ステップ1:Mavenのプロジェクトを作成し、インポートジャーパッケージ
<repositories>
<repository>
<id>cloudera</id>
<url>https://repository.cloudera.com/artifactory/cloudera-repos/</url>
</repository>
</repositories>
<dependencies>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-client</artifactId>
<version>2.6.0-mr1-cdh5.14.0</version>
</dependency>
<dependency>
<groupId>org.apache.hbase</groupId>
<artifactId>hbase-client</artifactId>
<version>1.2.0-cdh5.14.0</version>
</dependency>
<dependency>
<groupId>org.apache.hbase</groupId>
<artifactId>hbase-server</artifactId>
<version>1.2.0-cdh5.14.0</version>
</dependency>
<dependency>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
<version>4.12</version>
<scope>test</scope>
</dependency>
<dependency>
<groupId>org.testng</groupId>
<artifactId>testng</artifactId>
<version>6.14.3</version>
<scope>test</scope>
</dependency>
<dependency>
<groupId>org.junit.jupiter</groupId>
<artifactId>junit-jupiter-api</artifactId>
<version>RELEASE</version>
<scope>compile</scope>
</dependency>
</dependencies>
<build>
<plugins>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-compiler-plugin</artifactId>
<version>3.0</version>
<configuration>
<source>1.8</source>
<target>1.8</target>
<encoding>UTF-8</encoding>
<!-- <verbal>true</verbal>-->
</configuration>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-shade-plugin</artifactId>
<version>2.2</version>
<executions>
<execution>
<phase>package</phase>
<goals>
<goal>shade</goal>
</goals>
<configuration>
<filters>
<filter>
<artifact>*:*</artifact>
<excludes>
<exclude>META-INF/*.SF</exclude>
<exclude>META-INF/*.DSA</exclude>
<exclude>META-INF/*/RSA</exclude>
</excludes>
</filter>
</filters>
</configuration>
</execution>
</executions>
</plugin>
</plugins>
</build>
ステップ二つ:開発JAVAAPI 操作HB ASEテーブルデータ
1、クエリデータを、テーブルを作成し、テーブルにデータを追加
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.*;
import org.apache.hadoop.hbase.client.*;
import org.apache.hadoop.hbase.util.Bytes;
import java.io.IOException;
import java.util.ArrayList;
import java.util.Collections;
import java.util.List;
public class HbaseAPI {
/**
* 创建表 myuser
*
* @throws IOException
*/
public static void createTable() throws IOException {
//创建配置文件对象,并指定zookeeper的连接地址
Configuration conf = HBaseConfiguration.create();
conf.set("hbase.zookeeper.quorum", "node01:2181,node02:2181,node03:2181");
//获取连接
Connection connection = ConnectionFactory.createConnection(conf);
//获取超级管理员
Admin admin = connection.getAdmin();
//实例表名和表结构
Table myuser = connection.getTable(TableName.valueOf("myuser"));
//设置表结构
HTableDescriptor hTableDescriptor = new HTableDescriptor("myuser");
//设置列族
HColumnDescriptor hColumnDescriptor1 = new HColumnDescriptor("f1");
HColumnDescriptor hColumnDescriptor2 = new HColumnDescriptor("f2");
//建立表与列族之间的关系
hTableDescriptor.addFamily(hColumnDescriptor1);
hTableDescriptor.addFamily(hColumnDescriptor2);
//创建表
admin.createTable(hTableDescriptor);
admin.close();
//关闭连接
connection.close();
}
/**
* 向表中添加数据
*
* @throws IOException
*/
public static void putData() throws IOException {
Configuration conf = HBaseConfiguration.create();
conf.set("hbase.zookeeper.quorum", "node01:2181,node02:2181,node03:2181");
Connection connection = ConnectionFactory.createConnection(conf);
Admin admin = connection.getAdmin();
//实例表名和表结构
Table myuser = connection.getTable(TableName.valueOf("myuser"));
//创建put对象,并指定rowkey
Put put = new Put("001".getBytes());
put.addColumn("f1".getBytes(), "id".getBytes(), Bytes.toBytes("1"));
put.addColumn("f1".getBytes(), "name".getBytes(), Bytes.toBytes("zhangsan"));
put.addColumn("f1".getBytes(), "age".getBytes(), Bytes.toBytes("18"));
//插入数据
myuser.put(put);
//关闭表
myuser.close();
}
/**
* 初始化一批数据到HBase当中用于查询
*
* @throws IOException
*/
public static void putDatas() throws IOException {
Configuration conf = HBaseConfiguration.create();
conf.set("hbase.zookeeper.quorum", "node01:2181,node02:2181,node03:2181");
Connection connection = ConnectionFactory.createConnection(conf);
Admin admin = connection.getAdmin();
//实例表名和表结构
Table myuser = connection.getTable(TableName.valueOf("myuser"));
//创建put对象,并指定rowkey
Put put = new Put("001".getBytes());
put.addColumn("f1".getBytes(), "id".getBytes(), Bytes.toBytes(1));
put.addColumn("f1".getBytes(), "name".getBytes(), Bytes.toBytes("曹操"));
put.addColumn("f1".getBytes(), "age".getBytes(), Bytes.toBytes(30));
put.addColumn("f2".getBytes(), "sex".getBytes(), Bytes.toBytes("1"));
put.addColumn("f2".getBytes(), "address".getBytes(), Bytes.toBytes("沛国谯县"));
put.addColumn("f2".getBytes(), "phone".getBytes(), Bytes.toBytes("16888888888"));
put.addColumn("f2".getBytes(), "say".getBytes(), Bytes.toBytes("helloworld"));
Put put2 = new Put("0003".getBytes());
put2.addColumn("f1".getBytes(), "id".getBytes(), Bytes.toBytes(2));
put2.addColumn("f1".getBytes(), "name".getBytes(), Bytes.toBytes("刘备"));
put2.addColumn("f1".getBytes(), "age".getBytes(), Bytes.toBytes(32));
put2.addColumn("f2".getBytes(), "sex".getBytes(), Bytes.toBytes("1"));
put2.addColumn("f2".getBytes(), "address".getBytes(), Bytes.toBytes("幽州涿郡涿县"));
put2.addColumn("f2".getBytes(), "phone".getBytes(), Bytes.toBytes("17888888888"));
put2.addColumn("f2".getBytes(), "say".getBytes(), Bytes.toBytes("talk is cheap , show me the code"));
Put put3 = new Put("0004".getBytes());
put3.addColumn("f1".getBytes(), "id".getBytes(), Bytes.toBytes(3));
put3.addColumn("f1".getBytes(), "name".getBytes(), Bytes.toBytes("孙权"));
put3.addColumn("f1".getBytes(), "age".getBytes(), Bytes.toBytes(35));
put3.addColumn("f2".getBytes(), "sex".getBytes(), Bytes.toBytes("1"));
put3.addColumn("f2".getBytes(), "address".getBytes(), Bytes.toBytes("下邳"));
put3.addColumn("f2".getBytes(), "phone".getBytes(), Bytes.toBytes("12888888888"));
put3.addColumn("f2".getBytes(), "say".getBytes(), Bytes.toBytes("what are you 弄啥嘞!"));
Put put4 = new Put("0005".getBytes());
put4.addColumn("f1".getBytes(), "id".getBytes(), Bytes.toBytes(4));
put4.addColumn("f1".getBytes(), "name".getBytes(), Bytes.toBytes("诸葛亮"));
put4.addColumn("f1".getBytes(), "age".getBytes(), Bytes.toBytes(28));
put4.addColumn("f2".getBytes(), "sex".getBytes(), Bytes.toBytes("1"));
put4.addColumn("f2".getBytes(), "address".getBytes(), Bytes.toBytes("四川隆中"));
put4.addColumn("f2".getBytes(), "phone".getBytes(), Bytes.toBytes("14888888888"));
put4.addColumn("f2".getBytes(), "say".getBytes(), Bytes.toBytes("出师表你背了嘛"));
Put put5 = new Put("0005".getBytes());
put5.addColumn("f1".getBytes(), "id".getBytes(), Bytes.toBytes(5));
put5.addColumn("f1".getBytes(), "name".getBytes(), Bytes.toBytes("司马懿"));
put5.addColumn("f1".getBytes(), "age".getBytes(), Bytes.toBytes(27));
put5.addColumn("f2".getBytes(), "sex".getBytes(), Bytes.toBytes("1"));
put5.addColumn("f2".getBytes(), "address".getBytes(), Bytes.toBytes("哪里人有待考究"));
put5.addColumn("f2".getBytes(), "phone".getBytes(), Bytes.toBytes("15888888888"));
put5.addColumn("f2".getBytes(), "say".getBytes(), Bytes.toBytes("跟诸葛亮死掐"));
Put put6 = new Put("0006".getBytes());
put6.addColumn("f1".getBytes(), "id".getBytes(), Bytes.toBytes(5));
put6.addColumn("f1".getBytes(), "name".getBytes(), Bytes.toBytes("xiaobubu—吕布"));
put6.addColumn("f1".getBytes(), "age".getBytes(), Bytes.toBytes(28));
put6.addColumn("f2".getBytes(), "sex".getBytes(), Bytes.toBytes("1"));
put6.addColumn("f2".getBytes(), "address".getBytes(), Bytes.toBytes("内蒙人"));
put6.addColumn("f2".getBytes(), "phone".getBytes(), Bytes.toBytes("15788888888"));
put6.addColumn("f2".getBytes(), "say".getBytes(), Bytes.toBytes("貂蝉去哪了"));
List<Put> datas = new ArrayList<>();
Collections.addAll(datas, put, put2, put3, put4, put5, put6);
//插入数据
myuser.put(datas);
//关闭表
myuser.close();
}
/**
* 按照rowkey进行查询获取所有列的所有值
* 查询主键为0004的人
*
* @throws IOException
*/
public static void getData() throws IOException {
Configuration conf = new Configuration();
conf.set("hbase.zookeeper.quorum", "node01:2181,node02:2181,node03:2181");
Connection connection = ConnectionFactory.createConnection(conf);
Table myuser = connection.getTable(TableName.valueOf("myuser"));
//设置需要读取的数据(rowkey为0004)
Get get = new Get("0004".getBytes());
//查询某一个列族的数据
// get.addFamily("f1".getBytes());
//查询指定列族下的指定列,查询
get.addColumn("f1".getBytes(), "name".getBytes());
//读取数据 一个result,就是一行数据
Result result = myuser.get(get);
Cell[] cells = result.rawCells();
//获取所有的列名称以及列的值
for (Cell cell : cells) {
System.out.println(Bytes.toString(CellUtil.cloneFamily(cell)));
System.out.println(Bytes.toString(CellUtil.cloneQualifier(cell)));
System.out.println(Bytes.toString(CellUtil.cloneRow(cell)));
System.out.println(Bytes.toString(CellUtil.cloneValue(cell)));
}
myuser.close();
}
/**
* 通过startRowKey和endRowKey进行扫描
*
* @throws IOException
*/
public static void scanRowKey() throws IOException {
Configuration conf = new Configuration();
conf.set("hbase.zookeeper.quorum", "node01:2181,node02:2181,node03:2181");
Connection connection = ConnectionFactory.createConnection(conf);
Table myuser = connection.getTable(TableName.valueOf("myuser"));
Scan scan = new Scan();
scan.setStartRow("0001".getBytes());
scan.setStopRow("0006".getBytes());
//读取数据 一个result,就是一行数据
ResultScanner scanner = myuser.getScanner(scan);
for (Result result : scanner) {
KeyValue[] raw = result.raw();
for (KeyValue keyValue : raw) {
System.out.println(Bytes.toString(keyValue.getFamily()) + " " + Bytes.toString(keyValue.getQualifier()));
}
System.out.println(Bytes.toString(result.getValue("f1".getBytes(), "age".getBytes())));
}
myuser.close();
}
/**
* scan进行全表扫描
*
* @throws IOException
*/
public static void scanAllData() throws IOException {
Configuration conf = new Configuration();
conf.set("hbase.zookeeper.quorum", "node01:2181,node02:2181,node03:2181");
Connection connection = ConnectionFactory.createConnection(conf);
Table myuser = connection.getTable(TableName.valueOf("myuser"));
Scan scan = new Scan();
ResultScanner scanner = myuser.getScanner(scan);
for (Result result : scanner) {
System.out.println(Bytes.toString(result.getValue("f1".getBytes(), "id".getBytes())));
System.out.println(Bytes.toString(result.getValue("f1".getBytes(), "name".getBytes())));
System.out.println(Bytes.toString(result.getValue("f1".getBytes(), "age".getBytes())));
}
myuser.close();
}
public static void main(String[] args) throws IOException {
// createTable();
// putData();
// putDatas();
// getData();
// scanRowKey();
scanAllData();
}
}
2、フィルタクエリ
多くのフィルタの種類が、2つのカテゴリに分けることができる- コンパレータフィルタ、特殊なフィルター
アクションフィルタは、サーバーのデータが条件を満たしているかどうかを決定することで、その後、条件を満たしたデータのみをクライアントに。
HBaseのフィルター比較演算子:
LESS < LESS_OR_EQUAL <= EQUAL = NOT_EQUAL <> GREATER_OR_EQUAL> = GREATER> NO_OPはすべて除外します |
HBaseのは、フィルタの特殊フィルター(指定された比較機構):
比較BinaryComparatorはBytes.compareTo(バイト[])を使用して、バイト配列バイトインデックス順序を指定しました 同じフロントとBinaryPrefixComparatorが、より多くのデータが左端と同じです 与えられたNullComparatorの分析は空であります BitComparatorビット単位の比較 RegexStringComparatorは、通常のコンパレータを提供し、唯一の非EQUAL EQUALをサポートしています サブSubstringComparator値であったか否かを判断します。 |
2.1、フィルターコンパレータ
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.TableName;
import org.apache.hadoop.hbase.client.*;
import org.apache.hadoop.hbase.filter.CompareFilter;
import org.apache.hadoop.hbase.filter.SubstringComparator;
import org.apache.hadoop.hbase.filter.ValueFilter;
import org.apache.hadoop.hbase.util.Bytes;
import java.io.IOException;
public class HbaseAPI2 {
/**
* 比较过滤器
*
* @throws IOException
*/
public static void comparisonFilter() throws IOException {
Configuration conf = new Configuration();
conf.set("hbase.zookeeper.quorum", "node01:2181,node02:2181,node03:2181");
Connection connection = ConnectionFactory.createConnection(conf);
Table myuser = connection.getTable(TableName.valueOf("myuser"));
Scan scan = new Scan();
//1、比较过滤器
// //1.1、rowKey过滤器RowFilter(查询rowkey=0003的数据)
// RowFilter rowFilter = new RowFilter(CompareFilter.CompareOp.EQUAL, new BinaryComparator(Bytes.toBytes("0003")));
// scan.setFilter(rowFilter);
// //1.2、列族过滤器FamilyFilter(查询比f2列族小的所有的列族内的数据)
// FamilyFilter familyFilter = new FamilyFilter(CompareFilter.CompareOp.LESS_OR_EQUAL, new SubstringComparator("f2"));
// scan.setFilter(familyFilter);
// //1.3、列过滤器QualifierFilter(只查询name列的值)
// QualifierFilter qualifierFilter = new QualifierFilter(CompareFilter.CompareOp.EQUAL, new SubstringComparator("name"));
// scan.setFilter(qualifierFilter);
//1.4、列值过滤器ValueFilter(hbase值过滤器 查询所有列当中包含i的数据)
ValueFilter valueFilter = new ValueFilter(CompareFilter.CompareOp.EQUAL, new SubstringComparator("i"));
scan.setFilter(valueFilter);
ResultScanner scanner = myuser.getScanner(scan);
for (Result result : scanner) {
//获取rowkey
System.out.println(Bytes.toString(result.getRow()));
//指定列族以及列打印列当中的数据出来
System.out.println(Bytes.toString(result.getValue("f1".getBytes(),"id".getBytes())));
System.out.println(Bytes.toString(result.getValue("f1".getBytes(),"name".getBytes())));
System.out.println(Bytes.toString(result.getValue("f1".getBytes(),"age".getBytes())));
}
myuser.close();
}
public static void main(String[] args) throws IOException {
comparisonFilter();
}
}
2.2、特殊なフィルター
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.TableName;
import org.apache.hadoop.hbase.client.*;
import org.apache.hadoop.hbase.filter.PageFilter;
import org.apache.hadoop.hbase.util.Bytes;
import java.io.IOException;
public class HbaseAPI3 {
/**
* 专用过滤器
*
* @throws IOException
*/
public static void specialFilter() throws IOException {
Configuration conf = new Configuration();
conf.set("hbase.zookeeper.quorum", "node01:2181,node02:2181,node03:2181");
Connection connection = ConnectionFactory.createConnection(conf);
Table myuser = connection.getTable(TableName.valueOf("myuser"));
Scan scan = new Scan();
// //2.1、单列值过滤器 SingleColumnValueFilter(单列值过滤器,返回满足条件的整行数据)
// SingleColumnValueFilter singleColumnValueFilter = new SingleColumnValueFilter("f1".getBytes(), "name".getBytes(), CompareFilter.CompareOp.EQUAL, "刘备".getBytes());
// scan.setFilter(singleColumnValueFilter);
// //2.2、列值排除过滤器SingleColumnValueExcludeFilter(与SingleColumnValueFilter相反,会排除掉指定的列,其他的列全部返回)
// SingleColumnValueExcludeFilter singleColumnValueExcludeFilter = new SingleColumnValueExcludeFilter("f1".getBytes(), "name".getBytes(), CompareFilter.CompareOp.EQUAL, "孙权".getBytes());
// scan.setFilter(singleColumnValueExcludeFilter);
// //2.3、rowkey前缀过滤器PrefixFilter(查询以001开头的所有前缀的rowkey)
// PrefixFilter prefixFilter = new PrefixFilter("001".getBytes());
// scan.setFilter(prefixFilter);
//2.4、分页过滤器PageFilter(参数pageSize指定要查询数据 rowkey的个数)
PageFilter pageFilter = new PageFilter(3);
scan.setFilter(pageFilter);
ResultScanner scanner = myuser.getScanner(scan);
for (Result result : scanner) {
//获取rowkey
System.out.println(Bytes.toString(result.getRow()));
//指定列族以及列打印列当中的数据出来
System.out.println(Bytes.toString(result.getValue("f1".getBytes(),"id".getBytes())));
System.out.println(Bytes.toString(result.getValue("f1".getBytes(),"name".getBytes())));
System.out.println(Bytes.toString(result.getValue("f1".getBytes(),"age".getBytes())));
}
myuser.close();
}
public static void main(String[] args) throws IOException {
specialFilter();
}
}
ページングフィルタPageFilter
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.TableName;
import org.apache.hadoop.hbase.client.*;
import org.apache.hadoop.hbase.filter.PageFilter;
import org.apache.hadoop.hbase.util.Bytes;
import java.io.IOException;
public class HbaseAPI4 {
/**
* 分页过滤器PageFilter
* @throws IOException
*/
public static void pageFilter() throws IOException {
Configuration conf = new Configuration();
conf.set("hbase.zookeeper.quorum","node01:2181,node02:2181,node03:2181");
Connection connection = ConnectionFactory.createConnection(conf);
Table myuser = connection.getTable(TableName.valueOf("myuser"));
int pageNum = 4;
int pageSize = 2;
Scan scan = new Scan();
if (pageNum == 1) {
PageFilter filter = new PageFilter(pageSize);
scan.setStartRow(Bytes.toBytes(""));
scan.setFilter(filter);
scan.setMaxResultSize(pageSize);
ResultScanner scanner = myuser.getScanner(scan);
for (Result result : scanner) {
//获取rowkey
System.out.println(Bytes.toString(result.getRow()));
//指定列族以及列打印列当中的数据出来
// System.out.println(Bytes.toInt(result.getValue("f1".getBytes(), "id".getBytes())));
System.out.println(Bytes.toString(result.getValue("f1".getBytes(), "name".getBytes())));
//System.out.println(Bytes.toString(result.getValue("f2".getBytes(), "phone".getBytes())));
}
}else{
String startRowKey ="";
PageFilter filter = new PageFilter((pageNum - 1) * pageSize + 1 );
scan.setStartRow(startRowKey.getBytes());
scan.setMaxResultSize((pageNum - 1) * pageSize + 1);
scan.setFilter(filter);
ResultScanner scanner = myuser.getScanner(scan);
for (Result result : scanner) {
byte[] row = result.getRow();
startRowKey = new String(row);
}
Scan scan2 = new Scan();
scan2.setStartRow(startRowKey.getBytes());
scan2.setMaxResultSize(Long.valueOf(pageSize));
PageFilter filter2 = new PageFilter(pageSize);
scan2.setFilter(filter2);
ResultScanner scanner1 = myuser.getScanner(scan2);
for (Result result : scanner1) {
byte[] row = result.getRow();
System.out.println(new String(row));
}
}
myuser.close();
}
public static void main(String[] args) throws IOException {
pageFilter();
}
}
統合2.3、マルチフィルタクエリFilterList
要件:使用SingleColumnValueFilterクエリのF1列ファミリは、名前は劉備のデータであり、かつ同時に満たすの00のデータの先頭にプレフィックスのrowKey(PrefixFilter)
/**
* 多过滤器组合使用
*/
@Test
public void manyFilter() throws IOException {
//获取连接
Configuration configuration = HBaseConfiguration.create();
configuration.set("hbase.zookeeper.quorum", "node01:2181,node02:2181,node03:2181");
Connection connection = ConnectionFactory.createConnection(configuration);
Table myuser = connection.getTable(TableName.valueOf("myuser"));
Scan scan = new Scan();
FilterList filterList = new FilterList();
SingleColumnValueFilter singleColumnValueFilter = new SingleColumnValueFilter("f1".getBytes(), "name".getBytes(), CompareFilter.CompareOp.EQUAL, "刘备".getBytes());
PrefixFilter prefixFilter = new PrefixFilter("00".getBytes());
filterList.addFilter(singleColumnValueFilter);
filterList.addFilter(prefixFilter);
scan.setFilter(filterList);
ResultScanner scanner = myuser.getScanner(scan);
for (Result result : scanner) {
//获取rowkey
System.out.println(Bytes.toString(result.getRow()));
//指定列族以及列打印列当中的数据出来
// System.out.println(Bytes.toInt(result.getValue("f1".getBytes(), "id".getBytes())));
System.out.println(Bytes.toString(result.getValue("f1".getBytes(), "name".getBytes())));
//System.out.println(Bytes.toString(result.getValue("f2".getBytes(), "phone".getBytes())));
}
myuser.close();
}
3、削除データのrowKeyに従って
/**
* 删除数据
*/
@Test
public void deleteByRowKey() throws IOException {
//获取连接
Configuration configuration = HBaseConfiguration.create();
configuration.set("hbase.zookeeper.quorum","node01:2181,node02:2181,node03:2181");
Connection connection = ConnectionFactory.createConnection(configuration);
Table myuser = connection.getTable(TableName.valueOf("myuser"));
Delete delete = new Delete("0001".getBytes());
myuser.delete(delete);
myuser.close();
}
4、操作するテーブルを削除
@Test
public void deleteTable() throws IOException {
//获取连接
Configuration configuration = HBaseConfiguration.create();
configuration.set("hbase.zookeeper.quorum","node01:2181,node02:2181,node03:2181");
Connection connection = ConnectionFactory.createConnection(configuration);
Admin admin = connection.getAdmin();
admin.disableTable(TableName.valueOf("myuser"));
admin.deleteTable(TableName.valueOf("myuser"));
admin.close();
}