使用filter（过滤器）按照条件查询hbase

1.1. hbase过滤器

1.1.1. 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

1.1.2. 过滤器的种类

过滤器的种类：

列植过滤器—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。

1.1.3. 列植过滤器—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。

1.1.4. 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);

1.1.5. 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);

1.1.6. 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);

package hbase.test;

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.Test;

import java.text.DecimalFormat;
import java.util.Iterator;
import java.util.List;

/**
 * 测试过滤器
 */
public class TestFilter {
	/**
	 * rowkey过滤
	 */
	@Test
	public void testRowFilter() throws Exception {
		Configuration conf = HBaseConfiguration.create();
		Connection conn = ConnectionFactory.createConnection(conf);
		Table t = conn.getTable(TableName.valueOf("ns1:t2"));
		Scan scan = new Scan();
//		where rowkey <= row088
//		RowFilter filter = new RowFilter(CompareFilter.CompareOp.LESS_OR_EQUAL,new BinaryComparator(Bytes.toBytes("row088")));
		//where rowkey like '%88%'
//		RowFilter filter = new RowFilter(CompareFilter.CompareOp.EQUAL,new RegexStringComparator("88"));

		//while rowkey like '%88' ;
		RowFilter filter = new RowFilter(CompareFilter.CompareOp.EQUAL,new RegexStringComparator("88$"));
		scan.setFilter(filter);

		ResultScanner rs = t.getScanner(scan) ;
		Iterator<Result> it = rs.iterator();
		while(it.hasNext()){
			Result r = it.next();
			outResult(r);
		}
		rs.close();
	}

	/**
	 * family过滤
	 */
	@Test
	public void testFamilyFilter() throws Exception {
		Configuration conf = HBaseConfiguration.create();
		Connection conn = ConnectionFactory.createConnection(conf);
		Table t = conn.getTable(TableName.valueOf("ns1:t2"));
		Scan scan = new Scan();
		//以f开头的列族进行过滤
		FamilyFilter filter = new FamilyFilter(CompareFilter.CompareOp.EQUAL,new RegexStringComparator("^f"));
		scan.setFilter(filter);

		ResultScanner rs = t.getScanner(scan) ;
		Iterator<Result> it = rs.iterator();
		while(it.hasNext()){
			Result r = it.next();
			outResult(r);
		}
		rs.close();
	}

	/**
	 * col过滤
	 */
	@Test
	public void testQualifierFilter() throws Exception {
		Configuration conf = HBaseConfiguration.create();
		Connection conn = ConnectionFactory.createConnection(conf);
		Table t = conn.getTable(TableName.valueOf("ns1:t2"));
		Scan scan = new Scan();
		//以f开头的列族进行过滤
		QualifierFilter filter = new QualifierFilter(QualifierFilter.CompareOp.EQUAL,new RegexStringComparator("^name$"));
		scan.setFilter(filter);

		ResultScanner rs = t.getScanner(scan) ;
		Iterator<Result> it = rs.iterator();
		while(it.hasNext()){
			Result r = it.next();
			outResult(r);
		}
		rs.close();
	}

	/**
	 * 组合过滤
	 */
	@Test
	public void testFilterList() throws Exception {
		Configuration conf = HBaseConfiguration.create();
		Connection conn = ConnectionFactory.createConnection(conf);
		Table t = conn.getTable(TableName.valueOf("ns1:t2"));
		Scan scan = new Scan();
		//MUST_PASS_ALL : and
		//MUST_PASS_ONe :Or

		FilterList filter = new FilterList(FilterList.Operator.MUST_PASS_ALL) ;
		ValueFilter f1 = new ValueFilter(QualifierFilter.CompareOp.EQUAL,new RegexStringComparator("m8"));
		filter.addFilter(f1);
		RowFilter f2 = new RowFilter(CompareFilter.CompareOp.GREATER,new BinaryComparator(Bytes.toBytes("row8"))) ;
		filter.addFilter(f2);
		scan.setFilter(filter);

		ResultScanner rs = t.getScanner(scan) ;
		Iterator<Result> it = rs.iterator();
		while(it.hasNext()){
			Result r = it.next();
			outResult(r);
		}
		rs.close();
	}
	/**
	 * value过滤
	 */
	@Test
	public void testValueFilter() throws Exception {
		Configuration conf = HBaseConfiguration.create();
		Connection conn = ConnectionFactory.createConnection(conf);
		Table t = conn.getTable(TableName.valueOf("ns1:t2"));
		Scan scan = new Scan();
		//以f开头的列族进行过滤
		ValueFilter filter = new ValueFilter(QualifierFilter.CompareOp.EQUAL,new RegexStringComparator("m8"));
		scan.setFilter(filter);

		ResultScanner rs = t.getScanner(scan) ;
		Iterator<Result> it = rs.iterator();
		while(it.hasNext()){
			Result r = it.next();
			outResult(r);
		}
		rs.close();
	}



	private void outResult(Result r) {
		System.out.println("=========================");
		List<Cell> cells = r.listCells();
		for (Cell cell : cells) {
			String rowkey = Bytes.toString(CellUtil.cloneRow(cell));
			String f = Bytes.toString(CellUtil.cloneFamily(cell));
			String col = Bytes.toString(CellUtil.cloneQualifier(cell));
			long ts = cell.getTimestamp();
			String value = Bytes.toString(CellUtil.cloneValue(cell));
			System.out.println(rowkey + "/" + f + ":" + col + "/" + ts + "=" + value);
		}
	}