zoukankan      html  css  js  c++  java
  • hbase 分页过滤(新老API的差别)

    在hbase2.0以前分页过滤必须以上一次的最后一行+空字节数组作为下一次的起始行,

    因为scan扫描的时候是包含起始行的,为了既能准确定位起始行,但又不重复把上一次的最末一行加入下一页,

    所以,权威指南里才有了加上空字节数组的处理。

    hbase2.0以后,新的api是withStartRow(byte[] startRow, boolean inclusive),可以直接设置是否包含起始行,完美解决问题,但是又保留了对以前api函数的兼容性。

        //分页过滤
        private static void pageFilterData() throws IOException{
            Table table = helper.getConnection().getTable(TableName.valueOf("testtable"));
            final byte[] POSTFIX = new byte[] { 0x00 };
            Filter filter = new PageFilter(10);
    
            int totalRows = 0;
            byte[] lastRow = null;
            while(true){
                Scan scan = new Scan();
                scan.setFilter(filter);
                if(lastRow!=null){
    
                      //为了兼容以前的scan.setStartRow()代码
                      //在上一次的最后一行加上一个空的byte数据,在下一个分页上,就会以新的key开始,
                    // 但是实际上这个key并不存在,所以还是从真正的下一行开始扫描
                    //这么做的原因是scan的扫描会自动包含起始行,如果不加空字节数据,那么定位上就会把上一次的最后一行作为起始行,最后的数据就会多一行。
                    //而,新的api是withStartRow(byte[] startRow, boolean inclusive),可以直接设置是否包含起始行,完美解决问题,但是又保留了对
                    //以前api函数的兼容性
    //                byte[] startRow = Bytes.add(lastRow,POSTFIX);
    //                System.out.println("start row: " + Bytes.toStringBinary(startRow));
    //                scan.withStartRow(startRow,true);
    
                    System.out.println("start row: " + Bytes.toStringBinary(lastRow));
                    //不包含起始行,所以可以直接使用上一次的最后一行作为起始行
                    scan.withStartRow(lastRow,false);
                }
                ResultScanner scanner = table.getScanner(scan);
                int localRows = 0;
                Result result;
                while ((result=scanner.next())!=null){
                    System.out.println(localRows++ + ": " + result);
                    totalRows++;
                    lastRow = result.getRow();
                }
                scanner.close();
                if(localRows==0)break;
            }
            System.out.println("total rows: " + totalRows);
        }

    兼容老API输出如下:

    0: keyvalues={rowKey0/ex:addr/1555078771906/Put/vlen=7/seqid=0, rowKey0/info:username/1555078771906/Put/vlen=5/seqid=0, rowKey0/memo:detail/1555078771906/Put/vlen=7/seqid=0}
    1: keyvalues={rowKey1/ex:addr/1555078771906/Put/vlen=7/seqid=0, rowKey1/info:username/1555078771906/Put/vlen=5/seqid=0, rowKey1/memo:detail/1555078771906/Put/vlen=7/seqid=0}
    2: keyvalues={rowKey10/ex:addr/1555078771906/Put/vlen=8/seqid=0, rowKey10/info:username/1555078771906/Put/vlen=6/seqid=0, rowKey10/memo:detail/1555078771906/Put/vlen=8/seqid=0}
    3: keyvalues={rowKey11/ex:addr/1555078771906/Put/vlen=8/seqid=0, rowKey11/info:username/1555078771906/Put/vlen=6/seqid=0, rowKey11/memo:detail/1555078771906/Put/vlen=8/seqid=0}
    4: keyvalues={rowKey12/ex:addr/1555078771906/Put/vlen=8/seqid=0, rowKey12/info:username/1555078771906/Put/vlen=6/seqid=0, rowKey12/memo:detail/1555078771906/Put/vlen=8/seqid=0}
    5: keyvalues={rowKey13/ex:addr/1555078771906/Put/vlen=8/seqid=0, rowKey13/info:username/1555078771906/Put/vlen=6/seqid=0, rowKey13/memo:detail/1555078771906/Put/vlen=8/seqid=0}
    6: keyvalues={rowKey14/ex:addr/1555078771906/Put/vlen=8/seqid=0, rowKey14/info:username/1555078771906/Put/vlen=6/seqid=0, rowKey14/memo:detail/1555078771906/Put/vlen=8/seqid=0}
    7: keyvalues={rowKey15/ex:addr/1555078771906/Put/vlen=8/seqid=0, rowKey15/info:username/1555078771906/Put/vlen=6/seqid=0, rowKey15/memo:detail/1555078771906/Put/vlen=8/seqid=0}
    8: keyvalues={rowKey16/ex:addr/1555078771906/Put/vlen=8/seqid=0, rowKey16/info:username/1555078771906/Put/vlen=6/seqid=0, rowKey16/memo:detail/1555078771906/Put/vlen=8/seqid=0}
    9: keyvalues={rowKey17/ex:addr/1555078771906/Put/vlen=8/seqid=0, rowKey17/info:username/1555078771906/Put/vlen=6/seqid=0, rowKey17/memo:detail/1555078771906/Put/vlen=8/seqid=0}
    start row: rowKey17x00
    0: keyvalues={rowKey18/ex:addr/1555078771906/Put/vlen=8/seqid=0, rowKey18/info:username/1555078771906/Put/vlen=6/seqid=0, rowKey18/memo:detail/1555078771906/Put/vlen=8/seqid=0}
    1: keyvalues={rowKey19/ex:addr/1555078771906/Put/vlen=8/seqid=0, rowKey19/info:username/1555078771906/Put/vlen=6/seqid=0, rowKey19/memo:detail/1555078771906/Put/vlen=8/seqid=0}
    2: keyvalues={rowKey2/ex:addr/1555078771906/Put/vlen=7/seqid=0, rowKey2/info:username/1555078771906/Put/vlen=5/seqid=0, rowKey2/memo:detail/1555078771906/Put/vlen=7/seqid=0}
    3: keyvalues={rowKey20/ex:addr/1555078771906/Put/vlen=8/seqid=0, rowKey20/info:username/1555078771906/Put/vlen=6/seqid=0, rowKey20/memo:detail/1555078771906/Put/vlen=8/seqid=0}
    4: keyvalues={rowKey21/ex:addr/1555078771906/Put/vlen=8/seqid=0, rowKey21/info:username/1555078771906/Put/vlen=6/seqid=0, rowKey21/memo:detail/1555078771906/Put/vlen=8/seqid=0}
    5: keyvalues={rowKey22/ex:addr/1555078771906/Put/vlen=8/seqid=0, rowKey22/info:username/1555078771906/Put/vlen=6/seqid=0, rowKey22/memo:detail/1555078771906/Put/vlen=8/seqid=0}
    6: keyvalues={rowKey23/ex:addr/1555078771906/Put/vlen=8/seqid=0, rowKey23/info:username/1555078771906/Put/vlen=6/seqid=0, rowKey23/memo:detail/1555078771906/Put/vlen=8/seqid=0}
    7: keyvalues={rowKey24/ex:addr/1555078771906/Put/vlen=8/seqid=0, rowKey24/info:username/1555078771906/Put/vlen=6/seqid=0, rowKey24/memo:detail/1555078771906/Put/vlen=8/seqid=0}
    8: keyvalues={rowKey25/ex:addr/1555078771906/Put/vlen=8/seqid=0, rowKey25/info:username/1555078771906/Put/vlen=6/seqid=0, rowKey25/memo:detail/1555078771906/Put/vlen=8/seqid=0}
    9: keyvalues={rowKey26/ex:addr/1555078771906/Put/vlen=8/seqid=0, rowKey26/info:username/1555078771906/Put/vlen=6/seqid=0, rowKey26/memo:detail/1555078771906/Put/vlen=8/seqid=0}
    start row: rowKey26x00
    0: keyvalues={rowKey27/ex:addr/1555078771906/Put/vlen=8/seqid=0, rowKey27/info:username/1555078771906/Put/vlen=6/seqid=0, rowKey27/memo:detail/1555078771906/Put/vlen=8/seqid=0}
    1: keyvalues={rowKey28/ex:addr/1555078771906/Put/vlen=8/seqid=0, rowKey28/info:username/1555078771906/Put/vlen=6/seqid=0, rowKey28/memo:detail/1555078771906/Put/vlen=8/seqid=0}
    2: keyvalues={rowKey29/ex:addr/1555078771906/Put/vlen=8/seqid=0, rowKey29/info:username/1555078771906/Put/vlen=6/seqid=0, rowKey29/memo:detail/1555078771906/Put/vlen=8/seqid=0}
    3: keyvalues={rowKey3/ex:addr/1555078771906/Put/vlen=7/seqid=0, rowKey3/info:username/1555078771906/Put/vlen=5/seqid=0, rowKey3/memo:detail/1555078771906/Put/vlen=7/seqid=0}
    4: keyvalues={rowKey30/ex:addr/1555078771906/Put/vlen=8/seqid=0, rowKey30/info:username/1555078771906/Put/vlen=6/seqid=0, rowKey30/memo:detail/1555078771906/Put/vlen=8/seqid=0}
    5: keyvalues={rowKey31/ex:addr/1555078771906/Put/vlen=8/seqid=0, rowKey31/info:username/1555078771906/Put/vlen=6/seqid=0, rowKey31/memo:detail/1555078771906/Put/vlen=8/seqid=0}
    6: keyvalues={rowKey32/ex:addr/1555078771906/Put/vlen=8/seqid=0, rowKey32/info:username/1555078771906/Put/vlen=6/seqid=0, rowKey32/memo:detail/1555078771906/Put/vlen=8/seqid=0}
    7: keyvalues={rowKey33/ex:addr/1555078771906/Put/vlen=8/seqid=0, rowKey33/info:username/1555078771906/Put/vlen=6/seqid=0, rowKey33/memo:detail/1555078771906/Put/vlen=8/seqid=0}
    8: keyvalues={rowKey34/ex:addr/1555078771906/Put/vlen=8/seqid=0, rowKey34/info:username/1555078771906/Put/vlen=6/seqid=0, rowKey34/memo:detail/1555078771906/Put/vlen=8/seqid=0}
    9: keyvalues={rowKey35/ex:addr/1555078771906/Put/vlen=8/seqid=0, rowKey35/info:username/1555078771906/Put/vlen=6/seqid=0, rowKey35/memo:detail/1555078771906/Put/vlen=8/seqid=0}
    start row: rowKey35x00
    ... ...省略其他数据

    起始行加了空字节数据,形成了新的定位行(相当于真正的两页之间插入了一个虚拟行用于定位),解决了下一页首行的问题。

    新的api输出:下一页的定位行就是上一页的末行,采用新的API设置首行的时候把inclusive设置成false(即不包含首行),那么输出结果就是正确的。

    0: keyvalues={rowKey0/ex:addr/1555078771906/Put/vlen=7/seqid=0, rowKey0/info:username/1555078771906/Put/vlen=5/seqid=0, rowKey0/memo:detail/1555078771906/Put/vlen=7/seqid=0}
    1: keyvalues={rowKey1/ex:addr/1555078771906/Put/vlen=7/seqid=0, rowKey1/info:username/1555078771906/Put/vlen=5/seqid=0, rowKey1/memo:detail/1555078771906/Put/vlen=7/seqid=0}
    2: keyvalues={rowKey10/ex:addr/1555078771906/Put/vlen=8/seqid=0, rowKey10/info:username/1555078771906/Put/vlen=6/seqid=0, rowKey10/memo:detail/1555078771906/Put/vlen=8/seqid=0}
    3: keyvalues={rowKey11/ex:addr/1555078771906/Put/vlen=8/seqid=0, rowKey11/info:username/1555078771906/Put/vlen=6/seqid=0, rowKey11/memo:detail/1555078771906/Put/vlen=8/seqid=0}
    4: keyvalues={rowKey12/ex:addr/1555078771906/Put/vlen=8/seqid=0, rowKey12/info:username/1555078771906/Put/vlen=6/seqid=0, rowKey12/memo:detail/1555078771906/Put/vlen=8/seqid=0}
    5: keyvalues={rowKey13/ex:addr/1555078771906/Put/vlen=8/seqid=0, rowKey13/info:username/1555078771906/Put/vlen=6/seqid=0, rowKey13/memo:detail/1555078771906/Put/vlen=8/seqid=0}
    6: keyvalues={rowKey14/ex:addr/1555078771906/Put/vlen=8/seqid=0, rowKey14/info:username/1555078771906/Put/vlen=6/seqid=0, rowKey14/memo:detail/1555078771906/Put/vlen=8/seqid=0}
    7: keyvalues={rowKey15/ex:addr/1555078771906/Put/vlen=8/seqid=0, rowKey15/info:username/1555078771906/Put/vlen=6/seqid=0, rowKey15/memo:detail/1555078771906/Put/vlen=8/seqid=0}
    8: keyvalues={rowKey16/ex:addr/1555078771906/Put/vlen=8/seqid=0, rowKey16/info:username/1555078771906/Put/vlen=6/seqid=0, rowKey16/memo:detail/1555078771906/Put/vlen=8/seqid=0}
    9: keyvalues={rowKey17/ex:addr/1555078771906/Put/vlen=8/seqid=0, rowKey17/info:username/1555078771906/Put/vlen=6/seqid=0, rowKey17/memo:detail/1555078771906/Put/vlen=8/seqid=0}
    start row: rowKey17
    0: keyvalues={rowKey18/ex:addr/1555078771906/Put/vlen=8/seqid=0, rowKey18/info:username/1555078771906/Put/vlen=6/seqid=0, rowKey18/memo:detail/1555078771906/Put/vlen=8/seqid=0}
    1: keyvalues={rowKey19/ex:addr/1555078771906/Put/vlen=8/seqid=0, rowKey19/info:username/1555078771906/Put/vlen=6/seqid=0, rowKey19/memo:detail/1555078771906/Put/vlen=8/seqid=0}
    2: keyvalues={rowKey2/ex:addr/1555078771906/Put/vlen=7/seqid=0, rowKey2/info:username/1555078771906/Put/vlen=5/seqid=0, rowKey2/memo:detail/1555078771906/Put/vlen=7/seqid=0}
    3: keyvalues={rowKey20/ex:addr/1555078771906/Put/vlen=8/seqid=0, rowKey20/info:username/1555078771906/Put/vlen=6/seqid=0, rowKey20/memo:detail/1555078771906/Put/vlen=8/seqid=0}
    4: keyvalues={rowKey21/ex:addr/1555078771906/Put/vlen=8/seqid=0, rowKey21/info:username/1555078771906/Put/vlen=6/seqid=0, rowKey21/memo:detail/1555078771906/Put/vlen=8/seqid=0}
    5: keyvalues={rowKey22/ex:addr/1555078771906/Put/vlen=8/seqid=0, rowKey22/info:username/1555078771906/Put/vlen=6/seqid=0, rowKey22/memo:detail/1555078771906/Put/vlen=8/seqid=0}
    6: keyvalues={rowKey23/ex:addr/1555078771906/Put/vlen=8/seqid=0, rowKey23/info:username/1555078771906/Put/vlen=6/seqid=0, rowKey23/memo:detail/1555078771906/Put/vlen=8/seqid=0}
    7: keyvalues={rowKey24/ex:addr/1555078771906/Put/vlen=8/seqid=0, rowKey24/info:username/1555078771906/Put/vlen=6/seqid=0, rowKey24/memo:detail/1555078771906/Put/vlen=8/seqid=0}
    8: keyvalues={rowKey25/ex:addr/1555078771906/Put/vlen=8/seqid=0, rowKey25/info:username/1555078771906/Put/vlen=6/seqid=0, rowKey25/memo:detail/1555078771906/Put/vlen=8/seqid=0}
    9: keyvalues={rowKey26/ex:addr/1555078771906/Put/vlen=8/seqid=0, rowKey26/info:username/1555078771906/Put/vlen=6/seqid=0, rowKey26/memo:detail/1555078771906/Put/vlen=8/seqid=0}
    start row: rowKey26
    0: keyvalues={rowKey27/ex:addr/1555078771906/Put/vlen=8/seqid=0, rowKey27/info:username/1555078771906/Put/vlen=6/seqid=0, rowKey27/memo:detail/1555078771906/Put/vlen=8/seqid=0}
    1: keyvalues={rowKey28/ex:addr/1555078771906/Put/vlen=8/seqid=0, rowKey28/info:username/1555078771906/Put/vlen=6/seqid=0, rowKey28/memo:detail/1555078771906/Put/vlen=8/seqid=0}
    2: keyvalues={rowKey29/ex:addr/1555078771906/Put/vlen=8/seqid=0, rowKey29/info:username/1555078771906/Put/vlen=6/seqid=0, rowKey29/memo:detail/1555078771906/Put/vlen=8/seqid=0}
    3: keyvalues={rowKey3/ex:addr/1555078771906/Put/vlen=7/seqid=0, rowKey3/info:username/1555078771906/Put/vlen=5/seqid=0, rowKey3/memo:detail/1555078771906/Put/vlen=7/seqid=0}
    4: keyvalues={rowKey30/ex:addr/1555078771906/Put/vlen=8/seqid=0, rowKey30/info:username/1555078771906/Put/vlen=6/seqid=0, rowKey30/memo:detail/1555078771906/Put/vlen=8/seqid=0}
    5: keyvalues={rowKey31/ex:addr/1555078771906/Put/vlen=8/seqid=0, rowKey31/info:username/1555078771906/Put/vlen=6/seqid=0, rowKey31/memo:detail/1555078771906/Put/vlen=8/seqid=0}
    6: keyvalues={rowKey32/ex:addr/1555078771906/Put/vlen=8/seqid=0, rowKey32/info:username/1555078771906/Put/vlen=6/seqid=0, rowKey32/memo:detail/1555078771906/Put/vlen=8/seqid=0}
    7: keyvalues={rowKey33/ex:addr/1555078771906/Put/vlen=8/seqid=0, rowKey33/info:username/1555078771906/Put/vlen=6/seqid=0, rowKey33/memo:detail/1555078771906/Put/vlen=8/seqid=0}
    8: keyvalues={rowKey34/ex:addr/1555078771906/Put/vlen=8/seqid=0, rowKey34/info:username/1555078771906/Put/vlen=6/seqid=0, rowKey34/memo:detail/1555078771906/Put/vlen=8/seqid=0}
    9: keyvalues={rowKey35/ex:addr/1555078771906/Put/vlen=8/seqid=0, rowKey35/info:username/1555078771906/Put/vlen=6/seqid=0, rowKey35/memo:detail/1555078771906/Put/vlen=8/seqid=0}
    start row: rowKey35
    ... ...其他省略
  • 相关阅读:
    2020,最新Model的设计-APP重构之路
    2020,最新APP重构:网络请求框架
    APP重构之路:引入单元测试
    接口测试中postman环境和用例集
    测试行业是该选择手动测试还是自动化测试?
    2020,必备自动生成测试脚本方案
    2020,必备自动化测试 之 “好用例、坏用例”
    2020,你需掌握go 单元测试进阶篇
    前端测试框架Jest——语法篇
    2020,测试生涯该如何转型升级?
  • 原文地址:https://www.cnblogs.com/asker009/p/10699220.html
Copyright © 2011-2022 走看看