HBase API操作

环境准备

新建项目后在pom.xml中添加依赖：

<dependency>
    <groupId>org.apache.hbase</groupId>
    <artifactId>hbase-server</artifactId>
    <version>1.3.1</version>
</dependency>

<dependency>
    <groupId>org.apache.hbase</groupId>
    <artifactId>hbase-client</artifactId>
    <version>1.3.1</version>
</dependency>

<dependency>
    <groupId>jdk.tools</groupId>
    <artifactId>jdk.tools</artifactId>
    <version>1.8</version>
    <scope>system</scope>



    <systemPath>${JAVA_HOME}/lib/tools.jar</systemPath>
</dependency>

2 HBaseAPI

2.1 获取Configuration对象

public static Configuration conf;
static{
    //使用HBaseConfiguration的单例方法实例化
    conf = HBaseConfiguration.create();
conf.set("hbase.zookeeper.quorum", "192.168.9.102");
conf.set("hbase.zookeeper.property.clientPort", "2181");
}

2.2 判断表是否存在

public static boolean isTableExist(String tableName) throws MasterNotRunningException,
 ZooKeeperConnectionException, IOException{
    //在HBase中管理、访问表需要先创建HBaseAdmin对象
//Connection connection = ConnectionFactory.createConnection(conf);
//HBaseAdmin admin = (HBaseAdmin) connection.getAdmin();
    HBaseAdmin admin = new HBaseAdmin(conf);
    return admin.tableExists(tableName);
}　

2.3 创建表

public static void createTable(String tableName, String... columnFamily) throws
 MasterNotRunningException, ZooKeeperConnectionException, IOException{
    HBaseAdmin admin = new HBaseAdmin(conf);
    //判断表是否存在
    if(isTableExist(tableName)){
        System.out.println("表" + tableName + "已存在");
        //System.exit(0);
    }else{
        //创建表属性对象,表名需要转字节
        HTableDescriptor descriptor = new HTableDescriptor(TableName.valueOf(tableName));
        //创建多个列族
        for(String cf : columnFamily){
            descriptor.addFamily(new HColumnDescriptor(cf));
        }
        //根据对表的配置，创建表
        admin.createTable(descriptor);
        System.out.println("表" + tableName + "创建成功！");
    }
}

2.4 删除表

public static void dropTable(String tableName) throws MasterNotRunningException,
 ZooKeeperConnectionException, IOException{
    HBaseAdmin admin = new HBaseAdmin(conf);
    if(isTableExist(tableName)){
        admin.disableTable(tableName);
        admin.deleteTable(tableName);
        System.out.println("表" + tableName + "删除成功！");
    }else{
        System.out.println("表" + tableName + "不存在！");
    }
　　

2.5 向表中插入数据

public static void addRowData(String tableName, String rowKey, String columnFamily, String
 column, String value) throws IOException{
    //创建HTable对象
    HTable hTable = new HTable(conf, tableName);
    //向表中插入数据
    Put put = new Put(Bytes.toBytes(rowKey));
    //向Put对象中组装数据
    put.add(Bytes.toBytes(columnFamily), Bytes.toBytes(column), Bytes.toBytes(value));
    hTable.put(put);
    hTable.close();
    System.out.println("插入数据成功");
}

2.6 删除多行数据

public static void deleteMultiRow(String tableName, String... rows) throws IOException{
    HTable hTable = new HTable(conf, tableName);
    List<Delete> deleteList = new ArrayList<Delete>();
    for(String row : rows){
        Delete delete = new Delete(Bytes.toBytes(row));
        deleteList.add(delete);
    }
    hTable.delete(deleteList);
    hTable.close();
}

 

public static void deleteMultiRow(String tableName, String... rows) throws IOException{
    HTable hTable = new HTable(conf, tableName);
    List<Delete> deleteList = new ArrayList<Delete>();
    for(String row : rows){
        Delete delete = new Delete(Bytes.toBytes(row));
        deleteList.add(delete);
    }
    hTable.delete(deleteList);
    hTable.close();
}

 

2.7 获取所有数据

public static void getAllRows(String tableName) throws IOException{
    HTable hTable = new HTable(conf, tableName);
    //得到用于扫描region的对象
    Scan scan = new Scan();
    //使用HTable得到resultcanner实现类的对象
    ResultScanner resultScanner = hTable.getScanner(scan);
    for(Result result : resultScanner){
        Cell[] cells = result.rawCells();
        for(Cell cell : cells){
            //得到rowkey
            System.out.println("行键:" + Bytes.toString(CellUtil.cloneRow(cell)));
            //得到列族
            System.out.println("列族" + Bytes.toString(CellUtil.cloneFamily(cell)));
            System.out.println("列:" + Bytes.toString(CellUtil.cloneQualifier(cell)));
            System.out.println("值:" + Bytes.toString(CellUtil.cloneValue(cell)));
        }
    }
}

2.8 获取某一行数据

public static void getRow(String tableName, String rowKey) throws IOException{
    HTable table = new HTable(conf, tableName);
    Get get = new Get(Bytes.toBytes(rowKey));
    //get.setMaxVersions();显示所有版本
    //get.setTimeStamp();显示指定时间戳的版本
    Result result = table.get(get);
    for(Cell cell : result.rawCells()){
        System.out.println("行键:" + Bytes.toString(result.getRow()));
        System.out.println("列族" + Bytes.toString(CellUtil.cloneFamily(cell)));
        System.out.println("列:" + Bytes.toString(CellUtil.cloneQualifier(cell)));
        System.out.println("值:" + Bytes.toString(CellUtil.cloneValue(cell)));
        System.out.println("时间戳:" + cell.getTimestamp());
    }
}　

2.9 获取某一行指定“列族:列”的数据

public static void getRowQualifier(String tableName, String rowKey, String family, String
 qualifier) throws IOException{
    HTable table = new HTable(conf, tableName);
    Get get = new Get(Bytes.toBytes(rowKey));
    get.addColumn(Bytes.toBytes(family), Bytes.toBytes(qualifier));
    Result result = table.get(get);
    for(Cell cell : result.rawCells()){
        System.out.println("行键:" + Bytes.toString(result.getRow()));
        System.out.println("列族" + Bytes.toString(CellUtil.cloneFamily(cell)));
        System.out.println("列:" + Bytes.toString(CellUtil.cloneQualifier(cell)));
        System.out.println("值:" + Bytes.toString(CellUtil.cloneValue(cell)));
    }
}

 

　

3 MapReduce

通过HBase的相关JavaAPI，我们可以实现伴随HBase操作的MapReduce过程，比如使用MapReduce将数据从本地文件系统导入到HBase的表中，比如我们从HBase中读取一些原始数据后使用MapReduce做数据分析。

3.1 官方HBase-MapReduce

1．查看HBase的MapReduce任务的执行

$ bin/hbase mapredcp

2．环境变量的导入

（1）执行环境变量的导入（临时生效，在命令行执行下述操作）

$ export HBASE_HOME=/opt/module/hbase-1.3.1
$ export HADOOP_HOME=/opt/module/hadoop-2.7.2
$ export HADOOP_CLASSPATH=`${HBASE_HOME}/bin/hbase mapredcp`　

（2）永久生效：在/etc/profile配置

export HBASE_HOME=/opt/module/hbase-1.3.1
export HADOOP_HOME=/opt/module/hadoop-2.7.2

并在hadoop-env.sh中配置：（注意：在for循环之后配）

并在hadoop-env.sh中配置：（注意：在for循环之后配）
export HADOOP_CLASSPATH=$HADOOP_CLASSPATH:/opt/module/hbase/lib/*

3．运行官方的MapReduce任务

-- 案例一：统计Student表中有多少行数据

$ /opt/module/hadoop-2.7.2/bin/yarn jar lib/hbase-server-1.3.1.jar rowcounter student

　

-- 案例二：使用MapReduce将本地数据导入到HBase

1）在本地创建一个tsv格式的文件：fruit.tsv

1001    Apple    Red
1002    Pear        Yellow
1003    Pineapple    Yellow

2）创建HBase表

hbase(main):001:0> create 'fruit','info'　

3）在HDFS中创建input_fruit文件夹并上传fruit.tsv文件

$ /opt/module/hadoop-2.7.2/bin/hdfs dfs -mkdir /input_fruit/
$ /opt/module/hadoop-2.7.2/bin/hdfs dfs -put fruit.tsv /input_fruit/

4）执行MapReduce到HBase的fruit表中

$ /opt/module/hadoop-2.7.2/bin/yarn jar lib/hbase-server-1.3.1.jar importtsv \
-Dimporttsv.columns=HBASE_ROW_KEY,info:name,info:color fruit \
hdfs://hadoop102:9000/input_fruit

5）使用scan命令查看导入后的结果

hbase(main):001:0> scan ‘fruit’

3.2 自定义HBase-MapReduce1

目标：将fruit表中的一部分数据，通过MR迁入到fruit_mr表中。

分步实现：

1．构建ReadFruitMapper类，用于读取fruit表中的数据

import java.io.IOException;
import org.apache.hadoop.hbase.Cell;
import org.apache.hadoop.hbase.CellUtil;
import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.client.Result;
import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
import org.apache.hadoop.hbase.mapreduce.TableMapper;
import org.apache.hadoop.hbase.util.Bytes;

public class ReadFruitMapper extends TableMapper<ImmutableBytesWritable, Put> {

    @Override
    protected void map(ImmutableBytesWritable key, Result value, Context context) 
    throws IOException, InterruptedException {
    //将fruit的name和color提取出来，相当于将每一行数据读取出来放入到Put对象中。
        Put put = new Put(key.get());
        //遍历添加column行
        for(Cell cell: value.rawCells()){
            //添加/克隆列族:info
            if("info".equals(Bytes.toString(CellUtil.cloneFamily(cell)))){
                //添加/克隆列：name
                if("name".equals(Bytes.toString(CellUtil.cloneQualifier(cell)))){
                    //将该列cell加入到put对象中
                    put.add(cell);
                    //添加/克隆列:color
                }else if("color".equals(Bytes.toString(CellUtil.cloneQualifier(cell)))){
                    //向该列cell加入到put对象中
                    put.add(cell);
                }
            }
        }
        //将从fruit读取到的每行数据写入到context中作为map的输出
        context.write(key, put);
    }
}

2． 构建WriteFruitMRReducer类，用于将读取到的fruit表中的数据写入到fruit_mr表中

import java.io.IOException;
import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
import org.apache.hadoop.hbase.mapreduce.TableReducer;
import org.apache.hadoop.io.NullWritable;

public class WriteFruitMRReducer extends TableReducer<ImmutableBytesWritable, Put, NullWritable> {
    @Override
    protected void reduce(ImmutableBytesWritable key, Iterable<Put> values, Context context) 
    throws IOException, InterruptedException {
        //读出来的每一行数据写入到fruit_mr表中
        for(Put put: values){
            context.write(NullWritable.get(), put);
        }
    }
}

3．构建Fruit2FruitMRRunner extends Configured implements Tool用于组装运行Job任务

//组装Job
    public int run(String[] args) throws Exception {
        //得到Configuration
        Configuration conf = this.getConf();
        //创建Job任务
        Job job = Job.getInstance(conf, this.getClass().getSimpleName());
        job.setJarByClass(Fruit2FruitMRRunner.class);

        //配置Job
        Scan scan = new Scan();
        scan.setCacheBlocks(false);
        scan.setCaching(500);

        //设置Mapper，注意导入的是mapreduce包下的，不是mapred包下的，后者是老版本
        TableMapReduceUtil.initTableMapperJob(
        "fruit", //数据源的表名
        scan, //scan扫描控制器
        ReadFruitMapper.class,//设置Mapper类
        ImmutableBytesWritable.class,//设置Mapper输出key类型
        Put.class,//设置Mapper输出value值类型
        job//设置给哪个JOB
        );
        //设置Reducer
        TableMapReduceUtil.initTableReducerJob("fruit_mr", WriteFruitMRReducer.class, job);
        //设置Reduce数量，最少1个
        job.setNumReduceTasks(1);

        boolean isSuccess = job.waitForCompletion(true);
        if(!isSuccess){
            throw new IOException("Job running with error");
        }
        return isSuccess ? 0 : 1;
    }

4．主函数中调用运行该Job任务

public static void main( String[] args ) throws Exception{
Configuration conf = HBaseConfiguration.create();
int status = ToolRunner.run(conf, new Fruit2FruitMRRunner(), args);
System.exit(status);
}

5．打包运行任务

$ /opt/module/hadoop-2.7.2/bin/yarn jar ~/softwares/jars/hbase-0.0.1-SNAPSHOT.jar
 com.z.hbase.mr1.Fruit2FruitMRRunner

提示：运行任务前，如果待数据导入的表不存在，则需要提前创建。

提示：maven打包命令：-P local clean package或-P dev clean package install（将第三方jar包一同打包，需要插件：maven-shade-plugin）

3.3 自定义HBase-MapReduce2

目标：实现将HDFS中的数据写入到HBase表中。

分步实现：

1．构建ReadFruitFromHDFSMapper于读取HDFS中的文件数据

import java.io.IOException;

import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
import org.apache.hadoop.hbase.util.Bytes;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;

public class ReadFruitFromHDFSMapper extends Mapper<LongWritable, Text, ImmutableBytesWritable, Put> {
    @Override
    protected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {
        //从HDFS中读取的数据
        String lineValue = value.toString();
        //读取出来的每行数据使用\t进行分割，存于String数组
        String[] values = lineValue.split("\t");
        
        //根据数据中值的含义取值
        String rowKey = values[0];
        String name = values[1];
        String color = values[2];
        
        //初始化rowKey
        ImmutableBytesWritable rowKeyWritable = new ImmutableBytesWritable(Bytes.toBytes(rowKey));
        
        //初始化put对象
        Put put = new Put(Bytes.toBytes(rowKey));
        
        //参数分别:列族、列、值  
        put.add(Bytes.toBytes("info"), Bytes.toBytes("name"),  Bytes.toBytes(name)); 
        put.add(Bytes.toBytes("info"), Bytes.toBytes("color"),  Bytes.toBytes(color)); 
        
        context.write(rowKeyWritable, put);
    }
}

2．构建WriteFruitMRFromTxtReducer类

import java.io.IOException;
import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
import org.apache.hadoop.hbase.mapreduce.TableReducer;
import org.apache.hadoop.io.NullWritable;

public class WriteFruitMRFromTxtReducer extends TableReducer<ImmutableBytesWritable, Put, NullWritable> {
    @Override
    protected void reduce(ImmutableBytesWritable key, Iterable<Put> values, Context context) throws IOException, InterruptedException {
        //读出来的每一行数据写入到fruit_hdfs表中
        for(Put put: values){
            context.write(NullWritable.get(), put);
        }
    }
}

3．创建Txt2FruitRunner组装Job

public int run(String[] args) throws Exception {
//得到Configuration
Configuration conf = this.getConf();

//创建Job任务
Job job = Job.getInstance(conf, this.getClass().getSimpleName());
job.setJarByClass(Txt2FruitRunner.class);
Path inPath = new Path("hdfs://hadoop102:9000/input_fruit/fruit.tsv");
FileInputFormat.addInputPath(job, inPath);

//设置Mapper
job.setMapperClass(ReadFruitFromHDFSMapper.class);
job.setMapOutputKeyClass(ImmutableBytesWritable.class);
job.setMapOutputValueClass(Put.class);

//设置Reducer
TableMapReduceUtil.initTableReducerJob("fruit_mr", WriteFruitMRFromTxtReducer.class, job);

//设置Reduce数量，最少1个
job.setNumReduceTasks(1);

boolean isSuccess = job.waitForCompletion(true);
if(!isSuccess){
throw new IOException("Job running with error");
}

return isSuccess ? 0 : 1;
}

4．调用执行Job

public static void main(String[] args) throws Exception {
        Configuration conf = HBaseConfiguration.create();
        int status = ToolRunner.run(conf, new Txt2FruitRunner(), args);
        System.exit(status);
}

5．打包运行

$ /opt/module/hadoop-2.7.2/bin/yarn jar hbase-0.0.1-SNAPSHOT.jar com.atguigu.hbase.mr2.Txt2FruitRunner

提示：运行任务前，如果待数据导入的表不存在，则需要提前创建之。

提示：maven打包命令：-P local clean package或-P dev clean package install（将第三方jar包一同打包，需要插件：maven-shade-plugin）