JAVA API操作小文件合并至HDFS笔记

相关文件请自行创建！！！

package com.hadoop.hdfs;

import java.io.IOException;
import java.net.URI;
import java.net.URISyntaxException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FSDataOutputStream;
import org.apache.hadoop.fs.FileStatus;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.FileUtil;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.fs.PathFilter;
import org.apache.hadoop.io.IoUtils;
/**

• 合并小文件至 HDFS

• */
  public class MergeSmallFilesToHDFS {
  private static FileSystem fs = null;
  private static FileSystem local = null;

  public static void main(String[] args) throws IOException,
  URISyntaxException {
  list();
  }

  /**

  • 数据集合并，并上传至HDFS
  • throws IOException
    throws URISyntaxException
    /
    public static void list() throws IOException, URISyntaxException {
    // 读取hadoop文件系统的配置
    Configuration conf = new Configuration();
    //文件系统访问接口，注意：hdfs://master:9000修改成自己的HDFS地址
    URI uri = new URI("hdfs://master:9000");
    //创建FileSystem对象
    fs = FileSystem.get(uri, conf);
    // 获得本地文件系统
    local = FileSystem.getLocal(conf);
    //过滤目录下的 svn文件，注意：文件路径E://Hadoop/73/修改成自己的路径
    FileStatus[] dirstatus = local.globStatus(new Path("E://Hadoop/73/"),new RegexExcludePathFilter("^.svn$"));
    //获取73目录下的所有文件路径
    Path[] dirs = FileUtil.stat2Paths(dirstatus);
    FSDataOutputStream out = null;
    FSDataInputStream in = null;
    for (Path dir : dirs) {
    //2019-10-31
    String fileName = dir.getName().replace("-", "");//文件名称
    //只接受日期目录下的.txt文件
    FileStatus[] localStatus = local.globStatus(new Path(dir+"/"),new RegexAcceptPathFilter("^.txt$"));
    // 获得日期目录下的所有文件
    Path[] listedpaths = FileUtil.stat2Paths(localStatus);
    //输出路径，注意：hdfs://master:9000/20191031/修改成自己的HDFS目录地址
    Path block = new Path("hdfs://master:9000/20191031/"+ fileName + ".txt");
    System.out.println("合并后的文件名称："+fileName+".txt");
    // 打开输出流
    out = fs.create(block);
    for (Path p : listedpaths) {
    in = local.open(p);// 打开输入流
    IoUtils.copyBytes(in, out, 4096, false); // 复制数据
    // 关闭输入流
    in.close();
    }
    if (out != null) {
    // 关闭输出流
    out.close();
    }
    }

  }

  /**

  • 过滤 regex 格式的文件

  • */
    public static class RegexExcludePathFilter implements PathFilter {
    private final String regex;
    public RegexExcludePathFilter(String regex) {
    this.regex = regex;
    }

    public boolean accept(Path path) {
    boolean flag = path.toString().matches(regex);
    return !flag;
    }

  }

  /**

  • 接受 regex 格式的文件

  • */
    public static class RegexAcceptPathFilter implements PathFilter {
    private final String regex;
    public RegexAcceptPathFilter(String regex) {
    this.regex = regex;
    }

    @Override
    public boolean accept(Path path) {
    boolean flag = path.toString().matches(regex);
    return flag;
    }

  }
  }