{"id":69,"date":"2024-10-09T09:26:44","date_gmt":"2024-10-09T01:26:44","guid":{"rendered":"http:\/\/www.xtmouse.top\/?p=69"},"modified":"2024-11-12T21:03:37","modified_gmt":"2024-11-12T13:03:37","slug":"%e5%a4%a7%e6%95%b0%e6%8d%aehadoop%e5%ae%9e%e8%b7%b5","status":"publish","type":"post","link":"http:\/\/www.xtmouse.top\/index.php\/2024\/10\/09\/%e5%a4%a7%e6%95%b0%e6%8d%aehadoop%e5%ae%9e%e8%b7%b5\/","title":{"rendered":"\u5927\u6570\u636eHadoop\u5b9e\u8df5"},"content":{"rendered":"\n

\u8bcd\u9891\u7edf\u8ba1\u4ee3\u7801<\/h2>\n\n\n\n
\/\/ \u7528\u4e8e\u7edf\u8ba1\u6587\u672c\u6587\u4ef6\u4e2d\u6bcf\u4e2a\u5355\u8bcd\u51fa\u73b0\u7684\u6b21\u6570\npackage WC;\n\nimport java.io.IOException;\nimport org.apache.hadoop.conf.Configuration;\nimport org.apache.hadoop.fs.Path;\nimport org.apache.hadoop.io.IntWritable;\nimport org.apache.hadoop.io.Text;\nimport org.apache.hadoop.mapreduce.Job;\nimport org.apache.hadoop.mapreduce.Mapper;\nimport org.apache.hadoop.mapreduce.Reducer;\nimport org.apache.hadoop.mapreduce.lib.input.FileInputFormat;\nimport org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;\nimport org.apache.hadoop.util.GenericOptionsParser;\nimport java.util.StringTokenizer;\n\npublic class WordCount {\n\n  \/\/ \u5b9a\u4e49Mapper\u7c7b\n  public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable> {\n    \n    \/\/ \u4e00\u4e2aIntWritable\u5b9e\u4f8b\uff0c\u8868\u793a\u8ba1\u65701\n    private final static IntWritable one = new IntWritable(1);\n    \/\/ \u7528\u4e8e\u5b58\u50a8\u5f53\u524d\u5904\u7406\u7684\u5355\u8bcd\n    private Text word = new Text();\n      \n    \/\/ map\u65b9\u6cd5\uff1a\u5c06\u8f93\u5165\u7684\u4e00\u884c\u6587\u672c\u62c6\u5206\u6210\u5355\u8bcd\uff0c\u5e76\u4e3a\u6bcf\u4e2a\u5355\u8bcd\u751f\u6210\u4e00\u4e2a\u952e\u503c\u5bf9\n    public void map(Object key, Text value, Context context) throws IOException, InterruptedException {\n      \/\/ \u4f7f\u7528\u7a7a\u683c\u4f5c\u4e3a\u5206\u9694\u7b26\u5c06\u8f93\u5165\u884c\u62c6\u5206\u4e3a\u5355\u8bcd\n      StringTokenizer itr = new StringTokenizer(value.toString());\n      while (itr.hasMoreTokens()) {\n        \/\/ \u8bbe\u7f6e\u5f53\u524d\u5355\u8bcd\n        word.set(itr.nextToken());\n        \/\/ \u8f93\u51fa\u952e\u503c\u5bf9 (\u5355\u8bcd, 1)\n        context.write(word, one);\n      }\n    }\n  }\n  \n  \/\/ \u5b9a\u4e49Reducer\u7c7b\n  public static class IntSumReducer extends Reducer<Text, IntWritable, Text, IntWritable> {\n    \/\/ \u7528\u4e8e\u5b58\u50a8\u5355\u8bcd\u7684\u603b\u51fa\u73b0\u6b21\u6570\n    private IntWritable result = new IntWritable();\n\n    \/\/ reduce\u65b9\u6cd5\uff1a\u6c47\u603b\u76f8\u540c\u5355\u8bcd\u7684\u6240\u6709\u8ba1\u6570\u503c\n    public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException {\n      int sum = 0;\n      for (IntWritable val : values) {\n        \/\/ \u7d2f\u52a0\u6240\u6709\u76f8\u540c\u7684\u5355\u8bcd\u7684\u8ba1\u6570\u503c\n        sum += val.get();\n      }\n      \/\/ \u8bbe\u7f6e\u7ed3\u679c\u8ba1\u6570\u503c\n      result.set(sum);\n      \/\/ \u8f93\u51fa\u6700\u7ec8\u7684\u952e\u503c\u5bf9 (\u5355\u8bcd, \u603b\u8ba1\u6570)\n      context.write(key, result);\n    }\n  }\n\n  \/\/ \u4e3b\u65b9\u6cd5\n  public static void main(String[] args) throws Exception {\n    \/\/ \u521b\u5efa\u914d\u7f6e\u5bf9\u8c61\n    Configuration conf = new Configuration();\n    \/\/ \u89e3\u6790\u547d\u4ee4\u884c\u53c2\u6570\uff0c\u83b7\u53d6Hadoop\u901a\u7528\u9009\u9879\uff08\u5982\u8f93\u5165\u8f93\u51fa\u8def\u5f84\uff09\n    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();\n    \/\/ \u68c0\u67e5\u662f\u5426\u63d0\u4f9b\u4e86\u8db3\u591f\u7684\u53c2\u6570\n    if (otherArgs.length < 2) {\n      System.err.println(\"Usage: wordcount <in> [<in>...] <out>\");\n      System.exit(2);\n    }\n    \/\/ \u521b\u5efaJob\u5b9e\u4f8b\n    Job job = Job.getInstance(conf, \"word count\");\n    \/\/ \u8bbe\u7f6e\u4e3b\u7c7b\n    job.setJarByClass(WordCount.class);\n    \/\/ \u8bbe\u7f6eMapper\u7c7b\n    job.setMapperClass(TokenizerMapper.class);\n    \/\/ \u53ef\u9009\uff1a\u8bbe\u7f6eCombiner\u7c7b\uff08\u8fd9\u91cc\u88ab\u6ce8\u91ca\u6389\u4e86\uff09\n    \/\/ job.setCombinerClass(IntSumReducer.class);\n    \/\/ \u8bbe\u7f6eReducer\u7c7b\n    job.setReducerClass(IntSumReducer.class);\n    \/\/ \u8bbe\u7f6e\u8f93\u51fa\u952e\u7684\u7c7b\u578b\n    job.setOutputKeyClass(Text.class);\n    \/\/ \u8bbe\u7f6e\u8f93\u51fa\u503c\u7684\u7c7b\u578b\n    job.setOutputValueClass(IntWritable.class);\n    \/\/ \u6dfb\u52a0\u8f93\u5165\u8def\u5f84\n    for (int i = 0; i < otherArgs.length - 1; ++i) {\n      FileInputFormat.addInputPath(job, new Path(otherArgs[i]));\n    }\n    \/\/ \u8bbe\u7f6e\u8f93\u51fa\u8def\u5f84\n    FileOutputFormat.setOutputPath(job, new Path(otherArgs[otherArgs.length - 1]));\n    \/\/ \u63d0\u4ea4\u4f5c\u4e1a\u5e76\u7b49\u5f85\u5b8c\u6210\n    System.exit(job.waitForCompletion(true) ? 0 : 1);\n  }\n}\n<\/code><\/pre>\n\n\n\n
\"\"<\/figure >\n