rename HTMLParser to html.parser and htmlentitydefs to html.entities;

includes merge of trunk revision 63432

Author: freddrake

Doc/library/htmllib.rst

@@ -75,12 +75,12 @@ The module defines a parser class and an exception:
       Interface definition for transforming an abstract flow of formatting events into
       specific output events on writer objects.
 
-   Module :mod:`HTMLParser`
+   Module :mod:`html.parser`
       Alternate HTML parser that offers a slightly lower-level view of the input, but
       is designed to work with XHTML, and does not implement some of the SGML syntax
       not used in "HTML as deployed" and which isn't legal for XHTML.
 
-   Module :mod:`htmlentitydefs`
+   Module :mod:`html.entities`
       Definition of replacement text for XHTML 1.0  entities.
 
    Module :mod:`sgmllib`
@@ -147,10 +147,10 @@ additional methods and instance variables for use within tag methods.
    :meth:`save_bgn` will raise a :exc:`TypeError` exception.
 
 
-:mod:`htmlentitydefs` --- Definitions of HTML general entities
-==============================================================
+:mod:`html.entities` --- Definitions of HTML general entities
+=============================================================
 
-.. module:: htmlentitydefs
+.. module:: html.entities
    :synopsis: Definitions of HTML general entities.
 .. sectionauthor:: Fred L. Drake, Jr. <fdrake@acm.org>
 

Doc/library/htmlparser.rst

@@ -1,8 +1,8 @@
 
-:mod:`HTMLParser` --- Simple HTML and XHTML parser
-==================================================
+:mod:`html.parser` --- Simple HTML and XHTML parser
+===================================================
 
-.. module:: HTMLParser
+.. module:: html.parser
    :synopsis: A simple parser that can handle HTML and XHTML.
 
 
@@ -18,7 +18,7 @@ in :mod:`sgmllib`.
 
    The :class:`HTMLParser` class is instantiated without arguments.
 
-   An HTMLParser instance is fed HTML data and calls handler functions when tags
+   An :class:`HTMLParser` instance is fed HTML data and calls handler functions when tags
    begin and end.  The :class:`HTMLParser` class is meant to be overridden by the
    user to provide a desired behavior.
 
@@ -87,8 +87,8 @@ An exception is defined as well:
    HREF="http://www.cwi.nl/">``, this method would be called as
    ``handle_starttag('a', [('href', 'http://www.cwi.nl/')])``.
 
-   All entity references from htmlentitydefs are replaced in the attribute
-   values.
+   All entity references from :mod:`html.entities` are replaced in the
+   attribute values.
 
 
 .. method:: HTMLParser.handle_startendtag(tag, attrs)
@@ -166,7 +166,7 @@ Example HTML Parser Application
 As a basic example, below is a very basic HTML parser that uses the
 :class:`HTMLParser` class to print out tags as they are encountered::
 
-   from HTMLParser import HTMLParser
+   from html.parser import HTMLParser
 
    class MyHTMLParser(HTMLParser):
 

Lib/html/__init__.py

@@ -0,0 +1 @@
+# This directory is a Python package.

Lib/htmlentitydefs.py Lib/html/entities.pyLib/htmlentitydefs.py renamed to Lib/html/entities.py

@@ -372,16 +372,17 @@ def replaceEntities(s):
                     c = int(s)
                 return chr(c)
             else:
-                # Cannot use name2codepoint directly, because HTMLParser supports apos,
-                # which is not part of HTML 4
-                import htmlentitydefs
+                # 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 htmlentitydefs.name2codepoint.items():
-                        entitydefs[k] = chr(v)
+                    for k, v in html.entities.name2codepoint.items():
+                        entitydefs[k] = unichr(v)
                 try:
                     return self.entitydefs[s]
                 except KeyError:
                     return '&'+s+';'
 
-        return re.sub(r"&(#?[xX]?(?:[0-9a-fA-F]+|\w{1,8}));", replaceEntities, s)
+        return re.sub(r"&(#?[xX]?(?:[0-9a-fA-F]+|\w{1,8}));",
+                      replaceEntities, s)

Lib/HTMLParser.py Lib/html/parser.pyLib/HTMLParser.py renamed to Lib/html/parser.py

@@ -24,7 +24,7 @@ class HTMLParser(sgmllib.SGMLParser):
 
     """
 
-    from htmlentitydefs import entitydefs
+    from html.entities import entitydefs
 
     def __init__(self, formatter, verbose=0):
         """Creates an instance of the HTMLParser class.

Lib/htmllib.py

@@ -1,5 +1,5 @@
 import test.test_support, unittest
-import sys, codecs, htmlentitydefs, unicodedata
+import sys, codecs, html.entities, unicodedata
 
 class PosReturn:
     # this can be used for configurable callbacks
@@ -86,7 +86,7 @@ def xmlcharnamereplace(exc):
             l = []
             for c in exc.object[exc.start:exc.end]:
                 try:
-                    l.append("&%s;" % htmlentitydefs.codepoint2name[ord(c)])
+                    l.append("&%s;" % html.entities.codepoint2name[ord(c)])
                 except KeyError:
                     l.append("&#%d;" % ord(c))
             return ("".join(l), exc.end)

Lib/test/test_codeccallbacks.py

@@ -74,7 +74,7 @@ def test_customreplace_encode(self):
         if self.has_iso10646:
             return
 
-        from htmlentitydefs import codepoint2name
+        from html.entities import codepoint2name
 
         def xmlcharnamereplace(exc):
             if not isinstance(exc, UnicodeEncodeError):

Lib/test/test_multibytecodec_support.py

@@ -48,7 +48,7 @@ def test_at_least_import_untested_modules(self):
             import encodings
             import formatter
             import getpass
-            import htmlentitydefs
+            import html.entities
             import imghdr
             import keyword
             import linecache