Hbase各种查询总结
运用hbase好长时间了,今天利用闲暇时间把Hbase的各种查询总结下,以后有时间把协处理器和自定义File总结下。
查询条件分为:
1、统计表数据
2,hbase 简单分页
3,like 查询
4 , AND 查询
5 , OR 查询
6 ,rowkey 的 in 查询
7 , 正则查询
上代码先。
package com.query; 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.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.client.coprocessor.AggregationClient;
import org.apache.hadoop.hbase.client.coprocessor.LongColumnInterpreter;
import org.apache.hadoop.hbase.filter.BinaryComparator;
import org.apache.hadoop.hbase.filter.Filter;
import org.apache.hadoop.hbase.filter.FilterList;
import org.apache.hadoop.hbase.filter.FilterList.Operator;
import org.apache.hadoop.hbase.filter.PageFilter;
import org.apache.hadoop.hbase.filter.PrefixFilter;
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.filter.SubstringComparator;
import org.apache.hadoop.hbase.filter.CompareFilter.CompareOp;
import org.apache.hadoop.hbase.filter.ValueFilter;
import org.apache.hadoop.hbase.util.Bytes;
import org.apache.log4j.Logger; import basecommon.PropertyUtil; public class HbaseConnectionUtils {
private static Logger log = Logger.getLogger(HbaseConnectionUtils.class);
private static HbaseConnectionUtils instance = null;
public static Configuration config = null;
private static Connection connection = null; private HbaseConnectionUtils() { } /**
* @author c_lishaoying 983068303@qq.com
*
* 加载集群配置
*/
static {
config = HBaseConfiguration.create();
config.set("hbase.zookeeper.quorum",
PropertyUtil.get("zookeeper.quorum"));
config.set("hbase.zookeeper.property.clientPort",
PropertyUtil.get("zookeeper.property.clientPort"));
config.setLong("hbase.client.scanner.timeout.period", Integer.MAX_VALUE);
try {
connection = ConnectionFactory.createConnection(config);
} catch (Exception e) {
log.debug("connection构建失败");
}
} public static HbaseConnectionUtils getInstance() {
if (instance == null) {
// 给类加锁 防止线程并发
synchronized (HbaseConnectionUtils.class) {
if (instance == null) {
instance = new HbaseConnectionUtils();
}
}
}
return instance;
} public Configuration getConfiguration() {
return config;
} public Connection getConnection() {
return connection;
} /**
* @author c_lishaoying 983068303@qq.com 获取表连接
*
*/
public static Table getTable(String tableName) {
try {
return connection.getTable(TableName.valueOf(tableName));
} catch (IOException e) {
e.printStackTrace();
}
return null;
} /**
* @author c_lishaoying
* @email 983068303@qq.com 协处理器查询总数据
*
*/
public int getRecordCount(String tableName) {
AggregationClient aggregationClient = new AggregationClient(config);
Scan scan = new Scan();
try {
Long rowCount = aggregationClient.rowCount(
TableName.valueOf(tableName), new LongColumnInterpreter(),
scan);
aggregationClient.close();
return rowCount.intValue();
} catch (Throwable e) {
e.printStackTrace();
}
return 0;
} /**
* @author c_lishaoying
* @email 983068303@qq.com 协处理器查询总数据 添加查询条件的Scan统计总数
*/
public static int getTotalRecord(Table keyIndexTable, Configuration config,
final Scan scan) {
int count = 0;
AggregationClient aggregationClient = new AggregationClient(config);
try {
Long rowCount = aggregationClient.rowCount(keyIndexTable,
new LongColumnInterpreter(), scan);
aggregationClient.close();
count = rowCount.intValue();
} catch (Throwable e) {
e.printStackTrace();
}
return count;
} /**
* @author c_lishaoying
* @email 983068303@qq.com 协处理器查询总数据 添加查询条件的Scan统计总数 queryString数组长度为3
* queryString[0] 列族 queryString[1]字段 queryString[2] 字段值
*/
public static int queryByCloumn(String tablename, String[] queryString) { int count = 0;
if (tablename == null) {
log.info("配置的表名称为空!");
} else {
log.info("表名称为:" + tablename);
Table queryTablename = getTable(tablename);
Scan scan = new Scan();
scan = getScan(queryString);
count = getTotalRecord(queryTablename, config, scan);
} return count;
} /**
* @author c_lishaoying
* @email 983068303@qq.com 非协处理器查询总数据 添加查询条件的Scan统计总数 queryString数组长度为3
* queryString[0] 列族 queryString[1]字段 queryString[2] 字段值
*/
public static int scan(String tablename, String[] condition) {
Table queryTablename = getTable(tablename);
String[] s = condition;
Scan scan = new Scan();
scan.addColumn(Bytes.toBytes(s[0]), Bytes.toBytes(s[1]));
SingleColumnValueFilter singleColumnValueFilter = new SingleColumnValueFilter(
Bytes.toBytes(s[0]), Bytes.toBytes(s[1]), CompareOp.EQUAL,
new BinaryComparator(Bytes.toBytes(s[2])));
scan.setFilter(singleColumnValueFilter);
int i = 0;
try {
ResultScanner rs = queryTablename.getScanner(scan);
/*
* for(Iterator it = rs.iterator(); it.hasNext();){ it.next(); }
*/
for (Result r : rs) {
i++;
} } catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
return i;
} /**
* @author c_lishaoying
* @email 983068303@qq.com 查询字段相等的值 相当于where city = ‘上海’ queryString数组长度为3
* queryString[0] 列族 queryString[1]字段 queryString[2] 字段值
*/
public static Scan getScan(String[] condition) {
Scan scan = new Scan();
if (condition == null || condition.length != 3) {
return new Scan();
}
FilterList filterList = new FilterList();
String[] s = condition;
BinaryComparator comp = new BinaryComparator(Bytes.toBytes(s[2]));
filterList.addFilter(new SingleColumnValueFilter(Bytes.toBytes(s[0]),
Bytes.toBytes(s[1]), CompareOp.EQUAL, Bytes.toBytes(s[2])));
scan.setFilter(filterList);
return scan;
} /**
* @author c_lishaoying
* @email 983068303@qq.com 查询字段相等的值 应用正则表达式 相当于where city like ‘%上海%’
* queryString数组长度为3 queryString[0] 列族 queryString[1]字段
* queryString[2] 字段值
*/
public static Scan regexscan(String tablename, String[] condition) {
Table queryTablename = getTable(tablename);
String[] s = condition;
Scan scan = new Scan();
scan.addColumn(Bytes.toBytes(s[0]), Bytes.toBytes(s[1]));
SingleColumnValueFilter singleColumnValueFilter = new SingleColumnValueFilter(
Bytes.toBytes(s[0]), Bytes.toBytes(s[1]), CompareOp.EQUAL,
new RegexStringComparator(".*" + s[2] + ".*"));
scan.setFilter(singleColumnValueFilter);
return scan;
} /**
* @author c_lishaoying
* @email 983068303@qq.com 查询该列的值
*/
public static Scan valuescan(String tablename, String[] condition) {
Table queryTablename = getTable(tablename);
String[] s = condition;
Scan scan = new Scan(); Filter filter1 = new ValueFilter(CompareOp.EQUAL,
new SubstringComparator(s[2]));
scan.setFilter(filter1);
return scan;
} /**
* @author c_lishaoying
* @email 983068303@qq.com 根据rowkey 查询 相当于 where id in ()
* queryString数组都为rowkey
*/
public static Scan rowscan(String tablename, String[] condition) {
Scan scan = new Scan();
FilterList filterList = new FilterList(Operator.MUST_PASS_ONE);
for (String s : condition) {
Filter filter = new RowFilter(CompareOp.EQUAL,
new SubstringComparator(s));
filterList.addFilter(filter);
}
scan.setFilter(filterList);
return scan;
} /**
* @author c_lishaoying
* @email 983068303@qq.com 查询该列的值 相当于where city = ‘上海’ AND name =‘酒店’
* queryString数组长度为3 queryString[0] 列族 queryString[1]字段
* queryString[2] 字段值
*/ public static Scan listAndColumnscan(String tablename,
List<String[]> condition) {
Scan scan = new Scan();
List<Filter> filters = new ArrayList<Filter>(); for (String[] s : condition) {
filters.add(new SingleColumnValueFilter(Bytes.toBytes(s[0]), // 列族
Bytes.toBytes(s[1]), // 列名
CompareOp.EQUAL, Bytes.toBytes(s[2]))); // 值
}
FilterList filterList = new FilterList(Operator.MUST_PASS_ALL, filters);
scan.setFilter(filterList);
return scan;
} /**
* @author c_lishaoying
* @email 983068303@qq.com 查询该列的值 相当于where city = ‘上海’ OR name =‘酒店’
* queryString数组长度为3 queryString[0] 列族 queryString[1]字段
* queryString[2] 字段值
*/
public static Scan listOrColumnscan(String tablename,
List<String[]> condition) {
Scan scan = new Scan();
ArrayList<Filter> listForFilters = new ArrayList<Filter>();
Filter filter = null;
for (String[] s : condition) {
filter = new SingleColumnValueFilter(Bytes.toBytes(s[0]), // 列族
Bytes.toBytes(s[1]), // 列名
CompareOp.EQUAL, Bytes.toBytes(s[2]));
listForFilters.add(filter);
}
// 通过将operator参数设置为Operator.MUST_PASS_ONE,达到list中各filter为"或"的关系
// 默认operator参数的值为Operator.MUST_PASS_ALL,即list中各filter为"并"的关系
Filter filterList = new FilterList(FilterList.Operator.MUST_PASS_ONE,
listForFilters);
scan.setFilter(filterList);// 多条件过滤
return scan;
} /**
* @author c_lishaoying
* @email 983068303@qq.com 通过多条件联合查询和限制返回页数 相当于mysql 中的limit 0,1000
*/
public Scan queryByFilter(String tablename, List<String[]> arr,
String starString, String stopString) throws IOException {
FilterList filterList = new FilterList();
Scan scan = new Scan();
for (String[] s : arr) {
SubstringComparator comp = new SubstringComparator(s[2]);
filterList
.addFilter(new SingleColumnValueFilter(Bytes.toBytes(s[0]),
Bytes.toBytes(s[1]), CompareOp.EQUAL, comp));
}
PageFilter pageFilter = new PageFilter(1000);
filterList.addFilter(pageFilter);
scan.setFilter(filterList);
scan.setStartRow(Bytes.toBytes(starString));
scan.setStartRow(Bytes.toBytes(stopString));
return scan;
} }
Hbase各种查询总结的更多相关文章
- hbase分页查询
为了广大技术爱好者学习netty,在这里帮新浪微博@nettying宣传下他出版的新书 <netty权威指南>@nettying兄在华为NIO实践多年,这本书是他的技术和经验的一个结晶.N ...
- hadoop之根据Rowkey从HBase中查询数据
1.Hbase 根据rowkey 查询 conf的配置信息如下: conf = new Configuration(); conf.set("hbase.zookeeper.quorum&q ...
- hbase的查询scan功能注意点(setStartRow, setStopRow)
来自http://hi.baidu.com/7636553/blog/item/982beb17713bc004972b43ee.html hbase的scan查询功能注意项: Scan scan = ...
- 根据Rowkey从HBase中查询数据
/** * @Title: queryData * @Description: 从HBase查询出数据 * @author xxxx * @param tableName * 表名 * @param ...
- 基于Solr的HBase实时查询方案
实时查询方案 HBase+Solr+HBase-Indexer 1.HBase提供海量数据存储 2.solr提供索引构建与查询 3.HBase indexer提供自己主动化索引构建(从HBase到So ...
- 「从零单排HBase 04」HBase高性能查询揭秘
先给结论吧:HBase利用compaction机制,通过大量的读延迟毛刺和一定的写阻塞,来换取整体上的读取延迟的平稳. 1.为什么要compaction 在上一篇 HBase读写 中我们提到了,HBa ...
- 吴超老师课程--HBASE的查询手机项目
查询1.按RowKey查询2.按手机号码查询3.按手机号码的区域查询 //查询手机13450456688的所有上网记录 public static void scan(String tableName ...
- 云HBase发布全文索引服务,轻松应对复杂查询
云HBase发布了“全文索引服务”功能,自2019年01月25日后创建的云HBase实例,可以在控制台免费开启此“全文索引服务”功能.使用此功能可以让用户在HBase之上构建功能更丰富的搜索业务,不再 ...
- HBase根据Rowkey批量查询数据JAVA API(一次查多条,返回多个记录)
最近在生产中遇到了一个需求,前台给我多个rowkey的List,要在hbase中查询多个记录(返回给前台list).在网上也查了很多,不过自己都不太满意,filter的功能有可能查询结果不是准确值,而 ...
随机推荐
- [转]centos7.2 下 nginx 开机启动
1.在系统服务目录里创建nginx.service文件 vi /lib/systemd/system/nginx.service 内容如下 [Unit] Description=nginx After ...
- 历年NOIP真题总结
前言:最近把历年的NOIP真题肝了一遍(还有3个紫题先咕掉了),主要是到1998年的提高组的题.把题目的做题简要思路搁在这儿,一个是为了考前翻一翻,想想自己的哪些思路要梳理的什么什么的,反正怎么说呢, ...
- SP1716 GSS3
题意翻译 \(n\) 个数,\(q\) 次操作 操作\(0\) \(x\) \(y\)把\(A_x\) 修改为\(y\) 操作\(1\) \(l\) \(r\)询问区间\([l, r]\)的最大子段和 ...
- Error:依赖版本不一致
在编译unity时发现一个问题:依赖版本不一致 解决方案: 通过nugut管理在已安装项里选中要更新的dll文件
- 运算符优先级 (JavaScript)
运算符优先级描述了在计算表达式时执行运算的顺序.先执行具有较高优先级的运算,然后执行较低优先级的运算.例如,先执行相乘,再执行相加. JavaScript 运算符 下表列出了 JavaScri ...
- Linux--4
一.centos7安装python3 1.下载python3的源码包 下载地址:https://www.python.org/ftp/python/3.6.2/Python-3.6.2.tgz 1 2 ...
- 匿名内部类(new类时覆盖类中方法)
public class Person { private String name ; protected String getName() { return name; } public void ...
- JS——通过标签获取元素、循环语句、数组去重
通过标签获取元素: var aLi = document.getElementsByTagName('Li'); aLi[0].style.backgroundColor = 'gold'; 选中部分 ...
- jquery——动画
1.通过animate方法可以设置元素某属性值上的动画 <!DOCTYPE html> <html lang="en"> <head> < ...
- 029 Divide Two Integers 两数相除
不使用乘号,除号和取模符号将两数相除.如果溢出返回 MAX_INT.详见:https://leetcode.com/problems/divide-two-integers/description/ ...