HBase1.0+ java-api 介绍

该文章已在ChinaUnix公众号上发表，链接地址：
http://mp.weixin.qq.com/s?__biz=MjM5NTU2MTQwNA==&mid=2650652400&idx=2&sn=f29b2ee9f4f8a7f74c28ee9939fc03c0&scene=0#wechat_redirect

在网上查了hbase的java client api的介绍，发现很多都是之前的版本，虽然现在还可以运行，但是里面有很多不建议使用（@deprecated）的class及相关方法。其中很关键的就是增加了Connection类，使其给人感觉更像一个专业的客户端api，还有就是用Admin替换了HBaseAdmin，还有一些细节上的修改，比如：增加了TableName，获取数据的时候用Cell替换KeyValue，以及其他的一些修改。
本文主要介绍了这样的一些改动，并写了一些常用操作的代码以供参考。

---

1. 创建config和connection

org.apache.hadoop.hbase.client.Connection是hbase从0.99.0开始增加的类，Connection主要创建一个hbase客户端连接，用于和hbase通信：

Configuration conf = HBaseConfiguration.create();
conf.addResource("hbase-site.xml");
Connection connect = ConnectionFactory.createConnection(conf);

---

2. 创建表

0.99.0之前的版本主要用HBaseAdmin创建新的Table，但是在0.99.0之后，可以直接用Admin来create, drop, list, enable, disable Table了。
还有一个要注意的，在操作table的过程中，表名称不能再用String类型，而需要用TableName类型了：

    /* test create table. */
    public static void createTable(String tableName, String[] family) 
            throws Exception {
        Admin admin = connect.getAdmin();

        TableName tn = TableName.valueOf(tableName);
        HTableDescriptor desc = new HTableDescriptor(tn);
        for (int i = 0; i < family.length; i++) {
            desc.addFamily(new HColumnDescriptor(family[i]));
        }

        if (admin.tableExists(tn)) {
            System.out.println("table Exists!");
            System.exit(0);
        } else {
            admin.createTable(desc);
            System.out.println("create table Success!");
        }
    }

---

3. 写入数据

新的版本中（0.99.0+）还有一个重要的改动是，HTable不再是客户端api，一些操作Table的动作（get, put, delete, scan）都需要直接用Table class来完成：

    /* put data into table. */
    public static void addData(String rowKey, String tableName,
            String[] column1, String[] value1, String[] column2, String[] value2)
            throws IOException {
        /* get table. */
        TableName tn = TableName.valueOf(tableName);
        Table table = connect.getTable(tn);

        /* create put. */
        Put put = new Put(Bytes.toBytes(rowKey));
        HColumnDescriptor[] columnFamilies = table.getTableDescriptor().getColumnFamilies();

        for (int i = 0; i < columnFamilies.length; i++) {
            String f = columnFamilies[i].getNameAsString();
            if (f.equals("article")) {
                for (int j = 0; j < column1.length; j++) {
                    put.addColumn(Bytes.toBytes(f), Bytes.toBytes(column1[j]), Bytes.toBytes(value1[j]));
                }
            }
            if (f.equals("author")) {
                for (int j = 0; j < column2.length; j++) {
                    put.addColumn(Bytes.toBytes(f), Bytes.toBytes(column2[j]), Bytes.toBytes(value2[j]));
                }
            }
        }

        /* put data. */
        table.put(put);
        System.out.println("add data Success!");
    }

---

4. 获取数据

获取数据的时候，在0.96.0及之后的版本，有一个很重要的改动就是，弃用了Result class中的public List list()方法，统统改用public List listCells()方法：

    /* get data. */
    public static void getResult(String tableName, String rowKey)
            throws IOException {
        /* get table. */
        Table table = connect.getTable(TableName.valueOf(tableName));

        Get get = new Get(Bytes.toBytes(rowKey));

        Result result = table.get(get);
        for (Cell cell : result.listCells()) {
            System.out.println("------------------------------------");
            System.out.println("rowkey: " + new String(CellUtil.cloneRow(cell)));
            System.out.println("family: " + new String(CellUtil.cloneFamily(cell)));
            System.out.println("column: " + new String(CellUtil.cloneQualifier(cell)));
            System.out.println("value : " + new String(CellUtil.cloneValue(cell)));
            System.out.println("timest: " + cell.getTimestamp());
        }
    }

---

5. 遍历表数据

    /* scan table. */
    public static void getResultScan(String tableName) throws IOException {
        Scan scan = new Scan();
        ResultScanner rs = null;
        Table table = connect.getTable(TableName.valueOf(tableName));
        try {
            rs = table.getScanner(scan);
            for (Result r : rs) {
                for (Cell cell : r.listCells()) {
                    System.out.println("------------------------------------");
                    System.out.println("rowkey: " + new String(CellUtil.cloneRow(cell)));
                    System.out.println("family: " + new String(CellUtil.cloneFamily(cell)));
                    System.out.println("column: " + new String(CellUtil.cloneQualifier(cell)));
                    System.out.println("value : " + new String(CellUtil.cloneValue(cell)));
                    System.out.println("timest: " + cell.getTimestamp());
                }
            }
        } finally {
            rs.close();
        }
    }

---

6. 遍历一定范围的表数据

    /* range scan table. */
    public static void getResultScan(String tableName, String start_rowkey,
            String stop_rowkey) throws IOException {
        Scan scan = new Scan();
        scan.setStartRow(Bytes.toBytes(start_rowkey));
        scan.setStopRow(Bytes.toBytes(stop_rowkey));
        ResultScanner rs = null;
        Table table = connect.getTable(TableName.valueOf(tableName));
        try {
            rs = table.getScanner(scan);
            for (Result r : rs) {
                for (Cell cell : r.listCells()) {
                    System.out.println("------------------------------------");
                    System.out.println("rowkey: " + new String(CellUtil.cloneRow(cell)));
                    System.out.println("family: " + new String(CellUtil.cloneFamily(cell)));
                    System.out.println("column: " + new String(CellUtil.cloneQualifier(cell)));
                    System.out.println("value : " + new String(CellUtil.cloneValue(cell)));
                    System.out.println("timest: " + cell.getTimestamp());
                }
            }
        } finally {
            rs.close();
        }
    }

---

7. 获取指定行指定列数据

    /* get column data. */
    public static void getResultByColumn(String tableName, String rowKey,
            String familyName, String columnName) throws IOException {
        /* get table. */
        Table table = connect.getTable(TableName.valueOf(tableName));
        Get get = new Get(Bytes.toBytes(rowKey));
        get.addColumn(Bytes.toBytes(familyName), Bytes.toBytes(columnName)); // 获取指定列族和列修饰符对应的列
        Result result = table.get(get);

        for (Cell cell : result.listCells()) {
            System.out.println("------------------------------------");
            System.out.println("rowkey: " + new String(CellUtil.cloneRow(cell)));
            System.out.println("family: " + new String(CellUtil.cloneFamily(cell)));
            System.out.println("column: " + new String(CellUtil.cloneQualifier(cell)));
            System.out.println("value : " + new String(CellUtil.cloneValue(cell)));
            System.out.println("timest: " + cell.getTimestamp());
        }
    }

---

8. 修改列数据

和之前的实现类似，就是直接覆盖：

    /* update. */
    public static void updateTable(String tableName, String rowKey,
            String familyName, String columnName, String value)
            throws IOException {
        Table table = connect.getTable(TableName.valueOf(tableName));
        Put put = new Put(Bytes.toBytes(rowKey));
        put.addColumn(Bytes.toBytes(familyName), Bytes.toBytes(columnName),
                Bytes.toBytes(value));
        table.put(put);
        System.out.println("update table Success!");
    }

---

9. 获得多个版本的数据

    /* get multi-version data. */
    public static void getResultByVersion(String tableName, String rowKey,
            String familyName, String columnName) throws IOException {
        Table table = connect.getTable(TableName.valueOf(tableName));
        Get get = new Get(Bytes.toBytes(rowKey));
        get.addColumn(Bytes.toBytes(familyName), Bytes.toBytes(columnName));
        get.setMaxVersions(5);
        Result result = table.get(get);
        for (Cell cell : result.listCells()) {
            System.out.println("------------------------------------");
            System.out.println("timest: " + cell.getSequenceId());
            System.out.println("rowkey: " + new String(CellUtil.cloneRow(cell)));
            System.out.println("family: " + new String(CellUtil.cloneFamily(cell)));
            System.out.println("column: " + new String(CellUtil.cloneQualifier(cell)));
            System.out.println("value : " + new String(CellUtil.cloneValue(cell)));
            System.out.println("timest: " + cell.getTimestamp());
        }
    }

---

10. 删除数据

以下方法包括删除列、行数据：

    /* delete column. */
    public static void deleteColumn(String tableName, String rowKey,
            String falilyName, String columnName) throws IOException {
        Table table = connect.getTable(TableName.valueOf(tableName));
        Delete deleteColumn = new Delete(Bytes.toBytes(rowKey));
        deleteColumn.addColumns(Bytes.toBytes(falilyName), Bytes.toBytes(columnName));
        table.delete(deleteColumn);
        System.out.println(falilyName + ":" + columnName + "is deleted!");
    }

    /* delete row. */
    public static void deleteAllColumn(String tableName, String rowKey)
            throws IOException {
        Table table = connect.getTable(TableName.valueOf(tableName));
        Delete deleteAll = new Delete(Bytes.toBytes(rowKey));
        table.delete(deleteAll);
        System.out.println("all columns are deleted!");
    }

---

11. 删除表

和创建表一样，都需要Admin来删除表：

    /* delete table. */
    public static void deleteTable(String tableName) throws IOException {
        Admin admin = connect.getAdmin();
        admin.disableTable(TableName.valueOf(tableName));
        admin.deleteTable(TableName.valueOf(tableName));
        System.out.println(tableName + "is deleted!");
    }

---

12. 所有的代码

在此：

package chapter12;

import java.io.IOException;

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.Cell;
import org.apache.hadoop.hbase.CellUtil;
import org.apache.hadoop.hbase.client.Get;
import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.client.Delete;
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.ConnectionFactory;
import org.apache.hadoop.hbase.client.Connection;
import org.apache.hadoop.hbase.client.Table;
import org.apache.hadoop.hbase.client.Admin;
import org.apache.hadoop.hbase.TableName;
import org.apache.hadoop.hbase.util.Bytes;

public class HBaseTestCase {           
    /* create config and connection. */
    static Configuration conf = HBaseConfiguration.create();
    static Connection connect = null;
    static {
        try {
            connect = ConnectionFactory.createConnection(conf);
        } catch (Exception e) {
            e.printStackTrace();
        }
    }


    /* test create table. */
    public static void createTable(String tableName, String[] family) 
            throws Exception {
        Admin admin = connect.getAdmin();

        TableName tn = TableName.valueOf(tableName);
        HTableDescriptor desc = new HTableDescriptor(tn);
        for (int i = 0; i < family.length; i++) {
            desc.addFamily(new HColumnDescriptor(family[i]));
        }

        if (admin.tableExists(tn)) {
            System.out.println("table Exists!");
            System.exit(0);
        } else {
            admin.createTable(desc);
            System.out.println("create table Success!");
        }
    }

    /* put data into table. */
    public static void addData(String rowKey, String tableName,
            String[] column1, String[] value1, String[] column2, String[] value2)
            throws IOException {
        /* get table. */
        TableName tn = TableName.valueOf(tableName);
        Table table = connect.getTable(tn);

        /* create put. */
        Put put = new Put(Bytes.toBytes(rowKey));
        HColumnDescriptor[] columnFamilies = table.getTableDescriptor().getColumnFamilies();

        for (int i = 0; i < columnFamilies.length; i++) {
            String f = columnFamilies[i].getNameAsString();
            if (f.equals("article")) {
                for (int j = 0; j < column1.length; j++) {
                    put.addColumn(Bytes.toBytes(f), Bytes.toBytes(column1[j]), Bytes.toBytes(value1[j]));
                }
            }
            if (f.equals("author")) {
                for (int j = 0; j < column2.length; j++) {
                    put.addColumn(Bytes.toBytes(f), Bytes.toBytes(column2[j]), Bytes.toBytes(value2[j]));
                }
            }
        }

        /* put data. */
        table.put(put);
        System.out.println("add data Success!");
    }

    /* get data. */
    public static void getResult(String tableName, String rowKey)
            throws IOException {
        /* get table. */
        Table table = connect.getTable(TableName.valueOf(tableName));

        Get get = new Get(Bytes.toBytes(rowKey));

        Result result = table.get(get);
        for (Cell cell : result.listCells()) {
            System.out.println("------------------------------------");
            System.out.println("rowkey: " + new String(CellUtil.cloneRow(cell)));
            System.out.println("family: " + new String(CellUtil.cloneFamily(cell)));
            System.out.println("column: " + new String(CellUtil.cloneQualifier(cell)));
            System.out.println("value : " + new String(CellUtil.cloneValue(cell)));
            System.out.println("timest: " + cell.getTimestamp());
        }
    }

    /* scan table. */
    public static void getResultScan(String tableName) throws IOException {
        Scan scan = new Scan();
        ResultScanner rs = null;
        Table table = connect.getTable(TableName.valueOf(tableName));
        try {
            rs = table.getScanner(scan);
            for (Result r : rs) {
                for (Cell cell : r.listCells()) {
                    System.out.println("------------------------------------");
                    System.out.println("rowkey: " + new String(CellUtil.cloneRow(cell)));
                    System.out.println("family: " + new String(CellUtil.cloneFamily(cell)));
                    System.out.println("column: " + new String(CellUtil.cloneQualifier(cell)));
                    System.out.println("value : " + new String(CellUtil.cloneValue(cell)));
                    System.out.println("timest: " + cell.getTimestamp());
                }
            }
        } finally {
            rs.close();
        }
    }

    /* range scan table. */
    public static void getResultScan(String tableName, String start_rowkey,
            String stop_rowkey) throws IOException {
        Scan scan = new Scan();
        scan.setStartRow(Bytes.toBytes(start_rowkey));
        scan.setStopRow(Bytes.toBytes(stop_rowkey));
        ResultScanner rs = null;
        Table table = connect.getTable(TableName.valueOf(tableName));
        try {
            rs = table.getScanner(scan);
            for (Result r : rs) {
                for (Cell cell : r.listCells()) {
                    System.out.println("------------------------------------");
                    System.out.println("rowkey: " + new String(CellUtil.cloneRow(cell)));
                    System.out.println("family: " + new String(CellUtil.cloneFamily(cell)));
                    System.out.println("column: " + new String(CellUtil.cloneQualifier(cell)));
                    System.out.println("value : " + new String(CellUtil.cloneValue(cell)));
                    System.out.println("timest: " + cell.getTimestamp());
                }
            }
        } finally {
            rs.close();
        }
    }

    /* get column data. */
    public static void getResultByColumn(String tableName, String rowKey,
            String familyName, String columnName) throws IOException {
        /* get table. */
        Table table = connect.getTable(TableName.valueOf(tableName));
        Get get = new Get(Bytes.toBytes(rowKey));
        get.addColumn(Bytes.toBytes(familyName), Bytes.toBytes(columnName)); // 获取指定列族和列修饰符对应的列
        Result result = table.get(get);

        for (Cell cell : result.listCells()) {
            System.out.println("------------------------------------");
            System.out.println("rowkey: " + new String(CellUtil.cloneRow(cell)));
            System.out.println("family: " + new String(CellUtil.cloneFamily(cell)));
            System.out.println("column: " + new String(CellUtil.cloneQualifier(cell)));
            System.out.println("value : " + new String(CellUtil.cloneValue(cell)));
            System.out.println("timest: " + cell.getTimestamp());
        }
    }

    /* update. */
    public static void updateTable(String tableName, String rowKey,
            String familyName, String columnName, String value)
            throws IOException {
        Table table = connect.getTable(TableName.valueOf(tableName));
        Put put = new Put(Bytes.toBytes(rowKey));
        put.addColumn(Bytes.toBytes(familyName), Bytes.toBytes(columnName),
                Bytes.toBytes(value));
        table.put(put);
        System.out.println("update table Success!");
    }

    /* get multi-version data. */
    public static void getResultByVersion(String tableName, String rowKey,
            String familyName, String columnName) throws IOException {
        Table table = connect.getTable(TableName.valueOf(tableName));
        Get get = new Get(Bytes.toBytes(rowKey));
        get.addColumn(Bytes.toBytes(familyName), Bytes.toBytes(columnName));
        get.setMaxVersions(5);
        Result result = table.get(get);
        for (Cell cell : result.listCells()) {
            System.out.println("------------------------------------");
            System.out.println("timest: " + cell.getSequenceId());
            System.out.println("rowkey: " + new String(CellUtil.cloneRow(cell)));
            System.out.println("family: " + new String(CellUtil.cloneFamily(cell)));
            System.out.println("column: " + new String(CellUtil.cloneQualifier(cell)));
            System.out.println("value : " + new String(CellUtil.cloneValue(cell)));
            System.out.println("timest: " + cell.getTimestamp());
        }
    }

    /* delete column. */
    public static void deleteColumn(String tableName, String rowKey,
            String falilyName, String columnName) throws IOException {
        Table table = connect.getTable(TableName.valueOf(tableName));
        Delete deleteColumn = new Delete(Bytes.toBytes(rowKey));
        deleteColumn.addColumns(Bytes.toBytes(falilyName), Bytes.toBytes(columnName));
        table.delete(deleteColumn);
        System.out.println(falilyName + ":" + columnName + "is deleted!");
    }

    /* delete row. */
    public static void deleteAllColumn(String tableName, String rowKey)
            throws IOException {
        Table table = connect.getTable(TableName.valueOf(tableName));
        Delete deleteAll = new Delete(Bytes.toBytes(rowKey));
        table.delete(deleteAll);
        System.out.println("all columns are deleted!");
    }

    /* delete table. */
    public static void deleteTable(String tableName) throws IOException {
        Admin admin = connect.getAdmin();
        admin.disableTable(TableName.valueOf(tableName));
        admin.deleteTable(TableName.valueOf(tableName));
        System.out.println(tableName + "is deleted!");
    }

    public static void  main (String [] agrs) throws Exception {

        try {
            /* create table. */
            String tableName = "blog2";
            String[] family = { "article", "author" };
            createTable(tableName, family);

            /* put data. */
            String[] column1 = { "title", "content", "tag" };
            String[] value1 = {
                    "Head First HBase",
                    "HBase is the Hadoop database. Use it when you need random, realtime read/write access to your Big Data.",
                    "Hadoop,HBase,NoSQL" };
            String[] column2 = { "name", "nickname" };
            String[] value2 = { "nicholas", "lee" };
            addData("rowkey1", tableName, column1, value1, column2, value2);
            addData("rowkey2", tableName, column1, value1, column2, value2);
            addData("rowkey3", tableName, column1, value1, column2, value2);

            /* scan query. */
            getResultScan(tableName, "rowkey4", "rowkey5");

            /* range scan query. */
            getResultScan(tableName, "rowkey4", "rowkey5");

            /* get data. */
            getResult(tableName, "rowkey1");

            /* get column data. */
            getResultByColumn(tableName, "rowkey1", family[1], "name");

            /* update column data. */
            updateTable(tableName, "rowkey1", family[1], "name", "bin");

            /* get column data. */
            getResultByColumn(tableName, "rowkey1", family[1], "name");

            /* get multi-version data. */
            getResultByVersion(tableName, "rowkey1", family[1], "name");

            /* delete column.*/
            deleteColumn(tableName, "rowkey1", family[1], "nickname");

            /* delete row. */
            deleteAllColumn(tableName, "rowkey1");

            /* delete table. */
            deleteTable(tableName);
        } catch (Exception e) {
            e.printStackTrace();
        }
    }

}

---

ref

http://www.cnblogs.com/ggjucheng/p/3381328.html
http://blog.sina.com.cn/s/blog_66474b1601017fxr.html
http://www.aboutyun.com/thread-7149-1-1.html