fix api failing tests and update documentation

Author: davidgamez

api/tests/test_utils/db_utils.py

@@ -192,23 +192,14 @@ def is_test_db(url):
 
 def empty_database(db, url):
     if is_test_db(url):
-
-        metadata_tables = Base.metadata.tables
-
-        # Get all table names excluding those in the excluded_tables list
-        all_table_names = [table_name for table_name in metadata_tables.keys() if table_name not in excluded_tables]
-
-        # Sort the table names in reverse order of dependencies
-        tables_to_delete = sorted(
-            all_table_names, key=lambda name: len(metadata_tables[name].foreign_keys), reverse=True
-        )
-
         try:
             with db.start_db_session() as session:
-                for table_name in tables_to_delete:
-                    table = Base.metadata.tables[table_name]
-                    delete_stmt = delete(table)
-                    session.execute(delete_stmt)
-
+                # Using sorted_tables to respect foreign key constraints
+                for table in reversed(Base.metadata.sorted_tables):
+                    if table.name not in excluded_tables:
+                        table = Base.metadata.tables[table.name]
+                        delete_stmt = delete(table)
+                        session.execute(delete_stmt)
+                session.commit()
         except Exception as error:
             logging.error(f"Error while deleting from test db: {error}")

functions-python/tasks_executor/README.md

@@ -50,3 +50,14 @@ To get the list of supported tasks use:
    "payload": {}
 }
 ```
+To update the geolocation files precision:
+```json
+{
+   "task": "update_geojson_files_precision",
+   "payload": {
+      "dry_run": true,
+      "precision": 5,
+      "limit": 10
+   }
+}
+```

functions-python/tasks_executor/src/tasks/geojson/README.md

@@ -0,0 +1,55 @@
+# Update GeoJSON files
+
+This task adjust the GeoJSON files removing the map IDs and reducing the precision of the coordinates to 5 decimal places. ALso updates the geolocation_file_created_date and geolocation_file_dataset_id fields in the Feed table.
+
+---
+
+## Task ID
+
+Use task ID: `update_geojson_files_precision`
+
+---
+
+## Usage
+
+The function accepts the following payload:
+
+```json
+{
+  "dry_run": true,                // [optional] If true, do not upload or modify the database (default: true)
+  "precision": 5,                 // [optional] Number of decimal places to keep in coordinates (default: 5)
+  "limit": 10                     // [optional] Limit the number of feeds to process (default: no limit)
+}
+```
+
+### Example:
+
+```json
+{
+  "dry_run": true,
+  "limit": 10
+}
+```
+
+---
+
+## What It Does
+
+List all feeds with GeoJSON files, download each file, remove map IDs, reduce coordinate precision to the specified number of decimal places, and re-upload the modified file.
+Also updates the `geolocation_file_created_date` and `geolocation_file_dataset_id` fields in the `Feed` table.
+
+## GCP Environment Variables
+
+The function requires the following environment variables:
+
+| Variable               | Description                                                                  |
+| ---------------------- | ---------------------------------------------------------------------------- |
+| `DATASETS_BUCKET_NAME` | The name of the GCS bucket used to store extracted GTFS files                |
+
+---
+
+## Additional Notes
+
+* Commits to the database occur in batches of 100 feeds to improve performance and avoid large transaction blocks.
+* If `dry_run` is enabled, files are uploads or DB modifications are performed. Only the number of affected feeds is logged.
+* The function is safe to rerun. It will only affect feeds with missing geolocation_file_dataset_id.