Patch #912410: Replace HTML entity references for attribute values
in HTMLParser.
diff --git a/Lib/HTMLParser.py b/Lib/HTMLParser.py
index 8380466..2cbc2ec 100644
--- a/Lib/HTMLParser.py
+++ b/Lib/HTMLParser.py
@@ -358,12 +358,30 @@
self.error("unknown declaration: %r" % (data,))
# Internal -- helper to remove special character quoting
+ entitydefs = None
def unescape(self, s):
if '&' not in s:
return s
- s = s.replace("<", "<")
- s = s.replace(">", ">")
- s = s.replace("'", "'")
- s = s.replace(""", '"')
- s = s.replace("&", "&") # Must be last
- return s
+ def replaceEntities(s):
+ s = s.groups()[0]
+ if s[0] == "#":
+ s = s[1:]
+ if s[0] in ['x','X']:
+ c = int(s[1:], 16)
+ else:
+ c = int(s)
+ return unichr(c)
+ else:
+ # Cannot use name2codepoint directly, because HTMLParser supports apos,
+ # which is not part of HTML 4
+ import htmlentitydefs
+ if HTMLParser.entitydefs is None:
+ entitydefs = HTMLParser.entitydefs = {'apos':u"'"}
+ for k, v in htmlentitydefs.name2codepoint.iteritems():
+ entitydefs[k] = unichr(v)
+ try:
+ return self.entitydefs[s]
+ except KeyError:
+ return '&'+s+';'
+
+ return re.sub(r"&(#?[xX]?(?:[0-9a-fA-F]+|\w{1,8}));", replaceEntities, s)
diff --git a/Lib/test/test_htmlparser.py b/Lib/test/test_htmlparser.py
index 54b90cd..229bbed 100755
--- a/Lib/test/test_htmlparser.py
+++ b/Lib/test/test_htmlparser.py
@@ -309,6 +309,11 @@
("endtag", "script"),
])
+ def test_entityrefs_in_attributes(self):
+ self._run_check("<html foo='€&aa&unsupported;'>", [
+ ("starttag", "html", [("foo", u"\u20AC&aa&unsupported;")])
+ ])
+
def test_main():
test_support.run_unittest(HTMLParserTestCase)