#21047: set the default value for the *convert_charrefs* argument of HTMLParser to True. Patch by Berker Peksag.

This commit is contained in:
Ezio Melotti 2014-08-02 18:36:12 +03:00
parent 11bec7a1b8
commit 6fc16d81af
4 changed files with 12 additions and 17 deletions

View File

@ -16,15 +16,13 @@
This module defines a class :class:`HTMLParser` which serves as the basis for
parsing text files formatted in HTML (HyperText Mark-up Language) and XHTML.
.. class:: HTMLParser(*, convert_charrefs=False)
.. class:: HTMLParser(*, convert_charrefs=True)
Create a parser instance able to parse invalid markup.
If *convert_charrefs* is ``True`` (default: ``False``), all character
If *convert_charrefs* is ``True`` (the default), all character
references (except the ones in ``script``/``style`` elements) are
automatically converted to the corresponding Unicode characters.
The use of ``convert_charrefs=True`` is encouraged and will become
the default in Python 3.5.
An :class:`.HTMLParser` instance is fed HTML data and calls handler methods
when start tags, end tags, text, comments, and other markup elements are
@ -37,6 +35,9 @@ parsing text files formatted in HTML (HyperText Mark-up Language) and XHTML.
.. versionchanged:: 3.4
*convert_charrefs* keyword argument added.
.. versionchanged:: 3.5
The default value for argument *convert_charrefs* is now ``True``.
Example HTML Parser Application
-------------------------------

View File

@ -59,7 +59,6 @@ endendtag = re.compile('>')
endtagfind = re.compile('</\s*([a-zA-Z][-.a-zA-Z0-9:_]*)\s*>')
_default_sentinel = object()
class HTMLParser(_markupbase.ParserBase):
"""Find tags and other markup and call handler functions.
@ -85,17 +84,12 @@ class HTMLParser(_markupbase.ParserBase):
CDATA_CONTENT_ELEMENTS = ("script", "style")
def __init__(self, *, convert_charrefs=_default_sentinel):
def __init__(self, *, convert_charrefs=True):
"""Initialize and reset this instance.
If convert_charrefs is True (default: False), all character references
If convert_charrefs is True (the default), all character references
are automatically converted to the corresponding Unicode characters.
"""
if convert_charrefs is _default_sentinel:
convert_charrefs = False # default
warnings.warn("The value of convert_charrefs will become True in "
"3.5. You are encouraged to set the value explicitly.",
DeprecationWarning, stacklevel=2)
self.convert_charrefs = convert_charrefs
self.reset()

View File

@ -346,7 +346,8 @@ text
self._run_check(html, expected)
def test_convert_charrefs(self):
collector = lambda: EventCollectorCharrefs(convert_charrefs=True)
# default value for convert_charrefs is now True
collector = lambda: EventCollectorCharrefs()
self.assertTrue(collector().convert_charrefs)
charrefs = ['&quot;', '&#34;', '&#x22;', '&quot', '&#34', '&#x22']
# check charrefs in the middle of the text/attributes
@ -383,10 +384,6 @@ text
self._run_check('no charrefs here', [('data', 'no charrefs here')],
collector=collector())
def test_deprecation_warnings(self):
with self.assertWarns(DeprecationWarning):
EventCollector() # convert_charrefs not passed explicitly
# the remaining tests were for the "tolerant" parser (which is now
# the default), and check various kind of broken markup
def test_tolerant_parsing(self):

View File

@ -121,6 +121,9 @@ Core and Builtins
Library
-------
- Issue #21047: set the default value for the *convert_charrefs* argument
of HTMLParser to True. Patch by Berker Peksag.
- Add an __all__ to html.entities.
- Issue #15114: the strict mode and argument of HTMLParser, HTMLParser.error,