mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-08-04 08:59:19 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 11

Accept commas in unquoted attribute values.

Browse source 
This closes SF patch #669683.
This commit is contained in:
Fred Drake 2003-03-14 16:21:57 +00:00
parent 080cb3268f
commit 0834d77bc4
4 changed files with 10 additions and 2 deletions
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

2
Lib/sgmllib.py
View file

@ -34,7 +34,7 @@ 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./,:;+*%?!&$\(\)_#=~\'"]*))?')
class SGMLParseError(RuntimeError): class SGMLParseError(RuntimeError):

4
Lib/test/test_htmlparser.py
View file

@ -197,6 +197,10 @@ DOCTYPE html [
self._run_check("""<a b='' c="">""", [ self._run_check("""<a b='' c="">""", [
("starttag", "a", [("b", ""), ("c", "")]), ("starttag", "a", [("b", ""), ("c", "")]),
]) ])
# Regression test for SF patch #669683.
self._run_check("<e a=rgb(1,2,3)>", [
("starttag", "e", [("a", "rgb(1,2,3)")]),
])
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;'>""", [

4
Lib/test/test_sgmllib.py
View file

@ -200,6 +200,10 @@ DOCTYPE html PUBLIC '-//W3C//DTD HTML 4.01//EN'
self.check_events("""<a b='' c="">""", [ self.check_events("""<a b='' c="">""", [
("starttag", "a", [("b", ""), ("c", "")]), ("starttag", "a", [("b", ""), ("c", "")]),
]) ])
# Regression test for SF patch #669683.
self.check_events("<e a=rgb(1,2,3)>", [
("starttag", "e", [("a", "rgb(1,2,3)")]),
])
def test_attr_funky_names(self): def test_attr_funky_names(self):
self.check_events("""<a a.b='v' c:d=v e-f=v>""", [ self.check_events("""<a a.b='v' c:d=v e-f=v>""", [