diff options
| author | R David Murray <rdmurray@bitdance.com> | 2016-09-08 17:59:53 (GMT) |
|---|---|---|
| committer | R David Murray <rdmurray@bitdance.com> | 2016-09-08 17:59:53 (GMT) |
| commit | 44b548dda872c0d4f30afd6b44fd74b053a55ad8 (patch) | |
| tree | b3c1ff8485bc279000f9db95491ebc69a4385876 /Lib/html | |
| parent | 513d7478a136e7646075592da2593476299cc8be (diff) | |
| download | cpython-44b548dda872c0d4f30afd6b44fd74b053a55ad8.zip cpython-44b548dda872c0d4f30afd6b44fd74b053a55ad8.tar.gz cpython-44b548dda872c0d4f30afd6b44fd74b053a55ad8.tar.bz2 | |
#27364: fix "incorrect" uses of escape character in the stdlib.
And most of the tools.
Patch by Emanual Barry, reviewed by me, Serhiy Storchaka, and
Martin Panter.
Diffstat (limited to 'Lib/html')
| -rw-r--r-- | Lib/html/parser.py | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/Lib/html/parser.py b/Lib/html/parser.py index b781c63..ef869bc 100644 --- a/Lib/html/parser.py +++ b/Lib/html/parser.py @@ -34,7 +34,7 @@ commentclose = re.compile(r'--\s*>') # explode, so don't do it. # 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]*)(?:\s|/(?!>))*') +tagfind_tolerant = re.compile(r'([a-zA-Z][^\t\n\r\f />\x00]*)(?:\s|/(?!>))*') attrfind_tolerant = re.compile( r'((?<=[\'"\s/])[^\s/>][^\s/=>]*)(\s*=+\s*' r'(\'[^\']*\'|"[^"]*"|(?![\'"])[^>\s]*))?(?:\s|/(?!>))*') @@ -56,7 +56,7 @@ locatestarttagend_tolerant = re.compile(r""" endendtag = re.compile('>') # the HTML 5 spec, section 8.1.2.2, doesn't allow spaces between # </ and the tag name, so maybe this should be fixed -endtagfind = re.compile('</\s*([a-zA-Z][-.a-zA-Z0-9:_]*)\s*>') +endtagfind = re.compile(r'</\s*([a-zA-Z][-.a-zA-Z0-9:_]*)\s*>') |