Skip to content

Extend UCX schema scope limitation by allowing schema prefixes #4436

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
wants to merge 2 commits into
base: main
Choose a base branch
from
Draft

Extend UCX schema scope limitation by allowing schema prefixes #4436

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
5070237
Add a config to config.yml for database prefixes to limit the crawlin…
pritishpai Sep 23, 2025
e93a065
Add prompts during installation
pritishpai Sep 23, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions src/databricks/labs/ucx/config.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47,6 +47,8 @@ class WorkspaceConfig: # pylint: disable=too-many-instance-attributes

# Whether the assessment should capture a specific list of databases, if not specified, it will list all databases.
include_databases: list[str] | None = None
# Whether the assessment should capture databases matching specific prefixes, if not specified, it will list all databases.
include_database_prefixes: list[str] | None = None

# Whether the tables in mounts crawler should crawl a specific list of mounts.
# If not specified, it will list all mounts.
Expand Down
12 changes: 12 additions & 0 deletions src/databricks/labs/ucx/install.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -243,6 +243,7 @@ def _prompt_for_new_installation(self) -> WorkspaceConfig:
configure_groups = ConfigureGroups(self.prompts)
configure_groups.run()
include_databases = self._select_databases()
include_database_prefixes = self._select_database_prefixes()

skip_tacl_migration = self.prompts.confirm("Do you want to skip TACL migration when migrating tables?")

Expand Down Expand Up @@ -272,6 +273,7 @@ def _prompt_for_new_installation(self) -> WorkspaceConfig:
log_level=log_level,
num_threads=num_threads,
include_databases=include_databases,
include_database_prefixes=include_database_prefixes,
trigger_job=trigger_job,
recon_tolerance_percent=recon_tolerance_percent,
upload_dependencies=upload_dependencies,
Expand Down Expand Up @@ -428,6 +430,16 @@ def _select_databases(self):
return [x.strip() for x in selected_databases.split(",")]
return None

def _select_database_prefixes(self):
selected_prefixes = self.prompts.question(
"Comma-separated list of database prefixes to include (e.g., 'dev_', 'test_'). "
"If not specified, prefix filtering will not be applied",
default="<NONE>",
)
if selected_prefixes != "<NONE>":
return [x.strip() for x in selected_prefixes.split(",")]
return None

def configure_warehouse(self) -> str:
def warehouse_type(_):
return _.warehouse_type.value if not _.enable_serverless_compute else "SERVERLESS"
Expand Down