traverseda
/
cpython
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

[Bug #921657] Allow '@' in unquoted HTML attributes. Not strictly legal according to the HTML REC, but HTMLParser is already a pretty loose parser. Reported by Bernd Zimmermann.

This commit is contained in:
Andrew M. Kuchling 2004-06-05 15:31:45 +00:00
parent 9021c95595
commit b7d8ce0275
2 changed files with 5 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
Lib/HTMLParser.py
View File

@ -26,7 +26,7 @@ commentclose = re.compile(r'--\s*>')
tagfind = re.compile('[a-zA-Z][-.a-zA-Z0-9:_]*') tagfind = re.compile('[a-zA-Z][-.a-zA-Z0-9:_]*')
attrfind = re.compile( attrfind = re.compile(
r'\s*([a-zA-Z_][-.:a-zA-Z_0-9]*)(\s*=\s*' r'\s*([a-zA-Z_][-.:a-zA-Z_0-9]*)(\s*=\s*'
r'(\'[^\']*\'|"[^"]*"|[-a-zA-Z0-9./,:;+*%?!&$\(\)_#=~]*))?') r'(\'[^\']*\'|"[^"]*"|[-a-zA-Z0-9./,:;+*%?!&$\(\)_#=~@]*))?')
locatestarttagend = re.compile(r""" locatestarttagend = re.compile(r"""
<[a-zA-Z][-.a-zA-Z0-9:_]* # tag name <[a-zA-Z][-.a-zA-Z0-9:_]* # tag name

4
Lib/test/test_htmlparser.py
View File

@ -204,6 +204,10 @@ DOCTYPE html [
self._run_check("<e a=rgb(1,2,3)>", [ self._run_check("<e a=rgb(1,2,3)>", [
("starttag", "e", [("a", "rgb(1,2,3)")]), ("starttag", "e", [("a", "rgb(1,2,3)")]),
]) ])
# Regression test for SF bug #921657.
self._run_check("<a href=mailto:xyz@example.com>", [
("starttag", "a", [("href", "mailto:xyz@example.com")]),
])
def test_attr_entity_replacement(self): def test_attr_entity_replacement(self):
self._run_check("""<a b='&amp;&gt;&lt;&quot;&apos;'>""", [ self._run_check("""<a b='&amp;&gt;&lt;&quot;&apos;'>""", [