diff -r ca236138f0ce Lib/HTMLParser.py
--- a/Lib/HTMLParser.py Tue Jul 26 13:52:14 2011 -0700
+++ b/Lib/HTMLParser.py Tue Jul 26 20:21:25 2011 -0700
@@ -96,6 +96,7 @@
self.rawdata = ''
self.lasttag = '???'
self.interesting = interesting_normal
+ self.cdata_tag = None
markupbase.ParserBase.reset(self)
def feed(self, data):
@@ -120,11 +121,13 @@
"""Return full source of start tag: '<...>'."""
return self.__starttag_text
- def set_cdata_mode(self):
+ def set_cdata_mode(self, tag):
self.interesting = interesting_cdata
+ self.cdata_tag = tag.lower()
def clear_cdata_mode(self):
self.interesting = interesting_normal
+ self.cdata_tag = None
# Internal -- handle data as far as reasonable. May leave state
# and data to be processed by a subsequent call. If 'end' is
@@ -270,7 +273,7 @@
else:
self.handle_starttag(tag, attrs)
if tag in self.CDATA_CONTENT_ELEMENTS:
- self.set_cdata_mode()
+ self.set_cdata_mode(tag)
return endpos
# Internal -- check to see if we have a complete starttag; return end
@@ -314,10 +317,20 @@
j = match.end()
match = endtagfind.match(rawdata, i) #
if not match:
+ if self.cdata_tag is not None:
+ self.handle_data(rawdata[i:j])
+ return j
self.error("bad end tag: %r" % (rawdata[i:j],))
- tag = match.group(1)
+ tag = match.group(1).strip()
+
+ if self.cdata_tag is not None:
+ if tag.lower() != self.cdata_tag:
+ self.handle_data(rawdata[i:j])
+ return j
+
self.handle_endtag(tag.lower())
self.clear_cdata_mode()
+
return j
# Overridable -- finish processing of start+end tag:
diff -r ca236138f0ce Lib/test/test_htmlparser.py
--- a/Lib/test/test_htmlparser.py Tue Jul 26 13:52:14 2011 -0700
+++ b/Lib/test/test_htmlparser.py Tue Jul 26 20:21:25 2011 -0700
@@ -324,6 +324,18 @@
("data", " "),
("endtag", "script"),
])
+ s = """"""
+ self._run_check(s, [
+ ("starttag", "script", []),
+ ("data", '
'),
+ ("endtag", "script"),
+ ])
+ s = """"""
+ self._run_check(s, [
+ ("starttag", "script", []),
+ ("data", ' foo = ""; '),
+ ("endtag", "script"),
+ ])
def test_entityrefs_in_attributes(self):
self._run_check("", [