chore: use more of ruff

nijel · nijel · commit 4f022f705286 · 2025-02-05T14:40:41.000+01:00
diff --git a/pyproject.toml b/pyproject.toml
@@ -104,6 +104,11 @@ target-version = "py39"
 [tool.ruff.lint]
 ignore = [
   "D10",  # TODO: we are missing many docstrings
+  "PTH",  # TODO: Not using pathlib
+  "EM",  # TODO: exception literals
+  "PERF401",  # TODO
+  "COM812",  # CONFIG: trailing newlines
+  "FBT",  # TODO: Boolean in function definition
   "D203",  # CONFIG: incompatible with D211
   "D212",  # CONFIG: incompatible with D213
   "ISC001",  # CONFIG: incompatible with formatter
@@ -114,44 +119,14 @@ ignore = [
   "RUF012",  # TODO: Mutable class attributes should be annotated with `typing.ClassVar`
   "E501"  # WONTFIX: we accept long strings (rest is formatted by black)
 ]
-select = [
-  "E",
-  "F",
-  "B",
-  "T10",
-  "A",
-  "C4",
-  "C90",
-  "YTT",
-  "DJ",
-  "UP",
-  "D",
-  "PD",
-  "PGH",
-  "PL",
-  "TRY",
-  "RUF",
-  "ERA",
-  "ICN",
-  "ISC",
-  "EXE",
-  "INP",
-  "PIE",
-  "G",
-  "PYI",
-  "Q",
-  "SIM",
-  "TID",
-  "RSE",
-  "T20",
-  "RET",
-  "SLF",
-  "N"
-]
+select = ["ALL"]
 
 [tool.ruff.lint.mccabe]
 max-complexity = 16
 
+[tool.ruff.lint.per-file-ignores]
+"scripts/*" = ["S607", "S603", "S310", "ANN"]
+
 [tool.setuptools]
 include-package-data = true
 # Empty as a workaround for https://github.com/pypa/setuptools/issues/4759
diff --git a/scripts/add-iso b/scripts/add-iso
@@ -54,8 +54,11 @@ for code in sys.argv[1:]:
         sys.stderr.write(f"Failed to load data for {code}, using defaults\n")
     lines.append(
         "{},{},{},{}\n".format(
-            code, names[code].split(";")[-1].strip(), plurals, formula
-        )
+            code,
+            names[code].split(";")[-1].strip(),
+            plurals,
+            formula,
+        ),
     )
 
 with open("languages.csv", "w") as handle:
diff --git a/scripts/add-iso-population b/scripts/add-iso-population
@@ -36,4 +36,7 @@ for code, population in POPULATION.items():
         continue
     if code not in LANGUAGE_CODES and code not in ALIASES:
         print(f"Adding {code} ({population})")
-        subprocess.run(["./scripts/add-iso", code], check=False)
+        subprocess.run(
+            ["./scripts/add-iso", code],
+            check=False,
+        )
diff --git a/scripts/export-cldr b/scripts/export-cldr
@@ -4,6 +4,8 @@
 #
 # SPDX-License-Identifier: MIT
 
+from __future__ import annotations
+
 import json
 import re
 
@@ -106,7 +108,7 @@ def convert_atom(atom: str) -> str | bool:
         # For gettext: f == empty, t == empty, c == empty, e == empty
         return int(match.group(1)) != 0
     raise ValueError(
-        f"Unable to convert the formula chunk '{atom}' from CLDR to gettext"
+        f"Unable to convert the formula chunk '{atom}' from CLDR to gettext",
     )
 
 
@@ -131,7 +133,7 @@ def convert_formula(cldr_formula_and_examples: str) -> str:
     # Sanity checkign
     if "(" in cldr_formula or ")" in cldr_formula:
         raise ValueError(
-            f"Unable to convert the formula '{cldr_formula}': parenthesis handling not implemented"
+            f"Unable to convert the formula '{cldr_formula}': parenthesis handling not implemented",
         )
 
     # Blank formula for other
@@ -176,7 +178,8 @@ def reverse_formula(formula: str) -> str:
         return formula.replace(" == ", " != ").replace(" || ", " && ").strip("()")
 
     if match := re.match(
-        r"^(n(?: % \d+)?) == (\d+) && (n(?: % \d+)?) != (\d+)$", formula
+        r"^(n(?: % \d+)?) == (\d+) && (n(?: % \d+)?) != (\d+)$",
+        formula,
     ):
         return f"{match.group(1)} != {match.group(2)} || {match.group(3)} == {match.group(4)}"
 
@@ -199,7 +202,7 @@ def merge_formulas(formulas: list[str]) -> str:
     for n in range(max_n - 1, -1, -1):
         part = formulas[n]
 
-        if not re.match("^\([^()]+\)$", part):
+        if not re.match(r"^\([^()]+\)$", part):
             part = f"({part})"
         formula = f"{reduce_formula(part)} ? {n} : {formula}"
         if n > 0:
@@ -210,7 +213,7 @@ def merge_formulas(formulas: list[str]) -> str:
 
 # Load language names
 with open(
-    "modules/cldr-json/cldr-json/cldr-localenames-full/main/en/languages.json"
+    "modules/cldr-json/cldr-json/cldr-localenames-full/main/en/languages.json",
 ) as handle:
     data = json.load(handle)
     LANGUAGES = {
@@ -279,5 +282,10 @@ with open("cldr.csv", "w") as handle:
     for code in sorted(LANGUAGES):
         data = LANGUAGES[code]
         handle.write(
-            "{},{},{},{}\n".format(code, data["name"], data["plurals"], data["formula"])
+            "{},{},{},{}\n".format(
+                code,
+                data["name"],
+                data["plurals"],
+                data["formula"],
+            ),
         )
diff --git a/scripts/export-cldr-case b/scripts/export-cldr-case
@@ -4,8 +4,8 @@
 #
 # SPDX-License-Identifier: MIT
 
-import json
 import csv
+import json
 
 # Read languages
 with open("languages.csv") as csvfile:
@@ -25,7 +25,7 @@ with open("case-insensitive.csv") as csvfile:
 with open("modules/cldr-json/cldr-json/cldr-core/scriptMetadata.json") as handle:
     SCRIPTS = json.load(handle)["scriptMetadata"]
 with open(
-    "modules/cldr-json/cldr-json/cldr-core/supplemental/languageData.json"
+    "modules/cldr-json/cldr-json/cldr-core/supplemental/languageData.json",
 ) as handle:
     LANGUAGES = json.load(handle)["supplemental"]["languageData"]
 
diff --git a/scripts/export-cldr-orientation b/scripts/export-cldr-orientation
@@ -4,9 +4,9 @@
 #
 # SPDX-License-Identifier: MIT
 
+import csv
 import json
 from pathlib import Path
-import csv
 
 # Read languages
 with open("languages.csv") as csvfile:
diff --git a/scripts/export-cldr-population b/scripts/export-cldr-population
@@ -12,7 +12,7 @@ MAPPING = {
 }
 
 with open(
-    "modules/cldr-json/cldr-json/cldr-core/supplemental/territoryInfo.json"
+    "modules/cldr-json/cldr-json/cldr-core/supplemental/territoryInfo.json",
 ) as handle:
     languages = defaultdict(int)
     for code, territory in json.load(handle)["supplemental"]["territoryInfo"].items():
diff --git a/scripts/export-gettext b/scripts/export-gettext
@@ -28,7 +28,7 @@ for line in content.splitlines():
                     matches[2],
                     int(matches[3].split(";", 1)[0].split("=")[1]),
                     matches[3].split(";", 1)[1].split("=", 1)[1].rstrip(";"),
-                )
+                ),
             )
 
 with open("gettext.csv", "w") as handle:
diff --git a/scripts/export-iso-aliases b/scripts/export-iso-aliases
@@ -79,7 +79,7 @@ with open(ALIASES) as handle:
         if code in names:
             if names[code] != replacement:
                 print(
-                    f"Conflicting replacement for {code}: {names[code]} != {replacement} {alias}"
+                    f"Conflicting replacement for {code}: {names[code]} != {replacement} {alias}",
                 )
             continue
         names[code] = replacement
diff --git a/scripts/export-l10n-guide b/scripts/export-l10n-guide
@@ -29,7 +29,7 @@ for line in content.splitlines():
                     matches[2],
                     int(plural_parts[0].split("=")[1]),
                     plural_parts[1].split("=", 1)[1].rstrip(";"),
-                )
+                ),
             )
 
 with open("l10n-guide.csv", "w") as handle:
diff --git a/scripts/export-macrolanguages b/scripts/export-macrolanguages
@@ -77,5 +77,6 @@ with open("weblate_language_data/ambiguous.py", "w") as output:
 
 # Black format code
 subprocess.run(
-    ["pre-commit", "run", "--files", "weblate_language_data/ambiguous.py"], check=False
+    ["pre-commit", "run", "--files", "weblate_language_data/ambiguous.py"],
+    check=False,
 )
diff --git a/scripts/export-plural-tags b/scripts/export-plural-tags
@@ -4,8 +4,8 @@
 #
 # SPDX-License-Identifier: MIT
 
-import json
 import csv
+import json
 import pprint
 import subprocess
 
diff --git a/scripts/export-qt b/scripts/export-qt
@@ -4,9 +4,9 @@
 #
 # SPDX-License-Identifier: MIT
 
+import csv
 import os
 import re
-import csv
 
 ALIASES = {
     "Chinese": ("Chinese (Simplified Han script)", "Chinese (Traditional Han script)"),
@@ -46,7 +46,7 @@ def parse_csv(name):
 DEFINITIONS = parse_csv("languages.csv")
 
 plural_definition = re.compile(
-    '{\s*([^,]+)\s*,\s*([^,]+)\s*,\s*([^,]+)\s*,\s*([^,]+)\s*,\s*([^,]+)\s*,\s*"nplurals=([0-9]+); plural=([^"]+);"\s}'
+    r'{\s*([^,]+)\s*,\s*([^,]+)\s*,\s*([^,]+)\s*,\s*([^,]+)\s*,\s*([^,]+)\s*,\s*"nplurals=([0-9]+); plural=([^"]+);"\s}',
 )
 
 LANGUAGES = {}
@@ -59,7 +59,7 @@ def handle_language(parts):
     # Remove duplicate definition
     if name == "frenchStyleLanguages":
         text = text.replace("QLocale::Filipino,", "")
-    # Hack to deal with frenchStyleCountries
+    # Workaround to deal with frenchStyleCountries
     if name == "frenchStyleLanguages":
         text = text.replace("Portuguese", "PortugueseBrasil")
     LANGUAGES[name] = (
@@ -120,7 +120,7 @@ def generate(group, name):
             definition[1],
             plural[0],
             plural[1],
-        )
+        ),
     )
     processed.add(definition[0])
 
diff --git a/scripts/export-translate b/scripts/export-translate
@@ -19,12 +19,14 @@ for code, data in languages.items():
             "name": data[0].split(";")[0],
             "nplurals": data[1],
             "formula": data[2],
-        }
+        },
     )
 
 with open("translate.csv", "w") as handle:
     writer = csv.DictWriter(
-        handle, fieldnames=["code", "name", "nplurals", "formula"], lineterminator="\n"
+        handle,
+        fieldnames=["code", "name", "nplurals", "formula"],
+        lineterminator="\n",
     )
     writer.writeheader()
     writer.writerows(sorted(output, key=lambda x: x["code"]))
diff --git a/scripts/generate-language-data b/scripts/generate-language-data
@@ -17,7 +17,7 @@ from itertools import chain
 
 SPLIT_RE = re.compile(
     r"(?:\&(?:nbsp|rsaquo|lt|gt|amp|ldquo|rdquo|times|quot);|"
-    r'[() ,.^`"\'\\/_<>!?;:|{}*^@%#&~=+\r\n✓—-…\[\]0-9-])+'
+    r'[() ,.^`"\'\\/_<>!?;:|{}*^@%#&~=+\r\n✓—-…\[\]0-9-])+',
 )
 
 HEADER = '''# Copyright © Michal Čihař <michal@weblate.org>
@@ -307,7 +307,7 @@ words.difference_update(
         "use",
         "west",
         "western",
-    }
+    },
 )
 
 # Write same check blacklist
diff --git a/scripts/lint b/scripts/lint
@@ -59,7 +59,7 @@ for match in matching:
     plural_cldr = cldr[match][3]
     if plural_our == "n != 1" and plural_cldr != "n != 1":
         raise ValueError(
-            f"Mismatching plural form for {match}: {plural_our!r} != {plural_cldr!r}"
+            f"Mismatching plural form for {match}: {plural_our!r} != {plural_cldr!r}",
         )
 
 
@@ -76,5 +76,5 @@ for code, _name, plural_count, plural_formula in languages.values():
     )
     if calculated != int(plural_count):
         raise ValueError(
-            f"Mismatching plural count for {code}: {plural_count} != {calculated}"
+            f"Mismatching plural count for {code}: {plural_count} != {calculated}",
         )
diff --git a/scripts/list-diff b/scripts/list-diff
@@ -104,7 +104,7 @@ The Plurals column lists data in languages.csv which is used in Weblate
 
 Code | Name | Plurals | CLDR plurals | Gettext plurals | L10n guide | Translate toolkit
 ---- | ---- | --------| ------------ | --------------- | ---------- | -----------------
-"""
+""",
     )
     for code in sorted(set(LANGUAGES)):
         handle.write(code.replace("_", "\\_"))
diff --git a/setup.py b/setup.py
@@ -23,13 +23,13 @@ class BuildMo(Command):
     description = "update MO files to match PO"
     user_options = []
 
-    def initialize_options(self):
+    def initialize_options(self) -> None:
         self.build_base = None
 
-    def finalize_options(self):
+    def finalize_options(self) -> None:
         self.set_undefined_options("build", ("build_base", "build_base"))
 
-    def run(self):
+    def run(self) -> None:
         for name in chain.from_iterable(glob(mask) for mask in LOCALE_MASKS):
             output = os.path.splitext(name)[0] + ".mo"
             if not newer(name, output):
@@ -43,7 +43,10 @@ class WeblateBuild(build):
     """Override the default build with new subcommands."""
 
     # The build_mo has to be before build_data
-    sub_commands = [("build_mo", lambda self: True), *build.sub_commands]
+    sub_commands = [
+        ("build_mo", lambda self: True),  # noqa: ARG005
+        *build.sub_commands,
+    ]
 
 
 setup(
diff --git a/weblate_language_data/utils.py b/weblate_language_data/utils.py
@@ -3,5 +3,5 @@
 # SPDX-License-Identifier: MIT
 
 
-def gettext_noop(message):
+def gettext_noop(message: str) -> str:
     return message

Original file line number	Diff line number	Diff line change
`@@ -4,9 +4,9 @@`
`4`	`4`	`#`
`5`	`5`	`# SPDX-License-Identifier: MIT`
`6`	`6`
	`7`	`+import csv`
`7`	`8`	`import json`
`8`	`9`	`from pathlib import Path`
`9`		`-import csv`
`10`	`10`
`11`	`11`	`# Read languages`
`12`	`12`	`with open("languages.csv") as csvfile:`
Original file line number	Diff line number	Diff line change
`@@ -12,7 +12,7 @@ MAPPING = {`
`12`	`12`	`}`
`13`	`13`
`14`	`14`	`with open(`
`15`		`- "modules/cldr-json/cldr-json/cldr-core/supplemental/territoryInfo.json"`
	`15`	`+ "modules/cldr-json/cldr-json/cldr-core/supplemental/territoryInfo.json",`
`16`	`16`	`) as handle:`
`17`	`17`	`languages = defaultdict(int)`
`18`	`18`	`for code, territory in json.load(handle)["supplemental"]["territoryInfo"].items():`
Original file line number	Diff line number	Diff line change
`@@ -28,7 +28,7 @@ for line in content.splitlines():`
`28`	`28`	`matches[2],`
`29`	`29`	`int(matches[3].split(";", 1)[0].split("=")[1]),`
`30`	`30`	`matches[3].split(";", 1)[1].split("=", 1)[1].rstrip(";"),`
`31`		`- )`
	`31`	`+ ),`
`32`	`32`	`)`
`33`	`33`
`34`	`34`	`with open("gettext.csv", "w") as handle:`
Original file line number	Diff line number	Diff line change
`@@ -79,7 +79,7 @@ with open(ALIASES) as handle:`
`79`	`79`	`if code in names:`
`80`	`80`	`if names[code] != replacement:`
`81`	`81`	`print(`
`82`		`- f"Conflicting replacement for {code}: {names[code]} != {replacement} {alias}"`
	`82`	`+ f"Conflicting replacement for {code}: {names[code]} != {replacement} {alias}",`
`83`	`83`	`)`
`84`	`84`	`continue`
`85`	`85`	`names[code] = replacement`
Original file line number	Diff line number	Diff line change
`@@ -29,7 +29,7 @@ for line in content.splitlines():`
`29`	`29`	`matches[2],`
`30`	`30`	`int(plural_parts[0].split("=")[1]),`
`31`	`31`	`plural_parts[1].split("=", 1)[1].rstrip(";"),`
`32`		`- )`
	`32`	`+ ),`
`33`	`33`	`)`
`34`	`34`
`35`	`35`	`with open("l10n-guide.csv", "w") as handle:`