diff options
Diffstat (limited to 'Lib')
| -rw-r--r-- | Lib/HTMLParser.py | 7 | ||||
| -rw-r--r-- | Lib/test/test_htmlparser.py | 21 |
2 files changed, 25 insertions, 3 deletions
diff --git a/Lib/HTMLParser.py b/Lib/HTMLParser.py index cd353f8..1c6989e 100644 --- a/Lib/HTMLParser.py +++ b/Lib/HTMLParser.py @@ -14,7 +14,6 @@ import re # Regular expressions used for parsing interesting_normal = re.compile('[&<]') -interesting_cdata = re.compile(r'<(/|\Z)') incomplete = re.compile('&[a-zA-Z#]') entityref = re.compile('&([a-zA-Z][-.a-zA-Z0-9]*)[^a-zA-Z0-9]') @@ -125,8 +124,8 @@ class HTMLParser(markupbase.ParserBase): return self.__starttag_text def set_cdata_mode(self, elem): - self.interesting = interesting_cdata self.cdata_elem = elem.lower() + self.interesting = re.compile(r'</\s*%s\s*>' % self.cdata_elem, re.I) def clear_cdata_mode(self): self.interesting = interesting_normal @@ -144,6 +143,8 @@ class HTMLParser(markupbase.ParserBase): if match: j = match.start() else: + if self.cdata_elem: + break j = n if i < j: self.handle_data(rawdata[i:j]) i = self.updatepos(i, j) @@ -212,7 +213,7 @@ class HTMLParser(markupbase.ParserBase): else: assert 0, "interesting.search() lied" # end while - if end and i < n: + if end and i < n and not self.cdata_elem: self.handle_data(rawdata[i:n]) i = self.updatepos(i, n) self.rawdata = rawdata[i:] diff --git a/Lib/test/test_htmlparser.py b/Lib/test/test_htmlparser.py index b84e7dc..5dfe466 100644 --- a/Lib/test/test_htmlparser.py +++ b/Lib/test/test_htmlparser.py @@ -286,6 +286,27 @@ DOCTYPE html [ ("data", content), ("endtag", element_lower)]) + def test_cdata_with_closing_tags(self): + # see issue #13358 + # make sure that HTMLParser calls handle_data only once for each CDATA. + # The normal event collector normalizes the events in get_events, + # so we override it to return the original list of events. + class Collector(EventCollector): + def get_events(self): + return self.events + + content = """<!-- not a comment --> ¬-an-entity-ref; + <a href="" /> </p><p> & <span></span></style> + '</script' + '>' </html> </head> </scripter>!""" + for element in [' script', 'script ', ' script ', + '\nscript', 'script\n', '\nscript\n']: + s = u'<script>{content}</{element}>'.format(element=element, + content=content) + self._run_check(s, [("starttag", "script", []), + ("data", content), + ("endtag", "script")], + collector=Collector) + def test_malformatted_charref(self): self._run_check("<p>&#bad;</p>", [ ("starttag", "p", []), |