wzx140 commented on code in PR #7003:
URL: https://github.com/apache/hudi/pull/7003#discussion_r1027312754
##########
hudi-common/src/main/java/org/apache/hudi/io/storage/HoodieAvroParquetReader.java:
##########
@@ -105,8 +105,11 @@ public long getTotalRecords() {
}
private ClosableIterator<IndexedRecord>
getIndexedRecordIteratorInternal(Schema schema, Option<Schema> requestedSchema)
throws IOException {
- AvroReadSupport.setAvroReadSchema(conf, schema);
- if (requestedSchema.isPresent()) {
+ if (!requestedSchema.isPresent()) {
+ AvroReadSupport.setAvroReadSchema(conf, schema);
+ } else {
+ // Make record schema the same as requestedSchema(reader schema)
+ AvroReadSupport.setAvroReadSchema(conf, requestedSchema.get());
Review Comment:
To fix TestMergeIntoLogOnlyTable. Compaction will trigger at the end of
"merge into". It seems that schema is not Compatible when use
writeSchema+readerSchema to read parquet block to avro
```
java.lang.ArrayIndexOutOfBoundsException: 2
at
org.apache.avro.io.parsing.Symbol$Alternative.getSymbol(Symbol.java:424)
~[avro-1.8.2.jar:1.8.2]
at
org.apache.avro.io.ResolvingDecoder.doAction(ResolvingDecoder.java:290)
~[avro-1.8.2.jar:1.8.2]
at org.apache.avro.io.parsing.Parser.advance(Parser.java:88)
~[avro-1.8.2.jar:1.8.2]
at
org.apache.avro.io.ResolvingDecoder.readIndex(ResolvingDecoder.java:267)
~[avro-1.8.2.jar:1.8.2]
at
org.apache.avro.generic.GenericDatumReader.readWithoutConversion(GenericDatumReader.java:179)
~[avro-1.8.2.jar:1.8.2]
at
org.apache.avro.generic.GenericDatumReader.read(GenericDatumReader.java:153)
~[avro-1.8.2.jar:1.8.2]
at
org.apache.avro.generic.GenericDatumReader.readField(GenericDatumReader.java:232)
~[avro-1.8.2.jar:1.8.2]
at
org.apache.avro.generic.GenericDatumReader.readRecord(GenericDatumReader.java:222)
~[avro-1.8.2.jar:1.8.2]
at
org.apache.avro.generic.GenericDatumReader.readWithoutConversion(GenericDatumReader.java:175)
~[avro-1.8.2.jar:1.8.2]
at
org.apache.avro.generic.GenericDatumReader.read(GenericDatumReader.java:153)
~[avro-1.8.2.jar:1.8.2]
at
org.apache.avro.generic.GenericDatumReader.read(GenericDatumReader.java:145)
~[avro-1.8.2.jar:1.8.2]
at
org.apache.hudi.avro.HoodieAvroUtils.bytesToAvro(HoodieAvroUtils.java:170)
~[classes/:?]
at
org.apache.hudi.avro.HoodieAvroUtils.bytesToAvro(HoodieAvroUtils.java:160)
~[classes/:?]
at
org.apache.hudi.common.model.OverwriteWithLatestAvroPayload.getInsertValue(OverwriteWithLatestAvroPayload.java:75)
~[classes/:?]
at
org.apache.hudi.common.model.HoodieRecordPayload.getInsertValue(HoodieRecordPayload.java:118)
~[classes/:?]
at
org.apache.hudi.common.model.HoodieAvroRecord.isDelete(HoodieAvroRecord.java:148)
~[classes/:?]
at
org.apache.hudi.io.HoodieCreateHandle.doWrite(HoodieCreateHandle.java:135)
~[classes/:?]
at
org.apache.hudi.io.HoodieWriteHandle.write(HoodieWriteHandle.java:205)
~[classes/:?]
at
org.apache.hudi.io.HoodieCreateHandle.write(HoodieCreateHandle.java:189)
~[classes/:?]
at
org.apache.hudi.table.HoodieSparkCopyOnWriteTable.handleInsert(HoodieSparkCopyOnWriteTable.java:262)
~[classes/:?]
at
org.apache.hudi.table.action.compact.HoodieCompactor.compact(HoodieCompactor.java:231)
~[classes/:?]
at
org.apache.hudi.table.action.compact.HoodieCompactor.lambda$compact$57154431$1(HoodieCompactor.java:137)
~[classes/:?]
at
org.apache.spark.api.java.JavaPairRDD$$anonfun$toScalaFunction$1.apply(JavaPairRDD.scala:1040)
~[spark-core_2.11-2.4.4.jar:2.4.4]
at scala.collection.Iterator$$anon$11.next(Iterator.scala:410)
~[scala-library-2.11.12.jar:?]
at scala.collection.Iterator$$anon$12.nextCur(Iterator.scala:435)
~[scala-library-2.11.12.jar:?]
at scala.collection.Iterator$$anon$12.hasNext(Iterator.scala:441)
~[scala-library-2.11.12.jar:?]
at
org.apache.spark.storage.memory.MemoryStore.putIterator(MemoryStore.scala:221)
~[spark-core_2.11-2.4.4.jar:2.4.4]
at
org.apache.spark.storage.memory.MemoryStore.putIteratorAsBytes(MemoryStore.scala:349)
~[spark-core_2.11-2.4.4.jar:2.4.4]
at
org.apache.spark.storage.BlockManager$$anonfun$doPutIterator$1.apply(BlockManager.scala:1182)
~[spark-core_2.11-2.4.4.jar:2.4.4]
at
org.apache.spark.storage.BlockManager$$anonfun$doPutIterator$1.apply(BlockManager.scala:1156)
~[spark-core_2.11-2.4.4.jar:2.4.4]
at org.apache.spark.storage.BlockManager.doPut(BlockManager.scala:1091)
~[spark-core_2.11-2.4.4.jar:2.4.4]
at
org.apache.spark.storage.BlockManager.doPutIterator(BlockManager.scala:1156)
~[spark-core_2.11-2.4.4.jar:2.4.4]
at
org.apache.spark.storage.BlockManager.getOrElseUpdate(BlockManager.scala:882)
~[spark-core_2.11-2.4.4.jar:2.4.4]
at org.apache.spark.rdd.RDD.getOrCompute(RDD.scala:335)
~[spark-core_2.11-2.4.4.jar:2.4.4]
at org.apache.spark.rdd.RDD.iterator(RDD.scala:286)
~[spark-core_2.11-2.4.4.jar:2.4.4]
at
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
~[spark-core_2.11-2.4.4.jar:2.4.4]
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:324)
~[spark-core_2.11-2.4.4.jar:2.4.4]
at org.apache.spark.rdd.RDD.iterator(RDD.scala:288)
~[spark-core_2.11-2.4.4.jar:2.4.4]
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
~[spark-core_2.11-2.4.4.jar:2.4.4]
at org.apache.spark.scheduler.Task.run(Task.scala:123)
~[spark-core_2.11-2.4.4.jar:2.4.4]
at
org.apache.spark.executor.Executor$TaskRunner$$anonfun$10.apply(Executor.scala:408)
~[spark-core_2.11-2.4.4.jar:2.4.4]
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1360)
~[spark-core_2.11-2.4.4.jar:2.4.4]
at
org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:414)
~[spark-core_2.11-2.4.4.jar:2.4.4]
at
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
~[?:1.8.0_211]
at
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
~[?:1.8.0_211]
at java.lang.Thread.run(Thread.java:748) ~[?:1.8.0_211]
```
--
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]
