Hadoop入门之自定义groupingcomparator和outputformat的使用

自定义outputformat输出demo类:

/** * maptask或者reducetask在最终输出时，先调用OutputFormat的getRecordWriter方法拿到一个RecordWriter * 然后再调用RecordWriter的write(k,v)方法将数据写出 *  * @author *  */public class LogEnhanceOutputFormat extends FileOutputFormat<Text, NullWritable> {    @Override    public RecordWriter<Text, NullWritable> getRecordWriter(TaskAttemptContext context) throws IOException, InterruptedException {        FileSystem fs = FileSystem.get(context.getConfiguration());        Path enhancePath = new Path("D:/temp/en/log.dat");        Path tocrawlPath = new Path("D:/temp/crw/url.dat");        FSDataOutputStream enhancedOs = fs.create(enhancePath);        FSDataOutputStream tocrawlOs = fs.create(tocrawlPath);        return new EnhanceRecordWriter(enhancedOs, tocrawlOs);    }    /**     * 构造一个自己的recordwriter     *      * @author     *      */    static class EnhanceRecordWriter extends RecordWriter<Text, NullWritable> {        FSDataOutputStream enhancedOs = null;        FSDataOutputStream tocrawlOs = null;        public EnhanceRecordWriter(FSDataOutputStream enhancedOs, FSDataOutputStream tocrawlOs) {            super();            this.enhancedOs = enhancedOs;            this.tocrawlOs = tocrawlOs;        }        @Override        public void write(Text key, NullWritable value) throws IOException, InterruptedException {            String result = key.toString();            // 如果要写出的数据是待爬的url，则写入待爬清单文件 /logenhance/tocrawl/url.dat            if (result.contains("tocrawl")) {                tocrawlOs.write(result.getBytes());            } else {                // 如果要写出的数据是增强日志，则写入增强日志文件 /logenhance/enhancedlog/log.dat                enhancedOs.write(result.getBytes());            }        }        @Override        public void close(TaskAttemptContext context) throws IOException, InterruptedException {            if (tocrawlOs != null) {                tocrawlOs.close();            }            if (enhancedOs != null) {                enhancedOs.close();            }        }    }}

使用这个类需要在Job设置中设置如下:

 job.setOutputFormatClass(LogEnhanceOutputFormat.class);

自定义groupingcomparator的使用Demo:

有如下订单数据

订单id

商品id

成交金额

Order_0000001

Pdt_01

222.8

Order_0000001

Pdt_05

25.8

Order_0000002

Pdt_03

522.8

Order_0000002

Pdt_04

122.4

Order_0000002

Pdt_05

722.4

Order_0000003

Pdt_01

222.8

 

现在需要求出每一个订单中成交金额最大的一笔交易

1、利用“订单id和成交金额”作为key，可以将map阶段读取到的所有订单数据按照id分区，按照金额排序，发送到reduce

2、在reduce端利用groupingcomparator将订单id相同的kv聚合成组，然后取第一个即是最大值

自定义groupingcomparator

/** * 用于控制shuffle过程中reduce端对kv对的聚合逻辑 * @author [e-mail] * */public class ItemidGroupingComparator extends WritableComparator {protected ItemidGroupingComparator() {super(OrderBean.class, true);}   @Overridepublic int compare(WritableComparable a, WritableComparable b) {OrderBean abean = (OrderBean) a;OrderBean bbean = (OrderBean) b;//将item_id相同的bean都视为相同，从而聚合为一组return abean.getItemid().compareTo(bbean.getItemid());}}

/** * 订单信息bean，实现hadoop的序列化机制 * @author [e-mail] * */public class OrderBean implements WritableComparable<OrderBean>{private Text itemid;private DoubleWritable amount;public OrderBean() {}public OrderBean(Text itemid, DoubleWritable amount) {set(itemid, amount);}public void set(Text itemid, DoubleWritable amount) {this.itemid = itemid;this.amount = amount;}public Text getItemid() {return itemid;}public DoubleWritable getAmount() {return amount;}@Overridepublic int compareTo(OrderBean o) {int cmp = this.itemid.compareTo(o.getItemid());if (cmp == 0) {cmp = -this.amount.compareTo(o.getAmount());}return cmp;}@Overridepublic void write(DataOutput out) throws IOException {out.writeUTF(itemid.toString());out.writeDouble(amount.get());}@Overridepublic void readFields(DataInput in) throws IOException {String readUTF = in.readUTF();double readDouble = in.readDouble();this.itemid = new Text(readUTF);this.amount= new DoubleWritable(readDouble);}@Overridepublic String toString() {return itemid.toString() + "\t" + amount.get();}}

/** * 利用secondarysort机制输出每种item订单金额最大的记录 * @author [e-mail] * */public class SecondarySort {static class SecondarySortMapper extends Mapper<LongWritable, Text, OrderBean, NullWritable>{OrderBean bean = new OrderBean();@Overrideprotected void map(LongWritable key, Text value, Context context) throws IOException, InterruptedException {String line = value.toString();String[] fields = StringUtils.split(line, "\t");bean.set(new Text(fields[0]), new DoubleWritable(Double.parseDouble(fields[1])));context.write(bean, NullWritable.get());}}static class SecondarySortReducer extends Reducer<OrderBean, NullWritable, OrderBean, NullWritable>{//在设置了groupingcomparator以后，这里收到的kv数据 就是：  <1001 87.6>,null  <1001 76.5>,null  .... //此时，reduce方法中的参数key就是上述kv组中的第一个kv的key：<1001 87.6>//要输出同一个item的所有订单中最大金额的那一个，就只要输出这个key@Overrideprotected void reduce(OrderBean key, Iterable<NullWritable> values, Context context) throws IOException, InterruptedException {context.write(key, NullWritable.get());}}public static void main(String[] args) throws Exception {Configuration conf = new Configuration();Job job = Job.getInstance(conf);job.setJarByClass(SecondarySort.class);job.setMapperClass(SecondarySortMapper.class);job.setReducerClass(SecondarySortReducer.class);        job.setOutputKeyClass(OrderBean.class);job.setOutputValueClass(NullWritable.class);FileInputFormat.setInputPaths(job, new Path(args[0]));FileOutputFormat.setOutputPath(job, new Path(args[1]));//指定shuffle所使用的GroupingComparator类job.setGroupingComparatorClass(ItemidGroupingComparator.class);//指定shuffle所使用的partitioner类job.setPartitionerClass(ItemIdPartitioner.class);job.setNumReduceTasks(3);job.waitForCompletion(true);}}