您好,登錄后才能下訂單哦!
本篇內容介紹了“WordCount MapReduce怎么使用”的有關知識,在實際案例的操作過程中,不少人都會遇到這樣的困境,接下來就讓小編帶領大家學習一下如何處理這些情況吧!希望大家仔細閱讀,能夠學有所成!
package org.myorg; import java.io.*; import java.util.*; import org.apache.hadoop.fs.Path; import org.apache.hadoop.filecache.DistributedCache; import org.apache.hadoop.conf.*; import org.apache.hadoop.io.*; import org.apache.hadoop.mapred.*; import org.apache.hadoop.util.*; public class WordCount extends Configured implements Tool { public static class Map extends MapReduceBase implements Mapper<LongWritable, Text, Text, IntWritable> { static enum Counters {INPUT_WORDS} private final static IntWritable one = new IntWritable(1); private Text word = new Text(); private boolean caseSensitive = true; private Set<String> patternsToSkip = new HashSet<String>(); private long numRecords = 0; private String inputFile; public void configure(JobConf job) { caseSensitive = job.getBoolean("wordcount.case.sensitive", true); inputFile = job.get("map.input.file"); if (job.getBoolean("wordcount.skip.patterns", false)) { Path[] patternsFiles = new Path[0]; try { patternsFiles = DistributedCache.getLocalCacheFiles(job); } catch (IOException ioe) { System.err.println("Caught exception while getting cached files: " + StringUtils.stringifyException(ioe)); } for (Path patternsFile : patternsFiles) { parseSkipFile(patternsFile); } } } private void parseSkipFile(Path patternsFile) { try { BufferedReader fis = new BufferedReader(new FileReader(patternsFile.toString())); String pattern = null; while ((pattern = fis.readLine()) != null) { patternsToSkip.add(pattern); } } catch (IOException ioe) { System.err.println("Caught exception while parsing the cached file '" + patternsFile + "' : " + StringUtils.stringifyException(ioe)); } } public void map(LongWritable key, Text value, OutputCollector<Text, IntWritable> output, Reporter reporter) throws IOException { String line = (caseSensitive) ? value.toString() : value.toString().toLowerCase(); for (String pattern : patternsToSkip) { line = line.replaceAll(pattern, ""); } StringTokenizer tokenizer = new StringTokenizer(line); while (tokenizer.hasMoreTokens()) { word.set(tokenizer.nextToken()); output.collect(word, one); reporter.incrCounter(Counters.INPUT_WORDS, 1); } if ((++numRecords % 100) == 0) { reporter.setStatus("Finished processing " + numRecords + " records " + "from the input file: " + inputFile); } } } 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)); } } public int run(String[] args) throws Exception { JobConf conf = new JobConf(getConf(), WordCount.class); conf.setJobName("wordcount"); conf.setOutputKeyClass(Text.class); conf.setOutputValueClass(IntWritable.class); conf.setMapperClass(Map.class); conf.setCombinerClass(Reduce.class); conf.setReducerClass(Reduce.class); conf.setInputFormat(TextInputFormat.class); conf.setOutputFormat(TextOutputFormat.class); List<String> other_args = new ArrayList<String>(); for (int i = 0; i < args.length; ++i) { if ("-skip".equals(args[i])) { DistributedCache.addCacheFile(new Path(args[++i]).toUri(), conf); conf.setBoolean("wordcount.skip.patterns", true); } else { other_args.add(args[i]); } } FileInputFormat.setInputPaths(conf, new Path(other_args.get(0))); FileOutputFormat.setOutputPath(conf, new Path(other_args.get(1))); JobClient.runJob(conf); return 0; } public static void main(String[] args) throws Exception { int res = ToolRunner.run(new Configuration(), new WordCount(), args); System.exit(res); } }
“WordCount MapReduce怎么使用”的內容就介紹到這里了,感謝大家的閱讀。如果想了解更多行業相關的知識可以關注億速云網站,小編將為大家輸出更多高質量的實用文章!
免責聲明:本站發布的內容(圖片、視頻和文字)以原創、轉載和分享為主,文章觀點不代表本網站立場,如果涉及侵權請聯系站長郵箱:is@yisu.com進行舉報,并提供相關證據,一經查實,將立刻刪除涉嫌侵權內容。