gooddata-pipelines 1.49.1.dev1__tar.gz → 1.50.0__tar.gz

{gooddata_pipelines-1.49.1.dev1 → gooddata_pipelines-1.50.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: gooddata-pipelines
-Version: 1.49.1.dev1
+Version: 1.50.0
 Summary: GoodData Cloud lifecycle automation pipelines
 Author-email: GoodData <support@gooddata.com>
 License: MIT
@@ -8,7 +8,7 @@ License-File: LICENSE.txt
 Requires-Python: >=3.10
 Requires-Dist: boto3-stubs<2.0.0,>=1.39.3
 Requires-Dist: boto3<2.0.0,>=1.39.3
-Requires-Dist: gooddata-sdk~=1.49.1.dev1
+Requires-Dist: gooddata-sdk~=1.50.0
 Requires-Dist: pydantic<3.0.0,>=2.11.3
 Requires-Dist: requests<3.0.0,>=2.32.3
 Requires-Dist: types-pyyaml<7.0.0,>=6.0.12.20250326

{gooddata_pipelines-1.49.1.dev1 → gooddata_pipelines-1.50.0}/TODO.md

@@ -10,7 +10,7 @@ A list of outstanding tasks, features, or technical debt to be addressed in this
 
 - [ ] Integrate with GoodDataApiClient
 - [ ] Consider replacing the SdkMethods wrapper with direct calls to the SDK methods
-- [ ] Consider using orjson library instead of json
+- [ ] Consider using orjson library instead of json to load test data
 - [ ] Cleanup custom exceptions
 - [ ] Improve test coverage. Write missing unit tests for legacy code (e.g., user data filters)
 

{gooddata_pipelines-1.49.1.dev1 → gooddata_pipelines-1.50.0}/gooddata_pipelines/__init__.py

@@ -19,6 +19,7 @@ from .provisioning.entities.user_data_filters.user_data_filters import (
     UserDataFilterProvisioner,
 )
 from .provisioning.entities.users.models.permissions import (
+    EntityType,
     PermissionFullLoad,
     PermissionIncrementalLoad,
 )
@@ -33,7 +34,10 @@ from .provisioning.entities.users.models.users import (
 from .provisioning.entities.users.permissions import PermissionProvisioner
 from .provisioning.entities.users.user_groups import UserGroupProvisioner
 from .provisioning.entities.users.users import UserProvisioner
-from .provisioning.entities.workspaces.models import WorkspaceFullLoad
+from .provisioning.entities.workspaces.models import (
+    WorkspaceFullLoad,
+    WorkspaceIncrementalLoad,
+)
 from .provisioning.entities.workspaces.workspace import WorkspaceProvisioner
 
 __all__ = [
@@ -52,8 +56,10 @@ __all__ = [
     "UserGroupFullLoad",
     "UserProvisioner",
     "UserGroupProvisioner",
+    "WorkspaceIncrementalLoad",
     "PermissionProvisioner",
     "UserDataFilterProvisioner",
     "UserDataFilterFullLoad",
+    "EntityType",
     "__version__",
 ]

{gooddata_pipelines-1.49.1.dev1 → gooddata_pipelines-1.50.0}/gooddata_pipelines/api/gooddata_api.py

@@ -7,9 +7,6 @@ from typing import Any
 
 import requests
 
-# TODO: Limit the use of "typing.Any". Improve readability by using either models
-#  or typed dicts.
-
 TIMEOUT = 60
 REQUEST_PAGE_SIZE = 250
 API_VERSION = "v1"
@@ -55,42 +52,6 @@ class ApiMethods:
         """
         return f"{self.base_url}{endpoint}"
 
-    def get_custom_application_setting(
-        self, workspace_id: str, setting_id: str
-    ) -> requests.Response:
-        """Gets a custom application setting.
-
-        Args:
-            workspace_id (str): The ID of the workspace.
-            setting_id (str): The ID of the custom application setting.
-        Returns:
-            requests.Response: The response from the server containing the
-                custom application setting.
-        """
-        url = f"/entities/workspaces/{workspace_id}/customApplicationSettings/{setting_id}"
-        return self._get(url)
-
-    def put_custom_application_setting(
-        self, workspace_id: str, setting_id: str, data: dict[str, Any]
-    ) -> requests.Response:
-        url = f"/entities/workspaces/{workspace_id}/customApplicationSettings/{setting_id}"
-        return self._put(url, data, self.headers)
-
-    def post_custom_application_setting(
-        self, workspace_id: str, data: dict[str, Any]
-    ) -> requests.Response:
-        """Creates a custom application setting for a given workspace.
-
-        Args:
-            workspace_id (str): The ID of the workspace.
-            data (dict[str, Any]): The data for the custom application setting.
-        Returns:
-            requests.Response: The response from the server containing the
-                created custom application setting.
-        """
-        url = f"/entities/workspaces/{workspace_id}/customApplicationSettings/"
-        return self._post(url, data, self.headers)
-
     def get_all_workspace_data_filters(
         self, workspace_id: str
     ) -> requests.Response:
@@ -201,21 +162,6 @@ class ApiMethods:
             endpoint,
         )
 
-    def post_workspace_data_filter(
-        self, workspace_id: str, data: dict[str, Any]
-    ) -> requests.Response:
-        """Creates a workspace data filter for a given workspace.
-
-        Args:
-            workspace_id (str): The ID of the workspace.
-            data (dict[str, Any]): The data for the workspace data filter.
-        Returns:
-            requests.Response: The response from the server containing the
-                created workspace data filter.
-        """
-        endpoint = f"/entities/workspaces/{workspace_id}/workspaceDataFilters"
-        return self._post(endpoint, data, self.headers)
-
     def get_user_data_filters(self, workspace_id: str) -> requests.Response:
         """Gets the user data filters for a given workspace."""
         endpoint = f"/layout/workspaces/{workspace_id}/userDataFilters"

{gooddata_pipelines-1.49.1.dev1 → gooddata_pipelines-1.50.0}/gooddata_pipelines/backup_and_restore/backup_manager.py

@@ -55,7 +55,7 @@ class BackupManager:
 
         self.config = config
 
-        self.storage = self.get_storage(self.config)
+        self.storage = self._get_storage(self.config)
         self.org_id = self._api.get_organization_id()
 
         self.loader = BackupInputProcessor(self._api, self.config.api_page_size)
@@ -67,7 +67,7 @@ class BackupManager:
         host: str,
         token: str,
     ) -> "BackupManager":
-        """Creates a backup worker instance using provided host and token."""
+        """Creates a backup worker instance using the provided host and token."""
         return cls(host=host, token=token, config=config)
 
     @classmethod
@@ -81,7 +81,8 @@ class BackupManager:
         content = profile_content(profile, profiles_path)
         return cls(**content, config=config)
 
-    def get_storage(self, conf: BackupRestoreConfig) -> BackupStorage:
+    @staticmethod
+    def _get_storage(conf: BackupRestoreConfig) -> BackupStorage:
         """Returns the storage class based on the storage type."""
         if conf.storage_type == StorageType.S3:
             return S3Storage(conf)
@@ -100,7 +101,7 @@ class BackupManager:
         else:
             raise RuntimeError(f"{response.status_code}: {response.text}")
 
-    def store_user_data_filters(
+    def _store_user_data_filters(
         self,
         user_data_filters: dict,
         export_path: Path,
@@ -128,20 +129,20 @@ class BackupManager:
                 "user_data_filters",
                 filter["id"] + ".yaml",
             )
-            self.write_to_yaml(udf_file_path, filter)
+            self._write_to_yaml(udf_file_path, filter)
 
     @staticmethod
-    def move_folder(source: Path, destination: Path) -> None:
+    def _move_folder(source: Path, destination: Path) -> None:
         """Moves the source folder to the destination."""
         shutil.move(source, destination)
 
     @staticmethod
-    def write_to_yaml(path: str, source: Any) -> None:
+    def _write_to_yaml(path: str, source: Any) -> None:
         """Writes the source to a YAML file."""
         with open(path, "w") as outfile:
             yaml.dump(source, outfile)
 
-    def get_automations_from_api(self, workspace_id: str) -> Any:
+    def _get_automations_from_api(self, workspace_id: str) -> Any:
         """Returns automations for the workspace as JSON."""
         response: requests.Response = self._api.get_automations(workspace_id)
         if response.ok:
@@ -152,10 +153,10 @@ class BackupManager:
                 + f"{response.status_code}: {response.text}"
             )
 
-    def store_automations(self, export_path: Path, workspace_id: str) -> None:
+    def _store_automations(self, export_path: Path, workspace_id: str) -> None:
         """Stores the automations in the specified export path."""
         # Get the automations from the API
-        automations: Any = self.get_automations_from_api(workspace_id)
+        automations: Any = self._get_automations_from_api(workspace_id)
 
         automations_folder_path: Path = Path(
             export_path,
@@ -184,8 +185,8 @@ class BackupManager:
         # Get the filter views YAML files from the API
         self._api.store_declarative_filter_views(workspace_id, export_path)
 
-        # Move filter views to the subfolder containing analytics model
-        self.move_folder(
+        # Move filter views to the subfolder containing the analytics model
+        self._move_folder(
             Path(export_path, "gooddata_layouts", self.org_id, "filter_views"),
             Path(
                 export_path,
@@ -197,7 +198,7 @@ class BackupManager:
             ),
         )
 
-    def get_workspace_export(
+    def _get_workspace_export(
         self,
         local_target_path: str,
         workspaces_to_export: list[str],
@@ -232,9 +233,9 @@ class BackupManager:
                 # be more transparent/readable and possibly safer for threading
                 self._api.store_declarative_workspace(workspace_id, export_path)
                 self.store_declarative_filter_views(export_path, workspace_id)
-                self.store_automations(export_path, workspace_id)
+                self._store_automations(export_path, workspace_id)
 
-                self.store_user_data_filters(
+                self._store_user_data_filters(
                     user_data_filters, export_path, workspace_id
                 )
                 self.logger.info(f"Stored export for {workspace_id}")
@@ -250,7 +251,7 @@ class BackupManager:
                 + "is correct and that the workspaces exist."
             )
 
-    def archive_gooddata_layouts_to_zip(self, folder: str) -> None:
+    def _archive_gooddata_layouts_to_zip(self, folder: str) -> None:
         """Archives the gooddata_layouts directory to a zip file."""
         try:
             target_subdir = ""
@@ -271,11 +272,12 @@ class BackupManager:
             self.logger.error(f"Error archiving {folder} to zip: {e}")
             raise
 
-    def split_to_batches(
-        self, workspaces_to_export: list[str], batch_size: int
+    @staticmethod
+    def _split_to_batches(
+        workspaces_to_export: list[str], batch_size: int
     ) -> list[BackupBatch]:
-        """Splits the list of workspaces to into batches of the specified size.
-        The batch is respresented as a list of workspace IDs.
+        """Splits the list of workspaces into batches of the specified size.
+        The batch is represented as a list of workspace IDs.
         Returns a list of batches (i.e. list of lists of IDs)
         """
         list_of_batches = []
@@ -286,7 +288,7 @@ class BackupManager:
 
         return list_of_batches
 
-    def process_batch(
+    def _process_batch(
         self,
         batch: BackupBatch,
         stop_event: threading.Event,
@@ -298,14 +300,14 @@ class BackupManager:
         The base wait time is defined by BackupSettings.RETRY_DELAY.
         """
         if stop_event.is_set():
-            # If the stop_event flag is set, return. This will terminate the thread.
+            # If the stop_event flag is set, return. This will terminate the thread
             return
 
         try:
             with tempfile.TemporaryDirectory() as tmpdir:
-                self.get_workspace_export(tmpdir, batch.list_of_ids)
+                self._get_workspace_export(tmpdir, batch.list_of_ids)
 
-                self.archive_gooddata_layouts_to_zip(
+                self._archive_gooddata_layouts_to_zip(
                     str(Path(tmpdir, self.org_id))
                 )
 
@@ -316,7 +318,7 @@ class BackupManager:
                 return
 
             elif retry_count < BackupSettings.MAX_RETRIES:
-                # Retry with exponential backoff until MAX_RETRIES.
+                # Retry with exponential backoff until MAX_RETRIES
                 next_retry = retry_count + 1
                 wait_time = BackupSettings.RETRY_DELAY**next_retry
                 self.logger.info(
@@ -326,13 +328,13 @@ class BackupManager:
                 )
 
                 time.sleep(wait_time)
-                self.process_batch(batch, stop_event, next_retry)
+                self._process_batch(batch, stop_event, next_retry)
             else:
-                # If the batch fails after MAX_RETRIES, raise the error.
+                # If the batch fails after MAX_RETRIES, raise the error
                 self.logger.error(f"Batch failed: {e.__class__.__name__}: {e}")
                 raise
 
-    def process_batches_in_parallel(
+    def _process_batches_in_parallel(
         self,
         batches: list[BackupBatch],
     ) -> None:
@@ -345,14 +347,14 @@ class BackupManager:
         stop_event = threading.Event()
 
         with ThreadPoolExecutor(
-            max_workers=BackupSettings.MAX_WORKERS
+            max_workers=self.config.max_workers
         ) as executor:
             # Set the futures tasks.
             futures = []
             for batch in batches:
                 futures.append(
                     executor.submit(
-                        self.process_batch,
+                        self._process_batch,
                         batch,
                         stop_event,
                     )
@@ -363,10 +365,10 @@ class BackupManager:
                 try:
                     future.result()
                 except Exception:
-                    # On failure, set the flag to True - signal running processes to stop.
+                    # On failure, set the flag to True - signal running processes to stop
                     stop_event.set()
 
-                    # Cancel unstarted threads.
+                    # Cancel unstarted threads
                     for f in futures:
                         if not f.done():
                             f.cancel()
@@ -374,7 +376,9 @@ class BackupManager:
                     raise
 
     def backup_workspaces(
-        self, path_to_csv: str | None, workspace_ids: list[str] | None
+        self,
+        path_to_csv: str | None = None,
+        workspace_ids: list[str] | None = None,
     ) -> None:
         """Runs the backup process for a list of workspace IDs.
 
@@ -383,27 +387,29 @@ class BackupManager:
         workspace in storage specified in the configuration.
 
         Args:
-            path_to_csv (str): Path to a CSV file containing a list of workspace IDs.
+            path_to_csv (str): Path to a CSV file containing a list of workspace IDs
             workspace_ids (list[str]): List of workspace IDs
         """
-        self.backup(InputType.LIST_OF_WORKSPACES, path_to_csv, workspace_ids)
+        self._backup(InputType.LIST_OF_WORKSPACES, path_to_csv, workspace_ids)
 
     def backup_hierarchies(
-        self, path_to_csv: str | None, workspace_ids: list[str] | None
+        self,
+        path_to_csv: str | None = None,
+        workspace_ids: list[str] | None = None,
     ) -> None:
         """Runs the backup process for a list of hierarchies.
 
         Will take the list of workspace IDs or read the list of workspace IDs
-        from a CSV file and create backup for each those workspaces' hierarchies
+        from a CSV file and create backup for each of those workspaces' hierarchies
         in storage specified in the configuration.
         Workspace hierarchy means the workspace itself and all its direct and
         indirect children.
 
         Args:
-            path_to_csv (str): Path to a CSV file containing a list of workspace IDs.
+            path_to_csv (str): Path to a CSV file containing a list of workspace IDs
             workspace_ids (list[str]): List of workspace IDs
         """
-        self.backup(InputType.HIERARCHY, path_to_csv, workspace_ids)
+        self._backup(InputType.HIERARCHY, path_to_csv, workspace_ids)
 
     def backup_entire_organization(self) -> None:
         """Runs the backup process for the entire organization.
@@ -411,22 +417,22 @@ class BackupManager:
         Will create backup for all workspaces in the organization in storage
         specified in the configuration.
         """
-        self.backup(InputType.ORGANIZATION)
+        self._backup(InputType.ORGANIZATION)
 
-    def backup(
+    def _backup(
         self,
         input_type: InputType,
         path_to_csv: str | None = None,
         workspace_ids: list[str] | None = None,
     ) -> None:
-        """Runs the backup process with selected input type."""
+        """Runs the backup process with the selected input type."""
         try:
             workspaces_to_export: list[str] = self.loader.get_ids_to_backup(
                 input_type,
                 path_to_csv,
                 workspace_ids,
             )
-            batches = self.split_to_batches(
+            batches = self._split_to_batches(
                 workspaces_to_export, self.config.batch_size
             )
 
@@ -434,7 +440,7 @@ class BackupManager:
                 f"Exporting {len(workspaces_to_export)} workspaces in {len(batches)} batches."
             )
 
-            self.process_batches_in_parallel(batches)
+            self._process_batches_in_parallel(batches)
 
             self.logger.info("Backup completed")
         except Exception as e:

{gooddata_pipelines-1.49.1.dev1 → gooddata_pipelines-1.50.0}/gooddata_pipelines/backup_and_restore/constants.py

@@ -1,3 +1,4 @@
+# (C) 2025 GoodData Corporation
 import datetime
 from dataclasses import dataclass
 
@@ -22,7 +23,7 @@ class DirNames:
 
 @dataclass(frozen=True)
 class ConcurrencyDefaults:
-    MAX_WORKERS = 2
+    MAX_WORKERS = 1
     DEFAULT_BATCH_SIZE = 100
 
 

{gooddata_pipelines-1.49.1.dev1 → gooddata_pipelines-1.50.0}/gooddata_pipelines/backup_and_restore/models/storage.py

@@ -21,10 +21,40 @@ class S3StorageConfig(BaseModel):
 
     backup_path: str
     bucket: str
-    profile: str = "default"
+    profile: Optional[str] = None
     aws_access_key_id: Optional[str] = None
     aws_secret_access_key: Optional[str] = None
-    aws_default_region: Optional[str] = None
+    aws_default_region: Optional[str] = "us-east-1"
+
+    @classmethod
+    def from_iam_role(cls, backup_path: str, bucket: str) -> "S3StorageConfig":
+        """Use default IAM role or environment credentials."""
+        return cls(backup_path=backup_path, bucket=bucket)
+
+    @classmethod
+    def from_aws_credentials(
+        cls,
+        backup_path: str,
+        bucket: str,
+        aws_access_key_id: str,
+        aws_secret_access_key: str,
+        aws_default_region: str,
+    ) -> "S3StorageConfig":
+        """Use explicit AWS access keys and region."""
+        return cls(
+            backup_path=backup_path,
+            bucket=bucket,
+            aws_access_key_id=aws_access_key_id,
+            aws_secret_access_key=aws_secret_access_key,
+            aws_default_region=aws_default_region,
+        )
+
+    @classmethod
+    def from_aws_profile(
+        cls, backup_path: str, bucket: str, profile: str
+    ) -> "S3StorageConfig":
+        """Use a named AWS CLI profile."""
+        return cls(backup_path=backup_path, bucket=bucket, profile=profile)
 
 
 class LocalStorageConfig(BaseModel):
@@ -53,6 +83,14 @@ class BackupRestoreConfig(BaseModel):
             description="Batch size must be greater than 0",
         ),
     ] = Field(default=BackupSettings.DEFAULT_BATCH_SIZE)
+    max_workers: Annotated[
+        int,
+        Field(
+            gt=0,
+            lt=3,
+            description="Max workers must be greater than 0 and less than 3",
+        ),
+    ] = Field(default=BackupSettings.MAX_WORKERS)
 
     @classmethod
     def from_yaml(cls, conf_path: str) -> "BackupRestoreConfig":

{gooddata_pipelines-1.49.1.dev1 → gooddata_pipelines-1.50.0}/gooddata_pipelines/backup_and_restore/storage/s3_storage.py

@@ -22,6 +22,7 @@ class S3Storage(BackupStorage):
 
         self._config = conf.storage
         self._session = self._create_boto_session(self._config)
+        self._client = self._session.client("s3")
         self._resource = self._session.resource("s3")
         self._bucket = self._resource.Bucket(self._config.bucket)  # type: ignore [missing library stubs]
         suffix = "/" if not self._config.backup_path.endswith("/") else ""
@@ -43,32 +44,40 @@ class S3Storage(BackupStorage):
                 )
             except Exception:
                 self.logger.warning(
-                    "Failed to create boto3 session with supplied credentials. Falling back to profile..."
+                    "Failed to create boto3 session with supplied credentials."
+                )
+
+        if config.profile:
+            try:
+                return boto3.Session(profile_name=config.profile)
+            except Exception:
+                self.logger.warning(
+                    f"AWS profile [{config.profile}] not found."
                 )
 
         try:
-            return boto3.Session(profile_name=config.profile)
+            return boto3.Session()
         except Exception:
-            self.logger.warning(
-                'AWS profile "[default]" not found. Trying other fallback methods...'
+            self.logger.error(
+                "Failed to create boto3 session with default IAM role or environment credentials."
+            )
+            raise RuntimeError(
+                "Unable to create AWS session. Please check your AWS credentials, profile, or IAM role configuration."
             )
-
-        return boto3.Session()
 
     def _verify_connection(self) -> None:
         """
         Pings the S3 bucket to verify that the connection is working.
         """
         try:
-            # TODO: install boto3 s3 stubs
-            self._resource.meta.client.head_bucket(Bucket=self._config.bucket)
+            self._client.head_bucket(Bucket=self._config.bucket)
         except Exception as e:
             raise RuntimeError(
                 f"Failed to connect to S3 bucket {self._config.bucket}: {e}"
             )
 
     def export(self, folder: str, org_id: str) -> None:
-        """Uploads the content of the folder to S3 as backup."""
+        """Uploads the content of the folder to S3 as a backup."""
         storage_path = f"{self._config.bucket}/{self._backup_path}"
         self.logger.info(f"Uploading {org_id} to {storage_path}")
         folder = f"{folder}/{org_id}"
@@ -77,10 +86,12 @@ class S3Storage(BackupStorage):
             export_path = (
                 f"{self._backup_path}{org_id}/{full_path[len(folder) + 1 :]}/"
             )
-            self._bucket.put_object(Key=export_path)
+            self._client.put_object(Bucket=self._config.bucket, Key=export_path)
 
             for file in files:
                 full_path = os.path.join(subdir, file)
                 with open(full_path, "rb") as data:
                     export_path = f"{self._backup_path}{org_id}/{full_path[len(folder) + 1 :]}"
-                    self._bucket.put_object(Key=export_path, Body=data)
+                    self._client.put_object(
+                        Bucket=self._config.bucket, Key=export_path, Body=data
+                    )