Enforcing invalid-name pylint rule (#957)

Author: nfx

pyproject.toml

@@ -322,10 +322,19 @@ function-naming-style = "snake_case"
 
 # Regular expression matching correct function names. Overrides function-naming-
 # style. If left empty, function names will be checked with the set naming style.
-function-rgx = "[a-z_][a-z0-9_]{2,30}$"
+function-rgx = "[a-z_][a-z0-9_]{2,}$"
 
 # Good variable names which should always be accepted, separated by a comma.
-good-names = ["i", "j", "k", "ex", "Run", "_"]
+good-names = [
+    "f",            # use for file handles
+    "i", "j", "k",  # use for loops
+    "df",           # use for pyspark.sql.DataFrame
+    "ex", "e",      # use for exceptions
+    "fn", "cb",     # use for callbacks
+    "_",            # use for ignores
+    "a",            # use for databricks.sdk.AccountClient
+    "w", "ws"       # use for databricks.sdk.WorkspaceClient
+]
 
 # Good variable names regexes, separated by a comma. If names match any regex,
 # they will always be accepted
@@ -537,22 +546,12 @@ confidence = ["HIGH", "CONTROL_FLOW", "INFERENCE", "INFERENCE_FAILURE", "UNDEFIN
 # no Warning level messages displayed, use "--disable=all --enable=classes
 # --disable=W".
 disable = [
-    "raw-checker-failed",
-    "bad-inline-option",
-    "locally-disabled",
-    "file-ignored",
-    "suppressed-message",
-    "deprecated-pragma",
-    "use-implicit-booleaness-not-comparison-to-string",
-    "use-implicit-booleaness-not-comparison-to-zero",
     "consider-using-augmented-assign",
     "prefer-typing-namedtuple",
     "attribute-defined-outside-init",
-    "invalid-name",
     "missing-module-docstring",
     "missing-class-docstring",
     "missing-function-docstring",
-#    "protected-access", # TODO: enable back
     "too-few-public-methods",
     "line-too-long",
     "too-many-lines",

src/databricks/labs/ucx/account.py

@@ -22,9 +22,9 @@ class AccountWorkspaces:
 
     SYNC_FILE_NAME: ClassVar[str] = "workspaces.json"
 
-    def __init__(self, ac: AccountClient, new_workspace_client=WorkspaceClient):
+    def __init__(self, account_client: AccountClient, new_workspace_client=WorkspaceClient):
         self._new_workspace_client = new_workspace_client
-        self._ac = ac
+        self._ac = account_client
 
     def _workspaces(self):
         return self._ac.workspaces.list()

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

@@ -29,21 +29,21 @@ def _get_cluster_configs_from_all_jobs(all_jobs, all_clusters_by_id):  # pylint:
             if j.settings is None:
                 continue
             if j.settings.job_clusters is not None:
-                for jc in j.settings.job_clusters:
-                    if jc.new_cluster is None:
+                for job_cluster in j.settings.job_clusters:
+                    if job_cluster.new_cluster is None:
                         continue
-                    yield j, jc.new_cluster
+                    yield j, job_cluster.new_cluster
             if j.settings.tasks is None:
                 continue
-            for t in j.settings.tasks:
-                if t.existing_cluster_id is not None:
-                    interactive_cluster = all_clusters_by_id.get(t.existing_cluster_id, None)
+            for task in j.settings.tasks:
+                if task.existing_cluster_id is not None:
+                    interactive_cluster = all_clusters_by_id.get(task.existing_cluster_id, None)
                     if interactive_cluster is None:
                         continue
                     yield j, interactive_cluster
 
-                elif t.new_cluster is not None:
-                    yield j, t.new_cluster
+                elif task.new_cluster is not None:
+                    yield j, task.new_cluster
 
 
 class JobsCrawler(CrawlerBase[JobInfo], JobsMixin, CheckClusterMixin):
@@ -74,7 +74,7 @@ def _assess_jobs(self, all_jobs: list[BaseJob], all_clusters_by_id) -> Iterable[
         return list(job_details.values())
 
     @staticmethod
-    def _prepare(all_jobs):
+    def _prepare(all_jobs) -> tuple[dict[int, set[str]], dict[int, JobInfo]]:
         job_assessment: dict[int, set[str]] = {}
         job_details: dict[int, JobInfo] = {}
         for job in all_jobs:

src/databricks/labs/ucx/azure/access.py

@@ -20,10 +20,16 @@ class StoragePermissionMapping:
 
 
 class AzureResourcePermissions:
-    def __init__(self, installation: Installation, ws: WorkspaceClient, azurerm: AzureResources, lc: ExternalLocations):
+    def __init__(
+        self,
+        installation: Installation,
+        ws: WorkspaceClient,
+        azurerm: AzureResources,
+        external_locations: ExternalLocations,
+    ):
         self._filename = 'azure_storage_account_info.csv'
         self._installation = installation
-        self._locations = lc
+        self._locations = external_locations
         self._azurerm = azurerm
         self._ws = ws
         self._levels = {

src/databricks/labs/ucx/azure/resources.py

@@ -31,9 +31,9 @@ def __init__(self, resource_id: str):
         i = 0
         while i < len(split):
             k = split[i]
-            v = split[i + 1]
+            value = split[i + 1]
             i += 2
-            self._pairs[k] = v
+            self._pairs[k] = value
 
     @property
     def subscription_id(self):

src/databricks/labs/ucx/cli.py

@@ -170,10 +170,10 @@ def revert_migrated_tables(w: WorkspaceClient, schema: str, table: str, *, delet
         question = "You haven't specified a schema or a table. All migrated tables will be reverted. Continue?"
         if not prompts.confirm(question, max_attempts=2):
             return
-    tm = TablesMigrate.for_cli(w)
-    revert = tm.print_revert_report(delete_managed=delete_managed)
+    tables_migrate = TablesMigrate.for_cli(w)
+    revert = tables_migrate.print_revert_report(delete_managed=delete_managed)
     if revert and prompts.confirm("Would you like to continue?", max_attempts=2):
-        tm.revert_migrated_tables(schema, table, delete_managed=delete_managed)
+        tables_migrate.revert_migrated_tables(schema, table, delete_managed=delete_managed)
 
 
 @ucx.command

src/databricks/labs/ucx/configure.py

@@ -21,18 +21,18 @@ def configure(self):
         """User may override standard job clusters with interactive clusters"""
         logger.info("Configuring cluster overrides from existing clusters")
 
-        def is_classic(c) -> bool:
+        def is_classic(cluster_info) -> bool:
             return (
-                c.state == compute.State.RUNNING
-                and c.spark_version >= MINIMUM_SPARK_VERSION
-                and c.data_security_mode == compute.DataSecurityMode.NONE
+                cluster_info.state == compute.State.RUNNING
+                and cluster_info.spark_version >= MINIMUM_SPARK_VERSION
+                and cluster_info.data_security_mode == compute.DataSecurityMode.NONE
             )
 
-        def is_tacl(c) -> bool:
+        def is_tacl(cluster_info) -> bool:
             return (
-                c.state == compute.State.RUNNING
-                and c.spark_version >= MINIMUM_SPARK_VERSION
-                and c.data_security_mode == compute.DataSecurityMode.LEGACY_TABLE_ACL
+                cluster_info.state == compute.State.RUNNING
+                and cluster_info.spark_version >= MINIMUM_SPARK_VERSION
+                and cluster_info.data_security_mode == compute.DataSecurityMode.LEGACY_TABLE_ACL
             )
 
         def build_and_prompt(prompt, clusters):
@@ -44,11 +44,11 @@ def build_and_prompt(prompt, clusters):
         # build list of valid active clusters
         classic_clusters = []
         tacl_clusters = []
-        for c in self._ws.clusters.list(can_use_client="NOTEBOOK"):
-            if is_classic(c):
-                classic_clusters.append(c)
-            if is_tacl(c):
-                tacl_clusters.append(c)
+        for cluster in self._ws.clusters.list(can_use_client="NOTEBOOK"):
+            if is_classic(cluster):
+                classic_clusters.append(cluster)
+            if is_tacl(cluster):
+                tacl_clusters.append(cluster)
 
         preamble = """
         We detected an install issue and

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

@@ -19,6 +19,8 @@
 
 logger = logging.getLogger(__name__)
 
+# pylint: disable=invalid-name
+
 
 @dataclass
 class SimpleQuery:

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

@@ -96,27 +96,27 @@ def skip_table(self, schema: str, table: str):
             self._sql_backend.execute(
                 f"ALTER TABLE {escape_sql_identifier(schema)}.{escape_sql_identifier(table)} SET TBLPROPERTIES('{self.UCX_SKIP_PROPERTY}' = true)"
             )
-        except NotFound as nf:
-            if "[TABLE_OR_VIEW_NOT_FOUND]" in str(nf) or "[DELTA_TABLE_NOT_FOUND]" in str(nf):
+        except NotFound as err:
+            if "[TABLE_OR_VIEW_NOT_FOUND]" in str(err) or "[DELTA_TABLE_NOT_FOUND]" in str(err):
                 logger.error(f"Failed to apply skip marker for Table {schema}.{table}. Table not found.")
             else:
-                logger.error(f"Failed to apply skip marker for Table {schema}.{table}: {nf!s}", exc_info=True)
-        except BadRequest as br:
-            logger.error(f"Failed to apply skip marker for Table {schema}.{table}: {br!s}", exc_info=True)
+                logger.error(f"Failed to apply skip marker for Table {schema}.{table}: {err!s}", exc_info=True)
+        except BadRequest as err:
+            logger.error(f"Failed to apply skip marker for Table {schema}.{table}: {err!s}", exc_info=True)
 
     def skip_schema(self, schema: str):
         # Marks a schema to be skipped in the migration process by applying a table property
         try:
             self._sql_backend.execute(
                 f"ALTER SCHEMA {escape_sql_identifier(schema)} SET DBPROPERTIES('{self.UCX_SKIP_PROPERTY}' = true)"
             )
-        except NotFound as nf:
-            if "[SCHEMA_NOT_FOUND]" in str(nf):
+        except NotFound as err:
+            if "[SCHEMA_NOT_FOUND]" in str(err):
                 logger.error(f"Failed to apply skip marker for Schema {schema}. Schema not found.")
             else:
-                logger.error(nf)
-        except BadRequest as br:
-            logger.error(br)
+                logger.error(err)
+        except BadRequest as err:
+            logger.error(err)
 
     def get_tables_to_migrate(self, tables_crawler: TablesCrawler):
         rules = self.load()

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

@@ -25,15 +25,15 @@
 class TablesMigrate:
     def __init__(
         self,
-        tc: TablesCrawler,
+        tables_crawler: TablesCrawler,
         ws: WorkspaceClient,
         backend: SqlBackend,
-        tm: TableMapping,
+        table_mapping: TableMapping,
     ):
-        self._tc = tc
+        self._tc = tables_crawler
         self._backend = backend
         self._ws = ws
-        self._tm = tm
+        self._tm = table_mapping
         self._seen_tables: dict[str, str] = {}
 
     @classmethod