Skip to content
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

fix(ingest): omit schema fields when name is absent #5275

Merged
merged 1 commit into from
Jul 5, 2022
Merged

fix(ingest): omit schema fields when name is absent #5275

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
29 changes: 18 additions & 11 deletions metadata-ingestion/src/datahub/ingestion/source/tableau.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -330,7 +330,7 @@ def emit_workbooks(self) -> Iterable[MetadataWorkUnit]:
yield from self.emit_sheets_as_charts(workbook)
yield from self.emit_dashboards(workbook)
yield from self.emit_embedded_datasource(workbook)
yield from self.emit_upstream_tables()
yield from self.emit_upstream_tables()
Copy link
Contributor

Choose a reason for hiding this comment

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

intentional?

Copy link
Collaborator Author

Choose a reason for hiding this comment

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

yes, this will fix multiple emits of upstream tables. we should emit only once at the end.


def _track_custom_sql_ids(self, field: dict) -> None:
# Tableau shows custom sql datasource as a table in ColumnField.
Expand Down Expand Up @@ -551,28 +551,31 @@ def emit_custom_sql_datasources(self) -> Iterable[MetadataWorkUnit]:
def get_schema_metadata_for_custom_sql(
self, columns: List[dict]
) -> Optional[SchemaMetadata]:
fields = []
schema_metadata = None
for field in columns:
# Datasource fields
fields = []

if field.get("name") is None:
continue
nativeDataType = field.get("remoteType", "UNKNOWN")
TypeClass = FIELD_TYPE_MAPPING.get(nativeDataType, NullTypeClass)
schema_field = SchemaField(
fieldPath=field.get("name", ""),
fieldPath=field["name"],
type=SchemaFieldDataType(type=TypeClass()),
nativeDataType=nativeDataType,
description=field.get("description", ""),
)
fields.append(schema_field)

schema_metadata = SchemaMetadata(
schemaName="test",
platform=f"urn:li:dataPlatform:{self.platform}",
version=0,
fields=fields,
hash="",
platformSchema=OtherSchema(rawSchema=""),
)
schema_metadata = SchemaMetadata(
schemaName="test",
platform=f"urn:li:dataPlatform:{self.platform}",
version=0,
fields=fields,
hash="",
platformSchema=OtherSchema(rawSchema=""),
)
return schema_metadata

def _create_lineage_from_csql_datasource(
Expand Down Expand Up @@ -634,6 +637,8 @@ def _get_schema_metadata_for_datasource(
for field in datasource_fields:
# check datasource - custom sql relations from a field being referenced
self._track_custom_sql_ids(field)
if field.get("name") is None:
continue

nativeDataType = field.get("dataType", "UNKNOWN")
TypeClass = FIELD_TYPE_MAPPING.get(nativeDataType, NullTypeClass)
Expand Down Expand Up @@ -865,6 +870,8 @@ def emit_upstream_tables(self) -> Iterable[MetadataWorkUnit]:
if columns:
fields = []
for field in columns:
if field.get("name") is None:
continue
nativeDataType = field.get("remoteType", "UNKNOWN")
TypeClass = FIELD_TYPE_MAPPING.get(nativeDataType, NullTypeClass)

Expand Down
18 changes: 18 additions & 0 deletions metadata-ingestion/tests/integration/tableau/setup/workbooksConnection_all.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1522,6 +1522,24 @@
}
]
},
{
"__typename": "ColumnField",
"id": "xxxdc8ee-30e5-644b-cf76-48a3dea79cda",
"name": null,
"description": null,
"isHidden": false,
"folderName": null,
"dataCategory": "NOMINAL",
"role": "DIMENSION",
"dataType": "STRING",
"defaultFormat": null,
"aggregation": null,
"columns": [
{
"table": {}
}
]
},
{
"__typename": "ColumnField",
"id": "277dc8ee-30e5-644b-cf76-48a3dea79cda",
Expand Down
Loading