elem is the result of .lower() 6 lines above the handle_endtag call.
Patch by Motoki Naruse

* Revert "Fixed a typo in the HTMLParser.feed docstrings. The docstring started with an 'r', like a The docstring was correct. I read the patch in opposite direction, as *adding* the "r" prefix.
This reverts commit 5ba18503.

Fixed a typo in the HTMLParser.feed docstrings. The docstring started with an 'r', like a rawstring. (#1759)

And most of the tools.

Patch by Emanual Barry, reviewed by me, Serhiy Storchaka, and
Martin Panter.

Most fixes to Doc/ and Lib/ directories by Ville Skyttä.

#21047: set the default value for the *convert_charrefs* argument of HTMLParser to True.  Patch by Berker Peksag.

#15114: the strict mode and argument of HTMLParser, HTMLParser.error, and the HTMLParserError exception have been removed.

#13633: Added a new convert_charrefs keyword arg to HTMLParser that, when True, automatically converts all character references.

#15114: The html.parser module now raises a DeprecationWarning when the strict argument of HTMLParser or the HTMLParser.error method are used.

#15114: the strict mode of HTMLParser and the HTMLParseError exception are deprecated now that the parser is able to parse invalid markup.

#670664: Fix HTMLParser to correctly handle the content of ``<script>...</script>`` and ``<style>...</style>``.

#12888: Fix a bug in HTMLParser.unescape that prevented it to escape more than 128 entities.  Patch by Peter Otten.

svn+ssh://pythondev@svn.python.org/python/branches/py3k

........
  r87542 | senthil.kumaran | 2010-12-28 23:55:16 +0800 (Tue, 28 Dec 2010) | 3 lines

  Fix Issue10759 - html.parser.unescape() fails on HTML entities with incorrect syntax
........

The motivation for adding this option is that the the functionality it
provides used to be provided by sgmllib in Python2, and was used by,
for example, BeautifulSoup.  Without this option, the Python3 version
of BeautifulSoup and the many programs that use it are crippled.

The original patch was by 'kxroberto'.  I modified it heavily but kept his
heuristics and test.  I also added additional heuristics to fix #975556,
#1046092, and part of #6191.  This patch should be completely backward
compatible:  the behavior with the default strict=True is unchanged.

svn+ssh://pythondev@svn.python.org/python/branches/py3k

................
  r81504 | victor.stinner | 2010-05-24 23:46:25 +0200 (lun., 24 mai 2010) | 13 lines

  Recorded merge of revisions 81500-81501 via svnmerge from
  svn+ssh://pythondev@svn.python.org/python/trunk

  ........
    r81500 | victor.stinner | 2010-05-24 23:33:24 +0200 (lun., 24 mai 2010) | 2 lines

    Issue #6662: Fix parsing of malformatted charref (&#bad;)
  ........
    r81501 | victor.stinner | 2010-05-24 23:37:28 +0200 (lun., 24 mai 2010) | 2 lines

    Add the author of the last fix (Issue #6662)
  ........
................

svn+ssh://pythondev@svn.python.org/python/trunk

........
  r81500 | victor.stinner | 2010-05-24 23:33:24 +0200 (lun., 24 mai 2010) | 2 lines

  Issue #6662: Fix parsing of malformatted charref (&#bad;)
........
  r81501 | victor.stinner | 2010-05-24 23:37:28 +0200 (lun., 24 mai 2010) | 2 lines

  Add the author of the last fix (Issue #6662)
........

and str (unicode) patterns get full unicode matching by default. The re.ASCII
flag is also introduced to ask for ASCII matching instead.

rename in r63439.

Also fix one occurrence of unichr() in html.parser.

(http://bugs.python.org/issue2882)