gooddata-pipelines 1.51.0__tar.gz → 1.52.0__tar.gz

{gooddata_pipelines-1.51.0 → gooddata_pipelines-1.52.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: gooddata-pipelines
-Version: 1.51.0
+Version: 1.52.0
 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~=1.51.0
+Requires-Dist: gooddata-sdk~=1.52.0
 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-1.51.0 → gooddata_pipelines-1.52.0}/TODO.md

@@ -10,15 +10,10 @@ 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 to load test data
 - [ ] Cleanup custom exceptions
 - [ ] 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-1.51.0 → gooddata_pipelines-1.52.0}/gooddata_pipelines/backup_and_restore/backup_input_processor.py

@@ -1,7 +1,6 @@
 # (C) 2025 GoodData Corporation
 
-from dataclasses import dataclass
-
+import attrs
 import requests
 
 from gooddata_pipelines.api import GoodDataApi
@@ -46,7 +45,7 @@ class BackupInputProcessor:
         )
         self.all_workspaces_endpoint = f"{self.base_workspace_endpoint}?page=0&size={self.page_size}&sort=name,asc&metaInclude=page"
 
-    @dataclass
+    @attrs.define
     class _ProcessDataOutput:
         workspace_ids: list[str]
         sub_parents: list[str] | None = None

{gooddata_pipelines-1.51.0 → gooddata_pipelines-1.52.0}/gooddata_pipelines/backup_and_restore/backup_manager.py

@@ -6,10 +6,10 @@ import shutil
 import tempfile
 import time
 import traceback
-from dataclasses import dataclass
 from pathlib import Path
 from typing import Any, Type
 
+import attrs
 import requests
 import yaml
 from gooddata_sdk.utils import PROFILES_FILE_PATH, profile_content
@@ -40,7 +40,7 @@ from gooddata_pipelines.logger import LogObserver
 from gooddata_pipelines.utils.rate_limiter import RateLimiter
 
 
-@dataclass
+@attrs.define
 class BackupBatch:
     list_of_ids: list[str]
 

{gooddata_pipelines-1.51.0 → gooddata_pipelines-1.52.0}/gooddata_pipelines/backup_and_restore/constants.py

@@ -1,11 +1,11 @@
 # (C) 2025 GoodData Corporation
 import datetime
-from dataclasses import dataclass
 
+import attrs
 from gooddata_sdk._version import __version__ as sdk_version
 
 
-@dataclass(frozen=True)
+@attrs.frozen
 class DirNames:
     """
     Folder names used in the SDK backup process:
@@ -21,14 +21,14 @@ class DirNames:
     UDF = "user_data_filters"
 
 
-@dataclass(frozen=True)
+@attrs.frozen
 class ApiDefaults:
     DEFAULT_PAGE_SIZE = 100
     DEFAULT_BATCH_SIZE = 100
     DEFAULT_API_CALLS_PER_SECOND = 1.0
 
 
-@dataclass(frozen=True)
+@attrs.frozen
 class BackupSettings(ApiDefaults):
     MAX_RETRIES = 3
     RETRY_DELAY = 5  # seconds

{gooddata_pipelines-1.51.0 → gooddata_pipelines-1.52.0}/gooddata_pipelines/provisioning/entities/user_data_filters/models/udf_models.py

@@ -2,31 +2,29 @@
 
 """This module defines data models for user data filters in a GoodData workspace."""
 
-# TODO: consider using attrs instead of dataclasses for these models. Dataclasses
-# have different functionality per Python version (not package version).
+import attrs
+from pydantic import BaseModel, ConfigDict
 
-from dataclasses import dataclass, field
 
-
-@dataclass
+@attrs.define
 class UserDataFilterGroup:
     udf_id: str
     udf_values: list[str]
 
 
-@dataclass
+@attrs.define
 class WorkspaceUserDataFilters:
     workspace_id: str
-    user_data_filters: list["UserDataFilterGroup"] = field(default_factory=list)
+    user_data_filters: list["UserDataFilterGroup"] = attrs.field(factory=list)
+
 
+class UserDataFilterFullLoad(BaseModel):
+    model_config = ConfigDict(extra="forbid")
 
-@dataclass
-class UserDataFilterFullLoad:
     workspace_id: str
     udf_id: str
     udf_value: str
 
 
-@dataclass
 class UserDataFilterIncrementalLoad(UserDataFilterFullLoad):
     is_active: bool

{gooddata_pipelines-1.51.0 → gooddata_pipelines-1.52.0}/gooddata_pipelines/provisioning/entities/user_data_filters/user_data_filters.py

@@ -50,6 +50,8 @@ class UserDataFilterProvisioner(
     ldm_column_name: str = ""
     maql_column_name: str = ""
 
+    FULL_LOAD_TYPE = UserDataFilterFullLoad
+
     def set_ldm_column_name(self, ldm_column_name: str) -> None:
         """Set the LDM column name for user data filters.
 
@@ -214,8 +216,6 @@ class UserDataFilterProvisioner(
         )
         self._create_user_data_filters(grouped_db_user_data_filters)
 
-        self.logger.info("User data filters provisioning completed")
-
     def _provision_incremental_load(self) -> None:
         """Provision user data filters in GoodData workspaces."""
         raise NotImplementedError("Not implemented yet.")

{gooddata_pipelines-1.51.0 → gooddata_pipelines-1.52.0}/gooddata_pipelines/provisioning/entities/users/models/permissions.py

@@ -9,7 +9,7 @@ from gooddata_sdk.catalog.permission.declarative_model.permission import (
     CatalogDeclarativeSingleWorkspacePermission,
     CatalogDeclarativeWorkspacePermissions,
 )
-from pydantic import BaseModel
+from pydantic import BaseModel, ConfigDict
 
 from gooddata_pipelines.provisioning.utils.exceptions import BaseUserException
 
@@ -23,6 +23,8 @@ class EntityType(str, Enum):
 
 
 class BasePermission(BaseModel):
+    model_config = ConfigDict(extra="forbid")
+
     permission: str
     workspace_id: str
     entity_id: str

{gooddata_pipelines-1.51.0 → gooddata_pipelines-1.52.0}/gooddata_pipelines/provisioning/entities/users/models/user_groups.py

@@ -1,9 +1,17 @@
 # (C) 2025 GoodData Corporation
 
-from pydantic import BaseModel, Field, ValidationInfo, field_validator
+from pydantic import (
+    BaseModel,
+    ConfigDict,
+    Field,
+    ValidationInfo,
+    field_validator,
+)
 
 
 class UserGroupBase(BaseModel):
+    model_config = ConfigDict(extra="forbid")
+
     user_group_id: str
     user_group_name: str
     parent_user_groups: list[str] = Field(default_factory=list)

{gooddata_pipelines-1.51.0 → gooddata_pipelines-1.52.0}/gooddata_pipelines/provisioning/entities/users/models/users.py

@@ -3,7 +3,7 @@
 from typing import Any
 
 from gooddata_sdk.catalog.user.entity_model.user import CatalogUser
-from pydantic import BaseModel, Field
+from pydantic import BaseModel, ConfigDict, Field
 
 
 class UserProfile(BaseModel):
@@ -18,6 +18,8 @@ class UserProfile(BaseModel):
 class BaseUser(BaseModel):
     """Base class containing shared user fields and functionality."""
 
+    model_config = ConfigDict(extra="forbid")
+
     user_id: str
     firstname: str | None
     lastname: str | None

{gooddata_pipelines-1.51.0 → gooddata_pipelines-1.52.0}/gooddata_pipelines/provisioning/entities/workspaces/models.py

@@ -22,7 +22,7 @@ class WorkspaceDataMaps:
 
 
 class WorkspaceBase(BaseModel):
-    model_config = ConfigDict(coerce_numbers_to_str=True)
+    model_config = ConfigDict(coerce_numbers_to_str=True, extra="forbid")
 
     parent_id: str
     workspace_id: str

{gooddata_pipelines-1.51.0 → gooddata_pipelines-1.52.0}/gooddata_pipelines/provisioning/utils/utils.py

@@ -2,6 +2,8 @@
 
 """Module for utilities used in GoodData Pipelines provisioning."""
 
+from typing import Any, cast
+
 import attrs
 from requests import Response
 
@@ -11,9 +13,8 @@ class AttributesMixin:
     Mixin class to provide a method for getting attributes of an object which may or may not exist.
     """
 
-    @staticmethod
     def get_attrs(
-        *objects: object, overrides: dict[str, str] | None = None
+        self, *objects: object, overrides: dict[str, str] | None = None
     ) -> dict[str, str]:
         """
         Returns a dictionary of attributes from the given objects.
@@ -27,11 +28,11 @@ class AttributesMixin:
         """
         # TODO: This might not work great with nested objects, values  which are lists of objects etc.
         # If we care about parsing the logs back from the string, we should consider some other approach
-        attrs: dict[str, str] = {}
+        attributes: dict[str, str] = {}
         for context_object in objects:
             if isinstance(context_object, Response):
                 # for request.Response objects, keys need to be renamed to match the log schema
-                attrs.update(
+                attributes.update(
                     {
                         "http_status": str(context_object.status_code),
                         "http_method": getattr(
@@ -42,23 +43,31 @@ class AttributesMixin:
                         ),
                     }
                 )
+            elif attrs.has(type(context_object)):
+                for key, value in attrs.asdict(
+                    cast(attrs.AttrsInstance, context_object)
+                ).items():
+                    self._add_to_dict(attributes, key, value)
             else:
                 # Generic handling for other objects
                 for key, value in context_object.__dict__.items():
-                    if value is None:
-                        continue
-
-                    if isinstance(value, list):
-                        attrs[key] = ", ".join(
-                            str(list_item) for list_item in value
-                        )
-                    else:
-                        attrs[key] = str(value)
+                    self._add_to_dict(attributes, key, value)
 
         if overrides:
-            attrs.update(overrides)
+            attributes.update(overrides)
+
+        return attributes
+
+    def _add_to_dict(
+        self, attributes: dict[str, str], key: str, value: Any
+    ) -> None:
+        if value is None:
+            return
 
-        return attrs
+        if isinstance(value, list):
+            attributes[key] = ", ".join(str(list_item) for list_item in value)
+        else:
+            attributes[key] = str(value)
 
 
 @attrs.define

{gooddata_pipelines-1.51.0 → gooddata_pipelines-1.52.0}/pyproject.toml

@@ -1,7 +1,7 @@
 # (C) 2025 GoodData Corporation
 [project]
 name = "gooddata-pipelines"
-version = "1.51.0"
+version = "1.52.0"
 description = "GoodData Cloud lifecycle automation pipelines"
 authors = [{ name = "GoodData", email = "support@gooddata.com" }]
 license = { text = "MIT" }
@@ -11,7 +11,7 @@ dependencies = [
     "pydantic (>=2.11.3,<3.0.0)",
     "requests (>=2.32.3,<3.0.0)",
     "types-requests (>=2.32.0,<3.0.0)",
-    "gooddata-sdk~=1.51.0",
+    "gooddata-sdk~=1.52.0",
     "boto3 (>=1.39.3,<2.0.0)",
     "boto3-stubs (>=1.39.3,<2.0.0)",
     "types-pyyaml (>=6.0.12.20250326,<7.0.0)"
@@ -33,6 +33,7 @@ moto = ">=5.1.6,<6.0.0"
 pytest = ">=8.3.5,<9.0.0"
 pytest-mock = ">=3.14.0,<4.0.0"
 ruff = ">=0.11.2,<0.12.0"
+orjson = "^3.11.3"
 
 [build-system]
 requires = ["hatchling"]

{gooddata_pipelines-1.51.0 → gooddata_pipelines-1.52.0}/tests/provisioning/entities/users/test_permissions.py

@@ -1,7 +1,7 @@
 # (C) 2025 GoodData Corporation
-import json
 from typing import Literal
 
+import orjson
 import pytest
 from gooddata_api_client.exceptions import (  # type: ignore[import]
     NotFoundException,
@@ -455,7 +455,7 @@ def test_permission_provisioner(
         f"{TEST_DATA_SUBDIR}/existing_upstream_permissions.json"
     )
     with open(EXISTING_UPSTREAM_PERMISSIONS_PATH, "r") as f:
-        raw_existing_upstream_permissions = json.load(f)
+        raw_existing_upstream_permissions = orjson.loads(f.read())
 
     existing_upstream_permissions = parse_expected_permissions(
         raw_existing_upstream_permissions
@@ -477,11 +477,11 @@ def test_permission_provisioner(
 
     # Load source data
     with open(f"{TEST_DATA_SUBDIR}/{source_data_path}", "r") as f:
-        source_data = json.load(f)
+        source_data = orjson.loads(f.read())
 
     # Load and parse expected data
     with open(f"{TEST_DATA_SUBDIR}/{expected_data_path}", "r") as f:
-        raw_expected_result = json.load(f)
+        raw_expected_result = orjson.loads(f.read())
 
     expected_result = parse_expected_permissions(raw_expected_result)
 

{gooddata_pipelines-1.51.0 → gooddata_pipelines-1.52.0}/tests/provisioning/entities/users/test_users.py

@@ -1,8 +1,8 @@
 # (C) 2025 GoodData Corporation
-import json
-from dataclasses import dataclass
 from typing import Literal, Optional
 
+import attrs
+import orjson
 import pytest
 from gooddata_api_client.exceptions import NotFoundException  # type: ignore
 from gooddata_sdk.catalog.user.entity_model.user import (
@@ -29,7 +29,7 @@ from tests.conftest import TEST_DATA_DIR
 TEST_DATA_SUBDIR = f"{TEST_DATA_DIR}/provisioning/entities/users"
 
 
-@dataclass
+@attrs.define
 class MockUser:
     id: str
     firstname: Optional[str]
@@ -225,15 +225,15 @@ def test_user_provisioning(
 
     # Load input data
     with open(f"{TEST_DATA_SUBDIR}/{input_path}", "r") as f:
-        input_data = json.load(f)
+        input_data = orjson.loads(f.read())
 
     # Load expected data
     with open(f"{TEST_DATA_SUBDIR}/{expected_path}", "r") as f:
-        raw_expected_data = json.load(f)
+        raw_expected_data = orjson.loads(f.read())
 
     # Load and patch "existing users"
     with open(f"{TEST_DATA_SUBDIR}/existing_upstream_users.json", "r") as f:
-        raw_upstream_users = json.load(f)
+        raw_upstream_users = orjson.loads(f.read())
 
     upstream_users = parse_user_data(raw_upstream_users)
 

{gooddata_pipelines-1.51.0 → gooddata_pipelines-1.52.0}/tests/provisioning/entities/workspaces/test_workspace_data_filters.py

@@ -1,8 +1,8 @@
 # (C) 2025 GoodData Corporation
 
-import json
 from typing import Any
 
+import orjson
 import pytest
 from pydantic import ValidationError
 from requests import Response
@@ -67,7 +67,7 @@ def test_get_wdf_settings_for_workspace_valid_payload(
 
     payload = WDF_VALID_PAYLOAD
 
-    mock_response._content = json.dumps(payload).encode("utf-8")
+    mock_response._content = orjson.dumps(payload)
 
     mocker.patch.object(
         mock_gooddata_api,
@@ -102,7 +102,7 @@ def test_get_wdf_settings_for_workspace_invalid_payload(
         ]
     }
 
-    mock_response._content = json.dumps(payload).encode("utf-8")
+    mock_response._content = orjson.dumps(payload)
 
     mocker.patch.object(
         mock_gooddata_api,

{gooddata_pipelines-1.51.0 → gooddata_pipelines-1.52.0}/tests/provisioning/test_provisioning.py

@@ -3,11 +3,13 @@ import os
 from pathlib import Path
 
 import pytest
+from pydantic import BaseModel, ValidationError
 
 from gooddata_pipelines import (
     EntityType,
     PermissionFullLoad,
     PermissionIncrementalLoad,
+    UserDataFilterFullLoad,
     UserFullLoad,
     UserGroupFullLoad,
     UserGroupIncrementalLoad,
@@ -119,3 +121,106 @@ def test_create_from_profile() -> None:
     )
     assert provisioner._api._domain == "http://localhost:3000"
     assert provisioner._api._token == os.environ.pop("MOCK_TOKEN")
+
+
+MODELS_AND_VALID_DATA = [
+    (
+        WorkspaceFullLoad,
+        {
+            "parent_id": "parent_id",
+            "workspace_id": "workspace_id",
+            "workspace_name": "workspace_name",
+        },
+    ),
+    (
+        WorkspaceIncrementalLoad,
+        {
+            "parent_id": "parent_id",
+            "workspace_id": "workspace_id",
+            "workspace_name": "workspace_name",
+            "is_active": True,
+        },
+    ),
+    (
+        UserFullLoad,
+        {
+            "user_id": "user_id",
+            "firstname": "firstname",
+            "lastname": "lastname",
+            "email": "email",
+            "auth_id": "auth_id",
+            "user_groups": ["user_group_id"],
+        },
+    ),
+    (
+        UserIncrementalLoad,
+        {
+            "user_id": "user_id",
+            "firstname": "firstname",
+            "lastname": "lastname",
+            "email": "email",
+            "auth_id": "auth_id",
+            "user_groups": ["user_group_id"],
+            "is_active": True,
+        },
+    ),
+    (
+        UserGroupFullLoad,
+        {
+            "user_group_id": "user_group_id",
+            "user_group_name": "user_group_name",
+        },
+    ),
+    (
+        UserGroupIncrementalLoad,
+        {
+            "user_group_id": "user_group_id",
+            "user_group_name": "user_group_name",
+            "is_active": True,
+        },
+    ),
+    (
+        PermissionFullLoad,
+        {
+            "permission": "permission",
+            "workspace_id": "workspace_id",
+            "entity_id": "entity_id",
+            "entity_type": EntityType.user,
+        },
+    ),
+    (
+        PermissionIncrementalLoad,
+        {
+            "permission": "permission",
+            "workspace_id": "workspace_id",
+            "entity_id": "entity_id",
+            "entity_type": EntityType.user,
+            "is_active": True,
+        },
+    ),
+    (
+        UserDataFilterFullLoad,
+        {
+            "workspace_id": "workspace_id",
+            "udf_id": "udf_id",
+            "udf_value": "udf_value",
+        },
+    ),
+]
+
+
+@pytest.mark.parametrize(["provisioning_model", "data"], MODELS_AND_VALID_DATA)
+def test_validate_valid_data(provisioning_model: BaseModel, data: dict) -> None:
+    """Test validating valid data."""
+    provisioning_model.model_validate(data)
+
+
+@pytest.mark.parametrize(
+    ["provisioning_model", "data"],
+    MODELS_AND_VALID_DATA,
+)
+def test_raise_extra_fields(provisioning_model: BaseModel, data: dict) -> None:
+    """Test raising an error when extra fields are provided."""
+    data["extra_field"] = "extra_field"
+    with pytest.raises(ValidationError):
+        provisioning_model.model_validate(data)

{gooddata_pipelines-1.51.0 → gooddata_pipelines-1.52.0}/tests/test_ldm_extension/test_models/test_analytical_object.py

@@ -1,6 +1,5 @@
 # (C) 2025 GoodData Corporation
-import json
-
+import orjson
 import pytest
 
 from gooddata_pipelines.ldm_extension.models.analytical_object import (
@@ -20,7 +19,7 @@ from tests.conftest import TEST_DATA_DIR
 )
 def test_analytical_object_model_with_metrics(file_path):
     with open(file_path, "r") as file:
-        data = json.load(file)
+        data = orjson.loads(file.read())
     analytical_objects = AnalyticalObjects(**data)
     assert isinstance(analytical_objects, AnalyticalObjects)
     assert isinstance(analytical_objects.data, list)