5.Hbase API 操作开发
Hbase API 操作开发需要连接Zookeeper进行节点的管理控制
1.配置 HBaseConfiguration:
包:org.apache.hadoop.hbase.HBaseConfiguration下的HBaseConfiguration
作用:通过此类可以对HBase进行配置
static Configuration config = null; private Connection connection = null; private Table table = null; @Before public void init() throws Exception { config = HBaseConfiguration.create();//HBaseConfiguration.create()默认会从classpath中查找hbase-site.xml中的配置信息,初始化Configuration config.set("hbase.zookeeper.quorum", "shizhan3,shizhan5,shizhan6");// zookeeper地址 config.set("hbase.zookeeper.property.clientPort", "2183");// zookeeper端口(默认2181) connection = ConnectionFactory.createConnection(config); table = connection.getTable(TableName.valueOf("user"));//通过连接池获取表 }
2.表管理类 HBaseAdmin:
包:org.apache.hadoop.hbase.client.HBaseAdmin
作用:提供接口关系HBase 数据库中的表信息 用法:HBaseAdmin admin = new HBaseAdmin(config);
3.表描述类 HTableDescriptor:
包:org.apache.hadoop.hbase.HTableDescriptor
作用:HTableDescriptor 类包含了表的名字以及表的列族信息
用法:HTableDescriptor htd =new HTableDescriptor(tablename); htd.addFamily(new HColumnDescriptor(“myFamily”));
4.列族描述类 HColumnDescriptor:包:org.apache.hadoop.hbase.HColumnDescriptor,维护列族的信息
5.创建表的操作:一般我们用Shell创建表
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 }
6.批量插入数据:
/** * 向hbase中增加数据 */ @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(); }
7.修改数据:
/** * 修改数据 */ @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(); }
8.删除数据:
/** * 删除数据 */ @Test public void deleteDate() throws Exception { Delete delete = new Delete(Bytes.toBytes("1234")); delete.addFamily(Bytes.toBytes("info1"));//删除列族 delete.addColumn(Bytes.toBytes("info1"), Bytes.toBytes("name"));//删除列族下的name table.delete(delete); table.flushCommits(); }
9.查询数据:(单挑查询、批量查询、过滤器查询)
单条查询:
/** * 单条查询 */ @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")))); }
批量查询(全表扫描):ResultScanner
包:org.apache.hadoop.hbase.client.ResultScanner(获取值的接口)
/** * 全表扫描 */ @Test public void scanData() throws Exception { //设置全表扫描封装类 Scan scan = new Scan(); scan.setStartRow(Bytes.toBytes("wangsf_0"));//区间 scan.setStopRow(Bytes.toBytes("wangwu")); //扫描 ResultScanner scanner = table.getScanner(scan); for (Result result : scanner) { System.out.println(Bytes.toString(result.getRow())); //携带的rowkey 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")))); } }
过滤器查询:
1.hbase过滤器:
FilterList 代表一个过滤器列表,可以添加多个过滤器进行查询,多个过滤器之间的关系有:
与关系(符合所有):FilterList.Operator.MUST_PASS_ALL
或关系(符合任一):FilterList.Operator.MUST_PASS_ONE
2.过滤器的种类:
列值过滤器—SingleColumnValueFilter: 过滤列值的相等、不等、范围等
列名前缀过滤器—ColumnPrefixFilter:过滤指定前缀的列名
多个列名前缀过滤器—MultipleColumnPrefixFilter:过滤多个指定前缀的列名
rowKey过滤器—RowFilter:通过正则,过滤rowKey值。
2.1.列值过滤器:
/** * 全表扫描的过滤器 * 列值过滤器 */ @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"));//下面示例检查列值和字符串'zhangsan2'相等 //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")))); } }
2.2.列名前缀过滤器—ColumnPrefixFilter:用于指定列名前缀值相等
/** * 匹配列名前缀过滤器 */ @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")))); } } }
2.3.多个列值前缀过滤器—MultipleColumnPrefixFilter:用于指定多个前缀
byte[][] prefixes = new byte[][] {Bytes.toBytes("value1"),Bytes.toBytes("value2")};
Filter f = new MultipleColumnPrefixFilter(prefixes);
scan.setFilter(f);
2.4.rowkey过滤器:通常根据rowkey来指定范围时,使用scan扫描器的StartRow和StopRow方法比较好
/** * rowkey过滤器 */ @Test public void scanDataByFilter2() throws Exception { // 创建全表扫描的scan Scan scan = new Scan(); //匹配rowkey以12341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")))); } }
2.5.过滤器集合FilterList:
/** * 过滤器集合 */ @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")))); } } }
操作类文件:https://pan.baidu.com/s/1vDc-J-uleBPTB0_IMhAEeA