Skip to content
Projects
Groups
Snippets
Help
Loading...
Help
Support
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
C
cpython
Project overview
Project overview
Details
Activity
Releases
Repository
Repository
Files
Commits
Branches
Tags
Contributors
Graph
Compare
Issues
0
Issues
0
List
Boards
Labels
Milestones
Merge Requests
0
Merge Requests
0
Analytics
Analytics
Repository
Value Stream
Wiki
Wiki
Members
Members
Collapse sidebar
Close sidebar
Activity
Graph
Create a new issue
Commits
Issue Boards
Open sidebar
Kirill Smelkov
cpython
Commits
c45868ec
Commit
c45868ec
authored
Apr 18, 2012
by
Ezio Melotti
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
#14538: HTMLParser can now parse correctly start tags that contain a bare /.
parent
a72aa843
Changes
3
Show whitespace changes
Inline
Side-by-side
Showing
3 changed files
with
16 additions
and
3 deletions
+16
-3
Lib/HTMLParser.py
Lib/HTMLParser.py
+3
-3
Lib/test/test_htmlparser.py
Lib/test/test_htmlparser.py
+10
-0
Misc/NEWS
Misc/NEWS
+3
-0
No files found.
Lib/HTMLParser.py
View file @
c45868ec
...
...
@@ -22,13 +22,13 @@ charref = re.compile('&#(?:[0-9]+|[xX][0-9a-fA-F]+)[^0-9a-fA-F]')
starttagopen
=
re
.
compile
(
'<[a-zA-Z]'
)
piclose
=
re
.
compile
(
'>'
)
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
:
_
]
*
)(
?
:
\
s
|/
(
?!
>
))
*
')
# see http://www.w3.org/TR/html5/tokenization.html#tag-open-state
# and http://www.w3.org/TR/html5/tokenization.html#tag-name-state
tagfind_tolerant = re.compile('
[
a
-
zA
-
Z
][
^
\
t
\
n
\
r
\
f
/>
\
x00
]
*
')
attrfind = re.compile(
r'
[
\
s
/
]
*
((
?
<=
[
\
'"
\
s/])[^
\
s/>][^
\
s/=>]*)(
\
s*=+
\
s*
'
r'
((
?
<=
[
\
'"
\
s/])[^
\
s/>][^
\
s/=>]*)(
\
s*=+
\
s*
'
r'
(
\
'[^
\
'
]*
\
'
|"[^"]*"|(?![
\
'
"])[^>
\
s]*))?(?:
\
s|/(?!>))*'
)
locatestarttagend
=
re
.
compile
(
r"""
...
...
@@ -289,7 +289,7 @@ class HTMLParser(markupbase.ParserBase):
match
=
tagfind
.
match
(
rawdata
,
i
+
1
)
assert
match
,
'unexpected call to parse_starttag()'
k
=
match
.
end
()
self
.
lasttag
=
tag
=
rawdata
[
i
+
1
:
k
]
.
lower
()
self
.
lasttag
=
tag
=
match
.
group
(
1
)
.
lower
()
while
k
<
endpos
:
m
=
attrfind
.
match
(
rawdata
,
k
)
...
...
Lib/test/test_htmlparser.py
View file @
c45868ec
...
...
@@ -260,6 +260,16 @@ text
(
'starttag'
,
'a'
,
[(
'foo'
,
None
),
(
'='
,
None
),
(
'bar'
,
None
)])
]
self
.
_run_check
(
html
,
expected
)
#see issue #14538
html
=
(
'<meta><meta / ><meta // ><meta / / >'
'<meta/><meta /><meta //><meta//>'
)
expected
=
[
(
'starttag'
,
'meta'
,
[]),
(
'starttag'
,
'meta'
,
[]),
(
'starttag'
,
'meta'
,
[]),
(
'starttag'
,
'meta'
,
[]),
(
'startendtag'
,
'meta'
,
[]),
(
'startendtag'
,
'meta'
,
[]),
(
'startendtag'
,
'meta'
,
[]),
(
'startendtag'
,
'meta'
,
[]),
]
self
.
_run_check
(
html
,
expected
)
def
test_declaration_junk_chars
(
self
):
self
.
_run_check
(
"<!DOCTYPE foo $ >"
,
[(
'decl'
,
'DOCTYPE foo $ '
)])
...
...
Misc/NEWS
View file @
c45868ec
...
...
@@ -50,6 +50,9 @@ Core and Builtins
Library
-------
-
Issue
#
14538
:
HTMLParser
can
now
parse
correctly
start
tags
that
contain
a
bare
'/'
.
-
Issue
#
14452
:
SysLogHandler
no
longer
inserts
a
UTF
-
8
BOM
into
the
message
.
-
Issue
#
13496
:
Fix
potential
overflow
in
bisect
.
bisect
algorithm
when
applied
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment