메뉴 건너뛰기

Bigdata, Semantic IoT, Hadoop, NoSQL

Bigdata, Hadoop ecosystem, Semantic IoT등의 프로젝트를 진행중에 습득한 내용을 정리하는 곳입니다.
필요한 분을 위해서 공개하고 있습니다. 문의사항은 gooper@gooper.com로 메일을 보내주세요.


Hadoop 2.7.x에서 사용할 수 있는 파일/디렉토리 관련 utils

import java.io.BufferedInputStream;
import java.io.BufferedOutputStream;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.OutputStream;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FSDataOutputStream;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;

public class HDFSUtils {
	/**
	   * create a existing file from local filesystem to hdfs
	   * @param source
	   * @param dest
	   * @param conf
	   * @throws IOException
	   */
	  public void addFile(String source, String dest, Configuration conf) throws IOException {

	    FileSystem fileSystem = FileSystem.get(conf);

	    // Get the filename out of the file path
	    String filename = source.substring(source.lastIndexOf('/') + 1,source.length());

	    // Create the destination path including the filename.
	    if (dest.charAt(dest.length() - 1) != '/') {
	      dest = dest + "/" + filename;
	    } else {
	      dest = dest + filename;
	    }

	    // System.out.println("Adding file to " + destination);

	    // Check if the file already exists
	    Path path = new Path(dest);
	    if (fileSystem.exists(path)) {
	      System.out.println("File " + dest + " already exists");
	      return;
	    }

	    // Create a new file and write data to it.
	    FSDataOutputStream out = fileSystem.create(path);
	    InputStream in = new BufferedInputStream(new FileInputStream(new File(
	        source)));

	    byte[] b = new byte[1024];
	    int numBytes = 0;
	    while ((numBytes = in.read(b)) > 0) {
	      out.write(b, 0, numBytes);
	    }

	    // Close all the file descriptors
	    in.close();
	    out.close();
	    fileSystem.close();
	  }

	  /**
	   * read a file from hdfs
	   * @param file
	   * @param conf
	   * @throws IOException
	   */
	  public void readFile(String file, Configuration conf) throws IOException {
	    FileSystem fileSystem = FileSystem.get(conf);

	    Path path = new Path(file);
	    if (!fileSystem.exists(path)) {
	      System.out.println("File " + file + " does not exists");
	      return;
	    }

	    FSDataInputStream in = fileSystem.open(path);

	    String filename = file.substring(file.lastIndexOf('/') + 1,
	        file.length());

	    OutputStream out = new BufferedOutputStream(new FileOutputStream(
	        new File(filename)));

	    byte[] b = new byte[1024];
	    int numBytes = 0;
	    while ((numBytes = in.read(b)) > 0) {
	      out.write(b, 0, numBytes);
	    }

	    in.close();
	    out.close();
	    fileSystem.close();
	  }

	  /**
	   * delete a directory in hdfs
	   * @param file
	   * @throws IOException
	   */
	  public void deleteFile(String file, Configuration conf) throws IOException {
	    FileSystem fileSystem = FileSystem.get(conf);

	    Path path = new Path(file);
	    if (!fileSystem.exists(path)) {
	      System.out.println("File " + file + " does not exists");
	      return;
	    }

	    fileSystem.delete(new Path(file), true);

	    fileSystem.close();
	  }

	  /**
	   * create directory in hdfs
	   * @param dir
	   * @throws IOException
	   */
	  public void mkdir(String dir, Configuration conf) throws IOException {
	    FileSystem fileSystem = FileSystem.get(conf);

	    Path path = new Path(dir);
	    if (fileSystem.exists(path)) {
	      System.out.println("Dir " + dir + " already exists");
	      return;
	    } else {
		    fileSystem.mkdirs(path);
		    fileSystem.close();
	    }
	  }
	  
	  /**
	   * delete directory in hdfs
	   * @param dir
	   * @throws IOException
	   */
	  public void rmdir(String dir, Configuration conf) throws IOException {
	    FileSystem fileSystem = FileSystem.get(conf);

	    Path path = new Path(dir);
	    if (fileSystem.exists(path)) {
		    fileSystem.delete(path, true);
		    fileSystem.close();
	    } else {
		    System.out.println("Dir " + dir + " not exists");
	    }
	  }


	  /*
	  public static void main(String[] args) throws IOException {

	    if (args.length < 1) {
	      System.out.println("Usage: hdfsclient add/read/delete/mkdir"
	          + " [<local_path> <hdfs_path>]");
	      System.exit(1);
	    }

	    FileSystemOperations client = new FileSystemOperations();
	    String hdfsPath = "hdfs://" + args[0] + ":" + args[1];

	    Configuration conf = new Configuration();
	    // Providing conf files
	    // conf.addResource(new Path(HDFSAPIDemo.class.getResource("/conf/core-site.xml").getFile()));
	    // conf.addResource(new Path(HDFSAPIDemo.class.getResource("/conf/hdfs-site.xml").getFile()));
	    // (or) using relative paths
	    //    conf.addResource(new Path(
	    //        "/u/hadoop-1.0.2/conf/core-site.xml"));
	    //    conf.addResource(new Path(
	    //        "/u/hadoop-1.0.2/conf/hdfs-site.xml"));

	    //(or)
	    // alternatively provide namenode host and port info
	    conf.set("fs.default.name", hdfsPath);

	    if (args[0].equals("add")) {
	      if (args.length < 3) {
	        System.out.println("Usage: hdfsclient add <local_path> "
	            + "<hdfs_path>");
	        System.exit(1);
	      }

	      client.addFile(args[1], args[2], conf);

	    } else if (args[0].equals("read")) {
	      if (args.length < 2) {
	        System.out.println("Usage: hdfsclient read <hdfs_path>");
	        System.exit(1);
	      }

	      client.readFile(args[1], conf);

	    } else if (args[0].equals("delete")) {
	      if (args.length < 2) {
	        System.out.println("Usage: hdfsclient delete <hdfs_path>");
	        System.exit(1);
	      }

	      client.deleteFile(args[1], conf);

	    } else if (args[0].equals("mkdir")) {
	      if (args.length < 2) {
	        System.out.println("Usage: hdfsclient mkdir <hdfs_path>");
	        System.exit(1);
	      }

	      client.mkdir(args[1], conf);

	    } else {
	      System.out.println("Usage: hdfsclient add/read/delete/mkdir"
	          + " [<local_path> <hdfs_path>]");
	      System.exit(1);
	    }

	    System.out.println("Done!");
	  }
	  */
}


번호 제목 글쓴이 날짜 조회 수
129 [CDP7.1.7, Hive Replication]Hive Replication진행중 "The following columns have types incompatible with the existing columns in their respective positions " 오류 gooper 2023.12.27 7
128 [CDP7.1.7]Oozie job에서 ERROR: Kudu error(s) reported, first error: Timed out: Failed to write batch of 774 ops to tablet 8003f9a064bf4be5890a178439b2ba91가 발생하면서 쿼리가 실패하는 경우 gooper 2024.01.05 7
127 [CDP7.1.7]impala-shell수행시 간헐적으로 "-k requires a valid kerberos ticket but no valid kerberos ticket found." 오류 gooper 2023.11.16 11
126 임시 테이블에서 데이터를 읽어서 partitioned table에 입력하는 impala SQL문 예시 gooper 2023.11.10 15
125 [impala]insert into db명.table명 select a, b from db명.table명 쿼리 수행시 "Memory limit exceeded: Failed to allocate memory for Parquet page index"오류 조치 방법 gooper 2023.05.31 21
124 not leader of this config: current role FOLLOWER 오류 발생시 확인방법 총관리자 2022.01.17 23
123 kudu table와 impala(hive) table정보가 틀어져서 테이블을 읽지 못하는 경우(Error Loading Metadata) 조치방법 gooper 2023.11.10 24
122 [CDP7.1.7]Impala Query의 Memory Spilled 양은 ScratchFileUsedBytes값을 누적해서 구할 수 있다. gooper 2022.07.29 28
121 [Cloudera 6.3.4, Kudu]]Service Monitor에서 사용하는 metric중에 일부를 blacklist로 설정하여 모니터링 정보 수집 제외하는 방법 gooper 2022.07.08 31
120 Failed to write to server: (no server available): 총관리자 2022.01.17 32
119 AnalysisException: Incomplatible return type 'DECIMAL(38,0)' and 'DECIMAL(38,5)' of exprs가 발생시 조치 총관리자 2021.07.26 33
118 [KUDU] kudu tablet server여러가지 원인에 의해서 corrupted상태가 된 경우 복구방법 gooper 2023.03.28 33
117 [TLS/SSL]Kudu Tablet Server설정 총관리자 2022.05.13 33
116 spark에서 hive table을 읽어 출력하는 예제 소스 총관리자 2017.03.09 35
115 spark에서 hive table을 읽어 출력하는 예제 소스 총관리자 2017.03.09 37
114 [CDP7.1.7]impala-shell을 이용하여 kudu table에 insert/update수행시 발생하는 오류(Transport endpoint is not connected (error 107)) 발생시 확인할 내용 gooper 2023.11.30 40
113 spark 온라인 책자링크 (제목 : mastering-apache-spark) 총관리자 2016.05.25 48
112 [Impala jdbc]CDP7.1.7환경에서 java프로그램을 이용하여 kerberized impala cluster에 접근하여 SQL을 수행하는 방법 gooper 2023.08.22 53
111 [hive] hive.tbls테이블의 owner컬럼값은 hadoop.security.auth_to_local에 의해서 filtering된다. 총관리자 2022.04.14 55
110 [TLS/SSL]Kudu Master 설정하기 총관리자 2022.05.13 61

A personal place to organize information learned during the development of such Hadoop, Hive, Hbase, Semantic IoT, etc.
We are open to the required minutes. Please send inquiries to gooper@gooper.com.

위로