hbase 自定义过滤器

1、首先生成自定义过滤器，生成jar包，然后拷贝到服务器hbase目录的lib下。

1.1 自定义过滤器CustomFilter

import com.google.protobuf.InvalidProtocolBufferException;
import org.apache.hadoop.hbase.Cell;
import org.apache.hadoop.hbase.CellUtil;
import org.apache.hadoop.hbase.exceptions.DeserializationException;
import org.apache.hadoop.hbase.filter.Filter;
import org.apache.hadoop.hbase.filter.FilterBase;
import org.apache.hadoop.hbase.util.ByteStringer;

import java.io.IOException;

/**
 * @Author: xu.dm
 * @Date: 2019/4/14 12:16
 * @Description: 自定义过滤器，选择列值匹配的行数据
 */
public class CustomFilter extends FilterBase {
    private byte[] value = null;
    private boolean filterRow = true;

    public CustomFilter() {
        super();
    }

    public CustomFilter(byte[] value) {
        this.value = value;
    }

    @Override
    public void reset() throws IOException {
        this.filterRow = true;
    }

    @Override
    public boolean filterRow() throws IOException {
        return this.filterRow;
    }

    //匹配的数据不过滤
    @Override
    public ReturnCode filterCell(Cell c) throws IOException {
        if(CellUtil.matchingValue(c,value))
            filterRow = false;
        return ReturnCode.INCLUDE;
    }

    /**
     * protobuf生成MyFilterProtos
     */
    @Override
    public byte[] toByteArray() throws IOException {
        MyFilterProtos.CustomFilter.Builder builder = MyFilterProtos.CustomFilter.newBuilder();
        if(value!=null)
            builder.setValue(ByteStringer.wrap(value));

        return builder.build().toByteArray();
    }

    public static Filter parseFrom(final byte[] pbBytes)
            throws DeserializationException {
        MyFilterProtos.CustomFilter proto;
        try {
            proto = MyFilterProtos.CustomFilter.parseFrom(pbBytes);
        } catch (InvalidProtocolBufferException e) {
            throw new DeserializationException(e);
        }
        return new CustomFilter(proto.getValue().toByteArray());
    }
}

1.2 MyFilterProtos是通过protobuf生成的，这里需要注意hbase使用的是protobuf2.5.0版本，不要使用高于2.5.0版本的protobuf，不然hbase会报找不到类的错误。

proto文件

syntax = "proto2";

option java_package = "";
option java_outer_classname = "MyFilterProtos";
option java_generic_services = true;
option java_generate_equals_and_hash = true;
option optimize_for = SPEED;

message CustomFilter {
  required bytes value = 1;
}

1.3 编辑成jar包，发布到hbase的lib目录，hbase需要重启

[root@bigdata-senior01 lib]# ls $HBASE_HOME/lib/Custom*.*
/opt/hbase-2.0.4/lib/CustomFilter.jar

2、使用自定义过滤

2.1 程序中引入刚才发布的jar包

2.2 使用自定义过滤器过滤数据

   //使用自定义过滤器，只显示匹配列值的行
    private static void customFilterData() throws IOException{
        Table table = helper.getConnection().getTable(TableName.valueOf("testtable"));

        List<Filter> filters = new ArrayList<Filter>();

        Filter filter1 = new CustomFilter(Bytes.toBytes("user30"));
        filters.add(filter1);

        Filter filter2 = new CustomFilter(Bytes.toBytes("user20"));
        filters.add(filter2);

        Filter filter3 = new CustomFilter(Bytes.toBytes("user90"));
        filters.add(filter3);

        FilterList filterList = new FilterList(
                FilterList.Operator.MUST_PASS_ONE, filters);

        Scan scan = new Scan();
        scan.setFilter(filterList);
        ResultScanner scanner = table.getScanner(scan);
        for(Result result:scanner){
            helper.dumpResult(result);
        }

        scanner.close();
        table.close();
    }
}

输出结果：

Cell: rowKey20/ex:addr/1555078771906/Put/vlen=8/seqid=0, Value: street20
Cell: rowKey20/info:username/1555078771906/Put/vlen=6/seqid=0, Value: user20
Cell: rowKey20/memo:detail/1555078771906/Put/vlen=8/seqid=0, Value: remark20
Cell: rowKey30/ex:addr/1555078771906/Put/vlen=8/seqid=0, Value: street30
Cell: rowKey30/info:username/1555078771906/Put/vlen=6/seqid=0, Value: user30
Cell: rowKey30/memo:detail/1555078771906/Put/vlen=8/seqid=0, Value: remark30
Cell: rowKey90/ex:addr/1555078771906/Put/vlen=8/seqid=0, Value: street90
Cell: rowKey90/info:username/1555078771906/Put/vlen=6/seqid=0, Value: user90
Cell: rowKey90/memo:detail/1555078771906/Put/vlen=8/seqid=0, Value: remark90