Merge pull request #1170 from python-babel/small-cleanup

Small cleanups

Author: akx

.pre-commit-config.yaml

@@ -1,6 +1,6 @@
 repos:
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.8.2
+    rev: v0.9.1
     hooks:
       - id: ruff
         args:

README.rst

@@ -9,7 +9,7 @@ Details can be found in the HTML files in the ``docs`` folder.
 
 For more information please visit the Babel web site:
 
-http://babel.pocoo.org/
+https://babel.pocoo.org/
 
 Join the chat at https://gitter.im/python-babel/babel
 

babel/__init__.py

@@ -30,6 +30,7 @@
 __all__ = [
     'Locale',
     'UnknownLocaleError',
+    '__version__',
     'default_locale',
     'get_locale_identifier',
     'negotiate_locale',

babel/core.py

@@ -18,8 +18,15 @@
 from babel import localedata
 from babel.plural import PluralRule
 
-__all__ = ['UnknownLocaleError', 'Locale', 'default_locale', 'negotiate_locale',
-           'parse_locale']
+__all__ = [
+    'Locale',
+    'UnknownLocaleError',
+    'default_locale',
+    'get_global',
+    'get_locale_identifier',
+    'negotiate_locale',
+    'parse_locale',
+]
 
 if TYPE_CHECKING:
     from typing_extensions import Literal, TypeAlias
@@ -259,6 +266,7 @@ def negotiate(
         :param preferred: the list of locale identifiers preferred by the user
         :param available: the list of locale identifiers available
         :param aliases: a dictionary of aliases for locale identifiers
+        :param sep: separator for parsing; e.g. Windows tends to use '-' instead of '_'.
         """
         identifier = negotiate_locale(preferred, available, sep=sep,
                                       aliases=aliases)
@@ -575,7 +583,7 @@ def languages(self) -> localedata.LocaleDataDict:
         >>> Locale('de', 'DE').languages['ja']
         u'Japanisch'
 
-        See `ISO 639 <http://www.loc.gov/standards/iso639-2/>`_ for
+        See `ISO 639 <https://www.loc.gov/standards/iso639-2/>`_ for
         more information.
         """
         return self._data['languages']
@@ -587,7 +595,7 @@ def scripts(self) -> localedata.LocaleDataDict:
         >>> Locale('en', 'US').scripts['Hira']
         u'Hiragana'
 
-        See `ISO 15924 <http://www.evertype.com/standards/iso15924/>`_
+        See `ISO 15924 <https://www.unicode.org/iso15924/>`_
         for more information.
         """
         return self._data['scripts']
@@ -599,7 +607,7 @@ def territories(self) -> localedata.LocaleDataDict:
         >>> Locale('es', 'CO').territories['DE']
         u'Alemania'
 
-        See `ISO 3166 <http://www.iso.org/iso/en/prods-services/iso3166ma/>`_
+        See `ISO 3166 <https://en.wikipedia.org/wiki/ISO_3166>`_
         for more information.
         """
         return self._data['territories']

babel/dates.py

@@ -1935,14 +1935,18 @@ def match_skeleton(skeleton: str, options: Iterable[str], allow_different_fields
     :type skeleton: str
     :param options: An iterable of other skeletons to match against
     :type options: Iterable[str]
+    :param allow_different_fields: Whether to allow a match that uses different fields
+                                   than the skeleton requested.
+    :type allow_different_fields: bool
+
     :return: The closest skeleton match, or if no match was found, None.
     :rtype: str|None
     """
 
     # TODO: maybe implement pattern expansion?
 
     # Based on the implementation in
-    # http://source.icu-project.org/repos/icu/icu4j/trunk/main/classes/core/src/com/ibm/icu/text/DateIntervalInfo.java
+    # https://github.com/unicode-org/icu/blob/main/icu4j/main/core/src/main/java/com/ibm/icu/text/DateIntervalInfo.java
 
     # Filter out falsy values and sort for stability; when `interval_formats` is passed in, there may be a None key.
     options = sorted(option for option in options if option)

babel/messages/catalog.py

@@ -29,7 +29,14 @@
 
     _MessageID: TypeAlias = str | tuple[str, ...] | list[str]
 
-__all__ = ['Message', 'Catalog', 'TranslationError']
+__all__ = [
+    'DEFAULT_HEADER',
+    'PYTHON_FORMAT',
+    'Catalog',
+    'Message',
+    'TranslationError',
+]
+
 
 def get_close_matches(word, possibilities, n=3, cutoff=0.6):
     """A modified version of ``difflib.get_close_matches``.
@@ -42,7 +49,7 @@ def get_close_matches(word, possibilities, n=3, cutoff=0.6):
     if not 0.0 <= cutoff <= 1.0:  # pragma: no cover
         raise ValueError(f"cutoff must be in [0.0, 1.0]: {cutoff!r}")
     result = []
-    s = SequenceMatcher(autojunk=False) # only line changed from difflib.py
+    s = SequenceMatcher(autojunk=False)  # only line changed from difflib.py
     s.set_seq2(word)
     for x in possibilities:
         s.set_seq1(x)
@@ -274,6 +281,14 @@ def parse_separated_header(value: str) -> dict[str, str]:
     return dict(m.get_params())
 
 
+def _force_text(s: str | bytes, encoding: str = 'utf-8', errors: str = 'strict') -> str:
+    if isinstance(s, str):
+        return s
+    if isinstance(s, bytes):
+        return s.decode(encoding, errors)
+    return str(s)
+
+
 class Catalog:
     """Representation of a message catalog."""
 
@@ -428,46 +443,39 @@ def _set_header_comment(self, string: str | None) -> None:
     """)
 
     def _get_mime_headers(self) -> list[tuple[str, str]]:
-        headers: list[tuple[str, str]] = []
-        headers.append(("Project-Id-Version", f"{self.project} {self.version}"))
-        headers.append(('Report-Msgid-Bugs-To', self.msgid_bugs_address))
-        headers.append(('POT-Creation-Date',
-                        format_datetime(self.creation_date, 'yyyy-MM-dd HH:mmZ',
-                                        locale='en')))
         if isinstance(self.revision_date, (datetime.datetime, datetime.time, int, float)):
-            headers.append(('PO-Revision-Date',
-                            format_datetime(self.revision_date,
-                                            'yyyy-MM-dd HH:mmZ', locale='en')))
+            revision_date = format_datetime(self.revision_date, 'yyyy-MM-dd HH:mmZ', locale='en')
         else:
-            headers.append(('PO-Revision-Date', self.revision_date))
-        headers.append(('Last-Translator', self.last_translator))
+            revision_date = self.revision_date
+
+        language_team = self.language_team
+        if self.locale_identifier and 'LANGUAGE' in language_team:
+            language_team = language_team.replace('LANGUAGE', str(self.locale_identifier))
+
+        headers: list[tuple[str, str]] = [
+            ("Project-Id-Version", f"{self.project} {self.version}"),
+            ('Report-Msgid-Bugs-To', self.msgid_bugs_address),
+            ('POT-Creation-Date', format_datetime(self.creation_date, 'yyyy-MM-dd HH:mmZ', locale='en')),
+            ('PO-Revision-Date', revision_date),
+            ('Last-Translator', self.last_translator),
+        ]
         if self.locale_identifier:
             headers.append(('Language', str(self.locale_identifier)))
-        if self.locale_identifier and ('LANGUAGE' in self.language_team):
-            headers.append(('Language-Team',
-                            self.language_team.replace('LANGUAGE',
-                                                       str(self.locale_identifier))))
-        else:
-            headers.append(('Language-Team', self.language_team))
+        headers.append(('Language-Team', language_team))
         if self.locale is not None:
             headers.append(('Plural-Forms', self.plural_forms))
-        headers.append(('MIME-Version', '1.0'))
-        headers.append(("Content-Type", f"text/plain; charset={self.charset}"))
-        headers.append(('Content-Transfer-Encoding', '8bit'))
-        headers.append(("Generated-By", f"Babel {VERSION}\n"))
+        headers += [
+            ('MIME-Version', '1.0'),
+            ("Content-Type", f"text/plain; charset={self.charset}"),
+            ('Content-Transfer-Encoding', '8bit'),
+            ("Generated-By", f"Babel {VERSION}\n"),
+        ]
         return headers
 
-    def _force_text(self, s: str | bytes, encoding: str = 'utf-8', errors: str = 'strict') -> str:
-        if isinstance(s, str):
-            return s
-        if isinstance(s, bytes):
-            return s.decode(encoding, errors)
-        return str(s)
-
     def _set_mime_headers(self, headers: Iterable[tuple[str, str]]) -> None:
         for name, value in headers:
-            name = self._force_text(name.lower(), encoding=self.charset)
-            value = self._force_text(value, encoding=self.charset)
+            name = _force_text(name.lower(), encoding=self.charset)
+            value = _force_text(value, encoding=self.charset)
             if name == 'project-id-version':
                 parts = value.split(' ')
                 self.project = ' '.join(parts[:-1])
@@ -824,6 +832,9 @@ def update(
 
         :param template: the reference catalog, usually read from a POT file
         :param no_fuzzy_matching: whether to use fuzzy matching of message IDs
+        :param update_header_comment: whether to copy the header comment from the template
+        :param keep_user_comments: whether to keep user comments from the old catalog
+        :param update_creation_date: whether to copy the creation date from the template
         """
         messages = self._messages
         remaining = messages.copy()

babel/messages/extract.py

@@ -325,15 +325,20 @@ def extract_from_file(
                             options, strip_comment_tags))
 
 
-def _match_messages_against_spec(lineno: int, messages: list[str|None], comments: list[str],
-                                 fileobj: _FileObj, spec: tuple[int|tuple[int, str], ...]):
+def _match_messages_against_spec(
+    lineno: int,
+    messages: list[str | None],
+    comments: list[str],
+    fileobj: _FileObj,
+    spec: tuple[int | tuple[int, str], ...],
+):
     translatable = []
     context = None
 
     # last_index is 1 based like the keyword spec
     last_index = len(messages)
     for index in spec:
-        if isinstance(index, tuple): # (n, 'c')
+        if isinstance(index, tuple):  # (n, 'c')
             context = messages[index[0] - 1]
             continue
         if last_index < index:
@@ -421,7 +426,6 @@ def extract(
     :returns: iterable of tuples of the form ``(lineno, message, comments, context)``
     :rtype: Iterable[tuple[int, str|tuple[str], list[str], str|None]
     """
-    func = None
     if callable(method):
         func = method
     elif ':' in method or '.' in method:
@@ -622,9 +626,7 @@ def extract_python(
         elif tok == NAME and value in keywords:
             funcname = value
 
-        if (current_fstring_start is not None
-            and tok not in {FSTRING_START, FSTRING_MIDDLE}
-        ):
+        if current_fstring_start is not None and tok not in {FSTRING_START, FSTRING_MIDDLE}:
             # In Python 3.12, tokens other than FSTRING_* mean the
             # f-string is dynamic, so we don't wan't to extract it.
             # And if it's FSTRING_END, we've already handled it above.

babel/messages/frontend.py

@@ -961,7 +961,7 @@ def _configure_command(self, cmdname, argv):
             usage=self.usage % (cmdname, ''),
             description=self.commands[cmdname],
         )
-        as_args = getattr(cmdclass, "as_args", ())
+        as_args: str | None = getattr(cmdclass, "as_args", None)
         for long, short, help in cmdclass.user_options:
             name = long.strip("=")
             default = getattr(cmdinst, name.replace("-", "_"))
@@ -1012,6 +1012,7 @@ def parse_mapping_cfg(fileobj, filename=None):
 
     :param fileobj: a readable file-like object containing the configuration
                     text to parse
+    :param filename: the name of the file being parsed, for error messages
     """
     extractors = {}
     method_map = []

babel/messages/jslexer.py

@@ -162,6 +162,7 @@ def tokenize(source: str, jsx: bool = True, dotted: bool = True, template_string
     """
     Tokenize JavaScript/JSX source.  Returns a generator of tokens.
 
+    :param source: The JavaScript source to tokenize.
     :param jsx: Enable (limited) JSX parsing.
     :param dotted: Read dotted names as single name token.
     :param template_string: Support ES6 template strings

babel/messages/plurals.py

@@ -9,8 +9,6 @@
 """
 from __future__ import annotations
 
-from operator import itemgetter
-
 from babel.core import Locale, default_locale
 
 # XXX: remove this file, duplication with babel.plural
@@ -209,12 +207,21 @@ class _PluralTuple(tuple):
     """A tuple with plural information."""
 
     __slots__ = ()
-    num_plurals = property(itemgetter(0), doc="""
-    The number of plurals used by the locale.""")
-    plural_expr = property(itemgetter(1), doc="""
-    The plural expression used by the locale.""")
-    plural_forms = property(lambda x: 'nplurals={}; plural={};'.format(*x), doc="""
-    The plural expression used by the catalog or locale.""")
+
+    @property
+    def num_plurals(self) -> int:
+        """The number of plurals used by the locale."""
+        return self[0]
+
+    @property
+    def plural_expr(self) -> str:
+        """The plural expression used by the locale."""
+        return self[1]
+
+    @property
+    def plural_forms(self) -> str:
+        """The plural expression used by the catalog or locale."""
+        return f'nplurals={self[0]}; plural={self[1]};'
 
     def __str__(self) -> str:
         return self.plural_forms