HBase客户端API基本操作

来源:互联网 发布:淘宝店铺如何设置满减 编辑:程序博客网 时间:2024/04/29 23:23

Java类与HBase数据模型

HBaseConfiguration

包名 : org.apache.hadoop.hbase.HBaseConfiguration
作用:对HBase进行配置。
用法示例:

HBaseConfiguration hconfig = new HBaseConfiguration();hconfig.set("hbase.zookeeper.property.clientPort","2181");

HBaseAdmin

包名 : org.apache.hadoop.hbase.client.HBaseAdmin
作用:提供了一个接口来管理HBase数据库的表信息
它提供的方法包括:创建表,删除表,列出表项,使表有效或无效,以及添加或删除表列族成员等。
用法示例:

HBaseAdmin admin = new HBaseAdmin(config);admin.disableTable("tablename")

HTableDescriptor

包名: org.apache.hadoop.hbase.HTableDescriptor
作用:包含了表的名字及其对应表的列族。
用法示例:

HTableDescriptor htd = new HTableDescriptor(table);htd.addFamily(new HcolumnDescriptor("family"));

HColumnDescriptor

包名: org.apache.hadoop.hbase.HColumnDescriptor
作用:维护着关于列族的信息,例如版本号,压缩设置等。
它通常在创建表或者为表添加列族的时候使用。
列族被创建后不能直接修改,只能通过删除,然后重新创建的方式。
列族被删除的时候,列族里面的数据也会同时被删除。
用法示例:

HTableDescriptor htd = new HTableDescriptor(tablename);HColumnDescriptor col = new HColumnDescriptor("content:");htd.addFamily(col);

HTable

包名: org.apache.hadoop.hbase.client.HTable
作用:可以用来和HBase表直接通信。此方法对于更新操作来说是非线程安全的。
用法示例:

HTable table = new HTable(conf, Bytes.toBytes(tablename));ResultScanner scanner = table.getScanner(family);

HTablePool

包名: org.apache.hadoop.hbase.client.HTablePool
作用:可以解决HTable存在的线程不安全问题,同时通过维护固定数量的HTable对象,能够在程序运行期间复用这些HTable资源对象。
说明:
1. HTablePool可以自动创建HTable对象,而且对客户端来说使用上是完全透明的,可以避免多线程间数据并发修改问题
2. HTablePool中的HTable对象之间是公用Configuration连接的,能够可以减少网络开销。

HTablePool的使用很简单:每次进行操作前,通过HTablePool的getTable方法取得一个HTable对象,然后进行put/get/scan/delete等操作,最后通过HTablePool的putTable方法将HTable对象放回到HTablePool中。

/** * A simple pool of HTable instances. *  * Each HTablePool acts as a pool for all tables. To use, instantiate an * HTablePool and use {@link #getTable(String)} to get an HTable from the pool. * * This method is not needed anymore, clients should call HTableInterface.close()  * rather than returning the tables to the pool * * Once you are done with it, close your instance of {@link HTableInterface} * by calling {@link HTableInterface#close()} rather than returning the tables * to the pool with (deprecated) {@link #putTable(HTableInterface)}. * * <p> * A pool can be created with a <i>maxSize</i> which defines the most HTable * references that will ever be retained for each table. Otherwise the default * is {@link Integer#MAX_VALUE}. * * <p> * Pool will manage its own connections to the cluster. See * {@link HConnectionManager}. * @deprecated as of 0.98.1. See {@link HConnection#getTable(String)}. */@InterfaceAudience.Private@Deprecatedpublic class HTablePool implements Closeable {}

Put

包名: org.apache.hadoop.hbase.client.Put
作用:用来对单个行执行添加操作。
用法示例:

HTable table = new HTable(conf,Bytes.toBytes(tablename));Put p = new Put(brow);//为指定行创建一个Put操作p.add(family,qualifier,value);table.put(p);

Get

包名: org.apache.hadoop.hbase.client.Get
作用:用来获取单个行的相关信息。
用法示例:

HTable table = new HTable(conf, Bytes.toBytes(tablename));Get g = new Get(Bytes.toBytes(row));table.get(g);

Result

包名: org.apache.hadoop.hbase.client.Result
作用:存储Get或者Scan操作后获取表的单行值。使用此类提供的方法可以直接获取值或者各种Map结构( key-value对)。

ResultScanner

包名: org.apache.hadoop.hbase.client.ResultScanner
作用:存储Get或者Scan操作后获取表的单行值。使用此类提供的方法可以直接获取值或者各种Map结构( key-value对)。

例程

package HbaseAPI;import java.io.IOException;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.KeyValue;import org.apache.hadoop.hbase.MasterNotRunningException;import org.apache.hadoop.hbase.ZooKeeperConnectionException;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.HTableInterface;import org.apache.hadoop.hbase.client.Put;import org.apache.hadoop.hbase.client.Result;import org.apache.hadoop.hbase.io.compress.Compression.Algorithm;import org.apache.hadoop.hbase.io.encoding.DataBlockEncoding;import org.apache.hadoop.hbase.util.Bytes;public class HBaseConnection {    private String rootDir;    private String zkServer;    private String port;    private Configuration conf;     private HConnection hConn = null;    private HBaseConnection(String rootDir,String zkServer,String port) throws IOException{        this.rootDir = rootDir;        this.zkServer = zkServer;        this.port = port;        conf = HBaseConfiguration.create();        conf.set("hbase.rootdir", rootDir);        conf.set("hbase.zookeeper.quorum", zkServer);        conf.set("hbase.zookeeper.property.clientPort", port);        hConn = HConnectionManager.createConnection(conf);      }    public void creatTable(String tableName,List<String> cols){        try {            //管理数据库的表信息            HBaseAdmin admin = new HBaseAdmin(conf);            if(admin.tableExists(tableName)){                throw new Exception("table exists");            }            else{                //                HTableDescriptor tableDesc = new HTableDescriptor(tableName);                for (String col : cols) {                    //提供列族                    HColumnDescriptor colDesc = new HColumnDescriptor(col);                    colDesc.setCompressionType(Algorithm.GZ);                    colDesc.setDataBlockEncoding(DataBlockEncoding.DIFF);                    tableDesc.addFamily(colDesc);                }                //创建表                admin.createTable(tableDesc);            }        } catch (MasterNotRunningException e) {            e.printStackTrace();        } catch (ZooKeeperConnectionException e) {            e.printStackTrace();        } catch (IOException e) {            e.printStackTrace();        } catch (Exception e) {            e.printStackTrace();        }    }    //插入数据    public void putData(String tableName,List<Put> puts) throws IOException{        HTableInterface table = hConn.getTable(tableName);        table.put(puts);        table.setAutoFlush(false);        table.flushCommits();    }    //获取数据    public Result getData(String tableName,String rowkey) throws IOException{        HTableInterface table = hConn.getTable(tableName);        //用来获取单个行的相关信息        Get get = new Get(Bytes.toBytes(rowkey));        return table.get(get);    }    public void format(Result result){        //行键        String rowkey = Bytes.toString(result.getRow());        //Return an cells of a Result as an array of KeyValues        KeyValue[] kvs = result.raw();        for (KeyValue kv : kvs) {            //列族名            String family = Bytes.toString(kv.getFamily());            //列名            String qualifier = Bytes.toString(kv.getQualifier());            String value = Bytes.toString(result.getValue(Bytes.toBytes(family), Bytes.toBytes(qualifier)));            System.out.println("rowkey->"+rowkey+", family->"            +family+", qualifier->"+qualifier);            System.out.println("value->"+value);        }    }    public static void main(String[] args) throws IOException {        String rootDir = "hdfs://hadoop1:8020/hbase";        String zkServer = "hadoop1";        String port = "2181";        //初始化        HBaseConnection conn = new HBaseConnection(rootDir,zkServer,port);        //创建表        List<String> cols = new LinkedList<>();        cols.add("basicInfo");        cols.add("moreInfo");        conn.creatTable("students", cols);        //插入数据        List<Put> puts = new LinkedList<>();        Put put1 = new Put(Bytes.toBytes("Tom"));        //(列族名,列,值)        put1.add(Bytes.toBytes("basicInfo"),Bytes.toBytes("age"),Bytes.toBytes("27"));        put1.add(Bytes.toBytes("basicInfo"),Bytes.toBytes("tel"),Bytes.toBytes("3432"));        Put put2 = new Put(Bytes.toBytes("Joson"));        put2.add(Bytes.toBytes("basicInfo"),Bytes.toBytes("age"),Bytes.toBytes("24"));        put2.add(Bytes.toBytes("basicInfo"),Bytes.toBytes("tel"),Bytes.toBytes("34322"));        puts.add(put1);        puts.add(put2);        conn.putData("students", puts);        //输出结果        Result result = conn.getData("students", "Tom");        conn.format(result);    }}
0 0
原创粉丝点击