allow exluding datasets from taxonomy (#1345)

* allow exluding datasets from taxonomy

* add support for focus fields

Author: iakov-aws

cid/helpers/quicksight/__init__.py

@@ -1363,6 +1363,9 @@ def _build_params_for_create_update_dash(self, definition: dict) -> Dict:
             for dataset_reference in dataset_references:
                 dataset = self.describe_dataset(dataset_reference['DataSetArn'].split('/')[-1])
                 all_columns = dataset.raw['OutputColumns']
+                if dataset.name in definition.get('nonTaxonomyDatasets', []):
+                    logger.critical(f'Skipping {dataset.name}')
+                    continue
                 logger.debug(f'{dataset_references}: {all_columns}')
                 if common_columns is None:
                     common_columns = all_columns

cid/helpers/quicksight/dashboard_patching.py

@@ -33,10 +33,13 @@ def format_field_name(field_name: str, ignore_prefix: bool=False) -> str:
         assert format_field_name('tag_service') == 'Tag Service'
         assert format_field_name('ServiceCode') == 'Service Code'
     """
+    # Handle lowercase strings without underscores by inserting spaces at word boundaries (mainly for focus)
+    if field_name.islower() and '_' not in field_name:
+        field_name = re.sub(r'(account|period|discount|unit|price|category|name|id|cost|quantity)', r'_\1', field_name)
     # First, handle camelCase by inserting underscores before uppercase letters
     field_name = re.sub(r'([a-z])([A-Z])', r'\1_\2', field_name) # This converts "ServiceCode" to "Service_Code"
     field_name = field_name.lower()
-    parts = field_name.split('_')
+    parts = [part for part in field_name.split('_') if part]
     result = []
     i = 0
     while i < len(parts):