wikitextparser 0.56.2__tar.gz → 0.56.4__tar.gz

wikitextparser-0.56.4/.vscode/settings.json

@@ -0,0 +1,7 @@
+{
+    "python.testing.pytestArgs": [
+        "tests"
+    ],
+    "python.testing.unittestEnabled": false,
+    "python.testing.pytestEnabled": true
+}

{wikitextparser-0.56.2 → wikitextparser-0.56.4}/CHANGELOG.rst

@@ -1,3 +1,13 @@
+v0.56.4 (2025-05-14)
+--------------------
+* Fixed a bug in detection of images in ``plain_text`` method. (#141)
+* Improved typehints.
+
+v0.56.3 (2024-10-18)
+--------------------
+* Fixed a bug in detecting HTML tags nested in wiki markup. (#140)
+* Improved type hints.
+
 v0.56.2
 -------
 * Fixed a bug in ``external_links`` property where ``|`` was recognized as part of the link by mistake. (#139)

{wikitextparser-0.56.2 → wikitextparser-0.56.4}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: wikitextparser
-Version: 0.56.2
+Version: 0.56.4
 Summary: A simple parsing tool for MediaWiki's wikitext markup.
 Keywords: MediaWiki,wikitext,parser
 Author-email: 5j9 <5j9@users.noreply.github.com>
@@ -9,6 +9,7 @@ Description-Content-Type: text/x-rst
 Classifier: Programming Language :: Python
 Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3)
 Classifier: Topic :: Text Processing
+License-File: LICENSE.md
 Requires-Dist: regex >= 2022.9.11
 Requires-Dist: wcwidth
 Requires-Dist: coverage ; extra == "dev"

{wikitextparser-0.56.2 → wikitextparser-0.56.4}/docs/conf.py

@@ -69,7 +69,7 @@ version = search(
         join(repo_dir, 'wikitextparser', '__init__.py'), encoding='utf8'
     ).read(),
     MULTILINE,
-).group(1)
+).group(1)  # type: ignore
 # The full version, including alpha/beta/rc tags.
 release = version
 

{wikitextparser-0.56.2 → wikitextparser-0.56.4}/pyproject.toml

@@ -50,13 +50,31 @@ line-length = 79
 format.quote-style = 'single'
 lint.isort.combine-as-imports = true
 lint.extend-select = [
+    'W605', # invalid-escape-sequence
+    'FA',  # flake8-future-annotations
     'I',  # isort
     'UP',  # pyupgrade
+    'RUF', # Ruff-specific rules (RUF)
 ]
 lint.ignore = [
-    'UP027',  # list comprehensions are faster than generator expressions
     'E721',  # Do not compare types, use `isinstance()`
+    'RUF001',  # ambiguous-unicode-character-string	
+    'RUF002',  # ambiguous-unicode-character-docstring
+    'RUF003',  # ambiguous-unicode-character-comment
 ]
 
 [tool.pytest.ini_options]
 addopts = '--quiet --tb=short'
+
+[tool.pyright]
+typeCheckingMode = 'standard'
+reportDeprecated = "warning"
+reportPropertyTypeMismatch = "warning"
+reportUnnecessaryCast = "warning"
+reportUnnecessaryContains = "warning"
+reportUnnecessaryIsInstance = "warning"
+reportUnnecessaryTypeIgnoreComment = true
+reportInvalidStringEscapeSequence = false
+reportConstantRedefinition = 'error'
+reportTypeCommentUsage = 'warning'
+reportUnnecessaryComparison = 'warning'

{wikitextparser-0.56.2 → wikitextparser-0.56.4}/wikitextparser/__init__.py

@@ -1,5 +1,5 @@
 # Scheme: [N!]N(.N)*[{a|b|rc}N][.postN][.devN]
-__version__ = '0.56.2'
+__version__ = '0.56.4'
 
 from . import _wikitext
 from ._argument import Argument  # noqa: F401

{wikitextparser-0.56.2 → wikitextparser-0.56.4}/wikitextparser/_argument.py

@@ -1,7 +1,10 @@
-from typing import Dict, List, MutableSequence, Optional, Union
+from __future__ import annotations
 
-from regex import DOTALL, MULTILINE
+from typing import MutableSequence
 
+from regex import DOTALL, MULTILINE, Match
+
+from ._spans import TypeToSpans
 from ._wikitext import SECTION_HEADING, SubWikiText, rc
 
 ARG_SHADOW_FULLMATCH = rc(
@@ -21,32 +24,32 @@ class Argument(SubWikiText):
     See https://www.mediawiki.org/wiki/Help:Templates for more information.
     """
 
-    __slots__ = '_shadow_match_cache', '_parent'
+    __slots__ = '_parent', '_shadow_match_cache'
 
     def __init__(
         self,
-        string: Union[str, MutableSequence[str]],
-        _type_to_spans: Optional[Dict[str, List[List[int]]]] = None,
-        _span: Optional[List[int]] = None,
-        _type: Optional[Union[str, int]] = None,
-        _parent: 'SubWikiTextWithArgs' = None,
+        string: str | MutableSequence[str],
+        _type_to_spans: TypeToSpans | None = None,
+        _span: list[int] | None = None,
+        _type: str | int | None = None,
+        _parent: SubWikiTextWithArgs | None = None,
     ):
         super().__init__(string, _type_to_spans, _span, _type)
         self._parent = _parent or self
         self._shadow_match_cache = None, None
 
     @property
-    def _shadow_match(self):
+    def _shadow_match(self) -> Match[bytes]:
         cached_shadow_match, cache_string = self._shadow_match_cache
         self_string = str(self)
         if cache_string == self_string:
-            return cached_shadow_match
+            return cached_shadow_match  # type: ignore
         ss, se, _, _ = self._span_data
         parent = self._parent
         ps = parent._span_data[0]
         shadow_match = ARG_SHADOW_FULLMATCH(parent._shadow[ss - ps : se - ps])
         self._shadow_match_cache = shadow_match, self_string
-        return shadow_match
+        return shadow_match  # type: ignore
 
     @property
     def name(self) -> str:

{wikitextparser-0.56.2 → wikitextparser-0.56.4}/wikitextparser/_cell.py

@@ -1,8 +1,10 @@
-from typing import Dict, List, Match, MutableSequence, Union
+from __future__ import annotations
 
-from regex import DOTALL, VERBOSE
+from typing import MutableSequence
 
-from ._spans import ATTRS_MATCH
+from regex import DOTALL, VERBOSE, Match
+
+from ._spans import ATTRS_MATCH, TypeToSpans
 from ._tag import SubWikiTextWithAttrs
 from ._wikitext import rc
 
@@ -140,19 +142,18 @@ INLINE_NONHAEDER_CELL_MATCH = rc(
 
 
 class Cell(SubWikiTextWithAttrs):
-    __slots__ = '_header', '_match_cache', '_attrs_match_cache'
+    __slots__ = '_attrs_match_cache', '_header', '_match_cache'
 
     def __init__(
         self,
-        string: Union[str, MutableSequence[str]],
+        string: str | MutableSequence[str],
         header: bool = False,
-        _type_to_spans: Dict[str, List[List[int]]] = None,
-        _span: int = None,
-        _type: int = None,
-        _match: Match = None,
-        _attrs_match: Match = None,
+        _type_to_spans: TypeToSpans | None = None,
+        _span: list | None = None,
+        _type: int | None = None,
+        _match: Match | None = None,
+        _attrs_match: Match | None = None,
     ) -> None:
-        """Initialize the object."""
         super().__init__(string, _type_to_spans, _span, _type)
         self._header = header
         if _match:
@@ -175,7 +176,7 @@ class Cell(SubWikiTextWithAttrs):
             self._attrs_match_cache = self._match_cache = None, None
 
     @property
-    def _match(self):
+    def _match(self) -> Match[bytes]:
         """Return the match object for the current tag. Cache the result.
 
         Be extra careful when using this property. The position of match
@@ -185,15 +186,15 @@ class Cell(SubWikiTextWithAttrs):
         cache_match, cache_string = self._match_cache
         string = self.string
         if cache_string == string:
-            return cache_match
+            return cache_match  # type: ignore
         shadow = self._shadow
         if shadow[0] == 10:  # ord('\n')
-            m = NEWLINE_CELL_MATCH(shadow)
+            m: Match[bytes] = NEWLINE_CELL_MATCH(shadow)  # type: ignore
             self._header = m['sep'] == 33  # ord('!')
         elif self._header:
-            m = INLINE_HAEDER_CELL_MATCH(shadow)
+            m = INLINE_HAEDER_CELL_MATCH(shadow)  # type: ignore
         else:
-            m = INLINE_NONHAEDER_CELL_MATCH(shadow)
+            m = INLINE_NONHAEDER_CELL_MATCH(shadow)  # type: ignore
         self._match_cache = m, string
         self._attrs_match_cache = None, None
         return m
@@ -245,7 +246,7 @@ class Cell(SubWikiTextWithAttrs):
         attrs_start, attrs_end = cell_match.span('attrs')
         if attrs_start != -1:
             encoded_attr_name = attr_name.encode()
-            attrs_m = ATTRS_MATCH(shadow, attrs_start, attrs_end)
+            attrs_m: Match[bytes] = ATTRS_MATCH(shadow, attrs_start, attrs_end)  # type: ignore
             for i, n in enumerate(reversed(attrs_m.captures('attr_name'))):
                 if n == encoded_attr_name:
                     vs, ve = attrs_m.spans('attr_value')[-i - 1]

{wikitextparser-0.56.2 → wikitextparser-0.56.4}/wikitextparser/_comment_bold_italic.py

@@ -1,7 +1,10 @@
-from typing import Dict, List, MutableSequence, Optional, Tuple, Union
+from __future__ import annotations
 
-from regex import DOTALL, MULTILINE
+from typing import MutableSequence
 
+from regex import DOTALL, MULTILINE, Match
+
+from ._spans import TypeToSpans
 from ._wikitext import SubWikiText, rc
 
 COMMENT_PATTERN = r'<!--[\s\S]*?(?>-->|\Z)'
@@ -29,13 +32,16 @@ class Comment(SubWikiText):
         return s[4:]
 
     @property
-    def comments(self) -> List['Comment']:
+    def comments(self) -> list[Comment]:
         return []
 
 
 class BoldItalic(SubWikiText):
     __slots__ = ()
 
+    @property
+    def _match(self) -> Match[str]: ...
+
     @property
     def text(self) -> str:
         """Return text value of self (without triple quotes)."""
@@ -49,7 +55,7 @@ class BoldItalic(SubWikiText):
         self[b:e] = s
 
     @property
-    def _content_span(self) -> Tuple[int, int]:
+    def _content_span(self) -> tuple[int, int]:
         # noinspection PyUnresolvedReferences
         return self._match.span(1)
 
@@ -58,8 +64,8 @@ class Bold(BoldItalic):
     __slots__ = ()
 
     @property
-    def _match(self):
-        return BOLD_FULLMATCH(self.string)
+    def _match(self) -> Match[str]:
+        return BOLD_FULLMATCH(self.string)  # type: ignore
 
 
 class Italic(BoldItalic):
@@ -67,10 +73,10 @@ class Italic(BoldItalic):
 
     def __init__(
         self,
-        string: Union[str, MutableSequence[str]],
-        _type_to_spans: Optional[Dict[str, List[List[int]]]] = None,
-        _span: Optional[List[int]] = None,
-        _type: Optional[Union[str, int]] = None,
+        string: str | MutableSequence[str],
+        _type_to_spans: TypeToSpans | None = None,
+        _span: list[int] | None = None,
+        _type: str | int | None = None,
         end_token: bool = True,
     ):
         """Initialize the Italic object.
@@ -82,7 +88,7 @@ class Italic(BoldItalic):
         self.end_token = end_token
 
     @property
-    def _match(self):
+    def _match(self) -> Match[str]:
         if self.end_token:
-            return ITALIC_FULLMATCH(self.string)
-        return ITALIC_NOEND_FULLMATCH(self.string)
+            return ITALIC_FULLMATCH(self.string)  # type: ignore
+        return ITALIC_NOEND_FULLMATCH(self.string)  # type: ignore

{wikitextparser-0.56.2 → wikitextparser-0.56.4}/wikitextparser/_config.py

@@ -14,7 +14,7 @@ def _plant_trie(strings: _Iterable[str]) -> dict:
     for string in strings:
         d = trie
         for char in string:
-            d[char] = char in d and d[char] or {}
+            d[char] = (char in d and d[char]) or {}
             d = d[char]
         d[''] = None  # EOS
     return trie

{wikitextparser-0.56.2 → wikitextparser-0.56.4}/wikitextparser/_externallink.py

@@ -1,4 +1,4 @@
-from typing import List, Optional
+from __future__ import annotations
 
 from ._wikitext import BRACKET_EXTERNAL_LINK_URL, IGNORECASE, SubWikiText, rc
 
@@ -17,7 +17,7 @@ class ExternalLink(SubWikiText):
             external links.
         """
         if self(0) == '[':
-            return self(1, URL_MATCH(self._ext_link_shadow, 1).end())
+            return self(1, URL_MATCH(self._ext_link_shadow, 1).end())  # type: ignore
         return self.string
 
     @url.setter
@@ -28,7 +28,7 @@ class ExternalLink(SubWikiText):
             self[0 : len(self.url)] = newurl
 
     @property
-    def text(self) -> Optional[str]:
+    def text(self) -> str | None:
         """The text part (the part after the url).
 
         getter: Return None if this is a bare link or has no associated text.
@@ -38,7 +38,7 @@ class ExternalLink(SubWikiText):
         """
         string = self.string
         if string[0] == '[':
-            url_end = URL_MATCH(self._ext_link_shadow, 1).end()
+            url_end = URL_MATCH(self._ext_link_shadow, 1).end()  # type: ignore
             end_char = string[url_end]
             if end_char == ']':
                 return None
@@ -74,5 +74,5 @@ class ExternalLink(SubWikiText):
         return self(0) == '['
 
     @property
-    def external_links(self) -> List['ExternalLink']:
+    def external_links(self) -> list[ExternalLink]:
         return []

{wikitextparser-0.56.2 → wikitextparser-0.56.4}/wikitextparser/_parameter.py

@@ -1,4 +1,4 @@
-from typing import List, Optional, Tuple
+from __future__ import annotations
 
 from ._wikitext import WS, SubWikiText
 
@@ -35,7 +35,7 @@ class Parameter(SubWikiText):
         return '|' if self._shadow.find(124) != -1 else ''
 
     @property
-    def default(self) -> Optional[str]:
+    def default(self) -> str | None:
         """The default value of current parameter.
 
         getter: Return None if there is no default.
@@ -100,9 +100,9 @@ class Parameter(SubWikiText):
             ] = '{{{' + new_default_name + '|' + innermost_default + '}}}'
 
     @property
-    def parameters(self) -> List['Parameter']:
+    def parameters(self) -> list[Parameter]:
         return super().parameters[1:]
 
     @property
-    def _content_span(self) -> Tuple[int, int]:
+    def _content_span(self) -> tuple[int, int]:
         return 3, -3

{wikitextparser-0.56.2 → wikitextparser-0.56.4}/wikitextparser/_parser_function.py

@@ -1,5 +1,7 @@
+from __future__ import annotations
+
 from bisect import insort
-from typing import Iterable, List, Tuple, Union
+from typing import Iterable
 
 from ._argument import Argument
 from ._wikilist import WikiList
@@ -19,7 +21,7 @@ class SubWikiTextWithArgs(SubWikiText):
     _first_arg_sep = 0
 
     @property
-    def _content_span(self) -> Tuple[int, int]:
+    def _content_span(self) -> tuple[int, int]:
         return 2, -2
 
     @property
@@ -32,7 +34,7 @@ class SubWikiTextWithArgs(SubWikiText):
         return self._nesting_level(('Template', 'ParserFunction'))
 
     @property
-    def arguments(self) -> List[Argument]:
+    def arguments(self) -> list[Argument]:
         """Parse template content. Create self.name and self.arguments."""
         shadow = self._shadow
         split_spans = self._name_args_matcher(shadow, 2, -2).spans('arg')
@@ -65,8 +67,8 @@ class SubWikiTextWithArgs(SubWikiText):
         return arguments
 
     def get_lists(
-        self, pattern: Union[str, Iterable[str]] = (r'\#', r'\*', '[:;]')
-    ) -> List[WikiList]:
+        self, pattern: str | Iterable[str] = (r'\#', r'\*', '[:;]')
+    ) -> list[WikiList]:
         """Return the lists in all arguments.
 
         For performance reasons it is usually preferred to get a specific
@@ -103,5 +105,5 @@ class ParserFunction(SubWikiTextWithArgs):
     _first_arg_sep = 58
 
     @property
-    def parser_functions(self) -> List['ParserFunction']:
+    def parser_functions(self) -> list[ParserFunction]:
         return super().parser_functions[1:]

{wikitextparser-0.56.2 → wikitextparser-0.56.4}/wikitextparser/_section.py

@@ -1,4 +1,6 @@
-from typing import Optional
+from __future__ import annotations
+
+from regex import Match
 
 from ._wikitext import SubWikiText, rc
 
@@ -37,7 +39,7 @@ class Section(SubWikiText):
 
     @level.setter
     def level(self, value: int) -> None:
-        m = self._header_match
+        m: Match[bytes] = self._header_match  # type: ignore
         level_diff = len(m[1]) - value
         if level_diff == 0:
             return
@@ -50,7 +52,7 @@ class Section(SubWikiText):
         del self[m.end(2) : m.end(2) + level_diff]
 
     @property
-    def title(self) -> Optional[str]:
+    def title(self) -> str | None:
         """The title of this section.
 
         getter: Return the title or None for lead sections or sections that

{wikitextparser-0.56.2 → wikitextparser-0.56.4}/wikitextparser/_spans.py

@@ -1,7 +1,9 @@
 """Define the functions required for parsing wikitext into spans."""
 
+from __future__ import annotations
+
 from functools import partial
-from typing import Callable, Dict, Optional
+from typing import Callable, Dict, List, Union
 
 from regex import DOTALL, IGNORECASE, REVERSE, Match, compile as rc
 
@@ -210,7 +212,11 @@ HTML_END_TAG_FINDITER = rc(
 ).finditer
 
 
-def parse_to_spans(byte_array: bytearray) -> Dict[str, list]:
+# [stan_start: int, span_end: int, Match, byte_array]
+TypeToSpans = Dict[Union[str, int], List[List]]
+
+
+def parse_to_spans(byte_array: bytearray) -> TypeToSpans:
     """Calculate and set self._type_to_spans.
 
     Extracted spans will be removed from byte_array.
@@ -321,7 +327,7 @@ def extract_tag_extensions(
 def _parse_sub_spans(
     byte_array: bytearray,
     start: int,
-    end: Optional[int],
+    end: int | None,
     pms_append: Callable,
     pfs_append: Callable,
     tls_append: Callable,
@@ -336,7 +342,7 @@ def _parse_sub_spans(
         byte_array[ms:me] = byte_array[ms:me].translate(BRACKETS)
     while True:
         while True:
-            match: Optional[Match] = None
+            match: Match | None = None
             for match in WIKILINK_PARAM_FINDITER(byte_array, start, end):
                 ms, me = match.span()
                 if match[1] is None: