hbase基础知识-课件（PPT-精）.ppt

HBASE结合MapReduce批量导入 public static void main(String[] args) throws Exception { final Configuration configuration = new Configuration(); //设置zookeeper configuration.set(hbase.zookeeper.quorum, hadoop0); //设置hbase表名称 configuration.set(TableOutputFormat.OUTPUT_TABLE, wlan_log); //将该值改大，防止hbase超时退出 configuration.set(dfs.socket.timeout, 180000); final Job job = new Job(configuration, HBaseBatchImport); job.setMapperClass(BatchImportMapper.class); job.setReducerClass(BatchImportReducer.class); //设置map的输出，不设置reduce的输出类型 job.setMapOutputKeyClass(LongWritable.class); job.setMapOutputValueClass(Text.class); job.setInputFormatClass(TextInputFormat.class); //不再设置输出路径，而是设置输出格式类型 job.setOutputFormatClass(TableOutputFormat.class); FileInputFormat.setInputPaths(job, hdfs://hadoop0:9000/input); job.waitForCompletion(true); } HBASE的Java_API 练习 查询 按RowKey查询 按手机号码查询 按手机号码的区域查询 HBASE的Java_API练习 查询手所有上网记录 public static void scan(String tableName) throws IOException{ HTable table = new HTable(getConfiguration(), tableName); Scan scan = new Scan(); scan.setStartRow(Bytes.toBytes/)); scan.setStopRow(Bytes.toBytes:)); ResultScanner scanner = table.getScanner(scan); int i=0; for (Result result : scanner) { System.out.println(Scan: +i+++ +result); } } HBASE的Java_API练习 查询134号段的所有上网记录 public static void scanPeriod(String tableName) throws IOException{ HTable table = new HTable(getConfiguration(), tableName); Scan scan = new Scan(); scan.setStartRow(Bytes.toBytes(134/)); scan.setStopRow( Bytes.toBytes(134:)); scan.setMaxVersions(1); ResultScanner scanner = table.getScanner(scan); int i=0; for (Result result : scanner) { System.out.println(Scan: +i+++ +result); } } 思考题 HBASE是什么数据库，与普通RDBMS有什么区别 HBASE的结构 HBASE的常用命令 HMaster、HRegionServer、HRegion、Store、MemStore、StoreFile、HLog、HFile、KeyValue * 未验证 importtsv -Dimporttsv.columns=HBASE_ROW_KEY,cf:reportTime,cf:msisd