Update pre-commit shellcheck, markdownlint and ruff + lint fixes

.pre-commit-config.yaml

@@ -1,6 +1,6 @@
 repos:
   - repo: https://github.com/shellcheck-py/shellcheck-py
-    rev: v0.9.0.5
+    rev: v0.10.0.1
     hooks:
       - id: shellcheck
   - repo: https://github.com/pre-commit/mirrors-prettier
@@ -8,7 +8,7 @@ repos:
     hooks:
       - id: prettier
   - repo: https://github.com/igorshubovych/markdownlint-cli
-    rev: v0.32.2
+    rev: v0.43.0
     hooks:
       - id: markdownlint
         args: [--fix]
@@ -19,7 +19,7 @@ repos:
         args: [--profile=black]
         name: isort (python)
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.1.14
+    rev: v0.9.0
     hooks:
       - id: ruff
         args: [--fix, --show-fixes]

misc/compare_pushes.py

@@ -1,9 +1,10 @@
 #!/usr/bin/env python
-""" Script to compare pushes from a Treeherder instance against production.
+"""Script to compare pushes from a Treeherder instance against production.
 
 This is useful to compare if pushes between two different instances have been
 ingested differently.
 """
+
 import argparse
 import logging
 

misc/compare_tasks.py

@@ -1,5 +1,6 @@
 #!/usr/bin/env python
-""" Script to compare tasks from pushes on different Treeherder instances"""
+"""Script to compare tasks from pushes on different Treeherder instances"""
+
 import argparse
 import logging
 import pprint

tests/conftest.py

@@ -849,10 +849,7 @@ def mock_file_bugzilla_map_request(monkeypatch):
     import treeherder.etl.files_bugzilla_map
 
     def _fetch_data(self, project):
-        url = (
-            "https://firefox-ci-tc.services.mozilla.com/api/index/v1/task/gecko.v2.%s.latest.source.source-bugzilla-info/artifacts/public/components.json"
-            % project
-        )
+        url = f"https://firefox-ci-tc.services.mozilla.com/api/index/v1/task/gecko.v2.{project}.latest.source.source-bugzilla-info/artifacts/public/components.json"
         files_bugzilla_data = None
         file_name = f"files_bugzilla_map_{project}_{self.run_id}.json"
         exception = None
@@ -883,7 +880,7 @@ def mock_bugscache_bugzilla_request(monkeypatch):
 
     def _fetch_intermittent_bugs(additional_params, limit, duplicate_chain_length):
         tests_folder = os.path.dirname(__file__)
-        file_name = "run-%s.json" % str(duplicate_chain_length)
+        file_name = f"run-{str(duplicate_chain_length)}.json"
         data_path = os.path.join(tests_folder, "sample_data", "bugscache_population", file_name)
         with open(data_path) as f:
             bugzilla_data = json.load(f)
@@ -1209,7 +1206,7 @@ def group_data(transactional_db, eleven_job_blobs, create_jobs):
         job = eleven_job_blobs[i]
         job["job"].update(
             {
-                "taskcluster_task_id": "V3SVuxO8TFy37En_6HcXL%s" % i,
+                "taskcluster_task_id": f"V3SVuxO8TFy37En_6HcXL{i}",
                 "taskcluster_retry_id": "0",
                 "name": jt[i].name,
             }

tests/etl/test_job_loader.py

@@ -161,9 +161,9 @@ def test_ingest_pulse_job_with_long_job_type_name(
     job = pulse_jobs[0]
     jl = JobLoader()
     revision = push_stored[0]["revision"]
-    job["display"][
-        "jobName"
-    ] = "this is a very long string that exceeds the 100 character size that was the previous limit by just a little bit"
+    job["display"]["jobName"] = (
+        "this is a very long string that exceeds the 100 character size that was the previous limit by just a little bit"
+    )
     job["origin"]["revision"] = revision
     jl.process_job(job, "https://firefox-ci-tc.services.mozilla.com")
 

tests/model/cycle_data/test_perfherder_cycling.py

@@ -220,7 +220,7 @@ def test_irrelevant_repos_data_removal(
     relevant_repository.save()
 
     # hack after changing tests.settings.TREEHERDER_TEST_REPOSITORY_NAME to be m-c
-    test_repository.name = "%s-test" % test_repository.name
+    test_repository.name = f"{test_repository.name}-test"
     test_repository.save()
 
     six_months_ago_timestamp = datetime.now() - timedelta(days=(6 * 30))
@@ -311,12 +311,12 @@ def test_total_emails_sent(
     for n in range(0, total_signatures):
         PerformanceSignature.objects.create(
             repository=test_perf_signature.repository,
-            signature_hash=(20 * ("t%s" % n)),
+            signature_hash=(20 * (f"t{n}")),
             framework=test_perf_signature.framework,
             platform=test_perf_signature.platform,
             option_collection=test_perf_signature.option_collection,
-            suite="mysuite%s" % n,
-            test="mytest%s" % n,
+            suite=f"mysuite{n}",
+            test=f"mytest{n}",
             application="firefox",
             has_subtests=test_perf_signature.has_subtests,
             extra_options=test_perf_signature.extra_options,
@@ -326,12 +326,12 @@ def test_total_emails_sent(
     for n in range(0, 10):
         PerformanceSignature.objects.create(
             repository=try_repository,
-            signature_hash=(20 * ("e%s" % n)),
+            signature_hash=(20 * (f"e{n}")),
             framework=test_perf_signature.framework,
             platform=test_perf_signature.platform,
             option_collection=test_perf_signature.option_collection,
-            suite="mysuite%s" % n,
-            test="mytest%s" % n,
+            suite=f"mysuite{n}",
+            test=f"mytest{n}",
             application="firefox",
             has_subtests=test_perf_signature.has_subtests,
             extra_options=test_perf_signature.extra_options,

tests/perf/test_email.py

@@ -34,14 +34,22 @@ class TestDeletionNotificationWriter:
 
     @staticmethod
     def __prepare_expected_content(test_perf_signature):
-        expected_content = DeletionReportContent.DESCRIPTION + DeletionReportContent.TABLE_HEADERS
-        expected_content += """| {repository} | {framework} | {platform} | {suite} | {application} | {last_updated} |""".format(
-            repository=test_perf_signature.repository.name,
-            framework=test_perf_signature.framework.name,
-            platform=test_perf_signature.platform.platform,
-            suite=test_perf_signature.suite,
-            application=test_perf_signature.application,
-            last_updated=test_perf_signature.last_updated.date(),
+        expected_content = "".join(
+            (
+                DeletionReportContent.DESCRIPTION,
+                DeletionReportContent.TABLE_HEADERS,
+                "| ",
+                " | ".join(
+                    (
+                        test_perf_signature.repository.name,
+                        test_perf_signature.framework.name,
+                        test_perf_signature.platform.platform,
+                        test_perf_signature.suite,
+                        test_perf_signature.application,
+                        str(test_perf_signature.last_updated.date()),
+                    )
+                ),
+                " |\n",
+            )
         )
-        expected_content += "\n"
         return expected_content

tests/perfalert/test_alerts.py

@@ -59,7 +59,7 @@ def _generate_performance_data(
     ):
         push, _ = Push.objects.get_or_create(
             repository=test_repository,
-            revision="1234abcd%s" % t,
+            revision=f"1234abcd{t}",
             defaults={
                 "author": "foo@bar.com",
                 "time": datetime.datetime.fromtimestamp(base_timestamp + t),

tests/sample_data_generator.py

@@ -2,6 +2,7 @@
 Functions for flexible generation of sample input job JSON.
 
 """
+
 import time
 from datetime import timedelta
 

tests/sampledata.py

@@ -19,9 +19,7 @@ class SampleData:
             self.text_log_summary = json.load(f)
 
         with open(
-            "{}/sample_data/pulse_consumer/taskcluster_pulse_messages.json".format(
-                os.path.dirname(__file__)
-            )
+            f"{os.path.dirname(__file__)}/sample_data/pulse_consumer/taskcluster_pulse_messages.json"
         ) as f:
             self.taskcluster_pulse_messages = json.load(f)
 
@@ -31,9 +29,7 @@ class SampleData:
             self.taskcluster_tasks = json.load(f)
 
         with open(
-            "{}/sample_data/pulse_consumer/taskcluster_transformed_jobs.json".format(
-                os.path.dirname(__file__)
-            )
+            f"{os.path.dirname(__file__)}/sample_data/pulse_consumer/taskcluster_transformed_jobs.json"
         ) as f:
             self.taskcluster_transformed_jobs = json.load(f)
 

tests/webapp/api/test_groupsummary_api.py

@@ -9,7 +9,7 @@ def test_future_date(group_data, client):
 
     today = datetime.datetime.today().date()
     tomorrow = today + datetime.timedelta(days=1)
-    url = reverse("groupsummary") + "?startdate=%s" % tomorrow
+    url = reverse("groupsummary") + f"?startdate={tomorrow}"
     resp = client.get(url)
     assert resp.status_code == 200
     assert resp.json() == expected
@@ -29,7 +29,8 @@ def test_default_date(group_data, client):
 # test jobname chunk removal and aggregation
 def test_summarized(group_data, client):
     expected = group_data["expected"]
-    url = reverse("groupsummary") + "?startdate=%s" % str(group_data["date"]).split(" ")[0]
+    startdate = str(group_data["date"]).split(" ")[0]
+    url = reverse("groupsummary") + f"?startdate={startdate}"
     resp = client.get(url)
     assert resp.status_code == 200
     assert resp.json() == expected

tests/webapp/api/test_note_api.py

@@ -100,7 +100,7 @@ def test_create_note(client, test_job, test_user, test_no_auth):
         assert resp.status_code == 200
 
         content = json.loads(resp.content)
-        assert content["message"] == "note stored for job %s" % test_job.id
+        assert content["message"] == f"note stored for job {test_job.id}"
 
         note_list = JobNote.objects.filter(job=test_job)
 

tests/webapp/api/test_perfcompare_api.py

@@ -885,8 +885,9 @@ def test_revision_is_not_found(client, test_perf_signature, test_perfcomp_push):
 
     response = client.get(reverse("perfcompare-results") + query_params)
     assert response.status_code == 400
-    assert response.json() == "No base push with revision {} from repo {}.".format(
-        non_existent_revision, test_perf_signature.repository.name
+    assert (
+        response.json()
+        == f"No base push with revision {non_existent_revision} from repo {test_perf_signature.repository.name}."
     )
 
     query_params = (
@@ -902,8 +903,9 @@ def test_revision_is_not_found(client, test_perf_signature, test_perfcomp_push):
 
     response = client.get(reverse("perfcompare-results") + query_params)
     assert response.status_code == 400
-    assert response.json() == "No new push with revision {} from repo {}.".format(
-        non_existent_revision, test_perf_signature.repository.name
+    assert (
+        response.json()
+        == f"No new push with revision {non_existent_revision} from repo {test_perf_signature.repository.name}."
     )
 
 

tests/webapp/api/test_performance_data_api.py

@@ -201,7 +201,7 @@ def test_filter_signatures_by_framework(
     # Filter by original framework
     resp = client.get(
         reverse("performance-signatures-list", kwargs={"project": test_repository.name})
-        + "?framework=%s" % test_perf_signature.framework.id,
+        + f"?framework={test_perf_signature.framework.id}",
     )
     assert resp.status_code == 200
     assert len(resp.data.keys()) == 1
@@ -210,7 +210,7 @@ def test_filter_signatures_by_framework(
     # Filter by new framework
     resp = client.get(
         reverse("performance-signatures-list", kwargs={"project": test_repository.name})
-        + "?framework=%s" % signature2.framework.id,
+        + f"?framework={signature2.framework.id}",
     )
     assert resp.status_code == 200
     assert len(resp.data.keys()) == 1
@@ -305,9 +305,7 @@ def test_filter_data_by_framework(
     # Filtering by first framework
     resp = client.get(
         reverse("performance-data-list", kwargs={"project": test_repository.name})
-        + "?signatures={}&framework={}".format(
-            test_perf_signature.signature_hash, test_perf_signature.framework.id
-        )
+        + f"?signatures={test_perf_signature.signature_hash}&framework={test_perf_signature.framework.id}"
     )
     assert resp.status_code == 200
     datums = resp.data[test_perf_signature.signature_hash]
@@ -371,7 +369,7 @@ def test_filter_data_by_interval(
     ):
         push = Push.objects.create(
             repository=test_repository,
-            revision="abcdefgh%s" % i,
+            revision=f"abcdefgh{i}",
             author="foo@bar.com",
             time=timestamp,
         )
@@ -409,7 +407,7 @@ def test_filter_data_by_range(
     ):
         push = Push.objects.create(
             repository=test_repository,
-            revision="abcdefgh%s" % i,
+            revision=f"abcdefgh{i}",
             author="foo@bar.com",
             time=timestamp,
         )
@@ -479,17 +477,9 @@ def test_filter_data_by_signature(
 
 
 def test_perf_summary(client, test_perf_signature, test_perf_data):
-    query_params1 = (
-        "?repository={}&framework={}&interval=172800&no_subtests=true&revision={}".format(
-            test_perf_signature.repository.name,
-            test_perf_signature.framework_id,
-            test_perf_data[0].push.revision,
-        )
-    )
+    query_params1 = f"?repository={test_perf_signature.repository.name}&framework={test_perf_signature.framework_id}&interval=172800&no_subtests=true&revision={test_perf_data[0].push.revision}"
 
-    query_params2 = "?repository={}&framework={}&interval=172800&no_subtests=true&startday=2013-11-01T23%3A28%3A29&endday=2013-11-30T23%3A28%3A29".format(
-        test_perf_signature.repository.name, test_perf_signature.framework_id
-    )
+    query_params2 = f"?repository={test_perf_signature.repository.name}&framework={test_perf_signature.framework_id}&interval=172800&no_subtests=true&startday=2013-11-01T23%3A28%3A29&endday=2013-11-30T23%3A28%3A29"
 
     expected = [
         {
@@ -536,9 +526,7 @@ def test_data_points_from_same_push_are_ordered_chronologically(
     As job ids are auto incremented, older jobs have smaller ids than newer ones.
     Thus, these ids are sufficient to check for chronological order.
     """
-    query_params = "?repository={}&framework={}&interval=172800&no_subtests=true&startday=2013-11-01T23%3A28%3A29&endday=2013-11-30T23%3A28%3A29".format(
-        test_perf_signature.repository.name, test_perf_signature.framework_id
-    )
+    query_params = f"?repository={test_perf_signature.repository.name}&framework={test_perf_signature.framework_id}&interval=172800&no_subtests=true&startday=2013-11-01T23%3A28%3A29&endday=2013-11-30T23%3A28%3A29"
 
     response = client.get(reverse("performance-summary") + query_params)
     assert response.status_code == 200
@@ -551,12 +539,7 @@ def test_no_retriggers_perf_summary(
     client, push_stored, test_perf_signature, test_perf_signature_2, test_perf_data
 ):
     push = Push.objects.get(id=1)
-    query_params = "?repository={}&framework={}&no_subtests=true&revision={}&all_data=true&signature={}".format(
-        test_perf_signature.repository.name,
-        test_perf_signature.framework_id,
-        push.revision,
-        test_perf_signature.id,
-    )
+    query_params = f"?repository={test_perf_signature.repository.name}&framework={test_perf_signature.framework_id}&no_subtests=true&revision={push.revision}&all_data=true&signature={test_perf_signature.id}"
 
     PerformanceDatum.objects.create(
         repository=test_perf_signature.repository,

treeherder/changelog/collector.py

@@ -1,5 +1,5 @@
-""" Collector, grabs changes in various sources and put them in a DB.
-"""
+"""Collector, grabs changes in various sources and put them in a DB."""
+
 import json
 import os
 

treeherder/changelog/tasks.py

@@ -13,7 +13,7 @@ def update_changelog(days=1):
     """
     Collect changes and update the DB.
     """
-    logger.info("Updating unified changelog (days=%d)" % days)
+    logger.info(f"Updating unified changelog (days={days})")
     # collecting last day of changes across all sources
     since = datetime.datetime.now() - datetime.timedelta(days=days)
     since = since.strftime("%Y-%m-%dT%H:%M:%S")
@@ -34,6 +34,4 @@ def update_changelog(days=1):
             created += 1
             [ChangelogFile.objects.create(name=name, changelog=changelog) for name in files]
 
-    logger.info(
-        "Found %d items, %d existed and %d where created." % (created + existed, existed, created)
-    )
+    logger.info(f"Found {created + existed} items, {existed} existed and {created} where created.")

treeherder/config/settings.py

@@ -369,9 +369,9 @@ CELERY_TASK_TIME_LIMIT = CELERY_TASK_SOFT_TIME_LIMIT + 30
 
 # Periodically publish runtime statistics on statsd (in minutes)
 CELERY_STATS_PUBLICATION_DELAY = 5
-assert (
-    0 < CELERY_STATS_PUBLICATION_DELAY < 60 and 60 % 10 == 0
-), "Celery task must be a valid cron delay in minutes"
+assert 0 < CELERY_STATS_PUBLICATION_DELAY < 60 and 60 % 10 == 0, (
+    "Celery task must be a valid cron delay in minutes"
+)
 
 CELERY_BEAT_SCHEDULE = {
     # this is just a failsafe in case the Pulse ingestion misses something

treeherder/config/wsgi.py

@@ -6,6 +6,7 @@ and any production WSGI deployments. It should expose a module-level variable
 named ``application``. Django's ``runserver`` and ``runfcgi`` commands discover
 this application via the ``WSGI_APPLICATION`` setting.
 """
+
 import os
 
 from django.core.wsgi import get_wsgi_application

treeherder/etl/artifact.py

@@ -78,8 +78,7 @@ def store_job_artifacts(artifact_data):
             job_guid = artifact.get("job_guid")
             if not job_guid:
                 logger.error(
-                    "load_job_artifacts: Artifact '%s' with no " "job guid set, skipping",
-                    artifact_name,
+                    f"load_job_artifacts: Artifact '{artifact_name}' with no job guid set, skipping"
                 )
                 continue
 

treeherder/etl/classification_loader.py

@@ -32,9 +32,9 @@ class ClassificationLoader:
         task_id = pulse_job["status"]["taskId"]
 
         task_definition = get_task_definition(root_url, task_id)
-        assert (
-            "routes" in task_definition and len(task_definition["routes"]) > 0
-        ), "A route containing the push project and revision is needed to save the mozci classification"
+        assert "routes" in task_definition and len(task_definition["routes"]) > 0, (
+            "A route containing the push project and revision is needed to save the mozci classification"
+        )
         # Retrieving a Push object thanks to the project/revision parsed from the task first route
         try:
             push = self.get_push(task_definition["routes"][0])
@@ -53,9 +53,9 @@ class ClassificationLoader:
         # Saving the mozci classification in the database
         results = dict(MozciClassification.CLASSIFICATION_RESULT)
         classification = classification_json["push"]["classification"]
-        assert (
-            classification in results.keys()
-        ), "Classification result should be a value in BAD, GOOD, UNKNOWN"
+        assert classification in results.keys(), (
+            "Classification result should be a value in BAD, GOOD, UNKNOWN"
+        )
 
         logger.info(
             "Storing mozci classification calculated as %s for push %s on repository %s",

treeherder/etl/files_bugzilla_map.py

@@ -84,10 +84,7 @@ class FilesBugzillaMapProcess:
         )
 
     def fetch_data(self, project):
-        url = (
-            "https://firefox-ci-tc.services.mozilla.com/api/index/v1/task/gecko.v2.%s.latest.source.source-bugzilla-info/artifacts/public/components.json"
-            % project
-        )
+        url = f"https://firefox-ci-tc.services.mozilla.com/api/index/v1/task/gecko.v2.{project}.latest.source.source-bugzilla-info/artifacts/public/components.json"
         files_bugzilla_data = None
         exception = None
         try:

treeherder/etl/management/commands/ingest.py

@@ -104,7 +104,7 @@ def _ingest_hg_push(project, revision, fetch_push_id=None):
     # get reference to repo
     repo = Repository.objects.get(name=project, active_status="active")
     # get hg pushlog
-    pushlog_url = "%s/json-pushes/?full=1&version=2" % repo.url
+    pushlog_url = f"{repo.url}/json-pushes/?full=1&version=2"
     # ingest this particular revision for this project
     process = HgPushlogProcess()
     # Use the actual push SHA, in case the changeset specified was a tag

treeherder/etl/perf.py

@@ -157,13 +157,12 @@ def _load_perf_datum(job: Job, perf_datum: dict):
         if perf_datum["framework"]["name"] == "job_resource_usage":
             return
         logger.warning(
-            "Performance framework %s does not exist, skipping " "load of performance artifacts",
-            perf_datum["framework"]["name"],
+            f"Performance framework {perf_datum['framework']['name']} does not exist, skipping load of performance artifacts"
         )
         return
     if not framework.enabled:
         logger.info(
-            "Performance framework %s is not enabled, skipping", perf_datum["framework"]["name"]
+            f"Performance framework {perf_datum['framework']['name']} is not enabled, skipping"
         )
         return
     application = _get_application_name(perf_datum)

treeherder/etl/push.py

@@ -11,7 +11,7 @@ logger = logging.getLogger(__name__)
 def store_push(repository, push_dict):
     push_revision = push_dict.get("revision")
     if not push_dict.get("revision"):
-        raise ValueError("Push must have a revision " "associated with it!")
+        raise ValueError("Push must have a revision associated with it!")
     with transaction.atomic():
         push, _ = Push.objects.update_or_create(
             repository=repository,

treeherder/etl/push_loader.py

@@ -24,7 +24,7 @@ class PushLoader:
             newrelic.agent.add_custom_attribute("branch", transformer.branch)
             repos = Repository.objects
             if transformer.branch:
-                repos = repos.filter(branch__regex="(^|,)%s($|,)" % transformer.branch)
+                repos = repos.filter(branch__regex=f"(^|,){transformer.branch}($|,)")
             else:
                 repos = repos.filter(branch=None)
             repo = repos.get(url=transformer.repo_url, active_status="active")

treeherder/etl/pushlog.py

@@ -16,7 +16,7 @@ ONE_WEEK_IN_SECONDS = 604800
 
 def last_push_id_from_server(repo):
     """Obtain the last push ID from a ``Repository`` instance."""
-    url = "%s/json-pushes/?version=2" % repo.url
+    url = f"{repo.url}/json-pushes/?version=2"
     data = fetch_json(url)
     return data["lastpushid"]
 
@@ -92,15 +92,12 @@ class HgPushlogProcess:
         else:
             if changeset:
                 logger.info(
-                    "Getting all pushes for '%s' corresponding to " "changeset '%s'",
-                    repository_name,
-                    changeset,
+                    f"Getting all pushes for '{repository_name}' corresponding to changeset '{changeset}'"
                 )
-                extracted_content = self.extract(source_url + "&changeset=" + changeset)
+                extracted_content = self.extract(f"{source_url}&changeset={changeset}")
             else:
                 logger.warning(
-                    "Unable to get last push from cache for '%s', " "getting all pushes",
-                    repository_name,
+                    f"Unable to get last push from cache for '{repository_name}', getting all pushes",
                 )
                 extracted_content = self.extract(source_url)
 

treeherder/etl/tasks/pulse_tasks.py

@@ -1,6 +1,7 @@
 """
 This module contains tasks related to pulse job ingestion
 """
+
 import asyncio
 
 import newrelic.agent

treeherder/log_parser/artifactbuildercollection.py

@@ -92,9 +92,7 @@ class ArtifactBuilderCollection:
             )
 
             if download_size_in_bytes > MAX_DOWNLOAD_SIZE_IN_BYTES:
-                raise LogSizeError(
-                    "Download size of %i bytes exceeds limit" % download_size_in_bytes
-                )
+                raise LogSizeError(f"Download size of {download_size_in_bytes} bytes exceeds limit")
 
             # Lines must be explicitly decoded since `iter_lines()`` returns bytes by default
             # and we cannot use its `decode_unicode=True` mode, since otherwise Unicode newline

treeherder/log_parser/management/commands/test_parse_log.py

@@ -43,6 +43,6 @@ class Command(BaseCommand):
                     print(f"{name}, {json.dumps(artifact, indent=2)}")
 
         if options["profile"]:
-            print("Timings: %s" % times)
-            print("Average: %s" % (sum(times) / len(times)))
-            print("Total: %s" % sum(times))
+            print(f"Timings: {times}")
+            print(f"Average: {sum(times) / len(times)}")
+            print(f"Total: {sum(times)}")

treeherder/log_parser/parsers.py

@@ -201,11 +201,9 @@ class PerformanceParser(ParserBase):
                 validate_perf_data(data)
                 self.artifact.append(data)
             except ValueError:
-                logger.warning("Unable to parse Perfherder data from line: %s", line)
+                logger.warning(f"Unable to parse Perfherder data from line: {line}")
             except jsonschema.ValidationError as e:
-                logger.warning(
-                    "Perfherder line '%s' does not comply with " "json schema: %s", line, e
-                )
+                logger.warning(f"Perfherder line '{line}' does not comply with json schema: {e}")
 
             # Don't mark the parser as complete, in case there are multiple performance artifacts.
 

treeherder/log_parser/tasks.py

@@ -39,7 +39,7 @@ def parse_logs(job_id, job_log_ids, priority):
     first_exception = None
     completed_names = set()
     for job_log in job_logs:
-        newrelic.agent.add_custom_attribute("job_log_%s_url" % job_log.name, job_log.url)
+        newrelic.agent.add_custom_attribute(f"job_log_{job_log.name}_url", job_log.url)
         logger.info("parser_task for %s", job_log.id)
 
         # Only parse logs which haven't yet been processed or else failed on the last attempt.

treeherder/model/error_summary.py

@@ -253,7 +253,7 @@ def get_error_search_term_and_path(error_line):
             test_name_or_path = REFTEST_RE.sub("", test_name_or_path).replace("\\", "/")
             # split marionette paths to only include the filename
             if MARIONETTE_RE.search(test_name_or_path):
-                test_name_or_path = "%s.py" % test_name_or_path.split(".py ")[0]
+                test_name_or_path = f"{test_name_or_path.split('.py ')[0]}.py"
             path_end = test_name_or_path
             # if this is a path, we are interested in the last part
             search_term = test_name_or_path.split("/")[-1]

treeherder/model/management/commands/backfill_text_log_error_jobs.py

@@ -38,9 +38,7 @@ class Command(BaseCommand):
             TextLogError.objects.bulk_update(chunked_queryset, ["job"])
 
             logger.warning(
-                "successfully added job_id in TextLogError table to rows {} to {}".format(
-                    chunked_queryset[0].id, chunked_queryset[-1].id
-                )
+                f"successfully added job_id in TextLogError table to rows {chunked_queryset[0].id} to {chunked_queryset[-1].id}"
             )
 
         logger.warning("successfully finished backfilling job_ids in the TextLogError table")

treeherder/model/management/commands/cycle_data.py

@@ -45,9 +45,7 @@ class Command(BaseCommand):
             dest="chunk_size",
             default=100,
             type=int,
-            help=(
-                "Define the size of the chunks " "Split the job deletes into chunks of this size"
-            ),
+            help=("Define the size of the chunks Split the job deletes into chunks of this size"),
         )
         parser.add_argument(
             "--sleep-time",

treeherder/model/models.py

@@ -265,9 +265,7 @@ class Bugscache(models.Model):
         except ProgrammingError as e:
             newrelic.agent.notice_error()
             logger.error(
-                "Failed to execute FULLTEXT search on Bugscache, error={}, SQL={}".format(
-                    e, recent_qs.query.__str__()
-                )
+                f"Failed to execute FULLTEXT search on Bugscache, error={e}, SQL={recent_qs.query.__str__()}"
             )
             open_recent = []
             all_others = []
@@ -399,7 +397,6 @@ class FailureClassification(NamedModel):
 
 
 class ReferenceDataSignatures(models.Model):
-
     """
     A collection of all the possible combinations of reference data,
     populated on data ingestion. signature is a hash of the data it refers to
@@ -946,7 +943,7 @@ class FailureLine(models.Model):
 
     def _serialized_components(self):
         if self.action == "test_result":
-            return ["TEST-UNEXPECTED-%s" % self.status.upper(), self.test]
+            return [f"TEST-UNEXPECTED-{self.status.upper()}", self.test]
         if self.action == "log":
             return [self.level.upper(), self.message.split("\n")[0]]
 

treeherder/perf/alerts.py

@@ -112,7 +112,7 @@ def generate_new_alerts_in_series(signature):
 
                     if not isinstance(noise_profile, str):
                         raise Exception(
-                            "Expecting a string as a " f"noise profile, got: {type(noise_profile)}"
+                            f"Expecting a string as a noise profile, got: {type(noise_profile)}"
                         )
                 except Exception:
                     # Fail without breaking the alert computation

treeherder/perf/auto_perf_sheriffing/backfill_reports.py

@@ -264,9 +264,7 @@ class IdentifyAlertRetriggerables:
         retrigger_range = len(data_points_to_retrigger)
         if retrigger_range < self._range_width:
             self.log.warning(
-                "Found small backfill range (of size {} instead of {})".format(
-                    retrigger_range, self._range_width
-                )
+                f"Found small backfill range (of size {retrigger_range} instead of {self._range_width})"
             )
 
 

treeherder/perf/email.py

@@ -5,6 +5,7 @@ Its clients should only instantiate their writer of choice &
 provide it with some basic data to include in the email.
 They then get an email that's ready-to-send via taskcluster.Notify service.
 """
+
 import logging
 import re
 import urllib.parse

treeherder/perf/management/commands/backfill_perf_jobs.py

@@ -7,6 +7,7 @@ The subcommand's sole purpose is to act as a smoke test
 harness that quickly does an end-to-end check over the
 functionality of the `BackfillTool`.
 """
+
 from django.core.management.base import BaseCommand
 
 from treeherder.perf.auto_perf_sheriffing.factories import backfill_tool_factory

treeherder/perf/management/commands/generate_alerts.py

@@ -26,7 +26,7 @@ class Command(BaseCommand):
 
     def handle(self, *args, **options):
         if not options["project"]:
-            raise CommandError("Must specify at least one project with " "--project")
+            raise CommandError("Must specify at least one project with --project")
         for project in options["project"]:
             repository = models.Repository.objects.get(name=project)
 

treeherder/perf/management/commands/remove_multi_commit_data.py

@@ -4,6 +4,7 @@ This subcommand isn't intended for regular use.
 The subcommand's sole purpose is to clean the database of dirty
 performance_datum, in case a revert migration is needed.
 """
+
 from django.core.management.base import BaseCommand
 
 from treeherder.perf.models import MultiCommitDatum, PerformanceDatum

treeherder/perf/management/commands/remove_vcs_data.py

@@ -4,6 +4,7 @@ TODO: Remove this module entirely once all vcs data
  environments (from prototype up to & including production).
  See bug https://bugzilla.mozilla.org/show_bug.cgi?id=1694335
 """
+
 import time
 from datetime import timedelta
 

treeherder/perf/management/commands/test_analyze_perf.py

@@ -48,7 +48,7 @@ class Command(BaseCommand):
 
     def handle(self, *args, **options):
         if not options["project"]:
-            raise CommandError("Must specify at least one project with " "--project")
+            raise CommandError("Must specify at least one project with --project")
 
         pc = PerfherderClient(server_url=options["server"])
 

treeherder/perf/models.py

@@ -497,7 +497,7 @@ class PerformanceAlert(models.Model):
     prev_value = models.FloatField(help_text="Previous value of series before change")
     new_value = models.FloatField(help_text="New value of series after change")
     t_value = models.FloatField(
-        help_text="t value out of analysis indicating confidence " "that change is 'real'",
+        help_text="t value out of analysis indicating confidence that change is 'real'",
         null=True,
     )
 
@@ -549,7 +549,7 @@ class PerformanceAlert(models.Model):
         # or absence of a related summary
         if self.related_summary and self.status not in self.RELATIONAL_STATUS_IDS:
             raise ValidationError(
-                "Related summary set but status not in " "'{}'!".format(
+                "Related summary set but status not in '{}'!".format(
                     ", ".join(
                         [
                             STATUS[1]
@@ -561,7 +561,7 @@ class PerformanceAlert(models.Model):
             )
         if not self.related_summary and self.status not in self.UNRELATIONAL_STATUS_IDS:
             raise ValidationError(
-                "Related summary not set but status not in " "'{}'!".format(
+                "Related summary not set but status not in '{}'!".format(
                     ", ".join(
                         [
                             STATUS[1]

treeherder/perfalert/perfalert/__init__.py

@@ -106,14 +106,9 @@ class RevisionDatum:
         return self.push_timestamp < o.push_timestamp
 
     def __repr__(self):
-        values_str = "[ %s ]" % ", ".join(["%.3f" % value for value in self.values])
-        return "<{}: {}, {}, {:.3f}, {}>".format(
-            self.push_timestamp,
-            self.push_id,
-            values_str,
-            self.t,
-            self.change_detected,
-        )
+        values_csv = ", ".join([f"{value:.3f}" for value in self.values])
+        values_str = f"[ {values_csv} ]"
+        return f"<{self.push_timestamp}: {self.push_id}, {values_str}, {self.t:.3f}, {self.change_detected}>"
 
 
 def detect_changes(data, min_back_window=12, max_back_window=24, fore_window=12, t_threshold=7):

treeherder/push_health/utils.py

@@ -23,11 +23,11 @@ def clean_test(test, signature, message):
         left, right, *rest = clean_name.split(splitter)
 
         if "tests/layout/" in left and "tests/layout/" in right:
-            left = "layout%s" % left.split("tests/layout")[1]
-            right = "layout%s" % right.split("tests/layout")[1]
+            left = f"layout{left.split('tests/layout')[1]}"
+            right = f"layout{right.split('tests/layout')[1]}"
         elif "build/tests/reftest/tests/" in left and "build/tests/reftest/tests/" in right:
-            left = "%s" % left.split("build/tests/reftest/tests/")[1]
-            right = "%s" % right.split("build/tests/reftest/tests/")[1]
+            left = left.split("build/tests/reftest/tests/")[1]
+            right = right.split("build/tests/reftest/tests/")[1]
         elif clean_name.startswith("http://10.0"):
             left = "/tests/".join(left.split("/tests/")[1:])
             right = "/tests/".join(right.split("/tests/")[1:])

treeherder/webapp/api/performance_data.py

@@ -236,11 +236,11 @@ class PerformanceDatumViewSet(viewsets.ViewSet):
 
         if not (signature_ids or signature_hashes or push_ids or job_ids):
             raise exceptions.ValidationError(
-                "Need to specify either " "signature_id, signatures, " "push_id, or job_id"
+                "Need to specify either signature_id, signatures, push_id, or job_id"
             )
         if signature_ids and signature_hashes:
             raise exceptions.ValidationError(
-                "Can't specify both signature_id " "and signatures in same query"
+                "Can't specify both signature_id and signatures in same query"
             )
 
         datums = PerformanceDatum.objects.filter(repository=repository).select_related(
@@ -554,7 +554,7 @@ class PerformanceAlertViewSet(viewsets.ModelViewSet):
         data = request.data
         if "summary_id" not in data or "signature_id" not in data:
             return Response(
-                {"message": "Summary and signature ids necessary " "to create alert"},
+                {"message": "Summary and signature ids necessary to create alert"},
                 status=HTTP_400_BAD_REQUEST,
             )
 
@@ -1194,24 +1194,26 @@ class PerfCompareResults(generics.ListAPIView):
             highlighted_revisions_params.append((highlighted_revision_key, base_revision[:12]))
         highlighted_revisions_params.append((highlighted_revision_key, new_revision[:12]))
 
-        graph_link = "graphs?%s" % urlencode(highlighted_revisions_params)
+        encoded = urlencode(highlighted_revisions_params)
+        graph_link = f"graphs?{encoded}"
 
         if new_repo_name == base_repo_name:
             # if repo for base and new are not the same then make diff
             # series data one for each repo, else generate one
             repo_value = ",".join([new_repo_name, signature, "1", framework])
-            graph_link = graph_link + "&%s" % urlencode({series_key: repo_value})
+            encoded = urlencode({series_key: repo_value})
+            graph_link = f"{graph_link}&{encoded}"
         else:
             # if repos selected are not the same
             base_repo_value = ",".join([base_repo_name, signature, "1", framework])
             new_repo_value = ",".join([new_repo_name, signature, "1", framework])
             encoded = urlencode([(series_key, base_repo_value), (series_key, new_repo_value)])
+            graph_link = f"{graph_link}&{encoded}"
 
-            graph_link = graph_link + "&%s" % encoded
+        encoded = urlencode({time_range_key: time_range})
+        graph_link = f"{graph_link}&{encoded}"
 
-        graph_link = graph_link + "&%s" % urlencode({time_range_key: time_range})
-
-        return "https://treeherder.mozilla.org/perfherder/%s" % graph_link
+        return f"https://treeherder.mozilla.org/perfherder/{graph_link}"
 
     @staticmethod
     def _get_interval(base_push, new_push):

treeherder/webapp/api/performance_serializers.py

@@ -185,17 +185,13 @@ class PerformanceAlertSerializer(serializers.ModelSerializer):
                 and instance.summary.repository_id != related_summary.repository_id
             ):
                 raise exceptions.ValidationError(
-                    "New summary's repository ({}) does not match existing "
-                    "summary's repository ({})".format(
-                        related_summary.repository, instance.summary.framework
-                    )
+                    f"New summary's repository ({related_summary.repository}) does not match existing "
+                    f"summary's repository ({instance.summary.framework})"
                 )
             elif instance.summary.framework_id != related_summary.framework_id:
                 raise exceptions.ValidationError(
-                    "New summary's framework ({}) does not match existing "
-                    "summary's framework ({})".format(
-                        related_summary.framework, instance.summary.framework
-                    )
+                    f"New summary's framework ({related_summary.framework}) does not match existing "
+                    f"summary's framework ({instance.summary.framework})"
                 )
 
             status = validated_data.get("status")

treeherder/webapp/api/permissions.py

@@ -2,7 +2,6 @@ from rest_framework import permissions
 
 
 class IsStaffOrReadOnly(permissions.BasePermission):
-
     """
     The request is authenticated as an admin staff (eg. sheriffs), or is a read-only request.
     """

treeherder/webapp/api/refdata.py

@@ -11,7 +11,6 @@ from treeherder.webapp.api import serializers as th_serializers
 
 
 class RepositoryViewSet(viewsets.ReadOnlyModelViewSet):
-
     """ViewSet for the refdata Repository model"""
 
     queryset = models.Repository.objects.filter(active_status="active").select_related(
@@ -21,7 +20,6 @@ class RepositoryViewSet(viewsets.ReadOnlyModelViewSet):
 
 
 class OptionCollectionHashViewSet(viewsets.ViewSet):
-
     """ViewSet for the virtual OptionCollectionHash model"""
 
     def list(self, request):
@@ -39,7 +37,6 @@ class OptionCollectionHashViewSet(viewsets.ViewSet):
 
 
 class FailureClassificationViewSet(viewsets.ReadOnlyModelViewSet):
-
     """ViewSet for the refdata FailureClassification model"""
 
     queryset = models.FailureClassification.objects
@@ -47,7 +44,6 @@ class FailureClassificationViewSet(viewsets.ReadOnlyModelViewSet):
 
 
 class TaskclusterMetadataViewSet(viewsets.ReadOnlyModelViewSet):
-
     """ViewSet for the refdata TaskclusterMetadata model"""
 
     serializer_class = th_serializers.TaskclusterMetadataSerializer
@@ -63,7 +59,6 @@ class TaskclusterMetadataViewSet(viewsets.ReadOnlyModelViewSet):
 
 
 class UserViewSet(viewsets.ReadOnlyModelViewSet):
-
     """
     Info about a logged-in user.
     Used by Treeherder's UI to inspect user properties