如何从映射器中访问 Cassandra 列族？具体来说，如何将 map() 方法的参数转换回我期望的 java 类型？

Key {logType} -> {列名:timeUUID，列值:csv log line，ttl:1year}

感谢@Chris & @rs_atl

package com.xxx.hadoop;

import java.io.IOException;
import java.nio.ByteBuffer;
import java.util.Iterator;
import java.util.SortedMap;


import org.apache.cassandra.db.IColumn;
import org.apache.cassandra.hadoop.ColumnFamilyInputFormat;
import org.apache.cassandra.hadoop.ConfigHelper;
import org.apache.cassandra.thrift.SlicePredicate;
import org.apache.cassandra.thrift.SliceRange;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;
import org.apache.thrift.TBaseHelper;

import com.xxx.parser.LogParser;
import com.netflix.astyanax.serializers.StringSerializer;

public class LogTypeCounterByDate extends Configured implements Tool {
    private static final String KEYSPACE = "LogKS";
    private static final String COLUMN_FAMILY = "LogBlock";
    private static final String JOB_NAME = "LOG_LINE_COUNT";
    private static final String INPUT_PARTITIONER = "org.apache.cassandra.dht.RandomPartitioner";
    private static final String INPUT_RPC_PORT = "9160";
    private static final String INPUT_INITIAL_ADDRESS = "192.168.1.21";
    private static final String OUTPUT_PATH = "/logOutput/results";

    @Override
    public int run(String[] args) throws Exception {

        //Configuration conf = new Configuration();

        Job job = new Job(getConf(), JOB_NAME);
        job.setJarByClass(LogTypeCounterByDate.class);
        job.setMapperClass(LogTypeCounterByDateMapper.class);       
        job.setReducerClass(LogTypeCounterByDateReducer.class);

        job.setInputFormatClass(ColumnFamilyInputFormat.class);

        job.setMapOutputKeyClass(Text.class);
        job.setMapOutputValueClass(LongWritable.class);
        job.setNumReduceTasks(1);
        ConfigHelper.setRangeBatchSize(getConf(), 1000);

        /*SlicePredicate predicate = new SlicePredicate().setSlice_range(new SliceRange(ByteBuffer.wrap(new byte[0]), 
                ByteBuffer.wrap(new byte[0]), true, 1));*/
        SliceRange sliceRange = new SliceRange(ByteBuffer.wrap(new byte[0]), 
                ByteBuffer.wrap(new byte[0]), true, 1000);

        SlicePredicate slicePredicate = new SlicePredicate();
        slicePredicate.setSlice_range(sliceRange);


        ConfigHelper.setInputColumnFamily(job.getConfiguration(), KEYSPACE, COLUMN_FAMILY);
        ConfigHelper.setInputRpcPort(job.getConfiguration(), INPUT_RPC_PORT);
        ConfigHelper.setInputInitialAddress(job.getConfiguration(), INPUT_INITIAL_ADDRESS);
        ConfigHelper.setInputPartitioner(job.getConfiguration(), INPUT_PARTITIONER);
        ConfigHelper.setInputSlicePredicate(job.getConfiguration(), slicePredicate);

        FileOutputFormat.setOutputPath(job, new Path(OUTPUT_PATH));

        job.waitForCompletion(true);
        return job.isSuccessful() ? 0 : 1;
    }

    public static void main(String[] args) throws Exception{
        ToolRunner.run(new Configuration(), new LogTypeCounterByDate(), args);
        System.exit(0);
    }


    public static class LogTypeCounterByDateMapper extends Mapper<ByteBuffer, SortedMap<ByteBuffer, IColumn>, Text, LongWritable>
    {

        @SuppressWarnings("rawtypes")
        @Override
        protected void setup(Mapper.Context context){

        }

        @SuppressWarnings({ })
        public void map(ByteBuffer key, SortedMap<ByteBuffer, IColumn> columns, Context context) throws IOException, InterruptedException{
            //String[] lines = columns.;
            String rowkey = StringSerializer.get().fromByteBuffer(TBaseHelper.rightSize(key));  
            Iterator<ByteBuffer> iter = columns.keySet().iterator();
            IColumn column;
            String line;
            LogParser lp = null;

            while(iter.hasNext()){
                column = columns.get(iter.next());
                line = StringSerializer.get().fromByteBuffer(TBaseHelper.rightSize(column.value()));
                lp = new LogParser(line);               
                context.write(new Text(rowkey + "\t" + "LineCount"), new LongWritable(1L));
                context.write(new Text(rowkey + "\t" + "Minutes"), new LongWritable(lp.getTotalDuration()));
            }
        }
    }

    public static class LogTypeCounterByDateReducer extends Reducer<Text, LongWritable, Text, LongWritable>
    {           

        public void reduce(Text key, Iterable<LongWritable> values, Context context) throws IOException, InterruptedException{
            long total = 0;
            for(LongWritable val : values){
                total += val.get();
            }
            context.write(key, new LongWritable(total));
        }
    }               
}

ConfigHelper.setRangeBatchSize(getConf(), 1000);

        /*SlicePredicate predicate = new   SlicePredicate().setSlice_range(new SliceRange(ByteBuffer.wrap(new byte[0]), 
                ByteBuffer.wrap(new byte[0]), true, 1));*/
        SliceRange sliceRange = new SliceRange(ByteBuffer.wrap(new byte[0]), 
                ByteBuffer.wrap(new byte[0]), true, 1000);

        SlicePredicate slicePredicate = new SlicePredicate();
        slicePredicate.setSlice_range(sliceRange);

上面的代码只为每一行提供 1000 列映射器，因为我想每次以 1000 列的批处理为每一行提供所有列。

请有人帮助我。

最佳答案

给定参数:

ByteBuffer key;
SortedMap<ByteBuffer, IColumn> columns;

你会使用:

String rowkey = StringSerializer.get().fromByteBuffer(TBaseHelper.rightSize(key))

获取反序列化的键值。请注意，这里假设行键是一个字符串。如果是其他类型，则必须使用适当的序列化程序类。

要获取列值，请执行以下操作:

Iterator<ByteBuffer> = columns.keySet().iterator(); 
while (iter.hasNext()) {
    IColumn col = columns.get(iter.next()); 
    xxx colVal = xxxSerializer.get().fromByteBuffer(TBaseHelper.rightSize(col.value()));
}

其中xxx是列值的Java类型，xxxSerializer是对应的序列化器。

顺便说一句，TBaseHelper 类用于将内部字节数组中的值的偏移量更正为零，强制执行序列化程序实现所做的假设。

那么还有一件事......如果您要检索时间序列，那么每一列都是它自己的时间序列值，您需要包含适当的映射器逻辑(比如某种数学运算和写入上下文)在列上的迭代循环内。相反，如果您有一个更静态的列族(更像传统的 sql 表)，那么您可能会对整行的上下文进行一次写入。

关于java - 用于时间序列数据的 Cassandra Map Reduce，我们在Stack Overflow上找到一个类似的问题： https://stackoverflow.com/questions/13417785/