Sphinx 8.0.2__py3-none-any.whl → 8.1.0__py3-none-any.whl

sphinx/search/es.py

@@ -2,13 +2,11 @@
 
 from __future__ import annotations
 
-from typing import TYPE_CHECKING, Dict
-
 import snowballstemmer
 
 from sphinx.search import SearchLanguage, parse_stop_word
 
-spanish_stopwords = parse_stop_word('''
+spanish_stopwords = parse_stop_word("""
 |source: https://snowball.tartarus.org/algorithms/spanish/stop.txt
 de             |  from, of
 la             |  the, her
@@ -347,7 +345,7 @@ tenida
 tenidos
 tenidas
 tened
-''')
+""")
 
 
 class SearchSpanish(SearchLanguage):

sphinx/search/fi.py

@@ -2,13 +2,11 @@
 
 from __future__ import annotations
 
-from typing import TYPE_CHECKING, Dict
-
 import snowballstemmer
 
 from sphinx.search import SearchLanguage, parse_stop_word
 
-finnish_stopwords = parse_stop_word('''
+finnish_stopwords = parse_stop_word("""
 | source: https://snowball.tartarus.org/algorithms/finnish/stop.txt
 | forms of BE
 
@@ -97,7 +95,7 @@ kun    | when
 niin   | so
 nyt    | now
 itse   | self
-''')
+""")
 
 
 class SearchFinnish(SearchLanguage):

sphinx/search/fr.py

@@ -2,13 +2,11 @@
 
 from __future__ import annotations
 
-from typing import TYPE_CHECKING, Dict
-
 import snowballstemmer
 
 from sphinx.search import SearchLanguage, parse_stop_word
 
-french_stopwords = parse_stop_word('''
+french_stopwords = parse_stop_word("""
 | source: https://snowball.tartarus.org/algorithms/french/stop.txt
 au             |  a + le
 aux            |  a + les
@@ -183,7 +181,7 @@ quelle         |  which
 quelles        |  which
 sans           |  without
 soi            |  oneself
-''')
+""")
 
 
 class SearchFrench(SearchLanguage):

sphinx/search/hu.py

@@ -2,13 +2,11 @@
 
 from __future__ import annotations
 
-from typing import TYPE_CHECKING, Dict
-
 import snowballstemmer
 
 from sphinx.search import SearchLanguage, parse_stop_word
 
-hungarian_stopwords = parse_stop_word('''
+hungarian_stopwords = parse_stop_word("""
 | source: https://snowball.tartarus.org/algorithms/hungarian/stop.txt
 | prepared by Anna Tordai
 a
@@ -210,7 +208,7 @@ vissza
 vele
 viszont
 volna
-''')
+""")
 
 
 class SearchHungarian(SearchLanguage):

sphinx/search/it.py

@@ -2,13 +2,11 @@
 
 from __future__ import annotations
 
-from typing import TYPE_CHECKING, Dict
-
 import snowballstemmer
 
 from sphinx.search import SearchLanguage, parse_stop_word
 
-italian_stopwords = parse_stop_word('''
+italian_stopwords = parse_stop_word("""
 | source: https://snowball.tartarus.org/algorithms/italian/stop.txt
 ad             |  a (to) before vowel
 al             |  a + il
@@ -300,7 +298,7 @@ stessi
 stesse
 stessimo
 stessero
-''')
+""")
 
 
 class SearchItalian(SearchLanguage):

sphinx/search/ja.py

@@ -17,19 +17,21 @@ from typing import Any
 
 try:
     import MeCab  # type: ignore[import-not-found]
+
     native_module = True
 except ImportError:
     native_module = False
 
 try:
     import janome.tokenizer  # type: ignore[import-not-found]
+
     janome_module = True
 except ImportError:
     janome_module = False
 
 from sphinx.errors import ExtensionError, SphinxError
 from sphinx.search import SearchLanguage
-from sphinx.util import import_object
+from sphinx.util._importer import import_object
 
 
 class BaseSplitter:
@@ -61,7 +63,8 @@ class MecabSplitter(BaseSplitter):
             result = self.native.parse(input)
         else:
             result = self.ctypes_libmecab.mecab_sparse_tostr(
-                self.ctypes_mecab, input.encode(self.dict_encode))
+                self.ctypes_mecab, input.encode(self.dict_encode)
+            )
         return result.split(' ')
 
     def init_native(self, options: dict[str, str]) -> None:
@@ -89,7 +92,8 @@ class MecabSplitter(BaseSplitter):
             if os.path.exists(lib):
                 libpath = lib
         if libpath is None:
-            raise RuntimeError('MeCab dynamic library is not available')
+            msg = 'MeCab dynamic library is not available'
+            raise RuntimeError(msg)
 
         param = 'mecab -Owakati'
         dict = options.get('dict')
@@ -101,11 +105,15 @@ class MecabSplitter(BaseSplitter):
         self.ctypes_libmecab = ctypes.CDLL(libpath)
         self.ctypes_libmecab.mecab_new2.argtypes = (ctypes.c_char_p,)
         self.ctypes_libmecab.mecab_new2.restype = ctypes.c_void_p
-        self.ctypes_libmecab.mecab_sparse_tostr.argtypes = (ctypes.c_void_p, ctypes.c_char_p)
+        self.ctypes_libmecab.mecab_sparse_tostr.argtypes = (
+            ctypes.c_void_p,
+            ctypes.c_char_p,
+        )
         self.ctypes_libmecab.mecab_sparse_tostr.restype = ctypes.c_char_p
         self.ctypes_mecab = self.ctypes_libmecab.mecab_new2(param.encode(fs_enc))
         if self.ctypes_mecab is None:
-            raise SphinxError('mecab initialization failed')
+            msg = 'mecab initialization failed'
+            raise SphinxError(msg)
 
     def __del__(self) -> None:
         if self.ctypes_libmecab:
@@ -121,8 +129,11 @@ class JanomeSplitter(BaseSplitter):
 
     def init_tokenizer(self) -> None:
         if not janome_module:
-            raise RuntimeError('Janome is not available')
-        self.tokenizer = janome.tokenizer.Tokenizer(udic=self.user_dict, udic_enc=self.user_dict_enc)
+            msg = 'Janome is not available'
+            raise RuntimeError(msg)
+        self.tokenizer = janome.tokenizer.Tokenizer(
+            udic=self.user_dict, udic_enc=self.user_dict_enc
+        )
 
     def split(self, input: str) -> list[str]:
         result = ' '.join(token.surface for token in self.tokenizer.tokenize(input))
@@ -130,14 +141,18 @@ class JanomeSplitter(BaseSplitter):
 
 
 class DefaultSplitter(BaseSplitter):
-    patterns_ = {re.compile(pattern): value for pattern, value in {
-        '[一二三四五六七八九十百千万億兆]': 'M',
-        '[一-龠々〆ヵヶ]': 'H',
-        '[ぁ-ん]': 'I',
-        '[ァ-ヴーｱ-ﾝﾞｰ]': 'K',
-        '[a-zA-Zａ-ｚＡ-Ｚ]': 'A',
-        '[0-9０-９]': 'N',
-    }.items()}
+    patterns_ = {
+        re.compile(pattern): value
+        for pattern, value in {
+            '[一二三四五六七八九十百千万億兆]': 'M',
+            '[一-龠々〆ヵヶ]': 'H',
+            '[ぁ-ん]': 'I',
+            '[ァ-ヴーｱ-ﾝﾞｰ]': 'K',
+            '[a-zA-Zａ-ｚＡ-Ｚ]': 'A',
+            '[0-9０-９]': 'N',
+        }.items()
+    }
+    # fmt: off
     BIAS__ = -332
     BC1__ = {'HH': 6, 'II': 2461, 'KH': 406, 'OH': -1378}
     BC2__ = {'AA': -3267, 'AI': 2744, 'AN': -878, 'HH': -4070, 'HM': -1711,
@@ -398,6 +413,7 @@ class DefaultSplitter(BaseSplitter):
              '委': 798, '学': -960, '市': 887, '広': -695, '後': 535, '業': -697,
              '相': 753, '社': -507, '福': 974, '空': -822, '者': 1811, '連': 463,
              '郎': 1082, '１': -270, 'Ｅ１': 306, 'ﾙ': -673, 'ﾝ': -496}
+    # fmt: on
 
     # ctype_
     def ctype_(self, char: str) -> str:
@@ -427,18 +443,18 @@ class DefaultSplitter(BaseSplitter):
 
         for i in range(4, len(seg) - 3):
             score = self.BIAS__
-            w1 = seg[i-3]
-            w2 = seg[i-2]
-            w3 = seg[i-1]
+            w1 = seg[i - 3]
+            w2 = seg[i - 2]
+            w3 = seg[i - 1]
             w4 = seg[i]
-            w5 = seg[i+1]
-            w6 = seg[i+2]
-            c1 = ctype[i-3]
-            c2 = ctype[i-2]
-            c3 = ctype[i-1]
+            w5 = seg[i + 1]
+            w6 = seg[i + 2]
+            c1 = ctype[i - 3]
+            c2 = ctype[i - 2]
+            c3 = ctype[i - 1]
             c4 = ctype[i]
-            c5 = ctype[i+1]
-            c6 = ctype[i+2]
+            c5 = ctype[i + 1]
+            c6 = ctype[i + 2]
             score += self.ts_(self.UP1__, p1)
             score += self.ts_(self.UP2__, p2)
             score += self.ts_(self.UP3__, p3)
@@ -470,7 +486,7 @@ class DefaultSplitter(BaseSplitter):
             score += self.ts_(self.TC2__, c2 + c3 + c4)
             score += self.ts_(self.TC3__, c3 + c4 + c5)
             score += self.ts_(self.TC4__, c4 + c5 + c6)
-#           score += self.ts_(self.TC5__, c4 + c5 + c6)
+            # score += self.ts_(self.TC5__, c4 + c5 + c6)
             score += self.ts_(self.UQ1__, p1 + c1)
             score += self.ts_(self.UQ2__, p2 + c2)
             score += self.ts_(self.UQ1__, p3 + c3)
@@ -501,16 +517,23 @@ class SearchJapanese(SearchLanguage):
     Japanese search implementation: uses no stemmer, but word splitting is quite
     complicated.
     """
+
     lang = 'ja'
     language_name = 'Japanese'
 
     def init(self, options: dict[str, str]) -> None:
-        dotted_path = options.get('type', 'sphinx.search.ja.DefaultSplitter')
-        try:
-            self.splitter = import_object(dotted_path)(options)
-        except ExtensionError as exc:
-            raise ExtensionError("Splitter module %r can't be imported" %
-                                 dotted_path) from exc
+        dotted_path = options.get('type')
+        if dotted_path is None:
+            self.splitter = DefaultSplitter(options)
+        else:
+            try:
+                splitter_cls = import_object(
+                    dotted_path, "html_search_options['type'] setting"
+                )
+                self.splitter = splitter_cls(options)
+            except ExtensionError as exc:
+                msg = f"Splitter module {dotted_path!r} can't be imported"
+                raise ExtensionError(msg) from exc
 
     def split(self, input: str) -> list[str]:
         return self.splitter.split(input)

sphinx/search/nl.py

@@ -2,13 +2,11 @@
 
 from __future__ import annotations
 
-from typing import TYPE_CHECKING, Dict
-
 import snowballstemmer
 
 from sphinx.search import SearchLanguage, parse_stop_word
 
-dutch_stopwords = parse_stop_word('''
+dutch_stopwords = parse_stop_word("""
 | source: https://snowball.tartarus.org/algorithms/dutch/stop.txt
 de             |  the
 en             |  and
@@ -111,7 +109,7 @@ uw             |  your
 iemand         |  somebody
 geweest        |  been; past participle of 'be'
 andere         |  other
-''')
+""")
 
 
 class SearchDutch(SearchLanguage):

sphinx/search/no.py

@@ -2,13 +2,11 @@
 
 from __future__ import annotations
 
-from typing import TYPE_CHECKING, Dict
-
 import snowballstemmer
 
 from sphinx.search import SearchLanguage, parse_stop_word
 
-norwegian_stopwords = parse_stop_word('''
+norwegian_stopwords = parse_stop_word("""
 | source: https://snowball.tartarus.org/algorithms/norwegian/stop.txt
 og             | and
 i              | in
@@ -186,7 +184,7 @@ verte          | become *
 vort           | become *
 varte          | became *
 vart           | became *
-''')
+""")
 
 
 class SearchNorwegian(SearchLanguage):

sphinx/search/pt.py

@@ -2,13 +2,11 @@
 
 from __future__ import annotations
 
-from typing import TYPE_CHECKING, Dict
-
 import snowballstemmer
 
 from sphinx.search import SearchLanguage, parse_stop_word
 
-portuguese_stopwords = parse_stop_word('''
+portuguese_stopwords = parse_stop_word("""
 | source: https://snowball.tartarus.org/algorithms/portuguese/stop.txt
 de             |  of, from
 a              |  the; to, at; her
@@ -245,7 +243,7 @@ terão
 teria
 teríamos
 teriam
-''')
+""")
 
 
 class SearchPortuguese(SearchLanguage):

sphinx/search/ro.py

@@ -2,8 +2,6 @@
 
 from __future__ import annotations
 
-from typing import TYPE_CHECKING, Dict, Set
-
 import snowballstemmer
 
 from sphinx.search import SearchLanguage

sphinx/search/ru.py

@@ -2,13 +2,11 @@
 
 from __future__ import annotations
 
-from typing import TYPE_CHECKING, Dict
-
 import snowballstemmer
 
 from sphinx.search import SearchLanguage, parse_stop_word
 
-russian_stopwords = parse_stop_word('''
+russian_stopwords = parse_stop_word("""
 | source: https://snowball.tartarus.org/algorithms/russian/stop.txt
 и              | and
 в              | in/into
@@ -235,7 +233,7 @@ russian_stopwords = parse_stop_word('''
   | можн
   | нужн
   | нельзя
-''')
+""")
 
 
 class SearchRussian(SearchLanguage):

sphinx/search/sv.py

@@ -2,13 +2,11 @@
 
 from __future__ import annotations
 
-from typing import TYPE_CHECKING, Dict
-
 import snowballstemmer
 
 from sphinx.search import SearchLanguage, parse_stop_word
 
-swedish_stopwords = parse_stop_word('''
+swedish_stopwords = parse_stop_word("""
 | source: https://snowball.tartarus.org/algorithms/swedish/stop.txt
 och            | and
 det            | it, this/that
@@ -124,7 +122,7 @@ våra           | our
 ert            | your
 era            | your
 vilkas         | whose
-''')
+""")
 
 
 class SearchSwedish(SearchLanguage):

sphinx/search/tr.py

@@ -2,8 +2,6 @@
 
 from __future__ import annotations
 
-from typing import TYPE_CHECKING, Dict, Set
-
 import snowballstemmer
 
 from sphinx.search import SearchLanguage

sphinx/search/zh.py

@@ -11,11 +11,13 @@ from sphinx.search import SearchLanguage
 
 try:
     import jieba  # type: ignore[import-not-found]
+
     JIEBA = True
 except ImportError:
     JIEBA = False
 
-english_stopwords = set("""
+english_stopwords = set(
+    """
 a  and  are  as  at
 be  but  by
 for
@@ -25,7 +27,8 @@ of  on  or
 such
 that  the  their  then  there  these  they  this  to
 was  will  with
-""".split())
+""".split()
+)
 
 js_porter_stemmer = """
 /**
@@ -224,7 +227,10 @@ class SearchChinese(SearchLanguage):
     js_stemmer_code = js_porter_stemmer
     stopwords = english_stopwords
     latin1_letters = re.compile(r'[a-zA-Z0-9_]+')
-    latin_terms: list[str] = []
+
+    def __init__(self, options: dict[str, str]) -> None:
+        super().__init__(options)
+        self.latin_terms: set[str] = set()
 
     def init(self, options: dict[str, str]) -> None:
         if JIEBA:
@@ -235,13 +241,13 @@ class SearchChinese(SearchLanguage):
         self.stemmer = snowballstemmer.stemmer('english')
 
     def split(self, input: str) -> list[str]:
-        chinese: list[str] = []
         if JIEBA:
-            chinese = list(jieba.cut_for_search(input))
+            chinese: list[str] = list(jieba.cut_for_search(input))
+        else:
+            chinese = []
 
-        latin1 = \
-            [term.strip() for term in self.latin1_letters.findall(input)]
-        self.latin_terms.extend(latin1)
+        latin1 = [term.strip() for term in self.latin1_letters.findall(input)]
+        self.latin_terms.update(latin1)
         return chinese + latin1
 
     def word_filter(self, stemmed_word: str) -> bool:
@@ -251,11 +257,10 @@ class SearchChinese(SearchLanguage):
         # Don't stem Latin words that are long enough to be relevant for search
         # if not stemmed, but would be too short after being stemmed
         # avoids some issues with acronyms
+        stemmed = self.stemmer.stemWord(word.lower())
         should_not_be_stemmed = (
-            word in self.latin_terms and
-            len(word) >= 3 and
-            len(self.stemmer.stemWord(word.lower())) < 3
-        )
+            len(word) >= 3 > len(stemmed) and word in self.latin_terms
+        )  # fmt: skip
         if should_not_be_stemmed:
             return word.lower()
-        return self.stemmer.stemWord(word.lower())
+        return stemmed

sphinx/templates/graphviz/graphviz.css

@@ -1,12 +1,5 @@
 /*
- * graphviz.css
- * ~~~~~~~~~~~~
- *
  * Sphinx stylesheet -- graphviz extension.
- *
- * :copyright: Copyright 2007-2024 by the Sphinx team, see AUTHORS.
- * :license: BSD, see LICENSE for details.
- *
  */
 
 img.graphviz {

sphinx/testing/fixtures.py

@@ -28,7 +28,7 @@ DEFAULT_ENABLED_MARKERS = [
         'testroot="root", srcdir=None, '
         'confoverrides=None, freshenv=False, '
         'warningiserror=False, tags=None, verbosity=0, parallel=0, '
-        'keep_going=False, builddir=None, docutils_conf=None'
+        'builddir=None, docutils_conf=None'
         '): arguments to initialize the sphinx test application.'
     ),
     'test_params(shared_result=...): test parameters.',
@@ -42,7 +42,7 @@ def pytest_configure(config: pytest.Config) -> None:
 
 
 @pytest.fixture(scope='session')
-def rootdir() -> str | None:
+def rootdir() -> Path | None:
     return None
 
 
@@ -74,7 +74,7 @@ def app_params(
     test_params: dict[str, Any],
     shared_result: SharedResult,
     sphinx_test_tempdir: str,
-    rootdir: str,
+    rootdir: Path,
 ) -> _app_params:
     """
     Parameters that are specified by 'pytest.mark.sphinx' for
@@ -86,7 +86,7 @@ def app_params(
     kwargs: dict[str, Any] = {}
 
     # to avoid stacking positional args
-    for info in reversed(list(request.node.iter_markers("sphinx"))):
+    for info in reversed(list(request.node.iter_markers('sphinx'))):
         pargs |= dict(enumerate(info.args))
         kwargs.update(info.kwargs)
 
@@ -203,6 +203,7 @@ def make_app(test_params: dict[str, Any]) -> Iterator[Callable[[], SphinxTestApp
             app_ = SphinxTestApp(*args, **kwargs)
         apps.append(app_)
         return app_
+
     yield make
 
     sys.path[:] = syspath
@@ -239,7 +240,7 @@ def if_graphviz_found(app: SphinxTestApp) -> None:  # NoQA: PT004
 
 
 @pytest.fixture(scope='session')
-def sphinx_test_tempdir(tmp_path_factory: Any) -> Path:
+def sphinx_test_tempdir(tmp_path_factory: pytest.TempPathFactory) -> Path:
     """Temporary directory."""
     return tmp_path_factory.getbasetemp()
 

sphinx/testing/path.py

@@ -12,9 +12,11 @@ if TYPE_CHECKING:
     import builtins
     from collections.abc import Callable
 
-warnings.warn("'sphinx.testing.path' is deprecated. "
-              "Use 'os.path' or 'pathlib' instead.",
-              RemovedInSphinx90Warning, stacklevel=2)
+warnings.warn(
+    "'sphinx.testing.path' is deprecated. " "Use 'os.path' or 'pathlib' instead.",
+    RemovedInSphinx90Warning,
+    stacklevel=2,
+)
 
 FILESYSTEMENCODING = sys.getfilesystemencoding() or sys.getdefaultencoding()
 
@@ -86,7 +88,7 @@ class path(str):
     def rmtree(
         self,
         ignore_errors: bool = False,
-        onerror:  Callable[[Callable[..., Any], str, Any], object] | None = None,
+        onerror: Callable[[Callable[..., Any], str, Any], object] | None = None,
     ) -> None:
         """
         Removes the file or directory and any files or directories it may
@@ -178,7 +180,7 @@ class path(str):
         with open(self, mode='rb') as f:
             return f.read()
 
-    def write_bytes(self, bytes: str, append: bool = False) -> None:
+    def write_bytes(self, bytes: bytes, append: bool = False) -> None:
         """
         Writes the given `bytes` to the file.