Release v0.1.1 (#261)

* Added batched iteration for `INSERT INTO` queries in
`StatementExecutionBackend` with default `max_records_per_batch=1000`
([#237](#237)).
* Added crawler for mount points
([#209](#209)).
* Added crawlers for compatibility of jobs and clusters, along with
basic recommendations for external locations
([#244](#244)).
* Added safe return on grants
([#246](#246)).
* Added ability to specify empty group filter in the installer script
([#216](#216))
([#217](#217)).
* Added ability to install application by multiple different users on
the same workspace ([#235](#235)).
* Added dashboard creation on installation and a requirement for
`warehouse_id` in config, so that the assessment dashboards are
refreshed automatically after job runs
([#214](#214)).
* Added reliance on rate limiting from Databricks SDK for listing
workspace ([#258](#258)).
* Fixed errors in corner cases where Azure Service Principal Credentials
were not available in Spark context
([#254](#254)).
* Fixed `DESCRIBE TABLE` throwing errors when listing Legacy Table ACLs
([#238](#238)).
* Fixed `file already exists` error in the installer script
([#219](#219))
([#222](#222)).
* Fixed `guess_external_locations` failure with `AttributeError:
as_dict` and added an integration test
([#259](#259)).
* Fixed error handling edge cases in `crawl_tables` task
([#243](#243))
([#251](#251)).
* Fixed `crawl_permissions` task failure on folder names containing a
forward slash ([#234](#234)).
* Improved `README` notebook documentation
([#260](#260),
[#228](#228),
[#252](#252),
[#223](#223),
[#225](#225)).
* Removed redundant `.python-version` file
([#221](#221)).
* Removed discovery of account groups from `crawl_permissions` task
([#240](#240)).
* Updated databricks-sdk requirement from ~=0.8.0 to ~=0.9.0
([#245](#245)).

Author: nfx

CHANGELOG.md

@@ -1,5 +1,26 @@
 # Version changelog
 
+## 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)).
+* Added crawler for mount points ([#209](https://github.com/databricks/ucx/pull/209)).
+* Added crawlers for compatibility of jobs and clusters, along with basic recommendations for external locations ([#244](https://github.com/databricks/ucx/pull/244)).
+* Added safe return on grants ([#246](https://github.com/databricks/ucx/pull/246)).
+* Added ability to specify empty group filter in the installer script ([#216](https://github.com/databricks/ucx/pull/216)) ([#217](https://github.com/databricks/ucx/pull/217)).
+* Added ability to install application by multiple different users on the same workspace ([#235](https://github.com/databricks/ucx/pull/235)).
+* Added dashboard creation on installation and a requirement for `warehouse_id` in config, so that the assessment dashboards are refreshed automatically after job runs ([#214](https://github.com/databricks/ucx/pull/214)).
+* Added reliance on rate limiting from Databricks SDK for listing workspace ([#258](https://github.com/databricks/ucx/pull/258)).
+* Fixed errors in corner cases where Azure Service Principal Credentials were not available in Spark context ([#254](https://github.com/databricks/ucx/pull/254)).
+* Fixed `DESCRIBE TABLE` throwing errors when listing Legacy Table ACLs ([#238](https://github.com/databricks/ucx/pull/238)).
+* Fixed `file already exists` error in the installer script ([#219](https://github.com/databricks/ucx/pull/219)) ([#222](https://github.com/databricks/ucx/pull/222)).
+* Fixed `guess_external_locations` failure with `AttributeError: as_dict` and added an integration test ([#259](https://github.com/databricks/ucx/pull/259)).
+* Fixed error handling edge cases in `crawl_tables` task ([#243](https://github.com/databricks/ucx/pull/243)) ([#251](https://github.com/databricks/ucx/pull/251)).
+* Fixed `crawl_permissions` task failure on folder names containing a forward slash ([#234](https://github.com/databricks/ucx/pull/234)).
+* Improved `README` notebook documentation ([#260](https://github.com/databricks/ucx/pull/260), [#228](https://github.com/databricks/ucx/pull/228), [#252](https://github.com/databricks/ucx/pull/252), [#223](https://github.com/databricks/ucx/pull/223), [#225](https://github.com/databricks/ucx/pull/225)).
+* Removed redundant `.python-version` file ([#221](https://github.com/databricks/ucx/pull/221)).
+* Removed discovery of account groups from `crawl_permissions` task ([#240](https://github.com/databricks/ucx/pull/240)).
+* Updated databricks-sdk requirement from ~=0.8.0 to ~=0.9.0 ([#245](https://github.com/databricks/ucx/pull/245)).
+
 ## 0.1.0
 
 Features

src/databricks/labs/ucx/__about__.py

@@ -1 +1 @@
-__version__ = "0.1.0"
+__version__ = "0.1.1"

src/databricks/labs/ucx/assessment/commands/create_table_inventory.scala

@@ -148,7 +148,3 @@ def snapshot(self) -> list[ClusterInfo]:
     def _try_fetch(self) -> list[ClusterInfo]:
         for row in self._fetch(f"SELECT * FROM {self._schema}.{self._table}"):
             yield JobInfo(*row)
-
-
-if __name__ == "__main__":
-    print("Databricks UC Assessment")

src/databricks/labs/ucx/assessment/crawlers.py

@@ -86,7 +86,7 @@ def _row_to_sql(row, fields):
             elif f.type == bool:
                 data.append("TRUE" if value else "FALSE")
             elif f.type == str:
-                value = value.replace("'", "''")
+                value = str(value).replace("'", "''")
                 data.append(f"'{value}'")
             elif f.type == int:
                 data.append(f"{value}")

src/databricks/labs/ucx/framework/crawlers.py

@@ -25,7 +25,7 @@ def _external_locations(self, tables: list[Row], mounts) -> list[ExternalLocatio
         min_slash = 2
         external_locations: list[ExternalLocation] = []
         for table in tables:
-            location = table.as_dict()["location"]
+            location = table.location
             if location is not None and len(location) > 0:
                 if location.startswith("dbfs:/mnt"):
                     for mount in mounts:

src/databricks/labs/ucx/hive_metastore/data_objects.py

@@ -234,6 +234,6 @@ def _grants(
                     any_file=any_file,
                     anonymous_function=anonymous_function,
                 )
-        except RuntimeError as e:
+        except Exception as e:
             logger.error(f"Couldn't fetch grants for object {on_type} {key}: {e}")
             return []

src/databricks/labs/ucx/hive_metastore/grants.py

@@ -140,6 +140,6 @@ def _describe(self, catalog: str, database: str, table: str) -> Table | None:
                 location=describe.get("Location", None),
                 view_text=describe.get("View Text", None),
             )
-        except RuntimeError as e:
+        except Exception as e:
             logger.error(f"Couldn't fetch information for table {full_name} : {e}")
             return None

src/databricks/labs/ucx/hive_metastore/tables.py

@@ -36,17 +36,29 @@ def __repr__(self):
 
 
 class Row(tuple):
+    # Python SDK convention
     def as_dict(self) -> dict[str, any]:
         return dict(zip(self.__columns__, self, strict=True))
 
-    def __getattr__(self, col):
-        idx = self.__columns__.index(col)
-        return self[idx]
+    # PySpark convention
+    def __contains__(self, item):
+        return item in self.__columns__
 
     def __getitem__(self, col):
+        if isinstance(col, int | slice):
+            return super().__getitem__(col)
         # if columns are named `2 + 2`, for example
         return self.__getattr__(col)
 
+    def __getattr__(self, col):
+        try:
+            idx = self.__columns__.index(col)
+            return self[idx]
+        except IndexError:
+            raise AttributeError(col)  # noqa: B904
+        except ValueError:
+            raise AttributeError(col)  # noqa: B904
+
     def __repr__(self):
         return f"Row({', '.join(f'{k}={v}' for (k, v) in zip(self.__columns__, self, strict=True))})"
 

src/databricks/labs/ucx/mixins/sql.py

@@ -34,7 +34,12 @@ def crawl_tables(_: MigrationConfig):
     readily accessible point of reference for users, data engineers, and administrators."""
 
 
-@task("assessment", depends_on=[crawl_tables], job_cluster="tacl")
+@task("assessment", job_cluster="tacl")
+def setup_tacl(_: MigrationConfig):
+    """(Optimization) Starts tacl job cluster in parallel to crawling tables"""
+
+
+@task("assessment", depends_on=[crawl_tables, setup_tacl], job_cluster="tacl")
 def crawl_grants(cfg: MigrationConfig):
     """During this process, our methodology is purposefully designed to systematically scan and retrieve ACLs
     (Access Control Lists) associated with Legacy Tables from the Hive Metastore. These ACLs encompass comprehensive