eclipse实现 hbase api进阶(二)

其他 2018-09-16 01:38:47 阅读次数: 0

这篇都是纯代码，看基础的可以查看 https://blog.csdn.net/weixin_41122339/article/details/81905663

zhe这篇不会像之前写的那么详细了，我就补充一下特殊的属性和方法

 1，增删改查增强

package myhbasedemo;

import java.io.IOException;
import java.util.ArrayList;
import java.util.Iterator;
import java.util.List;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.Cell;
import org.apache.hadoop.hbase.CellUtil;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.TableName;
import org.apache.hadoop.hbase.client.Connection;
import org.apache.hadoop.hbase.client.ConnectionFactory;
import org.apache.hadoop.hbase.client.Get;
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.util.Bytes;
import org.junit.Test;

public class demo {
/**
 * get方式查询数据
 * @throws IOException 
 */
@Test
public void getdata() throws IOException {
	Configuration conf = HBaseConfiguration.create();
	Connection conn = ConnectionFactory.createConnection(conf);
	Table tab = conn.getTable(TableName.valueOf("zxz", "testZ"));
	Get get=new Get(Bytes.toBytes("2"));//创建get对象指定rowkey
	Result re = tab.get(get);//提交get操作返回一个一个结果集
    List<Cell> cells = re.getColumnCells(Bytes.toBytes("f2"),Bytes.toBytes("weidu"));
    for (Cell cell : cells) {
		System.out.println(Bytes.toString(CellUtil.cloneValue(cell)));//使用cellutil这个工具类的clonevalue方法来获取值，在把他转成string类型，要不会乱码
	}
   
}

@Test
public void getdata1() throws IOException {
	Configuration conf = HBaseConfiguration.create();
	Connection conn = ConnectionFactory.createConnection(conf);
	Table tab = conn.getTable(TableName.valueOf("zxz", "testZ"));
	Get get=new Get(Bytes.toBytes("2"));//创建get对象指定rowkey
	//get可以设置一下属性
	get.setMaxVersions(7);//设置最大版本数
	get.setTimeRange(1000000L, 10000000L);//可以设置查询时会安装时间戳范围查
	Result re = tab.get(get);//提交get操作返回一个一个结果集
    List<Cell> cells = re.getColumnCells(Bytes.toBytes("f2"),Bytes.toBytes("weidu"));
    for (Cell cell : cells) {
		System.out.println(Bytes.toString(CellUtil.cloneValue(cell)));//使用cellutil这个工具类的clonevalue方法来获取值，在把他转成string类型，要不会乱码
	}
   
}
//批量put数据
@Test
public void putdata() throws IOException {
	Configuration conf = HBaseConfiguration.create();
	Connection conn = ConnectionFactory.createConnection(conf);
	Table tab = conn.getTable(TableName.valueOf("zxz", "testZ"));
	List<Put> puts=new ArrayList<>();
	for(int i=1;i<=10000;i++) {
	Put put=new Put(Bytes.toBytes("row"+i));
	put.addColumn(Bytes.toBytes("z1"), Bytes.toBytes("id"),Bytes.toBytes(i) );
	puts.add(put);
	}
	tab.put(puts);
}
/**
 * 通过扫描器缓存实现出现
 */
@Test
public void scannerCache() throws Exception {
	Configuration conf = HBaseConfiguration.create();
	Connection conn = ConnectionFactory.createConnection(conf);
	Table table = conn.getTable(TableName.valueOf("t1"));

	Scan scan = new Scan();
	// 查询缓存
	// System.out.println(scan.getCaching());

	scan.setStartRow(Bytes.toBytes("row1"));
	scan.setStopRow(Bytes.toBytes("row999999"));
	scan.addColumn(Bytes.toBytes("f1"), Bytes.toBytes("name"));
	scan.setCaching(10000); // 缓存10000
	scan.setBatch(3);

	ResultScanner s = table.getScanner(scan);
	Iterator<Result> it = s.iterator();
	long start = System.currentTimeMillis();
	while (it.hasNext()) {
		Result r = it.next();
		String str = Bytes.toString(r.getColumnLatestCell(Bytes.toBytes("f1"), Bytes.toBytes("name")).getValue());
		// System.out.println(str);
	}
	System.out.println(System.currentTimeMillis() - start);
}
/**
 * 通过扫描器缓存和batch组合出现
 */
@Test
public void scannerCacheNBatch() throws Exception {
	Configuration conf = HBaseConfiguration.create();
	Connection conn = ConnectionFactory.createConnection(conf);
	Table table = conn.getTable(TableName.valueOf("t4"));

	Scan scan = new Scan();
	scan.setCaching(3);
	scan.setBatch(1);

	ResultScanner s = table.getScanner(scan);
	Iterator<Result> it = s.iterator();
	while (it.hasNext()) {
		System.out.println("====================");
		Result r = it.next();
		System.out.println(toStr(r,"f1","age"));
		System.out.println(toStr(r,"f1","id"));
		System.out.println(toStr(r,"f1","name"));
		System.out.println(toStr(r,"f2","age"));
		System.out.println(toStr(r,"f2","id"));
		System.out.println(toStr(r,"f2","name"));
	}
}

private String toStr(Result r, String f1,String c1){
	Cell cell = r.getColumnLatestCell(Bytes.toBytes(f1), Bytes.toBytes(c1));
	if(cell != null){
		String row = Bytes.toString(cell.getRow());
		return new String(row + "/" + f1 + ":" + c1 + "=" + Bytes.toString(cell.getValue()));
	}
	return  new String("/" + f1 + ":" + c1 + "= null "); 
}
}

2，filter过滤器

org.apache.hadoop.hbase.filter.Filter 
org.apache.hadoop.hbase.filter.FilterBase 
org.apache.hadoop.hbase.filter.ColumnCountGetFilter 
org.apache.hadoop.hbase.filter.ColumnPaginationFilter 
org.apache.hadoop.hbase.filter.ColumnPrefixFilter 
org.apache.hadoop.hbase.filter.ColumnRangeFilter 
org.apache.hadoop.hbase.filter.CompareFilter 
org.apache.hadoop.hbase.filter.DependentColumnFilter 
org.apache.hadoop.hbase.filter.FamilyFilter 
org.apache.hadoop.hbase.filter.QualifierFilter 
org.apache.hadoop.hbase.filter.RowFilter 
org.apache.hadoop.hbase.filter.ValueFilter 
org.apache.hadoop.hbase.filter.FirstKeyOnlyFilter 
org.apache.hadoop.hbase.filter.FirstKeyValueMatchingQualifiersFilter 
org.apache.hadoop.hbase.filter.FuzzyRowFilter 
org.apache.hadoop.hbase.filter.InclusiveStopFilter 
org.apache.hadoop.hbase.filter.KeyOnlyFilter 
org.apache.hadoop.hbase.filter.MultipleColumnPrefixFilter 
org.apache.hadoop.hbase.filter.PageFilter 
org.apache.hadoop.hbase.filter.PrefixFilter 
org.apache.hadoop.hbase.filter.RandomRowFilter 
org.apache.hadoop.hbase.filter.SingleColumnValueFilter 
org.apache.hadoop.hbase.filter.SingleColumnValueExcludeFilter 
org.apache.hadoop.hbase.filter.SkipFilter 
org.apache.hadoop.hbase.filter.TimestampsFilter 
org.apache.hadoop.hbase.filter.WhileMatchFilter 
org.apache.hadoop.hbase.filter.FilterList

上面就是hbase集成的filter过滤器，在这里我们介绍几个常用的，剩下的大家自己试试吧

1，比较过滤器

 他们通常会有两个参数，第一个参数可以使用下面的值

 第二个参数他们会使用哪种类型的比较器

package myhbasedemo;


import java.util.Iterator;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.Cell;
import org.apache.hadoop.hbase.CellUtil;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.TableName;
import org.apache.hadoop.hbase.client.Connection;
import org.apache.hadoop.hbase.client.ConnectionFactory;
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.BinaryComparator;
import org.apache.hadoop.hbase.filter.ColumnPaginationFilter;
import org.apache.hadoop.hbase.filter.CompareFilter.CompareOp;
import org.apache.hadoop.hbase.filter.FamilyFilter;
import org.apache.hadoop.hbase.filter.FilterList;
import org.apache.hadoop.hbase.filter.KeyOnlyFilter;
import org.apache.hadoop.hbase.filter.PageFilter;
import org.apache.hadoop.hbase.filter.QualifierFilter;
import org.apache.hadoop.hbase.filter.RegexStringComparator;
import org.apache.hadoop.hbase.util.Bytes;
import org.apache.hadoop.hbase.filter.RowFilter;
import org.apache.hadoop.hbase.filter.SingleColumnValueExcludeFilter;
import org.apache.hadoop.hbase.filter.SubstringComparator;
import org.apache.hadoop.hbase.filter.ValueFilter;
import org.junit.Test;

public class filterdemo {
	//创建一个工具类避免使用重复的代码，来获取值
public String tostr(Result re,String cf,String c) {
	Cell cell = re.getColumnLatestCell(Bytes.toBytes(cf),Bytes.toBytes(c));
	if(cell !=null) {
		String row = Bytes.toString(CellUtil.cloneRow(cell));
		int value = Bytes.toInt(CellUtil.cloneValue(cell));
		return new String(row +"    "+cf+"    "+c+"    "+value);
	}
	return new String(cf+"   "+c+"=null");
}
/**
 * 使用rowkey过滤器，字节对比器
 * @throws Exception
 */
@Test
public void filter1() throws Exception {
	Configuration conf = HBaseConfiguration.create();
	Connection conn = ConnectionFactory.createConnection(conf);
	Table tab = conn.getTable(TableName.valueOf("zxz","testZ"));
	Scan scan =new Scan();
	//创建RowFilter过滤器,条件为，使用字节对比器结果返回rowkey小于10的数据
	scan.setFilter(new RowFilter(CompareOp.LESS,new BinaryComparator(Bytes.toBytes("row10"))));
	 ResultScanner re = tab.getScanner(scan);
	 Iterator<Result> it = re.iterator();
	 while(it.hasNext()) {
		 Result res = it.next();
		System.out.println(tostr(res, "z1", "id"));
		System.out.println(tostr(res, "z2", "id"));
	 }
}

/**
 * 使用容rowkey过滤器，正则串对比器
 */
@Test
public void rowFilterRegex() throws Exception{
	Configuration conf = HBaseConfiguration.create();
	Connection conn = ConnectionFactory.createConnection(conf);
	
	Table t = conn.getTable(TableName.valueOf("zxz","testZ"));
	Scan scan = new Scan();
	//创建RowFilter过滤器,条件为，使用正则对比器返回rowkey含有123内容的数据
	scan.setFilter(new RowFilter(CompareOp.EQUAL, new RegexStringComparator(".*[123]")));
	ResultScanner scanner = t.getScanner(scan);
	Iterator<Result> it = scanner.iterator();
	while(it.hasNext()){
		Result res = it.next();
		System.out.println(tostr(res, "z1", "id"));
		System.out.println(tostr(res, "z2", "id"));
	}
}

/**
 * 使用rowkey过滤器，子串对比器:
 */
@Test
public void rowFilterSubstring() throws Exception{
	Configuration conf = HBaseConfiguration.create();
	Connection conn = ConnectionFactory.createConnection(conf);
	
	Table t = conn.getTable(TableName.valueOf("zxz","testZ"));
	Scan scan = new Scan();
	//创建RowFilter过滤器,条件为使用字串对比器返回rowkey中含有w5的数据
	scan.setFilter(new RowFilter(CompareOp.EQUAL, new SubstringComparator("w5")));
	ResultScanner scanner = t.getScanner(scan);
	Iterator<Result> it = scanner.iterator();
	while(it.hasNext()){
		Result res = it.next();
		System.out.println(tostr(res, "z1", "id"));
		System.out.println(tostr(res, "z2", "id"));
	}
}

/**
 * 列族过滤器:字节对比器
 */
@Test
public void familyFilter() throws Exception{
	Configuration conf = HBaseConfiguration.create();
	Connection conn = ConnectionFactory.createConnection(conf);
	
	Table t = conn.getTable(TableName.valueOf("zxz","testZ"));
	Scan scan = new Scan();
	//创建FamilyFilter过滤器,条件为使用字节对比器返回列族为z2的数据
	scan.setFilter(new FamilyFilter(CompareOp.EQUAL, new BinaryComparator(Bytes.toBytes("z2"))));
	ResultScanner scanner = t.getScanner(scan);
	Iterator<Result> it = scanner.iterator();
	while(it.hasNext()){
		Result res = it.next();
		System.out.println(tostr(res, "z1", "id"));
		System.out.println(tostr(res, "z2", "id"));
	}
}

/**
 * 列过滤器: Qualifier,字节对比器
 */
@Test
public void qualifierFilter() throws Exception{
	Configuration conf = HBaseConfiguration.create();
	Connection conn = ConnectionFactory.createConnection(conf);
	
	Table t = conn.getTable(TableName.valueOf("zxz","testZ"));
	Scan scan = new Scan();
	//创建QualifierFilter过滤器,条件为，使用字节对比器返回列为id的数据
	scan.setFilter(new QualifierFilter(CompareOp.EQUAL, new BinaryComparator(Bytes.toBytes("id"))));
	ResultScanner scanner = t.getScanner(scan);
	Iterator<Result> it = scanner.iterator();
	while(it.hasNext()){
		Result res = it.next();
		System.out.println(tostr(res, "z1", "id"));
		System.out.println(tostr(res, "z2", "id"));
	}
}
/**
 * 值过滤器: ValueFilter,字节对比器
 */
@Test
public void valueFilter() throws Exception{
	Configuration conf = HBaseConfiguration.create();
	Connection conn = ConnectionFactory.createConnection(conf);
	
	Table t = conn.getTable(TableName.valueOf("zxz","testZ"));
	Scan scan = new Scan();
	//创建ValueFilter过滤器,条件为使用字节对比器返回值小于9999的数据
	scan.setFilter(new ValueFilter(CompareOp.LESS, new BinaryComparator(Bytes.toBytes("9999"))));
	ResultScanner scanner = t.getScanner(scan);
	Iterator<Result> it = scanner.iterator();
	while(it.hasNext()){
		Result res = it.next();
		System.out.println(tostr(res, "z1", "id"));
		System.out.println(tostr(res, "z2", "id"));
	}
}

2，专用过滤器(不在使用对比器，反而很简单)

/**
 * 单列值过滤
 */
@Test
public void singleColValFilter() throws Exception{
	Configuration conf = HBaseConfiguration.create();
	Connection conn = ConnectionFactory.createConnection(conf);
	
	Table t = conn.getTable(TableName.valueOf("zxz","testZ"));
	Scan scan = new Scan();
	
	SingleColumnValueExcludeFilter f = new SingleColumnValueExcludeFilter(Bytes.toBytes("z1"),
 Bytes.toBytes("id"),CompareOp.EQUAL, Bytes.toBytes("999"));
	scan.setFilter(f);
	ResultScanner scanner = t.getScanner(scan);
	Iterator<Result> it = scanner.iterator();
	while(it.hasNext()){
		Result res = it.next();
		System.out.println(tostr(res, "z1", "id"));
		System.out.println(tostr(res, "z2", "id"));
	}
}

/**
 * 分页过滤器,类似于limit
 */
@Test
public void pageFilter() throws Exception{
	Configuration conf = HBaseConfiguration.create();
	Connection conn = ConnectionFactory.createConnection(conf);
	
	Table t = conn.getTable(TableName.valueOf("t4"));
	Scan scan = new Scan();
	
	PageFilter f = new PageFilter(5);
	scan.setFilter(f);
	
	ResultScanner scanner = t.getScanner(scan);
	Iterator<Result> it = scanner.iterator();
	while(it.hasNext()){
		Result res = it.next();
		System.out.println(tostr(res, "z1", "id"));
		System.out.println(tostr(res, "z2", "id"));
	}
}

/**
 * 列分页过滤器,类似于limit
 */
@Test
public void columnPageFilter() throws Exception{
	Configuration conf = HBaseConfiguration.create();
	Connection conn = ConnectionFactory.createConnection(conf);
	
	Table t = conn.getTable(TableName.valueOf("zxz","testZ"));
	Scan scan = new Scan();
	
	ColumnPaginationFilter f = new ColumnPaginationFilter(2, 1);
	scan.setFilter(f);
	
	ResultScanner scanner = t.getScanner(scan);
	Iterator<Result> it = scanner.iterator();
	while(it.hasNext()){
		Result res = it.next();
		System.out.println(tostr(res, "z1", "id"));
		System.out.println(tostr(res, "z2", "id"));
	}
}

/**
 * 只返回key，不返回value
 */
@Test
public void keyOnlyFilter() throws Exception{
	Configuration conf = HBaseConfiguration.create();
	Connection conn = ConnectionFactory.createConnection(conf);
	
	Table t = conn.getTable(TableName.valueOf("zxz","testZ"));
	Scan scan = new Scan();
	
	KeyOnlyFilter f = new KeyOnlyFilter();
	scan.setFilter(f);
	
	ResultScanner scanner = t.getScanner(scan);
	Iterator<Result> it = scanner.iterator();
	while(it.hasNext()){
		Result res = it.next();
		System.out.println(tostr(res, "z1", "id"));
		System.out.println(tostr(res, "z2", "id"));
	}
}
/**
 *过滤器链,FilterList,
 */
@Test
public void filterList() throws Exception{
	Configuration conf = HBaseConfiguration.create();
	Connection conn = ConnectionFactory.createConnection(conf);
	
	Table t = conn.getTable(TableName.valueOf("zxz","testZ"));
	Scan scan = new Scan();
	
	FilterList list = new FilterList(FilterList.Operator.MUST_PASS_ALL); //使用过滤器链链接下面两个过滤条件
	//MUST_PASS_ALL属性是把下面的条件全部执行 MUST_PASS_ONE是任意一个条件成功就行
	list.addFilter(new FamilyFilter(CompareOp.EQUAL, new BinaryComparator(Bytes.toBytes("z1"))));
	list.addFilter(new QualifierFilter(CompareOp.EQUAL, new BinaryComparator(Bytes.toBytes("id"))));
	
	ResultScanner scanner = t.getScanner(scan);
	Iterator<Result> it = scanner.iterator();
	while(it.hasNext()){
		Result res = it.next();
		System.out.println(tostr(res, "z1", "id"));
		System.out.println(tostr(res, "z2", "id"));
	}

猜你喜欢

转载自blog.csdn.net/weixin_41122339/article/details/82054595
今日推荐
开源日报 | Chrome内置Gemini的意义不在于Gemini；中国AI追随之路的五大误区；ECharts创始人“下海”养鱼；谷歌I/O开发者大会什么都有，只是没有惊喜
微软回应中国区AI团队“打包赴美”传闻
基于大语言模型的开源知识库问答系统 MaxKB GitHub Star 数量突破 5,000 个！
美国拟限制 AI 大模型出口中国和俄罗斯
苹果将与 OpenAI 达成协议，将 ChatGPT 应用于 iPhone
openKylin 社区生态委员会第六次会议圆满召开
阿里云正式发布通义千问 2.5
Python 3.13 发布首个 Beta：实验性自由线程模式和 JIT、改进交互式解释器
Stack Overflow 拿我的代码去训练 AI 大模型，还封了我的账号
Pop!_OS 的 COSMIC 桌面完成 App Store 上架工作
《2024 年一季度互联网投融资运行情况》研究报告
报告：Django 仍然是 74% 开发者的首选
周排行
laravle中orm简单的增删改查
文本分类 特征选取之CHI开方检验
Spark核心编程-WordCount
大数据开发实战系列之电信客服(1)
读书笔记 - 把时间当作朋友 by 李笑来
python 笔记--if else
SpringBoot/Mybatis/Druid, 多数据源MultiDataSource配置思路
排序三个整数
redis集群搭建【2】-Windows中Redis集群搭建
STM32F030驱动TM1650点亮4联数码管
每日归档
更多
2024-05-16(6)
2024-05-15(24)
2024-05-14(0)
2024-05-13(18)
2024-05-12(0)
2024-05-11(38)
2024-05-10(38)
2024-05-09(35)
2024-05-08(42)
2024-05-07(14)

代码天地 © 2018 codetd.com

境外服务器   最新电视剧2022