我正在编写一个代码来使用Apache做一个LeftOuterJoin，使用apache提供的类来轻松地工作apache提供一个连接类org.apache.beam.sdk.extensions.joinlibrary.Join;虽然当我使用POJO类或String，Integer，Long以KV格式时整个代码正常工作，但是当我在KV中使用TableRow并引发异常时失败。我还在例外情况下共享了一个代码供参考。
Apr 12, 2018 6:26:03 PM org.apache.beam.sdk.Pipeline validate
WARNING: The following transforms do not have stable unique names: ParDo(Anonymous), Create.Values
Exception in thread "main" java.lang.IllegalArgumentException: unable to serialize DoFnAndMainOutput{doFn=org.apache.beam.sdk.extensions.joinlibrary.Join$2@1817f1eb, mainOutputTag=Tag<output>}
at org.apache.beam.sdk.util.SerializableUtils.serializeToByteArray(SerializableUtils.java:57)
at org.apache.beam.runners.direct.repackaged.runners.core.construction.ParDoTranslation.translateDoFn(ParDoTranslation.java:440)
at org.apache.beam.runners.direct.repackaged.runners.core.construction.ParDoTranslation$1.translateDoFn(ParDoTranslation.java:148)
at org.apache.beam.runners.direct.repackaged.runners.core.construction.ParDoTranslation.payloadForParDoLike(ParDoTranslation.java:656)
at org.apache.beam.runners.direct.repackaged.runners.core.construction.ParDoTranslation.translateParDo(ParDoTranslation.java:144)
at org.apache.beam.runners.direct.repackaged.runners.core.construction.ParDoTranslation$ParDoPayloadTranslator.translate(ParDoTranslation.java:108)
at org.apache.beam.runners.direct.repackaged.runners.core.construction.PTransformTranslation.toProto(PTransformTranslation.java:193)
at org.apache.beam.runners.direct.repackaged.runners.core.construction.ParDoTranslation.getParDoPayload(ParDoTranslation.java:515)
at org.apache.beam.runners.direct.repackaged.runners.core.construction.ParDoTranslation.isSplittable(ParDoTranslation.java:525)
at org.apache.beam.runners.direct.repackaged.runners.core.construction.PTransformMatchers$4.matches(PTransformMatchers.java:194)
at org.apache.beam.sdk.Pipeline$2.visitPrimitiveTransform(Pipeline.java:278)
at org.apache.beam.sdk.runners.TransformHierarchy$Node.visit(TransformHierarchy.java:670)
at org.apache.beam.sdk.runners.TransformHierarchy$Node.visit(TransformHierarchy.java:662)
at org.apache.beam.sdk.runners.TransformHierarchy$Node.visit(TransformHierarchy.java:662)
at org.apache.beam.sdk.runners.TransformHierarchy$Node.access$600(TransformHierarchy.java:311)
at org.apache.beam.sdk.runners.TransformHierarchy.visit(TransformHierarchy.java:245)
at org.apache.beam.sdk.Pipeline.traverseTopologically(Pipeline.java:458)
at org.apache.beam.sdk.Pipeline.replace(Pipeline.java:256)
at org.apache.beam.sdk.Pipeline.replaceAll(Pipeline.java:209)
at org.apache.beam.runners.direct.DirectRunner.run(DirectRunner.java:173)
at org.apache.beam.runners.direct.DirectRunner.run(DirectRunner.java:62)
at org.apache.beam.sdk.Pipeline.run(Pipeline.java:311)
at org.apache.beam.sdk.Pipeline.run(Pipeline.java:297)
at com.bitwise.StarterPipeline.main(StarterPipeline.java:93)
Caused by: java.io.NotSerializableException: com.google.api.services.bigquery.model.TableRow
at java.io.ObjectOutputStream.writeObject0(Unknown Source)
at java.io.ObjectOutputStream.defaultWriteFields(Unknown Source)
at java.io.ObjectOutputStream.writeSerialData(Unknown Source)
at java.io.ObjectOutputStream.writeOrdinaryObject(Unknown Source)
at java.io.ObjectOutputStream.writeObject0(Unknown Source)
at java.io.ObjectOutputStream.defaultWriteFields(Unknown Source)
at java.io.ObjectOutputStream.writeSerialData(Unknown Source)
at java.io.ObjectOutputStream.writeOrdinaryObject(Unknown Source)
at java.io.ObjectOutputStream.writeObject0(Unknown Source)
at java.io.ObjectOutputStream.writeObject(Unknown Source)
at org.apache.beam.sdk.util.SerializableUtils.serializeToByteArray(SerializableUtils.java:53)
... 23 more
码
import org.apache.beam.runners.dataflow.options.DataflowPipelineOptions;
import org.apache.beam.runners.direct.DirectRunner;
import org.apache.beam.sdk.Pipeline;
import org.apache.beam.sdk.extensions.joinlibrary.Join;
import org.apache.beam.sdk.options.PipelineOptionsFactory;
import org.apache.beam.sdk.transforms.Create;
import org.apache.beam.sdk.transforms.DoFn;
import org.apache.beam.sdk.transforms.ParDo;
import org.apache.beam.sdk.values.KV;
import org.apache.beam.sdk.values.PCollection;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import com.google.api.services.bigquery.model.TableRow;
public class StarterPipeline {
private static final Logger LOG = LoggerFactory.getLogger(StarterPipeline.class);
static transient TableRow t= new TableRow();
public static void main(String[] args) {
DataflowPipelineOptions options = PipelineOptionsFactory.as(DataflowPipelineOptions.class);
options.setRunner(DirectRunner.class);
options.setProject("Project Name");
options.setTempLocation("Location");
options.setStagingLocation("Location");
Pipeline p = Pipeline.create(options);
PCollection<KV<String, String>> leftPcollection = p.apply(Create.of("Kishan")).apply(ParDo.of(new DoFn<String,KV<String,String>>(){
@ProcessElement
public void processElement(ProcessContext c){
c.output(KV.of("Kishan", "Kumar"));
c.output(KV.of("Kishan1", "Test"));
}
}));
//
PCollection<KV<String, TableRow>> rightPcollection = p.apply(Create.of("Kishan")).apply(ParDo.of(new DoFn<String,KV<String,TableRow>>(){
@ProcessElement
public void processElement(ProcessContext c){
c.output(KV.of("Kishan",new TableRow().set("Key", "Value")));
}
}));
//
PCollection<TableRow> joinedPcollection =
Join.leftOuterJoin(leftPcollection, rightPcollection,t).apply("Tesdt",ParDo.of(new DoFn<KV<String, KV<String, TableRow>>,TableRow>(){
@ProcessElement
public void processElement(ProcessContext c){
//Processing
}
}));
p.run();
}
}
这是因为你的DoFn是用Java序列化序列化的，以便分发和运行它，但是TableRow不能通过Java序列化来序列化。
我没有看到你的代码片段在TableRow的闭包中有一个实际的DoFn值，但这肯定是原因。