def generate_coverage_report()

in 5-app-infra/3-artifact-publish/docker/cdmc/tag_engine_api/TagEngineStoreHandler.py [0:0]

• 50 lines of code
• 10 McCabe index (conditional complexity)

    def generate_coverage_report(self, credentials):    
    
        summary_report = []
        detailed_report = []
        
        exists, settings = self.read_coverage_report_settings()
        included_bigquery_projects = settings['included_bigquery_projects']
        excluded_bigquery_datasets = settings['excluded_bigquery_datasets']
        excluded_bigquery_tables = settings['excluded_bigquery_tables']
        
        print('included_bigquery_projects: ' + included_bigquery_projects)
        print('excluded_bigquery_datasets: ' + excluded_bigquery_datasets)
        print('excluded_bigquery_tables: ' + excluded_bigquery_tables)
        
        log_ref = self.db.collection('logs')
        
        # list datasets and tables for chosen projects
        for project in included_bigquery_projects.split(','):
            project_id = project.strip()
            bq_client = bigquery.Client(project=project_id)
            datasets = list(bq_client.list_datasets())
            
            total_tags = 0
            
            for dataset in datasets:
                
                dataset_id = dataset.dataset_id

                if project_id + "." + dataset_id in excluded_bigquery_datasets:
                    #print('skipping ' + project_id + "." + dataset_id)
                    continue
               
                print("dataset: " + dataset_id)
                
                qualified_dataset = project_id + "." + dataset_id
                overall_sum = 0    
                table_list = []
                tables = list(bq_client.list_tables(dataset_id))
                
                dcc = controller.DataCatalogController(credentials)
                linked_resources = dcc.search_catalog(project_id, dataset_id)
                
                print('linked_resources: ' + str(linked_resources))
            
                for table in tables:
                    print("full_table_id: " + str(table.full_table_id))
                
                    table_path_full = table.full_table_id.replace(':', '/datasets/').replace('.', '/tables/')
                    table_path_short = table.full_table_id.replace(':', '.')
                    table_name = table_path_full.split('/')[4]
                
                    print('table_path_full: ' + table_path_full)
                    print('table_path_short: ' + table_path_short)
                    print('table_name: ' + table_name)
                
                    if table_path_short in project_id + '.' + excluded_bigquery_tables:
                        print('skipping ' + table_path_short)
                        continue
                    
                    if table_name in linked_resources:
                        tag_count = linked_resources[table_name]
                        overall_sum = overall_sum + tag_count
                        print("tag_count = " + str(tag_count))
                        print("overall_sum = " + str(overall_sum))
                
                        # add the table name and tag count to a list 
                        table_list.append((table_name, tag_count))

                # add record to summary report
                summary_record = (qualified_dataset, overall_sum)
                summary_report.append(summary_record)
                detailed_record = {qualified_dataset: table_list}
                detailed_report.append(detailed_record)
        
        return summary_report, detailed_report