HBase提供了Java API的訪問接口,實際開發中我們經常用來操作HBase,就和我們通過java API操作RDBMS一樣。如下
API | 作用 |
---|---|
HBaseAdmin | HBase 客戶端,用來操作HBase |
Configuration | 配置對象 |
Connection | 連接對象 |
Table | HBase 表對象 |
TableName | HBase 中的表名 |
HTableDescriptor | HBase 表描述信息對象 |
HColumnDescriptor | HBase 列族描述對象 |
Put | 用於插入數據 |
Get | 用於查詢單條記錄 |
Delete | 刪除數據對象 |
Scan | 全表掃描對象,查詢所有記錄 |
ResultScanner | 查詢數據返回結果集 |
Result | 查詢返回的單條記錄結果 |
Cell | 對應HBase中的列 |
SingleColumnValueFilter | 列值過濾器(過濾列植的相等、不等、範圍等) |
ColumnPrefixFilter | 列名前綴過濾器(過濾指定前綴的列名) |
multipleColumnPrefixFilter | 多個列名前綴過濾器(過濾多個指定前綴的列名) |
RowFilter rowKey | 過濾器(通過正則,過濾rowKey值) |
上面這些API,個人做了一個小Demo,代碼如下;
package com.cfl.hbase;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.*;
import org.apache.hadoop.hbase.client.*;
import org.apache.hadoop.hbase.filter.*;
import org.apache.hadoop.hbase.util.Bytes;
import org.junit.After;
import org.junit.Before;
import org.junit.Test;
import java.util.ArrayList;
import java.util.List;
/**
* HBase Java API 操作
* 一般我們使用Java API 主要操作的是數據即DML操作,DDL的操作較少
*/
public class HBaseTest {
static Configuration conf = null;
private Connection conn = null;
private HBaseAdmin admin = null;
private TableName tableName = null;
private Table table = null;
// 初始化配置
@Before
public void init() throws Exception {
conf = HBaseConfiguration.create();
// 如果不設置zookeeper地址,可以將hbase-site.xml文件複製到resource目錄下
conf.set("hbase.zookeeper.quorum","node3,node4,node5");// zookeeper 地址
// conf.set("hbase.zookeeper.property.clientPort","2188");// zookeeper 客戶端端口,默認爲2188,可以不用設置
conn = ConnectionFactory.createConnection(conf);// 創建連接
// admin = new HBaseAdmin(conf); // 已棄用,不推薦使用
admin = (HBaseAdmin) conn.getAdmin(); // hbase 表管理類
tableName = TableName.valueOf("students"); // 表名
table = conn.getTable(tableName);// 表對象
}
// --------------------DDL 操作 Start------------------
// 創建表 HTableDescriptor、HColumnDescriptor、addFamily()、createTable()
@Test
public void createTable() throws Exception {
// 創建表描述類
HTableDescriptor desc = new HTableDescriptor(tableName);
// 添加列族info
HColumnDescriptor family_info = new HColumnDescriptor("info");
desc.addFamily(family_info);
// 添加列族address
HColumnDescriptor family_address = new HColumnDescriptor("address");
desc.addFamily(family_address);
// 創建表
admin.createTable(desc);
}
// 刪除表 先棄用表disableTable(表名),再刪除表 deleteTable(表名)
@Test
public void deleteTable() throws Exception {
admin.disableTable(tableName);
admin.deleteTable(tableName);
}
// 添加列族 addColumn(表名,列族)
@Test
public void addFamily() throws Exception {
admin.addColumn(tableName, new HColumnDescriptor("hobbies"));
}
// 刪除列族 deleteColumn(表名,列族)
@Test
public void deleteFamily() throws Exception {
admin.deleteColumn(tableName, Bytes.toBytes("hobbies"));
}
// --------------------DDL 操作 End---------------------
// ----------------------DML 操作 Start-----------------
// 添加數據 Put(列族,列,列值)(HBase 中沒有修改,插入時rowkey相同,數據會覆蓋)
@Test
public void insertData() throws Exception {
// 添加一條記錄
// Put put = new Put(Bytes.toBytes("1001"));
// put.addColumn(Bytes.toBytes("info"), Bytes.toBytes("name"), Bytes.toBytes("San-Qiang Zhang"));
// put.addColumn(Bytes.toBytes("address"), Bytes.toBytes("province"), Bytes.toBytes("Hebei"));
// put.addColumn(Bytes.toBytes("address"), Bytes.toBytes("city"), Bytes.toBytes("Shijiazhuang"));
// table.put(put);
// 添加多條記錄(批量插入)
List<Put> putList = new ArrayList<Put>();
Put put1 = new Put(Bytes.toBytes("1002"));
put1.addColumn(Bytes.toBytes("info"), Bytes.toBytes("name"), Bytes.toBytes("Lisi"));
put1.addColumn(Bytes.toBytes("info"), Bytes.toBytes("sex"), Bytes.toBytes("1"));
put1.addColumn(Bytes.toBytes("address"), Bytes.toBytes("city"), Bytes.toBytes("Shanghai"));
Put put2 = new Put(Bytes.toBytes("1003"));
put2.addColumn(Bytes.toBytes("info"), Bytes.toBytes("name"), Bytes.toBytes("Lili"));
put2.addColumn(Bytes.toBytes("info"), Bytes.toBytes("sex"), Bytes.toBytes("0"));
put2.addColumn(Bytes.toBytes("address"), Bytes.toBytes("city"), Bytes.toBytes("Beijing"));
Put put3 = new Put(Bytes.toBytes("1004"));
put3.addColumn(Bytes.toBytes("info"), Bytes.toBytes("name_a"), Bytes.toBytes("Zhaosi"));
Put put4 = new Put(Bytes.toBytes("1004"));
put4.addColumn(Bytes.toBytes("info"), Bytes.toBytes("name_b"), Bytes.toBytes("Wangwu"));
putList.add(put1);
putList.add(put2);
putList.add(put3);
putList.add(put4);
table.put(putList);
}
// 刪除數據 Delete
@Test
public void deleteData() throws Exception {
// 刪除一條數據(行健爲1002)
// Delete delete = new Delete(Bytes.toBytes("1002"));
// table.delete(delete);
// 刪除行健爲1003,列族爲info的數據
// Delete delete = new Delete(Bytes.toBytes("1003"));
// delete.addFamily(Bytes.toBytes("info"));
// table.delete(delete);
// 刪除行健爲1,列族爲address,列爲city的數據
Delete delete = new Delete(Bytes.toBytes("1001"));
delete.addColumn(Bytes.toBytes("address"), Bytes.toBytes("city"));
table.delete(delete);
}
// 單條查詢 Get
@Test
public void getData() throws Exception {
Get get = new Get(Bytes.toBytes("1001"));
// get.addFamily(Bytes.toBytes("info")); //指定獲取某個列族
// get.addColumn(Bytes.toBytes("info"), Bytes.toBytes("name")); //指定獲取某個列族中的某個列
Result result = table.get(get);
System.out.println("行健:" + Bytes.toString(result.getRow()));
byte[] name = result.getValue(Bytes.toBytes("info"), Bytes.toBytes("name"));
byte[] sex = result.getValue(Bytes.toBytes("info"), Bytes.toBytes("sex"));
byte[] city = result.getValue(Bytes.toBytes("address"), Bytes.toBytes("city"));
byte[] province = result.getValue(Bytes.toBytes("address"), Bytes.toBytes("province"));
if (name != null) System.out.println("姓名:" + Bytes.toString( name));
if (sex != null) System.out.println("性別:" + Bytes.toString( sex));
if (province != null) System.out.println("省份:" + Bytes.toString(province));
if (city != null) System.out.println("城市:" + Bytes.toString(city));
}
// 全表掃描 Scan
@Test
public void scanData() throws Exception {
Scan scan = new Scan(); // Scan 全表掃描對象
// 行健是以字典序排序,可以使用scan.setStartRow(),scan.setStopRow()設置行健的字典序
// scan.addFamily(Bytes.toBytes("info")); // 只查詢列族info
//scan.addColumn(Bytes.toBytes("info"), Bytes.toBytes("name")); // 只查詢列name
ResultScanner scanner = table.getScanner(scan);
printResult1(scanner);
}
// 全表掃描:列值過濾器(過濾列植的相等、不等、範圍等) SingleColumnValueFilter
@Test
public void singleColumnValueFilter() throws Exception {
/**
* CompareOp 是一個枚舉,有如下幾個值
* LESS 小於
* LESS_OR_EQUAL 小於或等於
* EQUAL 等於
* NOT_EQUAL 不等於
* GREATER_OR_EQUAL 大於或等於
* GREATER 大於
* NO_OP 無操作
*/
// 查詢列名大於San-Qiang Zhang的數據
SingleColumnValueFilter singleColumnValueFilter = new SingleColumnValueFilter(
Bytes.toBytes("info"), Bytes.toBytes("name"),
CompareFilter.CompareOp.EQUAL, Bytes.toBytes("San-Qiang Zhang"));
Scan scan = new Scan();
scan.setFilter(singleColumnValueFilter);
ResultScanner scanner = table.getScanner(scan);
printResult1(scanner);
}
// 全表掃描:列名前綴過濾器(過濾指定前綴的列名) ColumnPrefixFilter
@Test
public void columnPrefixFilter() throws Exception {
// 查詢列以name_開頭的數據
ColumnPrefixFilter columnPrefixFilter = new ColumnPrefixFilter(Bytes.toBytes("name_"));
Scan scan = new Scan();
scan.setFilter(columnPrefixFilter);
ResultScanner scanner = table.getScanner(scan);
printResult1(scanner);
}
// 全表掃描:多個列名前綴過濾器(過濾多個指定前綴的列名) MultipleColumnPrefixFilter
@Test
public void multipleColumnPrefixFilter() throws Exception {
// 查詢列以name_或c開頭的數據
byte[][] bytes = new byte[][]{Bytes.toBytes("name_"), Bytes.toBytes("c")};
MultipleColumnPrefixFilter multipleColumnPrefixFilter = new MultipleColumnPrefixFilter(bytes);
Scan scan = new Scan();
scan.setFilter(multipleColumnPrefixFilter);
ResultScanner scanner = table.getScanner(scan);
printResult1(scanner);
}
// rowKey過濾器(通過正則,過濾rowKey值) RowFilter
@Test
public void rowFilter() throws Exception {
// 匹配rowkey以100開頭的數據
// Filter filter = new RowFilter(CompareFilter.CompareOp.EQUAL, new RegexStringComparator("^100"));
// 匹配rowkey以2結尾的數據
RowFilter filter = new RowFilter(CompareFilter.CompareOp.EQUAL, new RegexStringComparator("2$"));
Scan scan = new Scan();
scan.setFilter(filter);
ResultScanner scanner = table.getScanner(scan);
printResult1(scanner);
}
// 多個過濾器一起使用
@Test
public void multiFilterTest() throws Exception {
/**
* Operator 爲枚舉類型,有兩個值 MUST_PASS_ALL 表示 and,MUST_PASS_ONE 表示 or
*/
FilterList filterList = new FilterList(FilterList.Operator.MUST_PASS_ALL);
// 查詢性別爲0(nv)且 行健以10開頭的數據
SingleColumnValueFilter singleColumnValueFilter = new SingleColumnValueFilter(
Bytes.toBytes("info"), Bytes.toBytes("sex"),
CompareFilter.CompareOp.EQUAL, Bytes.toBytes("0"));
RowFilter rowFilter = new RowFilter(CompareFilter.CompareOp.EQUAL, new RegexStringComparator("^10"));
filterList.addFilter(singleColumnValueFilter);
filterList.addFilter(rowFilter);
Scan scan = new Scan();
scan.setFilter(rowFilter);
ResultScanner scanner = table.getScanner(scan);
// printResult1(scanner);
printResult2(scanner);
}
// --------------------DML 操作 End-------------------
/** 打印查詢結果:方法一 */
public void printResult1(ResultScanner scanner) throws Exception {
for (Result result: scanner) {
System.out.println("行健:" + Bytes.toString(result.getRow()));
byte[] name = result.getValue(Bytes.toBytes("info"), Bytes.toBytes("name"));
byte[] sex = result.getValue(Bytes.toBytes("info"), Bytes.toBytes("sex"));
byte[] city = result.getValue(Bytes.toBytes("address"), Bytes.toBytes("city"));
byte[] province = result.getValue(Bytes.toBytes("address"), Bytes.toBytes("province"));
if (name != null) System.out.println("姓名:" + Bytes.toString( name));
if (sex != null) System.out.println("性別:" + Bytes.toString( sex));
if (province != null) System.out.println("省份:" + Bytes.toString(province));
if (city != null) System.out.println("城市:" + Bytes.toString(city));
System.out.println("------------------------------");
}
}
/** 打印查詢結果:方法二 */
public void printResult2(ResultScanner scanner) throws Exception {
for (Result result: scanner) {
System.out.println("-----------------------");
// 遍歷所有的列及列值
for (Cell cell : result.listCells()) {
System.out.print(Bytes.toString(CellUtil.cloneQualifier(cell)) + ":");
System.out.print(Bytes.toString(CellUtil.cloneValue(cell)) + "\t");
}
System.out.println();
System.out.println("-----------------------");
}
}
// 釋放資源
@After
public void destory() throws Exception {
admin.close();
}
}