Trino has a bug of Merge Statement from Iceberg Catalog

[cheetile]

I only tested on Iceberg Catalog.

Setting:

create table iceberg.test.test_tbl (
	id integer not null,
	msg varchar not null,
	msg_2 varchar not null
)
with (format = 'PARQUET');
insert into iceberg.test.test_tbl(id, msg, msg_2) values (1, 'aa', 'bb');

Test Query:

merge into iceberg.test.test_tbl t
using (select 2 as id, 'cc' as msg) s on t.id = s.id
when matched 
	then update set 
		msg = s.msg
when not matched 
	then insert (id, msg) values(s.id, s.msg)
;

The execution of Test Query is succeeded.
And then when run next query, raise exception.

select * from iceberg.test.test_tbl;

Caused by: java.sql.SQLException: Query failed (#20240419_012952_00969_eenyh): Failed to read Parquet file: ~~~~~~~~~~.parquet
	at io.trino.jdbc.AbstractTrinoResultSet.resultsException(AbstractTrinoResultSet.java:1937)
	at io.trino.jdbc.TrinoResultSet$ResultsPageIterator.computeNext(TrinoResultSet.java:294)
	at io.trino.jdbc.TrinoResultSet$ResultsPageIterator.computeNext(TrinoResultSet.java:254)
	at io.trino.jdbc.$internal.guava.collect.AbstractIterator.tryToComputeNext(AbstractIterator.java:145)
	at io.trino.jdbc.$internal.guava.collect.AbstractIterator.hasNext(AbstractIterator.java:140)
	at java.base/java.util.Spliterators$IteratorSpliterator.tryAdvance(Unknown Source)
	at java.base/java.util.stream.StreamSpliterators$WrappingSpliterator.lambda$initPartialTraversalState$0(Unknown Source)
	at java.base/java.util.stream.StreamSpliterators$AbstractWrappingSpliterator.fillBuffer(Unknown Source)
	at java.base/java.util.stream.StreamSpliterators$AbstractWrappingSpliterator.doAdvance(Unknown Source)
	at java.base/java.util.stream.StreamSpliterators$WrappingSpliterator.tryAdvance(Unknown Source)
	at java.base/java.util.Spliterators$1Adapter.hasNext(Unknown Source)
	at io.trino.jdbc.TrinoResultSet$AsyncIterator.lambda$new$1(TrinoResultSet.java:179)
	at java.base/java.util.concurrent.Executors$RunnableAdapter.call(Unknown Source)
	at java.base/java.util.concurrent.FutureTask.run(Unknown Source)
	at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
	at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
	at java.base/java.lang.Thread.run(Unknown Source)
Caused by: io.trino.spi.TrinoException: Failed to read Parquet file: ~~~~~~~~~~~.parquet
	at io.trino.plugin.iceberg.IcebergPageSourceProvider.handleException(IcebergPageSourceProvider.java:1515)
	at io.trino.plugin.iceberg.IcebergPageSourceProvider.lambda$createParquetPageSource$26(IcebergPageSourceProvider.java:1081)
	at io.trino.parquet.reader.ParquetBlockFactory$ParquetBlockLoader.load(ParquetBlockFactory.java:75)
	at io.trino.spi.block.LazyBlock$LazyData.load(LazyBlock.java:361)
	at io.trino.spi.block.LazyBlock$LazyData.getFullyLoadedBlock(LazyBlock.java:340)
	at io.trino.spi.block.LazyBlock.getLoadedBlock(LazyBlock.java:235)
	at io.trino.spi.Page.getLoadedPage(Page.java:241)
	at io.trino.operator.TableScanOperator.getOutput(TableScanOperator.java:269)
	at io.trino.operator.Driver.processInternal(Driver.java:398)
	at io.trino.operator.Driver.lambda$process$8(Driver.java:301)
	at io.trino.operator.Driver.tryWithLock(Driver.java:704)
	at io.trino.operator.Driver.process(Driver.java:293)
	at io.trino.operator.Driver.processForDuration(Driver.java:264)
	at io.trino.execution.SqlTaskExecution$DriverSplitRunner.processFor(SqlTaskExecution.java:887)
	at io.trino.execution.executor.dedicated.SplitProcessor.run(SplitProcessor.java:76)
	at io.trino.execution.executor.dedicated.TaskEntry$VersionEmbedderBridge.lambda$run$0(TaskEntry.java:191)
	at io.trino.$gen.Trino_439____20240408_170237_2.run(Unknown Source)
	at io.trino.execution.executor.dedicated.TaskEntry$VersionEmbedderBridge.run(TaskEntry.java:192)
	at io.trino.execution.executor.scheduler.FairScheduler.runTask(FairScheduler.java:174)
	at io.trino.execution.executor.scheduler.FairScheduler.lambda$submit$0(FairScheduler.java:161)
	at java.base/java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:572)
	at com.google.common.util.concurrent.TrustedListenableFutureTask$TrustedFutureInterruptibleTask.runInterruptibly(TrustedListenableFutureTask.java:131)
	at com.google.common.util.concurrent.InterruptibleTask.run(InterruptibleTask.java:76)
	at com.google.common.util.concurrent.TrustedListenableFutureTask.run(TrustedListenableFutureTask.java:82)
	at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1144)
	at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:642)
	at java.base/java.lang.Thread.run(Thread.java:1583)
Caused by: java.lang.IndexOutOfBoundsException: Range [0, 0 + 4) out of bounds for length 0
	at java.base/jdk.internal.util.Preconditions.outOfBounds(Preconditions.java:100)
	at java.base/jdk.internal.util.Preconditions.outOfBoundsCheckFromIndexSize(Preconditions.java:118)
	at java.base/jdk.internal.util.Preconditions.checkFromIndexSize(Preconditions.java:397)
	at java.base/java.util.Objects.checkFromIndexSize(Objects.java:437)
	at io.airlift.slice.Slice.getInt(Slice.java:278)
	at io.trino.parquet.reader.decoders.PlainByteArrayDecoders$BinaryPlainValueDecoder.read(PlainByteArrayDecoders.java:156)
	at io.trino.parquet.reader.decoders.PlainByteArrayDecoders$BinaryPlainValueDecoder.read(PlainByteArrayDecoders.java:135)
	at io.trino.parquet.reader.flat.FlatColumnReader$DataValuesBuffer.readNonNullValues(FlatColumnReader.java:358)
	at io.trino.parquet.reader.flat.FlatColumnReader.readNonNull(FlatColumnReader.java:188)
	at io.trino.parquet.reader.flat.FlatColumnReader.readPrimitive(FlatColumnReader.java:90)
	at io.trino.parquet.reader.ParquetReader.readPrimitive(ParquetReader.java:463)
	at io.trino.parquet.reader.ParquetReader.readColumnChunk(ParquetReader.java:553)
	at io.trino.parquet.reader.ParquetReader.readBlock(ParquetReader.java:536)
	at io.trino.parquet.reader.ParquetReader.lambda$nextPage$3(ParquetReader.java:251)
	at io.trino.parquet.reader.ParquetBlockFactory$ParquetBlockLoader.load(ParquetBlockFactory.java:72)
	... 24 more

[ebyhr]

I can reproduce the issue on master.

[chenjian2664]

The msg_2 is not null, but in the merge insert not specify the column, I think it' should fail in first merge. @djsstarburst