【2019-05-29】Parquet

Apache Parquet是一种能够有效存储嵌套数据的列式存储格式。

Parquet的原子类型

Parquet的逻辑类型

Parquet文件的内部结构

Parquet文件由一个文件头(header),一个或多个紧随其后的文件块(block),以及一个用于结尾的文件尾(footer)构成。文件头仅包含
Parquet文件的每个文件块负责存储一个行组,行组由列块组成,且一个列块负责存储一列数据。每个列块中的的数据以页为单位。

Parquet Map reduce

文本文件转化为Parquet文件

import java.io.IOException;
import org.apache.avro.Schema;
import org.apache.avro.generic.GenericData;
import org.apache.avro.generic.GenericRecord;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;
import parquet.avro.AvroParquetOutputFormat;
import parquet.example.data.Group;

/**
 * Convert text files to Parquet files using Parquet's {@code AvroParquetOutputFormat}.
 */
public class TextToParquetWithAvro extends Configured implements Tool {

  private static final Schema SCHEMA = new Schema.Parser().parse(
      "{\n" +
      "  \"type\": \"record\",\n" +
      "  \"name\": \"Line\",\n" +
      "  \"fields\": [\n" +
      "    {\"name\": \"offset\", \"type\": \"long\"},\n" +
      "    {\"name\": \"line\", \"type\": \"string\"}\n" +
      "  ]\n" +
      "}");

  public static class TextToParquetMapper
      extends Mapper {

    private GenericRecord record = new GenericData.Record(SCHEMA);

    @Override
    protected void map(LongWritable key, Text value, Context context)
        throws IOException, InterruptedException {
      record.put("offset", key.get());
      record.put("line", value.toString());
      context.write(null, record);
    }
  }

  @Override
  public int run(String[] args) throws Exception {
    if (args.length != 2) {
      System.err.printf("Usage: %s [generic options]  \n",
          getClass().getSimpleName());
      ToolRunner.printGenericCommandUsage(System.err);
      return -1;
    }

    Job job = new Job(getConf(), "Text to Parquet");
    job.setJarByClass(getClass());

    FileInputFormat.addInputPath(job, new Path(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));

    job.setMapperClass(TextToParquetMapper.class);
    job.setNumReduceTasks(0);

    job.setOutputFormatClass(AvroParquetOutputFormat.class);
    AvroParquetOutputFormat.setSchema(job, SCHEMA);

    job.setOutputKeyClass(Void.class);
    job.setOutputValueClass(Group.class);

    return job.waitForCompletion(true) ? 0 : 1;
  }

  public static void main(String[] args) throws Exception {
    int exitCode = ToolRunner.run(new TextToParquetWithAvro(), args);
    System.exit(exitCode);
  }
}

你可能感兴趣的:(【2019-05-29】Parquet)