com.google.cloud.hadoop.io.bigquery.GsonBigQueryInputFormat Maven / Gradle / Ivy

Go to download

Show more of this group Show more artifacts with this name
Show all versions of bigquery-connector Show documentation

Hadoop 2 MapReduce input and output formats for use with BigQuery

There is a newer version: 0.13.4-hadoop3

package com.google.cloud.hadoop.io.bigquery;

import com.google.cloud.hadoop.util.LogUtil;
import com.google.gson.JsonObject;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.mapreduce.InputSplit;
import org.apache.hadoop.mapreduce.RecordReader;

import java.io.IOException;

/**
 * GsonBigQueryInputFormat provides access to BigQuery tables via exports to GCS in the form of
 * gson JsonObjects as mapper values.
 */
public class GsonBigQueryInputFormat
    extends AbstractBigQueryInputFormat {
  protected static final LogUtil log = new LogUtil(GsonBigQueryInputFormat.class);

  @Override
  public RecordReader createDelegateRecordReader(
      InputSplit split, Configuration configuration) throws IOException, InterruptedException {
    log.debug("createDelegateRecordReader -> new GsonRecordReader");
    return new GsonRecordReader();
  }

  @Override
  public ExportFileFormat getExportFileFormat() {
    return ExportFileFormat.LINE_DELIMITED_JSON;
  }
}