chore: use ruff for formatting

There are a few minor changes here compared to black; it flagged
unnecessary string concatenations, and has slightly different
opinions on line length.

.github/workflows/python-formatting.yml

@@ -22,10 +22,10 @@ jobs:
     - name: Create virtual environment
       run: python -m venv venv
 
-    - name: Install black
+    - name: Install ruff
       run: |
         ./venv/bin/pip install --upgrade pip
-        ./venv/bin/pip install black
+        ./venv/bin/pip install ruff
 
     - name: Run formatting check
       run: make ck-format

Makefile

@@ -1,7 +1,7 @@
 .PHONY: format
 format:
-	venv/bin/black -t py35 -t py36 -t py37 -t py38 -t py39 -t py310 -t py311 -t py312 .
+	venv/bin/ruff format --target-version py37 .
 
 .PHONY: ck-format
 ck-format:
-	venv/bin/black --check .
+	venv/bin/ruff format --check --target-version py37 .

brozzler/chrome.py

@@ -367,7 +367,7 @@ class Chrome:
             os.killpg(self.chrome_process.pid, signal.SIGKILL)
             status = self.chrome_process.wait()
             pid_logger.warning(
-                "chrome reaped after killing with " "SIGKILL",
+                "chrome reaped after killing with SIGKILL",
                 status=status,
             )
 

brozzler/cli.py

@@ -937,7 +937,7 @@ def brozzler_list_pages(argv=None):
         "--claimed",
         dest="claimed",
         action="store_true",
-        help=("limit to pages that are currently claimed by a brozzler " "worker"),
+        help=("limit to pages that are currently claimed by a brozzler worker"),
     )
     add_rethinkdb_options(arg_parser)
     add_common_options(arg_parser, argv)
@@ -1008,22 +1008,21 @@ def brozzler_purge(argv=None):
         dest="job",
         metavar="JOB_ID",
         help=(
-            "purge crawl state from rethinkdb for a job, including all "
+            "purge crawl state from rethinkdb for a job, including all sites and pages"
-            "sites and pages"
         ),
     )
     group.add_argument(
         "--site",
         dest="site",
         metavar="SITE_ID",
-        help=("purge crawl state from rethinkdb for a site, including all " "pages"),
+        help=("purge crawl state from rethinkdb for a site, including all pages"),
     )
     group.add_argument(
         "--finished-before",
         dest="finished_before",
         metavar="YYYY-MM-DD",
         help=(
-            "purge crawl state from rethinkdb for a jobs that ended " "before this date"
+            "purge crawl state from rethinkdb for a jobs that ended before this date"
         ),
     )
     arg_parser.add_argument(

brozzler/dashboard/__init__.py

@@ -334,7 +334,7 @@ def main(argv=None):
         prog=os.path.basename(argv[0]),
         formatter_class=argparse.RawDescriptionHelpFormatter,
         description=(
-            "brozzler-dashboard - web application for viewing brozzler " "crawl status"
+            "brozzler-dashboard - web application for viewing brozzler crawl status"
         ),
         epilog=(
             "brozzler-dashboard has no command line options, but can be "

brozzler/easy.py

@@ -81,8 +81,7 @@ def _build_arg_parser(argv=None):
         dest="cacert",
         default="./%s-warcprox-ca.pem" % socket.gethostname(),
         help=(
-            "warcprox CA certificate file; if file does not exist, it "
+            "warcprox CA certificate file; if file does not exist, it will be created"
-            "will be created"
         ),
     )
     arg_parser.add_argument(
@@ -95,7 +94,7 @@ def _build_arg_parser(argv=None):
         "--onion-tor-socks-proxy",
         dest="onion_tor_socks_proxy",
         default=None,
-        help=("host:port of tor socks proxy, used only to connect to " ".onion sites"),
+        help=("host:port of tor socks proxy, used only to connect to .onion sites"),
     )
 
     # brozzler-worker args
@@ -112,7 +111,7 @@ def _build_arg_parser(argv=None):
         dest="max_browsers",
         type=int,
         default=1,
-        help=("max number of chrome instances simultaneously " "browsing pages"),
+        help=("max number of chrome instances simultaneously browsing pages"),
     )
 
     # pywb args

brozzler/pywb.py

@@ -447,8 +447,6 @@ def main(argv=sys.argv):
     wayback_cli = BrozzlerWaybackCli(
         args=argv[1:],
         default_port=8880,
-        desc=(
+        desc=("brozzler-wayback - pywb wayback (monkey-patched for use with brozzler)"),
-            "brozzler-wayback - pywb wayback (monkey-patched for use " "with brozzler)"
-        ),
     )
     wayback_cli.run()

brozzler/robots.py

@@ -120,7 +120,7 @@ def is_permitted_by_robots(site, url, proxy=None):
             raise brozzler.ProxyError(e)
         else:
             structlog.get_logger(logger_name=__name__).warning(
-                "returning true (permitted) after problem fetching " "robots.txt",
+                "returning true (permitted) after problem fetching robots.txt",
                 url=url,
                 raised_exception=e,
             )

brozzler/worker.py

@@ -168,7 +168,7 @@ class BrozzlerWorker:
             svc = self._choose_warcprox()
             if svc is None:
                 raise brozzler.ProxyError(
-                    "no available instances of warcprox in the service " "registry"
+                    "no available instances of warcprox in the service registry"
                 )
             site.proxy = "%s:%s" % (svc["host"], svc["port"])
             site.save()
@@ -759,7 +759,7 @@ class BrozzlerWorker:
         with self._start_stop_lock:
             if self._thread:
                 self.logger.warning(
-                    "ignoring start request because self._thread is " "not None"
+                    "ignoring start request because self._thread is not None"
                 )
                 return
             self._thread = threading.Thread(target=self.run, name="BrozzlerWorker")

brozzler/ydl.py

@@ -426,7 +426,7 @@ def _try_youtube_dl(worker, ydl, site, page):
     if worker._using_warcprox(site):
         info_json = json.dumps(ie_result, sort_keys=True, indent=4)
         logger.info(
-            "sending WARCPROX_WRITE_RECORD request to warcprox " "with yt-dlp json",
+            "sending WARCPROX_WRITE_RECORD request to warcprox with yt-dlp json",
             url=ydl.url,
         )
         worker._warcprox_write_record(

vagrant/vagrant-brozzler-new-site.py

@@ -82,7 +82,7 @@ def main(argv=[]):
     os.chdir(os.path.dirname(__file__))
 
     cmd = (
-        "/opt/brozzler-ve3/bin/python /opt/brozzler-ve3/bin/brozzler-new-site " "%s %s"
+        "/opt/brozzler-ve3/bin/python /opt/brozzler-ve3/bin/brozzler-new-site %s %s"
     ) % (" ".join(options), args.seed)
     subprocess.call(["vagrant", "ssh", "--", cmd])