From 3c50ea4303ad58785e7f5058cdd353c6d0140ee4 Mon Sep 17 00:00:00 2001 From: Fred Drake Date: Sat, 17 May 2008 22:02:32 +0000 Subject: [PATCH] rename HTMLParser to html.parser and htmlentitydefs to html.entities; includes merge of trunk revision 63432 --- Doc/library/htmllib.rst | 10 +++++----- Doc/library/htmlparser.rst | 14 +++++++------- Lib/html/__init__.py | 1 + Lib/{htmlentitydefs.py => html/entities.py} | 0 Lib/{HTMLParser.py => html/parser.py} | 13 +++++++------ Lib/htmllib.py | 2 +- Lib/test/test_codeccallbacks.py | 4 ++-- Lib/test/test_multibytecodec_support.py | 2 +- Lib/test/test_sundry.py | 2 +- 9 files changed, 25 insertions(+), 23 deletions(-) create mode 100644 Lib/html/__init__.py rename Lib/{htmlentitydefs.py => html/entities.py} (100%) rename Lib/{HTMLParser.py => html/parser.py} (97%) diff --git a/Doc/library/htmllib.rst b/Doc/library/htmllib.rst index e1f2447fbdd..34423a04471 100644 --- a/Doc/library/htmllib.rst +++ b/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. diff --git a/Doc/library/htmlparser.rst b/Doc/library/htmlparser.rst index 5cfe04ef1a4..4bfb2878403 100644 --- a/Doc/library/htmlparser.rst +++ b/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): diff --git a/Lib/html/__init__.py b/Lib/html/__init__.py new file mode 100644 index 00000000000..196d3788575 --- /dev/null +++ b/Lib/html/__init__.py @@ -0,0 +1 @@ +# This directory is a Python package. diff --git a/Lib/htmlentitydefs.py b/Lib/html/entities.py similarity index 100% rename from Lib/htmlentitydefs.py rename to Lib/html/entities.py diff --git a/Lib/HTMLParser.py b/Lib/html/parser.py similarity index 97% rename from Lib/HTMLParser.py rename to Lib/html/parser.py index 99791955f31..352a78841c0 100644 --- a/Lib/HTMLParser.py +++ b/Lib/html/parser.py @@ -372,16 +372,17 @@ class HTMLParser(_markupbase.ParserBase): 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) diff --git a/Lib/htmllib.py b/Lib/htmllib.py index 88e1df5741c..a5800068283 100644 --- a/Lib/htmllib.py +++ b/Lib/htmllib.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. diff --git a/Lib/test/test_codeccallbacks.py b/Lib/test/test_codeccallbacks.py index 12eb068c2aa..64d1645dbb2 100644 --- a/Lib/test/test_codeccallbacks.py +++ b/Lib/test/test_codeccallbacks.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 @@ class CodecCallbackTest(unittest.TestCase): 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) diff --git a/Lib/test/test_multibytecodec_support.py b/Lib/test/test_multibytecodec_support.py index 48e90899dda..5508c9d09c2 100644 --- a/Lib/test/test_multibytecodec_support.py +++ b/Lib/test/test_multibytecodec_support.py @@ -74,7 +74,7 @@ class TestBase: if self.has_iso10646: return - from htmlentitydefs import codepoint2name + from html.entities import codepoint2name def xmlcharnamereplace(exc): if not isinstance(exc, UnicodeEncodeError): diff --git a/Lib/test/test_sundry.py b/Lib/test/test_sundry.py index dd81e5b27e3..1b6069dde08 100644 --- a/Lib/test/test_sundry.py +++ b/Lib/test/test_sundry.py @@ -48,7 +48,7 @@ class TestUntestedModules(unittest.TestCase): import encodings import formatter import getpass - import htmlentitydefs + import html.entities import imghdr import keyword import linecache