diff --git a/Lib/html/parser.py b/Lib/html/parser.py index 94f4aaecfc61b3..255f07a40ae480 100644 --- a/Lib/html/parser.py +++ b/Lib/html/parser.py @@ -27,7 +27,8 @@ starttagopen = re.compile('<[a-zA-Z]') endtagopen = re.compile('') -commentclose = re.compile(r'--\s*>') +commentclose = re.compile(r'--!?>') +commentabruptclose = re.compile(r'-?>') # Note: # 1) if you change tagfind/attrfind remember to update locatestarttagend too; # 2) if you change tagfind/attrfind and/or locatestarttagend the parser will @@ -290,6 +291,21 @@ def parse_html_declaration(self, i): else: return self.parse_bogus_comment(i) + # Internal -- parse comment, return length or -1 if not terminated + # see https://html.spec.whatwg.org/multipage/parsing.html#comment-start-state + def parse_comment(self, i, report=True): + rawdata = self.rawdata + assert rawdata.startswith('" '' '' + '' '' + # abrupt-closing-of-empty-comment + '' + '' '' '' - '') + '' + '' + '' + '' + '' + '' + '' + # nested-comment + ' -->' + '' + '' + ) expected = [('comment', " I'm a valid comment "), ('comment', 'me too!'), ('comment', '--'), + ('comment', '-'), + ('comment', ''), + ('comment', ''), ('comment', ''), ('comment', '--I have many hyphens--'), ('comment', ' I have a > in the middle '), - ('comment', ' and I have -- in the middle! ')] + ('comment', ' and I have -- in the middle! '), + ('comment', 'incorrectly-closed-comment'), + ('comment', ''), + ('comment', '--!'), + ('comment', '-- >'), + ('comment', '-!>'), + ('comment', '!>'), + ('comment', ' '), + ('comment', '`` now ends the comment. ``-- >`` no longer ends the +comment. Support abnormally ended empty comments ``<-->`` and ``<--->``. pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy