wikitextparser 0.55.13__tar.gz → 0.56.2__tar.gz

{wikitextparser-0.55.13 → wikitextparser-0.56.2}/.github/workflows/tests.yml

@@ -13,7 +13,7 @@ jobs:
     strategy:
       matrix:
         os: [ubuntu-latest, windows-latest, macos-latest]
-        python-version: ["3.7", "3.8", "3.9", "3.10", "3.11", "3.12"]
+        python-version: ["3.8", "3.9", "3.10", "3.11", "3.12"]
     env:
       OS: ${{ matrix.os }}
       PYTHON: ${{ matrix.python-version }}

{wikitextparser-0.55.13 → wikitextparser-0.56.2}/CHANGELOG.rst

@@ -1,3 +1,19 @@
+v0.56.2
+-------
+* Fixed a bug in ``external_links`` property where ``|`` was recognized as part of the link by mistake. (#139)
+
+v0.56.1
+-------
+* Fixed a bug in ``get_sections`` when ``top_levels_only`` was ``True``.
+
+v0.56.0
+-------
+* Drop Python 3.7 support.
+
+v0.55.14
+--------
+* Fixed a bug in detecting the text of an external link. (#137)
+
 v0.55.13
 --------
 *  Fixed a bug in ``Section.level`` resulting in malformed section titles when multiple levels are added (#135)

{wikitextparser-0.55.13 → wikitextparser-0.56.2}/PKG-INFO

@@ -1,10 +1,10 @@
 Metadata-Version: 2.1
 Name: wikitextparser
-Version: 0.55.13
+Version: 0.56.2
 Summary: A simple parsing tool for MediaWiki's wikitext markup.
 Keywords: MediaWiki,wikitext,parser
 Author-email: 5j9 <5j9@users.noreply.github.com>
-Requires-Python: >= 3.7
+Requires-Python: >= 3.8
 Description-Content-Type: text/x-rst
 Classifier: Programming Language :: Python
 Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3)
@@ -38,7 +38,7 @@ The purpose is to allow users easily extract and/or manipulate templates, templa
 Installation
 ============
 
-- Python 3.7+ is required
+- Python 3.8+ is required
 - ``pip install wikitextparser``
 
 Usage

{wikitextparser-0.55.13 → wikitextparser-0.56.2}/README.rst

@@ -19,7 +19,7 @@ The purpose is to allow users easily extract and/or manipulate templates, templa
 Installation
 ============
 
-- Python 3.7+ is required
+- Python 3.8+ is required
 - ``pip install wikitextparser``
 
 Usage

{wikitextparser-0.55.13 → wikitextparser-0.56.2}/pyproject.toml

@@ -19,7 +19,7 @@ classifiers = [
     "License :: OSI Approved :: GNU General Public License v3 (GPLv3)",
     "Topic :: Text Processing",
 ]
-requires-python = ">= 3.7"
+requires-python = ">= 3.8"
 dependencies = [
     "regex >= 2022.9.11",
     "wcwidth",

{wikitextparser-0.55.13 → wikitextparser-0.56.2}/wikitextparser/__init__.py

@@ -1,5 +1,5 @@
 # Scheme: [N!]N(.N)*[{a|b|rc}N][.postN][.devN]
-__version__ = '0.55.13'
+__version__ = '0.56.2'
 
 from . import _wikitext
 from ._argument import Argument  # noqa: F401

{wikitextparser-0.55.13 → wikitextparser-0.56.2}/wikitextparser/_wikitext.py

@@ -63,13 +63,13 @@ EXTERNAL_LINK = (
     rb'(?>' + BARE_EXTERNAL_LINK + rb'|' + BRACKET_EXTERNAL_LINK + rb')'
 )
 EXTERNAL_LINK_FINDITER = rc(EXTERNAL_LINK, IGNORECASE).finditer
-INVALID_EXT_CHARS_SUB = rc(  # the [:-4] slice allows \[ and \]
-    rb'[' + INVALID_URL_CHARS[:-4] + rb'{}]'
+INVALID_EL_TPP_CHRS_SUB = rc(  # the [:-4] slice allows \[ and \]
+    rb'[' + INVALID_URL_CHARS[:-4] + rb'{}|]'
 ).sub
 
 # Sections
 SECTION_HEADING = rb'^(?<equals>={1,6})[^\n]+?(?P=equals)[ \t]*+$'
-SUBSECTION_HEADING = rb'^(?P=equals)=[^\n]+?(?P=equals)=[ \t]*+$'
+SUB_SECTION = rb'(?:^(?P=equals)=[^\n]+?(?P=equals)=[ \t]*+$.*?)*'
 LEAD_SECTION = rb'(?<section>(?<equals>).*?)'
 SECTIONS_FULLMATCH = rc(
     LEAD_SECTION
@@ -84,9 +84,8 @@ SECTIONS_TOP_LEVELS_ONLY = rc(
     + rb'(?<section>'
     + SECTION_HEADING
     + rb'.*?'
-    + SUBSECTION_HEADING
-    + rb'.*?'
-    rb')*',
+    + SUB_SECTION
+    + rb')*',
     DOTALL | MULTILINE | VERBOSE,
 ).fullmatch
 
@@ -432,10 +431,7 @@ class WikiText:
     @property
     def span(self) -> tuple:
         """Return the span of self relative to the start of the root node."""
-        # In Python 3.7 and earlier, generalized iterable unpacking in yield
-        # and return statements requires enclosing parentheses:
-        # https://docs.python.org/3.8/whatsnew/3.8.html#other-language-changes
-        return (*self._span_data[:2],)  # noqa
+        return (*self._span_data[:2],)
 
     @property
     def string(self) -> str:
@@ -1194,7 +1190,7 @@ class WikiText:
         )
 
     @property
-    def _ext_link_shadow(self):
+    def _ext_link_shadow(self) -> bytearray:
         """Replace the invalid chars of SPAN_PARSER_TYPES with b'_'.
 
         For comments, all characters are replaced, but for ('Template',
@@ -1204,12 +1200,14 @@ class WikiText:
         byte_array = bytearray(self._lststr[0][ss:se], 'ascii', 'replace')
         subspans = self._subspans
         for s, e, _, _ in subspans('Comment'):
-            byte_array[s:e] = (e - s) * b'_'
+            byte_array[s - ss : e - ss] = (e - s) * b'_'
         for s, e, _, _ in subspans('WikiLink'):
-            byte_array[s:e] = (e - s) * b' '
+            byte_array[s - ss : e - ss] = (e - s) * b' '
         for type_ in 'Template', 'ParserFunction', 'Parameter':
             for s, e, _, _ in subspans(type_):
-                byte_array[s:e] = INVALID_EXT_CHARS_SUB(b' ', byte_array[s:e])
+                byte_array[s - ss : e - ss] = INVALID_EL_TPP_CHRS_SUB(
+                    b' ', byte_array[s:e]
+                )
         return byte_array
 
     @property