fix: Resolving syntax error while querying a feature view with column…

… name starting with a number and BigQuery as data source (feast-dev#4908) * Fixing issue feast-dev#4688 Signed-off-by: Dharmisha Doshi <[email protected]> * Fixing issue feast-dev#4688 Signed-off-by: Dharmisha Doshi <[email protected]> * Fixing issue feast-dev#4688 Signed-off-by: Dharmisha Doshi <[email protected]> * resolving PEP 8 warnings Signed-off-by: Dharmisha Doshi <[email protected]> * resolving linting issues Signed-off-by: Dharmisha Doshi <[email protected]> --------- Signed-off-by: Dharmisha Doshi <[email protected]> Co-authored-by: n0g0791 <[email protected]> Co-authored-by: nishantgaurav-dev <[email protected]> Co-authored-by: [email protected] <[email protected]>
opendatahub-io · Jan 21, 2025 · 029d4ff · 029d4ff
1 parent a993b01
commit 029d4ff
Show file tree

Hide file tree

Showing 2 changed files with 17 additions and 4 deletions.
diff --git a/sdk/python/feast/infra/offline_stores/bigquery.py b/sdk/python/feast/infra/offline_stores/bigquery.py
@@ -901,7 +901,10 @@ def arrow_schema_to_bq_schema(arrow_schema: pyarrow.Schema) -> List[SchemaField]
             {{ featureview.created_timestamp_column ~ ' as created_timestamp,' if featureview.created_timestamp_column else '' }}
             {{ featureview.entity_selections | join(', ')}}{% if featureview.entity_selections %},{% else %}{% endif %}
             {% for feature in featureview.features %}
-                {{ feature }} as {% if full_feature_names %}{{ featureview.name }}__{{featureview.field_mapping.get(feature, feature)}}{% else %}{{ featureview.field_mapping.get(feature, feature) }}{% endif %}{% if loop.last %}{% else %}, {% endif %}
+                {{ feature | backticks }} as {% if full_feature_names %}
+                {{ featureview.name }}__{{featureview.field_mapping.get(feature, feature)}}{% else %}
+                {{ featureview.field_mapping.get(feature, feature) | backticks }}{% endif %}
+                {% if loop.last %}{% else %}, {% endif %}
             {% endfor %}
         FROM {{ featureview.table_subquery }}
         WHERE {{ featureview.timestamp_field }} <= '{{ featureview.max_event_timestamp }}'
@@ -995,14 +998,14 @@ def arrow_schema_to_bq_schema(arrow_schema: pyarrow.Schema) -> List[SchemaField]
  The entity_dataframe dataset being our source of truth here.
  */
 
-SELECT {{ final_output_feature_names | join(', ')}}
+SELECT {{ final_output_feature_names | backticks | join(', ')}}
 FROM entity_dataframe
 {% for featureview in featureviews %}
 LEFT JOIN (
     SELECT
         {{featureview.name}}__entity_row_unique_id
         {% for feature in featureview.features %}
-            ,{% if full_feature_names %}{{ featureview.name }}__{{featureview.field_mapping.get(feature, feature)}}{% else %}{{ featureview.field_mapping.get(feature, feature) }}{% endif %}
+            ,{% if full_feature_names %}{{ featureview.name }}__{{featureview.field_mapping.get(feature, feature)}}{% else %}{{ featureview.field_mapping.get(feature, feature) | backticks }}{% endif %}
         {% endfor %}
     FROM {{ featureview.name }}__cleaned
 ) USING ({{featureview.name}}__entity_row_unique_id)

diff --git a/sdk/python/feast/infra/offline_stores/offline_utils.py b/sdk/python/feast/infra/offline_stores/offline_utils.py
@@ -186,7 +186,9 @@ def build_point_in_time_query(
     full_feature_names: bool = False,
 ) -> str:
     """Build point-in-time query between each feature view table and the entity dataframe for Bigquery and Redshift"""
-    template = Environment(loader=BaseLoader()).from_string(source=query_template)
+    env = Environment(loader=BaseLoader())
+    env.filters["backticks"] = enclose_in_backticks
+    template = env.from_string(source=query_template)
 
     final_output_feature_names = list(entity_df_columns)
     final_output_feature_names.extend(
@@ -252,3 +254,11 @@ def get_pyarrow_schema_from_batch_source(
         column_names.append(column_name)
 
     return pa.schema(pa_schema), column_names
+
+
+def enclose_in_backticks(value):
+    # Check if the input is a list
+    if isinstance(value, list):
+        return [f"`{v}`" for v in value]
+    else:
+        return f"`{value}`"