global: enforce line length

.github/actions/combine-durations/combine_durations.py

@@ -7,13 +7,15 @@
 
 current_path = Path(".").resolve()
 print(
-    f"Combining durations with split-prefix={split_prefix} and durations-path={durations_path} in {current_path}."
+    f"Combining durations with split-prefix={split_prefix} and"
+    f" durations-path={durations_path} in {current_path}."
 )
 split_paths = Path(".").glob(f"{split_prefix}*/{durations_path.name}")
 try:
     previous_durations = json.loads(durations_path.read_text())
     print(
-        f"Loaded previous durations from {durations_path}, found {len(previous_durations)} test durations."
+        f"Loaded previous durations from {durations_path}, found"
+        f" {len(previous_durations)} test durations."
     )
 except FileNotFoundError:
     previous_durations = {}
@@ -31,7 +33,8 @@
     }
     new_durations.update(updated_durations)
     print(
-        f"Updated durations from {path} containing {len(updated_durations)} changed test durations."
+        f"Updated durations from {path} containing {len(updated_durations)} changed"
+        " test durations."
     )
 
 durations_path.parent.mkdir(parents=True, exist_ok=True)

backend/inspirehep/accounts/views.py

@@ -99,7 +99,8 @@ def set_orcid_push_setting():
 
         if len(tokens) != 1:
             raise ValueError(
-                f"One token per remote account is expected, but found {len(tokens)} for {orcid}"
+                f"One token per remote account is expected, but found {len(tokens)} for"
+                f" {orcid}"
             )
 
         push_account_literature_to_orcid.apply_async(

backend/inspirehep/alembic/3637cb5551a8_update_values_in_authorschematype.py

@@ -46,7 +46,8 @@ def upgrade():
         "CREATE TABLE tmp_records_authors (LIKE records_authors INCLUDING CONSTRAINTS);"
     )
     op.execute(
-        f"INSERT INTO tmp_records_authors SELECT * FROM records_authors WHERE id_type IN {new_enum_types};"
+        "INSERT INTO tmp_records_authors SELECT * FROM records_authors WHERE id_type"
+        f" IN {new_enum_types};"
     )
     op.execute(
         "ALTER TABLE tmp_records_authors ALTER COLUMN id_type TYPE VARCHAR(255);"
@@ -81,7 +82,8 @@ def upgrade():
     op.execute(f"CREATE TYPE enum_author_schema_type AS ENUM {new_enum_types};")
     op.execute("ALTER TABLE tmp_records_authors RENAME TO records_authors")
     op.execute(
-        "ALTER TABLE records_authors ALTER COLUMN id_type TYPE enum_author_schema_type USING (id_type::enum_author_schema_type);"
+        "ALTER TABLE records_authors ALTER COLUMN id_type TYPE enum_author_schema_type"
+        " USING (id_type::enum_author_schema_type);"
     )
 
 
@@ -91,5 +93,6 @@ def downgrade():
     op.execute("DROP TYPE IF EXISTS enum_author_schema_type;")
     op.execute(f"CREATE TYPE enum_author_schema_type AS ENUM {old_enum_values}")
     op.execute(
-        "ALTER TABLE records_authors ALTER COLUMN id_type TYPE enum_author_schema_type USING (id_type::enum_author_schema_type);"
+        "ALTER TABLE records_authors ALTER COLUMN id_type TYPE enum_author_schema_type"
+        " USING (id_type::enum_author_schema_type);"
     )

backend/inspirehep/alembic/72d010d89702_update_constraints_in_records_authors.py

@@ -20,10 +20,12 @@ def upgrade():
     """Upgrade database."""
     op.execute("CREATE SEQUENCE records_authors_id_seq OWNED BY records_authors.id;")
     op.execute(
-        "SELECT SETVAL('records_authors_id_seq', (select max(id) from records_authors), false)"
+        "SELECT SETVAL('records_authors_id_seq', (select max(id) from records_authors),"
+        " false)"
     )
     op.execute(
-        "ALTER TABLE records_authors ALTER COLUMN id SET DEFAULT nextval('records_authors_id_seq');"
+        "ALTER TABLE records_authors ALTER COLUMN id SET DEFAULT"
+        " nextval('records_authors_id_seq');"
     )
     op.execute(
         "ALTER TABLE records_authors ADD CONSTRAINT pk_authors_records PRIMARY KEY (id)"

backend/inspirehep/alembic/b495825c322b_add_recid_to_recordsauthors_id_type.py

@@ -51,5 +51,6 @@ def downgrade():
     op.execute("DROP TYPE IF EXISTS enum_author_schema_type;")
     op.execute(f"CREATE TYPE enum_author_schema_type AS ENUM {old_enum_values}")
     op.execute(
-        "ALTER TABLE records_authors ALTER COLUMN id_type TYPE enum_author_schema_type USING (id_type::enum_author_schema_type);"
+        "ALTER TABLE records_authors ALTER COLUMN id_type TYPE enum_author_schema_type"
+        " USING (id_type::enum_author_schema_type);"
     )

backend/inspirehep/alembic/c6570e49b7b2_change_record_citations_to_records_.py

@@ -19,10 +19,12 @@ def upgrade():
     """Upgrade database."""
     op.rename_table("record_citations", "records_citations")
     op.execute(
-        "ALTER TABLE records_citations RENAME CONSTRAINT fk_record_citations_cited TO fk_records_citations_cited_id"
+        "ALTER TABLE records_citations RENAME CONSTRAINT fk_record_citations_cited TO"
+        " fk_records_citations_cited_id"
     )
     op.execute(
-        "ALTER TABLE records_citations RENAME CONSTRAINT fk_record_citations_citer TO fk_records_citations_citer_id"
+        "ALTER TABLE records_citations RENAME CONSTRAINT fk_record_citations_citer TO"
+        " fk_records_citations_citer_id"
     )
     op.execute(
         "ALTER INDEX idx_citations_cited RENAME TO ix_records_citations_cited_id"
@@ -33,10 +35,12 @@ def downgrade():
     """Downgrade database."""
     op.rename_table("records_citations", "record_citations")
     op.execute(
-        "ALTER TABLE record_citations RENAME CONSTRAINT fk_records_citations_cited_id TO fk_record_citations_cited"
+        "ALTER TABLE record_citations RENAME CONSTRAINT fk_records_citations_cited_id"
+        " TO fk_record_citations_cited"
     )
     op.execute(
-        "ALTER TABLE record_citations RENAME CONSTRAINT fk_records_citations_citer_id TO fk_record_citations_citer"
+        "ALTER TABLE record_citations RENAME CONSTRAINT fk_records_citations_citer_id"
+        " TO fk_record_citations_citer"
     )
     op.execute(
         "ALTER INDEX ix_records_citations_cited_id RENAME TO idx_citations_cited"

backend/inspirehep/assign/views.py

@@ -60,7 +60,8 @@ def assign_to_new_stub_author(author_record, literature_recids):
         stub_author_data = update_author_names({"name": {}}, author_signatures)
     else:
         LOGGER.warning(
-            "Author not found in literature authors, creating stub author with author record data",
+            "Author not found in literature authors, creating stub author with author"
+            " record data",
             author_recid=from_author_recid,
         )
         stub_author_data = {"name": author_record["name"]}

backend/inspirehep/cds/api.py

@@ -40,7 +40,8 @@ def sync_identifiers(since=None):
     since = since or last_run_date
     if not since:
         LOGGER.error(
-            "CDS Sync failed. No `since` provided and no successful runs in DB. Aborting."
+            "CDS Sync failed. No `since` provided and no successful runs in DB."
+            " Aborting."
         )
         raise CDSSyncError("Missing `since` date")
 
@@ -144,10 +145,11 @@ def get_record_for_provided_ids(control_numbers, arxivs, dois, report_numbers):
     for report_number in report_numbers:
         arxiv = report_number.lower().split("arxiv:")[-1]
         #  Report numbers might contain arxivs or normal report numbers
-        if is_arxiv(arxiv):
-            record_object = get_record_for_pid_or_none("arxiv", arxiv)
-        else:
-            record_object = query_report_number(report_number)
+        record_object = (
+            get_record_for_pid_or_none("arxiv", arxiv)
+            if is_arxiv(arxiv)
+            else query_report_number(report_number)
+        )
         if record_object:
             LOGGER.info(
                 "Matched record by `report_number`",

backend/inspirehep/cds/cli.py

@@ -25,7 +25,10 @@ def cds():
     "-s",
     "since",
     default=None,
-    help="Date from when CDS should be synced. If not provided last successful run date will be used.",
+    help=(
+        "Date from when CDS should be synced. If not provided last successful run date"
+        " will be used."
+    ),
 )
 @with_appcontext
 def sync(since=None):
@@ -43,7 +46,8 @@ def sync(since=None):
             since = datetime.strptime(since, "%Y-%m-%d").date()
         except ValueError as e:
             raise WrongDateFormat(
-                f"`since`: {since} is in wrong format. Should be in ISO format: YYYY-MM-DD."
+                f"`since`: {since} is in wrong format. Should be in ISO format:"
+                " YYYY-MM-DD."
             ) from e
     try:
         click.echo("Starting CDS Sync.")

backend/inspirehep/curation/errors.py

@@ -10,4 +10,7 @@ def __init__(self, collaboration_id, subgroup, **kwargs):
         super().__init__(**kwargs)
         self.collaboration_id = collaboration_id
         self.subgroup_missing = subgroup
-        self.message = f"Subgroup {self.subgroup_missing} was not found in collaboration {self.collaboration_id} (normalization problem)."
+        self.message = (
+            f"Subgroup {self.subgroup_missing} was not found in collaboration"
+            f" {self.collaboration_id} (normalization problem)."
+        )

backend/inspirehep/curation/search_check_do/base.py

@@ -63,10 +63,11 @@ def search(self):
         search_instance = self.search_class()
         # For literature, `query_from_iq` does unwanted permission checks,
         # so we work around it
-        if isinstance(search_instance, LiteratureSearch):
-            query = search_instance.query(IQ(self.query, search_instance))
-        else:
-            query = search_instance.query_from_iq(self.query)
+        query = (
+            search_instance.query(IQ(self.query, search_instance))
+            if isinstance(search_instance, LiteratureSearch)
+            else search_instance.query_from_iq(self.query)
+        )
         query = query.params(_source={}, size=self.size, scroll="60m")
         if shard_filter := self._current_shard_filter():
             query = query.filter("script", script=shard_filter)

backend/inspirehep/curation/search_check_do/examples.py

@@ -180,7 +180,10 @@ def do(record, logger, state):
 
 
 class MoveFermilabURLs(SearchCheckDo):
-    query = "urls.value:http://lss.fnal.gov/cgi-bin/find_paper.pl* OR urls.value:https://lss.fnal.gov/cgi-bin/find_paper.pl*"
+    query = (
+        "urls.value:http://lss.fnal.gov/cgi-bin/find_paper.pl* OR"
+        " urls.value:https://lss.fnal.gov/cgi-bin/find_paper.pl*"
+    )
 
     @staticmethod
     def check(record, logger, state):
@@ -197,7 +200,10 @@ def do(record, logger, state):
 class HideElsevierFulltext(SearchCheckDo):
     """Hide fulltexts from Elsevier that have been incorrectly set as non-hidden."""
 
-    query = "(jy 2013 or 2014 or 2015) and documents.filename:'xml' and (arxiv_eprints.value:* or not documents.hidden:true)"
+    query = (
+        "(jy 2013 or 2014 or 2015) and documents.filename:'xml' and"
+        " (arxiv_eprints.value:* or not documents.hidden:true)"
+    )
 
     @staticmethod
     def check(record, logger, state):

backend/inspirehep/curation/utils.py

@@ -265,7 +265,11 @@ def find_unambiguous_affiliation(result, wf_id):
             )
         if matched_aff:
             message_payload = {"literature recid": matched_author["control_number"]}
-            message = f"Found matching affiliation, literature recid: {matched_author['control_number']}, raw_affiliations: {matched_author_raw_affs}, matched affiliations: {matched_aff}"
+            message = (
+                "Found matching affiliation, literature recid:"
+                f" {matched_author['control_number']}, raw_affiliations:"
+                f" {matched_author_raw_affs}, matched affiliations: {matched_aff}"
+            )
             if wf_id:
                 message += f" workflow_id: {wf_id}"
             LOGGER.info("Found matching affiliation", message_payload)

backend/inspirehep/disambiguation/cli.py

@@ -162,21 +162,30 @@ def _send_celery_group_disambiguation_task(uuids, batch_size):
 @click.option(
     "--total-records",
     type=int,
-    help="Number of records to disambiguate, if not passed all records with at least one not disambiguated will be sent to the queue",
+    help=(
+        "Number of records to disambiguate, if not passed all records with at least one"
+        " not disambiguated will be sent to the queue"
+    ),
 )
 @click.option(
     "--indexing-queue-limit",
     type=int,
     default=MAX_INDEXER_QUEUE_LEN,
     show_default=True,
-    help="Number of records to disambiguate, if not passed all records with at least one not disambiguated will be sent to the queue",
+    help=(
+        "Number of records to disambiguate, if not passed all records with at least one"
+        " not disambiguated will be sent to the queue"
+    ),
 )
 @click.option(
     "--disambiguation-queue-limit",
     type=int,
     default=MAX_DISAMBIGUATION_QUEUE_LEN,
     show_default=True,
-    help="Number of records to disambiguate, if not passed all records with at least one not disambiguated will be sent to the queue",
+    help=(
+        "Number of records to disambiguate, if not passed all records with at least one"
+        " not disambiguated will be sent to the queue"
+    ),
 )
 def disambiguate_all_not_disambiguated(
     celery_batch_size, total_records, indexing_queue_limit, disambiguation_queue_limit

backend/inspirehep/editor/authorlist_utils.py

@@ -373,7 +373,7 @@ def create_authors(text):
     else:
         # authors = parse_blocks(text_blocks)
         raise ValueError(
-            "Authors grouped by affiliation? - Comming soon." "Or too many empty lines."
+            "Authors grouped by affiliation? - Comming soon.Or too many empty lines."
         )
 
     if warnings:

backend/inspirehep/editor/editor_soft_lock.py

@@ -72,9 +72,15 @@ def prepare_editor_lock_api_payload(self):
             ]
         ).strip(", ")
         if existing_user_locks:
-            editor_user_lock_msg = f"Record opened by {existing_user_locks} Their modifications aren't saved yet, they (or yours) might get lost."
+            editor_user_lock_msg = (
+                f"Record opened by {existing_user_locks} Their modifications aren't"
+                " saved yet, they (or yours) might get lost."
+            )
             payload["user_locks"] = editor_user_lock_msg
         elif existing_task_locks:
-            editor_task_lock_msg = f"Scheduled tasks: {existing_task_locks}. Your modifications might get lost"
+            editor_task_lock_msg = (
+                f"Scheduled tasks: {existing_task_locks}. Your modifications might get"
+                " lost"
+            )
             payload["task_locks"] = editor_task_lock_msg
         return payload

backend/inspirehep/editor/errors.py

@@ -9,7 +9,10 @@
 
 class EditorRevertToRevisionError(RESTException):
     code = 400
-    description = "Something went wrong while reverting to the previous revision, please try again later."
+    description = (
+        "Something went wrong while reverting to the previous revision, please try"
+        " again later."
+    )
 
 
 class EditorGetRevisionError(RESTException):

backend/inspirehep/editor/views.py

@@ -390,7 +390,8 @@ def normalize_affiliations_for_authors(parsed_authors):
         if normalized_affiliation:
             author["affiliations"] = normalized_affiliation
     LOGGER.info(
-        "Found ambiguous affiliations for raw affiliations, skipping affiliation linking.",
+        "Found ambiguous affiliations for raw affiliations, skipping affiliation"
+        " linking.",
         ambiguous_affiliations=normalized_affiliations_result["ambiguous_affiliations"],
     )
     return parsed_authors

backend/inspirehep/hal/tasks.py

@@ -83,10 +83,9 @@ def _hal_push(record):
         hal_id = hal_value[0] if hal_value else ""
         lock_name = f"hal:{record['control_number']}"
         with distributed_lock(lock_name, blocking=True):
-            if hal_id:
-                receipt = _hal_update(tei, hal_id, record)
-            else:
-                receipt = _hal_create(tei, record)
+            receipt = (
+                _hal_update(tei, hal_id, record) if hal_id else _hal_create(tei, record)
+            )
             if receipt and receipt.id != hal_id:
                 _write_hal_id_to_record(record, receipt.id)
             return receipt

backend/inspirehep/hepdata/cli.py

@@ -28,7 +28,10 @@ def hepdata():
     "-s",
     "since",
     default=None,
-    help="Date from when hepdata should be harvested. If not provided the date from a day before would be used.",
+    help=(
+        "Date from when hepdata should be harvested. If not provided the date from a"
+        " day before would be used."
+    ),
 )
 @with_appcontext
 def harvest(since):
@@ -37,7 +40,8 @@ def harvest(since):
             since = datetime.strptime(since, "%Y-%m-%d").date()
         except ValueError as e:
             raise ValueError(
-                f"`since`: {since} is in wrong format. Should be in ISO format: YYYY-MM-DD."
+                f"`since`: {since} is in wrong format. Should be in ISO format:"
+                " YYYY-MM-DD."
             ) from e
     else:
         since = (datetime.now() - timedelta(1)).strftime("%Y-%m-%d")

backend/inspirehep/indexer/base.py

@@ -26,12 +26,12 @@ class InspireRecordIndexer(RecordIndexer):
     def _prepare_record(record, index, doc_type="_doc", arguments=None, **kwargs):
         from inspirehep.records.api import LiteratureRecord
 
-        if current_app.config["FEATURE_FLAG_ENABLE_FULLTEXT"] and isinstance(
-            record, LiteratureRecord
-        ):
-            data = record.serialize_for_es_with_fulltext()
-        else:
-            data = record.serialize_for_es()
+        data = (
+            record.serialize_for_es_with_fulltext()
+            if current_app.config["FEATURE_FLAG_ENABLE_FULLTEXT"]
+            and isinstance(record, LiteratureRecord)
+            else record.serialize_for_es()
+        )
         before_record_index.send(
             current_app._get_current_object(),
             json=data,