[Lxml-checkins] r44207 - in lxml/branch/lxml-1.3: . src/lxml src/lxml/tests
scoder at codespeak.net
scoder at codespeak.net
Tue Jun 12 22:18:08 CEST 2007
Author: scoder
Date: Tue Jun 12 22:18:06 2007
New Revision: 44207
Modified:
lxml/branch/lxml-1.3/CHANGES.txt
lxml/branch/lxml-1.3/src/lxml/apihelpers.pxi
lxml/branch/lxml-1.3/src/lxml/etree.pyx
lxml/branch/lxml-1.3/src/lxml/tests/test_elementtree.py
Log:
support Comment and ProcessingInstruction elements in el.getiterator()
Modified: lxml/branch/lxml-1.3/CHANGES.txt
==============================================================================
--- lxml/branch/lxml-1.3/CHANGES.txt (original)
+++ lxml/branch/lxml-1.3/CHANGES.txt Tue Jun 12 22:18:06 2007
@@ -25,6 +25,9 @@
* Replacing the children slice of an Element would cut off the tails of the
original children
+* ``Element.getiterator(tag)`` did not accept ``Comment`` and
+ ``ProcessingInstruction`` as tags
+
* API functions now check incoming strings for XML conformity. Zero bytes or
low ASCII characters are no longer accepted.
Modified: lxml/branch/lxml-1.3/src/lxml/apihelpers.pxi
==============================================================================
--- lxml/branch/lxml-1.3/src/lxml/apihelpers.pxi (original)
+++ lxml/branch/lxml-1.3/src/lxml/apihelpers.pxi Tue Jun 12 22:18:06 2007
@@ -436,6 +436,9 @@
* its name string equals the c_name string
"""
cdef char* c_node_href
+ if c_node.type != tree.XML_ELEMENT_NODE:
+ # not an element, only succeed if we match everything
+ return c_name is NULL and c_href is NULL
if c_name is NULL:
if c_href is NULL:
# always match
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 Jun 12 22:18:06 2007
@@ -1596,17 +1596,22 @@
cdef public class _ElementTagMatcher [ object LxmlElementTagMatcher,
type LxmlElementTagMatcherType ]:
cdef object _pystrings
+ cdef int _node_type
cdef char* _href
cdef char* _name
cdef _initTagMatch(self, tag):
+ self._href = NULL
+ self._name = NULL
if tag is None:
- self._href = NULL
- self._name = NULL
+ self._node_type = 0
+ elif tag is Comment:
+ self._node_type = tree.XML_COMMENT_NODE
+ elif tag is ProcessingInstruction:
+ self._node_type = tree.XML_PI_NODE
else:
+ self._node_type = tree.XML_ELEMENT_NODE
self._pystrings = _getNsTag(tag)
- if self._pystrings[0] is None:
- self._href = NULL
- else:
+ if self._pystrings[0] is not None:
self._href = _cstr(self._pystrings[0])
self._name = _cstr(self._pystrings[1])
if self._name[0] == c'*' and self._name[1] == c'\0':
@@ -1624,7 +1629,9 @@
cdef xmlNode* c_node
c_node = self._next_element(node._c_node)
while c_node is not NULL and \
- not _tagMatches(c_node, self._href, self._name):
+ self._node_type != 0 and \
+ (self._node_type != c_node.type or
+ not _tagMatches(c_node, self._href, self._name)):
c_node = self._next_element(c_node)
if c_node is NULL:
self._node = None
@@ -1655,7 +1662,9 @@
self._next_element = _nextElement
if tag is not None:
while c_node is not NULL and \
- not _tagMatches(c_node, self._href, self._name):
+ self._node_type != 0 and \
+ (self._node_type != c_node.type or
+ not _tagMatches(c_node, self._href, self._name)):
c_node = self._next_element(c_node)
if c_node is not NULL:
# store Python ref:
@@ -1702,9 +1711,11 @@
self._top_node = node
self._next_node = node
self._initTagMatch(tag)
- if tag is not None and \
- not _tagMatches(node._c_node, self._href, self._name) or \
- not inclusive:
+ if not inclusive or \
+ tag is not None and \
+ self._node_type != 0 and \
+ (self._node_type != node._c_node.type or
+ not _tagMatches(node._c_node, self._href, self._name)):
# this cannot raise StopIteration, self._next_node != None
self.next()
@@ -1727,7 +1738,8 @@
cdef xmlNode* _nextNodeAnyTag(self, xmlNode* c_node):
tree.BEGIN_FOR_EACH_ELEMENT_FROM(self._top_node._c_node, c_node, 0)
- return c_node
+ if self._node_type == 0 or self._node_type == c_node.type:
+ return c_node
tree.END_FOR_EACH_ELEMENT_FROM(c_node)
return NULL
Modified: lxml/branch/lxml-1.3/src/lxml/tests/test_elementtree.py
==============================================================================
--- lxml/branch/lxml-1.3/src/lxml/tests/test_elementtree.py (original)
+++ lxml/branch/lxml-1.3/src/lxml/tests/test_elementtree.py Tue Jun 12 22:18:06 2007
@@ -1429,6 +1429,56 @@
[a2],
list(c.getiterator('a')))
+ def test_getiterator_filter_comment(self):
+ Element = self.etree.Element
+ Comment = self.etree.Comment
+ SubElement = self.etree.SubElement
+
+ a = Element('a')
+ b = SubElement(a, 'b')
+ comment_b = Comment("TEST-b")
+ b.append(comment_b)
+
+ self.assertEquals(
+ [comment_b],
+ list(a.getiterator(Comment)))
+
+ comment_a = Comment("TEST-a")
+ a.append(comment_a)
+
+ self.assertEquals(
+ [comment_b, comment_a],
+ list(a.getiterator(Comment)))
+
+ self.assertEquals(
+ [comment_b],
+ list(b.getiterator(Comment)))
+
+ def test_getiterator_filter_pi(self):
+ Element = self.etree.Element
+ PI = self.etree.ProcessingInstruction
+ SubElement = self.etree.SubElement
+
+ a = Element('a')
+ b = SubElement(a, 'b')
+ pi_b = PI("TEST-b")
+ b.append(pi_b)
+
+ self.assertEquals(
+ [pi_b],
+ list(a.getiterator(PI)))
+
+ pi_a = PI("TEST-a")
+ a.append(pi_a)
+
+ self.assertEquals(
+ [pi_b, pi_a],
+ list(a.getiterator(PI)))
+
+ self.assertEquals(
+ [pi_b],
+ list(b.getiterator(PI)))
+
def test_getiterator_with_text(self):
Element = self.etree.Element
SubElement = self.etree.SubElement
More information about the lxml-checkins
mailing list