[Python-checkins] cpython: #15156: HTMLParser now uses the new "html.entities.html5" dictionary.

[ezio.melotti]

http://hg.python.org/cpython/rev/0d53703b1a99
changeset:   77742:0d53703b1a99
parent:      77740:1120041f2df4
user:        Ezio Melotti <ezio.melotti at gmail.com>
date:        Sun Jun 24 22:02:56 2012 +0200
summary:
  #15156: HTMLParser now uses the new "html.entities.html5" dictionary.

files:
  Doc/library/html.entities.rst |   4 ---
  Lib/html/parser.py            |  30 ++++++++++------------
  Lib/test/test_htmlparser.py   |   7 ++++-
  Misc/NEWS                     |   2 +
  4 files changed, 22 insertions(+), 21 deletions(-)


diff --git a/Doc/library/html.entities.rst b/Doc/library/html.entities.rst
--- a/Doc/library/html.entities.rst
+++ b/Doc/library/html.entities.rst
@@ -11,10 +11,6 @@
 
 This module defines four dictionaries, :data:`html5`,
 :data:`name2codepoint`, :data:`codepoint2name`, and :data:`entitydefs`.
-:data:`entitydefs` is used to provide the :attr:`entitydefs`
-attribute of the :class:`html.parser.HTMLParser` class.  The definition provided
-here contains all the entities defined by XHTML 1.0 that can be handled using
-simple textual substitution in the Latin-1 character set (ISO-8859-1).
 
 
 .. data:: html5
diff --git a/Lib/html/parser.py b/Lib/html/parser.py
--- a/Lib/html/parser.py
+++ b/Lib/html/parser.py
@@ -500,7 +500,6 @@
             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 @@
                 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+';'
+                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{1,8}));",
+        return re.sub(r"&(#?[xX]?(?:[0-9a-fA-F]+;|\w{1,32};?))",
                       replaceEntities, s, flags=re.ASCII)
diff --git a/Lib/test/test_htmlparser.py b/Lib/test/test_htmlparser.py
--- a/Lib/test/test_htmlparser.py
+++ b/Lib/test/test_htmlparser.py
@@ -456,7 +456,7 @@
         self._run_check('<form action="/xxx.php?a=1&amp;b=2&amp", '
                         'method="post">', [
                             ('starttag', 'form',
-                                [('action', '/xxx.php?a=1&b=2&amp'),
+                                [('action', '/xxx.php?a=1&b=2&'),
                                  (',', None), ('method', 'post')])])
 
     def test_weird_chars_in_unquoted_attribute_values(self):
@@ -541,6 +541,11 @@
         self.assertEqual(p.unescape('&#0038;'),'&')
         # see #12888
         self.assertEqual(p.unescape('&#123; ' * 1050), '{ ' * 1050)
+        # see #15156
+        self.assertEqual(p.unescape('&Eacuteric&Eacute;ric'
+                                    '&alphacentauri&alpha;centauri'),
+                                    'ÉricÉric&alphacentauriαcentauri')
+        self.assertEqual(p.unescape('&co;'), '&co;')
 
     def test_broken_comments(self):
         html = ('<! not really a comment >'
diff --git a/Misc/NEWS b/Misc/NEWS
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -76,6 +76,8 @@
   It is used automatically on platforms supporting the necessary os.openat()
   and os.unlinkat() functions. Main code by Martin von Löwis.
 
+- Issue #15156: HTMLParser now uses the new "html.entities.html5" dictionary.
+
 - Issue #11113: add a new "html5" dictionary containing the named character
   references defined by the HTML5 standard and the equivalent Unicode
   character(s) to the html.entities module.

-- 
Repository URL: http://hg.python.org/cpython