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/s3): add status aspect for detected s3 datasets #6402

Merged
merged 1 commit into from
Nov 14, 2022
Merged

fix(ingest/s3): add status aspect for detected s3 datasets #6402

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
3 changes: 2 additions & 1 deletion metadata-ingestion/src/datahub/ingestion/source/s3/source.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -63,6 +63,7 @@
from datahub.ingestion.source.s3.profiling import _SingleTableProfiler
from datahub.ingestion.source.s3.report import DataLakeSourceReport
from datahub.ingestion.source.schema_inference import avro, csv_tsv, json, parquet
from datahub.metadata.com.linkedin.pegasus2avro.common import Status
from datahub.metadata.com.linkedin.pegasus2avro.metadata.snapshot import DatasetSnapshot
from datahub.metadata.com.linkedin.pegasus2avro.mxe import MetadataChangeEvent
from datahub.metadata.com.linkedin.pegasus2avro.schema import (
Expand Down Expand Up @@ -536,7 +537,7 @@ def ingest_table(

dataset_snapshot = DatasetSnapshot(
urn=dataset_urn,
aspects=[],
aspects=[Status(removed=False)],
)

customProperties: Optional[Dict[str, str]] = None
Expand Down
5 changes: 5 additions & 0 deletions ...ingestion/tests/integration/s3/golden-files/local/golden_mces_file_without_extension.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,11 @@
"com.linkedin.pegasus2avro.metadata.snapshot.DatasetSnapshot": {
"urn": "urn:li:dataset:(urn:li:dataPlatform:file,test-platform-instance.tests/integration/s3/test_data/local_system/folder_a/folder_aa/folder_aaa/no_extension/small,DEV)",
"aspects": [
{
"com.linkedin.pegasus2avro.common.Status": {
"removed": false
}
},
{
"com.linkedin.pegasus2avro.dataset.DatasetProperties": {
"customProperties": {
Expand Down
10 changes: 10 additions & 0 deletions ...ta-ingestion/tests/integration/s3/golden-files/local/golden_mces_folder_no_partition.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,11 @@
"com.linkedin.pegasus2avro.metadata.snapshot.DatasetSnapshot": {
"urn": "urn:li:dataset:(urn:li:dataPlatform:file,tests/integration/s3/test_data/local_system/folder_a/folder_aa/folder_aaa/food_parquet,UAT)",
"aspects": [
{
"com.linkedin.pegasus2avro.common.Status": {
"removed": false
}
},
{
"com.linkedin.pegasus2avro.dataset.DatasetProperties": {
"customProperties": {
Expand Down Expand Up @@ -685,6 +690,11 @@
"com.linkedin.pegasus2avro.metadata.snapshot.DatasetSnapshot": {
"urn": "urn:li:dataset:(urn:li:dataPlatform:file,tests/integration/s3/test_data/local_system/folder_a/folder_aa/folder_aaa/food_csv,UAT)",
"aspects": [
{
"com.linkedin.pegasus2avro.common.Status": {
"removed": false
}
},
{
"com.linkedin.pegasus2avro.dataset.DatasetProperties": {
"customProperties": {
Expand Down
5 changes: 5 additions & 0 deletions ...tion/tests/integration/s3/golden-files/local/golden_mces_folder_no_partition_exclude.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,11 @@
"com.linkedin.pegasus2avro.metadata.snapshot.DatasetSnapshot": {
"urn": "urn:li:dataset:(urn:li:dataPlatform:file,tests/integration/s3/test_data/local_system/folder_a/folder_aa/folder_aaa/food_parquet,UAT)",
"aspects": [
{
"com.linkedin.pegasus2avro.common.Status": {
"removed": false
}
},
{
"com.linkedin.pegasus2avro.dataset.DatasetProperties": {
"customProperties": {
Expand Down
10 changes: 10 additions & 0 deletions ...ion/tests/integration/s3/golden-files/local/golden_mces_folder_no_partition_filename.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,11 @@
"com.linkedin.pegasus2avro.metadata.snapshot.DatasetSnapshot": {
"urn": "urn:li:dataset:(urn:li:dataPlatform:file,tests/integration/s3/test_data/local_system/folder_a/folder_aa/folder_aaa/food_parquet,UAT)",
"aspects": [
{
"com.linkedin.pegasus2avro.common.Status": {
"removed": false
}
},
{
"com.linkedin.pegasus2avro.dataset.DatasetProperties": {
"customProperties": {
Expand Down Expand Up @@ -685,6 +690,11 @@
"com.linkedin.pegasus2avro.metadata.snapshot.DatasetSnapshot": {
"urn": "urn:li:dataset:(urn:li:dataPlatform:file,tests/integration/s3/test_data/local_system/folder_a/folder_aa/folder_aaa/food_csv,UAT)",
"aspects": [
{
"com.linkedin.pegasus2avro.common.Status": {
"removed": false
}
},
{
"com.linkedin.pegasus2avro.dataset.DatasetProperties": {
"customProperties": {
Expand Down
5 changes: 5 additions & 0 deletions ...gestion/tests/integration/s3/golden-files/local/golden_mces_folder_no_partition_glob.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,11 @@
"com.linkedin.pegasus2avro.metadata.snapshot.DatasetSnapshot": {
"urn": "urn:li:dataset:(urn:li:dataPlatform:file,tests/integration/s3/test_data/local_system/folder_a/folder_aa/folder_aaa/food_parquet,UAT)",
"aspects": [
{
"com.linkedin.pegasus2avro.common.Status": {
"removed": false
}
},
{
"com.linkedin.pegasus2avro.dataset.DatasetProperties": {
"customProperties": {
Expand Down
5 changes: 5 additions & 0 deletions ...ingestion/tests/integration/s3/golden-files/local/golden_mces_folder_partition_basic.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,11 @@
"com.linkedin.pegasus2avro.metadata.snapshot.DatasetSnapshot": {
"urn": "urn:li:dataset:(urn:li:dataPlatform:file,tests/integration/s3/test_data/local_system/folder_a/folder_aa/folder_aaa/pokemon_abilities_json,UAT)",
"aspects": [
{
"com.linkedin.pegasus2avro.common.Status": {
"removed": false
}
},
{
"com.linkedin.pegasus2avro.dataset.DatasetProperties": {
"customProperties": {
Expand Down
5 changes: 5 additions & 0 deletions ...ngestion/tests/integration/s3/golden-files/local/golden_mces_folder_partition_keyval.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,11 @@
"com.linkedin.pegasus2avro.metadata.snapshot.DatasetSnapshot": {
"urn": "urn:li:dataset:(urn:li:dataPlatform:file,tests/integration/s3/test_data/local_system/folder_a/folder_aa/folder_aaa/pokemon_abilities_json,UAT)",
"aspects": [
{
"com.linkedin.pegasus2avro.common.Status": {
"removed": false
}
},
{
"com.linkedin.pegasus2avro.dataset.DatasetProperties": {
"customProperties": {
Expand Down
35 changes: 35 additions & 0 deletions metadata-ingestion/tests/integration/s3/golden-files/local/golden_mces_multiple_files.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,11 @@
"com.linkedin.pegasus2avro.metadata.snapshot.DatasetSnapshot": {
"urn": "urn:li:dataset:(urn:li:dataPlatform:file,test-platform-instance.tests/integration/s3/test_data/local_system/folder_a/folder_aa/folder_aaa/NPS.7.1.package_data_NPS.6.1_ARCN_Lakes_ChemistryData_v1_csv.csv,DEV)",
"aspects": [
{
"com.linkedin.pegasus2avro.common.Status": {
"removed": false
}
},
{
"com.linkedin.pegasus2avro.dataset.DatasetProperties": {
"customProperties": {
Expand Down Expand Up @@ -997,6 +1002,11 @@
"com.linkedin.pegasus2avro.metadata.snapshot.DatasetSnapshot": {
"urn": "urn:li:dataset:(urn:li:dataPlatform:file,test-platform-instance.tests/integration/s3/test_data/local_system/folder_a/folder_aa/folder_aaa/chord_progressions_avro.avro,DEV)",
"aspects": [
{
"com.linkedin.pegasus2avro.common.Status": {
"removed": false
}
},
{
"com.linkedin.pegasus2avro.dataset.DatasetProperties": {
"customProperties": {
Expand Down Expand Up @@ -1132,6 +1142,11 @@
"com.linkedin.pegasus2avro.metadata.snapshot.DatasetSnapshot": {
"urn": "urn:li:dataset:(urn:li:dataPlatform:file,test-platform-instance.tests/integration/s3/test_data/local_system/folder_a/folder_aa/folder_aaa/chord_progressions_csv.csv,DEV)",
"aspects": [
{
"com.linkedin.pegasus2avro.common.Status": {
"removed": false
}
},
{
"com.linkedin.pegasus2avro.dataset.DatasetProperties": {
"customProperties": {
Expand Down Expand Up @@ -1267,6 +1282,11 @@
"com.linkedin.pegasus2avro.metadata.snapshot.DatasetSnapshot": {
"urn": "urn:li:dataset:(urn:li:dataPlatform:file,test-platform-instance.tests/integration/s3/test_data/local_system/folder_a/folder_aa/folder_aaa/countries_json.json,DEV)",
"aspects": [
{
"com.linkedin.pegasus2avro.common.Status": {
"removed": false
}
},
{
"com.linkedin.pegasus2avro.dataset.DatasetProperties": {
"customProperties": {
Expand Down Expand Up @@ -1378,6 +1398,11 @@
"com.linkedin.pegasus2avro.metadata.snapshot.DatasetSnapshot": {
"urn": "urn:li:dataset:(urn:li:dataPlatform:file,test-platform-instance.tests/integration/s3/test_data/local_system/folder_a/folder_aa/folder_aaa/food_parquet.parquet,DEV)",
"aspects": [
{
"com.linkedin.pegasus2avro.common.Status": {
"removed": false
}
},
{
"com.linkedin.pegasus2avro.dataset.DatasetProperties": {
"customProperties": {
Expand Down Expand Up @@ -1513,6 +1538,11 @@
"com.linkedin.pegasus2avro.metadata.snapshot.DatasetSnapshot": {
"urn": "urn:li:dataset:(urn:li:dataPlatform:file,test-platform-instance.tests/integration/s3/test_data/local_system/folder_a/folder_aa/folder_aaa/small.csv,DEV)",
"aspects": [
{
"com.linkedin.pegasus2avro.common.Status": {
"removed": false
}
},
{
"com.linkedin.pegasus2avro.dataset.DatasetProperties": {
"customProperties": {
Expand Down Expand Up @@ -1648,6 +1678,11 @@
"com.linkedin.pegasus2avro.metadata.snapshot.DatasetSnapshot": {
"urn": "urn:li:dataset:(urn:li:dataPlatform:file,test-platform-instance.tests/integration/s3/test_data/local_system/folder_a/folder_aa/folder_aaa/wa_fn_usec_hr_employee_attrition_csv.csv,DEV)",
"aspects": [
{
"com.linkedin.pegasus2avro.common.Status": {
"removed": false
}
},
{
"com.linkedin.pegasus2avro.dataset.DatasetProperties": {
"customProperties": {
Expand Down
10 changes: 10 additions & 0 deletions ...ngestion/tests/integration/s3/golden-files/local/golden_mces_multiple_spec_for_files.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,11 @@
"com.linkedin.pegasus2avro.metadata.snapshot.DatasetSnapshot": {
"urn": "urn:li:dataset:(urn:li:dataPlatform:file,tests/integration/s3/test_data/local_system/folder_a/folder_aa/folder_aaa/chord_progressions_avro.avro,PROD)",
"aspects": [
{
"com.linkedin.pegasus2avro.common.Status": {
"removed": false
}
},
{
"com.linkedin.pegasus2avro.dataset.DatasetProperties": {
"customProperties": {
Expand Down Expand Up @@ -685,6 +690,11 @@
"com.linkedin.pegasus2avro.metadata.snapshot.DatasetSnapshot": {
"urn": "urn:li:dataset:(urn:li:dataPlatform:file,tests/integration/s3/test_data/local_system/folder_a/folder_aa/folder_aaa/chord_progressions_csv.csv,PROD)",
"aspects": [
{
"com.linkedin.pegasus2avro.common.Status": {
"removed": false
}
},
{
"com.linkedin.pegasus2avro.dataset.DatasetProperties": {
"customProperties": {
Expand Down
5 changes: 5 additions & 0 deletions metadata-ingestion/tests/integration/s3/golden-files/local/golden_mces_single_file.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,11 @@
"com.linkedin.pegasus2avro.metadata.snapshot.DatasetSnapshot": {
"urn": "urn:li:dataset:(urn:li:dataPlatform:file,tests/integration/s3/test_data/local_system/folder_a/folder_aa/folder_aaa/chord_progressions_avro.avro,PROD)",
"aspects": [
{
"com.linkedin.pegasus2avro.common.Status": {
"removed": false
}
},
{
"com.linkedin.pegasus2avro.dataset.DatasetProperties": {
"customProperties": {
Expand Down
5 changes: 5 additions & 0 deletions ...ta-ingestion/tests/integration/s3/golden-files/s3/golden_mces_file_without_extension.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,11 @@
"com.linkedin.pegasus2avro.metadata.snapshot.DatasetSnapshot": {
"urn": "urn:li:dataset:(urn:li:dataPlatform:s3,test-platform-instance.my-test-bucket/folder_a/folder_aa/folder_aaa/no_extension/small,DEV)",
"aspects": [
{
"com.linkedin.pegasus2avro.common.Status": {
"removed": false
}
},
{
"com.linkedin.pegasus2avro.dataset.DatasetProperties": {
"customProperties": {
Expand Down
10 changes: 10 additions & 0 deletions metadata-ingestion/tests/integration/s3/golden-files/s3/golden_mces_folder_no_partition.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,11 @@
"com.linkedin.pegasus2avro.metadata.snapshot.DatasetSnapshot": {
"urn": "urn:li:dataset:(urn:li:dataPlatform:s3,my-test-bucket/folder_a/folder_aa/folder_aaa/food_csv,UAT)",
"aspects": [
{
"com.linkedin.pegasus2avro.common.Status": {
"removed": false
}
},
{
"com.linkedin.pegasus2avro.dataset.DatasetProperties": {
"customProperties": {},
Expand Down Expand Up @@ -388,6 +393,11 @@
"com.linkedin.pegasus2avro.metadata.snapshot.DatasetSnapshot": {
"urn": "urn:li:dataset:(urn:li:dataPlatform:s3,my-test-bucket/folder_a/folder_aa/folder_aaa/food_parquet,UAT)",
"aspects": [
{
"com.linkedin.pegasus2avro.common.Status": {
"removed": false
}
},
{
"com.linkedin.pegasus2avro.dataset.DatasetProperties": {
"customProperties": {},
Expand Down
5 changes: 5 additions & 0 deletions ...gestion/tests/integration/s3/golden-files/s3/golden_mces_folder_no_partition_exclude.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,11 @@
"com.linkedin.pegasus2avro.metadata.snapshot.DatasetSnapshot": {
"urn": "urn:li:dataset:(urn:li:dataPlatform:s3,my-test-bucket/folder_a/folder_aa/folder_aaa/food_parquet,UAT)",
"aspects": [
{
"com.linkedin.pegasus2avro.common.Status": {
"removed": false
}
},
{
"com.linkedin.pegasus2avro.dataset.DatasetProperties": {
"customProperties": {},
Expand Down
10 changes: 10 additions & 0 deletions ...estion/tests/integration/s3/golden-files/s3/golden_mces_folder_no_partition_filename.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,11 @@
"com.linkedin.pegasus2avro.metadata.snapshot.DatasetSnapshot": {
"urn": "urn:li:dataset:(urn:li:dataPlatform:s3,my-test-bucket/folder_a/folder_aa/folder_aaa/food_csv,UAT)",
"aspects": [
{
"com.linkedin.pegasus2avro.common.Status": {
"removed": false
}
},
{
"com.linkedin.pegasus2avro.dataset.DatasetProperties": {
"customProperties": {},
Expand Down Expand Up @@ -388,6 +393,11 @@
"com.linkedin.pegasus2avro.metadata.snapshot.DatasetSnapshot": {
"urn": "urn:li:dataset:(urn:li:dataPlatform:s3,my-test-bucket/folder_a/folder_aa/folder_aaa/food_parquet,UAT)",
"aspects": [
{
"com.linkedin.pegasus2avro.common.Status": {
"removed": false
}
},
{
"com.linkedin.pegasus2avro.dataset.DatasetProperties": {
"customProperties": {},
Expand Down
5 changes: 5 additions & 0 deletions ...-ingestion/tests/integration/s3/golden-files/s3/golden_mces_folder_no_partition_glob.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,11 @@
"com.linkedin.pegasus2avro.metadata.snapshot.DatasetSnapshot": {
"urn": "urn:li:dataset:(urn:li:dataPlatform:s3,my-test-bucket/folder_a/folder_aa/folder_aaa/food_parquet,UAT)",
"aspects": [
{
"com.linkedin.pegasus2avro.common.Status": {
"removed": false
}
},
{
"com.linkedin.pegasus2avro.dataset.DatasetProperties": {
"customProperties": {},
Expand Down
5 changes: 5 additions & 0 deletions ...ta-ingestion/tests/integration/s3/golden-files/s3/golden_mces_folder_partition_basic.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,11 @@
"com.linkedin.pegasus2avro.metadata.snapshot.DatasetSnapshot": {
"urn": "urn:li:dataset:(urn:li:dataPlatform:s3,my-test-bucket/folder_a/folder_aa/folder_aaa/pokemon_abilities_json,UAT)",
"aspects": [
{
"com.linkedin.pegasus2avro.common.Status": {
"removed": false
}
},
{
"com.linkedin.pegasus2avro.dataset.DatasetProperties": {
"customProperties": {},
Expand Down
5 changes: 5 additions & 0 deletions ...a-ingestion/tests/integration/s3/golden-files/s3/golden_mces_folder_partition_keyval.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,11 @@
"com.linkedin.pegasus2avro.metadata.snapshot.DatasetSnapshot": {
"urn": "urn:li:dataset:(urn:li:dataPlatform:s3,my-test-bucket/folder_a/folder_aa/folder_aaa/pokemon_abilities_json,UAT)",
"aspects": [
{
"com.linkedin.pegasus2avro.common.Status": {
"removed": false
}
},
{
"com.linkedin.pegasus2avro.dataset.DatasetProperties": {
"customProperties": {},
Expand Down
Loading