feat: add gooddata-pipelines package

Author: janmatzek

.gitignore

@@ -1,4 +1,5 @@
 .idea
+.vscode
 *.iml
 .env
 .env.test

gooddata-pipelines/.gitignore

@@ -0,0 +1,5 @@
+**venv/*
+**/__pycache__/*
+**.env
+**.log
+dist/**

gooddata-pipelines/LICENSE.txt

@@ -0,0 +1,69 @@
+# GoodData Pipelines
+
+The `gooddata-pipelines` package provides a number of high level scripts to interact with and manage [GoodData](https://www.gooddata.com/).
+
+At the moment, the package allows you to automate these features:
+
+- Provisioning (creation, updtating and removal of resources) of
+  - workspaces
+  - users
+  - user groups
+  - user permissions
+  - user data filters
+  <!-- TODO: Backups, restores -->
+
+<!-- TODO: link to documentation -->
+<!-- See [DOCUMENTATION](https://www.gooddata.com/docs/python-sdk/1.43.0) for more details. -->
+
+## Requirements
+
+- GoodData Cloud or GoodData.CN installation
+- Python 3.10 or newer
+
+## Installation
+
+Run the following command to install the `gooddata-pipelines` package on your system:
+
+    pip install gooddata-pipelines
+
+## Example
+
+This example illustrates how to use this package to manage GoodData Cloud workspaces. The provisioning script will ingest data which will be used as a source of truth to configure GoodData. The script will compare the source data with the current state of GoodData instance and will create, update and delete workspaces and user data filter settings to match the source data.
+
+```python
+
+# Import WorkspaceProvisioner and Workspace model.
+from gooddata_pipelines import Workspace, WorkspaceProvisioner
+
+# Gather the raw data to be used by the provisioner.
+raw_data: list[dict] = [
+    {
+        "parent_id": "parent_workspace_id",
+        "workspace_id": "workspace_id",
+        "workspace_name": "Workspace Name",
+        "workspace_data_filter_id": "wdf_id",
+        "workspace_data_filter_values": ["value1", "value2"],
+    }
+]
+
+# Convert raw data to Workspace objects.
+data = [Workspace(**item) for item in raw_data]
+
+# Create a WorkspaceProvisioner using your GoodData host name and token.
+host = "https://your-gooddata-host.com"
+token = "your_gooddata_token"
+provisioner = WorkspaceProvisioner.create(host=host, token=token)
+
+# Provision the workspaces
+provisioner.provision(data)
+```
+
+## Bugs & Requests
+
+Please use the [GitHub issue tracker](https://github.com/gooddata/gooddata-python-sdk/issues) to submit bugs
+or request features.
+
+## Changelog
+
+See [Github releases](https://github.com/gooddata/gooddata-python-sdk/releases) for released versions
+and a list of changes.

gooddata-pipelines/README.md

@@ -0,0 +1,29 @@
+# TODO
+
+A list of outstanding tasks, features, or technical debt to be addressed in this project.
+
+## Pre-release
+
+- [ ] License file
+
+## Features
+
+- [ ] Workspace backup
+- [ ] Workspace restore
+- [ ] Handle input from csv files [?]
+
+## Refactoring / Debt
+
+- [ ] Cleanup custom exception
+- [ ] Use objects to make `workspace_data_parses.py` more transparent
+- [ ] Use objects in API integration. Consider using existing Python SDK objects where possible, otherwise create pydantic models to use instead of `dict[str, Any]` stand-ins for json values
+- [ ] Improve test coverage. Write missing unit tests for legacy code (e.g., user data filters)
+
+## Documentation
+
+- [ ] Improve package README
+- [ ] Workspace provisioning
+- [ ] User provisioning
+- [ ] User group provisioning
+- [ ] Permission provisioning
+- [ ] User data filter provisioning

gooddata-pipelines/TODO.md

@@ -0,0 +1,29 @@
+# (C) 2025 GoodData Corporation
+
+from ._version import __version__
+from .provisioning.entities.user_data_filters.models.udf_models import (
+    UserDataFilter,
+)
+from .provisioning.entities.user_data_filters.user_data_filters import (
+    UserDataFilterProvisioner,
+)
+from .provisioning.entities.users.models import Permission, User, UserGroup
+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 Workspace
+from .provisioning.entities.workspaces.workspace import WorkspaceProvisioner
+
+__all__ = [
+    "Workspace",
+    "WorkspaceProvisioner",
+    "User",
+    "UserGroup",
+    "Permission",
+    "UserProvisioner",
+    "UserGroupProvisioner",
+    "PermissionProvisioner",
+    "UserDataFilterProvisioner",
+    "UserDataFilter",
+    "__version__",
+]

gooddata-pipelines/gooddata_pipelines/__init__.py

@@ -0,0 +1,7 @@
+# (C) 2025 GoodData Corporation
+from importlib import metadata
+
+try:
+    __version__ = metadata.version("gooddata-pipelines")
+except metadata.PackageNotFoundError:
+    __version__ = "unknown-version"

gooddata-pipelines/gooddata_pipelines/_version.py

@@ -0,0 +1,5 @@
+# (C) 2025 GoodData Corporation
+
+from .gooddata_api_wrapper import GoodDataAPI
+
+__all__ = ["GoodDataAPI"]

gooddata-pipelines/gooddata_pipelines/api/__init__.py

@@ -0,0 +1,41 @@
+# (C) 2025 GoodData Corporation
+
+"""Exception class for Panther operations.
+
+This module defines the internally used `PantherException` class, which is used
+to handle exceptions that occur during operations related to the Panther SDK or
+GoodData Cloud API.
+"""
+
+
+class GoodDataApiException(Exception):
+    """Exception raised during Panther operations.
+
+    This exception is used to indicate errors that occur during operations
+    related to interactions with the GoodData Python SDK or GoodData Cloud API.
+    It can include additional context provided through keyword arguments.
+    """
+
+    def __init__(self, message: str, **kwargs: str) -> None:
+        """Raise a PantherException with a message and optional context.
+
+        Args:
+            message (str): The error message describing the exception.
+            **kwargs: Additional context for the exception, such as HTTP status,
+                    API endpoint, and HTTP method or any other relevant information.
+        """
+
+        super().__init__(message)
+        self.error_message: str = message
+
+        # Set default values for attributes.
+        # TODO: Consider if the defaults for these are still needed
+        # - the values were necessary for log schema implementations, which
+        #   are not used anymore.
+        self.http_status: str = "500 Internal Server Error"
+        self.api_endpoint: str = "NA"
+        self.http_method: str = "NA"
+
+        # Set attributes from kwargs.
+        for key, value in kwargs.items():
+            setattr(self, key, value)