google-drive-haystack 1.1.0__tar.gz → 2.0.0__tar.gz

{google_drive_haystack-1.1.0 → google_drive_haystack-2.0.0}/CHANGELOG.md

@@ -1,5 +1,12 @@
 # Changelog
 
+## [integrations/google_drive-v1.1.0] - 2026-06-25
+
+### 🚀 Features
+
+- *(google_drive)* Add Google Drive fetcher (#3488)
+
+
 ## [integrations/google_drive-v1.0.0] - 2026-06-23
 
 ### 🚀 Features

{google_drive_haystack-1.1.0 → google_drive_haystack-2.0.0}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.4
+Metadata-Version: 2.5
 Name: google-drive-haystack
-Version: 1.1.0
+Version: 2.0.0
 Summary: Haystack integration for google_drive
 Project-URL: Documentation, https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/google_drive#readme
 Project-URL: Issues, https://github.com/deepset-ai/haystack-core-integrations/issues
@@ -12,14 +12,14 @@ Keywords: drive,fetcher,google,haystack,retriever
 Classifier: Development Status :: 4 - Beta
 Classifier: License :: OSI Approved :: Apache Software License
 Classifier: Programming Language :: Python
-Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
 Classifier: Programming Language :: Python :: 3.14
+Classifier: Programming Language :: Python :: 3.15
 Classifier: Programming Language :: Python :: Implementation :: CPython
 Classifier: Programming Language :: Python :: Implementation :: PyPy
-Requires-Python: >=3.10
+Requires-Python: >=3.11
 Requires-Dist: haystack-ai>=2.17.0
 Requires-Dist: httpx>=0.28.0
 Requires-Dist: tenacity>=8.2.3
@@ -30,6 +30,7 @@ Description-Content-Type: text/markdown
 [![PyPI - Version](https://img.shields.io/pypi/v/google-drive-haystack.svg)](https://pypi.org/project/google-drive-haystack)
 [![PyPI - Python Version](https://img.shields.io/pypi/pyversions/google-drive-haystack.svg)](https://pypi.org/project/google-drive-haystack)
 
+- [Integration page](https://haystack.deepset.ai/integrations/google-drive)
 - [Changelog](https://github.com/deepset-ai/haystack-core-integrations/blob/main/integrations/google_drive/CHANGELOG.md)
 
 ---
@@ -37,3 +38,5 @@ Description-Content-Type: text/markdown
 ## Contributing
 
 Refer to the general [Contribution Guidelines](https://github.com/deepset-ai/haystack-core-integrations/blob/main/CONTRIBUTING.md).
+
+To run integration tests locally, you need to export the `GOOGLE_DRIVE_ACCESS_TOKEN` environment variable.

{google_drive_haystack-1.1.0 → google_drive_haystack-2.0.0}/README.md

@@ -3,6 +3,7 @@
 [![PyPI - Version](https://img.shields.io/pypi/v/google-drive-haystack.svg)](https://pypi.org/project/google-drive-haystack)
 [![PyPI - Python Version](https://img.shields.io/pypi/pyversions/google-drive-haystack.svg)](https://pypi.org/project/google-drive-haystack)
 
+- [Integration page](https://haystack.deepset.ai/integrations/google-drive)
 - [Changelog](https://github.com/deepset-ai/haystack-core-integrations/blob/main/integrations/google_drive/CHANGELOG.md)
 
 ---
@@ -10,3 +11,5 @@
 ## Contributing
 
 Refer to the general [Contribution Guidelines](https://github.com/deepset-ai/haystack-core-integrations/blob/main/CONTRIBUTING.md).
+
+To run integration tests locally, you need to export the `GOOGLE_DRIVE_ACCESS_TOKEN` environment variable.

{google_drive_haystack-1.1.0 → google_drive_haystack-2.0.0}/pyproject.toml

@@ -7,7 +7,7 @@ name = "google-drive-haystack"
 dynamic = ["version"]
 description = "Haystack integration for google_drive"
 readme = "README.md"
-requires-python = ">=3.10"
+requires-python = ">=3.11"
 license = "Apache-2.0"
 keywords = [
   "haystack",
@@ -21,11 +21,11 @@ classifiers = [
   "License :: OSI Approved :: Apache Software License",
   "Development Status :: 4 - Beta",
   "Programming Language :: Python",
-  "Programming Language :: Python :: 3.10",
   "Programming Language :: Python :: 3.11",
   "Programming Language :: Python :: 3.12",
   "Programming Language :: Python :: 3.13",
   "Programming Language :: Python :: 3.14",
+  "Programming Language :: Python :: 3.15",
   "Programming Language :: Python :: Implementation :: CPython",
   "Programming Language :: Python :: Implementation :: PyPy",
 ]
@@ -133,6 +133,7 @@ ignore = [
     "PLR0912",
     "PLR0913",
     "PLR0915",
+    "PLR0917",
     # Allow `Any` type - used legitimately for dynamic types and SDK boundaries
     "ANN401",
 ]

{google_drive_haystack-1.1.0 → google_drive_haystack-2.0.0}/src/haystack_integrations/common/google_drive/utils.py

@@ -2,6 +2,9 @@
 #
 # SPDX-License-Identifier: Apache-2.0
 
+import asyncio
+from typing import TypeVar
+
 import httpx
 from haystack import logging
 from haystack.utils import Secret
@@ -18,12 +21,31 @@ from .errors import GoogleDriveConfigError, GoogleDriveRequestError
 
 logger = logging.getLogger(__name__)
 
+T = TypeVar("T")
+
 DEFAULT_API_BASE_URL = "https://www.googleapis.com/drive/v3"
 _RETRYABLE_STATUS = frozenset({429, 500, 502, 503, 504})
 # Fallback backoff when a throttled response carries no `Retry-After` header: 1s, 2s, 4s, ...
 _EXPONENTIAL_BACKOFF = wait_exponential()
 
 
+async def _gather_tasks_with_cancel(tasks: list[asyncio.Task[T]]) -> list[T]:
+    """
+    Wait for all tasks, cancelling and draining unfinished siblings if one fails.
+
+    :param tasks: Tasks to wait for.
+    :returns:
+        The task results in input order.
+    """
+    try:
+        return await asyncio.gather(*tasks)
+    except BaseException:
+        for task in tasks:
+            task.cancel()
+        await asyncio.gather(*tasks, return_exceptions=True)
+        raise
+
+
 def resolve_access_token(access_token: str | Secret) -> str:
     """Return the bearer token string, resolving it if a `Secret` was passed."""
     if not isinstance(access_token, Secret):

{google_drive_haystack-1.1.0 → google_drive_haystack-2.0.0}/src/haystack_integrations/components/fetchers/google_drive/fetcher.py

@@ -14,6 +14,7 @@ from haystack.utils import Secret
 from haystack_integrations.common.google_drive.errors import GoogleDriveConfigError, GoogleDriveRequestError
 from haystack_integrations.common.google_drive.utils import (
     DEFAULT_API_BASE_URL,
+    _gather_tasks_with_cancel,
     build_async_retrying,
     build_retrying,
     resolve_access_token,
@@ -197,7 +198,8 @@ class GoogleDriveFetcher:
                 return await self._process_async(client, token, file_id, hints)
 
         async with httpx.AsyncClient(timeout=self.timeout, follow_redirects=True) as client:
-            results = await asyncio.gather(*(fetch_one(client, file_id, hints) for file_id, hints in resolved))
+            tasks = [asyncio.create_task(fetch_one(client, file_id, hints)) for file_id, hints in resolved]
+            results = await _gather_tasks_with_cancel(tasks)
 
         return {"streams": [stream for stream in results if stream is not None]}
 

{google_drive_haystack-1.1.0 → google_drive_haystack-2.0.0}/src/haystack_integrations/components/retrievers/google_drive/retriever.py

@@ -59,7 +59,7 @@ class GoogleDriveRetriever:
     file content is needed.
 
     The retriever takes a per-user `access_token` as a run input, typically wired from an upstream
-    `OAuthResolver`. The token must carry a delegated Google OAuth scope that allows search
+    `OAuthTokenResolver`. The token must carry a delegated Google OAuth scope that allows search
     (for example `https://www.googleapis.com/auth/drive.readonly`). The metadata-only
     `drive.metadata.readonly` scope cannot search file content or export documents.
 
@@ -67,15 +67,15 @@ class GoogleDriveRetriever:
     ```python
     from haystack import Pipeline
     from haystack.utils import Secret
-    from haystack_integrations.components.connectors.oauth import OAuthResolver
-    from haystack_integrations.utils.oauth import RefreshTokenSource
+    from haystack_integrations.components.connectors.oauth import OAuthTokenResolver
+    from haystack_integrations.utils.oauth import OAuthRefreshTokenSource
     from haystack_integrations.components.retrievers.google_drive import GoogleDriveRetriever
 
     pipeline = Pipeline()
     pipeline.add_component(
         "resolver",
-        OAuthResolver(
-            token_source=RefreshTokenSource(
+        OAuthTokenResolver(
+            token_source=OAuthRefreshTokenSource(
                 token_url="https://oauth2.googleapis.com/token",
                 client_id="aaa-bbb-ccc",
                 refresh_token=Secret.from_env_var("GOOGLE_REFRESH_TOKEN"),
@@ -150,7 +150,7 @@ class GoogleDriveRetriever:
         :param query: The search query string, matched against the full text of files via
             `fullText contains`.
         :param access_token: A delegated Google OAuth bearer token for the user whose Drive is searched,
-            typically wired from an upstream `OAuthResolver` (which emits a plain `str`). A `Secret` is also
+            typically wired from an upstream `OAuthTokenResolver` (which emits a plain `str`). A `Secret` is also
             accepted and resolved internally.
         :param top_k: Overrides the `top_k` configured at initialization for this run.
         :returns: A dictionary with a `documents` key holding the list of retrieved `Document` objects.
@@ -187,7 +187,7 @@ class GoogleDriveRetriever:
         :param query: The search query string, matched against the full text of files via
             `fullText contains`.
         :param access_token: A delegated Google OAuth bearer token for the user whose Drive is searched,
-            typically wired from an upstream `OAuthResolver` (which emits a plain `str`). A `Secret` is also
+            typically wired from an upstream `OAuthTokenResolver` (which emits a plain `str`). A `Secret` is also
             accepted and resolved internally.
         :param top_k: Overrides the `top_k` configured at initialization for this run.
         :returns: A dictionary with a `documents` key holding the list of retrieved `Document` objects.

{google_drive_haystack-1.1.0 → google_drive_haystack-2.0.0}/tests/test_fetcher.py

@@ -1,6 +1,7 @@
 # SPDX-FileCopyrightText: 2022-present deepset GmbH <info@deepset.ai>
 #
 # SPDX-License-Identifier: Apache-2.0
+import asyncio
 import os
 from unittest.mock import AsyncMock, patch
 
@@ -358,6 +359,50 @@ class TestPipeline:
 
 @pytest.mark.asyncio
 class TestRunAsync:
+    async def test_failure_cancels_and_drains_siblings(self):
+        fetcher = GoogleDriveFetcher(max_retries=0)
+        slow_started = asyncio.Event()
+        slow_cancelled = False
+        current_task = asyncio.current_task()
+        tasks_before = asyncio.all_tasks() - {current_task}
+
+        async def get(url, *_args, **_kwargs):
+            nonlocal slow_cancelled
+            if "SLOW" in url:
+                slow_started.set()
+                try:
+                    await asyncio.Event().wait()
+                except asyncio.CancelledError:
+                    slow_cancelled = True
+                    raise
+            await slow_started.wait()
+            msg = "failed"
+            raise httpx.ReadError(msg)
+
+        targets = [_drive_doc(file_id="SLOW"), _drive_doc(file_id="FAILING")]
+        with patch.object(httpx.AsyncClient, "get", AsyncMock(side_effect=get)):
+            with pytest.raises(httpx.ReadError):
+                await fetcher.run_async(access_token="tok", targets=targets)
+
+        assert slow_cancelled is True
+        assert asyncio.all_tasks() - {current_task} == tasks_before
+
+    async def test_raise_on_failure_false_skips_failed_files(self):
+        fetcher = GoogleDriveFetcher(max_retries=0, raise_on_failure=False)
+
+        async def get(url, *_args, **_kwargs):
+            if "MISSING" in url:
+                msg = "failed"
+                raise httpx.ReadError(msg)
+            return _binary(content=b"ok")
+
+        targets = [_drive_doc(file_id="MISSING"), _drive_doc(file_id="OK")]
+        with patch.object(httpx.AsyncClient, "get", AsyncMock(side_effect=get)):
+            streams = (await fetcher.run_async(access_token="tok", targets=targets))["streams"]
+
+        assert len(streams) == 1
+        assert streams[0].data == b"ok"
+
     async def test_downloads_binary(self):
         fetcher = GoogleDriveFetcher()
         get = AsyncMock(return_value=_binary(content=b"async-bytes"))