lokeshj1703 commented on code in PR #8574:
URL: https://github.com/apache/hudi/pull/8574#discussion_r1192120284


##########
hudi-utilities/src/test/java/org/apache/hudi/utilities/deltastreamer/TestTransformer.java:
##########
@@ -79,6 +96,71 @@ public void testMultipleTransformersWithIdentifiers() throws 
Exception {
     assertEquals(0, 
sqlContext.read().format("org.apache.hudi").load(tableBasePath).where("timestamp
 != 110").count());
   }
 
+  @Test
+  public void testTransformerSchemaValidation() throws Exception {
+    List<String> transformerClassNames = Arrays.asList(
+        FlatteningTransformerWithTransformedSchema.class.getName(),
+        TimestampTransformer.class.getName(),
+        AddColumnTransformerWithTransformedSchema.class.getName());
+    runDeltaStreamerWithTransformers(transformerClassNames);
+  }
+
+  @Test
+  public void testTransformerSchemaValidationFails() throws Exception {

Review Comment:
   Addressed.



##########
hudi-utilities/src/test/java/org/apache/hudi/utilities/deltastreamer/TestTransformer.java:
##########
@@ -79,6 +96,71 @@ public void testMultipleTransformersWithIdentifiers() throws 
Exception {
     assertEquals(0, 
sqlContext.read().format("org.apache.hudi").load(tableBasePath).where("timestamp
 != 110").count());
   }
 
+  @Test
+  public void testTransformerSchemaValidation() throws Exception {
+    List<String> transformerClassNames = Arrays.asList(
+        FlatteningTransformerWithTransformedSchema.class.getName(),
+        TimestampTransformer.class.getName(),
+        AddColumnTransformerWithTransformedSchema.class.getName());
+    runDeltaStreamerWithTransformers(transformerClassNames);
+  }
+
+  @Test
+  public void testTransformerSchemaValidationFails() throws Exception {
+    String errorMsg = "Expected target schema not provided for transformer";
+    List<String> transformerClassNames = Arrays.asList(
+        FlatteningTransformer.class.getName(),
+        TimestampTransformer.class.getName(),
+        AddColumnTransformerWithTransformedSchema.class.getName());
+    testTransformerSchemaValidationFails(transformerClassNames, errorMsg);
+
+    transformerClassNames = Arrays.asList(
+        FlatteningTransformerWithTransformedSchema.class.getName(),
+        TimestampTransformer.class.getName(),
+        AddColumnTransformer.class.getName());
+    testTransformerSchemaValidationFails(transformerClassNames, errorMsg);
+
+    errorMsg = "Schema of transformed data does not match expected schema";
+    transformerClassNames = Arrays.asList(
+        FlatteningTransformerWithTransformedSchema.class.getName(),
+        TimestampTransformer.class.getName(),
+        AddColumnTransformerWithWrongTransformedSchema.class.getName());
+    testTransformerSchemaValidationFails(transformerClassNames, errorMsg);
+  }
+
+  private void testTransformerSchemaValidationFails(List<String> 
transformerClasses, String errorMsg) {
+    try {
+      runDeltaStreamerWithTransformers(transformerClasses);
+      fail();
+    } catch (Exception e) {
+      assertTrue(e.getMessage().contains(errorMsg), e.getMessage());
+    }
+  }
+
+  private void runDeltaStreamerWithTransformers(List<String> 
transformerClassNames) throws Exception {
+    // Create source using TRIP_EXAMPLE_SCHEMA
+    boolean useSchemaProvider = true;
+    PARQUET_SOURCE_ROOT = basePath + "/parquetFilesDfs" + testNum;
+    int parquetRecordsCount = 10;
+    prepareParquetDFSFiles(parquetRecordsCount, PARQUET_SOURCE_ROOT, 
FIRST_PARQUET_FILE_NAME, false, null, null);
+    prepareParquetDFSSource(useSchemaProvider, true, "source.avsc", 
"target-flattened-addcolumn-transformer.avsc", PROPS_FILENAME_TEST_PARQUET,
+        PARQUET_SOURCE_ROOT, false, "partition_path", "");
+    String tableBasePath = basePath + "/testTransformerSchemaValidation" + 
testNum;
+    HoodieDeltaStreamer.Config config = 
TestHoodieDeltaStreamer.TestHelpers.makeConfig(tableBasePath, 
WriteOperationType.INSERT,
+        ParquetDFSSource.class.getName(), transformerClassNames, 
PROPS_FILENAME_TEST_PARQUET, false, useSchemaProvider,
+        100000, false, null, null, "timestamp", null);
+    config.enableTransformerSchemaValidation = true;
+    HoodieDeltaStreamer deltaStreamer = new HoodieDeltaStreamer(config, jsc);
+    Properties properties = ((HoodieDeltaStreamer.DeltaSyncService) 
deltaStreamer.getIngestionService()).getProps();
+    properties.setProperty("timestamp.transformer.increment", "20");
+    properties.setProperty("timestamp.transformer.multiplier", "2");
+
+    deltaStreamer.sync();
+    TestHoodieDeltaStreamer.TestHelpers.assertRecordCount(parquetRecordsCount, 
tableBasePath, sqlContext);
+    sqlContext.read().format("org.apache.hudi").load(tableBasePath).show();

Review Comment:
   Removed it.



##########
hudi-utilities/src/test/java/org/apache/hudi/utilities/deltastreamer/TestTransformer.java:
##########
@@ -79,6 +96,71 @@ public void testMultipleTransformersWithIdentifiers() throws 
Exception {
     assertEquals(0, 
sqlContext.read().format("org.apache.hudi").load(tableBasePath).where("timestamp
 != 110").count());
   }
 
+  @Test
+  public void testTransformerSchemaValidation() throws Exception {
+    List<String> transformerClassNames = Arrays.asList(
+        FlatteningTransformerWithTransformedSchema.class.getName(),
+        TimestampTransformer.class.getName(),
+        AddColumnTransformerWithTransformedSchema.class.getName());
+    runDeltaStreamerWithTransformers(transformerClassNames);
+  }
+
+  @Test
+  public void testTransformerSchemaValidationFails() throws Exception {
+    String errorMsg = "Expected target schema not provided for transformer";
+    List<String> transformerClassNames = Arrays.asList(
+        FlatteningTransformer.class.getName(),
+        TimestampTransformer.class.getName(),
+        AddColumnTransformerWithTransformedSchema.class.getName());
+    testTransformerSchemaValidationFails(transformerClassNames, errorMsg);
+
+    transformerClassNames = Arrays.asList(
+        FlatteningTransformerWithTransformedSchema.class.getName(),
+        TimestampTransformer.class.getName(),
+        AddColumnTransformer.class.getName());
+    testTransformerSchemaValidationFails(transformerClassNames, errorMsg);
+
+    errorMsg = "Schema of transformed data does not match expected schema";
+    transformerClassNames = Arrays.asList(
+        FlatteningTransformerWithTransformedSchema.class.getName(),
+        TimestampTransformer.class.getName(),
+        AddColumnTransformerWithWrongTransformedSchema.class.getName());
+    testTransformerSchemaValidationFails(transformerClassNames, errorMsg);
+  }
+
+  private void testTransformerSchemaValidationFails(List<String> 
transformerClasses, String errorMsg) {
+    try {

Review Comment:
   Addressed.



-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: [email protected]

For queries about this service, please contact Infrastructure at:
[email protected]

Reply via email to