🔄 synced file(s) with WordPress/openverse

.github/workflows/new_issues.yml

@@ -8,7 +8,6 @@ on:
 env:
   GH_TOKEN: ${{ secrets.ACCESS_TOKEN }} # Projects need a personal access token to work.
   ISSUE_ID: ${{ github.event.issue.node_id }} # The global issue ID that works in both REST and GraphQL APIs.
-  PROJECT_ID: "PVT_kwDOAAQ2Js4AMZdL" # The ID for the Openverse project (#75).
 
 jobs:
   add_issue:
@@ -26,65 +25,18 @@ jobs:
   add_issue_to_project:
     name: Add new issue to project
     runs-on: ubuntu-latest
-    env:
-      PRIORITY_FIELD_ID: "PVTSSF_lADOAAQ2Js4AMZdLzgH6Kbo" # The ID for the project Priority custom field.
     steps:
-      - name: Add issue to "Backlog"
-        run: |
-          # shellcheck disable=SC2016
-          gh api graphql -f query='
-          mutation($project:ID!, $issue:ID!) {
-            addProjectV2ItemById(input: {projectId: $project, contentId: $issue}) {
-              item {
-                id
-                content {
-                  ... on Issue {
-                    labels(first: 10) {
-                      nodes {
-                        name
-                      }
-                    }
-                  }
-                }
-              }
-            }
-          }' -f project="$PROJECT_ID" -f issue="$ISSUE_ID" >> issue_data.json
-
-          echo 'ITEM_ID='"$(jq '.data.addProjectV2ItemById.item.id' issue_data.json)" >> "$GITHUB_ENV"
-          ITEM_PRIORITY="$(jq '.data.addProjectV2ItemById.item.content.labels.nodes[] | select(.name | contains("priority")).name | split(": ")[1]' issue_data.json)" >> "$GITHUB_ENV"
-          # The IDs for the project's Priority custom field options.
-          # These IDs were manually retrieved from the GitHub API.
-          if [[ $ITEM_PRIORITY == "low" ]]; then
-              PRIORITY_VALUE_ID="279ae886"
-          elif [[ $ITEM_PRIORITY == "medium" ]]; then
-              PRIORITY_VALUE_ID="333b3c1d"
-          elif [[ $ITEM_PRIORITY == "high" ]]; then
-              PRIORITY_VALUE_ID="03fe8945"
-          else
-              PRIORITY_VALUE_ID="fb76bdbc"
-          fi
-          echo 'PRIORITY_VALUE_ID='"$PRIORITY_VALUE_ID" >> "$GITHUB_ENV"
-
-      - name: Set issue priority
-        run: |
-          # shellcheck disable=SC2016
-          gh api graphql -f query='
-            mutation (
-              $project: ID!
-              $item: ID!
-              $priority_field: ID!
-              $priority_value: String!
-            ) {
-              set_priority_field: updateProjectV2ItemFieldValue(input: {
-                projectId: $project
-                itemId: $item
-                fieldId: $priority_field
-                value: {
-                  singleSelectOptionId: $priority_value
-                  }
-              }) {
-                projectV2Item {
-                  id
-                  }
-              }
-            }' -f project="$PROJECT_ID" -f item="$ITEM_ID" -f priority_field="$PRIORITY_FIELD_ID" -f priority_value="$PRIORITY_VALUE_ID"
+      - uses: bulatt3/[email protected]
+        with:
+          project-url: https://github.com/orgs/WordPress/projects/75
+          github-token: ${{ secrets.ACCESS_TOKEN }}
+          # Exclude the issues with the following labels
+          labeled: project
+          label-operator: NOT
+          label-map: |
+            { "Priority": [
+              { "label": "🟥 priority: critical", "fieldValue": "🟥 priority: critical" },
+              { "label": "🟧 priority: high", "fieldValue": "🟧 priority: high" },
+              { "label": "🟨 priority: medium", "fieldValue": "🟨 priority: medium" },
+              { "label": "🟩 priority: low", "fieldValue": "🟩 priority: low" }
+            ]}

.pre-commit-config.yaml

@@ -6,7 +6,7 @@ exclude: Pipfile\.lock|migrations|\.idea|node_modules|archive|retired
 
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.0.1
+    rev: v4.4.0
     hooks:
       - id: trailing-whitespace
         args: [--markdown-linebreak-ext=md]
@@ -40,26 +40,26 @@ repos:
           - --lines-after-imports=2
 
   - repo: https://github.com/asottile/pyupgrade
-    rev: v3.2.2
+    rev: v3.3.1
     hooks:
       - id: pyupgrade
         args:
           - --py310-plus
 
   - repo: https://github.com/charliermarsh/ruff-pre-commit
-    rev: "v0.0.257"
+    rev: "v0.0.261"
     hooks:
       - id: ruff
 
   - repo: https://github.com/ambv/black
-    rev: 22.3.0
+    rev: 23.3.0
     hooks:
       - id: black
         args:
           - --safe
 
   - repo: https://github.com/pycqa/pydocstyle
-    rev: 6.2.2 # 6.2.3 is slightly broken
+    rev: 6.3.0
     hooks:
       - id: pydocstyle
         args:
@@ -83,11 +83,11 @@ repos:
           - [email protected]
 
   - repo: https://github.com/koalaman/shellcheck-precommit
-    rev: v0.8.0
+    rev: v0.9.0
     hooks:
       - id: shellcheck
 
   - repo: https://github.com/rhysd/actionlint
-    rev: main
+    rev: v1.6.24
     hooks:
       - id: actionlint-docker

docker/airflow/entrypoint.sh

@@ -29,9 +29,9 @@ END
 function header() {
   size=${COLUMNS:-80}
   # Print centered text between two dividers of length $size
-  printf '#%.0s' $(seq 1 $size) && echo
+  printf '#%.0s' $(seq 1 "$size") && echo
   printf "%*s\n" $(( (${#1} + size) / 2)) "$1"
-  printf '#%.0s' $(seq 1 $size) && echo
+  printf '#%.0s' $(seq 1 "$size") && echo
 }
 
 if [ "$1" == help ] || [ "$1" == --help ]; then help_text && exit 0; fi

openverse_catalog/dags/common/popularity/sql.py

@@ -73,7 +73,6 @@ def drop_media_popularity_relations(
     metrics=IMAGE_POPULARITY_METRICS_TABLE_NAME,
     pg_timeout: float = timedelta(minutes=10).total_seconds(),
 ):
-
     if media_type == AUDIO:
         db_view = AUDIO_VIEW_NAME
         constants = AUDIO_POPULARITY_CONSTANTS_VIEW

openverse_catalog/dags/common/slack.py

@@ -96,7 +96,6 @@ def __init__(
         unfurl_media: bool = True,
         http_conn_id: str = SLACK_NOTIFICATIONS_CONN_ID,
     ):
-
         self.http = HttpHook(method="POST", http_conn_id=http_conn_id)
         self.blocks = []
         self._context = {}

openverse_catalog/dags/maintenance/check_silenced_dags.py

@@ -96,7 +96,7 @@ def check_configuration(github_pat: str, airflow_variable: str):
         " a new issue."
     )
 
-    for (dag, issue, predicate, task_id_pattern) in dags_to_reenable:
+    for dag, issue, predicate, task_id_pattern in dags_to_reenable:
         dag_name = f"{dag} ({task_id_pattern})" if task_id_pattern else dag
         message += f"\n  - <{issue}|{dag_name}: '{predicate}'>"
 

openverse_catalog/dags/maintenance/flickr_audit_sub_provider_workflow.py

@@ -43,7 +43,6 @@ class SuggestedSubProvider(NamedTuple):
 
 
 class FlickrSubProviderAuditor:
-
     endpoint = "https://www.flickr.com/services/rest"
     retries = 2
 
@@ -162,7 +161,7 @@ def audit_flickr_sub_providers():
         raise AirflowSkipException("No new potential sub-providers were identified.")
 
     message = "Consider adding the following sub-providers for Flickr:"
-    for (name, nsid, cc_count) in potential_sub_providers:
+    for name, nsid, cc_count in potential_sub_providers:
         message += "\n"
         message += f"{name}: {nsid} _({cc_count} cc-licensed images)_"
 

openverse_catalog/dags/providers/provider_api_scripts/inaturalist.py

@@ -53,7 +53,6 @@
 
 
 class INaturalistDataIngester(ProviderDataIngester):
-
     providers = {"image": provider_details.INATURALIST_DEFAULT_PROVIDER}
 
     def get_next_query_params(self, prev_query_params=None, **kwargs):
@@ -293,9 +292,7 @@ def load_catalog_of_life_names(task: PythonOperator, remove_api_files: bool):
 
     @staticmethod
     def create_preingestion_tasks():
-
         with TaskGroup(group_id="preingestion_tasks") as preingestion_tasks:
-
             check_for_file_updates = PythonOperator(
                 task_id="check_for_file_updates",
                 python_callable=INaturalistDataIngester.compare_update_dates,
@@ -365,9 +362,7 @@ def create_postingestion_tasks():
 
     @staticmethod
     def create_ingestion_workflow():
-
         with TaskGroup(group_id="ingest_data") as ingest_data:
-
             preingestion_tasks = INaturalistDataIngester.create_preingestion_tasks()
 
             with TaskGroup(group_id="pull_image_data") as pull_data:
@@ -380,7 +375,6 @@ def create_ingestion_workflow():
                     ),
 
             with TaskGroup(group_id="load_image_data") as loader_tasks:
-
                 # Using the existing set up, but the indexes on the temporary table
                 # probably slows down the load a bit.
                 create_loading_table = PythonOperator(

openverse_catalog/dags/providers/provider_api_scripts/smithsonian.py

@@ -150,7 +150,6 @@ def get_record_data(self, data: dict) -> dict | list[dict] | None:
         # Parse out the necessary info from the record data into a dictionary.
         images = []
         if image_list := self._get_image_list(data):
-
             if (foreign_landing_url := self._get_foreign_landing_url(data)) is None:
                 return None
 

openverse_catalog/dags/providers/provider_api_scripts/time_delineated_provider_data_ingester.py

@@ -159,7 +159,7 @@ def _get_timestamp_pairs(self, **kwargs):
         # portions.
         hour_slices = self._get_timestamp_query_params_list(start_ts, end_ts, 24)
 
-        for (start_hour, end_hour) in hour_slices:
+        for start_hour, end_hour in hour_slices:
             # Get the number of records in this hour interval
             record_count = self._get_record_count(start_hour, end_hour, **kwargs)
             if record_count == 0:

openverse_catalog/dags/providers/provider_api_scripts/wikimedia_commons.py

@@ -564,7 +564,7 @@ def extract_geo_data(media_data):
             "map_datum": "GPSMapDatum",
         }
         geo_data = {}
-        for (key, value) in geo_properties.items():
+        for key, value in geo_properties.items():
             key_value = media_data.get(value, {}).get("value")
             if key_value:
                 geo_data[key] = key_value

tests/dags/common/popularity/test_sql.py

@@ -345,7 +345,7 @@ def test_constants_view_adds_values_and_constants(
         ("my_provider", "views", 0.5, 50.0, 50.0, 50.0),
     ]
     sorted_rows = sorted(list(postgres_with_image_table.cursor), key=lambda x: x[0])
-    for (expect_row, sorted_row) in zip(expect_rows, sorted_rows):
+    for expect_row, sorted_row in zip(expect_rows, sorted_rows):
         assert expect_row == pytest.approx(sorted_row)
 
 
@@ -401,7 +401,7 @@ def test_constants_view_handles_zeros_and_missing(
         ("my_provider", "views", 0.8, 0.0, 1.0, 0.25),
     ]
     sorted_rows = sorted(list(postgres_with_image_table.cursor), key=lambda x: x[0])
-    for (expect_row, sorted_row) in zip(expect_rows, sorted_rows):
+    for expect_row, sorted_row in zip(expect_rows, sorted_rows):
         assert expect_row == pytest.approx(sorted_row)
 
 

tests/dags/providers/provider_api_scripts/resources/inaturalist/pull_sample_records.py

@@ -96,7 +96,6 @@ def get_sample_id_list(sample_file, joined_on):
 
 
 if __name__ == "__main__":
-
     # PHOTOS
     photo_ids = [
         str(i)

tests/dags/providers/provider_api_scripts/test_provider_data_ingester.py

@@ -193,7 +193,6 @@ def test_process_batch_halts_processing_after_reaching_ingestion_limit():
         patch.object(image_store, "add_item"),
         patch.object(ingester, "get_record_data") as get_record_data_mock,
     ):
-
         # Mock `get_record_data` to return a list of 2 records
         get_record_data_mock.return_value = MOCK_RECORD_DATA_LIST
         record_count = ingester.process_batch(EXPECTED_BATCH_DATA)

tests/dags/providers/provider_api_scripts/test_time_delineated_provider_data_ingester.py

@@ -237,7 +237,7 @@ def test_ingest_records_raises_error_if_the_total_count_has_been_exceeded():
         )
         # Assert that attempting to ingest records raises an exception when
         # `should_raise_error` is enabled
-        with (pytest.raises(Exception, match=expected_error_string)):
+        with pytest.raises(Exception, match=expected_error_string):
             ingester.ingest_records()
 
         # get_mock should have been called 4 times, twice for each batch (once in `get_batch`