rename HTMLParser to html.parser and htmlentitydefs to html.entities;
includes merge of trunk revision 63432
diff --git a/Lib/html/__init__.py b/Lib/html/__init__.py
new file mode 100644
index 0000000..196d378
--- /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 96%
rename from Lib/HTMLParser.py
rename to Lib/html/parser.py
index 9979195..352a788 100644
--- a/Lib/HTMLParser.py
+++ b/Lib/html/parser.py
@@ -372,16 +372,17 @@
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 88e1df5..a580006 100644
--- a/Lib/htmllib.py
+++ b/Lib/htmllib.py
@@ -24,7 +24,7 @@
"""
- 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 12eb068..64d1645 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 @@
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 48e9089..5508c9d 100644
--- a/Lib/test/test_multibytecodec_support.py
+++ b/Lib/test/test_multibytecodec_support.py
@@ -74,7 +74,7 @@
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 dd81e5b..1b6069d 100644
--- a/Lib/test/test_sundry.py
+++ b/Lib/test/test_sundry.py
@@ -48,7 +48,7 @@
import encodings
import formatter
import getpass
- import htmlentitydefs
+ import html.entities
import imghdr
import keyword
import linecache