mirror of
https://github.com/Tautulli/Tautulli.git
synced 2025-07-05 12:45:47 -07:00
Bump beautifulsoup4 from 4.12.2 to 4.12.3 (#2267)
* Bump beautifulsoup4 from 4.12.2 to 4.12.3 Bumps [beautifulsoup4](https://www.crummy.com/software/BeautifulSoup/bs4/) from 4.12.2 to 4.12.3. --- updated-dependencies: - dependency-name: beautifulsoup4 dependency-type: direct:production update-type: version-update:semver-patch ... Signed-off-by: dependabot[bot] <support@github.com> * Update beautifulsoup4==4.12.3 --------- Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> Co-authored-by: JonnyWong16 <9099342+JonnyWong16@users.noreply.github.com> [skip ci]
This commit is contained in:
dependabot[bot]
GitHub
parent
faef9a94c4
commit
a0170a6f3d
25 changed files with 263 additions and 173 deletions
|
|
@ -15,8 +15,8 @@ documentation: http://www.crummy.com/software/BeautifulSoup/bs4/doc/
|
|||
"""
|
||||
|
||||
__author__ = "Leonard Richardson (leonardr@segfault.org)"
|
||||
__version__ = "4.12.2"
|
||||
__copyright__ = "Copyright (c) 2004-2023 Leonard Richardson"
|
||||
__version__ = "4.12.3"
|
||||
__copyright__ = "Copyright (c) 2004-2024 Leonard Richardson"
|
||||
# Use of this source code is governed by the MIT license.
|
||||
__license__ = "MIT"
|
||||
|
||||
|
|
|
|||
|
|
@ -514,15 +514,19 @@ class DetectsXMLParsedAsHTML(object):
|
|||
XML_PREFIX_B = b'<?xml'
|
||||
|
||||
@classmethod
|
||||
def warn_if_markup_looks_like_xml(cls, markup):
|
||||
def warn_if_markup_looks_like_xml(cls, markup, stacklevel=3):
|
||||
"""Perform a check on some markup to see if it looks like XML
|
||||
that's not XHTML. If so, issue a warning.
|
||||
|
||||
This is much less reliable than doing the check while parsing,
|
||||
but some of the tree builders can't do that.
|
||||
|
||||
:param stacklevel: The stacklevel of the code calling this
|
||||
function.
|
||||
|
||||
:return: True if the markup looks like non-XHTML XML, False
|
||||
otherwise.
|
||||
|
||||
"""
|
||||
if isinstance(markup, bytes):
|
||||
prefix = cls.XML_PREFIX_B
|
||||
|
|
@ -535,15 +539,16 @@ class DetectsXMLParsedAsHTML(object):
|
|||
and markup.startswith(prefix)
|
||||
and not looks_like_html.search(markup[:500])
|
||||
):
|
||||
cls._warn()
|
||||
cls._warn(stacklevel=stacklevel+2)
|
||||
return True
|
||||
return False
|
||||
|
||||
@classmethod
|
||||
def _warn(cls):
|
||||
def _warn(cls, stacklevel=5):
|
||||
"""Issue a warning about XML being parsed as HTML."""
|
||||
warnings.warn(
|
||||
XMLParsedAsHTMLWarning.MESSAGE, XMLParsedAsHTMLWarning
|
||||
XMLParsedAsHTMLWarning.MESSAGE, XMLParsedAsHTMLWarning,
|
||||
stacklevel=stacklevel
|
||||
)
|
||||
|
||||
def _initialize_xml_detector(self):
|
||||
|
|
|
|||
|
|
@ -77,7 +77,9 @@ class HTML5TreeBuilder(HTMLTreeBuilder):
|
|||
|
||||
# html5lib only parses HTML, so if it's given XML that's worth
|
||||
# noting.
|
||||
DetectsXMLParsedAsHTML.warn_if_markup_looks_like_xml(markup)
|
||||
DetectsXMLParsedAsHTML.warn_if_markup_looks_like_xml(
|
||||
markup, stacklevel=3
|
||||
)
|
||||
|
||||
yield (markup, None, None, False)
|
||||
|
||||
|
|
|
|||
|
|
@ -378,10 +378,10 @@ class HTMLParserTreeBuilder(HTMLTreeBuilder):
|
|||
parser.soup = self.soup
|
||||
try:
|
||||
parser.feed(markup)
|
||||
parser.close()
|
||||
except AssertionError as e:
|
||||
# html.parser raises AssertionError in rare cases to
|
||||
# indicate a fatal problem with the markup, especially
|
||||
# when there's an error in the doctype declaration.
|
||||
raise ParserRejectedMarkup(e)
|
||||
parser.close()
|
||||
parser.already_closed_empty_element = []
|
||||
|
|
|
|||
|
|
@ -179,7 +179,9 @@ class LXMLTreeBuilderForXML(TreeBuilder):
|
|||
self.processing_instruction_class = ProcessingInstruction
|
||||
# We're in HTML mode, so if we're given XML, that's worth
|
||||
# noting.
|
||||
DetectsXMLParsedAsHTML.warn_if_markup_looks_like_xml(markup)
|
||||
DetectsXMLParsedAsHTML.warn_if_markup_looks_like_xml(
|
||||
markup, stacklevel=3
|
||||
)
|
||||
else:
|
||||
self.processing_instruction_class = XMLProcessingInstruction
|
||||
|
||||
|
|
|
|||
|
|
@ -1356,7 +1356,7 @@ class Tag(PageElement):
|
|||
This is the first step in the deepcopy process.
|
||||
"""
|
||||
clone = type(self)(
|
||||
None, self.builder, self.name, self.namespace,
|
||||
None, None, self.name, self.namespace,
|
||||
self.prefix, self.attrs, is_xml=self._is_xml,
|
||||
sourceline=self.sourceline, sourcepos=self.sourcepos,
|
||||
can_be_empty_element=self.can_be_empty_element,
|
||||
|
|
@ -1845,6 +1845,11 @@ class Tag(PageElement):
|
|||
return space_before + s + space_after
|
||||
|
||||
def _format_tag(self, eventual_encoding, formatter, opening):
|
||||
if self.hidden:
|
||||
# A hidden tag is invisible, although its contents
|
||||
# are visible.
|
||||
return ''
|
||||
|
||||
# A tag starts with the < character (see below).
|
||||
|
||||
# Then the / character, if this is a closing tag.
|
||||
|
|
|
|||
|
|
@ -51,7 +51,7 @@ class Formatter(EntitySubstitution):
|
|||
void_element_close_prefix='/', cdata_containing_tags=None,
|
||||
empty_attributes_are_booleans=False, indent=1,
|
||||
):
|
||||
"""Constructor.
|
||||
r"""Constructor.
|
||||
|
||||
:param language: This should be Formatter.XML if you are formatting
|
||||
XML markup and Formatter.HTML if you are formatting HTML markup.
|
||||
|
|
@ -76,7 +76,7 @@ class Formatter(EntitySubstitution):
|
|||
negative, or "" will only insert newlines. Using a
|
||||
positive integer indent indents that many spaces per
|
||||
level. If indent is a string (such as "\t"), that string
|
||||
is used to indent each level. The default behavior to
|
||||
is used to indent each level. The default behavior is to
|
||||
indent one space per level.
|
||||
"""
|
||||
self.language = language
|
||||
|
|
|
|||
|
|
@ -1105,7 +1105,7 @@ class XMLTreeBuilderSmokeTest(TreeBuilderSmokeTest):
|
|||
doc = """<?xml version="1.0" encoding="utf-8"?>
|
||||
<Document xmlns="http://example.com/ns0"
|
||||
xmlns:ns1="http://example.com/ns1"
|
||||
xmlns:ns2="http://example.com/ns2"
|
||||
xmlns:ns2="http://example.com/ns2">
|
||||
<ns1:tag>foo</ns1:tag>
|
||||
<ns1:tag>bar</ns1:tag>
|
||||
<ns2:tag key="value">baz</ns2:tag>
|
||||
|
|
|
|||
|
|
@ -0,0 +1 @@
|
|||
<20><> <20> <css
|
||||
Binary file not shown.
Binary file not shown.
|
|
@ -0,0 +1 @@
|
|||
˙ ><applet></applet><applet></applet><apple|><applet><applet><appl›„><applet><applet></applet></applet></applet></applet><applet></applet><apple>t<applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet>et><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><azplet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><plet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet><applet></applet></applet></applet></applet></appt></applet></applet></applet></applet></applet></applet></applet></applet></applet></applet></applet></applet></applet></applet></applet></applet></applet></applet><<meta charset=utf-8>
|
||||
Binary file not shown.
|
|
@ -0,0 +1 @@
|
|||
- ˙˙ <math><select><mi><select><select>t
|
||||
Binary file not shown.
|
|
@ -14,30 +14,75 @@ from bs4 import (
|
|||
BeautifulSoup,
|
||||
ParserRejectedMarkup,
|
||||
)
|
||||
try:
|
||||
from soupsieve.util import SelectorSyntaxError
|
||||
import lxml
|
||||
import html5lib
|
||||
fully_fuzzable = True
|
||||
except ImportError:
|
||||
fully_fuzzable = False
|
||||
|
||||
|
||||
@pytest.mark.skipif(not fully_fuzzable, reason="Prerequisites for fuzz tests are not installed.")
|
||||
class TestFuzz(object):
|
||||
|
||||
# Test case markup files from fuzzers are given this extension so
|
||||
# they can be included in builds.
|
||||
TESTCASE_SUFFIX = ".testcase"
|
||||
|
||||
# Copied 20230512 from
|
||||
# https://github.com/google/oss-fuzz/blob/4ac6a645a197a695fe76532251feb5067076b3f3/projects/bs4/bs4_fuzzer.py
|
||||
#
|
||||
# Copying the code lets us precisely duplicate the behavior of
|
||||
# oss-fuzz. The downside is that this code changes over time, so
|
||||
# multiple copies of the code must be kept around to run against
|
||||
# older tests. I'm not sure what to do about this, but I may
|
||||
# retire old tests after a time.
|
||||
def fuzz_test_with_css(self, filename):
|
||||
data = self.__markup(filename)
|
||||
parsers = ['lxml-xml', 'html5lib', 'html.parser', 'lxml']
|
||||
try:
|
||||
idx = int(data[0]) % len(parsers)
|
||||
except ValueError:
|
||||
return
|
||||
|
||||
css_selector, data = data[1:10], data[10:]
|
||||
|
||||
try:
|
||||
soup = BeautifulSoup(data[1:], features=parsers[idx])
|
||||
except ParserRejectedMarkup:
|
||||
return
|
||||
except ValueError:
|
||||
return
|
||||
|
||||
list(soup.find_all(True))
|
||||
try:
|
||||
soup.css.select(css_selector.decode('utf-8', 'replace'))
|
||||
except SelectorSyntaxError:
|
||||
return
|
||||
soup.prettify()
|
||||
|
||||
# This class of error has been fixed by catching a less helpful
|
||||
# exception from html.parser and raising ParserRejectedMarkup
|
||||
# instead.
|
||||
@pytest.mark.parametrize(
|
||||
"filename", [
|
||||
"clusterfuzz-testcase-minimized-bs4_fuzzer-5703933063462912",
|
||||
"crash-ffbdfa8a2b26f13537b68d3794b0478a4090ee4a",
|
||||
]
|
||||
)
|
||||
def test_rejected_markup(self, filename):
|
||||
markup = self.__markup(filename)
|
||||
with pytest.raises(ParserRejectedMarkup):
|
||||
BeautifulSoup(markup, 'html.parser')
|
||||
|
||||
|
||||
# This class of error has to do with very deeply nested documents
|
||||
# which overflow the Python call stack when the tree is converted
|
||||
# to a string. This is an issue with Beautiful Soup which was fixed
|
||||
# as part of [bug=1471755].
|
||||
#
|
||||
# These test cases are in the older format that doesn't specify
|
||||
# which parser to use or give a CSS selector.
|
||||
@pytest.mark.parametrize(
|
||||
"filename", [
|
||||
"clusterfuzz-testcase-minimized-bs4_fuzzer-5984173902397440",
|
||||
|
|
@ -46,18 +91,44 @@ class TestFuzz(object):
|
|||
"clusterfuzz-testcase-minimized-bs4_fuzzer-6450958476902400",
|
||||
]
|
||||
)
|
||||
def test_deeply_nested_document(self, filename):
|
||||
def test_deeply_nested_document_without_css(self, filename):
|
||||
# Parsing the document and encoding it back to a string is
|
||||
# sufficient to demonstrate that the overflow problem has
|
||||
# been fixed.
|
||||
markup = self.__markup(filename)
|
||||
BeautifulSoup(markup, 'html.parser').encode()
|
||||
|
||||
# This class of error has to do with very deeply nested documents
|
||||
# which overflow the Python call stack when the tree is converted
|
||||
# to a string. This is an issue with Beautiful Soup which was fixed
|
||||
# as part of [bug=1471755].
|
||||
@pytest.mark.parametrize(
|
||||
"filename", [
|
||||
"clusterfuzz-testcase-minimized-bs4_fuzzer-5000587759190016",
|
||||
"clusterfuzz-testcase-minimized-bs4_fuzzer-5375146639360000",
|
||||
"clusterfuzz-testcase-minimized-bs4_fuzzer-5492400320282624",
|
||||
]
|
||||
)
|
||||
def test_deeply_nested_document(self, filename):
|
||||
self.fuzz_test_with_css(filename)
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"filename", [
|
||||
"clusterfuzz-testcase-minimized-bs4_fuzzer-4670634698080256",
|
||||
"clusterfuzz-testcase-minimized-bs4_fuzzer-5270998950477824",
|
||||
]
|
||||
)
|
||||
def test_soupsieve_errors(self, filename):
|
||||
self.fuzz_test_with_css(filename)
|
||||
|
||||
# This class of error represents problems with html5lib's parser,
|
||||
# not Beautiful Soup. I use
|
||||
# https://github.com/html5lib/html5lib-python/issues/568 to notify
|
||||
# the html5lib developers of these issues.
|
||||
@pytest.mark.skip("html5lib problems")
|
||||
#
|
||||
# These test cases are in the older format that doesn't specify
|
||||
# which parser to use or give a CSS selector.
|
||||
@pytest.mark.skip(reason="html5lib-specific problems")
|
||||
@pytest.mark.parametrize(
|
||||
"filename", [
|
||||
# b"""ÿ<!DOCTyPEV PUBLIC'''Ð'"""
|
||||
|
|
@ -68,7 +139,7 @@ class TestFuzz(object):
|
|||
|
||||
# b'-<math><sElect><mi><sElect><sElect>'
|
||||
"clusterfuzz-testcase-minimized-bs4_fuzzer-5843991618256896",
|
||||
|
||||
|
||||
# b'ñ<table><svg><html>'
|
||||
"clusterfuzz-testcase-minimized-bs4_fuzzer-6241471367348224",
|
||||
|
||||
|
|
@ -79,10 +150,24 @@ class TestFuzz(object):
|
|||
"crash-0d306a50c8ed8bcd0785b67000fcd5dea1d33f08"
|
||||
]
|
||||
)
|
||||
def test_html5lib_parse_errors(self, filename):
|
||||
def test_html5lib_parse_errors_without_css(self, filename):
|
||||
markup = self.__markup(filename)
|
||||
print(BeautifulSoup(markup, 'html5lib').encode())
|
||||
|
||||
# This class of error represents problems with html5lib's parser,
|
||||
# not Beautiful Soup. I use
|
||||
# https://github.com/html5lib/html5lib-python/issues/568 to notify
|
||||
# the html5lib developers of these issues.
|
||||
@pytest.mark.skip(reason="html5lib-specific problems")
|
||||
@pytest.mark.parametrize(
|
||||
"filename", [
|
||||
# b'- \xff\xff <math>\x10<select><mi><select><select>t'
|
||||
"clusterfuzz-testcase-minimized-bs4_fuzzer-6306874195312640",
|
||||
]
|
||||
)
|
||||
def test_html5lib_parse_errors(self, filename):
|
||||
self.fuzz_test_with_css(filename)
|
||||
|
||||
def __markup(self, filename):
|
||||
if not filename.endswith(self.TESTCASE_SUFFIX):
|
||||
filename += self.TESTCASE_SUFFIX
|
||||
|
|
|
|||
|
|
@ -219,3 +219,16 @@ class TestMultiValuedAttributes(SoupTest):
|
|||
)
|
||||
assert soup.a['class'] == 'foo'
|
||||
assert soup.a['id'] == ['bar']
|
||||
|
||||
def test_hidden_tag_is_invisible(self):
|
||||
# Setting .hidden on a tag makes it invisible in output, but
|
||||
# leaves its contents visible.
|
||||
#
|
||||
# This is not a documented or supported feature of Beautiful
|
||||
# Soup (e.g. NavigableString doesn't support .hidden even
|
||||
# though it could), but some people use it and it's not
|
||||
# hurting anything to verify that it keeps working.
|
||||
#
|
||||
soup = self.soup('<div id="1"><span id="2">a string</span></div>')
|
||||
soup.span.hidden = True
|
||||
assert '<div id="1">a string</div>' == str(soup.div)
|
||||
|
|
|
|||
|
|
@ -78,13 +78,13 @@ def purge() -> None:
|
|||
|
||||
def closest(
|
||||
select: str,
|
||||
tag: 'bs4.Tag',
|
||||
tag: bs4.Tag,
|
||||
namespaces: dict[str, str] | None = None,
|
||||
flags: int = 0,
|
||||
*,
|
||||
custom: dict[str, str] | None = None,
|
||||
**kwargs: Any
|
||||
) -> 'bs4.Tag':
|
||||
) -> bs4.Tag:
|
||||
"""Match closest ancestor."""
|
||||
|
||||
return compile(select, namespaces, flags, **kwargs).closest(tag)
|
||||
|
|
@ -92,7 +92,7 @@ def closest(
|
|||
|
||||
def match(
|
||||
select: str,
|
||||
tag: 'bs4.Tag',
|
||||
tag: bs4.Tag,
|
||||
namespaces: dict[str, str] | None = None,
|
||||
flags: int = 0,
|
||||
*,
|
||||
|
|
@ -106,13 +106,13 @@ def match(
|
|||
|
||||
def filter( # noqa: A001
|
||||
select: str,
|
||||
iterable: Iterable['bs4.Tag'],
|
||||
iterable: Iterable[bs4.Tag],
|
||||
namespaces: dict[str, str] | None = None,
|
||||
flags: int = 0,
|
||||
*,
|
||||
custom: dict[str, str] | None = None,
|
||||
**kwargs: Any
|
||||
) -> list['bs4.Tag']:
|
||||
) -> list[bs4.Tag]:
|
||||
"""Filter list of nodes."""
|
||||
|
||||
return compile(select, namespaces, flags, **kwargs).filter(iterable)
|
||||
|
|
@ -120,13 +120,13 @@ def filter( # noqa: A001
|
|||
|
||||
def select_one(
|
||||
select: str,
|
||||
tag: 'bs4.Tag',
|
||||
tag: bs4.Tag,
|
||||
namespaces: dict[str, str] | None = None,
|
||||
flags: int = 0,
|
||||
*,
|
||||
custom: dict[str, str] | None = None,
|
||||
**kwargs: Any
|
||||
) -> 'bs4.Tag':
|
||||
) -> bs4.Tag:
|
||||
"""Select a single tag."""
|
||||
|
||||
return compile(select, namespaces, flags, **kwargs).select_one(tag)
|
||||
|
|
@ -134,14 +134,14 @@ def select_one(
|
|||
|
||||
def select(
|
||||
select: str,
|
||||
tag: 'bs4.Tag',
|
||||
tag: bs4.Tag,
|
||||
namespaces: dict[str, str] | None = None,
|
||||
limit: int = 0,
|
||||
flags: int = 0,
|
||||
*,
|
||||
custom: dict[str, str] | None = None,
|
||||
**kwargs: Any
|
||||
) -> list['bs4.Tag']:
|
||||
) -> list[bs4.Tag]:
|
||||
"""Select the specified tags."""
|
||||
|
||||
return compile(select, namespaces, flags, **kwargs).select(tag, limit)
|
||||
|
|
@ -149,18 +149,17 @@ def select(
|
|||
|
||||
def iselect(
|
||||
select: str,
|
||||
tag: 'bs4.Tag',
|
||||
tag: bs4.Tag,
|
||||
namespaces: dict[str, str] | None = None,
|
||||
limit: int = 0,
|
||||
flags: int = 0,
|
||||
*,
|
||||
custom: dict[str, str] | None = None,
|
||||
**kwargs: Any
|
||||
) -> Iterator['bs4.Tag']:
|
||||
) -> Iterator[bs4.Tag]:
|
||||
"""Iterate the specified tags."""
|
||||
|
||||
for el in compile(select, namespaces, flags, **kwargs).iselect(tag, limit):
|
||||
yield el
|
||||
yield from compile(select, namespaces, flags, **kwargs).iselect(tag, limit)
|
||||
|
||||
|
||||
def escape(ident: str) -> str:
|
||||
|
|
|
|||
|
|
@ -93,7 +93,7 @@ class Version(namedtuple("Version", ["major", "minor", "micro", "release", "pre"
|
|||
raise ValueError("All version parts except 'release' should be integers.")
|
||||
|
||||
if release not in REL_MAP:
|
||||
raise ValueError("'{}' is not a valid release type.".format(release))
|
||||
raise ValueError(f"'{release}' is not a valid release type.")
|
||||
|
||||
# Ensure valid pre-release (we do not allow implicit pre-releases).
|
||||
if ".dev-candidate" < release < "final":
|
||||
|
|
@ -118,7 +118,7 @@ class Version(namedtuple("Version", ["major", "minor", "micro", "release", "pre"
|
|||
elif dev:
|
||||
raise ValueError("Version is not a development release.")
|
||||
|
||||
return super(Version, cls).__new__(cls, major, minor, micro, release, pre, post, dev)
|
||||
return super().__new__(cls, major, minor, micro, release, pre, post, dev)
|
||||
|
||||
def _is_pre(self) -> bool:
|
||||
"""Is prerelease."""
|
||||
|
|
@ -145,15 +145,15 @@ class Version(namedtuple("Version", ["major", "minor", "micro", "release", "pre"
|
|||
|
||||
# Assemble major, minor, micro version and append `pre`, `post`, or `dev` if needed..
|
||||
if self.micro == 0:
|
||||
ver = "{}.{}".format(self.major, self.minor)
|
||||
ver = f"{self.major}.{self.minor}"
|
||||
else:
|
||||
ver = "{}.{}.{}".format(self.major, self.minor, self.micro)
|
||||
ver = f"{self.major}.{self.minor}.{self.micro}"
|
||||
if self._is_pre():
|
||||
ver += '{}{}'.format(REL_MAP[self.release], self.pre)
|
||||
ver += f'{REL_MAP[self.release]}{self.pre}'
|
||||
if self._is_post():
|
||||
ver += ".post{}".format(self.post)
|
||||
ver += f".post{self.post}"
|
||||
if self._is_dev():
|
||||
ver += ".dev{}".format(self.dev)
|
||||
ver += f".dev{self.dev}"
|
||||
|
||||
return ver
|
||||
|
||||
|
|
@ -164,7 +164,7 @@ def parse_version(ver: str) -> Version:
|
|||
m = RE_VER.match(ver)
|
||||
|
||||
if m is None:
|
||||
raise ValueError("'{}' is not a valid version".format(ver))
|
||||
raise ValueError(f"'{ver}' is not a valid version")
|
||||
|
||||
# Handle major, minor, micro
|
||||
major = int(m.group('major'))
|
||||
|
|
@ -193,5 +193,5 @@ def parse_version(ver: str) -> Version:
|
|||
return Version(major, minor, micro, release, pre, post, dev)
|
||||
|
||||
|
||||
__version_info__ = Version(2, 4, 1, "final")
|
||||
__version_info__ = Version(2, 5, 0, "final")
|
||||
__version__ = __version_info__._get_canonical()
|
||||
|
|
|
|||
|
|
@ -85,7 +85,7 @@ class _DocumentNav:
|
|||
|
||||
# Fail on unexpected types.
|
||||
if not cls.is_tag(tag):
|
||||
raise TypeError("Expected a BeautifulSoup 'Tag', but instead received type {}".format(type(tag)))
|
||||
raise TypeError(f"Expected a BeautifulSoup 'Tag', but instead received type {type(tag)}")
|
||||
|
||||
@staticmethod
|
||||
def is_doc(obj: bs4.Tag) -> bool:
|
||||
|
|
@ -165,8 +165,7 @@ class _DocumentNav:
|
|||
def get_contents(self, el: bs4.Tag, no_iframe: bool = False) -> Iterator[bs4.PageElement]:
|
||||
"""Get contents or contents in reverse."""
|
||||
if not no_iframe or not self.is_iframe(el):
|
||||
for content in el.contents:
|
||||
yield content
|
||||
yield from el.contents
|
||||
|
||||
def get_children(
|
||||
self,
|
||||
|
|
@ -283,7 +282,7 @@ class _DocumentNav:
|
|||
like we do in the case of `is_html_tag`.
|
||||
"""
|
||||
|
||||
ns = getattr(el, 'namespace') if el else None
|
||||
ns = getattr(el, 'namespace') if el else None # noqa: B009
|
||||
return bool(ns and ns == NS_XHTML)
|
||||
|
||||
@staticmethod
|
||||
|
|
@ -394,7 +393,7 @@ class Inputs:
|
|||
def validate_week(year: int, week: int) -> bool:
|
||||
"""Validate week."""
|
||||
|
||||
max_week = datetime.strptime("{}-{}-{}".format(12, 31, year), "%m-%d-%Y").isocalendar()[1]
|
||||
max_week = datetime.strptime(f"{12}-{31}-{year}", "%m-%d-%Y").isocalendar()[1]
|
||||
if max_week == 1:
|
||||
max_week = 53
|
||||
return 1 <= week <= max_week
|
||||
|
|
@ -1272,11 +1271,7 @@ class CSSMatch(_DocumentNav):
|
|||
# Auto handling for text inputs
|
||||
if ((is_input and itype in ('text', 'search', 'tel', 'url', 'email')) or is_textarea) and direction == 0:
|
||||
if is_textarea:
|
||||
temp = []
|
||||
for node in self.get_contents(el, no_iframe=True):
|
||||
if self.is_content_string(node):
|
||||
temp.append(node)
|
||||
value = ''.join(temp)
|
||||
value = ''.join(node for node in self.get_contents(el, no_iframe=True) if self.is_content_string(node))
|
||||
else:
|
||||
value = cast(str, self.get_attribute_by_name(el, 'value', ''))
|
||||
if value:
|
||||
|
|
@ -1571,17 +1566,14 @@ class SoupSieve(ct.Immutable):
|
|||
def iselect(self, tag: bs4.Tag, limit: int = 0) -> Iterator[bs4.Tag]:
|
||||
"""Iterate the specified tags."""
|
||||
|
||||
for el in CSSMatch(self.selectors, tag, self.namespaces, self.flags).select(limit):
|
||||
yield el
|
||||
yield from CSSMatch(self.selectors, tag, self.namespaces, self.flags).select(limit)
|
||||
|
||||
def __repr__(self) -> str: # pragma: no cover
|
||||
"""Representation."""
|
||||
|
||||
return "SoupSieve(pattern={!r}, namespaces={!r}, custom={!r}, flags={!r})".format(
|
||||
self.pattern,
|
||||
self.namespaces,
|
||||
self.custom,
|
||||
self.flags
|
||||
return (
|
||||
f"SoupSieve(pattern={self.pattern!r}, namespaces={self.namespaces!r}, "
|
||||
f"custom={self.custom!r}, flags={self.flags!r})"
|
||||
)
|
||||
|
||||
__str__ = __repr__
|
||||
|
|
|
|||
|
|
@ -92,94 +92,79 @@ PSEUDO_SUPPORTED = PSEUDO_SIMPLE | PSEUDO_SIMPLE_NO_MATCH | PSEUDO_COMPLEX | PSE
|
|||
# Sub-patterns parts
|
||||
# Whitespace
|
||||
NEWLINE = r'(?:\r\n|(?!\r\n)[\n\f\r])'
|
||||
WS = r'(?:[ \t]|{})'.format(NEWLINE)
|
||||
WS = fr'(?:[ \t]|{NEWLINE})'
|
||||
# Comments
|
||||
COMMENTS = r'(?:/\*[^*]*\*+(?:[^/*][^*]*\*+)*/)'
|
||||
# Whitespace with comments included
|
||||
WSC = r'(?:{ws}|{comments})'.format(ws=WS, comments=COMMENTS)
|
||||
WSC = fr'(?:{WS}|{COMMENTS})'
|
||||
# CSS escapes
|
||||
CSS_ESCAPES = r'(?:\\(?:[a-f0-9]{{1,6}}{ws}?|[^\r\n\f]|$))'.format(ws=WS)
|
||||
CSS_STRING_ESCAPES = r'(?:\\(?:[a-f0-9]{{1,6}}{ws}?|[^\r\n\f]|$|{nl}))'.format(ws=WS, nl=NEWLINE)
|
||||
CSS_ESCAPES = fr'(?:\\(?:[a-f0-9]{{1,6}}{WS}?|[^\r\n\f]|$))'
|
||||
CSS_STRING_ESCAPES = fr'(?:\\(?:[a-f0-9]{{1,6}}{WS}?|[^\r\n\f]|$|{NEWLINE}))'
|
||||
# CSS Identifier
|
||||
IDENTIFIER = r'''
|
||||
(?:(?:-?(?:[^\x00-\x2f\x30-\x40\x5B-\x5E\x60\x7B-\x9f]|{esc})+|--)
|
||||
(?:[^\x00-\x2c\x2e\x2f\x3A-\x40\x5B-\x5E\x60\x7B-\x9f]|{esc})*)
|
||||
'''.format(esc=CSS_ESCAPES)
|
||||
IDENTIFIER = fr'''
|
||||
(?:(?:-?(?:[^\x00-\x2f\x30-\x40\x5B-\x5E\x60\x7B-\x9f]|{CSS_ESCAPES})+|--)
|
||||
(?:[^\x00-\x2c\x2e\x2f\x3A-\x40\x5B-\x5E\x60\x7B-\x9f]|{CSS_ESCAPES})*)
|
||||
'''
|
||||
# `nth` content
|
||||
NTH = r'(?:[-+])?(?:[0-9]+n?|n)(?:(?<=n){ws}*(?:[-+]){ws}*(?:[0-9]+))?'.format(ws=WSC)
|
||||
NTH = fr'(?:[-+])?(?:[0-9]+n?|n)(?:(?<=n){WSC}*(?:[-+]){WSC}*(?:[0-9]+))?'
|
||||
# Value: quoted string or identifier
|
||||
VALUE = r'''
|
||||
(?:"(?:\\(?:.|{nl})|[^\\"\r\n\f]+)*?"|'(?:\\(?:.|{nl})|[^\\'\r\n\f]+)*?'|{ident}+)
|
||||
'''.format(nl=NEWLINE, ident=IDENTIFIER)
|
||||
VALUE = fr'''(?:"(?:\\(?:.|{NEWLINE})|[^\\"\r\n\f]+)*?"|'(?:\\(?:.|{NEWLINE})|[^\\'\r\n\f]+)*?'|{IDENTIFIER}+)'''
|
||||
# Attribute value comparison. `!=` is handled special as it is non-standard.
|
||||
ATTR = r'''
|
||||
(?:{ws}*(?P<cmp>[!~^|*$]?=){ws}*(?P<value>{value})(?:{ws}*(?P<case>[is]))?)?{ws}*\]
|
||||
'''.format(ws=WSC, value=VALUE)
|
||||
ATTR = fr'(?:{WSC}*(?P<cmp>[!~^|*$]?=){WSC}*(?P<value>{VALUE})(?:{WSC}*(?P<case>[is]))?)?{WSC}*\]'
|
||||
|
||||
# Selector patterns
|
||||
# IDs (`#id`)
|
||||
PAT_ID = r'\#{ident}'.format(ident=IDENTIFIER)
|
||||
PAT_ID = fr'\#{IDENTIFIER}'
|
||||
# Classes (`.class`)
|
||||
PAT_CLASS = r'\.{ident}'.format(ident=IDENTIFIER)
|
||||
PAT_CLASS = fr'\.{IDENTIFIER}'
|
||||
# Prefix:Tag (`prefix|tag`)
|
||||
PAT_TAG = r'(?P<tag_ns>(?:{ident}|\*)?\|)?(?P<tag_name>{ident}|\*)'.format(ident=IDENTIFIER)
|
||||
PAT_TAG = fr'(?P<tag_ns>(?:{IDENTIFIER}|\*)?\|)?(?P<tag_name>{IDENTIFIER}|\*)'
|
||||
# Attributes (`[attr]`, `[attr=value]`, etc.)
|
||||
PAT_ATTR = r'''
|
||||
\[{ws}*(?P<attr_ns>(?:{ident}|\*)?\|)?(?P<attr_name>{ident}){attr}
|
||||
'''.format(ws=WSC, ident=IDENTIFIER, attr=ATTR)
|
||||
PAT_ATTR = fr'\[{WSC}*(?P<attr_ns>(?:{IDENTIFIER}|\*)?\|)?(?P<attr_name>{IDENTIFIER}){ATTR}'
|
||||
# Pseudo class (`:pseudo-class`, `:pseudo-class(`)
|
||||
PAT_PSEUDO_CLASS = r'(?P<name>:{ident})(?P<open>\({ws}*)?'.format(ws=WSC, ident=IDENTIFIER)
|
||||
PAT_PSEUDO_CLASS = fr'(?P<name>:{IDENTIFIER})(?P<open>\({WSC}*)?'
|
||||
# Pseudo class special patterns. Matches `:pseudo-class(` for special case pseudo classes.
|
||||
PAT_PSEUDO_CLASS_SPECIAL = r'(?P<name>:{ident})(?P<open>\({ws}*)'.format(ws=WSC, ident=IDENTIFIER)
|
||||
PAT_PSEUDO_CLASS_SPECIAL = fr'(?P<name>:{IDENTIFIER})(?P<open>\({WSC}*)'
|
||||
# Custom pseudo class (`:--custom-pseudo`)
|
||||
PAT_PSEUDO_CLASS_CUSTOM = r'(?P<name>:(?=--){ident})'.format(ident=IDENTIFIER)
|
||||
PAT_PSEUDO_CLASS_CUSTOM = fr'(?P<name>:(?=--){IDENTIFIER})'
|
||||
# Closing pseudo group (`)`)
|
||||
PAT_PSEUDO_CLOSE = r'{ws}*\)'.format(ws=WSC)
|
||||
PAT_PSEUDO_CLOSE = fr'{WSC}*\)'
|
||||
# Pseudo element (`::pseudo-element`)
|
||||
PAT_PSEUDO_ELEMENT = r':{}'.format(PAT_PSEUDO_CLASS)
|
||||
PAT_PSEUDO_ELEMENT = fr':{PAT_PSEUDO_CLASS}'
|
||||
# At rule (`@page`, etc.) (not supported)
|
||||
PAT_AT_RULE = r'@P{ident}'.format(ident=IDENTIFIER)
|
||||
PAT_AT_RULE = fr'@P{IDENTIFIER}'
|
||||
# Pseudo class `nth-child` (`:nth-child(an+b [of S]?)`, `:first-child`, etc.)
|
||||
PAT_PSEUDO_NTH_CHILD = r'''
|
||||
(?P<pseudo_nth_child>{name}
|
||||
(?P<nth_child>{nth}|even|odd))(?:{wsc}*\)|(?P<of>{comments}*{ws}{wsc}*of{comments}*{ws}{wsc}*))
|
||||
'''.format(name=PAT_PSEUDO_CLASS_SPECIAL, wsc=WSC, comments=COMMENTS, ws=WS, nth=NTH)
|
||||
PAT_PSEUDO_NTH_CHILD = fr'''
|
||||
(?P<pseudo_nth_child>{PAT_PSEUDO_CLASS_SPECIAL}
|
||||
(?P<nth_child>{NTH}|even|odd))(?:{WSC}*\)|(?P<of>{COMMENTS}*{WS}{WSC}*of{COMMENTS}*{WS}{WSC}*))
|
||||
'''
|
||||
# Pseudo class `nth-of-type` (`:nth-of-type(an+b)`, `:first-of-type`, etc.)
|
||||
PAT_PSEUDO_NTH_TYPE = r'''
|
||||
(?P<pseudo_nth_type>{name}
|
||||
(?P<nth_type>{nth}|even|odd)){ws}*\)
|
||||
'''.format(name=PAT_PSEUDO_CLASS_SPECIAL, ws=WSC, nth=NTH)
|
||||
PAT_PSEUDO_NTH_TYPE = fr'''
|
||||
(?P<pseudo_nth_type>{PAT_PSEUDO_CLASS_SPECIAL}
|
||||
(?P<nth_type>{NTH}|even|odd)){WSC}*\)
|
||||
'''
|
||||
# Pseudo class language (`:lang("*-de", en)`)
|
||||
PAT_PSEUDO_LANG = r'{name}(?P<values>{value}(?:{ws}*,{ws}*{value})*){ws}*\)'.format(
|
||||
name=PAT_PSEUDO_CLASS_SPECIAL, ws=WSC, value=VALUE
|
||||
)
|
||||
PAT_PSEUDO_LANG = fr'{PAT_PSEUDO_CLASS_SPECIAL}(?P<values>{VALUE}(?:{WSC}*,{WSC}*{VALUE})*){WSC}*\)'
|
||||
# Pseudo class direction (`:dir(ltr)`)
|
||||
PAT_PSEUDO_DIR = r'{name}(?P<dir>ltr|rtl){ws}*\)'.format(name=PAT_PSEUDO_CLASS_SPECIAL, ws=WSC)
|
||||
PAT_PSEUDO_DIR = fr'{PAT_PSEUDO_CLASS_SPECIAL}(?P<dir>ltr|rtl){WSC}*\)'
|
||||
# Combining characters (`>`, `~`, ` `, `+`, `,`)
|
||||
PAT_COMBINE = r'{wsc}*?(?P<relation>[,+>~]|{ws}(?![,+>~])){wsc}*'.format(ws=WS, wsc=WSC)
|
||||
PAT_COMBINE = fr'{WSC}*?(?P<relation>[,+>~]|{WS}(?![,+>~])){WSC}*'
|
||||
# Extra: Contains (`:contains(text)`)
|
||||
PAT_PSEUDO_CONTAINS = r'{name}(?P<values>{value}(?:{ws}*,{ws}*{value})*){ws}*\)'.format(
|
||||
name=PAT_PSEUDO_CLASS_SPECIAL, ws=WSC, value=VALUE
|
||||
)
|
||||
PAT_PSEUDO_CONTAINS = fr'{PAT_PSEUDO_CLASS_SPECIAL}(?P<values>{VALUE}(?:{WSC}*,{WSC}*{VALUE})*){WSC}*\)'
|
||||
|
||||
# Regular expressions
|
||||
# CSS escape pattern
|
||||
RE_CSS_ESC = re.compile(r'(?:(\\[a-f0-9]{{1,6}}{ws}?)|(\\[^\r\n\f])|(\\$))'.format(ws=WSC), re.I)
|
||||
RE_CSS_STR_ESC = re.compile(
|
||||
r'(?:(\\[a-f0-9]{{1,6}}{ws}?)|(\\[^\r\n\f])|(\\$)|(\\{nl}))'.format(ws=WS, nl=NEWLINE), re.I
|
||||
)
|
||||
RE_CSS_ESC = re.compile(fr'(?:(\\[a-f0-9]{{1,6}}{WSC}?)|(\\[^\r\n\f])|(\\$))', re.I)
|
||||
RE_CSS_STR_ESC = re.compile(fr'(?:(\\[a-f0-9]{{1,6}}{WS}?)|(\\[^\r\n\f])|(\\$)|(\\{NEWLINE}))', re.I)
|
||||
# Pattern to break up `nth` specifiers
|
||||
RE_NTH = re.compile(
|
||||
r'(?P<s1>[-+])?(?P<a>[0-9]+n?|n)(?:(?<=n){ws}*(?P<s2>[-+]){ws}*(?P<b>[0-9]+))?'.format(ws=WSC),
|
||||
re.I
|
||||
)
|
||||
RE_NTH = re.compile(fr'(?P<s1>[-+])?(?P<a>[0-9]+n?|n)(?:(?<=n){WSC}*(?P<s2>[-+]){WSC}*(?P<b>[0-9]+))?', re.I)
|
||||
# Pattern to iterate multiple values.
|
||||
RE_VALUES = re.compile(r'(?:(?P<value>{value})|(?P<split>{ws}*,{ws}*))'.format(ws=WSC, value=VALUE), re.X)
|
||||
RE_VALUES = re.compile(fr'(?:(?P<value>{VALUE})|(?P<split>{WSC}*,{WSC}*))', re.X)
|
||||
# Whitespace checks
|
||||
RE_WS = re.compile(WS)
|
||||
RE_WS_BEGIN = re.compile('^{}*'.format(WSC))
|
||||
RE_WS_END = re.compile('{}*$'.format(WSC))
|
||||
RE_CUSTOM = re.compile(r'^{}$'.format(PAT_PSEUDO_CLASS_CUSTOM), re.X)
|
||||
RE_WS_BEGIN = re.compile(fr'^{WSC}*')
|
||||
RE_WS_END = re.compile(fr'{WSC}*$')
|
||||
RE_CUSTOM = re.compile(fr'^{PAT_PSEUDO_CLASS_CUSTOM}$', re.X)
|
||||
|
||||
# Constants
|
||||
# List split token
|
||||
|
|
@ -241,9 +226,9 @@ def process_custom(custom: ct.CustomSelectors | None) -> dict[str, str | ct.Sele
|
|||
for key, value in custom.items():
|
||||
name = util.lower(key)
|
||||
if RE_CUSTOM.match(name) is None:
|
||||
raise SelectorSyntaxError("The name '{}' is not a valid custom pseudo-class name".format(name))
|
||||
raise SelectorSyntaxError(f"The name '{name}' is not a valid custom pseudo-class name")
|
||||
if name in custom_selectors:
|
||||
raise KeyError("The custom selector '{}' has already been registered".format(name))
|
||||
raise KeyError(f"The custom selector '{name}' has already been registered")
|
||||
custom_selectors[css_unescape(name)] = value
|
||||
return custom_selectors
|
||||
|
||||
|
|
@ -283,23 +268,23 @@ def escape(ident: str) -> str:
|
|||
start_dash = length > 0 and ident[0] == '-'
|
||||
if length == 1 and start_dash:
|
||||
# Need to escape identifier that is a single `-` with no other characters
|
||||
string.append('\\{}'.format(ident))
|
||||
string.append(f'\\{ident}')
|
||||
else:
|
||||
for index, c in enumerate(ident):
|
||||
codepoint = ord(c)
|
||||
if codepoint == 0x00:
|
||||
string.append('\ufffd')
|
||||
elif (0x01 <= codepoint <= 0x1F) or codepoint == 0x7F:
|
||||
string.append('\\{:x} '.format(codepoint))
|
||||
string.append(f'\\{codepoint:x} ')
|
||||
elif (index == 0 or (start_dash and index == 1)) and (0x30 <= codepoint <= 0x39):
|
||||
string.append('\\{:x} '.format(codepoint))
|
||||
string.append(f'\\{codepoint:x} ')
|
||||
elif (
|
||||
codepoint in (0x2D, 0x5F) or codepoint >= 0x80 or (0x30 <= codepoint <= 0x39) or
|
||||
(0x30 <= codepoint <= 0x39) or (0x41 <= codepoint <= 0x5A) or (0x61 <= codepoint <= 0x7A)
|
||||
):
|
||||
string.append(c)
|
||||
else:
|
||||
string.append('\\{}'.format(c))
|
||||
string.append(f'\\{c}')
|
||||
return ''.join(string)
|
||||
|
||||
|
||||
|
|
@ -419,11 +404,10 @@ class _Selector:
|
|||
"""String representation."""
|
||||
|
||||
return (
|
||||
'_Selector(tag={!r}, ids={!r}, classes={!r}, attributes={!r}, nth={!r}, selectors={!r}, '
|
||||
'relations={!r}, rel_type={!r}, contains={!r}, lang={!r}, flags={!r}, no_match={!r})'
|
||||
).format(
|
||||
self.tag, self.ids, self.classes, self.attributes, self.nth, self.selectors,
|
||||
self.relations, self.rel_type, self.contains, self.lang, self.flags, self.no_match
|
||||
f'_Selector(tag={self.tag!r}, ids={self.ids!r}, classes={self.classes!r}, attributes={self.attributes!r}, '
|
||||
f'nth={self.nth!r}, selectors={self.selectors!r}, relations={self.relations!r}, '
|
||||
f'rel_type={self.rel_type!r}, contains={self.contains!r}, lang={self.lang!r}, flags={self.flags!r}, '
|
||||
f'no_match={self.no_match!r})'
|
||||
)
|
||||
|
||||
__repr__ = __str__
|
||||
|
|
@ -563,7 +547,7 @@ class CSSParser:
|
|||
selector = self.custom.get(pseudo)
|
||||
if selector is None:
|
||||
raise SelectorSyntaxError(
|
||||
"Undefined custom selector '{}' found at position {}".format(pseudo, m.end(0)),
|
||||
f"Undefined custom selector '{pseudo}' found at position {m.end(0)}",
|
||||
self.pattern,
|
||||
m.end(0)
|
||||
)
|
||||
|
|
@ -663,13 +647,13 @@ class CSSParser:
|
|||
has_selector = True
|
||||
elif pseudo in PSEUDO_SUPPORTED:
|
||||
raise SelectorSyntaxError(
|
||||
"Invalid syntax for pseudo class '{}'".format(pseudo),
|
||||
f"Invalid syntax for pseudo class '{pseudo}'",
|
||||
self.pattern,
|
||||
m.start(0)
|
||||
)
|
||||
else:
|
||||
raise NotImplementedError(
|
||||
"'{}' pseudo-class is not implemented at this time".format(pseudo)
|
||||
f"'{pseudo}' pseudo-class is not implemented at this time"
|
||||
)
|
||||
|
||||
return has_selector, is_html
|
||||
|
|
@ -793,7 +777,7 @@ class CSSParser:
|
|||
# multiple non-whitespace combinators. So if the current combinator is not a whitespace,
|
||||
# then we've hit the multiple combinator case, so we should fail.
|
||||
raise SelectorSyntaxError(
|
||||
'The multiple combinators at position {}'.format(index),
|
||||
f'The multiple combinators at position {index}',
|
||||
self.pattern,
|
||||
index
|
||||
)
|
||||
|
|
@ -824,7 +808,7 @@ class CSSParser:
|
|||
if not has_selector:
|
||||
if not is_forgive or combinator != COMMA_COMBINATOR:
|
||||
raise SelectorSyntaxError(
|
||||
"The combinator '{}' at position {}, must have a selector before it".format(combinator, index),
|
||||
f"The combinator '{combinator}' at position {index}, must have a selector before it",
|
||||
self.pattern,
|
||||
index
|
||||
)
|
||||
|
|
@ -869,7 +853,7 @@ class CSSParser:
|
|||
|
||||
pseudo = util.lower(css_unescape(m.group('name')))
|
||||
if pseudo == ":contains":
|
||||
warnings.warn(
|
||||
warnings.warn( # noqa: B028
|
||||
"The pseudo class ':contains' is deprecated, ':-soup-contains' should be used moving forward.",
|
||||
FutureWarning
|
||||
)
|
||||
|
|
@ -982,13 +966,13 @@ class CSSParser:
|
|||
|
||||
# Handle parts
|
||||
if key == "at_rule":
|
||||
raise NotImplementedError("At-rules found at position {}".format(m.start(0)))
|
||||
raise NotImplementedError(f"At-rules found at position {m.start(0)}")
|
||||
elif key == 'pseudo_class_custom':
|
||||
has_selector = self.parse_pseudo_class_custom(sel, m, has_selector)
|
||||
elif key == 'pseudo_class':
|
||||
has_selector, is_html = self.parse_pseudo_class(sel, m, has_selector, iselector, is_html)
|
||||
elif key == 'pseudo_element':
|
||||
raise NotImplementedError("Pseudo-element found at position {}".format(m.start(0)))
|
||||
raise NotImplementedError(f"Pseudo-element found at position {m.start(0)}")
|
||||
elif key == 'pseudo_contains':
|
||||
has_selector = self.parse_pseudo_contains(sel, m, has_selector)
|
||||
elif key in ('pseudo_nth_type', 'pseudo_nth_child'):
|
||||
|
|
@ -1003,7 +987,7 @@ class CSSParser:
|
|||
if not has_selector:
|
||||
if not is_forgive:
|
||||
raise SelectorSyntaxError(
|
||||
"Expected a selector at position {}".format(m.start(0)),
|
||||
f"Expected a selector at position {m.start(0)}",
|
||||
self.pattern,
|
||||
m.start(0)
|
||||
)
|
||||
|
|
@ -1013,7 +997,7 @@ class CSSParser:
|
|||
break
|
||||
else:
|
||||
raise SelectorSyntaxError(
|
||||
"Unmatched pseudo-class close at position {}".format(m.start(0)),
|
||||
f"Unmatched pseudo-class close at position {m.start(0)}",
|
||||
self.pattern,
|
||||
m.start(0)
|
||||
)
|
||||
|
|
@ -1031,7 +1015,7 @@ class CSSParser:
|
|||
elif key == 'tag':
|
||||
if has_selector:
|
||||
raise SelectorSyntaxError(
|
||||
"Tag name found at position {} instead of at the start".format(m.start(0)),
|
||||
f"Tag name found at position {m.start(0)} instead of at the start",
|
||||
self.pattern,
|
||||
m.start(0)
|
||||
)
|
||||
|
|
@ -1046,7 +1030,7 @@ class CSSParser:
|
|||
# Handle selectors that are not closed
|
||||
if is_open and not closed:
|
||||
raise SelectorSyntaxError(
|
||||
"Unclosed pseudo-class at position {}".format(index),
|
||||
f"Unclosed pseudo-class at position {index}",
|
||||
self.pattern,
|
||||
index
|
||||
)
|
||||
|
|
@ -1076,7 +1060,7 @@ class CSSParser:
|
|||
# We will always need to finish a selector when `:has()` is used as it leads with combining.
|
||||
# May apply to others as well.
|
||||
raise SelectorSyntaxError(
|
||||
'Expected a selector at position {}'.format(index),
|
||||
f'Expected a selector at position {index}',
|
||||
self.pattern,
|
||||
index
|
||||
)
|
||||
|
|
@ -1108,7 +1092,7 @@ class CSSParser:
|
|||
end = (m.start(0) - 1) if m else (len(pattern) - 1)
|
||||
|
||||
if self.debug: # pragma: no cover
|
||||
print('## PARSING: {!r}'.format(pattern))
|
||||
print(f'## PARSING: {pattern!r}')
|
||||
while index <= end:
|
||||
m = None
|
||||
for v in self.css_tokens:
|
||||
|
|
@ -1116,7 +1100,7 @@ class CSSParser:
|
|||
if m:
|
||||
name = v.get_name()
|
||||
if self.debug: # pragma: no cover
|
||||
print("TOKEN: '{}' --> {!r} at position {}".format(name, m.group(0), m.start(0)))
|
||||
print(f"TOKEN: '{name}' --> {m.group(0)!r} at position {m.start(0)}")
|
||||
index = m.end(0)
|
||||
yield name, m
|
||||
break
|
||||
|
|
@ -1126,15 +1110,15 @@ class CSSParser:
|
|||
# throw an exception mentioning that the known selector type is in error;
|
||||
# otherwise, report the invalid character.
|
||||
if c == '[':
|
||||
msg = "Malformed attribute selector at position {}".format(index)
|
||||
msg = f"Malformed attribute selector at position {index}"
|
||||
elif c == '.':
|
||||
msg = "Malformed class selector at position {}".format(index)
|
||||
msg = f"Malformed class selector at position {index}"
|
||||
elif c == '#':
|
||||
msg = "Malformed id selector at position {}".format(index)
|
||||
msg = f"Malformed id selector at position {index}"
|
||||
elif c == ':':
|
||||
msg = "Malformed pseudo-class selector at position {}".format(index)
|
||||
msg = f"Malformed pseudo-class selector at position {index}"
|
||||
else:
|
||||
msg = "Invalid character {!r} position {}".format(c, index)
|
||||
msg = f"Invalid character {c!r} position {index}"
|
||||
raise SelectorSyntaxError(msg, self.pattern, index)
|
||||
if self.debug: # pragma: no cover
|
||||
print('## END PARSING')
|
||||
|
|
|
|||
|
|
@ -45,11 +45,11 @@ class Immutable:
|
|||
for k, v in kwargs.items():
|
||||
temp.append(type(v))
|
||||
temp.append(v)
|
||||
super(Immutable, self).__setattr__(k, v)
|
||||
super(Immutable, self).__setattr__('_hash', hash(tuple(temp)))
|
||||
super().__setattr__(k, v)
|
||||
super().__setattr__('_hash', hash(tuple(temp)))
|
||||
|
||||
@classmethod
|
||||
def __base__(cls) -> "type[Immutable]":
|
||||
def __base__(cls) -> type[Immutable]:
|
||||
"""Get base class."""
|
||||
|
||||
return cls
|
||||
|
|
@ -59,7 +59,7 @@ class Immutable:
|
|||
|
||||
return (
|
||||
isinstance(other, self.__base__()) and
|
||||
all([getattr(other, key) == getattr(self, key) for key in self.__slots__ if key != '_hash'])
|
||||
all(getattr(other, key) == getattr(self, key) for key in self.__slots__ if key != '_hash')
|
||||
)
|
||||
|
||||
def __ne__(self, other: Any) -> bool:
|
||||
|
|
@ -67,7 +67,7 @@ class Immutable:
|
|||
|
||||
return (
|
||||
not isinstance(other, self.__base__()) or
|
||||
any([getattr(other, key) != getattr(self, key) for key in self.__slots__ if key != '_hash'])
|
||||
any(getattr(other, key) != getattr(self, key) for key in self.__slots__ if key != '_hash')
|
||||
)
|
||||
|
||||
def __hash__(self) -> int:
|
||||
|
|
@ -78,14 +78,13 @@ class Immutable:
|
|||
def __setattr__(self, name: str, value: Any) -> None:
|
||||
"""Prevent mutability."""
|
||||
|
||||
raise AttributeError("'{}' is immutable".format(self.__class__.__name__))
|
||||
raise AttributeError(f"'{self.__class__.__name__}' is immutable")
|
||||
|
||||
def __repr__(self) -> str: # pragma: no cover
|
||||
"""Representation."""
|
||||
|
||||
return "{}({})".format(
|
||||
self.__class__.__name__, ', '.join(["{}={!r}".format(k, getattr(self, k)) for k in self.__slots__[:-1]])
|
||||
)
|
||||
r = ', '.join([f"{k}={getattr(self, k)!r}" for k in self.__slots__[:-1]])
|
||||
return f"{self.__class__.__name__}({r})"
|
||||
|
||||
__str__ = __repr__
|
||||
|
||||
|
|
@ -112,10 +111,10 @@ class ImmutableDict(Mapping[Any, Any]):
|
|||
"""Validate arguments."""
|
||||
|
||||
if isinstance(arg, dict):
|
||||
if not all([isinstance(v, Hashable) for v in arg.values()]):
|
||||
raise TypeError('{} values must be hashable'.format(self.__class__.__name__))
|
||||
elif not all([isinstance(k, Hashable) and isinstance(v, Hashable) for k, v in arg]):
|
||||
raise TypeError('{} values must be hashable'.format(self.__class__.__name__))
|
||||
if not all(isinstance(v, Hashable) for v in arg.values()):
|
||||
raise TypeError(f'{self.__class__.__name__} values must be hashable')
|
||||
elif not all(isinstance(k, Hashable) and isinstance(v, Hashable) for k, v in arg):
|
||||
raise TypeError(f'{self.__class__.__name__} values must be hashable')
|
||||
|
||||
def __iter__(self) -> Iterator[Any]:
|
||||
"""Iterator."""
|
||||
|
|
@ -140,7 +139,7 @@ class ImmutableDict(Mapping[Any, Any]):
|
|||
def __repr__(self) -> str: # pragma: no cover
|
||||
"""Representation."""
|
||||
|
||||
return "{!r}".format(self._d)
|
||||
return f"{self._d!r}"
|
||||
|
||||
__str__ = __repr__
|
||||
|
||||
|
|
@ -157,10 +156,10 @@ class Namespaces(ImmutableDict):
|
|||
"""Validate arguments."""
|
||||
|
||||
if isinstance(arg, dict):
|
||||
if not all([isinstance(v, str) for v in arg.values()]):
|
||||
raise TypeError('{} values must be hashable'.format(self.__class__.__name__))
|
||||
elif not all([isinstance(k, str) and isinstance(v, str) for k, v in arg]):
|
||||
raise TypeError('{} keys and values must be Unicode strings'.format(self.__class__.__name__))
|
||||
if not all(isinstance(v, str) for v in arg.values()):
|
||||
raise TypeError(f'{self.__class__.__name__} values must be hashable')
|
||||
elif not all(isinstance(k, str) and isinstance(v, str) for k, v in arg):
|
||||
raise TypeError(f'{self.__class__.__name__} keys and values must be Unicode strings')
|
||||
|
||||
|
||||
class CustomSelectors(ImmutableDict):
|
||||
|
|
@ -175,10 +174,10 @@ class CustomSelectors(ImmutableDict):
|
|||
"""Validate arguments."""
|
||||
|
||||
if isinstance(arg, dict):
|
||||
if not all([isinstance(v, str) for v in arg.values()]):
|
||||
raise TypeError('{} values must be hashable'.format(self.__class__.__name__))
|
||||
elif not all([isinstance(k, str) and isinstance(v, str) for k, v in arg]):
|
||||
raise TypeError('{} keys and values must be Unicode strings'.format(self.__class__.__name__))
|
||||
if not all(isinstance(v, str) for v in arg.values()):
|
||||
raise TypeError(f'{self.__class__.__name__} values must be hashable')
|
||||
elif not all(isinstance(k, str) and isinstance(v, str) for k, v in arg):
|
||||
raise TypeError(f'{self.__class__.__name__} keys and values must be Unicode strings')
|
||||
|
||||
|
||||
class Selector(Immutable):
|
||||
|
|
@ -367,7 +366,7 @@ class SelectorList(Immutable):
|
|||
"""Initialize."""
|
||||
|
||||
super().__init__(
|
||||
selectors=tuple(selectors) if selectors is not None else tuple(),
|
||||
selectors=tuple(selectors) if selectors is not None else (),
|
||||
is_not=is_not,
|
||||
is_html=is_html
|
||||
)
|
||||
|
|
|
|||
|
|
@ -10,7 +10,7 @@ The format and various output types is fairly known (though it
|
|||
hasn't been tested extensively to make sure we aren't missing corners).
|
||||
|
||||
Example:
|
||||
|
||||
-------
|
||||
```
|
||||
>>> import soupsieve as sv
|
||||
>>> sv.compile('this > that.class[name=value]').selectors.pretty()
|
||||
|
|
@ -64,6 +64,7 @@ SelectorList(
|
|||
is_not=False,
|
||||
is_html=False)
|
||||
```
|
||||
|
||||
"""
|
||||
from __future__ import annotations
|
||||
import re
|
||||
|
|
@ -123,16 +124,16 @@ def pretty(obj: Any) -> str: # pragma: no cover
|
|||
index = m.end(0)
|
||||
if name in ('class', 'lstrt', 'dstrt', 'tstrt'):
|
||||
indent += 4
|
||||
output.append('{}\n{}'.format(m.group(0), " " * indent))
|
||||
output.append(f'{m.group(0)}\n{" " * indent}')
|
||||
elif name in ('param', 'int', 'kword', 'sqstr', 'dqstr', 'empty'):
|
||||
output.append(m.group(0))
|
||||
elif name in ('lend', 'dend', 'tend'):
|
||||
indent -= 4
|
||||
output.append(m.group(0))
|
||||
elif name in ('sep',):
|
||||
output.append('{}\n{}'.format(m.group(1), " " * indent))
|
||||
output.append(f'{m.group(1)}\n{" " * indent}')
|
||||
elif name in ('dsep',):
|
||||
output.append('{} '.format(m.group(1)))
|
||||
output.append(f'{m.group(1)} ')
|
||||
break
|
||||
|
||||
return ''.join(output)
|
||||
|
|
|
|||
|
|
@ -37,7 +37,7 @@ class SelectorSyntaxError(Exception):
|
|||
if pattern is not None and index is not None:
|
||||
# Format pattern to show line and column position
|
||||
self.context, self.line, self.col = get_pattern_context(pattern, index)
|
||||
msg = '{}\n line {}:\n{}'.format(msg, self.line, self.context)
|
||||
msg = f'{msg}\n line {self.line}:\n{self.context}'
|
||||
|
||||
super().__init__(msg)
|
||||
|
||||
|
|
@ -105,7 +105,7 @@ def get_pattern_context(pattern: str, index: int) -> tuple[str, int, int]:
|
|||
# we will render the output with just `\n`. We will still log the column
|
||||
# correctly though.
|
||||
text.append('\n')
|
||||
text.append('{}{}'.format(indent, linetext))
|
||||
text.append(f'{indent}{linetext}')
|
||||
if offset is not None:
|
||||
text.append('\n')
|
||||
text.append(' ' * (col + offset) + '^')
|
||||
|
|
|
|||
|
|
@ -3,7 +3,7 @@ arrow==1.3.0
|
|||
backports.csv==1.0.7
|
||||
backports.functools-lru-cache==2.0.0
|
||||
backports.zoneinfo==0.2.1;python_version<"3.9"
|
||||
beautifulsoup4==4.12.2
|
||||
beautifulsoup4==4.12.3
|
||||
bleach==6.1.0
|
||||
certifi==2024.2.2
|
||||
cheroot==10.0.0
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue