wombatu-kun commented on code in PR #18914:
URL: https://github.com/apache/hudi/pull/18914#discussion_r3411386423


##########
hudi-utilities/src/test/java/org/apache/hudi/utilities/functional/TestErrorTableAwareChainedTransformer.java:
##########
@@ -86,7 +87,45 @@ public void testForErrorRecordColumn() {
     TypedProperties properties = new TypedProperties();
     properties.setProperty(ERROR_TABLE_ENABLED.key(), "true");
     ErrorTableAwareChainedTransformer transformer = new 
ErrorTableAwareChainedTransformer(Arrays.asList(t1, t2, t3));
-    assertThrows(HoodieValidationException.class, () -> 
transformer.apply(jsc(), spark(), original, properties));
+    Dataset<Row> transformed = transformer.apply(jsc(), spark(), original, 
properties);
+
+    assertArrayEquals(new String[]{"foo", 
ERROR_TABLE_CURRUPT_RECORD_COL_NAME}, transformed.columns());
+    assertEquals(2, transformed.count());
+  }
+
+  @Test
+  void testCustomColumnProjectionPreservesCorruptRecord() {
+    // Single custom transformer doing column projection — drops 
_corrupt_record.
+    Dataset<Row> original = getTestDataset();
+
+    Transformer columnFilter = (jsc, sparkSession, dataset, props) -> 
dataset.select("foo");
+    TypedProperties properties = new TypedProperties();
+    properties.setProperty(ERROR_TABLE_ENABLED.key(), "true");
+    ErrorTableAwareChainedTransformer transformer =
+        new ErrorTableAwareChainedTransformer(Arrays.asList(columnFilter));
+    Dataset<Row> transformed = transformer.apply(jsc(), spark(), original, 
properties);
+
+    assertArrayEquals(new String[]{"foo", 
ERROR_TABLE_CURRUPT_RECORD_COL_NAME}, transformed.columns());
+    assertEquals(2, transformed.count());
+    assertEquals(2, transformed.filter(new 
Column(ERROR_TABLE_CURRUPT_RECORD_COL_NAME).isNull()).count());
+  }
+
+  @Test
+  void testTransformerPreservingCorruptRecordIsNoOp() {
+    // Transformer that keeps all columns — re-injection is a no-op.
+    Dataset<Row> original = getTestDataset();
+
+    Transformer keepAll = (jsc, sparkSession, dataset, properties) -> 
dataset.withColumn("foo",
+        dataset.col("foo").cast(IntegerType));
+    TypedProperties properties = new TypedProperties();

Review Comment:
   +1



-- 
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