cpython: 8dd2f5754b2f (original) (raw)

Mercurial > cpython

changeset 77630:8dd2f5754b2f

#15114: the strict mode of HTMLParser and the HTMLParseError exception are deprecated now that the parser is able to parse invalid markup. [#15114]

line wrap: on

line diff

--- a/Doc/library/html.parser.rst +++ b/Doc/library/html.parser.rst @@ -16,13 +16,14 @@ 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(strict=True) +.. class:: HTMLParser(strict=False)

• Create a parser instance. If strict is True (the default), invalid
• HTML results in :exc:~html.parser.HTMLParseError exceptions [#]_. If
• strict is False, the parser uses heuristics to make a best guess at
• the intention of any invalid HTML it encounters, similar to the way most
• browsers do. Using strict=False is advised.

• Create a parser instance. If strict is False (the default), the parser
• will accept and parse invalid markup. If strict is True the parser
• will raise an :exc:~html.parser.HTMLParseError exception instead [#]_ when
• it's not able to parse the markup.
• The use of strict=True is discouraged and the strict argument is
• deprecated. An :class:.HTMLParser instance is fed HTML data and calls handler methods when start tags, end tags, text, comments, and other markup elements are @@ -34,6 +35,10 @@ parsing text files formatted in HTML (Hy .. versionchanged:: 3.2 strict keyword added
• .. deprecated-removed:: 3.3 3.5

•  The *strict* argument and the strict mode have been deprecated.[](#l1.29)

•  The parser is now able to accept and parse invalid markup too.[](#l1.30)

+ An exception is defined as well: @@ -46,6 +51,10 @@ An exception is defined as well: detected, and :attr:offset is the number of characters into the line at which the construct starts.

• .. deprecated-removed:: 3.3 3.5

•  This exception has been deprecated because it's never raised by the parser[](#l1.40)

•  (when the default non-strict mode is used).[](#l1.41)

+ Example HTML Parser Application -------------------------------

--- 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 @@ class HTMLParser(_markupbase.ParserBase) 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[](#l2.19)

•    HTML is encountered.  If set to False, an attempt is instead made to[](#l2.20)

•    continue parsing, making "best guesses" about the intended meaning, in[](#l2.21)

•    a fashion similar to what browsers typically do.[](#l2.22)

•    If strict is set to False (the default) the parser will parse invalid[](#l2.23)

•    markup, otherwise it will raise an error.  Note that the strict mode[](#l2.24)

•    is deprecated.[](#l2.25)
     """[](#l2.26)

•    if strict:[](#l2.27)

•        warnings.warn("The strict mode is deprecated.",[](#l2.28)

•                      DeprecationWarning, stacklevel=2)[](#l2.29)
     self.strict = strict[](#l2.30)
     self.reset()[](#l2.31)

@@ -271,8 +274,8 @@ class HTMLParser(_markupbase.ParserBase) # See also parse_declaration in _markupbase def parse_html_declaration(self, i): rawdata = self.rawdata

•    if rawdata[i:i+2] != '<!':[](#l2.37)

•        self.error('unexpected call to parse_html_declaration()')[](#l2.38)

•    assert rawdata[i:i+2] == '<!', ('unexpected call to '[](#l2.39)

•                                    'parse_html_declaration()')[](#l2.40)
     if rawdata[i:i+4] == '<!--':[](#l2.41)
         # this case is actually already handled in goahead()[](#l2.42)
         return self.parse_comment(i)[](#l2.43)

@@ -292,8 +295,8 @@ class HTMLParser(_markupbase.ParserBase) # see http://www.w3.org/TR/html5/tokenization.html#bogus-comment-state[](#l2.45) def parse_bogus_comment(self, i, report=1): rawdata = self.rawdata

•    if rawdata[i:i+2] not in ('<!', '</'):[](#l2.48)

•        self.error('unexpected call to parse_comment()')[](#l2.49)

•    assert rawdata[i:i+2] in ('<!', '</'), ('unexpected call to '[](#l2.50)

•                                            'parse_comment()')[](#l2.51)
     pos = rawdata.find('>', i+2)[](#l2.52)
     if pos == -1:[](#l2.53)
         return -1[](#l2.54)

--- a/Lib/test/test_htmlparser.py +++ b/Lib/test/test_htmlparser.py @@ -102,7 +102,8 @@ class TestCaseBase(unittest.TestCase): class HTMLParserStrictTestCase(TestCaseBase): def get_collector(self):

•    return EventCollector(strict=True)[](#l3.7)

•    with support.check_warnings(("", DeprecationWarning), quite=False):[](#l3.8)

•        return EventCollector(strict=True)[](#l3.9)

def test_processing_instruction_only(self): self._run_check("<?processing instruction>", [ @@ -594,7 +595,8 @@ class HTMLParserTolerantTestCase(HTMLPar class AttributesStrictTestCase(TestCaseBase): def get_collector(self):

•    return EventCollector(strict=True)[](#l3.17)

•    with support.check_warnings(("", DeprecationWarning), quite=False):[](#l3.18)

•        return EventCollector(strict=True)[](#l3.19)

def test_attr_syntax(self): output = [

--- a/Misc/NEWS +++ b/Misc/NEWS @@ -43,6 +43,9 @@ Core and Builtins Library ------- +- Issue #15114: the strict mode of HTMLParser and the HTMLParseError exception

• are deprecated now that the parser is able to parse invalid markup. +

• Issue #3665: \u and \U escapes are now supported in unicode regular expressions. Patch by Serhiy Storchaka. @@ -78,7 +81,7 @@ Library
• Issue #9527: datetime.astimezone() method will now supply a class timezone instance corresponding to the system local timezone when called with no arguments.
• +
• Issue #14653: email.utils.mktime_tz() no longer relies on system mktime() when timezone offest is supplied.