Java 连接HDFS，读取文件

获取HDFS文件连接

public static FileSystem getFileSystem() {
    try {
        Configuration conf = new Configuration();
        //下面三行如果不加则自动读取项目路径下的配置文件
        conf.addResource(new Path("c://conf/core-site.xml");
        conf.addResource(new Path("c://conf/hdfs-site.xml");
	conf.addResource(new Path("c://conf/mapred-site.xml");

        fs = FileSystem.get(conf);
    } catch (IOException e) {
         e.printStackTrace();
    }
    return fs;
}

获取文件大小

 public static Long getFileLen(String hdfsPath) throws IOException {
    	return getFileSystem().getFileStatus(new Path(hdfsPath)).getLen();
    }

获取文件字符串

 public static String readStringFromHdfsNoPage(String Path, int  pageNum, int readSize ) throws IllegalArgumentException, IOException {
        FSDataInputStream in = HDFSUtil.getFileSystem().open(new Path(Path));
        BufferedReader reader = new BufferedReader(new InputStreamReader(in));
        StringBuffer buffer = new StringBuffer();
        String line = "";
        while ((line = in.readLine()) != null){
          buffer.append(line);
        }
        reader.close();
        in.close();
        return buffer.toString();
    }

获取文件二进制数据

public static byte[] readByteFromHdfs(String path, int  pageNum, int readSize ) throws IllegalArgumentException, IOException {
    	FSDataInputStream in = HDFSUtil.getFileSystem().open(new Path(path));
    	FileStatus stat = HDFSUtil.getFileSystem().getFileStatus(new Path(path));  
        byte[] buffer = new byte[Integer.parseInt(String.valueOf(stat.getLen()))];  
        in.readFully(0, buffer);  
        in.close();  
        return buffer;
    }

获取目录下文件列表

 public static List<String> ListDir(String srcPath) throws Exception
    {
    	List<String> fileNameList = new ArrayList<String>();
        FileStatus[] srcFileStatus = getFileSystem().listStatus(new Path(srcPath));
        Path[] srcFilePath = FileUtil.stat2Paths(srcFileStatus);
        for (int i = 0; i < srcFilePath.length; i++)
        {
            String srcFile = srcFilePath[i].toString();
            int fileNamePosi = srcFile.lastIndexOf('/');
            String fileName = srcFile.substring(fileNamePosi + 1);
            fileNameList.add(fileName);
        }
        return fileNameList;
    }

配置文件

‍m103替换为hdfs服务地址‍

‍core-site.xml

<?xml version="1.0" encoding="UTF-8"?>

<!--Autogenerated by Cloudera Manager-->
<configuration>
  <property>
    <name>fs.defaultFS</name>
    <value>hdfs://m103:8020</value>
  </property>
  <property>
    <name>fs.trash.interval</name>
    <value>1</value>
  </property>
  <property>
    <name>io.compression.codecs</name>
    <value>org.apache.hadoop.io.compress.DefaultCodec,org.apache.hadoop.io.compress.GzipCodec,org.apache.hadoop.io.compress.BZip2Codec,org.apache.hadoop.io.compress.DeflateCodec,org.apache.hadoop.io.compress.SnappyCodec,org.apache.hadoop.io.compress.Lz4Codec</value>
  </property>
  <property>
    <name>hadoop.security.authentication</name>
    <value>simple</value>
  </property>
  <property>
    <name>hadoop.security.authorization</name>
    <value>false</value>
  </property>
  <property>
    <name>hadoop.rpc.protection</name>
    <value>authentication</value>
  </property>
  <property>
    <name>hadoop.security.auth_to_local</name>
    <value>DEFAULT</value>
  </property>
  <property>
    <name>hadoop.proxyuser.oozie.hosts</name>
    <value>*</value>
  </property>
  <property>
    <name>hadoop.proxyuser.oozie.groups</name>
    <value>*</value>
  </property>
  <property>
    <name>hadoop.proxyuser.mapred.hosts</name>
    <value>*</value>
  </property>
  <property>
    <name>hadoop.proxyuser.mapred.groups</name>
    <value>*</value>
  </property>
  <property>
    <name>hadoop.proxyuser.flume.hosts</name>
    <value>*</value>
  </property>
  <property>
    <name>hadoop.proxyuser.flume.groups</name>
    <value>*</value>
  </property>
  <property>
    <name>hadoop.proxyuser.HTTP.hosts</name>
    <value>*</value>
  </property>
  <property>
    <name>hadoop.proxyuser.HTTP.groups</name>
    <value>*</value>
  </property>
  <property>
    <name>hadoop.proxyuser.hive.hosts</name>
    <value>*</value>
  </property>
  <property>
    <name>hadoop.proxyuser.hive.groups</name>
    <value>*</value>
  </property>
  <property>
    <name>hadoop.proxyuser.hue.hosts</name>
    <value>*</value>
  </property>
  <property>
    <name>hadoop.proxyuser.hue.groups</name>
    <value>*</value>
  </property>
  <property>
    <name>hadoop.proxyuser.httpfs.hosts</name>
    <value>*</value>
  </property>
  <property>
    <name>hadoop.proxyuser.httpfs.groups</name>
    <value>*</value>
  </property>
  <property>
    <name>hadoop.proxyuser.hdfs.groups</name>
    <value>*</value>
  </property>
  <property>
    <name>hadoop.proxyuser.hdfs.hosts</name>
    <value>*</value>
  </property>
  <property>
    <name>hadoop.proxyuser.yarn.hosts</name>
    <value>*</value>
  </property>
  <property>
    <name>hadoop.proxyuser.yarn.groups</name>
    <value>*</value>
  </property>
  <property>
    <name>hadoop.security.group.mapping</name>
    <value>org.apache.hadoop.security.ShellBasedUnixGroupsMapping</value>
  </property>
  <property>
    <name>hadoop.security.instrumentation.requires.admin</name>
    <value>false</value>
  </property>
  <property>
    <name>net.topology.script.file.name</name>
    <value>/etc/hadoop/conf.cloudera.yarn/topology.py</value>
  </property>
  <property>
    <name>io.file.buffer.size</name>
    <value>65536</value>
  </property>
  <property>
    <name>hadoop.ssl.enabled</name>
    <value>false</value>
  </property>
  <property>
    <name>hadoop.ssl.require.client.cert</name>
    <value>false</value>
    <final>true</final>
  </property>
  <property>
    <name>hadoop.ssl.keystores.factory.class</name>
    <value>org.apache.hadoop.security.ssl.FileBasedKeyStoresFactory</value>
    <final>true</final>
  </property>
  <property>
    <name>hadoop.ssl.server.conf</name>
    <value>ssl-server.xml</value>
    <final>true</final>
  </property>
  <property>
    <name>hadoop.ssl.client.conf</name>
    <value>ssl-client.xml</value>
    <final>true</final>
  </property>
</configuration>

hdfs-site.xml

<?xml version="1.0" encoding="UTF-8"?>

<!--Autogenerated by Cloudera Manager-->
<configuration>
  <property>
    <name>dfs.namenode.name.dir</name>
    <value>file:///mnt/sdc1/dfs/nn</value>
  </property>
  <property>
    <name>dfs.namenode.servicerpc-address</name>
    <value>m103:8022</value>
  </property>
  <property>
    <name>dfs.https.address</name>
    <value>m103:50470</value>
  </property>
  <property>
    <name>dfs.https.port</name>
    <value>50470</value>
  </property>
  <property>
    <name>dfs.namenode.http-address</name>
    <value>m103:50070</value>
  </property>
  <property>
    <name>dfs.replication</name>
    <value>3</value>
  </property>
  <property>
    <name>dfs.blocksize</name>
    <value>134217728</value>
  </property>
  <property>
    <name>dfs.client.use.datanode.hostname</name>
    <value>false</value>
  </property>
  <property>
    <name>fs.permissions.umask-mode</name>
    <value>022</value>
  </property>
  <property>
    <name>dfs.namenode.acls.enabled</name>
    <value>false</value>
  </property>
  <property>
    <name>dfs.block.local-path-access.user</name>
    <value>cloudera-scm</value>
  </property>
  <property>
    <name>dfs.client.read.shortcircuit</name>
    <value>false</value>
  </property>
  <property>
    <name>dfs.domain.socket.path</name>
    <value>/var/run/hdfs-sockets/dn</value>
  </property>
  <property>
    <name>dfs.client.read.shortcircuit.skip.checksum</name>
    <value>false</value>
  </property>
  <property>
    <name>dfs.client.domain.socket.data.traffic</name>
    <value>false</value>
  </property>
  <property>
    <name>dfs.datanode.hdfs-blocks-metadata.enabled</name>
    <value>true</value>
  </property>
  <property>
    <name>fs.http.impl</name>
    <value>com.scistor.datavision.fs.HTTPFileSystem</value>
  </property>
</configuration>

mapred-site.xml‍

<?xml version="1.0" encoding="UTF-8"?>

<!--Autogenerated by Cloudera Manager-->
<configuration>
  <property>
    <name>mapreduce.job.split.metainfo.maxsize</name>
    <value>10000000</value>
  </property>
  <property>
    <name>mapreduce.job.counters.max</name>
    <value>120</value>
  </property>
  <property>
    <name>mapreduce.output.fileoutputformat.compress</name>
    <value>true</value>
  </property>
  <property>
    <name>mapreduce.output.fileoutputformat.compress.type</name>
    <value>BLOCK</value>
  </property>
  <property>
    <name>mapreduce.output.fileoutputformat.compress.codec</name>
    <value>org.apache.hadoop.io.compress.SnappyCodec</value>
  </property>
  <property>
    <name>mapreduce.map.output.compress.codec</name>
    <value>org.apache.hadoop.io.compress.SnappyCodec</value>
  </property>
  <property>
    <name>mapreduce.map.output.compress</name>
    <value>true</value>
  </property>
  <property>
    <name>zlib.compress.level</name>
    <value>DEFAULT_COMPRESSION</value>
  </property>
  <property>
    <name>mapreduce.task.io.sort.factor</name>
    <value>64</value>
  </property>
  <property>
    <name>mapreduce.map.sort.spill.percent</name>
    <value>0.8</value>
  </property>
  <property>
    <name>mapreduce.reduce.shuffle.parallelcopies</name>
    <value>10</value>
  </property>
  <property>
    <name>mapreduce.task.timeout</name>
    <value>600000</value>
  </property>
  <property>
    <name>mapreduce.client.submit.file.replication</name>
    <value>1</value>
  </property>
  <property>
    <name>mapreduce.job.reduces</name>
    <value>24</value>
  </property>
  <property>
    <name>mapreduce.task.io.sort.mb</name>
    <value>256</value>
  </property>
  <property>
    <name>mapreduce.map.speculative</name>
    <value>false</value>
  </property>
  <property>
    <name>mapreduce.reduce.speculative</name>
    <value>false</value>
  </property>
  <property>
    <name>mapreduce.job.reduce.slowstart.completedmaps</name>
    <value>0.8</value>
  </property>
  <property>
    <name>mapreduce.jobhistory.address</name>
    <value>m103:10020</value>
  </property>
  <property>
    <name>mapreduce.jobhistory.webapp.address</name>
    <value>m103:19888</value>
  </property>
  <property>
    <name>mapreduce.jobhistory.webapp.https.address</name>
    <value>m103:19890</value>
  </property>
  <property>
    <name>mapreduce.jobhistory.admin.address</name>
    <value>m103:10033</value>
  </property>
  <property>
    <name>mapreduce.framework.name</name>
    <value>yarn</value>
  </property>
  <property>
    <name>yarn.app.mapreduce.am.staging-dir</name>
    <value>/user</value>
  </property>
  <property>
    <name>mapreduce.am.max-attempts</name>
    <value>2</value>
  </property>
  <property>
    <name>yarn.app.mapreduce.am.resource.mb</name>
    <value>2048</value>
  </property>
  <property>
    <name>yarn.app.mapreduce.am.resource.cpu-vcores</name>
    <value>1</value>
  </property>
  <property>
    <name>mapreduce.job.ubertask.enable</name>
    <value>false</value>
  </property>
  <property>
    <name>yarn.app.mapreduce.am.command-opts</name>
    <value>-Djava.net.preferIPv4Stack=true -Xmx1717986918</value>
  </property>
  <property>
    <name>mapreduce.map.java.opts</name>
    <value>-Djava.net.preferIPv4Stack=true -Xmx1717986918</value>
  </property>
  <property>
    <name>mapreduce.reduce.java.opts</name>
    <value>-Djava.net.preferIPv4Stack=true -Xmx2576980378</value>
  </property>
  <property>
    <name>yarn.app.mapreduce.am.admin.user.env</name>
    <value>LD_LIBRARY_PATH=$HADOOP_COMMON_HOME/lib/native:$JAVA_LIBRARY_PATH</value>
  </property>
  <property>
    <name>mapreduce.map.memory.mb</name>
    <value>2048</value>
  </property>
  <property>
    <name>mapreduce.map.cpu.vcores</name>
    <value>1</value>
  </property>
  <property>
    <name>mapreduce.reduce.memory.mb</name>
    <value>3072</value>
  </property>
  <property>
    <name>mapreduce.reduce.cpu.vcores</name>
    <value>1</value>
  </property>
  <property>
    <name>mapreduce.application.classpath</name>
    <value>$HADOOP_MAPRED_HOME/*,$HADOOP_MAPRED_HOME/lib/*,$MR2_CLASSPATH,$CDH_HCAT_HOME/share/hcatalog/*,$CDH_HIVE_HOME/lib/*,/etc/hive/conf,/opt/cloudera/parcels/CDH/lib/udps/*</value>
  </property>
  <property>
    <name>mapreduce.admin.user.env</name>
    <value>LD_LIBRARY_PATH=$HADOOP_COMMON_HOME/lib/native:$JAVA_LIBRARY_PATH</value>
  </property>
  <property>
    <name>mapreduce.shuffle.max.connections</name>
    <value>80</value>
  </property>
</configuration>