1.1. 配置
HBaseConfiguration
包:org.apache.hadoop.hbase.HBaseConfiguration
作用:通过此类可以对HBase进行配置
用法实例:
Configuration config = HBaseConfiguration.create();
说明: HBaseConfiguration.create() 默认会从classpath 中查找 hbase-site.xml 中的配置信息,初始化 Configuration。
使用方法:
static Configuration config = null;
static {
config = HBaseConfiguration.create();
config.set("hbase.zookeeper.quorum", "slave1,slave2,slave3");
config.set("hbase.zookeeper.property.clientPort", "2181");
}
1.2. 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);
1.3. 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
表的schema(设计)
用法:
HTableDescriptor htd =new HTableDescriptor(tablename);
htd.addFamily(new HColumnDescriptor(“myFamily”));
1.4. 列族的描述类
HColumnDescriptor
包:org.apache.hadoop.hbase.HColumnDescriptor
作用:HColumnDescriptor 维护列族的信息
用法:
htd.addFamily(new HColumnDescriptor(“myFamily”));
1.5. 创建表的操作
CreateTable(一般我们用shell创建表)
static Configuration config = null;
static {
config = HBaseConfiguration.create();
config.set("hbase.zookeeper.quorum", "slave1,slave2,slave3");
config.set("hbase.zookeeper.property.clientPort", "2181");
}
HBaseAdmin admin = new HBaseAdmin(config);
HTableDescriptor desc = new HTableDescriptor(tableName);
HColumnDescriptor family1 = new HColumnDescriptor(“f1”);
HColumnDescriptor family2 = new HColumnDescriptor(“f2”);
desc.addFamily(family1);
desc.addFamily(family2);
admin.createTable(desc);
1.6. 删除表
HBaseAdmin admin = new HBaseAdmin(config);
admin.disableTable(tableName);
admin.deleteTable(tableName);
1.7. 创建一个表的类
HTable
包:org.apache.hadoop.hbase.client.HTable
作用:HTable 和 HBase 的表通信
用法:
// 普通获取表
HTable table = new HTable(config,Bytes.toBytes(tablename);
// 通过连接池获取表
Connection connection = ConnectionFactory.createConnection(config);
HTableInterface table = connection.getTable(TableName.valueOf("user"));
1.8. 单条插入数据
Put
包:org.apache.hadoop.hbase.client.Put
作用:插入数据
用法:
Put put = new Put(row);
p.add(family,qualifier,value);
说明:向表 tablename 添加 “family,qualifier,value”指定的值。
示例代码:
Connection connection = ConnectionFactory.createConnection(config);
HTableInterface table = connection.getTable(TableName.valueOf("user"));
Put put = new Put(Bytes.toBytes(rowKey));
put.add(Bytes.toBytes(family), Bytes.toBytes(qualifier),Bytes.toBytes(value));
table.put(put);
1.9. 批量插入
批量插入
List<Put> list = new ArrayList<Put>();
Put put = new Put(Bytes.toBytes(rowKey));//获取put,用于插入
put.add(Bytes.toBytes(family), Bytes.toBytes(qualifier),Bytes.toBytes(value));//封装信息
list.add(put);
table.put(list);//添加记录
1.10. 删除数据
Delete
包:org.apache.hadoop.hbase.client.Delete
作用:删除给定rowkey的数据
用法:
Delete del= new Delete(Bytes.toBytes(rowKey));
table.delete(del);
代码实例
Connection connection = ConnectionFactory.createConnection(config);
HTableInterface table = connection.getTable(TableName.valueOf("user"));
Delete del= new Delete(Bytes.toBytes(rowKey));
table.delete(del);
1.11. 单条查询
Get
包:org.apache.hadoop.hbase.client.Get
作用:获取单个行的数据
用法:
HTable table = new HTable(config,Bytes.toBytes(tablename));
Get get = new Get(Bytes.toBytes(row));
Result result = table.get(get);
说明:获取 tablename 表中 row 行的对应数据
代码示例:
Connection connection = ConnectionFactory.createConnection(config);
HTableInterface table = connection.getTable(TableName.valueOf("user"));
Get get = new Get(rowKey.getBytes());
Result row = table.get(get);
for (KeyValue kv : row.raw()) {
System.out.print(new String(kv.getRow()) + " ");
System.out.print(new String(kv.getFamily()) + ":");
System.out.print(new String(kv.getQualifier()) + " = ");
System.out.print(new String(kv.getValue()));
System.out.print(" timestamp = " + kv.getTimestamp() + " ");
}
1.12. 批量查询
ResultScanner
包:org.apache.hadoop.hbase.client.ResultScanner
作用:获取值的接口
用法:
ResultScanner scanner = table.getScanner(scan);
For(Result rowResult : scanner){
Bytes[] str = rowResult.getValue(family,column);
}
说明:循环获取行中列值。
代码示例:
Connection connection = ConnectionFactory.createConnection(config);
HTableInterface table = connection.getTable(TableName.valueOf("user"));
Scan scan = new Scan();
scan.setStartRow("a1".getBytes());
scan.setStopRow("a20".getBytes());
ResultScanner scanner = table.getScanner(scan);
for (Result row : scanner) {
System.out.println(" Rowkey: " + new String(row.getRow()));
for (KeyValue kv : row.raw()) {
System.out.print(new String(kv.getRow()) + " ");
System.out.print(new String(kv.getFamily()) + ":");
System.out.print(new String(kv.getQualifier()) + " = ");
System.out.print(new String(kv.getValue()));
System.out.print(" timestamp = " + kv.getTimestamp() + " ");
}
}
1.13. hbase过滤器
1.13.1. FilterList
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
使用方法:
FilterList filterList = new FilterList(FilterList.Operator.MUST_PASS_ONE);
Scan s1 = new Scan();
filterList.addFilter(new SingleColumnValueFilter(Bytes.toBytes(“f1”), Bytes.toBytes(“c1”), CompareOp.EQUAL,Bytes.toBytes(“v1”) ) );
filterList.addFilter(new SingleColumnValueFilter(Bytes.toBytes(“f1”), Bytes.toBytes(“c2”), CompareOp.EQUAL,Bytes.toBytes(“v2”) ) );
// 添加下面这一行后,则只返回指定的cell,同一行中的其他cell不返回
s1.addColumn(Bytes.toBytes(“f1”), Bytes.toBytes(“c1”));
s1.setFilter(filterList); //设置filter
ResultScanner ResultScannerFilterList = table.getScanner(s1); //返回结果列表
1.13.2. 过滤器的种类
过滤器的种类:
列值过滤器—SingleColumnValueFilter
过滤列植的相等、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。
1.13.3. 列值过滤器—SingleColumnValueFilter
SingleColumnValueFilter 列值判断
相等 (CompareOp.EQUAL ),
不等(CompareOp.NOT_EQUAL),
范围 (e.g., CompareOp.GREATER)…………
下面示例检查列值和字符串'values' 相等...
SingleColumnValueFilter f = new SingleColumnValueFilter(Bytes.toBytes("cFamily") ,Bytes.toBytes("column"), CompareFilter.CompareOp.EQUAL, Bytes.toBytes("values"));
s1.setFilter(f);
注意:如果过滤器过滤的列在数据表中有的行中不存在,那么这个过滤器对此行无法过滤。
1.13.4. 列名前缀过滤器—ColumnPrefixFilter
过滤器—ColumnPrefixFilter
ColumnPrefixFilter 用于指定列名前缀值相等
ColumnPrefixFilter f = new ColumnPrefixFilter(Bytes.toBytes("values"));
s1.setFilter(f);
1.13.5. 多个列值前缀过滤器—MultipleColumnPrefixFilter
MultipleColumnPrefixFilter 和 ColumnPrefixFilter 行为差不多,但可以指定多个前缀
byte[][] prefixes = new byte[][] {Bytes.toBytes("value1"),Bytes.toBytes("value2")};
Filter f = new MultipleColumnPrefixFilter(prefixes);
s1.setFilter(f);
1.13.6. rowKey过滤器—RowFilter
RowFilter 是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。
Filter f = new RowFilter(CompareFilter.CompareOp.EQUAL, new RegexStringComparator("^1234")); //匹配以1234开头的rowkey
s1.setFilter(f);
附录:Java API测试demo:

package cn.darrenchan.hbase; import java.util.ArrayList; 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.MasterNotRunningException; import org.apache.hadoop.hbase.TableName; import org.apache.hadoop.hbase.ZooKeeperConnectionException; import org.apache.hadoop.hbase.client.Connection; import org.apache.hadoop.hbase.client.ConnectionFactory; import org.apache.hadoop.hbase.client.Delete; import org.apache.hadoop.hbase.client.Get; import org.apache.hadoop.hbase.client.HBaseAdmin; import org.apache.hadoop.hbase.client.Put; 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.Table; import org.apache.hadoop.hbase.filter.ColumnPrefixFilter; import org.apache.hadoop.hbase.filter.CompareFilter; import org.apache.hadoop.hbase.filter.FilterList; import org.apache.hadoop.hbase.filter.FilterList.Operator; import org.apache.hadoop.hbase.filter.RegexStringComparator; import org.apache.hadoop.hbase.filter.RowFilter; import org.apache.hadoop.hbase.filter.SingleColumnValueFilter; import org.apache.hadoop.hbase.util.Bytes; import org.junit.After; import org.junit.Before; import org.junit.Test; public class HbaseTest { /** * 配置ss */ static Configuration config = null; private Connection connection = null; private Table table = null; @Before public void init() throws Exception { config = HBaseConfiguration.create();// 配置 config.set("hbase.zookeeper.quorum", "weekend05,weekend06,weekend07");// zookeeper地址 config.set("hbase.zookeeper.property.clientPort", "2181");// zookeeper端口 connection = ConnectionFactory.createConnection(config); table = connection.getTable(TableName.valueOf("user")); } /** * 创建一个表 * * @throws Exception */ @Test 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 } @Test @SuppressWarnings("deprecation") public void deleteTable() throws MasterNotRunningException, ZooKeeperConnectionException, Exception { HBaseAdmin admin = new HBaseAdmin(config); admin.disableTable("test3"); admin.deleteTable("test3"); admin.close(); } /** * 向hbase中增加数据 * * @throws Exception */ @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("info1"), Bytes.toBytes("name"), Bytes.toBytes("wangwu"+i)); put.add(Bytes.toBytes("info1"), Bytes.toBytes("password"), Bytes.toBytes(1234+i)); arrayList.add(put); } //插入数据 table.put(arrayList); //提交 table.flushCommits(); } /** * 修改数据 * 修改就是重复覆盖 * * @throws Exception */ @Test public void updateData() throws Exception { Put put = new Put(Bytes.toBytes("1234")); put.add(Bytes.toBytes("info1"), Bytes.toBytes("col1"), Bytes.toBytes("qq")); put.add(Bytes.toBytes("info1"), Bytes.toBytes("col2"), Bytes.toBytes(904000612)); put.add(Bytes.toBytes("info1"), Bytes.toBytes("col3"), Bytes.toBytes("男")); //插入数据 table.put(put); //提交 table.flushCommits(); } /** * 删除数据 * * @throws Exception */ @Test public void deleteDate() throws Exception { Delete delete = new Delete(Bytes.toBytes("1234")); //删除某一个列族 //delete.addFamily(Bytes.toBytes("info1")); //删除某一列 delete.addColumn(Bytes.toBytes("info1"), Bytes.toBytes("password")); table.delete(delete); table.flushCommits(); } /** * 单条查询 * * @throws Exception */ @Test public void queryData() throws Exception { Get get = new Get(Bytes.toBytes("1234")); // 可以指定查询某一个列 // get.addColumn(Bytes.toBytes("info2"), Bytes.toBytes("password")); // 可以指定查询某一个列族 // get.addFamily(Bytes.toBytes("info2")); Result result = table.get(get); System.out.println(Bytes.toInt(result.getValue(Bytes.toBytes("info1"), Bytes.toBytes("password")))); System.out.println(Bytes.toString(result.getValue(Bytes.toBytes("info1"), Bytes.toBytes("namessss")))); System.out.println(Bytes.toString(result.getValue(Bytes.toBytes("info1"), Bytes.toBytes("sex")))); } /** * 全表扫描 * * @throws Exception */ @Test public void scanData() throws Exception { //设置全表扫描封装类 Scan scan = new Scan(); //scan.addFamily(Bytes.toBytes("info")); //scan.addColumn(Bytes.toBytes("info"), Bytes.toBytes("password")); //scan.setStartRow(Bytes.toBytes("wangsf_0")); //rowkey //scan.setStopRow(Bytes.toBytes("wangwu")); //rowkey ResultScanner scanner = table.getScanner(scan); for (Result result : scanner) { System.out.println(Bytes.toInt(result.getValue(Bytes.toBytes("info1"), Bytes.toBytes("password")))); System.out.println(Bytes.toString(result.getValue(Bytes.toBytes("info1"), Bytes.toBytes("name")))); //System.out.println(Bytes.toInt(result.getValue(Bytes.toBytes("info2"), Bytes.toBytes("password")))); //System.out.println(Bytes.toString(result.getValue(Bytes.toBytes("info2"), Bytes.toBytes("name")))); } } /** * 全表扫描的过滤器 * 列值过滤器 * * @throws Exception */ @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("info1"), Bytes.toBytes("name"), CompareFilter.CompareOp.EQUAL, Bytes.toBytes("wangwu21")); // 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.toString(result.getRow()));//row key System.out.println(Bytes.toInt(result.getValue(Bytes.toBytes("info1"), Bytes.toBytes("password")))); System.out.println(Bytes.toString(result.getValue(Bytes.toBytes("info1"), Bytes.toBytes("name")))); System.out.println(Bytes.toString(result.getValue(Bytes.toBytes("info1"), Bytes.toBytes("sex")))); //System.out.println(Bytes.toInt(result.getValue(Bytes.toBytes("info2"), Bytes.toBytes("password")))); //System.out.println(Bytes.toString(result.getValue(Bytes.toBytes("info2"), Bytes.toBytes("name")))); } } /** * rowkey过滤器 * @throws Exception */ @Test public void scanDataByFilter2() throws Exception { // 创建全表扫描的scan Scan scan = new Scan(); //匹配rowkey RowFilter filter = new RowFilter(CompareFilter.CompareOp.EQUAL, new RegexStringComparator("^\d{4}2.$")); // 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.toString(result.getRow())); System.out.println(Bytes.toInt(result.getValue(Bytes.toBytes("info1"), Bytes.toBytes("password")))); System.out.println(Bytes.toString(result.getValue(Bytes.toBytes("info1"), Bytes.toBytes("name")))); //System.out.println(Bytes.toInt(result.getValue(Bytes.toBytes("info2"), Bytes.toBytes("password")))); //System.out.println(Bytes.toString(result.getValue(Bytes.toBytes("info2"), Bytes.toBytes("name")))); } } /** * 匹配列名前缀 * @throws Exception */ @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("info1"), Bytes.toBytes("name")))); // 判断取出来的值是否为空 if (result.getValue(Bytes.toBytes("info1"), Bytes.toBytes("age")) != null) { System.out.println("info:age:" + Bytes.toInt(result.getValue(Bytes.toBytes("info"), Bytes.toBytes("age")))); } } } /** * 过滤器集合 * @throws Exception */ @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")))); } } } @After public void close() throws Exception { table.close(); connection.close(); } }