refactor: update _index_selected_files method signatures in Dropbox, Google Drive, and OneDrive indexers to include unsupported file count, enhancing error reporting and consistency across connectors

surfsense_backend/app/tasks/connector_indexers/dropbox_indexer.py

@@ -501,7 +501,7 @@ async def _index_selected_files(
     enable_summary: bool,
     incremental_sync: bool = True,
     on_heartbeat: HeartbeatCallbackType | None = None,
-) -> tuple[int, int, list[str]]:
+) -> tuple[int, int, int, list[str]]:
     """Index user-selected files using the parallel pipeline."""
     page_limit_service = PageLimitService(session)
     pages_used, pages_limit = await page_limit_service.get_page_usage(user_id)

surfsense_backend/app/tasks/connector_indexers/google_drive_indexer.py

@@ -474,13 +474,13 @@ async def _index_selected_files(
     user_id: str,
     enable_summary: bool,
     on_heartbeat: HeartbeatCallbackType | None = None,
-) -> tuple[int, int, list[str]]:
+) -> tuple[int, int, int, list[str]]:
     """Index user-selected files using the parallel pipeline.
 
     Phase 1 (serial): fetch metadata + skip checks.
     Phase 2+3 (parallel): download, ETL, index via _download_and_index.
 
-    Returns (indexed_count, skipped_count, errors).
+    Returns (indexed_count, skipped_count, unsupported_count, errors).
     """
     page_limit_service = PageLimitService(session)
     pages_used, pages_limit = await page_limit_service.get_page_usage(user_id)

surfsense_backend/app/tasks/connector_indexers/onedrive_indexer.py

@@ -293,7 +293,7 @@ async def _index_selected_files(
     user_id: str,
     enable_summary: bool,
     on_heartbeat: HeartbeatCallbackType | None = None,
-) -> tuple[int, int, list[str]]:
+) -> tuple[int, int, int, list[str]]:
     """Index user-selected files using the parallel pipeline."""
     page_limit_service = PageLimitService(session)
     pages_used, pages_limit = await page_limit_service.get_page_usage(user_id)

surfsense_backend/tests/unit/connector_indexers/test_google_drive_parallel.py

@@ -366,7 +366,7 @@ async def test_full_scan_three_phase_counts(full_scan_mocks, monkeypatch):
     full_scan_mocks["download_mock"].return_value = (mock_docs, 0)
     full_scan_mocks["batch_mock"].return_value = ([], 2, 0)
 
-    indexed, skipped = await _run_full_scan(full_scan_mocks)
+    indexed, skipped, unsupported = await _run_full_scan(full_scan_mocks)
 
     assert indexed == 3  # 1 renamed + 2 from batch
     assert skipped == 1  # 1 unchanged
@@ -589,7 +589,7 @@ async def test_selected_files_single_file_indexed(selected_files_mocks):
     )
     selected_files_mocks["download_and_index_mock"].return_value = (1, 0)
 
-    indexed, skipped, errors = await _run_selected(
+    indexed, skipped, unsup, errors = await _run_selected(
         selected_files_mocks,
         [("f1", "report.pdf")],
     )
@@ -613,7 +613,7 @@ async def test_selected_files_fetch_failure_isolation(selected_files_mocks):
     )
     selected_files_mocks["download_and_index_mock"].return_value = (2, 0)
 
-    indexed, skipped, errors = await _run_selected(
+    indexed, skipped, unsup, errors = await _run_selected(
         selected_files_mocks,
         [("f1", "first.txt"), ("f2", "mid.txt"), ("f3", "third.txt")],
     )
@@ -647,7 +647,7 @@ async def test_selected_files_skip_rename_counting(selected_files_mocks):
 
     selected_files_mocks["download_and_index_mock"].return_value = (2, 0)
 
-    indexed, skipped, errors = await _run_selected(
+    indexed, skipped, unsup, errors = await _run_selected(
         selected_files_mocks,
         [
             ("s1", "unchanged.txt"),

surfsense_backend/tests/unit/connector_indexers/test_page_limits.py

@@ -198,7 +198,7 @@ async def test_gdrive_files_within_quota_are_downloaded(gdrive_selected_mocks):
         )
     m["download_and_index_mock"].return_value = (3, 0)
 
-    indexed, _skipped, errors = await _run_gdrive_selected(
+    indexed, _skipped, _unsup, errors = await _run_gdrive_selected(
         m, [("f1", "f1.xyz"), ("f2", "f2.xyz"), ("f3", "f3.xyz")]
     )
 
@@ -219,7 +219,7 @@ async def test_gdrive_files_exceeding_quota_rejected(gdrive_selected_mocks):
         None,
     )
 
-    indexed, _skipped, errors = await _run_gdrive_selected(m, [("big", "huge.pdf")])
+    indexed, _skipped, _unsup, errors = await _run_gdrive_selected(m, [("big", "huge.pdf")])
 
     assert indexed == 0
     assert len(errors) == 1
@@ -239,7 +239,7 @@ async def test_gdrive_quota_mix_partial_indexing(gdrive_selected_mocks):
         )
     m["download_and_index_mock"].return_value = (2, 0)
 
-    indexed, _skipped, errors = await _run_gdrive_selected(
+    indexed, _skipped, _unsup, errors = await _run_gdrive_selected(
         m, [("f1", "f1.xyz"), ("f2", "f2.xyz"), ("f3", "f3.xyz")]
     )
 
@@ -299,7 +299,7 @@ async def test_gdrive_zero_quota_rejects_all(gdrive_selected_mocks):
             None,
         )
 
-    indexed, _skipped, errors = await _run_gdrive_selected(
+    indexed, _skipped, _unsup, errors = await _run_gdrive_selected(
         m, [("f1", "f1.xyz"), ("f2", "f2.xyz")]
     )
 
@@ -552,7 +552,7 @@ async def test_onedrive_over_quota_rejected(onedrive_selected_mocks):
         None,
     )
 
-    indexed, _skipped, errors = await _run_onedrive_selected(m, [("big", "huge.pdf")])
+    indexed, _skipped, _unsup, errors = await _run_onedrive_selected(m, [("big", "huge.pdf")])
 
     assert indexed == 0
     assert len(errors) == 1
@@ -652,7 +652,7 @@ async def test_dropbox_over_quota_rejected(dropbox_selected_mocks):
         None,
     )
 
-    indexed, _skipped, errors = await _run_dropbox_selected(
+    indexed, _skipped, _unsup, errors = await _run_dropbox_selected(
         m, [("/huge.pdf", "huge.pdf")]
     )