[youtube-data-api] feat: add support for filters in WHERE statement

Author: AndreyMarkinPPC

libs/community/google/youtube/youtube-data-api/garf_youtube_data_api/api_clients.py

@@ -13,10 +13,15 @@
 # limitations under the License.
 """Creates API client for YouTube Data API."""
 
+import datetime
+import functools
 import logging
+import operator
 import os
 import warnings
 
+import dateutil
+import pydantic
 from garf_core import api_clients, query_editor
 from googleapiclient.discovery import build
 from googleapiclient.errors import HttpError
@@ -92,6 +97,39 @@ def get_response(
       if data := result.get('items'):
         results.extend(data)
 
+    if filters := request.filters:
+      span.set_attribute('youtube_data_api.filters', filters)
+      filtered_results = []
+      comparators = []
+      for filter in filters:
+        field, op, value = filter.split(' ')
+        comparators.append(Comparator(field=field, operator=op, value=value))
+      with telemetry.tracer.start_as_current_span(
+        'youtube_data_api.apply_filters'
+      ):
+        for row in results:
+          include_row = True
+          for comparator in comparators:
+            key = comparator.field.split('.')
+            res = functools.reduce(operator.getitem, key, row)
+            if isinstance(comparator.value, datetime.date):
+              expr = f'res {comparator.operator} comp'
+              include_row = eval(
+                expr,
+                {
+                  'res': dateutil.parser.parse(res).date(),
+                  'comp': comparator.value,
+                },
+              )
+            else:
+              include_row = eval(
+                f'{res} {comparator.operator} {comparator.value}', globals()
+              )
+            if not include_row:
+              break
+          if include_row:
+            filtered_results.append(row)
+      return api_clients.GarfApiResponse(results=filtered_results)
     return api_clients.GarfApiResponse(results=results)
 
   def _list(
@@ -105,3 +143,15 @@ def _list(
       return service.list(part=part, **kwargs).execute()
     except HttpError:
       return {'items': None}
+
+
+class Comparator(pydantic.BaseModel):
+  field: str
+  operator: str
+  value: str | datetime.date
+
+  def model_post_init(self, __context) -> None:
+    if self.operator == '=':
+      self.operator = '=='
+    if self.field in ('snippet.publishedAt'):
+      self.value = dateutil.parser.parse(self.value).date()

libs/community/google/youtube/youtube-data-api/tests/unit/test_report_fetcher.py

@@ -0,0 +1,63 @@
+# Copyright 2025 Google LLC
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     https://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import garf_core
+import pytest
+from garf_youtube_data_api.report_fetcher import YouTubeDataApiReportFetcher
+
+
+class TestYouTubeDataApiReportFetcher:
+  @pytest.fixture
+  def fetcher(self):
+    return YouTubeDataApiReportFetcher()
+
+  def test_fetch(self, mocker, fetcher):
+    query = """
+      SELECT
+        id,
+        statistics.viewCount AS views,
+        statistics.likeCount AS likes,
+        snippet.publishedAt AS published_at,
+      FROM videos
+      WHERE
+        snippet.publishedAt > 2025-01-01
+        AND statistics.viewCount = 11
+        AND statistics.likeCount > 1
+    """
+
+    mocker.patch(
+      'garf_youtube_data_api.api_clients.YouTubeDataApiClient._list',
+      return_value={
+        'items': [
+          {
+            'id': 1,
+            'statistics': {'viewCount': 10, 'likeCount': 1},
+            'snippet': {'publishedAt': '2024-07-10T22:15:44Z'},
+          },
+          {
+            'id': 2,
+            'statistics': {'viewCount': 11, 'likeCount': 2},
+            'snippet': {'publishedAt': '2025-07-10T22:15:44Z'},
+          },
+        ],
+      },
+    )
+
+    result = fetcher.fetch(query, id=['1', '2'])
+    expected_report = garf_core.GarfReport(
+      results=[[2, 11, 2, '2025-07-10T22:15:44Z']],
+      column_names=['id', 'views', 'likes', 'published_at'],
+    )
+
+    assert result == expected_report