#670664: Fix HTMLParser to correctly handle the content of ``<script>...</script>`` and ``<style>...</style>``.
diff --git a/Lib/HTMLParser.py b/Lib/HTMLParser.py
index 884d2a5..94ebc7f 100644
--- a/Lib/HTMLParser.py
+++ b/Lib/HTMLParser.py
@@ -43,6 +43,8 @@
\s* # trailing whitespace
""", re.VERBOSE)
endendtag = re.compile('>')
+# the HTML 5 spec, section 8.1.2.2, doesn't allow spaces between
+# </ and the tag name, so maybe this should be fixed
endtagfind = re.compile('</\s*([a-zA-Z][-.a-zA-Z0-9:_]*)\s*>')
@@ -96,6 +98,7 @@
self.rawdata = ''
self.lasttag = '???'
self.interesting = interesting_normal
+ self.cdata_elem = None
markupbase.ParserBase.reset(self)
def feed(self, data):
@@ -120,11 +123,13 @@
"""Return full source of start tag: '<...>'."""
return self.__starttag_text
- def set_cdata_mode(self):
+ def set_cdata_mode(self, elem):
self.interesting = interesting_cdata
+ self.cdata_elem = elem.lower()
def clear_cdata_mode(self):
self.interesting = interesting_normal
+ self.cdata_elem = 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 +275,7 @@
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
@@ -314,9 +319,18 @@
j = match.end()
match = endtagfind.match(rawdata, i) # </ + tag + >
if not match:
+ if self.cdata_elem is not None:
+ self.handle_data(rawdata[i:j])
+ return j
self.error("bad end tag: %r" % (rawdata[i:j],))
- tag = match.group(1)
- self.handle_endtag(tag.lower())
+
+ elem = match.group(1).lower() # script or style
+ if self.cdata_elem is not None:
+ if elem != self.cdata_elem:
+ self.handle_data(rawdata[i:j])
+ return j
+
+ self.handle_endtag(elem)
self.clear_cdata_mode()
return j