Update the facets in BigQuery tests to include catalog facets

Signed-off-by: Pawel Marut <[email protected]>

Author: LegendPawel-Marut

producer/spark_dataproc/scenarios/bigquery_to_iceberg/config.json

@@ -221,7 +221,7 @@
         ]
       },
       "openlineage_versions": {
-        "min": "1.38.0" //???
+        "min": "1.38.0"
       }
     }
   ]

producer/spark_dataproc/scenarios/bigquery_to_iceberg/events/catalog_test.json

@@ -7,18 +7,16 @@
   "outputs": [
     {
       "namespace": "gs://open-lineage-e2e",
-      "name": "{{ match(result, 'data/bigquery_metastore/e2e_dataset.*/e2e_table') }}", //"data/bigquery_metastore/e2e_dataset.db/e2e_table" ??
+      "name": "{{ match(result, 'data/bigquery_metastore/e2e_dataset.*/e2e_table') }}",
       "facets": {
         "catalog": {
-          ".*producer": "https://github.com/OpenLineage/OpenLineage.*",
-          ".*schemaURL": "https://openlineage.io/spec.*",
           "framework": "iceberg",
           "type": "bigquerymetastore",
           "name": "gcp_iceberg_catalog",
           "warehouseUri": "gs://open-lineage-e2e/data/bigquery_metastore/",
           "source": "spark",
           "catalogProperties": {
-            "gcp_location": "us-west1", // "{{ any(result) }}" ??
+            "gcp_location": "us-west1",
             "gcp_project_id": "gcp-open-lineage-testing"
           }
         }

producer/spark_dataproc/scenarios/bigquery_to_iceberg/events/gcp_dataproc_test.json

@@ -14,6 +14,7 @@
         "appName": "BigQuery to Iceberg with BigQueryMetastoreCatalog",
         "clusterName": "{{ match(result, 'dataproc-producer-test-.+') }}",
         "appId": "{{ match(result, 'application_.+') }}",
+        "jobType": "dataproc_job",
         "projectId": "gcp-open-lineage-testing"
       }
     }

producer/spark_dataproc/scenarios/bigquery_to_iceberg/events/sql_test.json

@@ -5,7 +5,8 @@
     "name": "big_query_to_iceberg_with_big_query_metastore_catalog.append_data.gcp_iceberg_catalog_e2e_dataset_e2e_table",
     "facets": {
       "sql": {
-        "query": "SELECT word, SUM(word_count) AS word_count FROM words GROUP BY word"
+        "query": "SELECT word, SUM(word_count) AS word_count FROM words GROUP BY word",
+        "dialect": "spark"
       }
     }
   }