Skip to content

fix(bigquery): apply case normalization consistently for temp table inference #15252

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

Merged
merged 10 commits into from
Nov 24, 2025
Merged

fix(bigquery): apply case normalization consistently for temp table inference #15252

Show file tree
Hide file tree
Changes from 7 commits
Commits
Show all changes
10 commits
Select commit Hold shift + click to select a range
b05793e
debug(bigquery): add debug logging for temp table inference issue
sgomezvillamor Nov 10, 2025
784dc09
fix: standardize case in temp table lookup to match discovered_tables
sgomezvillamor Nov 13, 2025
c176ba5
fix: apply case normalization consistently in is_allowed_table method
sgomezvillamor Nov 18, 2025
77c8c4a
Merge branch 'master' into debug/bigquery-temp-table-inference
sgomezvillamor Nov 18, 2025
53bec30
Merge branch 'master' into debug/bigquery-temp-table-inference
sgomezvillamor Nov 18, 2025
5c119be
cleanup: remove verbose debug logging while keeping useful temp table…
sgomezvillamor Nov 22, 2025
1c2b0a2
Merge branch 'master' into debug/bigquery-temp-table-inference
sgomezvillamor Nov 22, 2025
812ef3f
Update queries_extractor.py
sgomezvillamor Nov 24, 2025
773258c
Merge branch 'master' into debug/bigquery-temp-table-inference
sgomezvillamor Nov 24, 2025
634a5b2
Merge branch 'master' into debug/bigquery-temp-table-inference
sgomezvillamor Nov 24, 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
41 changes: 37 additions & 4 deletions metadata-ingestion/src/datahub/ingestion/source/bigquery_v2/bigquery_schema_gen.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -527,19 +527,32 @@ def _process_schema(
)
elif self.store_table_refs:
# Need table_refs to calculate lineage and usage
logger.debug(
f"Lightweight table discovery for dataset {dataset_name} in project {project_id}"
)
for table_item in self.schema_api.list_tables(dataset_name, project_id):
table_type = getattr(table_item, "table_type", "UNKNOWN")

identifier = BigqueryTableIdentifier(
project_id=project_id,
dataset=dataset_name,
table=table_item.table_id,
)

logger.debug(f"Processing {table_type}: {identifier.raw_table_name()}")

if not self.config.table_pattern.allowed(identifier.raw_table_name()):
logger.debug(
f"Dropped by table_pattern: {identifier.raw_table_name()}"
)
self.report.report_dropped(identifier.raw_table_name())
continue
try:
self.table_refs.add(
str(BigQueryTableRef(identifier).get_sanitized_table_ref())
table_ref = str(
BigQueryTableRef(identifier).get_sanitized_table_ref()
)
self.table_refs.add(table_ref)
logger.debug(f"Added to table_refs: {table_ref}")
except Exception as e:
logger.warning(
f"Could not create table ref for {table_item.path}: {e}"
Expand Down Expand Up @@ -628,14 +641,24 @@ def _process_table(
table_identifier = BigqueryTableIdentifier(project_id, dataset_name, table.name)

self.report.report_entity_scanned(table_identifier.raw_table_name())
logger.debug(
f"Full schema processing - Scanning TABLE: {table_identifier.raw_table_name()}"
)

if not self.config.table_pattern.allowed(table_identifier.raw_table_name()):
logger.debug(
f"Full schema processing - Dropped TABLE by table_pattern: {table_identifier.raw_table_name()}"
)
self.report.report_dropped(table_identifier.raw_table_name())
return

if self.store_table_refs:
self.table_refs.add(
str(BigQueryTableRef(table_identifier).get_sanitized_table_ref())
table_ref = str(
BigQueryTableRef(table_identifier).get_sanitized_table_ref()
)
self.table_refs.add(table_ref)
logger.debug(
f"Full schema processing - Added TABLE to table_refs: {table_ref}"
)
table.column_count = len(columns)

Expand Down Expand Up @@ -668,13 +691,20 @@ def _process_view(
table_identifier = BigqueryTableIdentifier(project_id, dataset_name, view.name)

self.report.report_entity_scanned(table_identifier.raw_table_name(), "view")
logger.debug(
f"Full schema processing - Scanning VIEW: {table_identifier.raw_table_name()}"
)

if not self.config.view_pattern.allowed(table_identifier.raw_table_name()):
logger.debug(
f"Full schema processing - Dropped VIEW by view_pattern: {table_identifier.raw_table_name()}"
)
self.report.report_dropped(table_identifier.raw_table_name())
return

table_ref = str(BigQueryTableRef(table_identifier).get_sanitized_table_ref())
self.table_refs.add(table_ref)
logger.debug(f"Full schema processing - Added VIEW to table_refs: {table_ref}")
if view.view_definition:
self.view_refs_by_project[project_id].add(table_ref)
self.view_definitions[table_ref] = view.view_definition
Expand Down Expand Up @@ -720,6 +750,9 @@ def _process_snapshot(

table_ref = str(BigQueryTableRef(table_identifier).get_sanitized_table_ref())
self.table_refs.add(table_ref)
logger.debug(
f"Full schema processing - Added SNAPSHOT to table_refs: {table_ref}"
)
if snapshot.base_table_identifier:
self.snapshot_refs_by_project[project_id].add(table_ref)
self.snapshots_by_ref[table_ref] = snapshot
Expand Down
15 changes: 12 additions & 3 deletions metadata-ingestion/src/datahub/ingestion/source/bigquery_v2/queries_extractor.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -245,12 +245,18 @@ def is_temp_table(self, name: str) -> bool:
# 1. this name would be allowed by the dataset patterns, and
# 2. we have a list of discovered tables, and
# 3. it's not in the discovered tables list

if (
self.filters.is_allowed(table)
and self.discovered_tables
and str(BigQueryTableRef(table)) not in self.discovered_tables
and self.identifiers.standardize_identifier_case(
str(BigQueryTableRef(table))
)
not in self.discovered_tables
):
logger.debug(f"inferred as temp table {name}")
logger.debug(
f"Inferred as temp table {name} (is_allowed?{self.filters.is_allowed(table)}"
Copy link
Contributor

@treff7es treff7es Nov 24, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Is this correct?
A parenthesis is missing for sure, but I'm unsure if you wanted is_allowed there as a string with a question mark.

Copy link
Contributor Author

@sgomezvillamor sgomezvillamor Nov 24, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I like using question mark for booleans 😅

indeed, parenthesis was missed, nice catch!

)
self.report.inferred_temp_tables.add(name)
return True

Expand All @@ -263,7 +269,10 @@ def is_allowed_table(self, name: str) -> bool:
table = BigqueryTableIdentifier.from_string_name(name)
if (
self.discovered_tables
and str(BigQueryTableRef(table)) not in self.discovered_tables
and self.identifiers.standardize_identifier_case(
str(BigQueryTableRef(table))
)
not in self.discovered_tables
):
logger.debug(f"not allowed table {name}")
return False
Expand Down
Loading