add logging for company merge command

datahub/dbmaintenance/management/commands/company_merge_duns_number.py

@@ -1,8 +1,12 @@
+from logging import getLogger
+
 from datahub.company.merge_company import merge_companies
 from datahub.company.models import Company
 from datahub.dbmaintenance.management.base import CSVBaseCommand
 from datahub.dbmaintenance.utils import parse_uuid
 
+logger = getLogger(__name__)
+
 
 class Command(CSVBaseCommand):
     """
@@ -15,6 +19,16 @@ class Command(CSVBaseCommand):
     its related models, and find the company with Duns number and merge.
     """
 
+    additional_logging: dict
+
+    def __init__(self, *args, **kwargs):
+        super().__init__(*args, **kwargs)
+        self.additional_logging = {
+            'companies_with_subsidiaries': [],
+            'target_companies_archived': [],
+            'source_company_global_headquarters': [],
+        }
+
     def _process_row(self, row, simulate=False, **options):
         """Process one single row."""
         source_pk = parse_uuid(row['id'])
@@ -23,4 +37,28 @@ def _process_row(self, row, simulate=False, **options):
         source_company = Company.objects.get(pk=source_pk)
         target_company = Company.objects.get(duns_number=target_duns)
 
+        if source_company.subsidiaries.all().exists():
+            self.additional_logging['companies_with_subsidiaries'].append(str(source_company.id))
+        if target_company.archived:
+            self.additional_logging['target_companies_archived'].append(str(target_company.id))
+        if source_company.global_headquarters:
+            self.additional_logging['source_company_global_headquarters'].append(
+                str(source_company.id))
         merge_companies(source_company, target_company, None)
+
+    def handle(self, *args, **options):
+        """
+        Process the CSV file and logs some additional logging to help with companies merging
+        """
+        super().handle(*args, **options)
+        logger.info(
+            'List of Source Companies with Subsidiaries: '
+            f'{self.additional_logging["companies_with_subsidiaries"]}')
+        logger.info(
+            'List of Target Companies Archived: '
+            f'{self.additional_logging["target_companies_archived"]}')
+        logger.info(
+            'List of Source Compnies with Global Headqaurters: '
+            f'{self.additional_logging["source_company_global_headquarters"]}')
+
+        self.additional_logging.clear()

datahub/dbmaintenance/test/commands/test_company_merge_duns_number.py

@@ -5,7 +5,7 @@
 from django.core.management import call_command
 
 from datahub.company.test.factories import CompanyFactory
-
+from datahub.company.test.factories import SubsidiaryFactory
 pytestmark = pytest.mark.django_db
 
 
@@ -49,3 +49,94 @@ def test_merge_id_duns_number(s3_stubber):
     company_4.refresh_from_db()
     assert company_3.transferred_to == company_1
     assert company_4.transferred_to == company_2
+
+
+def test_logs_contain_errors(s3_stubber, caplog):
+    """Tests errors are captured in the logs"""
+    caplog.set_level('INFO')
+    global_company = CompanyFactory()
+    company_source = CompanyFactory(
+        global_headquarters=global_company,
+    )
+    company_with_duns = CompanyFactory(duns_number='12345678', archived=True)
+
+    bucket = 'test_bucket'
+    object_key = 'test_key'
+    csv_content = f"""id,duns
+{company_source.id},{company_with_duns.duns_number}
+"""
+
+    s3_stubber.add_response(
+        'get_object',
+        {
+            'Body': BytesIO(csv_content.encode(encoding='utf-8')),
+        },
+        expected_params={
+            'Bucket': bucket,
+            'Key': object_key,
+        },
+    )
+
+    call_command('company_merge_duns_number', bucket, object_key)
+
+    assert 'List of Target Companies Archived: ' in caplog.text
+    assert str(company_with_duns.id) in caplog.text
+    assert 'List of Source Compnies with Global Headqaurters: ' in caplog.text
+    assert str(company_source.id)
+
+
+def test_subsidiary_logs(s3_stubber, caplog):
+    """Tests subsidiary errors are captured in the logs"""
+    caplog.set_level('INFO')
+    company = CompanyFactory()
+    SubsidiaryFactory(global_headquarters=company)
+    company_with_duns = CompanyFactory(duns_number='12345678')
+    bucket = 'test_bucket'
+    object_key = 'test_key'
+    csv_content = f"""id,duns
+{company.id},{company_with_duns.duns_number}
+"""
+
+    s3_stubber.add_response(
+        'get_object',
+        {
+            'Body': BytesIO(csv_content.encode(encoding='utf-8')),
+        },
+        expected_params={
+            'Bucket': bucket,
+            'Key': object_key,
+        },
+    )
+
+    call_command('company_merge_duns_number', bucket, object_key)
+
+    assert 'List of Source Companies with Subsidiaries: ' in caplog.text
+    assert f'{str(company.id)}' in caplog.text
+
+
+def test_non_subsidiary_logs(s3_stubber, caplog):
+    """Tests subsidiary list in log is empty"""
+    caplog.set_level('INFO')
+    non_subsidiary_company = CompanyFactory()
+    company_with_duns = CompanyFactory(duns_number='12345678')
+
+    bucket = 'test_bucket'
+    object_key = 'test_key'
+    csv_content = f"""id,duns
+{non_subsidiary_company.id},{company_with_duns.duns_number}
+"""
+
+    s3_stubber.add_response(
+        'get_object',
+        {
+            'Body': BytesIO(csv_content.encode(encoding='utf-8')),
+        },
+        expected_params={
+            'Bucket': bucket,
+            'Key': object_key,
+        },
+    )
+
+    call_command('company_merge_duns_number', bucket, object_key)
+
+    assert 'List of Source Companies with Subsidiaries: []' in caplog.text