#15114: the strict mode of HTMLParser and the HTMLParseError exception are deprecated now that the parser is able to parse invalid markup.
diff --git a/Lib/html/parser.py b/Lib/html/parser.py
index de504ab..494cf24 100644
--- a/Lib/html/parser.py
+++ b/Lib/html/parser.py
@@ -10,6 +10,7 @@
import _markupbase
import re
+import warnings
# Regular expressions used for parsing
@@ -113,14 +114,16 @@
CDATA_CONTENT_ELEMENTS = ("script", "style")
- def __init__(self, strict=True):
+ def __init__(self, strict=False):
"""Initialize and reset this instance.
- If strict is set to True (the default), errors are raised when invalid
- HTML is encountered. If set to False, an attempt is instead made to
- continue parsing, making "best guesses" about the intended meaning, in
- a fashion similar to what browsers typically do.
+ If strict is set to False (the default) the parser will parse invalid
+ markup, otherwise it will raise an error. Note that the strict mode
+ is deprecated.
"""
+ if strict:
+ warnings.warn("The strict mode is deprecated.",
+ DeprecationWarning, stacklevel=2)
self.strict = strict
self.reset()
@@ -271,8 +274,8 @@
# See also parse_declaration in _markupbase
def parse_html_declaration(self, i):
rawdata = self.rawdata
- if rawdata[i:i+2] != '<!':
- self.error('unexpected call to parse_html_declaration()')
+ assert rawdata[i:i+2] == '<!', ('unexpected call to '
+ 'parse_html_declaration()')
if rawdata[i:i+4] == '<!--':
# this case is actually already handled in goahead()
return self.parse_comment(i)
@@ -292,8 +295,8 @@
# see http://www.w3.org/TR/html5/tokenization.html#bogus-comment-state
def parse_bogus_comment(self, i, report=1):
rawdata = self.rawdata
- if rawdata[i:i+2] not in ('<!', '</'):
- self.error('unexpected call to parse_comment()')
+ assert rawdata[i:i+2] in ('<!', '</'), ('unexpected call to '
+ 'parse_comment()')
pos = rawdata.find('>', i+2)
if pos == -1:
return -1
diff --git a/Lib/test/test_htmlparser.py b/Lib/test/test_htmlparser.py
index c4f80cc..64a4f5d 100644
--- a/Lib/test/test_htmlparser.py
+++ b/Lib/test/test_htmlparser.py
@@ -102,7 +102,8 @@
class HTMLParserStrictTestCase(TestCaseBase):
def get_collector(self):
- return EventCollector(strict=True)
+ with support.check_warnings(("", DeprecationWarning), quite=False):
+ return EventCollector(strict=True)
def test_processing_instruction_only(self):
self._run_check("<?processing instruction>", [
@@ -594,7 +595,8 @@
class AttributesStrictTestCase(TestCaseBase):
def get_collector(self):
- return EventCollector(strict=True)
+ with support.check_warnings(("", DeprecationWarning), quite=False):
+ return EventCollector(strict=True)
def test_attr_syntax(self):
output = [