summaryrefslogtreecommitdiffstats
path: root/Lib/html
diff options
context:
space:
mode:
authorEzio Melotti <ezio.melotti@gmail.com>2012-06-24 20:02:56 (GMT)
committerEzio Melotti <ezio.melotti@gmail.com>2012-06-24 20:02:56 (GMT)
commit46495182d0fc58b519d10315f1bf392f08f33a2e (patch)
tree0503e0a7032d33e98954331d3a2d5c6e19607392 /Lib/html
parenta504a7a7d1fd6056e067027354d31595aa4b8958 (diff)
downloadcpython-46495182d0fc58b519d10315f1bf392f08f33a2e.zip
cpython-46495182d0fc58b519d10315f1bf392f08f33a2e.tar.gz
cpython-46495182d0fc58b519d10315f1bf392f08f33a2e.tar.bz2
#15156: HTMLParser now uses the new "html.entities.html5" dictionary.
Diffstat (limited to 'Lib/html')
-rw-r--r--Lib/html/parser.py32
1 files changed, 15 insertions, 17 deletions
diff --git a/Lib/html/parser.py b/Lib/html/parser.py
index 494cf24..f8ac828 100644
--- a/Lib/html/parser.py
+++ b/Lib/html/parser.py
@@ -500,7 +500,6 @@ class HTMLParser(_markupbase.ParserBase):
self.error("unknown declaration: %r" % (data,))
# Internal -- helper to remove special character quoting
- entitydefs = None
def unescape(self, s):
if '&' not in s:
return s
@@ -510,24 +509,23 @@ class HTMLParser(_markupbase.ParserBase):
if s[0] == "#":
s = s[1:]
if s[0] in ['x','X']:
- c = int(s[1:], 16)
+ c = int(s[1:].rstrip(';'), 16)
else:
- c = int(s)
+ c = int(s.rstrip(';'))
return chr(c)
except ValueError:
- return '&#'+ s +';'
+ return '&#' + s
else:
- # Cannot use name2codepoint directly, because HTMLParser
- # supports apos, which is not part of HTML 4
- import html.entities
- if HTMLParser.entitydefs is None:
- entitydefs = HTMLParser.entitydefs = {'apos':"'"}
- for k, v in html.entities.name2codepoint.items():
- entitydefs[k] = chr(v)
- try:
- return self.entitydefs[s]
- except KeyError:
- return '&'+s+';'
-
- return re.sub(r"&(#?[xX]?(?:[0-9a-fA-F]+|\w{1,8}));",
+ from html.entities import html5
+ if s in html5:
+ return html5[s]
+ elif s.endswith(';'):
+ return '&' + s
+ for x in range(2, len(s)):
+ if s[:x] in html5:
+ return html5[s[:x]] + s[x:]
+ else:
+ return '&' + s
+
+ return re.sub(r"&(#?[xX]?(?:[0-9a-fA-F]+;|\w{1,32};?))",
replaceEntities, s, flags=re.ASCII)