Importer - updates for btr changes

Signed-off-by: Kial Jinnah <kialj876@gmail.com>
bcgov · Sep 26, 2024 · f24bfe9 · f24bfe9
1 parent a08842f
commit f24bfe9
Show file tree

Hide file tree

Showing 3 changed files with 32 additions and 22 deletions.
diff --git a/search-solr-importer/data_import_handler.py b/search-solr-importer/data_import_handler.py
@@ -97,6 +97,7 @@ def load_search_core():  # pylint: disable=too-many-statements,too-many-locals,t
                 current_app.logger.debug('---------- Collecting/Importing BTR Data ----------')
                 btr_fetch_count = 0
                 batch_limit = current_app.config.get('BTR_BATCH_LIMIT')
+                btr_data_descs = []
                 loop_count = 0
 
                 while loop_count < 100:  # NOTE: should never get to this condition
@@ -110,7 +111,10 @@ def load_search_core():  # pylint: disable=too-many-statements,too-many-locals,t
                         break
 
                     current_app.logger.debug('********** Mapping BTR data **********')
-                    prepped_btr_data = prep_data_btr(btr_data)
+                    if not btr_data_descs:
+                        # just need to do once
+                        btr_data_descs = [desc[0].lower() for desc in btr_data_cur.description]
+                    prepped_btr_data = prep_data_btr(btr_data, btr_data_descs)
                     current_app.logger.debug(f'{len(prepped_btr_data)} BTR records ready for import.')
 
                     current_app.logger.debug('********** Importing BTR entities **********')

diff --git a/search-solr-importer/src/search_solr_importer/utils/data_collection.py b/search-solr-importer/src/search_solr_importer/utils/data_collection.py
@@ -145,7 +145,7 @@ def collect_btr_data(limit: int = None, offset: int = None):
         limit_clause += f' OFFSET {offset}'
     if limit_clause:
         # NOTE: needed in order to make sure we get every record when doing batch loads
-        limit_clause = f'ORDER BY id {limit_clause}'
+        limit_clause = f'ORDER BY p.id {limit_clause}'
 
     current_app.logger.debug('Connecting to BTR GCP Postgres instance...')
     conn = psycopg2.connect(host=current_app.config.get('BTR_DB_HOST'),
@@ -155,5 +155,11 @@ def collect_btr_data(limit: int = None, offset: int = None):
                             password=current_app.config.get('BTR_DB_PASSWORD'))
     cur = conn.cursor()
     current_app.logger.debug('Collecting BTR data...')
-    cur.execute(f'SELECT payload FROM submission {limit_clause}')
+    cur.execute(f"""
+                SELECT s.business_identifier, p.person_json
+                FROM submission s
+                JOIN ownership o on s.id = o.submission_id
+                JOIN person p on p.id = o.person_id
+                {limit_clause}
+                """)
     return cur
diff --git a/search-solr-importer/src/search_solr_importer/utils/data_parsing.py b/search-solr-importer/src/search_solr_importer/utils/data_parsing.py
@@ -187,33 +187,33 @@ def prep_data(data: list, data_descs: list[str], source: str) -> list[dict]:  #
     return solr_docs
 
 
-def prep_data_btr(data: list[dict]) -> list[dict]:
+def prep_data_btr(data: list[dict], data_descs: list[str]) -> list[dict]:
     """Return the list of partial business docs containing the SI party information."""
     prepped_data: list[dict] = []
 
     for item in data:
-        submission = item[0]
-        identifier = submission['businessIdentifier']
+        item_dict = dict(zip(data_descs, item))
+        identifier = item_dict['business_identifier']
 
         business = {'id': identifier, 'parties': {'add': []}}
 
         # collect current SIs.
-        for person in submission.get('personStatements', []):
-            party_name = ''
-            for name in person.get('names'):
-                if name.get('type') == 'individual':  # expecting this to be 'individual' or 'alternative'
-                    party_name = name.get('fullName')
-                    break
-            if not party_name:
-                current_app.logger.debug('Person names: %s', person.get('names'))
-                current_app.logger.error('Error parsing SI name for %s', identifier)
-
-            business['parties']['add'].append({
-                PartyField.UNIQUE_KEY.value: identifier + '_' + person['uuid'],
-                PartyField.PARTY_NAME.value: party_name,
-                PartyField.PARTY_ROLE.value: ['significant individual'],
-                PartyField.PARENT_TYPE.value: 'person'
-            })
+        person = item_dict['person_json']
+        party_name = ''
+        for name in person.get('names'):
+            if name.get('type') == 'individual':  # expecting this to be 'individual' or 'alternative'
+                party_name = name.get('fullName')
+                break
+        if not party_name:
+            current_app.logger.debug('Person names: %s', person.get('names'))
+            current_app.logger.error('Error parsing SI name for %s', identifier)
+
+        business['parties']['add'].append({
+            PartyField.UNIQUE_KEY.value: identifier + '_' + person['statementID'],
+            PartyField.PARTY_NAME.value: party_name,
+            PartyField.PARTY_ROLE.value: ['significant individual'],
+            PartyField.PARENT_TYPE.value: 'person'
+        })
 
         prepped_data.append(business)