summaryrefslogtreecommitdiffstats
path: root/Lib/html/parser.py
diff options
context:
space:
mode:
authorEzio Melotti <ezio.melotti@gmail.com>2012-02-21 07:25:00 (GMT)
committerEzio Melotti <ezio.melotti@gmail.com>2012-02-21 07:25:00 (GMT)
commit29877e8e04755c919b42ee012495f2e9671f3251 (patch)
tree05d086dff8880990b213a0f4af769c53895c998e /Lib/html/parser.py
parent178e5ea305848015d514f4038118777374e44c87 (diff)
downloadcpython-29877e8e04755c919b42ee012495f2e9671f3251.zip
cpython-29877e8e04755c919b42ee012495f2e9671f3251.tar.gz
cpython-29877e8e04755c919b42ee012495f2e9671f3251.tar.bz2
HTMLParser is now able to handle slashes in the start tag.
Diffstat (limited to 'Lib/html/parser.py')
-rw-r--r--Lib/html/parser.py18
1 files changed, 11 insertions, 7 deletions
diff --git a/Lib/html/parser.py b/Lib/html/parser.py
index aa31fbc..2bfd187 100644
--- a/Lib/html/parser.py
+++ b/Lib/html/parser.py
@@ -26,14 +26,18 @@ tagfind = re.compile('[a-zA-Z][-.a-zA-Z0-9:_]*')
# 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]*')
-# Note, the strict one of this pair isn't really strict, but we can't
-# make it correctly strict without breaking backward compatibility.
+# Note:
+# 1) the strict attrfind isn't really strict, but we can't make it
+# correctly strict without breaking backward compatibility;
+# 2) if you change attrfind remember to update locatestarttagend too;
+# 3) if you change attrfind and/or locatestarttagend the parser will
+# explode, so don't do it.
attrfind = re.compile(
r'\s*([a-zA-Z_][-.:a-zA-Z_0-9]*)(\s*=\s*'
r'(\'[^\']*\'|"[^"]*"|[^\s"\'=<>`]*))?')
attrfind_tolerant = re.compile(
- r'\s*((?<=[\'"\s])[^\s/>][^\s/=>]*)(\s*=+\s*'
- r'(\'[^\']*\'|"[^"]*"|(?![\'"])[^>\s]*))?')
+ r'[\s/]*((?<=[\'"\s/])[^\s/>][^\s/=>]*)(\s*=+\s*'
+ r'(\'[^\']*\'|"[^"]*"|(?![\'"])[^>\s]*))?(?:\s|/(?!>))*')
locatestarttagend = re.compile(r"""
<[a-zA-Z][-.a-zA-Z0-9:_]* # tag name
(?:\s+ # whitespace before attribute name
@@ -50,15 +54,15 @@ locatestarttagend = re.compile(r"""
""", re.VERBOSE)
locatestarttagend_tolerant = re.compile(r"""
<[a-zA-Z][-.a-zA-Z0-9:_]* # tag name
- (?:\s* # optional whitespace before attribute name
- (?:(?<=['"\s])[^\s/>][^\s/=>]* # attribute name
+ (?:[\s/]* # optional whitespace before attribute name
+ (?:(?<=['"\s/])[^\s/>][^\s/=>]* # attribute name
(?:\s*=+\s* # value indicator
(?:'[^']*' # LITA-enclosed value
|"[^"]*" # LIT-enclosed value
|(?!['"])[^>\s]* # bare value
)
(?:\s*,)* # possibly followed by a comma
- )?\s*
+ )?(?:\s|/(?!>))*
)*
)?
\s* # trailing whitespace