JVM上高性能數(shù)據(jù)格式庫包Apache Arrow入門和架構(gòu)詳解(Gkatziouras)

<dependency>
    <groupId>org.apache.arrow</groupId>
    <artifactId>arrow-memory-netty</artifactId>
    <version>${arrow.version}</version>
</dependency>
<dependency>
    <groupId>org.apache.arrow</groupId>
    <artifactId>arrow-vector</artifactId>
    <version>${arrow.version}</version>
</dependency>

package com.gkatzioura.arrow;

import java.io.IOException;

import java.util.List;

import org.apache.arrow.vector.types.pojo.ArrowType;

import org.apache.arrow.vector.types.pojo.Field;

import org.apache.arrow.vector.types.pojo.FieldType;

import org.apache.arrow.vector.types.pojo.Schema;

public class SchemaFactory {

public static Schema DEFAULT_SCHEMA = createDefault();

public static Schema createDefault() {

var strField = new Field("col1", FieldType.nullable(new ArrowType.Utf8()), null);

var intField = new Field("col2", FieldType.nullable(new ArrowType.Int(32, true)), null);

return new Schema(List.of(strField, intField));

}

public static Schema schemaWithChildren() {

var amount = new Field("amount", FieldType.nullable(new ArrowType.Decimal(19,4,128)), null);

var currency = new Field("currency",FieldType.nullable(new ArrowType.Utf8()), null);

var itemField = new Field("item", FieldType.nullable(new ArrowType.Utf8()), List.of(amount,currency));

return new Schema(List.of(itemField));

}

public static Schema fromJson(String jsonString) {

try {

return Schema.fromJSON(jsonString);

} catch (IOException e) {

throw new ArrowExampleException(e);

}

}

}

{
  "fields" : [ {
    "name" : "col1",
    "nullable" : true,
    "type" : {
      "name" : "utf8"
    },
    "children" : [ ]
  }, {
    "name" : "col2",
    "nullable" : true,
    "type" : {
      "name" : "int",
      "bitWidth" : 32,
      "isSigned" : true
    },
    "children" : [ ]
  } ]
}

public static Schema schemaWithChildren() {
    var amount = new Field("amount", FieldType.nullable(new ArrowType.Decimal(19,4,128)), null);
    var currency = new Field("currency",FieldType.nullable(new ArrowType.Utf8()), null);
    var itemField = new Field("item", FieldType.nullable(new ArrowType.Utf8()), List.of(amount,currency));
 
    return new Schema(List.of(itemField));
}

package com.gkatzioura.arrow;
 
import lombok.Builder;
import lombok.Data;
 
@Data
@Builder
public class DefaultArrowEntry {
 
    private String col1;
    private Integer col2;
 
}

package com.gkatzioura.arrow;
 
import java.io.Closeable;
import java.io.IOException;
import java.nio.channels.WritableByteChannel;
import java.util.List;
 
import org.apache.arrow.memory.RootAllocator;
import org.apache.arrow.vector.IntVector;
import org.apache.arrow.vector.VarCharVector;
import org.apache.arrow.vector.VectorSchemaRoot;
import org.apache.arrow.vector.dictionary.DictionaryProvider;
import org.apache.arrow.vector.ipc.ArrowStreamWriter;
import org.apache.arrow.vector.util.Text;
 
import static com.gkatzioura.arrow.SchemaFactory.DEFAULT_SCHEMA;
 
public class DefaultEntriesWriter implements Closeable {
 
    private final RootAllocator rootAllocator;
    private final VectorSchemaRoot vectorSchemaRoot;//向量分配器創(chuàng)建：
 
    public DefaultEntriesWriter() {
        rootAllocator = new RootAllocator();
        vectorSchemaRoot = VectorSchemaRoot.create(DEFAULT_SCHEMA, rootAllocator);
    }
 
    public void write(List<DefaultArrowEntry> defaultArrowEntries, int batchSize, WritableByteChannel out) {
        if (batchSize <= 0) {
            batchSize = defaultArrowEntries.size();
        }
 
        DictionaryProvider.MapDictionaryProvider dictProvider = new DictionaryProvider.MapDictionaryProvider();
        try(ArrowStreamWriter writer = new ArrowStreamWriter(vectorSchemaRoot, dictProvider, out)) {
            writer.start();
 
            VarCharVector childVector1 = (VarCharVector) vectorSchemaRoot.getVector(0);
            IntVector childVector2 = (IntVector) vectorSchemaRoot.getVector(1);
            childVector1.reset();
            childVector2.reset();
 
            boolean exactBatches = defaultArrowEntries.size()%batchSize == 0;
            int batchCounter = 0;
 
            for(int i=0; i < defaultArrowEntries.size(); i++) {
                childVector1.setSafe(batchCounter, new Text(defaultArrowEntries.get(i).getCol1()));
                childVector2.setSafe(batchCounter, defaultArrowEntries.get(i).getCol2());
 
                batchCounter++;
 
                if(batchCounter == batchSize) {
                    vectorSchemaRoot.setRowCount(batchSize);
                    writer.writeBatch();
                    batchCounter = 0;
                }
            }
 
            if(!exactBatches) {
                vectorSchemaRoot.setRowCount(batchCounter);
                writer.writeBatch();
            }
 
            writer.end();
        } catch (IOException e) {
            throw new ArrowExampleException(e);
        }
    }
 
    @Override
    public void close() throws IOException {
        vectorSchemaRoot.close();
        rootAllocator.close();
    }
 
}

public DefaultEntriesToBytesConverter() {
    rootAllocator = new RootAllocator();
    vectorSchemaRoot = VectorSchemaRoot.create(DEFAULT_SCHEMA, rootAllocator);
}

ArrowStreamWriter writer = new ArrowStreamWriter(vectorSchemaRoot, dictProvider, Channels.newChannel(out));
writer.start();

VarCharVector childVector1 = (VarCharVector) vectorSchemaRoot.getVector(0);
IntVector childVector2 = (IntVector) vectorSchemaRoot.getVector(1);
childVector1.reset();
childVector2.reset();

childVector1.setSafe(i, new Text(defaultArrowEntries.get(i).getCol1()));
childVector2.setSafe(i, defaultArrowEntries.get(i).getCol2());

vectorSchemaRoot.setRowCount(batchSize);
writer.writeBatch();

@Override
public void close() throws IOException {
    vectorSchemaRoot.close();
    rootAllocator.close();
}