py_ssize_t slicelength, step
+ _assertValidNode(self)
if value is None:
raise ValueError, u"cannot assign None"
if python.PySlice_Check(x):
@@ -622,6 +622,7 @@
else:
# otherwise: normal item assignment
element = value
+ _assertValidNode(element)
c_node = _findChild(self._c_node, x)
if c_node is NULL:
raise IndexError, u"list index out of range"
@@ -642,6 +643,7 @@
cdef xmlNode* c_node
cdef xmlNode* c_next
cdef Py_ssize_t step, slicelength
+ _assertValidNode(self)
if python.PySlice_Check(x):
# slice deletion
if _isFullSlice(x):
@@ -673,6 +675,7 @@
cdef xmlDoc* c_doc
cdef xmlNode* c_node
cdef _Document new_doc
+ _assertValidNode(self)
c_doc = _copyDocRoot(self._doc._c_doc, self._c_node) # recursive
new_doc = _documentFactory(c_doc, self._doc._parser)
root = new_doc.getroot()
@@ -691,6 +694,7 @@
Sets an element attribute.
"""
+ _assertValidNode(self)
_setAttributeValue(self, key, value)
def append(self, _Element element not None):
@@ -698,9 +702,11 @@
Adds a subelement to the end of this element.
"""
+ _assertValidNode(self)
+ _assertValidNode(element)
_appendChild(self, element)
- def addnext(self, _Element element):
+ def addnext(self, _Element element not None):
u"""addnext(self, element)
Adds the element as a following sibling directly after this
@@ -710,6 +716,8 @@
the root node of a document. Note that tail text is automatically
discarded when adding at the root level.
"""
+ _assertValidNode(self)
+ _assertValidNode(element)
if self._c_node.parent != NULL and not _isElement(self._c_node.parent):
if element._c_node.type != tree.XML_PI_NODE:
if element._c_node.type != tree.XML_COMMENT_NODE:
@@ -717,7 +725,7 @@
element.tail = None
_appendSibling(self, element)
- def addprevious(self, _Element element):
+ def addprevious(self, _Element element not None):
u"""addprevious(self, element)
Adds the element as a preceding sibling directly before this
@@ -727,6 +735,8 @@
before the root node of a document. Note that tail text is
automatically discarded when adding at the root level.
"""
+ _assertValidNode(self)
+ _assertValidNode(element)
if self._c_node.parent != NULL and not _isElement(self._c_node.parent):
if element._c_node.type != tree.XML_PI_NODE:
if element._c_node.type != tree.XML_COMMENT_NODE:
@@ -739,7 +749,10 @@
Extends the current children by the elements in the iterable.
"""
+ _assertValidNode(self)
for element in elements:
+ assert element is not None, u"Node must not be None"
+ _assertValidNode(element)
_appendChild(self, element)
def clear(self):
@@ -752,6 +765,7 @@
cdef xmlAttr* c_attr_next
cdef xmlNode* c_node
cdef xmlNode* c_node_next
+ _assertValidNode(self)
c_node = self._c_node
# remove self.text and self.tail
_removeText(c_node.children)
@@ -780,6 +794,8 @@
cdef xmlNode* c_node
cdef xmlNode* c_next
cdef xmlDoc* c_source_doc
+ _assertValidNode(self)
+ _assertValidNode(element)
c_node = _findChild(self._c_node, index)
if c_node is NULL:
_appendChild(self, element)
@@ -799,6 +815,8 @@
"""
cdef xmlNode* c_node
cdef xmlNode* c_next
+ _assertValidNode(self)
+ _assertValidNode(element)
c_node = element._c_node
if c_node.parent is not self._c_node:
raise ValueError, u"Element is not a child of this node."
@@ -819,6 +837,9 @@
cdef xmlNode* c_new_node
cdef xmlNode* c_new_next
cdef xmlDoc* c_source_doc
+ _assertValidNode(self)
+ _assertValidNode(old_element)
+ _assertValidNode(new_element)
c_old_node = old_element._c_node
if c_old_node.parent is not self._c_node:
raise ValueError, u"Element is not a child of this node."
@@ -840,11 +861,13 @@
def __get__(self):
if self._tag is not None:
return self._tag
+ _assertValidNode(self)
self._tag = _namespacedName(self._c_node)
return self._tag
def __set__(self, value):
cdef _BaseParser parser
+ _assertValidNode(self)
ns, name = _getNsTag(value)
parser = self._doc._parser
if parser is not None and parser._for_html:
@@ -863,6 +886,7 @@
keys(), values() and items() to access element attributes.
"""
def __get__(self):
+ _assertValidNode(self)
return _Attrib(self)
## cdef python.PyObject* ref
## if self._attrib is not None:
@@ -878,9 +902,11 @@
the value None, if there was no text.
"""
def __get__(self):
+ _assertValidNode(self)
return _collectText(self._c_node.children)
def __set__(self, value):
+ _assertValidNode(self)
if isinstance(value, QName):
value = python.PyUnicode_FromEncodedObject(
_resolveQNameText(self, value), 'UTF-8', 'strict')
@@ -896,9 +922,11 @@
there was no text.
"""
def __get__(self):
+ _assertValidNode(self)
return _collectText(self._c_node.next)
def __set__(self, value):
+ _assertValidNode(self)
_setTailText(self._c_node, value)
# using 'del el.tail' is the wrong thing to do
@@ -921,6 +949,7 @@
"""
def __get__(self):
cdef long line
+ _assertValidNode(self)
line = tree.xmlGetLineNo(self._c_node)
if line > 0:
return line
@@ -928,6 +957,7 @@
return None
def __set__(self, line):
+ _assertValidNode(self)
if line < 0:
self._c_node.line = 0
else:
@@ -945,6 +975,7 @@
cdef xmlNode* c_node
cdef xmlNs* c_ns
cdef dict nsmap = {}
+ _assertValidNode(self)
c_node = self._c_node
while c_node is not NULL and c_node.type == tree.XML_ELEMENT_NODE:
c_ns = c_node.nsDef
@@ -973,6 +1004,7 @@
"""
def __get__(self):
cdef char* c_base
+ _assertValidNode(self)
c_base = tree.xmlNodeGetBase(self._doc._c_doc, self._c_node)
if c_base is NULL:
if self._doc._c_doc.URL is NULL:
@@ -981,8 +1013,10 @@
base = _decodeFilename(c_base)
tree.xmlFree(c_base)
return base
+
def __set__(self, url):
cdef char* c_base
+ _assertValidNode(self)
if url is None:
c_base = NULL
else:
@@ -1004,6 +1038,7 @@
cdef Py_ssize_t c, i
cdef _node_to_node_function next_element
cdef list result
+ _assertValidNode(self)
if python.PySlice_Check(x):
# slicing
if _isFullSlice(x):
@@ -1036,6 +1071,7 @@
Returns the number of subelements.
"""
+ _assertValidNode(self)
return _countElements(self._c_node.children)
def __nonzero__(self):
@@ -1047,11 +1083,13 @@
FutureWarning
)
# emulate old behaviour
+ _assertValidNode(self)
return _hasChild(self._c_node)
def __contains__(self, element):
u"__contains__(self, element)"
cdef xmlNode* c_node
+ _assertValidNode(self)
if not isinstance(element, _Element):
return 0
c_node = (<_Element>element)._c_node
@@ -1076,6 +1114,8 @@
cdef Py_ssize_t c_start, c_stop
cdef xmlNode* c_child
cdef xmlNode* c_start_node
+ _assertValidNode(self)
+ _assertValidNode(child)
c_child = child._c_node
if c_child.parent is not self._c_node:
raise ValueError, u"Element is not a child of this node."
@@ -1155,6 +1195,7 @@
Gets an element attribute.
"""
+ _assertValidNode(self)
return _getAttributeValue(self, key, default)
def keys(self):
@@ -1163,6 +1204,7 @@
Gets a list of attribute names. The names are returned in an
arbitrary order (just like for an ordinary Python dictionary).
"""
+ _assertValidNode(self)
return _collectAttributes(self._c_node, 1)
def values(self):
@@ -1171,6 +1213,7 @@
Gets element attribute values as a sequence of strings. The
attributes are returned in an arbitrary order.
"""
+ _assertValidNode(self)
return _collectAttributes(self._c_node, 2)
def items(self):
@@ -1179,6 +1222,7 @@
Gets element attributes, as a sequence. The attributes are returned in
an arbitrary order.
"""
+ _assertValidNode(self)
return _collectAttributes(self._c_node, 3)
def getchildren(self):
@@ -1191,6 +1235,7 @@
ElementTree 1.3 and lxml 2.0. New code should use
``list(element)`` or simply iterate over elements.
"""
+ _assertValidNode(self)
return _collectChildren(self)
def getparent(self):
@@ -1199,6 +1244,7 @@
Returns the parent of this element or None for the root element.
"""
cdef xmlNode* c_node
+ #_assertValidNode(self) # not needed
c_node = _parentElement(self._c_node)
if c_node is NULL:
return None
@@ -1210,6 +1256,7 @@
Returns the following sibling of this element or None.
"""
cdef xmlNode* c_node
+ #_assertValidNode(self) # not needed
c_node = _nextElement(self._c_node)
if c_node is NULL:
return None
@@ -1221,6 +1268,7 @@
Returns the preceding sibling of this element or None.
"""
cdef xmlNode* c_node
+ #_assertValidNode(self) # not needed
c_node = _previousElement(self._c_node)
if c_node is NULL:
return None
@@ -1282,6 +1330,7 @@
This is the same as following element.getparent() up the tree until it
returns None (for the root element) and then build an ElementTree for
the last parent that was returned."""
+ _assertValidDoc(self._doc)
return _elementTreeFactory(self._doc, None)
def getiterator(self, tag=None):
@@ -1339,6 +1388,7 @@
Creates a new element associated with the same document.
"""
+ _assertValidDoc(self._doc)
return _makeElement(_tag, NULL, self._doc, None, None, None,
attrib, nsmap, _extra)
@@ -1408,7 +1458,7 @@
cdef extern from "etree_defs.h":
# macro call to 't->tp_new()' for fast instantiation
- cdef _Element NEW_ELEMENT "PY_NEW" (object t)
+ cdef object NEW_ELEMENT "PY_NEW" (object t)
cdef _Element _elementFactory(_Document doc, xmlNode* c_node):
cdef _Element result
@@ -1461,6 +1511,7 @@
property text:
def __get__(self):
+ _assertValidNode(self)
if self._c_node.content is NULL:
return ''
else:
@@ -1469,6 +1520,7 @@
def __set__(self, value):
cdef tree.xmlDict* c_dict
cdef char* c_text
+ _assertValidNode(self)
if value is None:
c_text = NULL
else:
@@ -1520,9 +1572,11 @@
property target:
# not in ElementTree
def __get__(self):
+ _assertValidNode(self)
return funicode(self._c_node.name)
def __set__(self, value):
+ _assertValidNode(self)
value = _utf8(value)
c_text = _cstr(value)
tree.xmlNodeSetName(self._c_node, c_text)
@@ -1542,9 +1596,11 @@
property name:
# not in ElementTree
def __get__(self):
+ _assertValidNode(self)
return funicode(self._c_node.name)
def __set__(self, value):
+ _assertValidNode(self)
value_utf = _utf8(value)
assert u'&' not in value and u';' not in value, \
u"Invalid entity name '%s'" % value
@@ -1554,6 +1610,7 @@
# FIXME: should this be None or '&[VALUE];' or the resolved
# entity value ?
def __get__(self):
+ _assertValidNode(self)
return u'&%s;' % funicode(self._c_node.name)
def __repr__(self):
@@ -1659,6 +1716,7 @@
Relocate the ElementTree to a new root node.
"""
+ _assertValidNode(root)
if root._c_node.type != tree.XML_ELEMENT_NODE:
raise TypeError, u"Only elements can be the root of an ElementTree"
self._context_node = root
@@ -1693,6 +1751,7 @@
python.PyErr_NoMemory()
return _elementTreeFactory(None, root)
elif self._doc is not None:
+ _assertValidDoc(self._doc)
c_doc = tree.xmlCopyDoc(self._doc._c_doc, 1)
if c_doc is NULL:
python.PyErr_NoMemory()
@@ -1754,6 +1813,7 @@
cdef bint write_declaration
cdef int is_standalone
self._assertHasRoot()
+ _assertValidNode(self._context_node)
if compression is None or compression < 0:
compression = 0
# C14N serialisation
@@ -1797,12 +1857,24 @@
Returns a structural, absolute XPath expression to find that element.
"""
cdef _Document doc
+ cdef _Element root
cdef xmlDoc* c_doc
cdef char* c_path
- doc = self._context_node._doc
+ _assertValidNode(element)
+ if self._context_node is not None:
+ root = self._context_node
+ doc = root._doc
+ elif self._doc is not None:
+ doc = self._doc
+ root = doc.getroot()
+ else:
+ raise ValueError, u"Element is not in this tree."
+ _assertValidDoc(doc)
+ _assertValidNode(root)
if element._doc is not doc:
raise ValueError, u"Element is not in this tree."
- c_doc = _fakeRootDoc(doc._c_doc, self._context_node._c_node)
+
+ c_doc = _fakeRootDoc(doc._c_doc, root._c_node)
c_path = tree.xmlGetNodePath(element._c_node)
_destroyFakeDoc(doc._c_doc, c_doc)
if c_path is NULL:
@@ -2020,7 +2092,6 @@
Note that XInclude does not support custom resolvers in Python space
due to restrictions of libxml2 <= 2.6.29.
"""
- cdef int result
self._assertHasRoot()
XInclude()(self._context_node)
@@ -2034,6 +2105,7 @@
The ``compression`` option enables GZip compression level 1-9.
"""
self._assertHasRoot()
+ _assertValidNode(self._context_node)
if compression is None or compression < 0:
compression = 0
_tofilelikeC14N(file, self._context_node, exclusive, with_comments,
@@ -2049,7 +2121,10 @@
if context_node is None and doc is not None:
context_node = doc.getroot()
if context_node is None:
+ _assertValidDoc(doc)
result._doc = doc
+ else:
+ _assertValidNode(context_node)
result._context_node = context_node
return result
@@ -2059,6 +2134,7 @@
"""
cdef _Element _element
def __cinit__(self, _Element element not None):
+ _assertValidNode(element)
self._element = element
# MANIPULATORS
@@ -2285,8 +2361,9 @@
u"""ElementChildIterator(self, node, tag=None, reversed=False)
Iterates over the children of an element.
"""
- def __init__(self, _Element node not None, tag=None, *, reversed=False):
+ def __cinit__(self, _Element node not None, tag=None, *, reversed=False):
cdef xmlNode* c_node
+ _assertValidNode(node)
self._initTagMatch(tag)
if reversed:
c_node = _findChildBackwards(node._c_node, 0)
@@ -2310,7 +2387,8 @@
You can pass the boolean keyword ``preceding`` to specify the direction.
"""
- def __init__(self, _Element node not None, tag=None, *, preceding=False):
+ def __cinit__(self, _Element node not None, tag=None, *, preceding=False):
+ _assertValidNode(node)
self._initTagMatch(tag)
if preceding:
self._next_element = _previousElement
@@ -2322,7 +2400,8 @@
u"""AncestorsIterator(self, node, tag=None)
Iterates over the ancestors of an element (from parent to parent).
"""
- def __init__(self, _Element node not None, tag=None):
+ def __cinit__(self, _Element node not None, tag=None):
+ _assertValidNode(node)
self._initTagMatch(tag)
self._next_element = _parentElement
self._storeNext(node)
@@ -2351,7 +2430,8 @@
# keep next node to return and the (s)top node
cdef _Element _next_node
cdef _Element _top_node
- def __init__(self, _Element node not None, tag=None, *, inclusive=True):
+ def __cinit__(self, _Element node not None, tag=None, *, inclusive=True):
+ _assertValidNode(node)
self._top_node = node
self._next_node = node
self._initTagMatch(tag)
@@ -2417,7 +2497,8 @@
"""
cdef object _nextEvent
cdef _Element _start_element
- def __init__(self, _Element element not None, tag=None, *, with_tail=True):
+ def __cinit__(self, _Element element not None, tag=None, *, with_tail=True):
+ _assertValidNode(element)
if with_tail:
events = (u"start", u"end")
else:
@@ -2683,7 +2764,7 @@
Checks if an object appears to be a valid element object.
"""
- return isinstance(element, _Element)
+ return isinstance(element, _Element) and (<_Element>element)._c_node is not NULL
def dump(_Element elem not None, *, pretty_print=True, with_tail=True):
u"""dump(elem, pretty_print=True, with_tail=True)
@@ -2691,6 +2772,7 @@
Writes an element tree or element structure to sys.stdout. This function
should be used for debugging only.
"""
+ _assertValidNode(elem)
_dumpToFile(sys.stdout, elem._c_node, pretty_print, with_tail)
def tostring(element_or_tree, *, encoding=None, method=u"xml",
@@ -2900,8 +2982,7 @@
cdef class _Validator:
u"Base class for XML validators."
cdef _ErrorLog _error_log
- def __init__(self):
- u"__init__(self)"
+ def __cinit__(self):
self._error_log = _ErrorLog()
def validate(self, etree):
@@ -2943,6 +3024,7 @@
property error_log:
u"The log of validation errors and warnings."
def __get__(self):
+ assert self._error_log is not None, "XPath evaluator not initialised"
return self._error_log.copy()
include "dtd.pxi" # DTD
Modified: lxml/trunk/src/lxml/parser.pxi
==============================================================================
--- lxml/trunk/src/lxml/parser.pxi (original)
+++ lxml/trunk/src/lxml/parser.pxi Tue Apr 27 21:41:38 2010
@@ -20,18 +20,18 @@
# Python >= 2.5 uses new style class exceptions
super(_ParseError, self).__init__(message)
else:
- _XMLSyntaxError.__init__(self, message)
+ _LxmlSyntaxError.__init__(self, message)
self.position = (line, column)
self.code = code
+cdef object _LxmlSyntaxError = LxmlSyntaxError
+cdef object _ParseError = ParseError
+
class XMLSyntaxError(ParseError):
u"""Syntax error while parsing an XML document.
"""
pass
-cdef object _XMLSyntaxError = XMLSyntaxError
-cdef object _ParseError = ParseError
-
class ParserError(LxmlError):
u"""Internal lxml parser error.
"""
@@ -51,7 +51,8 @@
cdef _BaseParser _default_parser
cdef list _implied_parser_contexts
- def __init__(self):
+ def __cinit__(self):
+ self._c_dict = NULL
self._implied_parser_contexts = []
def __dealloc__(self):
@@ -65,7 +66,7 @@
cdef python.PyObject* result
thread_dict = python.PyThreadState_GetDict()
if thread_dict is not NULL:
- (