yujunjun/datahub
2
0
Fork 0
mirror of https://github.com/datahub-project/datahub.git synced 2025-11-12 01:11:41 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs(ingest/glue): add permissions for glue (#12290)

Browse Source
This commit is contained in:
Aseem Bansal 2025-01-10 16:24:29 +05:30 committed by GitHub
parent efc5d31f03
commit a92a10770e
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 14 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
metadata-ingestion/src/datahub/ingestion/source/aws/glue.py
View File

@ -248,6 +248,9 @@ class GlueSourceReport(StaleEntityRemovalSourceReport):
"Enabled by default when stateful ingestion is turned on.", "Enabled by default when stateful ingestion is turned on.",
) )
@capability(SourceCapability.LINEAGE_COARSE, "Enabled by default") @capability(SourceCapability.LINEAGE_COARSE, "Enabled by default")
@capability(
SourceCapability.LINEAGE_FINE, "Support via the `emit_s3_lineage` config field"
)
class GlueSource(StatefulIngestionSourceBase): class GlueSource(StatefulIngestionSourceBase):
""" """
Note: if you also have files in S3 that you'd like to ingest, we recommend you use Glue's built-in data catalog. See [here](../../../../docs/generated/ingestion/sources/s3.md) for a quick guide on how to set up a crawler on Glue and ingest the outputs with DataHub. Note: if you also have files in S3 that you'd like to ingest, we recommend you use Glue's built-in data catalog. See [here](../../../../docs/generated/ingestion/sources/s3.md) for a quick guide on how to set up a crawler on Glue and ingest the outputs with DataHub.
@ -284,12 +287,22 @@ class GlueSource(StatefulIngestionSourceBase):
"Action": [ "Action": [
"glue:GetDataflowGraph", "glue:GetDataflowGraph",
"glue:GetJobs", "glue:GetJobs",
"s3:GetObject",
], ],
"Resource": "*" "Resource": "*"
} }
``` ```
plus `s3:GetObject` for the job script locations. For profiling datasets, the following additional permissions are required:
```json
{
"Effect": "Allow",
"Action": [
"glue:GetPartitions",
],
"Resource": "*"
}
```
""" """