cherry pick #24041: fixing BigQuery Query retry vulnerability (#24095)

ahmedabu98 · web-flow · commit 9a9438130d90 · 2022-11-10T15:26:16.000-08:00
* add random string at the end of query job name

* use deterministic temp table name
diff --git a/sdks/java/io/google-cloud-platform/src/main/java/org/apache/beam/sdk/io/gcp/bigquery/BigQueryQueryHelper.java b/sdks/java/io/google-cloud-platform/src/main/java/org/apache/beam/sdk/io/gcp/bigquery/BigQueryQueryHelper.java
@@ -119,16 +119,21 @@ public static TableReference executeQuery(
       }
 
       // Step 2: Create a temporary dataset in the query location only if the user has not specified
-      // a temp dataset.
-      String queryJobId =
+      // a temp dataset. The temp table name may be deterministic but the query job ID has to be
+      // non-deterministic to protect against retries. If BigQuery sees a repeated query job ID, it
+      // will be skipped.
+      String tempTableID =
           BigQueryResourceNaming.createJobIdPrefix(options.getJobName(), stepUuid, JobType.QUERY);
+      String queryJobId =
+          BigQueryResourceNaming.createJobIdPrefix(
+              options.getJobName(), stepUuid, JobType.QUERY, BigQueryHelpers.randomUUIDString());
       Optional<String> queryTempDatasetOpt = Optional.ofNullable(queryTempDatasetId);
       TableReference queryResultTable =
           createTempTableReference(
               options.getBigQueryProject() == null
                   ? options.getProject()
                   : options.getBigQueryProject(),
-              queryJobId,
+              tempTableID,
               queryTempDatasetOpt);
 
       boolean beamToCreateTempDataset = !queryTempDatasetOpt.isPresent();
