diff --git a/Doc/library/html.parser.rst b/Doc/library/html.parser.rst
--- a/Doc/library/html.parser.rst
+++ b/Doc/library/html.parser.rst
@@ -16,14 +16,9 @@
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=False)
+.. class:: HTMLParser()
- 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.
+ Create a parser instance able to parse invalid markup.
An :class:`.HTMLParser` instance is fed HTML data and calls handler methods
when start tags, end tags, text, comments, and other markup elements are
@@ -33,30 +28,6 @@
This parser does not check that end tags match start tags or call the end-tag
handler for elements which are closed implicitly by closing an outer element.
- .. versionchanged:: 3.2
- *strict* keyword added.
-
- .. deprecated-removed:: 3.3 3.5
- The *strict* argument and the strict mode have been deprecated.
- The parser is now able to accept and parse invalid markup too.
-
-An exception is defined as well:
-
-
-.. exception:: HTMLParseError
-
- Exception raised by the :class:`HTMLParser` class when it encounters an error
- while parsing and *strict* is ``True``. This exception provides three
- attributes: :attr:`msg` is a brief message explaining the error,
- :attr:`lineno` is the number of the line on which the broken construct was
- 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
- (when the default non-strict mode is used).
-
-
Example HTML Parser Application
-------------------------------
@@ -234,8 +205,7 @@
The *data* parameter will be the entire contents of the declaration inside
the ```` markup. It is sometimes useful to be overridden by a
- derived class. The base class implementation raises an :exc:`HTMLParseError`
- when *strict* is ``True``.
+ derived class. The base class implementation does nothing.
.. _htmlparser-examples:
@@ -345,9 +315,3 @@
Data : tag soup
End tag : p
End tag : a
-
-.. rubric:: Footnotes
-
-.. [#] For backward compatibility reasons *strict* mode does not raise
- exceptions for all non-compliant HTML. That is, some invalid HTML
- is tolerated even in *strict* mode.
diff --git a/Lib/html/parser.py b/Lib/html/parser.py
--- a/Lib/html/parser.py
+++ b/Lib/html/parser.py
@@ -25,36 +25,12 @@
starttagopen = re.compile('<[a-zA-Z]')
piclose = re.compile('>')
commentclose = re.compile(r'--\s*>')
-# Note:
-# 1) the strict attrfind isn't really strict, but we can't make it
-# correctly strict without breaking backward compatibility;
-# 2) if you change tagfind/attrfind remember to update locatestarttagend too;
-# 3) if you change tagfind/attrfind and/or locatestarttagend the parser will
-# explode, so don't do it.
-tagfind = re.compile('([a-zA-Z][-.a-zA-Z0-9:_]*)(?:\s|/(?!>))*')
# see http://www.w3.org/TR/html5/tokenization.html#tag-open-state
# and http://www.w3.org/TR/html5/tokenization.html#tag-name-state
tagfind_tolerant = re.compile('([a-zA-Z][^\t\n\r\f />\x00]*)(?:\s|/(?!>))*')
-attrfind = re.compile(
- r'\s*([a-zA-Z_][-.:a-zA-Z_0-9]*)(\s*=\s*'
- r'(\'[^\']*\'|"[^"]*"|[^\s"\'=<>`]*))?')
attrfind_tolerant = re.compile(
r'((?<=[\'"\s/])[^\s/>][^\s/=>]*)(\s*=+\s*'
r'(\'[^\']*\'|"[^"]*"|(?![\'"])[^>\s]*))?(?:\s|/(?!>))*')
-locatestarttagend = re.compile(r"""
- <[a-zA-Z][-.a-zA-Z0-9:_]* # tag name
- (?:\s+ # whitespace before attribute name
- (?:[a-zA-Z_][-.:a-zA-Z0-9_]* # attribute name
- (?:\s*=\s* # value indicator
- (?:'[^']*' # LITA-enclosed value
- |\"[^\"]*\" # LIT-enclosed value
- |[^'\">\s]+ # bare value
- )
- )?
- )
- )*
- \s* # trailing whitespace
-""", re.VERBOSE)
locatestarttagend_tolerant = re.compile(r"""
<[a-zA-Z][^\t\n\r\f />\x00]* # tag name
(?:[\s/]* # optional whitespace before attribute name
@@ -76,25 +52,6 @@
endtagfind = re.compile('\s*([a-zA-Z][-.a-zA-Z0-9:_]*)\s*>')
-class HTMLParseError(Exception):
- """Exception raised for all parse errors."""
-
- def __init__(self, msg, position=(None, None)):
- assert msg
- self.msg = msg
- self.lineno = position[0]
- self.offset = position[1]
-
- def __str__(self):
- result = self.msg
- if self.lineno is not None:
- result = result + ", at line %d" % self.lineno
- if self.offset is not None:
- result = result + ", column %d" % (self.offset + 1)
- return result
-
-
-_strict_sentinel = object()
class HTMLParser(_markupbase.ParserBase):
"""Find tags and other markup and call handler functions.
@@ -118,19 +75,8 @@
CDATA_CONTENT_ELEMENTS = ("script", "style")
- 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
- and argument are 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
+ def __init__(self):
+ """Initialize and reset this instance."""
self.reset()
def reset(self):
@@ -154,11 +100,6 @@
"""Handle any buffered data."""
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
def get_starttag_text(self):
@@ -202,10 +143,7 @@
elif startswith("", i):
k = self.parse_pi(i)
elif startswith("', i + 1)
if k < 0:
k = rawdata.find('<', i + 1)
@@ -254,13 +190,10 @@
if match:
# match.group() will contain at least 2 chars
if end and match.group() == rawdata[i:]:
- if self.strict:
- self.error("EOF in middle of entity or char ref")
- else:
- k = match.end()
- if k <= i:
- k = n
- i = self.updatepos(i, i + 1)
+ k = match.end()
+ if k <= i:
+ k = n
+ i = self.updatepos(i, i + 1)
# incomplete
break
elif (i + 1) < n:
@@ -336,18 +269,12 @@
# Now parse the data between i+1 and j into a tag and attrs
attrs = []
- if self.strict:
- match = tagfind.match(rawdata, i+1)
- else:
- match = tagfind_tolerant.match(rawdata, i+1)
+ match = tagfind_tolerant.match(rawdata, i+1)
assert match, 'unexpected call to parse_starttag()'
k = match.end()
self.lasttag = tag = match.group(1).lower()
while k < endpos:
- if self.strict:
- m = attrfind.match(rawdata, k)
- else:
- m = attrfind_tolerant.match(rawdata, k)
+ m = attrfind_tolerant.match(rawdata, k)
if not m:
break
attrname, rest, attrvalue = m.group(1, 2, 3)
@@ -370,9 +297,6 @@
- self.__starttag_text.rfind("\n")
else:
offset = offset + len(self.__starttag_text)
- if self.strict:
- self.error("junk characters in start tag: %r"
- % (rawdata[k:endpos][:20],))
self.handle_data(rawdata[i:endpos])
return endpos
if end.endswith('/>'):
@@ -388,10 +312,7 @@
# or -1 if incomplete.
def check_for_whole_start_tag(self, i):
rawdata = self.rawdata
- if self.strict:
- m = locatestarttagend.match(rawdata, i)
- else:
- m = locatestarttagend_tolerant.match(rawdata, i)
+ m = locatestarttagend_tolerant.match(rawdata, i)
if m:
j = m.end()
next = rawdata[j:j+1]
@@ -404,9 +325,6 @@
# buffer boundary
return -1
# else bogus input
- if self.strict:
- self.updatepos(i, j + 1)
- self.error("malformed empty start tag")
if j > i:
return j
else:
@@ -419,9 +337,6 @@
# end of input in or before attribute value, or we have the
# '/' from a '/>' ending
return -1
- if self.strict:
- self.updatepos(i, j)
- self.error("malformed start tag")
if j > i:
return j
else:
@@ -441,8 +356,6 @@
if self.cdata_elem is not None:
self.handle_data(rawdata[i:gtpos])
return gtpos
- if self.strict:
- self.error("bad end tag: %r" % (rawdata[i:gtpos],))
# find the name: w3.org/TR/html5/tokenization.html#tag-name-state
namematch = tagfind_tolerant.match(rawdata, i+2)
if not namematch:
@@ -508,8 +421,7 @@
pass
def unknown_decl(self, data):
- if self.strict:
- self.error("unknown declaration: %r" % (data,))
+ pass
# Internal -- helper to remove special character quoting
def unescape(self, s):
diff --git a/Lib/test/test_htmlparser.py b/Lib/test/test_htmlparser.py
--- a/Lib/test/test_htmlparser.py
+++ b/Lib/test/test_htmlparser.py
@@ -91,21 +91,11 @@
def _run_check_extra(self, source, events):
self._run_check(source, events, EventCollectorExtra())
- def _parse_error(self, source):
- def parse(source=source):
- parser = self.get_collector()
- parser.feed(source)
- parser.close()
- with self.assertRaises(html.parser.HTMLParseError):
- with self.assertWarns(DeprecationWarning):
- parse()
-
-class HTMLParserStrictTestCase(TestCaseBase):
+class HTMLParserTestCase(TestCaseBase):
def get_collector(self):
- with support.check_warnings(("", DeprecationWarning), quite=False):
- return EventCollector(strict=True)
+ return EventCollector()
def test_processing_instruction_only(self):
self._run_check("", [
@@ -181,9 +171,6 @@
("data", "this < text > contains < bare>pointy< brackets"),
])
- def test_illegal_declarations(self):
- self._parse_error('')
-
def test_starttag_end_boundary(self):
self._run_check("""""", [("starttag", "a", [("b", "<")])])
self._run_check("""""", [("starttag", "a", [("b", ">")])])
@@ -218,25 +205,6 @@
self._run_check(["", ""], output)
- def test_starttag_junk_chars(self):
- self._parse_error(">")
- self._parse_error("$>")
- self._parse_error("")
- self._parse_error("")
- self._parse_error("")
- self._parse_error("'")
- self._parse_error("" % dtd,
[('decl', 'DOCTYPE ' + dtd)])
- def test_declaration_junk_chars(self):
- self._parse_error("")
-
def test_startendtag(self):
self._run_check("", [
("startendtag", "p", []),
@@ -363,20 +328,8 @@
('comment', '[if lte IE 7]>pretty?te>>xt&a<