summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorFred Drake <fdrake@acm.org>2008-05-17 21:14:05 (GMT)
committerFred Drake <fdrake@acm.org>2008-05-17 21:14:05 (GMT)
commitcb51d84214ed07268338392abef986b9a56d0141 (patch)
tree474b5ec5794e8e97953df73059c55d78cc2df631
parent91ae2502739ecfcc7a8a013473553224b8387521 (diff)
downloadcpython-cb51d84214ed07268338392abef986b9a56d0141.zip
cpython-cb51d84214ed07268338392abef986b9a56d0141.tar.gz
cpython-cb51d84214ed07268338392abef986b9a56d0141.tar.bz2
update references and documentation for modules in the new html package
(http://bugs.python.org/issue2882)
-rw-r--r--Doc/library/htmllib.rst10
-rw-r--r--Doc/library/htmlparser.rst14
-rw-r--r--Lib/html/parser.py11
-rw-r--r--Lib/htmllib.py2
-rw-r--r--Lib/test/test_codeccallbacks.py4
-rw-r--r--Lib/test/test_multibytecodec_support.py2
-rw-r--r--Lib/test/test_sundry.py2
7 files changed, 23 insertions, 22 deletions
diff --git a/Doc/library/htmllib.rst b/Doc/library/htmllib.rst
index 96a7d08..ffaaaec 100644
--- a/Doc/library/htmllib.rst
+++ b/Doc/library/htmllib.rst
@@ -77,12 +77,12 @@ 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`
@@ -149,10 +149,10 @@ 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>
diff --git a/Doc/library/htmlparser.rst b/Doc/library/htmlparser.rst
index 85a38fb..ee3e1f2 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.
@@ -22,7 +22,7 @@ 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.
@@ -92,8 +92,8 @@ An exception is defined as well:
``handle_starttag('a', [('href', 'http://www.cwi.nl/')])``.
.. versionchanged:: 2.6
- All entity references from htmlentitydefs are now replaced in the attribute
- values.
+ All entity references from :mod:`html.entities` are now replaced in the
+ attribute values.
.. method:: HTMLParser.handle_startendtag(tag, attrs)
@@ -171,7 +171,7 @@ 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/parser.py b/Lib/html/parser.py
index 2cbc2ec..b5010ac 100644
--- a/Lib/html/parser.py
+++ b/Lib/html/parser.py
@@ -372,16 +372,17 @@ class HTMLParser(markupbase.ParserBase):
c = int(s)
return unichr(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':u"'"}
- for k, v in htmlentitydefs.name2codepoint.iteritems():
+ for k, v in html.entities.name2codepoint.iteritems():
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 24a2e2f..7ebb622 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 656551d..a0fa343 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(u"&%s;" % htmlentitydefs.codepoint2name[ord(c)])
+ l.append(u"&%s;" % html.entities.codepoint2name[ord(c)])
except KeyError:
l.append(u"&#%d;" % ord(c))
return (u"".join(l), exc.end)
diff --git a/Lib/test/test_multibytecodec_support.py b/Lib/test/test_multibytecodec_support.py
index 6055764..b9aa34b 100644
--- a/Lib/test/test_multibytecodec_support.py
+++ b/Lib/test/test_multibytecodec_support.py
@@ -64,7 +64,7 @@ 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 404a405..c2fb66d 100644
--- a/Lib/test/test_sundry.py
+++ b/Lib/test/test_sundry.py
@@ -50,7 +50,7 @@ class TestUntestedModules(unittest.TestCase):
import encodings
import formatter
import getpass
- import htmlentitydefs
+ import html.entities
import ihooks
import imghdr
import imputil