Update reprocess_unnormalised_notices_from_backlog.py

.github/workflows/unit-tests.yml

@@ -26,9 +26,7 @@ jobs:
       - name: Install dependencies
         run: |
           sudo apt-get install -y libssl-dev libcurl4-openssl-dev
-          python -m pip install --upgrade setuptools pip wheel
-          make install
-          make install-dev
+          python -m pip install --upgrade setuptools pip wheel tox~=4.11.3
       - name: Make envfile
         uses: SpicyPizza/create-envfile@v1
         with:

dags/reprocess_unnormalised_notices_from_backlog.py

@@ -31,7 +31,8 @@ def reprocess_unnormalised_notices_from_backlog():
     def select_all_raw_notices():
         start_date = get_dag_param(key=START_DATE_DAG_PARAM)
         end_date = get_dag_param(key=END_DATE_DAG_PARAM)
-        notice_ids = notice_ids_selector_by_status(notice_statuses=[NoticeStatus.RAW], start_date=start_date,
+        notice_ids = notice_ids_selector_by_status(notice_statuses=[NoticeStatus.RAW, NoticeStatus.INDEXED],
+                                                   start_date=start_date,
                                                    end_date=end_date)
         push_dag_downstream(key=NOTICE_IDS_KEY, value=notice_ids)
 

requirements.dev.txt

@@ -1,8 +1,8 @@
-coverage~=6.3.1
-pytest~=7.0.0
-pytest-bdd~=5.0.0
-pytest-cov~=3.0.0
-pytest-subtests~=0.6.0
-tox~=3.24.5
+coverage~=7.3.2
+pytest~=7.4.3
+pytest-bdd~=7.0.0
+pytest-cov~=4.1.0
+pytest-subtests~=0.11.0
+tox~=4.11.3
 tox-pytest-summary~=0.1.2
-mongomock==4.0.0
+mongomock~=4.1.2

requirements.txt

@@ -1,4 +1,4 @@
-git+https://github.com/OP-TED/ted-rdf-conversion-pipeline.git@main
+git+https://github.com/OP-TED/ted-rdf-conversion-pipeline.git@1.2.0-rc.2
 elasticsearch~=8.6.2
 currencyconverter~=0.17.6
 pycountry~=22.3.5

ted_data_eu/adapters/nuts_processor.py

@@ -114,6 +114,7 @@ def __init__(self, nuts_csv: io.StringIO):
             }
         )
         self.dataframe[self.NUTS_PARENT_COLUMN_NAME] = self.dataframe[self.NUTS_PARENT_COLUMN_NAME].str.split("/").str[-1]
+        self.dataframe[self.NUTS_LABEL_COLUMN_NAME] = self.dataframe[self.NUTS_LABEL_COLUMN_NAME].str.partition(" ")[2]
 
     def nuts_exists(self, nuts_code: str) -> bool:
         """

ted_data_eu/services/etl_pipelines/ted_data_etl_pipeline.py

@@ -34,6 +34,7 @@
 END_DATE_METADATA_FIELD = "end_date"
 TRIPLE_STORE_ENDPOINT = "notices"
 TED_NOTICES_LINK = 'https://ted.europa.eu/udl?uri=TED:NOTICE:{notice_id}:TEXT:EN:HTML'
+TRIPLE_STORE_ENDPOINT_FIELD = "triple_store_endpoint"
 
 PROCEDURE_TYPE_COLUMN_NAME = "procedure_type"
 WINNER_NUTS_COLUMN_NAME = "winner_nuts"
@@ -204,6 +205,7 @@ def extract(self) -> Dict:
         """
         etl_metadata = self.get_metadata()
         etl_metadata_fields = etl_metadata.keys()
+        triple_store_endpoint = etl_metadata[TRIPLE_STORE_ENDPOINT_FIELD] if TRIPLE_STORE_ENDPOINT_FIELD in etl_metadata_fields else TRIPLE_STORE_ENDPOINT
         if START_DATE_METADATA_FIELD in etl_metadata_fields and END_DATE_METADATA_FIELD in etl_metadata_fields:
             if START_DATE_METADATA_FIELD == END_DATE_METADATA_FIELD:
                 date_range = datetime.strptime(START_DATE_METADATA_FIELD, "\"%Y%m%d\"")
@@ -218,7 +220,7 @@ def extract(self) -> Dict:
 
         sparql_query_template = Template(config.BQ_PATHS[SPARQL_QUERY_NAME].read_text(encoding='utf-8'))
         sparql_query_str = sparql_query_template.substitute(date_range=date_range)
-        triple_store_endpoint = GraphDBAdapter().get_sparql_triple_store_endpoint(repository_name=TRIPLE_STORE_ENDPOINT)
+        triple_store_endpoint = GraphDBAdapter().get_sparql_triple_store_endpoint(repository_name=triple_store_endpoint)
         result_table = triple_store_endpoint.with_query(sparql_query_str).fetch_tabular()
         return {"data": result_table}
 

tests/e2e/test_ted_etl.py

@@ -7,7 +7,7 @@
     CONTRACT_VALUE_AVAILABLE_INDICATOR, PROCEDURE_TYPE_INDICATOR, PRODUCT_CODES_AVAILABLE_INDICATOR, LOT_NUTS_0, \
     LOT_NUTS_1, LOT_NUTS_2, LOT_NUTS_3, get_country_name_by_code, BUYER_NUTS_COLUMN_NAME, PROCEDURE_ID_COLUMN_NAME, \
     PROCEDURE_DESCRIPTION_COLUMN_NAME, PROCEDURE_COLUMN_NAME, TDA_FREE_INDEX_NAME, TDA_STARTER_INDEX_NAME, CPV_RANK_4, \
-    CPV_RANK_2, CPV_RANK_1, CPV_RANK_3, LOT_COUNTRY
+    CPV_RANK_2, CPV_RANK_1, CPV_RANK_3, LOT_COUNTRY, TRIPLE_STORE_ENDPOINT_FIELD
 
 
 def test_get_country_name_by_code(real_country_code_alpha_2, fake_country_code_alpha_2, real_country_code_alpha_3,
@@ -20,6 +20,7 @@ def test_get_country_name_by_code(real_country_code_alpha_2, fake_country_code_a
 
 def test_etl_pipeline(ted_data_etl_pipelines, etl_pipeline_config, graphdb_triple_store, example_notices,
                       tmp_repository_name):
+    etl_pipeline_config[TRIPLE_STORE_ENDPOINT_FIELD] = tmp_repository_name
     for ted_data_etl_pipeline in ted_data_etl_pipelines:
         graphdb_repositories = graphdb_triple_store.list_repositories()
         if tmp_repository_name in graphdb_repositories:

tests/unit/test_nuts_generation.py

@@ -53,4 +53,6 @@ def test_cellar_nuts_processor(real_nuts, fake_nuts, cellar_nuts_processor):
     assert cellar_nuts_processor.get_nuts_level_by_code(nuts_code='FRK') == 1
     assert cellar_nuts_processor.get_nuts_level_by_code(nuts_code='FR') == 0
     assert cellar_nuts_processor.get_nuts_level_by_code(nuts_code='F') is None
-    assert cellar_nuts_processor.get_nuts_level_by_code(nuts_code=None) is None
+    assert cellar_nuts_processor.get_nuts_level_by_code(nuts_code=None) is None
+
+    assert cellar_nuts_processor.get_nuts_label_by_code(nuts_code='BE32') == 'Prov. Hainaut'