= hadoop programming 完全公式 =

 ||       ||   || 輸入 key ||   || 輸入 value|| || 輸出 Key                     ||   || 輸出 Value||   ||  
 || Mapper|| < || A       || , || B      || , ||  C                           || , || D || >  ||
 || map   || ( || A       || , || B      || , ||  !OutputCollector < C , D >  || , ||Reporter reporter  ||  ) || 
 || output|| . || collect || ( || c      || , ||  d                           || ) ||   || || 
 ||Reducer|| < || C       || , || D      || , ||  E                           || , ||F  || >  || 
 || reduce|| ( || C       || , || Iterator<D>|| , ||  !OutputCollector < E , F >  || , ||Reporter reporter  ||  ) || 
 || output|| . || collect || ( || e      || , ||  f                           || ) ||   || 

 * A, B, C, D ,E, F 分別代表可以用的類別；c, d, e, f 代表由C,D,E,F所產生的物件
 * 有了這張表，我們規劃要寫M/R程式的時候:
   * 先把Map的輸入<key,value> 應該屬於哪種類別的，則A,B定好
   * Map的輸出<key,value>定好，則 C,D也ok了
   * 接下來想最終輸出的<key,value>該為何類別，則 E,F 決定好
   * 分別填入 ABCDEF之後，整個程式的架構就出來了，接下來就看你的程式如何實做

 * 舉例<WordCount> :
   * 由於輸入為hdfs的路徑，因此傳到mapper裡時，key= 檔案內每一行的位址、value代表檔案內的每一行字串，因此A可以任意類別，B則為Text
   * 而wordcount最終要算出的是每個字的出現次數，因此輸出的<key,value>應該是文字，數字，故 E=Text, F=!IntWritable
   * 如何才能原本一開始每一行字，進而分析成<文字，數字>，故邏輯為先把每一行的單字都取出，然後設定map的輸出為<單字,1>，以便放到Reduce去相加，所以C=Text, D=!IntWritable
   * 把ABCDEF填入之後，剩下只是程式邏輯而已！


{{{
#!java
public static class Map extends MapReduceBase implements Mapper<LongWritable, Text, Text, IntWritable> {
private final static IntWritable one = new IntWritable(1);
private Text word = new Text();

public void map(LongWritable key, Text value, OutputCollector<Text, IntWritable> output, Reporter reporter) throws IOException {
  String line = value.toString();
  StringTokenizer tokenizer = new StringTokenizer(line);
  while (tokenizer.hasMoreTokens()) {
    word.set(tokenizer.nextToken());
    output.collect(word, one);
  }
}

public static class Reduce extends MapReduceBase implements Reducer<Text, IntWritable, Text, IntWritable> {
  public void reduce(Text key, Iterator<IntWritable> values, OutputCollector<Text, IntWritable> output, Reporter reporter) throws IOException {
    int sum = 0;
    while (values.hasNext()) {
      sum += values.next().get();
    }
    output.collect(key, new IntWritable(sum));
  }
}
}}}