feat: add support for timezones - 946

api/src/feeds/impl/models/gtfs_dataset_impl.py

@@ -51,4 +51,5 @@ def from_orm(cls, gtfs_dataset: Gtfsdataset | None) -> GtfsDataset | None:
             validation_report=cls.from_orm_latest_validation_report(gtfs_dataset.validation_reports),
             service_date_range_start=gtfs_dataset.service_date_range_start,
             service_date_range_end=gtfs_dataset.service_date_range_end,
+            agency_timezone=gtfs_dataset.agency_timezone,
         )

api/src/feeds/impl/models/latest_dataset_impl.py

@@ -53,6 +53,7 @@ def from_orm(cls, dataset: Gtfsdataset | None) -> LatestDataset | None:
             downloaded_at=dataset.downloaded_at,
             service_date_range_start=dataset.service_date_range_start,
             service_date_range_end=dataset.service_date_range_end,
+            agency_timezone=dataset.agency_timezone,
             hash=dataset.hash,
             validation_report=validation_report,
         )

api/src/feeds/impl/models/search_feed_item_result_impl.py

@@ -46,6 +46,7 @@ def from_orm_gtfs(cls, feed_search_row):
                 hash=feed_search_row.latest_dataset_hash,
                 service_date_range_start=feed_search_row.latest_dataset_service_date_range_start,
                 service_date_range_end=feed_search_row.latest_dataset_service_date_range_end,
+                agency_timezone=feed_search_row.latest_dataset_agency_timezone,
             )
             if feed_search_row.latest_dataset_id
             else None,

api/tests/test_data/extra_test_data.json

@@ -8,8 +8,9 @@
       "hash": "hash",
       "downloaded_at": "2024-01-31T00:00:00+00:00",
       "feed_stable_id": "mdb-1",
-      "service_date_range_start": "2024-01-01",
-      "service_date_range_end":"2025-01-01"
+      "service_date_range_start": "2024-09-29T00:00:00+00:00",
+      "service_date_range_end":"2025-09-29T00:00:00+00:00",
+      "agency_timezone": "Canada/Atlantic"
     },
     {
       "id": "dataset-2",
@@ -19,8 +20,9 @@
       "hash": "hash",
       "downloaded_at": "2024-02-01T00:00:00+00:00",
       "feed_stable_id": "mdb-1",
-      "service_date_range_start": "2024-01-01",
-      "service_date_range_end":"2025-01-01"
+      "service_date_range_start": "2024-09-29T00:00:00+00:00",
+      "service_date_range_end":"2025-09-29T00:00:00+00:00",
+      "agency_timezone": "Canada/Atlantic"
     },
     {
       "id": "dataset-3",
@@ -30,8 +32,9 @@
       "hash": "hash",
       "downloaded_at": "2024-02-02T00:00:00+00:00",
       "feed_stable_id": "mdb-10",
-      "service_date_range_start": "2024-01-01",
-      "service_date_range_end":"2025-01-01"
+      "service_date_range_start": "2024-09-29T00:00:00+00:00",
+      "service_date_range_end":"2025-09-29T00:00:00+00:00",
+      "agency_timezone": "Canada/Atlantic"
     },
     {
       "id": "dataset-4",
@@ -41,8 +44,9 @@
       "hash": "hash",
       "downloaded_at": "2024-02-03T00:00:00+00:00",
       "feed_stable_id": "mdb-10",
-      "service_date_range_start": "2024-01-01",
-      "service_date_range_end":"2025-01-01"
+      "service_date_range_start": "2024-09-29T00:00:00+00:00",
+      "service_date_range_end":"2025-09-29T00:00:00+00:00",
+      "agency_timezone": "Canada/Atlantic"
     }
   ],
   "validation_reports": [

api/tests/test_data/test_datasets.json

@@ -9,8 +9,9 @@
       "hash": "hash-1",
       "latest": true,
       "bounding_box": "POLYGON((-122.75 36.8, -122.75 37.8, -121.75 37.8, -121.75 36.8, -122.75 36.8))",
-      "service_date_range_start": "2024-01-01",
-      "service_date_range_end":"2025-01-01"
+      "service_date_range_start": "2024-09-29T00:00:00+00:00",
+      "service_date_range_end":"2025-09-29T00:00:00+00:00",
+      "agency_timezone": "Canada/Atlantic"
     },
     {
       "id": "dataset-2",
@@ -20,8 +21,9 @@
       "hash": "hash-2",
       "latest": false,
       "bounding_box": "POLYGON((-122.75 36.8, -122.75 37.8, -121.75 37.8, -121.75 36.8, -122.75 36.8))",
-      "service_date_range_start": "2024-01-01",
-      "service_date_range_end":"2025-01-01"
+      "service_date_range_start": "2024-09-29T00:00:00+00:00",
+      "service_date_range_end":"2025-09-29T00:00:00+00:00",
+      "agency_timezone": "Canada/Atlantic"
     },
     {
       "id": "dataset-3",
@@ -31,8 +33,9 @@
       "hash": "hash-3",
       "latest": true,
       "bounding_box": "POLYGON((-122.75 36.8, -122.75 37.8, -121.75 37.8, -121.75 36.8, -122.75 36.8))",
-      "service_date_range_start": "2024-01-01",
-      "service_date_range_end":"2025-01-01"
+      "service_date_range_start": "2024-09-29T00:00:00+00:00",
+      "service_date_range_end":"2025-09-29T00:00:00+00:00",
+      "agency_timezone": "Canada/Atlantic"
     },
     {
       "id": "dataset-4",
@@ -42,8 +45,9 @@
       "hash": "hash-4",
       "latest": false,
       "bounding_box": "POLYGON((-122.75 36.8, -122.75 37.8, -121.75 37.8, -121.75 36.8, -122.75 36.8))",
-      "service_date_range_start": "2024-01-01",
-      "service_date_range_end":"2025-01-01"
+      "service_date_range_start": "2024-09-29T00:00:00+00:00",
+      "service_date_range_end":"2025-09-29T00:00:00+00:00",
+      "agency_timezone": "Canada/Atlantic"
     },
     {
       "id": "dataset-5",
@@ -53,8 +57,9 @@
       "hash": "hash-5",
       "latest": true,
       "bounding_box": "POLYGON((-122.75 36.8, -122.75 37.8, -121.75 37.8, -121.75 36.8, -122.75 36.8))",
-      "service_date_range_start": "2024-01-01",
-      "service_date_range_end":"2025-01-01"
+      "service_date_range_start": "2024-09-29T00:00:00+00:00",
+      "service_date_range_end":"2025-09-29T00:00:00+00:00",
+      "agency_timezone": "Canada/Atlantic"
     }
   ],
   "validation_reports": [

api/tests/unittest/models/test_basic_feed_impl.py

@@ -1,6 +1,7 @@
 import copy
 import unittest
-from datetime import datetime, date
+from datetime import datetime
+from zoneinfo import ZoneInfo
 
 from shared.database_gen.sqlacodegen_models import (
     Feed,
@@ -64,8 +65,9 @@
             downloaded_at="downloaded_at",
             hash="hash",
             bounding_box="bounding_box",
-            service_date_range_start=date(2024, 1, 1),
-            service_date_range_end=date(2025, 1, 1),
+            service_date_range_start=datetime(2024, 1, 1, 0, 0, 0, tzinfo=ZoneInfo("Canada/Atlantic")),
+            service_date_range_end=datetime(2025, 1, 1, 0, 0, 0, tzinfo=ZoneInfo("Canada/Atlantic")),
+            agency_timezone="Canada/Atlantic",
             validation_reports=[
                 Validationreport(
                     id="id",

api/tests/unittest/models/test_gtfs_dataset_impl.py

@@ -1,5 +1,6 @@
 import unittest
-from datetime import datetime, date
+from datetime import datetime
+from zoneinfo import ZoneInfo
 
 from geoalchemy2 import WKTElement
 
@@ -42,8 +43,9 @@ def test_from_orm(self):
                 Validationreport(validator_version="0.2.0"),
                 Validationreport(validator_version="1.1.1"),
             ],
-            service_date_range_start=date(2024, 1, 1),
-            service_date_range_end=date(2025, 1, 1),
+            service_date_range_start=datetime(2024, 1, 1, 0, 0, 0, tzinfo=ZoneInfo("Canada/Atlantic")),
+            service_date_range_end=datetime(2025, 1, 1, 0, 0, 0, tzinfo=ZoneInfo("Canada/Atlantic")),
+            agency_timezone="Canada/Atlantic",
         )
         result = GtfsDatasetImpl.from_orm(orm)
         assert result.id == "stable_id"
@@ -58,7 +60,8 @@ def test_from_orm(self):
         assert result.bounding_box.minimum_longitude == 3.0
         assert result.bounding_box.maximum_longitude == 4.0
         assert result.validation_report.validator_version == "1.1.1"
-        assert result.service_date_range_start == date(2024, 1, 1)
-        assert result.service_date_range_end == date(2025, 1, 1)
+        assert result.service_date_range_start == datetime(2024, 1, 1, 0, 0, 0, tzinfo=ZoneInfo("Canada/Atlantic"))
+        assert result.service_date_range_end == datetime(2025, 1, 1, 0, 0, 0, tzinfo=ZoneInfo("Canada/Atlantic"))
+        assert result.agency_timezone == "Canada/Atlantic"
 
         assert GtfsDatasetImpl.from_orm(None) is None

api/tests/unittest/models/test_gtfs_feed_impl.py

@@ -1,6 +1,7 @@
 import copy
 import unittest
-from datetime import datetime, date
+from datetime import datetime
+from zoneinfo import ZoneInfo
 
 from geoalchemy2 import WKTElement
 
@@ -87,8 +88,9 @@ def create_test_notice(notice_code: str, total_notices: int, severity: str):
             note="note",
             downloaded_at=datetime(year=2022, month=12, day=31, hour=13, minute=45, second=56),
             hash="hash",
-            service_date_range_start=date(2024, 1, 1),
-            service_date_range_end=date(2025, 1, 1),
+            service_date_range_start=datetime(2024, 1, 1, 0, 0, 0, tzinfo=ZoneInfo("Canada/Atlantic")),
+            service_date_range_end=datetime(2025, 1, 1, 0, 0, 0, tzinfo=ZoneInfo("Canada/Atlantic")),
+            agency_timezone="Canada/Atlantic",
             bounding_box=WKTElement(POLYGON, srid=4326),
             latest=True,
             validation_reports=[
@@ -171,8 +173,9 @@ def create_test_notice(notice_code: str, total_notices: int, severity: str):
             unique_warning_count=4,
             unique_info_count=2,
         ),
-        service_date_range_start="2024-01-01",
-        service_date_range_end="2025-01-01",
+        service_date_range_start=datetime(2024, 1, 1, 0, 0, 0, tzinfo=ZoneInfo("Canada/Atlantic")),
+        service_date_range_end=datetime(2025, 1, 1, 0, 0, 0, tzinfo=ZoneInfo("Canada/Atlantic")),
+        agency_timezone="Canada/Atlantic",
     ),
 )
 

api/tests/unittest/models/test_latest_dataset_impl.py

@@ -1,5 +1,6 @@
 import unittest
-from datetime import datetime, date
+from datetime import datetime
+from zoneinfo import ZoneInfo
 
 from geoalchemy2 import WKTElement
 
@@ -23,8 +24,9 @@ def test_from_orm(self):
                 downloaded_at=now,
                 hash="hash",
                 bounding_box=WKTElement(POLYGON, srid=4326),
-                service_date_range_start=date(2024, 1, 1),
-                service_date_range_end=date(2025, 1, 1),
+                service_date_range_start=datetime(2024, 1, 1, 0, 0, 0, tzinfo=ZoneInfo("Canada/Atlantic")),
+                service_date_range_end=datetime(2025, 1, 1, 0, 0, 0, tzinfo=ZoneInfo("Canada/Atlantic")),
+                agency_timezone="Canada/Atlantic",
                 validation_reports=[
                     Validationreport(validator_version="1.0.0"),
                     Validationreport(
@@ -52,8 +54,9 @@ def test_from_orm(self):
                 minimum_longitude=3.0,
                 maximum_longitude=4.0,
             ),
-            service_date_range_start=date(2024, 1, 1),
-            service_date_range_end=date(2025, 1, 1),
+            service_date_range_start=datetime(2024, 1, 1, 0, 0, 0, tzinfo=ZoneInfo("Canada/Atlantic")),
+            service_date_range_end=datetime(2025, 1, 1, 0, 0, 0, tzinfo=ZoneInfo("Canada/Atlantic")),
+            agency_timezone="Canada/Atlantic",
             validation_report={
                 "validator_version": "1.2.0",
                 "total_error": 3,

api/tests/unittest/models/test_search_feed_item_result_impl.py

@@ -40,8 +40,9 @@ def __init__(self, **kwargs):
     latest_dataset_downloaded_at=downloaded_at,
     latest_dataset_bounding_box=None,
     latest_dataset_hash="latest_dataset_hash",
-    latest_dataset_service_date_range_start="2030-10-10",
-    latest_dataset_service_date_range_end="2031-10-10",
+    latest_dataset_service_date_range_start="2030-09-29T00:00:00+00:00",
+    latest_dataset_service_date_range_end="2031-09-29T00:00:00+00:00",
+    latest_dataset_agency_timezone="Canada/Atlantic",
     external_ids=[],
     redirect_ids=[],
     feed_reference_ids=[],
@@ -84,6 +85,7 @@ def test_from_orm_gtfs(self):
                 hash=item.latest_dataset_hash,
                 service_date_range_start=item.latest_dataset_service_date_range_start,
                 service_date_range_end=item.latest_dataset_service_date_range_end,
+                agency_timezone=item.latest_dataset_agency_timezone,
             ),
         )
         assert result == expected

docs/DatabaseCatalogAPI.yaml

@@ -584,15 +584,19 @@ components:
           type: string
           example: ad3805c4941cd37881ff40c342e831b5f5224f3d8a9a2ec3ac197d3652c78e42
         service_date_range_start:
-          description: The start date of the service date range for the dataset.
+          description: The start date of the service date range for the dataset in UTC. Timing starts at 00:00:00 of the day.
           type: string
-          example: 2023-07-10
-          format: date
+          example: 2023-07-10T06:00:00Z
+          format: date-time
         service_date_range_end:
-          description: The start date of the service date range for the dataset.
+          description: The start date of the service date range for the dataset in UTC. Timing ends at 23:59:59 of the day.
+          type: string
+          example: 2023-07-10T05:59:59+00Z
+          format: date-time
+        agency_timezone:
+          description: The timezone of the agency.
           type: string
-          example: 2023-07-10
-          format: date
+          example: America/Los_Angeles
         validation_report:
           type: object
           properties:
@@ -784,15 +788,19 @@ components:
             validation_report:
               $ref: "#/components/schemas/ValidationReport"
             service_date_range_start:
-              description: The start date of the service date range for the dataset.
+              description: The start date of the service date range for the dataset in UTC. Timing starts at 00:00:00 of the day.
               type: string
-              example: 2023-07-10
-              format: date
+              example: 2023-07-10T06:00:00Z
+              format: date-time
             service_date_range_end:
-              description: The start date of the service date range for the dataset.
+              description: The start date of the service date range for the dataset in UTC. Timing ends at 23:59:59 of the day.
+              type: string
+              example: 2023-07-10T05:59:59+00Z
+              format: date-time
+            agency_timezone:
+              description: The timezone of the agency.
               type: string
-              example: 2023-07-10
-              format: date
+              example: America/Los_Angeles
 
     BoundingBox:
       description: Bounding box of the dataset when it was first added to the catalog.

functions-python/backfill_dataset_service_date_range/.env.rename_me

@@ -1,2 +1,3 @@
 # Environment variables for the validation report information extraction to run locally
 export FEEDS_DATABASE_URL=${{FEEDS_DATABASE_URL}}
+export ENV=${{ENV}}