apache-airflow-providers-google 16.0.0a1__py3-none-any.whl → 16.1.0__py3-none-any.whl

airflow/providers/google/cloud/transfers/gdrive_to_local.py

@@ -19,8 +19,8 @@ from __future__ import annotations
 from collections.abc import Sequence
 from typing import TYPE_CHECKING
 
-from airflow.models import BaseOperator
 from airflow.providers.google.suite.hooks.drive import GoogleDriveHook
+from airflow.providers.google.version_compat import BaseOperator
 
 if TYPE_CHECKING:
     from airflow.utils.context import Context

airflow/providers/google/cloud/transfers/http_to_gcs.py

@@ -0,0 +1,193 @@
+#
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements.  See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership.  The ASF licenses this file
+# to you 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
+#
+#   http://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.
+"""This module contains operator to move data from HTTP endpoint to GCS."""
+
+from __future__ import annotations
+
+from functools import cached_property
+from typing import TYPE_CHECKING, Any
+
+from airflow.providers.google.cloud.hooks.gcs import GCSHook
+from airflow.providers.google.version_compat import BaseOperator
+from airflow.providers.http.hooks.http import HttpHook
+
+if TYPE_CHECKING:
+    from collections.abc import Sequence
+
+    from requests.auth import AuthBase
+
+    from airflow.utils.context import Context
+
+
+class HttpToGCSOperator(BaseOperator):
+    """
+    Calls an endpoint on an HTTP system to execute an action and store the result in GCS.
+
+    :param http_conn_id: The :ref:`http connection<howto/connection:http>` to run
+        the operator against
+    :param endpoint: The relative part of the full url. (templated)
+    :param method: The HTTP method to use, default = "POST"
+    :param data: The data to pass. POST-data in POST/PUT and params
+        in the URL for a GET request. (templated)
+    :param headers: The HTTP headers to be added to the GET request
+    :param response_check: A check against the 'requests' response object.
+        The callable takes the response object as the first positional argument
+        and optionally any number of keyword arguments available in the context dictionary.
+        It should return True for 'pass' and False otherwise.
+    :param response_filter: A function allowing you to manipulate the response
+        text. e.g response_filter=lambda response: json.loads(response.text).
+        The callable takes the response object as the first positional argument
+        and optionally any number of keyword arguments available in the context dictionary.
+    :param extra_options: Extra options for the 'requests' library, see the
+        'requests' documentation (options to modify timeout, ssl, etc.)
+    :param log_response: Log the response (default: False)
+    :param auth_type: The auth type for the service
+    :param tcp_keep_alive: Enable TCP Keep Alive for the connection.
+    :param tcp_keep_alive_idle: The TCP Keep Alive Idle parameter (corresponds to ``socket.TCP_KEEPIDLE``).
+    :param tcp_keep_alive_count: The TCP Keep Alive count parameter (corresponds to ``socket.TCP_KEEPCNT``)
+    :param tcp_keep_alive_interval: The TCP Keep Alive interval parameter (corresponds to
+        ``socket.TCP_KEEPINTVL``)
+    :param gcp_conn_id: The connection ID to use when fetching connection info.
+    :param impersonation_chain: Optional service account to impersonate using short-term credentials,
+        or chained list of accounts required to get the access_token of the last account in the list,
+        which will be impersonated in the request. If set as a string,
+        the account must grant the originating account the Service Account Token Creator IAM role.
+        If set as a sequence, the identities from the list must grant Service Account Token Creator IAM role to the directly preceding identity,
+        with first account from the list granting this role to the originating account.
+    :param bucket_name: The bucket to upload to.
+    :param object_name: The object name to set when uploading the file.
+    :param mime_type: The file mime type set when uploading the file.
+    :param gzip: Option to compress local file or file data for upload
+    :param encoding: bytes encoding for file data if provided as string
+    :param chunk_size: Blob chunk size.
+    :param timeout: Request timeout in seconds.
+    :param num_max_attempts: Number of attempts to try to upload the file.
+    :param metadata: The metadata to be uploaded with the file.
+    :param cache_contro: Cache-Control metadata field.
+    :param user_project: The identifier of the Google Cloud project to bill for the request. Required for Requester Pays buckets.
+    """
+
+    template_fields: Sequence[str] = (
+        "http_conn_id",
+        "endpoint",
+        "data",
+        "headers",
+        "gcp_conn_id",
+        "bucket_name",
+        "object_name",
+    )
+    template_fields_renderers = {"headers": "json", "data": "py"}
+    template_ext: Sequence[str] = ()
+    ui_color = "#f4a460"
+
+    def __init__(
+        self,
+        *,
+        endpoint: str | None = None,
+        method: str = "GET",
+        data: Any = None,
+        headers: dict[str, str] | None = None,
+        extra_options: dict[str, Any] | None = None,
+        http_conn_id: str = "http_default",
+        log_response: bool = False,
+        auth_type: type[AuthBase] | None = None,
+        tcp_keep_alive: bool = True,
+        tcp_keep_alive_idle: int = 120,
+        tcp_keep_alive_count: int = 20,
+        tcp_keep_alive_interval: int = 30,
+        gcp_conn_id: str = "google_cloud_default",
+        impersonation_chain: str | Sequence[str] | None = None,
+        bucket_name: str,
+        object_name: str,
+        mime_type: str | None = None,
+        gzip: bool = False,
+        encoding: str | None = None,
+        chunk_size: int | None = None,
+        timeout: int | None = None,
+        num_max_attempts: int = 3,
+        metadata: dict | None = None,
+        cache_control: str | None = None,
+        user_project: str | None = None,
+        **kwargs,
+    ):
+        super().__init__(**kwargs)
+        self.http_conn_id = http_conn_id
+        self.method = method
+        self.endpoint = endpoint
+        self.headers = headers or {}
+        self.data = data or {}
+        self.extra_options = extra_options or {}
+        self.log_response = log_response
+        self.auth_type = auth_type
+        self.tcp_keep_alive = tcp_keep_alive
+        self.tcp_keep_alive_idle = tcp_keep_alive_idle
+        self.tcp_keep_alive_count = tcp_keep_alive_count
+        self.tcp_keep_alive_interval = tcp_keep_alive_interval
+        self.gcp_conn_id = gcp_conn_id
+        self.impersonation_chain = impersonation_chain
+        self.bucket_name = bucket_name
+        self.object_name = object_name
+        self.mime_type = mime_type
+        self.gzip = gzip
+        self.encoding = encoding
+        self.chunk_size = chunk_size
+        self.timeout = timeout
+        self.num_max_attempts = num_max_attempts
+        self.metadata = metadata
+        self.cache_control = cache_control
+        self.user_project = user_project
+
+    @cached_property
+    def http_hook(self) -> HttpHook:
+        """Create and return an HttpHook."""
+        return HttpHook(
+            self.method,
+            http_conn_id=self.http_conn_id,
+            auth_type=self.auth_type,
+            tcp_keep_alive=self.tcp_keep_alive,
+            tcp_keep_alive_idle=self.tcp_keep_alive_idle,
+            tcp_keep_alive_count=self.tcp_keep_alive_count,
+            tcp_keep_alive_interval=self.tcp_keep_alive_interval,
+        )
+
+    @cached_property
+    def gcs_hook(self) -> GCSHook:
+        """Create and return an GCSHook."""
+        return GCSHook(gcp_conn_id=self.gcp_conn_id, impersonation_chain=self.impersonation_chain)
+
+    def execute(self, context: Context):
+        self.log.info("Calling HTTP method")
+        response = self.http_hook.run(
+            endpoint=self.endpoint, data=self.data, headers=self.headers, extra_options=self.extra_options
+        )
+
+        self.log.info("Uploading to GCS")
+        self.gcs_hook.upload(
+            data=response.content,
+            bucket_name=self.bucket_name,
+            object_name=self.object_name,
+            mime_type=self.mime_type,
+            gzip=self.gzip,
+            encoding=self.encoding or response.encoding,
+            chunk_size=self.chunk_size,
+            timeout=self.timeout,
+            num_max_attempts=self.num_max_attempts,
+            metadata=self.metadata,
+            cache_control=self.cache_control,
+            user_project=self.user_project,
+        )

airflow/providers/google/cloud/transfers/local_to_gcs.py

@@ -24,8 +24,8 @@ from collections.abc import Sequence
 from glob import glob
 from typing import TYPE_CHECKING
 
-from airflow.models import BaseOperator
 from airflow.providers.google.cloud.hooks.gcs import GCSHook
+from airflow.providers.google.version_compat import BaseOperator
 
 if TYPE_CHECKING:
     from airflow.utils.context import Context

airflow/providers/google/cloud/transfers/s3_to_gcs.py

@@ -181,21 +181,27 @@ class S3ToGCSOperator(S3ListOperator):
                 'The destination Google Cloud Storage path must end with a slash "/" or be empty.'
             )
 
-    def execute(self, context: Context):
-        self._check_inputs()
+    def _get_files(self, context: Context, gcs_hook: GCSHook) -> list[str]:
         # use the super method to list all the files in an S3 bucket/key
         s3_objects = super().execute(context)
 
+        if not self.replace:
+            s3_objects = self.exclude_existing_objects(s3_objects=s3_objects, gcs_hook=gcs_hook)
+
+        return s3_objects
+
+    def execute(self, context: Context):
+        self._check_inputs()
         gcs_hook = GCSHook(
             gcp_conn_id=self.gcp_conn_id,
             impersonation_chain=self.google_impersonation_chain,
         )
-        if not self.replace:
-            s3_objects = self.exclude_existing_objects(s3_objects=s3_objects, gcs_hook=gcs_hook)
-
         s3_hook = S3Hook(aws_conn_id=self.aws_conn_id, verify=self.verify)
+
+        s3_objects = self._get_files(context, gcs_hook)
         if not s3_objects:
             self.log.info("In sync, no files needed to be uploaded to Google Cloud Storage")
+
         elif self.deferrable:
             self.transfer_files_async(s3_objects, gcs_hook, s3_hook)
         else:

airflow/providers/google/cloud/transfers/salesforce_to_gcs.py

@@ -21,8 +21,8 @@ import tempfile
 from collections.abc import Sequence
 from typing import TYPE_CHECKING
 
-from airflow.models import BaseOperator
 from airflow.providers.google.cloud.hooks.gcs import GCSHook
+from airflow.providers.google.version_compat import BaseOperator
 from airflow.providers.salesforce.hooks.salesforce import SalesforceHook
 
 if TYPE_CHECKING:

airflow/providers/google/cloud/transfers/sftp_to_gcs.py

@@ -26,8 +26,8 @@ from tempfile import NamedTemporaryFile
 from typing import TYPE_CHECKING
 
 from airflow.exceptions import AirflowException
-from airflow.models import BaseOperator
 from airflow.providers.google.cloud.hooks.gcs import GCSHook
+from airflow.providers.google.version_compat import BaseOperator
 from airflow.providers.sftp.hooks.sftp import SFTPHook
 
 if TYPE_CHECKING:

airflow/providers/google/cloud/transfers/sheets_to_gcs.py

@@ -21,9 +21,9 @@ from collections.abc import Sequence
 from tempfile import NamedTemporaryFile
 from typing import TYPE_CHECKING, Any
 
-from airflow.models import BaseOperator
 from airflow.providers.google.cloud.hooks.gcs import GCSHook
 from airflow.providers.google.suite.hooks.sheets import GSheetsHook
+from airflow.providers.google.version_compat import BaseOperator
 
 if TYPE_CHECKING:
     from airflow.utils.context import Context
@@ -130,5 +130,5 @@ class GoogleSheetsToGCSOperator(BaseOperator):
             gcs_path_to_file = self._upload_data(gcs_hook, sheet_hook, sheet_range, data)
             destination_array.append(gcs_path_to_file)
 
-        self.xcom_push(context, "destination_objects", destination_array)
+        context["ti"].xcom_push(key="destination_objects", value=destination_array)
         return destination_array

airflow/providers/google/cloud/transfers/sql_to_gcs.py

@@ -30,8 +30,8 @@ from typing import TYPE_CHECKING, Any
 import pyarrow as pa
 import pyarrow.parquet as pq
 
-from airflow.models import BaseOperator
 from airflow.providers.google.cloud.hooks.gcs import GCSHook
+from airflow.providers.google.version_compat import BaseOperator
 
 if TYPE_CHECKING:
     from airflow.providers.common.compat.openlineage.facet import OutputDataset

airflow/providers/google/cloud/triggers/bigquery.py

@@ -22,10 +22,12 @@ from typing import TYPE_CHECKING, Any, SupportsAbs
 
 from aiohttp import ClientSession
 from aiohttp.client_exceptions import ClientResponseError
+from asgiref.sync import sync_to_async
 
 from airflow.exceptions import AirflowException
 from airflow.models.taskinstance import TaskInstance
 from airflow.providers.google.cloud.hooks.bigquery import BigQueryAsyncHook, BigQueryTableAsyncHook
+from airflow.providers.google.version_compat import AIRFLOW_V_3_0_PLUS
 from airflow.triggers.base import BaseTrigger, TriggerEvent
 from airflow.utils.session import provide_session
 from airflow.utils.state import TaskInstanceState
@@ -116,16 +118,41 @@ class BigQueryInsertJobTrigger(BaseTrigger):
             )
         return task_instance
 
-    def safe_to_cancel(self) -> bool:
+    async def get_task_state(self):
+        from airflow.sdk.execution_time.task_runner import RuntimeTaskInstance
+
+        task_states_response = await sync_to_async(RuntimeTaskInstance.get_task_states)(
+            dag_id=self.task_instance.dag_id,
+            task_ids=[self.task_instance.task_id],
+            run_ids=[self.task_instance.run_id],
+            map_index=self.task_instance.map_index,
+        )
+        try:
+            task_state = task_states_response[self.task_instance.run_id][self.task_instance.task_id]
+        except Exception:
+            raise AirflowException(
+                "TaskInstance with dag_id: %s, task_id: %s, run_id: %s and map_index: %s is not found",
+                self.task_instance.dag_id,
+                self.task_instance.task_id,
+                self.task_instance.run_id,
+                self.task_instance.map_index,
+            )
+        return task_state
+
+    async def safe_to_cancel(self) -> bool:
         """
         Whether it is safe to cancel the external job which is being executed by this trigger.
 
         This is to avoid the case that `asyncio.CancelledError` is called because the trigger itself is stopped.
         Because in those cases, we should NOT cancel the external job.
         """
-        # Database query is needed to get the latest state of the task instance.
-        task_instance = self.get_task_instance()  # type: ignore[call-arg]
-        return task_instance.state != TaskInstanceState.DEFERRED
+        if AIRFLOW_V_3_0_PLUS:
+            task_state = await self.get_task_state()
+        else:
+            # Database query is needed to get the latest state of the task instance.
+            task_instance = self.get_task_instance()  # type: ignore[call-arg]
+            task_state = task_instance.state
+        return task_state != TaskInstanceState.DEFERRED
 
     async def run(self) -> AsyncIterator[TriggerEvent]:  # type: ignore[override]
         """Get current job execution status and yields a TriggerEvent."""
@@ -155,7 +182,7 @@ class BigQueryInsertJobTrigger(BaseTrigger):
                     )
                     await asyncio.sleep(self.poll_interval)
         except asyncio.CancelledError:
-            if self.job_id and self.cancel_on_kill and self.safe_to_cancel():
+            if self.job_id and self.cancel_on_kill and await self.safe_to_cancel():
                 self.log.info(
                     "The job is safe to cancel the as airflow TaskInstance is not in deferred state."
                 )

airflow/providers/google/cloud/triggers/dataproc.py

@@ -25,6 +25,7 @@ import time
 from collections.abc import AsyncIterator, Sequence
 from typing import TYPE_CHECKING, Any
 
+from asgiref.sync import sync_to_async
 from google.api_core.exceptions import NotFound
 from google.cloud.dataproc_v1 import Batch, Cluster, ClusterStatus, JobStatus
 
@@ -33,6 +34,7 @@ from airflow.models.taskinstance import TaskInstance
 from airflow.providers.google.cloud.hooks.dataproc import DataprocAsyncHook, DataprocHook
 from airflow.providers.google.cloud.utils.dataproc import DataprocOperationType
 from airflow.providers.google.common.hooks.base_google import PROVIDE_PROJECT_ID
+from airflow.providers.google.version_compat import AIRFLOW_V_3_0_PLUS
 from airflow.triggers.base import BaseTrigger, TriggerEvent
 from airflow.utils.session import provide_session
 from airflow.utils.state import TaskInstanceState
@@ -141,16 +143,41 @@ class DataprocSubmitTrigger(DataprocBaseTrigger):
             )
         return task_instance
 
-    def safe_to_cancel(self) -> bool:
+    async def get_task_state(self):
+        from airflow.sdk.execution_time.task_runner import RuntimeTaskInstance
+
+        task_states_response = await sync_to_async(RuntimeTaskInstance.get_task_states)(
+            dag_id=self.task_instance.dag_id,
+            task_ids=[self.task_instance.task_id],
+            run_ids=[self.task_instance.run_id],
+            map_index=self.task_instance.map_index,
+        )
+        try:
+            task_state = task_states_response[self.task_instance.run_id][self.task_instance.task_id]
+        except Exception:
+            raise AirflowException(
+                "TaskInstance with dag_id: %s, task_id: %s, run_id: %s and map_index: %s is not found",
+                self.task_instance.dag_id,
+                self.task_instance.task_id,
+                self.task_instance.run_id,
+                self.task_instance.map_index,
+            )
+        return task_state
+
+    async def safe_to_cancel(self) -> bool:
         """
         Whether it is safe to cancel the external job which is being executed by this trigger.
 
         This is to avoid the case that `asyncio.CancelledError` is called because the trigger itself is stopped.
         Because in those cases, we should NOT cancel the external job.
         """
-        # Database query is needed to get the latest state of the task instance.
-        task_instance = self.get_task_instance()  # type: ignore[call-arg]
-        return task_instance.state != TaskInstanceState.DEFERRED
+        if AIRFLOW_V_3_0_PLUS:
+            task_state = await self.get_task_state()
+        else:
+            # Database query is needed to get the latest state of the task instance.
+            task_instance = self.get_task_instance()  # type: ignore[call-arg]
+            task_state = task_instance.state
+        return task_state != TaskInstanceState.DEFERRED
 
     async def run(self):
         try:
@@ -167,7 +194,7 @@ class DataprocSubmitTrigger(DataprocBaseTrigger):
         except asyncio.CancelledError:
             self.log.info("Task got cancelled.")
             try:
-                if self.job_id and self.cancel_on_kill and self.safe_to_cancel():
+                if self.job_id and self.cancel_on_kill and await self.safe_to_cancel():
                     self.log.info(
                         "Cancelling the job as it is safe to do so. Note that the airflow TaskInstance is not"
                         " in deferred state."
@@ -243,16 +270,41 @@ class DataprocClusterTrigger(DataprocBaseTrigger):
             )
         return task_instance
 
-    def safe_to_cancel(self) -> bool:
+    async def get_task_state(self):
+        from airflow.sdk.execution_time.task_runner import RuntimeTaskInstance
+
+        task_states_response = await sync_to_async(RuntimeTaskInstance.get_task_states)(
+            dag_id=self.task_instance.dag_id,
+            task_ids=[self.task_instance.task_id],
+            run_ids=[self.task_instance.run_id],
+            map_index=self.task_instance.map_index,
+        )
+        try:
+            task_state = task_states_response[self.task_instance.run_id][self.task_instance.task_id]
+        except Exception:
+            raise AirflowException(
+                "TaskInstance with dag_id: %s, task_id: %s, run_id: %s and map_index: %s is not found",
+                self.task_instance.dag_id,
+                self.task_instance.task_id,
+                self.task_instance.run_id,
+                self.task_instance.map_index,
+            )
+        return task_state
+
+    async def safe_to_cancel(self) -> bool:
         """
         Whether it is safe to cancel the external job which is being executed by this trigger.
 
         This is to avoid the case that `asyncio.CancelledError` is called because the trigger itself is stopped.
         Because in those cases, we should NOT cancel the external job.
         """
-        # Database query is needed to get the latest state of the task instance.
-        task_instance = self.get_task_instance()  # type: ignore[call-arg]
-        return task_instance.state != TaskInstanceState.DEFERRED
+        if AIRFLOW_V_3_0_PLUS:
+            task_state = await self.get_task_state()
+        else:
+            # Database query is needed to get the latest state of the task instance.
+            task_instance = self.get_task_instance()  # type: ignore[call-arg]
+            task_state = task_instance.state
+        return task_state != TaskInstanceState.DEFERRED
 
     async def run(self) -> AsyncIterator[TriggerEvent]:
         try:
@@ -283,7 +335,7 @@ class DataprocClusterTrigger(DataprocBaseTrigger):
                 await asyncio.sleep(self.polling_interval_seconds)
         except asyncio.CancelledError:
             try:
-                if self.delete_on_error and self.safe_to_cancel():
+                if self.delete_on_error and await self.safe_to_cancel():
                     self.log.info(
                         "Deleting the cluster as it is safe to delete as the airflow TaskInstance is not in "
                         "deferred state."

airflow/providers/google/cloud/utils/field_validator.py

@@ -134,8 +134,7 @@ Here are the guidelines that you should follow to make validation forward-compat
 from __future__ import annotations
 
 import re
-from collections.abc import Sequence
-from typing import Callable
+from collections.abc import Callable, Sequence
 
 from airflow.exceptions import AirflowException
 from airflow.utils.log.logging_mixin import LoggingMixin

airflow/providers/google/common/auth_backend/google_openid.py

@@ -20,8 +20,9 @@
 from __future__ import annotations
 
 import logging
+from collections.abc import Callable
 from functools import wraps
-from typing import Callable, TypeVar, cast
+from typing import TypeVar, cast
 
 import google
 import google.auth.transport.requests

airflow/providers/google/common/deprecated.py

@@ -18,8 +18,9 @@ from __future__ import annotations
 
 import inspect
 import re
+from collections.abc import Callable
 from datetime import date, datetime
-from typing import Any, Callable
+from typing import Any
 
 from deprecated import deprecated as standard_deprecated
 from deprecated.classic import ClassicAdapter

airflow/providers/google/common/hooks/base_google.py

@@ -26,10 +26,10 @@ import json
 import logging
 import os
 import tempfile
-from collections.abc import Generator, Sequence
+from collections.abc import Callable, Generator, Sequence
 from contextlib import ExitStack, contextmanager
 from subprocess import check_output
-from typing import TYPE_CHECKING, Any, Callable, TypeVar, cast
+from typing import TYPE_CHECKING, Any, TypeVar, cast
 
 import google.auth
 import google.oauth2.service_account
@@ -50,12 +50,16 @@ from requests import Session
 
 from airflow import version
 from airflow.exceptions import AirflowException
-from airflow.hooks.base import BaseHook
 from airflow.providers.google.cloud.utils.credentials_provider import (
     _get_scopes,
     _get_target_principal_and_delegates,
     get_credentials_and_project_id,
 )
+
+try:
+    from airflow.sdk import BaseHook
+except ImportError:
+    from airflow.hooks.base import BaseHook  # type: ignore[attr-defined,no-redef]
 from airflow.utils.process_utils import patch_environ
 
 if TYPE_CHECKING:

airflow/providers/google/common/links/storage.py

@@ -18,18 +18,12 @@
 
 from __future__ import annotations
 
-from typing import TYPE_CHECKING
-
 from airflow.providers.google.cloud.links.base import BaseGoogleLink
 
 BASE_LINK = "https://console.cloud.google.com"
 GCS_STORAGE_LINK = BASE_LINK + "/storage/browser/{uri};tab=objects?project={project_id}"
 GCS_FILE_DETAILS_LINK = BASE_LINK + "/storage/browser/_details/{uri};tab=live_object?project={project_id}"
 
-if TYPE_CHECKING:
-    from airflow.models import BaseOperator
-    from airflow.utils.context import Context
-
 
 class StorageLink(BaseGoogleLink):
     """Helper class for constructing GCS Storage link."""
@@ -38,14 +32,6 @@ class StorageLink(BaseGoogleLink):
     key = "storage_conf"
     format_str = GCS_STORAGE_LINK
 
-    @staticmethod
-    def persist(context: Context, task_instance, uri: str, project_id: str | None):
-        task_instance.xcom_push(
-            context=context,
-            key=StorageLink.key,
-            value={"uri": uri, "project_id": project_id},
-        )
-
 
 class FileDetailsLink(BaseGoogleLink):
     """Helper class for constructing GCS file details link."""
@@ -53,11 +39,3 @@ class FileDetailsLink(BaseGoogleLink):
     name = "GCS File Details"
     key = "file_details"
     format_str = GCS_FILE_DETAILS_LINK
-
-    @staticmethod
-    def persist(context: Context, task_instance: BaseOperator, uri: str, project_id: str | None):
-        task_instance.xcom_push(
-            context=context,
-            key=FileDetailsLink.key,
-            value={"uri": uri, "project_id": project_id},
-        )

airflow/providers/google/firebase/operators/firestore.py

@@ -20,9 +20,9 @@ from collections.abc import Sequence
 from typing import TYPE_CHECKING
 
 from airflow.exceptions import AirflowException
-from airflow.models import BaseOperator
 from airflow.providers.google.common.hooks.base_google import PROVIDE_PROJECT_ID
 from airflow.providers.google.firebase.hooks.firestore import CloudFirestoreHook
+from airflow.providers.google.version_compat import BaseOperator
 
 if TYPE_CHECKING:
     from airflow.utils.context import Context