Hbase API

package cn.itcast_01_hbase;

import java.util.ArrayList;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.Cell;
import org.apache.hadoop.hbase.CellUtil;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.HColumnDescriptor;
import org.apache.hadoop.hbase.HTableDescriptor;
import org.apache.hadoop.hbase.MasterNotRunningException;
import org.apache.hadoop.hbase.TableName;
import org.apache.hadoop.hbase.ZooKeeperConnectionException;
import org.apache.hadoop.hbase.client.Connection;
import org.apache.hadoop.hbase.client.ConnectionFactory;
import org.apache.hadoop.hbase.client.Delete;
import org.apache.hadoop.hbase.client.Get;
import org.apache.hadoop.hbase.client.HBaseAdmin;
import org.apache.hadoop.hbase.client.HConnection;
import org.apache.hadoop.hbase.client.HConnectionManager;
import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.client.Result;
import org.apache.hadoop.hbase.client.ResultScanner;
import org.apache.hadoop.hbase.client.Scan;
import org.apache.hadoop.hbase.client.Table;
import org.apache.hadoop.hbase.filter.ColumnPrefixFilter;
import org.apache.hadoop.hbase.filter.CompareFilter;
import org.apache.hadoop.hbase.filter.FilterList;
import org.apache.hadoop.hbase.filter.FilterList.Operator;
import org.apache.hadoop.hbase.filter.RegexStringComparator;
import org.apache.hadoop.hbase.filter.RowFilter;
import org.apache.hadoop.hbase.filter.SingleColumnValueFilter;
import org.apache.hadoop.hbase.util.Bytes;
import org.junit.After;
import org.junit.Before;
import org.junit.Test;

public class HbaseTest {

    /**
     * 配置ss
     */
    static Configuration config = null;
    private Connection connection = null;
    private Table table = null;

    @Before
    public void init() throws Exception {
        config = HBaseConfiguration.create();// 配置
        config.set("hbase.zookeeper.quorum", "master,work1,work2");// zookeeper地址
        config.set("hbase.zookeeper.property.clientPort", "2181");// zookeeper端口
        connection = ConnectionFactory.createConnection(config);
        table = connection.getTable(TableName.valueOf("user"));
    }

    /**
     * 创建一个表
     * 
     * @throws Exception
     */
    @Test
    public void createTable() throws Exception {
        // 创建表管理类
        HBaseAdmin admin = new HBaseAdmin(config); // hbase表管理
        // 创建表描述类
        TableName tableName = TableName.valueOf("test3"); // 表名称
        HTableDescriptor desc = new HTableDescriptor(tableName);
        // 创建列族的描述类
        HColumnDescriptor family = new HColumnDescriptor("info"); // 列族
        // 将列族添加到表中
        desc.addFamily(family);
        HColumnDescriptor family2 = new HColumnDescriptor("info2"); // 列族
        // 将列族添加到表中
        desc.addFamily(family2);
        // 创建表
        admin.createTable(desc); // 创建表
    }

    @Test
    @SuppressWarnings("deprecation")
    public void deleteTable() throws MasterNotRunningException,
            ZooKeeperConnectionException, Exception {
        HBaseAdmin admin = new HBaseAdmin(config);
        admin.disableTable("test3");
        admin.deleteTable("test3");
        admin.close();
    }

    /**
     * 向hbase中增加数据
     * 
     * @throws Exception
     */
    @SuppressWarnings({ "deprecation", "resource" })
    @Test
    public void insertData() throws Exception {
        table.setAutoFlushTo(false);
        table.setWriteBufferSize(534534534);
        ArrayList<Put> arrayList = new ArrayList<Put>();
        for (int i = 21; i < 50; i++) {
            Put put = new Put(Bytes.toBytes("1234"+i));
            put.add(Bytes.toBytes("info"), Bytes.toBytes("name"), Bytes.toBytes("wangwu"+i));
            put.add(Bytes.toBytes("info"), Bytes.toBytes("password"), Bytes.toBytes(1234+i));
            arrayList.add(put);
        }

        //插入数据
        table.put(arrayList);
        //提交
        table.flushCommits();
    }

    /**
     * 修改数据
     * 
     * @throws Exception
     */
    @Test
    public void uodateData() throws Exception {
        Put put = new Put(Bytes.toBytes("1234"));
        put.add(Bytes.toBytes("info"), Bytes.toBytes("namessss"), Bytes.toBytes("lisi1234"));
        put.add(Bytes.toBytes("info"), Bytes.toBytes("password"), Bytes.toBytes(1234));
        //插入数据
        table.put(put);
        //提交
        table.flushCommits();
    }

    /**
     * 删除数据
     * 
     * @throws Exception
     */
    @Test
    public void deleteDate() throws Exception {
        Delete delete = new Delete(Bytes.toBytes("1234"));
        table.delete(delete);
        table.flushCommits();
    }

    /**
     * 单条查询
     * 
     * @throws Exception
     */
    @Test
    public void queryData() throws Exception {
        Get get = new Get(Bytes.toBytes("1234"));
        Result result = table.get(get);
        System.out.println(Bytes.toInt(result.getValue(Bytes.toBytes("info"), Bytes.toBytes("password"))));
        System.out.println(Bytes.toString(result.getValue(Bytes.toBytes("info"), Bytes.toBytes("namessss"))));
        System.out.println(Bytes.toString(result.getValue(Bytes.toBytes("info"), Bytes.toBytes("sex"))));
    }

    /**
     * 全表扫描
     * 
     * @throws Exception
     */
    @Test
    public void scanData() throws Exception {
        Scan scan = new Scan();
        //scan.addFamily(Bytes.toBytes("info"));
        //scan.addColumn(Bytes.toBytes("info"), Bytes.toBytes("password"));
        scan.setStartRow(Bytes.toBytes("wangsf_0"));
        scan.setStopRow(Bytes.toBytes("wangwu"));
        ResultScanner scanner = table.getScanner(scan);
        for (Result result : scanner) {
            System.out.println(Bytes.toInt(result.getValue(Bytes.toBytes("info"), Bytes.toBytes("password"))));
            System.out.println(Bytes.toString(result.getValue(Bytes.toBytes("info"), Bytes.toBytes("name"))));
            //System.out.println(Bytes.toInt(result.getValue(Bytes.toBytes("info2"), Bytes.toBytes("password"))));
            //System.out.println(Bytes.toString(result.getValue(Bytes.toBytes("info2"), Bytes.toBytes("name"))));
        }
    }

    /**
     * 全表扫描的过滤器
     * 列值过滤器
     * 
     * @throws Exception
     */
    @Test
    public void scanDataByFilter1() throws Exception {

        // 创建全表扫描的scan
        Scan scan = new Scan();
        //过滤器：列值过滤器
        SingleColumnValueFilter filter = new SingleColumnValueFilter(Bytes.toBytes("info"),
                Bytes.toBytes("name"), CompareFilter.CompareOp.EQUAL,
                Bytes.toBytes("zhangsan2"));
        // 设置过滤器
        scan.setFilter(filter);

        // 打印结果集
        ResultScanner scanner = table.getScanner(scan);
        for (Result result : scanner) {
            System.out.println(Bytes.toInt(result.getValue(Bytes.toBytes("info"), Bytes.toBytes("password"))));
            System.out.println(Bytes.toString(result.getValue(Bytes.toBytes("info"), Bytes.toBytes("name"))));
            //System.out.println(Bytes.toInt(result.getValue(Bytes.toBytes("info2"), Bytes.toBytes("password"))));
            //System.out.println(Bytes.toString(result.getValue(Bytes.toBytes("info2"), Bytes.toBytes("name"))));
        }

    }
    /**
     * rowkey过滤器
     * @throws Exception
     */
    @Test
    public void scanDataByFilter2() throws Exception {

        // 创建全表扫描的scan
        Scan scan = new Scan();
        //匹配rowkey以wangsenfeng开头的
        RowFilter filter = new RowFilter(CompareFilter.CompareOp.EQUAL, new RegexStringComparator("^12341"));
        // 设置过滤器
        scan.setFilter(filter);
        // 打印结果集
        ResultScanner scanner = table.getScanner(scan);
        for (Result result : scanner) {
            System.out.println(Bytes.toInt(result.getValue(Bytes.toBytes("info"), Bytes.toBytes("password"))));
            System.out.println(Bytes.toString(result.getValue(Bytes.toBytes("info"), Bytes.toBytes("name"))));
            //System.out.println(Bytes.toInt(result.getValue(Bytes.toBytes("info2"), Bytes.toBytes("password"))));
            //System.out.println(Bytes.toString(result.getValue(Bytes.toBytes("info2"), Bytes.toBytes("name"))));
        }


    }

    /**
     * 匹配列名前缀
     * @throws Exception
     */
    @Test
    public void scanDataByFilter3() throws Exception {

        // 创建全表扫描的scan
        Scan scan = new Scan();
        //匹配rowkey以wangsenfeng开头的
        ColumnPrefixFilter filter = new ColumnPrefixFilter(Bytes.toBytes("na"));
        // 设置过滤器
        scan.setFilter(filter);
        // 打印结果集
        ResultScanner scanner = table.getScanner(scan);
        for (Result result : scanner) {
            System.out.println("rowkey：" + Bytes.toString(result.getRow()));
            System.out.println("info:name："
                    + Bytes.toString(result.getValue(Bytes.toBytes("info"),
                            Bytes.toBytes("name"))));
            // 判断取出来的值是否为空
            if (result.getValue(Bytes.toBytes("info"), Bytes.toBytes("age")) != null) {
                System.out.println("info:age："
                        + Bytes.toInt(result.getValue(Bytes.toBytes("info"),
                                Bytes.toBytes("age"))));
            }
            // 判断取出来的值是否为空
            if (result.getValue(Bytes.toBytes("info"), Bytes.toBytes("sex")) != null) {
                System.out.println("infi:sex："
                        + Bytes.toInt(result.getValue(Bytes.toBytes("info"),
                                Bytes.toBytes("sex"))));
            }
            // 判断取出来的值是否为空
            if (result.getValue(Bytes.toBytes("info2"), Bytes.toBytes("name")) != null) {
                System.out
                .println("info2:name："
                        + Bytes.toString(result.getValue(
                                Bytes.toBytes("info2"),
                                Bytes.toBytes("name"))));
            }
            // 判断取出来的值是否为空
            if (result.getValue(Bytes.toBytes("info2"), Bytes.toBytes("age")) != null) {
                System.out.println("info2:age："
                        + Bytes.toInt(result.getValue(Bytes.toBytes("info2"),
                                Bytes.toBytes("age"))));
            }
            // 判断取出来的值是否为空
            if (result.getValue(Bytes.toBytes("info2"), Bytes.toBytes("sex")) != null) {
                System.out.println("info2:sex："
                        + Bytes.toInt(result.getValue(Bytes.toBytes("info2"),
                                Bytes.toBytes("sex"))));
            }
        }

    }
    /**
     * 过滤器集合
     * @throws Exception
     */
    @Test
    public void scanDataByFilter4() throws Exception {

        // 创建全表扫描的scan
        Scan scan = new Scan();
        //过滤器集合：MUST_PASS_ALL（and）,MUST_PASS_ONE(or)
        FilterList filterList = new FilterList(Operator.MUST_PASS_ONE);
        //匹配rowkey以wangsenfeng开头的
        RowFilter filter = new RowFilter(CompareFilter.CompareOp.EQUAL, new RegexStringComparator("^wangsenfeng"));
        //匹配name的值等于wangsenfeng
        SingleColumnValueFilter filter2 = new SingleColumnValueFilter(Bytes.toBytes("info"),
                Bytes.toBytes("name"), CompareFilter.CompareOp.EQUAL,
                Bytes.toBytes("zhangsan"));
        filterList.addFilter(filter);
        filterList.addFilter(filter2);
        // 设置过滤器
        scan.setFilter(filterList);
        // 打印结果集
        ResultScanner scanner = table.getScanner(scan);
        for (Result result : scanner) {
            System.out.println("rowkey：" + Bytes.toString(result.getRow()));
            System.out.println("info:name："
                    + Bytes.toString(result.getValue(Bytes.toBytes("info"),
                            Bytes.toBytes("name"))));
            // 判断取出来的值是否为空
            if (result.getValue(Bytes.toBytes("info"), Bytes.toBytes("age")) != null) {
                System.out.println("info:age："
                        + Bytes.toInt(result.getValue(Bytes.toBytes("info"),
                                Bytes.toBytes("age"))));
            }
            // 判断取出来的值是否为空
            if (result.getValue(Bytes.toBytes("info"), Bytes.toBytes("sex")) != null) {
                System.out.println("infi:sex："
                        + Bytes.toInt(result.getValue(Bytes.toBytes("info"),
                                Bytes.toBytes("sex"))));
            }
            // 判断取出来的值是否为空
            if (result.getValue(Bytes.toBytes("info2"), Bytes.toBytes("name")) != null) {
                System.out
                .println("info2:name："
                        + Bytes.toString(result.getValue(
                                Bytes.toBytes("info2"),
                                Bytes.toBytes("name"))));
            }
            // 判断取出来的值是否为空
            if (result.getValue(Bytes.toBytes("info2"), Bytes.toBytes("age")) != null) {
                System.out.println("info2:age："
                        + Bytes.toInt(result.getValue(Bytes.toBytes("info2"),
                                Bytes.toBytes("age"))));
            }
            // 判断取出来的值是否为空
            if (result.getValue(Bytes.toBytes("info2"), Bytes.toBytes("sex")) != null) {
                System.out.println("info2:sex："
                        + Bytes.toInt(result.getValue(Bytes.toBytes("info2"),
                                Bytes.toBytes("sex"))));
            }
        }

    }

    @After
    public void close() throws Exception {
        table.close();
        connection.close();
    }

}

package cn.itcast_01_hbase;

import java.io.IOException;
import java.util.ArrayList;
import java.util.List;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.HColumnDescriptor;
import org.apache.hadoop.hbase.HTableDescriptor;
import org.apache.hadoop.hbase.client.HBaseAdmin;
import org.apache.hadoop.hbase.client.HTable;
import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.client.Result;
import org.apache.hadoop.hbase.client.Scan;
import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
import org.apache.hadoop.hbase.mapreduce.TableMapReduceUtil;
import org.apache.hadoop.hbase.mapreduce.TableMapper;
import org.apache.hadoop.hbase.mapreduce.TableReducer;
import org.apache.hadoop.hbase.util.Bytes;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
/**
 * mapreduce操作hbase
 * @author wilson
 *
 */
public class HBaseMr {
    /**
     * 创建hbase配置
     */
    static Configuration config = null;
    static {
        config = HBaseConfiguration.create();
        config.set("hbase.zookeeper.quorum", "slave1,slave2,slave3");
        config.set("hbase.zookeeper.property.clientPort", "2181");
    }
    /**
     * 表信息
     */
    public static final String tableName = "word";//表名1
    public static final String colf = "content";//列族
    public static final String col = "info";//列
    public static final String tableName2 = "stat";//表名2
    /**
     * 初始化表结构，及其数据
     */
    public static void initTB() {
        HTable table=null;
        HBaseAdmin admin=null;
        try {
            admin = new HBaseAdmin(config);//创建表管理
            /*删除表*/
            if (admin.tableExists(tableName)||admin.tableExists(tableName2)) {
                System.out.println("table is already exists!");
                admin.disableTable(tableName);
                admin.deleteTable(tableName);
                admin.disableTable(tableName2);
                admin.deleteTable(tableName2);
            }
            /*创建表*/
                HTableDescriptor desc = new HTableDescriptor(tableName);
                HColumnDescriptor family = new HColumnDescriptor(colf);
                desc.addFamily(family);
                admin.createTable(desc);
                HTableDescriptor desc2 = new HTableDescriptor(tableName2);
                HColumnDescriptor family2 = new HColumnDescriptor(colf);
                desc2.addFamily(family2);
                admin.createTable(desc2);
            /*插入数据*/
                table = new HTable(config,tableName);
                table.setAutoFlush(false);
                table.setWriteBufferSize(500);
                List<Put> lp = new ArrayList<Put>();
                Put p1 = new Put(Bytes.toBytes("1"));
                p1.add(colf.getBytes(), col.getBytes(), ("The Apache Hadoop software library is a framework").getBytes());
                lp.add(p1);
                Put p2 = new Put(Bytes.toBytes("2"));p2.add(colf.getBytes(),col.getBytes(),("The common utilities that support the other Hadoop modules").getBytes());
                lp.add(p2);
                Put p3 = new Put(Bytes.toBytes("3"));
                p3.add(colf.getBytes(), col.getBytes(),("Hadoop by reading the documentation").getBytes());
                lp.add(p3);
                Put p4 = new Put(Bytes.toBytes("4"));
                p4.add(colf.getBytes(), col.getBytes(),("Hadoop from the release page").getBytes());
                lp.add(p4);
                Put p5 = new Put(Bytes.toBytes("5"));
                p5.add(colf.getBytes(), col.getBytes(),("Hadoop on the mailing list").getBytes());
                lp.add(p5);
                table.put(lp);
                table.flushCommits();
                lp.clear();
        } catch (Exception e) {
            e.printStackTrace();
        } finally {
            try {
                if(table!=null){
                    table.close();
                }
            } catch (IOException e) {
                e.printStackTrace();
            }
        }
    }
    /**
     * MyMapper 继承 TableMapper
     * TableMapper<Text,IntWritable> 
     * Text:输出的key类型，
     * IntWritable：输出的value类型
     */
    public static class MyMapper extends TableMapper<Text, IntWritable> {
        private static IntWritable one = new IntWritable(1);
        private static Text word = new Text();
        @Override
        //输入的类型为：key：rowKey； value：一行数据的结果集Result
        protected void map(ImmutableBytesWritable key, Result value,
                Context context) throws IOException, InterruptedException {
            //获取一行数据中的colf：col
            String words = Bytes.toString(value.getValue(Bytes.toBytes(colf), Bytes.toBytes(col)));// 表里面只有一个列族，所以我就直接获取每一行的值
            //按空格分割
            String itr[] = words.toString().split(" ");
            //循环输出word和1
            for (int i = 0; i < itr.length; i++) {
                word.set(itr[i]);
                context.write(word, one);
            }
        }
    }
    /**
     * MyReducer 继承 TableReducer
     * TableReducer<Text,IntWritable> 
     * Text:输入的key类型，
     * IntWritable：输入的value类型，
     * ImmutableBytesWritable：输出类型，表示rowkey的类型
     */
    public static class MyReducer extends
            TableReducer<Text, IntWritable, ImmutableBytesWritable> {
        @Override
        protected void reduce(Text key, Iterable<IntWritable> values,
                Context context) throws IOException, InterruptedException {
            //对mapper的数据求和
            int sum = 0;
            for (IntWritable val : values) {//叠加
                sum += val.get();
            }
            // 创建put，设置rowkey为单词
            Put put = new Put(Bytes.toBytes(key.toString()));
            // 封装数据
            put.add(Bytes.toBytes(colf), Bytes.toBytes(col),Bytes.toBytes(String.valueOf(sum)));
            //写到hbase,需要指定rowkey、put
            context.write(new ImmutableBytesWritable(Bytes.toBytes(key.toString())),put);
        }
    }

    public static void main(String[] args) throws IOException,
            ClassNotFoundException, InterruptedException {
        config.set("df.default.name", "hdfs://master:9000/");//设置hdfs的默认路径
        config.set("hadoop.job.ugi", "hadoop,hadoop");//用户名，组
        config.set("mapred.job.tracker", "master:9001");//设置jobtracker在哪
        //初始化表
        initTB();//初始化表
        //创建job
        Job job = new Job(config, "HBaseMr");//job
        job.setJarByClass(HBaseMr.class);//主类
        //创建scan
        Scan scan = new Scan();
        //可以指定查询某一列
        scan.addColumn(Bytes.toBytes(colf), Bytes.toBytes(col));
        //创建查询hbase的mapper，设置表名、scan、mapper类、mapper的输出key、mapper的输出value
        TableMapReduceUtil.initTableMapperJob(tableName, scan, MyMapper.class,Text.class, IntWritable.class, job);
        //创建写入hbase的reducer，指定表名、reducer类、job
        TableMapReduceUtil.initTableReducerJob(tableName2, MyReducer.class, job);
        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }
}