ci: Add Ruff as code formatter and linter

.github/workflows/ci.yml

@@ -1,11 +1,12 @@
-name: Validate JavaScript Build
+name: CI
 
 on:
   pull_request:
     types: [opened, synchronize, reopened]
 
 jobs:
   check:
+    name: Validate JavaScript Build
     runs-on: ubuntu-latest
     container:
       image: debian:bookworm
@@ -61,3 +62,22 @@ jobs:
           git add video2commons/frontend/static/*.min.js video2commons/frontend/templates/*.min.html
           git commit -m "Update built files from CI"
           git push origin $GITHUB_HEAD_REF
+
+  ruff:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Setup uv
+        uses: astral-sh/setup-uv@v7.2.1
+        with:
+          python-version: "3.14"
+          enable-cache: true
+
+      - name: Run Ruff
+        run: uv run ruff check --output-format=github .
+
+      - name: Run the Ruff formatter
+        run: uv run ruff format --check .

.python-version

@@ -0,0 +1 @@
+3.14

pyproject.toml

@@ -0,0 +1,13 @@
+[project]
+name = "video2commons"
+version = "0.1.0"
+requires-python = ">=3.14"
+
+[dependency-groups]
+dev = ["ruff>=0.14.14"]
+
+[tool.ruff.lint]
+ignore = ["E722"]
+
+[tool.ruff.format]
+docstring-code-format = true

user-config.py

@@ -4,7 +4,7 @@
 
 """Pywikibot configs."""
 
-family = 'commons'
-mylang = 'commons'
+family = "commons"
+mylang = "commons"
 
 socket_timeout = 30, 300  # chunked uploading unreliable

utils/cleanuptasks.py

@@ -23,21 +23,20 @@
 import sys
 from redis import Redis
 
-sys.path.append(os.path.dirname(os.path.realpath(__file__)) +
-                "/../video2commons")
+sys.path.append(os.path.dirname(os.path.realpath(__file__)) + "/../video2commons")
 from config import redis_pw, redis_host  # NOQA
 
 redisconnection = Redis(host=redis_host, db=3, password=redis_pw)
 
-for userkey in redisconnection.keys('tasks:*') + ['alltasks']:
+for userkey in redisconnection.keys("tasks:*") + ["alltasks"]:
     for taskid in redisconnection.lrange(userkey, 0, -1):
-        if not redisconnection.exists('titles:' + taskid):
+        if not redisconnection.exists("titles:" + taskid):
             redisconnection.lrem(userkey, 0, taskid)
             print("delete %s from %s" % (taskid, userkey))
 
-for pattern in ['params:*', 'restarted:*']:  # 'tasklock:*'
+for pattern in ["params:*", "restarted:*"]:  # 'tasklock:*'
     for key in redisconnection.keys(pattern):
-        taskid = key.split(':')[1]
-        if not redisconnection.exists('titles:' + taskid):
+        taskid = key.split(":")[1]
+        if not redisconnection.exists("titles:" + taskid):
             redisconnection.delete(key)
             print("delete %s" % (key))

utils/extracti18n.py

@@ -27,50 +27,55 @@
 import re
 import json
 
-if not len(sys.argv) > 1 or '/messages' not in sys.argv[1]:
-    print(("usage: python " + sys.argv[0] + " <dir>\n\n"
-           "  <dir>  The path to mediawiki/languages/messages\n"))
+if not len(sys.argv) > 1 or "/messages" not in sys.argv[1]:
+    print(
+        (
+            "usage: python " + sys.argv[0] + " <dir>\n\n"
+            "  <dir>  The path to mediawiki/languages/messages\n"
+        )
+    )
     sys.exit(1)
 
 msgDir = sys.argv[1]
 
-dest = os.path.dirname(os.path.realpath(__file__)) + \
-    '/../video2commons/frontend/i18n-metadata'
+dest = (
+    os.path.dirname(os.path.realpath(__file__))
+    + "/../video2commons/frontend/i18n-metadata"
+)
 
 data = {
-    'fallbacks': {},
-    'rtl': [],
-    'alllangs': [],
+    "fallbacks": {},
+    "rtl": [],
+    "alllangs": [],
 }
 rFallback = re.compile(r"fallback = '(.*?)'", re.I)
-rIsRtl = re.compile(r'rtl = true', re.I)
+rIsRtl = re.compile(r"rtl = true", re.I)
 for file in os.listdir(msgDir):
     filePath = msgDir + "/" + file
-    if file in ['.', '..'] or not os.path.isfile(filePath):
+    if file in [".", ".."] or not os.path.isfile(filePath):
         continue
 
-    with open(filePath, 'r') as openfile:
+    with open(filePath, "r") as openfile:
         content = openfile.read()
 
-    fileMatch = re.match(r'Messages(.*?)\.php', file)
-    source = fileMatch.group(1).lower().replace('_', '-')
+    fileMatch = re.match(r"Messages(.*?)\.php", file)
+    source = fileMatch.group(1).lower().replace("_", "-")
     contentMatch = rFallback.search(content)
     if contentMatch:
-        fallbacks = [s.strip() for s in contentMatch.group(1).split(',')]
-        data['fallbacks'][source] = \
-            fallbacks if len(fallbacks) > 1 else fallbacks[0]
+        fallbacks = [s.strip() for s in contentMatch.group(1).split(",")]
+        data["fallbacks"][source] = fallbacks if len(fallbacks) > 1 else fallbacks[0]
 
     if rIsRtl.search(content):
-        data['rtl'].append(source)
+        data["rtl"].append(source)
 
-    data['alllangs'].append(source)
+    data["alllangs"].append(source)
 
 
 def _write(key):
     dest_file = dest + "/" + key + ".json"
-    with open(dest_file, 'w') as openfile:
-        json.dump(data[key], openfile, sort_keys=True,
-                  indent=4, separators=(',', ': '))
+    with open(dest_file, "w") as openfile:
+        json.dump(data[key], openfile, sort_keys=True, indent=4, separators=(",", ": "))
+
 
 for key in data:
     _write(key)

utils/stats.py

@@ -6,7 +6,7 @@
 import sys
 import time
 
-sys.path.insert(0, '/srv/v2c')
+sys.path.insert(0, "/srv/v2c")
 
 from redis import Redis
 
@@ -17,7 +17,7 @@
     collect_worker_stats,
     get_worker_stats,
     release_write_lock,
-    update_worker_stats
+    update_worker_stats,
 )
 
 # Stats are considered stale if they haven't been updated in 30 minutes.
@@ -41,8 +41,8 @@ def main():
 
     # Don't update stats if they've been updated recently by another job.
     existing_stats = get_worker_stats(app_conn)
-    if existing_stats and 'last_updated_by_job' in existing_stats:
-        if int(time.time()) - existing_stats['last_updated_by_job'] < STALE_SECS:
+    if existing_stats and "last_updated_by_job" in existing_stats:
+        if int(time.time()) - existing_stats["last_updated_by_job"] < STALE_SECS:
             print("Stats have been updated recently, skipping update.")
             return
 
@@ -58,5 +58,6 @@ def main():
     finally:
         release_write_lock(app_conn)
 
-if __name__ == '__main__':
+
+if __name__ == "__main__":
     main()

video2commons/backend/__init__.py

@@ -19,8 +19,6 @@
 
 """videocommons backend."""
 
-
-
 from video2commons.backend import worker
 
-__all__ = ['worker']
+__all__ = ["worker"]

video2commons/backend/categories/__init__.py

@@ -24,18 +24,26 @@
 def has_video_track(source: str) -> bool:
     """Check if a video has an audio track."""
 
-    result = subprocess.run([
-        ffprobe_location,
-        '-loglevel', 'error',
-        '-select_streams', 'v',
-        '-show_entries', 'stream=index,codec_type',
-        '-of', 'json',
-        source
-    ], capture_output=True, text=True)
+    result = subprocess.run(
+        [
+            ffprobe_location,
+            "-loglevel",
+            "error",
+            "-select_streams",
+            "v",
+            "-show_entries",
+            "stream=index,codec_type",
+            "-of",
+            "json",
+            source,
+        ],
+        capture_output=True,
+        text=True,
+    )
 
     if result.returncode == 0:
-        for stream in json.loads(result.stdout).get('streams', []):
-            if stream.get('codec_type') == 'video':
+        for stream in json.loads(result.stdout).get("streams", []):
+            if stream.get("codec_type") == "video":
                 return True
 
     return False
@@ -44,18 +52,26 @@ def has_video_track(source: str) -> bool:
 def has_audio_track(source: str) -> bool:
     """Check if a video has an audio track."""
 
-    result = subprocess.run([
-        ffprobe_location,
-        '-loglevel', 'error',
-        '-select_streams', 'a',
-        '-show_entries', 'stream=index,codec_type',
-        '-of', 'json',
-        source
-    ], capture_output=True, text=True)
+    result = subprocess.run(
+        [
+            ffprobe_location,
+            "-loglevel",
+            "error",
+            "-select_streams",
+            "a",
+            "-show_entries",
+            "stream=index,codec_type",
+            "-of",
+            "json",
+            source,
+        ],
+        capture_output=True,
+        text=True,
+    )
 
     if result.returncode == 0:
-        for stream in json.loads(result.stdout).get('streams', []):
-            if stream.get('codec_type') == 'audio':
+        for stream in json.loads(result.stdout).get("streams", []):
+            if stream.get("codec_type") == "audio":
                 return True
 
     return False
@@ -82,7 +98,7 @@ def get_inferable_categories(source: str) -> Set[str]:
     categories = set()
 
     if not has_audio_track(source):
-        categories.add('[[Category:Videos without audio]]')
+        categories.add("[[Category:Videos without audio]]")
 
     return categories