apache / apache/arrow-java

[Java][Windows][Substrait] Failed to parse memory address from string value. Error: stol argument out of range on Substrait Windows environment

Aberta
#176 0 comentários 0 reações 0 responsáveis Ver no GitHub
Linguagem predominante
Java
Estrelas
94
Forks
152
Merge médio
3d 16h
PRs com merge (30d)
11

Descrição

### Describe the bug, including details regarding any error messages, version, and platform.

Trying to run Java Substrait demo into Windows OS and seeing this error response:

```
java.lang.RuntimeException: Failed to parse memory address from string value. Error: stol argument out of range
at org.apache.arrow.dataset.substrait.JniWrapper.executeSerializedPlan(Native Method)
at org.apache.arrow.dataset.substrait.AceroSubstraitConsumer.execute(AceroSubstraitConsumer.java:119)
at org.apache.arrow.dataset.substrait.AceroSubstraitConsumer.runQuery(AceroSubstraitConsumer.java:90)
```

```Java
.. testcode::

import com.google.common.collect.ImmutableList;
import io.substrait.isthmus.SqlToSubstrait;
import io.substrait.proto.Plan;
import org.apache.arrow.dataset.file.FileFormat;
import org.apache.arrow.dataset.file.FileSystemDatasetFactory;
import org.apache.arrow.dataset.jni.NativeMemoryPool;
import org.apache.arrow.dataset.scanner.ScanOptions;
import org.apache.arrow.dataset.scanner.Scanner;
import org.apache.arrow.dataset.source.Dataset;
import org.apache.arrow.dataset.source.DatasetFactory;
import org.apache.arrow.dataset.substrait.AceroSubstraitConsumer;
import org.apache.arrow.memory.BufferAllocator;
import org.apache.arrow.memory.RootAllocator;
import org.apache.arrow.vector.ipc.ArrowReader;
import org.apache.calcite.sql.parser.SqlParseException;

import java.nio.ByteBuffer;
import java.util.HashMap;
import java.util.Map;

static Plan queryTableNationJoinCustomer() throws SqlParseException {
String sql = "SELECT n.n_name, COUNT(*) AS NUMBER_CUSTOMER FROM NATION n JOIN CUSTOMER c " +
"ON n.n_nationkey = c.c_nationkey WHERE n.n_nationkey = 17 " +
"GROUP BY n.n_name";
String nation = "CREATE TABLE NATION (N_NATIONKEY BIGINT NOT NULL, " +
"N_NAME CHAR(25), N_REGIONKEY BIGINT NOT NULL, N_COMMENT VARCHAR(152))";
String customer = "CREATE TABLE CUSTOMER (C_CUSTKEY BIGINT NOT NULL, " +
"C_NAME VARCHAR(25), C_ADDRESS VARCHAR(40), C_NATIONKEY BIGINT NOT NULL, " +
"C_PHONE CHAR(15), C_ACCTBAL DECIMAL, C_MKTSEGMENT CHAR(10), " +
"C_COMMENT VARCHAR(117) )";
SqlToSubstrait sqlToSubstrait = new SqlToSubstrait();
Plan plan = sqlToSubstrait.execute(sql,
ImmutableList.of(nation, customer));
return plan;
}

static void queryTwoDatasetsThruSubstraitPlanDefinition() {
String uriNation = "file:" + System.getProperty("user.dir") + "/thirdpartydeps/tpch/nation.parquet";
String uriCustomer = "file:" + System.getProperty("user.dir") + "/thirdpartydeps/tpch/customer.parquet";
ScanOptions options = new ScanOptions(/*batchSize*/ 32768);
try (
BufferAllocator allocator = new RootAllocator();
DatasetFactory datasetFactory = new FileSystemDatasetFactory(
allocator, NativeMemoryPool.getDefault(),
FileFormat.PARQUET, uriNation);
Dataset dataset = datasetFactory.finish();
Scanner scanner = dataset.newScan(options);
ArrowReader readerNation = scanner.scanBatches();
DatasetFactory datasetFactoryCustomer = new FileSystemDatasetFactory(
allocator, NativeMemoryPool.getDefault(),
FileFormat.PARQUET, uriCustomer);
Dataset datasetCustomer = datasetFactoryCustomer.finish();
Scanner scannerCustomer = datasetCustomer.newScan(options);
ArrowReader readerCustomer = scannerCustomer.scanBatches()
) {
// map table to reader
Map mapTableToArrowReader = new HashMap<>();
mapTableToArrowReader.put("NATION", readerNation);
mapTableToArrowReader.put("CUSTOMER", readerCustomer);
// get binary plan
Plan plan = queryTableNationJoinCustomer();
ByteBuffer substraitPlan = ByteBuffer.allocateDirect(
plan.toByteArray().length);
substraitPlan.put(plan.toByteArray());
// run query
try (ArrowReader arrowReader = new AceroSubstraitConsumer(
allocator).runQuery(
substraitPlan,
mapTableToArrowReader
)) {
while (arrowReader.loadNextBatch()) {
System.out.print(arrowReader.getVectorSchemaRoot().contentToTSVString());
}
}
} catch (Exception e) {
e.printStackTrace();
}
}

queryTwoDatasetsThruSubstraitPlanDefinition();

.. testoutput::

N_NAME NUMBER_CUSTOMER
PERU 573
```

### Component(s)

Java

Guia de contribuição

Abrir o guia de contribuição

Direção de pesquisa

Reproduza a demonstração Java Substrait no Windows e comece em AceroSubstraitConsumer.java:119, onde o stack trace entra em JniWrapper.executeSerializedPlan. Rastreie a análise do endereço de memória nativo, reportada como um erro de intervalo de stol. A tarefa estará concluída quando a consulta for executada no Windows e produzir a saída esperada de N_NAME e NUMBER_CUSTOMER.

Escrita pelo modelo de indexação a partir do texto da issue.

Avaliação

Stack de tecnologia
java
Domínio
data-engineering
Tipo de issue
Bug
Dificuldade
4/5
Tempo estimado
3-5 dias
Status de atividade
Estagnada
Clareza
Razoavelmente clara
Facilidade para iniciantes
35/100

Receba novas issues na sua caixa de entrada

Um resumo curto de issues do GitHub para quem está começando.