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/mode): move sql logic to view properties aspect #12196

Merged
merged 1 commit into from
Dec 23, 2024
Merged

fix(ingest/mode): move sql logic to view properties aspect #12196

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
21 changes: 14 additions & 7 deletions metadata-ingestion/src/datahub/ingestion/source/mode.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -98,6 +98,7 @@
TagPropertiesClass,
UpstreamClass,
UpstreamLineageClass,
ViewPropertiesClass,
)
from datahub.metadata.urns import QueryUrn
from datahub.sql_parsing.sqlglot_lineage import (
Expand Down Expand Up @@ -930,16 +931,13 @@ def construct_query_or_dataset(

dataset_props = DatasetPropertiesClass(
name=report_info.get("name") if is_mode_dataset else query_data.get("name"),
description=f"""### Source Code
``` sql
{query_data.get("raw_query")}
```
""",
description=None,
externalUrl=externalUrl,
customProperties=self.get_custom_props_from_dict(
query_data,
[
"id" "created_at",
Copy link
Collaborator

Choose a reason for hiding this comment

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

Woah, nice catch

"id",
"created_at",
"updated_at",
"last_run_id",
"data_source_id",
Expand All @@ -949,14 +947,23 @@ def construct_query_or_dataset(
],
),
)

yield (
MetadataChangeProposalWrapper(
entityUrn=query_urn,
aspect=dataset_props,
).as_workunit()
)

if raw_query := query_data.get("raw_query"):
yield MetadataChangeProposalWrapper(
entityUrn=query_urn,
aspect=ViewPropertiesClass(
viewLogic=raw_query,
viewLanguage=QueryLanguageClass.SQL,
materialized=False,
),
).as_workunit()

if is_mode_dataset:
space_container_key = self.gen_space_key(space_token)
yield from add_dataset_to_container(
Expand Down
43 changes: 41 additions & 2 deletions metadata-ingestion/tests/integration/mode/mode_mces_golden.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -176,6 +176,7 @@
"datasets": [
"urn:li:dataset:(urn:li:dataPlatform:mode,5450544,PROD)"
],
"dashboards": [],
"lastModified": {
"created": {
"time": 1639169724316,
Expand Down Expand Up @@ -253,14 +254,15 @@
"aspect": {
"json": {
"customProperties": {
"id": "19780522",
"created_at": "2024-09-02T07:38:43.755Z",
"updated_at": "2024-09-02T07:40:44.046Z",
"last_run_id": "3535709679",
"data_source_id": "44763",
"report_imports_count": "2"
},
"externalUrl": "https://app.mode.com/acryl/datasets/24f66e1701b6",
"name": "Dataset 1",
"description": "### Source Code\n``` sql\n-- Returns first 100 rows from DATAHUB_COMMUNITY.POSTGRES_PUBLIC.COMPANY\n SELECT \n\t\tAGE,\n\t\tID,\n\t\tNAME,\n\t\t_FIVETRAN_DELETED,\n\t\t_FIVETRAN_SYNCED\n FROM DATAHUB_COMMUNITY.POSTGRES_PUBLIC.COMPANY LIMIT 100;\n\n-- Returns first 100 rows from ETHAN_TEST_DB.PUBLIC.ACCOUNT_PHONE_NUMBER\n SELECT \n\t\tCOMMUNICATION_ACCOUNT_ID,\n\t\tID,\n\t\tMMS_CAPABLE,\n\t\tPHONE_NUMBER,\n\t\tSMS_CAPABLE,\n\t\tSTATUS,\n\t\tSTATUS_TLM,\n\t\tTLM,\n\t\tVOICE_CAPABLE,\n\t\tWHEN_CREATED\n FROM ETHAN_TEST_DB.PUBLIC.ACCOUNT_PHONE_NUMBER LIMIT 100;\n \n \n```\n ",
"tags": []
}
},
Expand All @@ -270,6 +272,24 @@
"lastRunId": "no-run-id-provided"
}
},
{
"entityType": "dataset",
"entityUrn": "urn:li:dataset:(urn:li:dataPlatform:mode,5450544,PROD)",
"changeType": "UPSERT",
"aspectName": "viewProperties",
"aspect": {
"json": {
"materialized": false,
"viewLogic": "-- Returns first 100 rows from DATAHUB_COMMUNITY.POSTGRES_PUBLIC.COMPANY\n SELECT \n\t\tAGE,\n\t\tID,\n\t\tNAME,\n\t\t_FIVETRAN_DELETED,\n\t\t_FIVETRAN_SYNCED\n FROM DATAHUB_COMMUNITY.POSTGRES_PUBLIC.COMPANY LIMIT 100;\n\n-- Returns first 100 rows from ETHAN_TEST_DB.PUBLIC.ACCOUNT_PHONE_NUMBER\n SELECT \n\t\tCOMMUNICATION_ACCOUNT_ID,\n\t\tID,\n\t\tMMS_CAPABLE,\n\t\tPHONE_NUMBER,\n\t\tSMS_CAPABLE,\n\t\tSTATUS,\n\t\tSTATUS_TLM,\n\t\tTLM,\n\t\tVOICE_CAPABLE,\n\t\tWHEN_CREATED\n FROM ETHAN_TEST_DB.PUBLIC.ACCOUNT_PHONE_NUMBER LIMIT 100;\n \n ",
"viewLanguage": "SQL"
}
},
"systemMetadata": {
"lastObserved": 1638860400000,
"runId": "mode-test",
"lastRunId": "no-run-id-provided"
}
},
{
"entityType": "dataset",
"entityUrn": "urn:li:dataset:(urn:li:dataPlatform:mode,5450544,PROD)",
Expand Down Expand Up @@ -336,13 +356,14 @@
"aspect": {
"json": {
"customProperties": {
"id": "10149707",
"created_at": "2021-12-10T20:55:24.361Z",
"updated_at": "2021-12-10T23:12:53.273Z",
"last_run_id": "1897576958",
"data_source_id": "34499"
},
"externalUrl": "https://app.mode.com/acryl/reports/9d2da37fa91e/details/queries/6e26a9f3d4e2",
"name": "Customer and staff",
"description": "### Source Code\n``` sql\nSELECT rental.*, staff.first_name \"Staff First Name\", staff.last_name \"Staff Last Name\" FROM {{ @join_on_definition as rental }} join staff on staff.staff_id = rental.staff_id where selected_id = {{ selected_id }} \n{% form %}\nselected_id:\n type: text\n default: my_id\n{% endform %}\n```\n ",
"tags": []
}
},
Expand All @@ -352,6 +373,24 @@
"lastRunId": "no-run-id-provided"
}
},
{
"entityType": "dataset",
"entityUrn": "urn:li:dataset:(urn:li:dataPlatform:mode,10149707,PROD)",
"changeType": "UPSERT",
"aspectName": "viewProperties",
"aspect": {
"json": {
"materialized": false,
"viewLogic": "SELECT rental.*, staff.first_name \"Staff First Name\", staff.last_name \"Staff Last Name\" FROM {{ @join_on_definition as rental }} join staff on staff.staff_id = rental.staff_id where selected_id = {{ selected_id }} \n{% form %}\nselected_id:\n type: text\n default: my_id\n{% endform %}",
"viewLanguage": "SQL"
}
},
"systemMetadata": {
"lastObserved": 1638860400000,
"runId": "mode-test",
"lastRunId": "no-run-id-provided"
}
},
{
"entityType": "dataset",
"entityUrn": "urn:li:dataset:(urn:li:dataPlatform:mode,10149707,PROD)",
Expand Down
Loading