常用Java API的用法:
1、加载配置
Configuration config = HBaseConfiguration.create(); //可以自定义配置,也可以从自定义配置文件中读取 /*config.set("hbase.zookeeper.property.clientPort", "4181"); config.set("hbase.zookeeper.quorum", "hadoop.datanode5.com,hadoop.datanode2.com,hadoop.datanode3.com"); config.set("hbase.master", "hadoop.datanode3.com\\:600000");*/
2、表的创建、表信息修改、表删除
HBaseAdmin admin = new HBaseAdmin(config); //创建表 HTableDescriptor htd = new HTableDescriptor(tableName); htd.addFamily(new HColumnDescriptor("cf1")); htd.addFamily(new HColumnDescriptor("cf2")); admin.createTable(htd); //修改表信息 admin.disableTable(tableName); // modifying existing ColumnFamily admin.modifyColumn(tableName, new HColumnDescriptor("cf1")); admin.enableTable(tableName); //删除表 admin.disableTable(Bytes.toBytes(tableName)); admin.deleteTable(Bytes.toBytes(tableName));3、添加记录
/** 在多次使用时,建议用HTablePool HTable table = new HTable(config, tableName); => HTablePool pool = new HTablePool(config, 1000); HTableInterface table = pool.getTable(tableName);*/ HTable table = new HTable(config, tableName); /** * 在插入操作时,默认不适用任何缓存 * 可自定义使用缓存,以及缓存大小 * 每个任务最后需要手工调用 flushCommits(); */ /*table.setAutoFlush(false); table.setWriteBufferSize(1024);*/ Put put1 = new Put(Bytes.toBytes(rowKey)); if (ts == 0) { put1.add(Bytes.toBytes(family), Bytes.toBytes(qualifier), Bytes.toBytes(value)); } else { //自定义版本时,从自定义的版本号,类型为long put1.add(Bytes.toBytes(family), Bytes.toBytes(qualifier), ts,Bytes.toBytes(value)); } table.put(put1); //table.flushCommits();4、查询,根据Rowkey查询
Get get1 = new Get(Bytes.toBytes(rowKey)); Result result = table.get(get1); System.out.println("get result:" + Bytes.toString(result.getValue(Bytes.toBytes(family), Bytes.toBytes(qualifier)))); Result[] result = table.get(List<Get>);//查询指定Rowkey的多条记录5、查询,指定条件和rowkey区间查询
Scan scan = new Scan(); //默认缓存大小为1,设置成一个合理的值,可以减少scan过程中next()的时间开销,代价是客户端的内存 scan.setCaching(500); scan.setCacheBlocks(false); //根据startRowKey、endRowKey查询 //Scan scan = new Scan(Bytes.toBytes("startRowKey"), Bytes.toBytes("endRowKey")); //rowKey之外的过滤条件,在List中可以add; /**List<Filter> filters = new ArrayList<Filter>(); Filter filter = new SingleColumnValueFilter("familyName".getBytes(), "qualifierName".getBytes(), CompareOp.EQUAL, Bytes.toBytes("value")); filters.add(filter); scan.setFilter(new FilterList(filters));*/ ResultScanner scanner = table.getScanner(scan); System.out.println("scan result list:"); for (Result result : scanner) { System.out.println(Bytes.toString(result.getRow())); System.out.println(Bytes.toString(result.getValue(Bytes.toBytes("data"), Bytes.toBytes("data1")))); System.out.println(Bytes.toString(result.getValue(Bytes.toBytes("data"), Bytes.toBytes("data2")))); } scanner.close();参考:
1、http://www.taobaotest.com/blogs/1605
2、http://abloz.com/hbase/book.html#data_model_operations(官网示例)