#15114: The html.parser module now raises a DeprecationWarning when the strict argument of HTMLParser or the HTMLParser.error method are used.
diff --git a/Doc/library/html.parser.rst b/Doc/library/html.parser.rst
index e4154ef..0ea9644 100644
--- a/Doc/library/html.parser.rst
+++ b/Doc/library/html.parser.rst
@@ -74,7 +74,7 @@
def handle_data(self, data):
print("Encountered some data :", data)
- parser = MyHTMLParser(strict=False)
+ parser = MyHTMLParser()
parser.feed('<html><head><title>Test</title></head>'
'<body><h1>Parse me!</h1></body></html>')
@@ -272,7 +272,7 @@
def handle_decl(self, data):
print("Decl :", data)
- parser = MyHTMLParser(strict=False)
+ parser = MyHTMLParser()
Parsing a doctype::
diff --git a/Lib/html/parser.py b/Lib/html/parser.py
index 18f3115..d7541ae 100644
--- a/Lib/html/parser.py
+++ b/Lib/html/parser.py
@@ -94,6 +94,8 @@
return result
+_strict_sentinel = object()
+
class HTMLParser(_markupbase.ParserBase):
"""Find tags and other markup and call handler functions.
@@ -116,16 +118,18 @@
CDATA_CONTENT_ELEMENTS = ("script", "style")
- def __init__(self, strict=False):
+ def __init__(self, strict=_strict_sentinel):
"""Initialize and reset this instance.
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.
+ and argument are deprecated.
"""
- if strict:
- warnings.warn("The strict mode is deprecated.",
+ if strict is not _strict_sentinel:
+ warnings.warn("The strict argument and mode are deprecated.",
DeprecationWarning, stacklevel=2)
+ else:
+ strict = False # default
self.strict = strict
self.reset()
@@ -151,6 +155,8 @@
self.goahead(1)
def error(self, message):
+ warnings.warn("The 'error' method is deprecated.",
+ DeprecationWarning, stacklevel=2)
raise HTMLParseError(message, self.getpos())
__starttag_text = None
diff --git a/Lib/test/test_htmlparser.py b/Lib/test/test_htmlparser.py
index b15b6fd..6ebf5b8 100644
--- a/Lib/test/test_htmlparser.py
+++ b/Lib/test/test_htmlparser.py
@@ -96,7 +96,9 @@
parser = self.get_collector()
parser.feed(source)
parser.close()
- self.assertRaises(html.parser.HTMLParseError, parse)
+ with self.assertRaises(html.parser.HTMLParseError):
+ with self.assertWarns(DeprecationWarning):
+ parse()
class HTMLParserStrictTestCase(TestCaseBase):
@@ -360,7 +362,16 @@
class HTMLParserTolerantTestCase(HTMLParserStrictTestCase):
def get_collector(self):
- return EventCollector(strict=False)
+ return EventCollector()
+
+ def test_deprecation_warnings(self):
+ with self.assertWarns(DeprecationWarning):
+ EventCollector(strict=True)
+ with self.assertWarns(DeprecationWarning):
+ EventCollector(strict=False)
+ with self.assertRaises(html.parser.HTMLParseError):
+ with self.assertWarns(DeprecationWarning):
+ EventCollector().error('test')
def test_tolerant_parsing(self):
self._run_check('<html <html>te>>xt&a<<bc</a></html>\n'
@@ -676,7 +687,7 @@
class AttributesTolerantTestCase(AttributesStrictTestCase):
def get_collector(self):
- return EventCollector(strict=False)
+ return EventCollector()
def test_attr_funky_names2(self):
self._run_check(
diff --git a/Misc/NEWS b/Misc/NEWS
index e54a16c..ff9860e 100644
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -31,6 +31,9 @@
Library
-------
+- Issue #15114: The html.parser module now raises a DeprecationWarning when the
+ strict argument of HTMLParser or the HTMLParser.error method are used.
+
- Issue #19410: Undo the special-casing removal of '' for
importlib.machinery.FileFinder.