Merge branch 'datahub-project:master' into master

acryldata · Jul 31, 2024 · 4a54301 · 4a54301
2 parents e6de1e6 + f73149a
commit 4a54301
Show file tree

Hide file tree

Showing 3 changed files with 36 additions and 3 deletions.
diff --git a/...ore/src/main/java/com/linkedin/datahub/graphql/types/chart/mappers/InputFieldsMapper.java b/...ore/src/main/java/com/linkedin/datahub/graphql/types/chart/mappers/InputFieldsMapper.java
@@ -11,7 +11,6 @@
 import javax.annotation.Nullable;
 import lombok.extern.slf4j.Slf4j;
 
-
 @Slf4j
 public class InputFieldsMapper {
 
@@ -40,9 +39,14 @@ public com.linkedin.datahub.graphql.generated.InputFields apply(
                   if (field.hasSchemaFieldUrn()) {
                     fieldResult.setSchemaFieldUrn(field.getSchemaFieldUrn().toString());
                     try {
-                      parentUrn = Urn.createFromString(field.getSchemaFieldUrn().getEntityKey().get(0));
+                      parentUrn =
+                          Urn.createFromString(field.getSchemaFieldUrn().getEntityKey().get(0));
                     } catch (URISyntaxException e) {
-                      log.error("Field urn resolution: failed to extract parentUrn successfully from {}. Falling back to {}", field.getSchemaFieldUrn(), entityUrn, e);
+                      log.error(
+                          "Field urn resolution: failed to extract parentUrn successfully from {}. Falling back to {}",
+                          field.getSchemaFieldUrn(),
+                          entityUrn,
+                          e);
                     }
                   }
                   if (field.hasSchemaField()) {

diff --git a/docs/api/graphql/getting-started.md b/docs/api/graphql/getting-started.md
@@ -27,6 +27,7 @@ For more information on, please refer to the following links."
 - [Querying for Domain of a Dataset](/docs/api/tutorials/domains.md#read-domains)
 - [Querying for Glossary Terms of a Dataset](/docs/api/tutorials/terms.md#read-terms)
 - [Querying for Deprecation of a dataset](/docs/api/tutorials/deprecation.md#read-deprecation)
+- [Querying for all DataJobs that belong to a DataFlow](/docs/lineage/airflow.md#get-all-datajobs-associated-with-a-dataflow)
 
 ### Search
 

diff --git a/docs/lineage/airflow.md b/docs/lineage/airflow.md
@@ -266,6 +266,34 @@ with DAG(
 - ingest this DAG, and it will remove all the obsolete pipelines and tasks from the Datahub based on the `cluster` value set in the `airflow.cfg`
 
 
+## Get all dataJobs associated with a dataFlow
+
+If you are looking to find all tasks (aka DataJobs) that belong to a specific pipeline (aka DataFlow), you can use the following GraphQL query:
+
+```graphql
+query {
+  dataFlow(urn: "urn:li:dataFlow:(airflow,db_etl,prod)") {
+    childJobs: relationships(
+      input: {
+        types: ["IsPartOf"],
+        direction: INCOMING,
+        start: 0,
+        count: 100
+      }
+    ) {
+      total
+      relationships {
+        entity {
+          ... on DataJob {
+            urn
+          }
+        }
+      }
+    }
+  }
+}
+```
+
 ## Emit Lineage Directly
 
 If you can't use the plugin or annotate inlets/outlets, you can also emit lineage using the `DatahubEmitterOperator`.