Set up pre-commit (#13)

.pre-commit-config.yaml

@@ -0,0 +1,26 @@
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.6.0
+    hooks:
+      - id: check-ast
+      - id: check-builtin-literals
+      - id: check-yaml
+      - id: end-of-file-fixer
+      - id: fix-encoding-pragma
+        args:
+          - --remove
+      - id: mixed-line-ending
+        args:
+          - --fix=lf
+      - id: trailing-whitespace
+
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.4.7
+    hooks:
+      - id: ruff
+      - id: ruff-format
+
+  - repo: https://github.com/pycqa/isort
+    rev: 5.13.2
+    hooks:
+      - id: isort

changes.rst

@@ -3,7 +3,7 @@ Changelog
 
 5.0
 ------------------------
-- Fork lingua as lingva. 
+- Fork lingua as lingva.
 - Bump version to 5.0.
 
 4.??
@@ -16,7 +16,7 @@ Changelog
 4.15 - February 12, 2022
 ------------------------
 
-- Fix file not found error with ``--list-files`` due to a ``\n`` appended 
+- Fix file not found error with ``--list-files`` due to a ``\n`` appended
   to each filename.
   `Patch #97 <https://github.com/wichert/lingua/pull/102>`_ from Johannes Raggam.
 

pyproject.toml

@@ -54,3 +54,19 @@ norecursedirs = ".git tmp* .eggs bin build include lib share src"
 
 [tool.setuptools.dynamic]
 version = { attr = "lingva.__version__" }
+
+[tool.isort]
+known_first_party = ["lingva", "tests"]
+line_length = 99
+multi_line_output = 3
+profile = "black"
+
+[tool.ruff]
+line-length = 99
+target-version = "py311"
+
+[tool.ruff.lint]
+select = ["E4", "E7", "E9", "F"]
+
+[tool.ruff.lint.flake8-errmsg]
+max-string-length = 99

src/lingva/extract.py

@@ -4,22 +4,21 @@
     from collections import OrderedDict
 except ImportError:
     from ordereddict import OrderedDict
-from operator import attrgetter
+
 import os
 import re
 import sys
 import tempfile
 import time
-
 from configparser import ConfigParser as SafeConfigParser
+from operator import attrgetter
+
 import click
 import polib
-from lingva.extractors import get_extractor
-from lingva.extractors import register_extractors
-from lingva.extractors.babel import register_babel_plugins
-from lingva.extractors import EXTRACTORS
-from lingva.extractors import EXTENSIONS
+
 from lingva import __version__
+from lingva.extractors import EXTENSIONS, EXTRACTORS, get_extractor, register_extractors
+from lingva.extractors.babel import register_babel_plugins
 
 
 def po_timestamp():
@@ -116,7 +115,7 @@ def list_files(files_from, sources):
         if os.path.isfile(file):
             yield file
         elif os.path.isdir(file):
-            for (dirpath, dirnames, filenames) in os.walk(file):
+            for dirpath, dirnames, filenames in os.walk(file):
                 for file in filenames:
                     if get_extractor(file) is not None:
                         yield os.path.join(dirpath, file)
@@ -146,9 +145,7 @@ def strip_linenumbers(entry):
     entry.occurrences = occurrences
 
 
-def create_catalog(
-    width, copyright_holder, package_name, package_version, msgid_bugs_address
-):
+def create_catalog(width, copyright_holder, package_name, package_version, msgid_bugs_address):
     catalog = POFile(wrapwidth=width)
     catalog.copyright_holder = copyright_holder
     catalog.package_name = package_name
@@ -174,8 +171,7 @@ def create_catalog(
 def _register_extension(extension, extractor):
     if extractor not in EXTRACTORS:
         click.echo(
-            "Unknown extractor %s. Check --list-extractors for available options"
-            % extractor,
+            "Unknown extractor %s. Check --list-extractors for available options" % extractor,
             err=True,
         )
         sys.exit(1)
@@ -187,7 +183,7 @@ def read_config(cfg_file):
     config.read_file(cfg_file)
     for section in config.sections():
         if section == "extensions":
-            for (extension, extractor) in config.items(section):
+            for extension, extractor in config.items(section):
                 _register_extension(extension, extractor)
         elif section.startswith("extractor:"):
             extractor = section[10:]
@@ -202,8 +198,7 @@ def read_config(cfg_file):
             EXTRACTORS[extractor].update_config(**extractor_config)
         elif section.startswith("extension"):
             click.echo(
-                "Use of %s section is obsolete. "
-                'Please use the "extensions" section.' % section,
+                "Use of %s section is obsolete. " 'Please use the "extensions" section.' % section,
                 err=True,
             )
             extension = section[10:]
@@ -286,9 +281,7 @@ def __init__(self, comment_tag, domain, keywords):
     help="Add DIRECTORY to list of paths to check for input files",
 )
 @click.argument("sources", nargs=-1, type=click.Path(exists=True))
-@click.option(
-    "--list-extractors", is_flag=True, help="List all known extraction plugins"
-)
+@click.option("--list-extractors", is_flag=True, help="List all known extraction plugins")
 # Output options
 @click.option(
     "-o",
@@ -359,9 +352,7 @@ def __init__(self, comment_tag, domain, keywords):
     default="1.0",
     help="Package version to use in the generated POT file",
 )
-@click.option(
-    "--msgid-bugs-address", metavar="EMAIL", help="Email address bugs should be send to"
-)
+@click.option("--msgid-bugs-address", metavar="EMAIL", help="Email address bugs should be send to")
 def main(
     cfg_file,
     files_from,

src/lingva/extractors/__init__.py

@@ -1,14 +1,13 @@
 from __future__ import print_function
 
-from importlib.metadata import entry_points
-
 import abc
 import collections
 import os
 import re
 import sys
-from .compat import add_metaclass
+from importlib.metadata import entry_points
 
+from .compat import add_metaclass
 
 Message = collections.namedtuple(
     "Message", "msgctxt msgid msgid_plural flags comment tcomment location"

src/lingva/extractors/babel.py

@@ -1,13 +1,7 @@
 from importlib.metadata import entry_points
 
-from .python import KEYWORDS
-from .python import parse_keyword
-from . import EXTRACTORS
-from . import Message
-from . import check_c_format
-from . import check_python_format
-from . import Extractor
-from . import update_keywords
+from . import EXTRACTORS, Extractor, Message, check_c_format, check_python_format, update_keywords
+from .python import KEYWORDS, parse_keyword
 
 
 class BabelExtractor(Extractor):
@@ -23,10 +17,8 @@ def __call__(self, filename, options, fileobj=None, firstline=0):
         if fileobj is None:
             fileobj = open(filename, "rb")
         comment_tags = self.config["comment-tags"].split()
-        messages = self.extractor(
-            fileobj, list(self.keywords.keys()), comment_tags, self.config
-        )
-        for (lineno, function, args, comment) in messages:
+        messages = self.extractor(fileobj, list(self.keywords.keys()), comment_tags, self.config)
+        for lineno, function, args, comment in messages:
             if not isinstance(args, (list, tuple)):
                 args = [args]
             if function in self.keywords:

src/lingva/extractors/python.py

@@ -1,17 +1,20 @@
 from __future__ import print_function
+
 import ast
 import io
 import sys
 import tokenize
 import warnings
-from . import Extractor
-from . import Message
-from . import check_comment_flags
-from . import check_c_format
-from . import check_python_format
-from . import Keyword
-from . import update_keywords
 
+from . import (
+    Extractor,
+    Keyword,
+    Message,
+    check_c_format,
+    check_comment_flags,
+    check_python_format,
+    update_keywords,
+)
 
 try:
     basestring
@@ -84,7 +87,7 @@ def parse_translationstring(arguments, filename, firstline):
         msgid = args[0]
     if len(args) > 2 and isinstance(args[2], basestring):
         default = args[2]
-    for (key, value) in kwargs.items():
+    for key, value in kwargs.items():
         if not isinstance(value, basestring):
             continue
         if key == "msgid":
@@ -184,7 +187,7 @@ def __call__(self, token_stream, options, filename, firstline):
         self.messages = []
         self.handler = self.state_skip
         try:
-            for (token_type, token, location, _) in token_stream:
+            for token_type, token, location, _ in token_stream:
                 self.process_token(token_type, token, location, token_stream)
         except tokenize.TokenError as e:
             print(
@@ -223,9 +226,7 @@ def process_comment(self, token, location):
             if self.include_comments == "tagged":
                 comment = comment[len(self.comment_marker) :].strip()
             (flags, comment) = check_comment_flags(comment)
-            if self.messages and self.messages[-1].location[1] == (
-                self.firstline + location[0]
-            ):
+            if self.messages and self.messages[-1].location[1] == (self.firstline + location[0]):
                 last_message = self.messages[-1]
                 # Comment at the end of the line of a keyword call
                 new_comment = []
@@ -341,7 +342,7 @@ def add_argument(self, value, lineno):
 
     def skip_iterable(self, start_token, end_token, token_stream):
         depth = 1
-        for (token_type, token, loc, _) in token_stream:
+        for token_type, token, loc, _ in token_stream:
             if token_type == tokenize.OP:
                 if token == start_token:
                     depth += 1
@@ -356,9 +357,7 @@ def skip_iterable(self, start_token, end_token, token_stream):
 
     def process_keyword(self):
         if self.keyword is not None:
-            msg = parse_keyword(
-                self.arguments, self.keyword, self.filename, self.firstline
-            )
+            msg = parse_keyword(self.arguments, self.keyword, self.filename, self.firstline)
         else:
             msg = parse_translationstring(self.arguments, self.filename, self.firstline)
         if msg is None: