changeset: 76413:36c901fcfcda
branch: 2.7
user: Ezio Melotti <ezio.melotti@gmail.com>
date: Wed Apr 18 19:08:41 2012 -0600
files: Lib/HTMLParser.py Lib/test/test_htmlparser.py Misc/NEWS
description:
#14538: HTMLParser can now parse correctly start tags that contain a bare /.
diff -r b82a471d2c5e -r 36c901fcfcda Lib/HTMLParser.py
--- a/Lib/HTMLParser.py	Wed Apr 18 16:41:56 2012 -0700
+++ b/Lib/HTMLParser.py	Wed Apr 18 19:08:41 2012 -0600
@@ -22,13 +22,13 @@
 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&#124;/(?!>))*')
 # 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'(\'[^\']*\'&#124;"[^"]*"&#124;(?![\'"])[^>\s]*))?(?:\s&#124;/(?!>))*')
 
 locatestarttagend = re.compile(r"""
@@ -289,7 +289,7 @@
 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) diff -r b82a471d2c5e -r 36c901fcfcda Lib/test/test_htmlparser.py --- a/Lib/test/test_htmlparser.py Wed Apr 18 16:41:56 2012 -0700 +++ b/Lib/test/test_htmlparser.py Wed Apr 18 19:08:41 2012 -0600 @@ -260,6 +260,16 @@ ('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 $ ')])
diff -r b82a471d2c5e -r 36c901fcfcda Misc/NEWS
--- a/Misc/NEWS	Wed Apr 18 16:41:56 2012 -0700
+++ b/Misc/NEWS	Wed Apr 18 19:08:41 2012 -0600
@@ -50,6 +50,9 @@
 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
</div><div class="naked_ctrl">
<form action="/index.cgi/contrast" method="get" name="gate">
<p><a href="http://altstyle.alfasado.net">AltStyle</a> によって変換されたページ <a href="https://hg.python.org/cpython/rev/36c901fcfcda">(-&gt;オリジナル)</a>
/ <label>アドレス: <input type="text" name="naked_post_url" value="https://hg.python.org/cpython/rev/36c901fcfcda" size="22" /></label> <label>モード: <select name="naked_post_mode">
<option value="default">デフォルト</option>
<option value="speech">音声ブラウザ</option>
<option value="ruby">ルビ付き</option>
<option value="contrast" selected="selected">配色反転</option>
<option value="larger-text">文字拡大</option>
<option value="mobile">モバイル</option>
</select>
<input type="submit" value="表示" />
</p>
</form>
</div>