Release v0.2.0 (#328)

# Version changelog

## 0.2.0

* Added retrieving for all account-level groups with matching names to
workspace-level groups in case no explicit configuration
([#277](#277)).
* Added crawler for Azure Service principals used for direct storage
access ([#305](#305)).
* Added more SQL queries to the assessment step dashboard
([#269](#269)).
* Added filtering out for job clusters in the clusters crawler
([#298](#298)).
* Added recording errors from `crawl_tables` step in
`$inventory.table_failures` table and display counter on the dashboard
([#300](#300)).
* Added comprehensive introduction user manual
([#273](#273)).
* Added interactive tutorial for local group migration readme
([#291](#291)).
* Added tutorial links to the landing page of documentation
([#290](#290)).
* Added (internal) support for account-level configuration and
multi-cloud workspace list
([#264](#264)).
* Improved order of tasks in the README notebook
([#286](#286)).
* Improved installation script to run in a Windows Git Bash terminal
([#282](#282)).
* Improved installation script by setting log level to uppercase by
default ([#271](#271)).
* Improved installation finish messages within installer script
([#267](#267)).
* Improved automation for `MANAGED` table migration and continued
building tables migration component
([#295](#295)).
* Fixed debug notebook code with refactored package structure
([#250](#250))
([#265](#265)).
* Fixed replacement of custom configured database to replicate in the
report for external locations
([#296](#296)).
* Removed redundant `notebooks` top-level folder
([#263](#263)).
* Split checking for test failures and linting errors into independent
GitHub Actions checks
([#287](#287)).
* Verify query metadata for assessment dashboards during unit tests
([#294](#294)).

Author: nfx

CHANGELOG.md

@@ -1,5 +1,27 @@
 # Version changelog
 
+## 0.2.0
+
+* Added retrieving for all account-level groups with matching names to workspace-level groups in case no explicit configuration ([#277](https://github.com/databricks/ucx/pull/277)).
+* Added crawler for Azure Service principals used for direct storage access ([#305](https://github.com/databricks/ucx/pull/305)).
+* Added more SQL queries to the assessment step dashboard ([#269](https://github.com/databricks/ucx/pull/269)).
+* Added filtering out for job clusters in the clusters crawler ([#298](https://github.com/databricks/ucx/pull/298)).
+* Added recording errors from `crawl_tables` step in `$inventory.table_failures` table and display counter on the dashboard ([#300](https://github.com/databricks/ucx/pull/300)).
+* Added comprehensive introduction user manual ([#273](https://github.com/databricks/ucx/pull/273)).
+* Added interactive tutorial for local group migration readme ([#291](https://github.com/databricks/ucx/pull/291)).
+* Added tutorial links to the landing page of documentation ([#290](https://github.com/databricks/ucx/pull/290)).
+* Added (internal) support for account-level configuration and multi-cloud workspace list ([#264](https://github.com/databricks/ucx/pull/264)).
+* Improved order of tasks in the README notebook ([#286](https://github.com/databricks/ucx/pull/286)).
+* Improved installation script to run in a Windows Git Bash terminal ([#282](https://github.com/databricks/ucx/pull/282)).
+* Improved installation script by setting log level to uppercase by default ([#271](https://github.com/databricks/ucx/pull/271)).
+* Improved installation finish messages within installer script ([#267](https://github.com/databricks/ucx/pull/267)).
+* Improved automation for `MANAGED` table migration and continued building tables migration component ([#295](https://github.com/databricks/ucx/pull/295)).
+* Fixed debug notebook code with refactored package structure ([#250](https://github.com/databricks/ucx/pull/250)) ([#265](https://github.com/databricks/ucx/pull/265)).
+* Fixed replacement of custom configured database to replicate in the report for external locations ([#296](https://github.com/databricks/ucx/pull/296)).
+* Removed redundant `notebooks` top-level folder ([#263](https://github.com/databricks/ucx/pull/263)).
+* Split checking for test failures and linting errors into independent GitHub Actions checks ([#287](https://github.com/databricks/ucx/pull/287)).
+* Verify query metadata for assessment dashboards during unit tests ([#294](https://github.com/databricks/ucx/pull/294)).
+
 ## 0.1.1
 
 * Added batched iteration for `INSERT INTO` queries in `StatementExecutionBackend` with default `max_records_per_batch=1000` ([#237](https://github.com/databricks/ucx/pull/237)).

src/databricks/labs/ucx/__about__.py

@@ -1 +1 @@
-__version__ = "0.1.1"
+__version__ = "0.2.0"

src/databricks/labs/ucx/install.py

@@ -393,7 +393,7 @@ def _job_settings(self, step_name: str, dbfs_path: str):
         tasks = sorted([t for t in _TASKS.values() if t.workflow == step_name], key=lambda _: _.name)
         return {
             "name": self._name(step_name),
-            "tags": {TAG_APP: self._app, TAG_STEP: step_name},
+            "tags": {TAG_APP: self._app, TAG_STEP: step_name, "version": f"v{__version__}"},
             "job_clusters": self._job_clusters({t.job_cluster for t in tasks}),
             "email_notifications": email_notifications,
             "tasks": [self._job_task(task, dbfs_path) for task in tasks],

tests/integration/conftest.py

@@ -82,11 +82,10 @@ def test_catalog_fixture(make_catalog):
 
 @pytest.fixture
 def make_schema(sql_exec, make_random):
-    def create(*, catalog="hive_metastore", schema):
+    def create(*, catalog: str = "hive_metastore", schema: str | None = None):
         if schema is None:
-            schema = f"{catalog}.ucx_S{make_random(4)}".lower()
-        else:
-            schema = f"{catalog}.{schema}"
+            schema = f"ucx_S{make_random(4)}"
+        schema = f"{catalog}.{schema}".lower()
         sql_exec(f"CREATE SCHEMA {schema}")
         return schema
 

tests/integration/hive_metastore/test_migrate.py

@@ -15,7 +15,7 @@ def test_migrate_managed_tables(ws, make_catalog, make_schema, make_table):
     schema_a = make_schema(catalog="hive_metastore")
     _, target_schema = schema_a.split(".")
 
-    make_schema(catalog=target_catalog, schema_name=target_schema)
+    make_schema(catalog=target_catalog, schema=target_schema)
 
     managed_table = make_table(schema=schema_a)
 

tests/integration/test_installation.py

@@ -47,16 +47,16 @@ def test_jobs_with_no_inventory_database(
     sql_exec(f"GRANT MODIFY ON SCHEMA {schema_b} TO `{ws_group_b.display_name}`")
 
     cluster_policy = make_cluster_policy()
+    make_cluster_policy_permissions(
+        object_id=cluster_policy.policy_id,
+        permission_level=PermissionLevel.CAN_USE,
+        group_name=ws_group_a.display_name,
+    )
     cpp_src = ws.permissions.get("cluster-policies", cluster_policy.policy_id)
     cluster_policy_src_permissions = sorted(
         [_ for _ in cpp_src.access_control_list if _.group_name == ws_group_a.display_name],
         key=lambda p: p.group_name,
     )
-    make_cluster_policy_permissions(
-        object_id=cluster_policy.policy_id,
-        permission_level=random.choice([PermissionLevel.CAN_USE]),
-        group_name=ws_group_a.display_name,
-    )
 
     job = make_job()
     make_job_permissions(
@@ -86,7 +86,7 @@ def test_jobs_with_no_inventory_database(
     )
 
     try:
-        for step in ["assessment", "migrate-groups", "migrate-groups-cleanup"]:
+        for step in ["assessment", "migrate-groups"]:
             logger.debug(f"starting {step} job: {ws.config.host}#job/{install._deployed_steps[step]}")
             ws.jobs.run_now(install._deployed_steps[step]).result()