Changes between Initial Version and Version 1 of wc2

Timestamp:

Jul 31, 2011, 7:20:16 AM (13 years ago)

Author:

waue

Comment:

--

wc2

@@ +1 @@
+
+{{{
+#!java
+package waue;
+
+import java.io.BufferedReader;
+import java.io.FileReader;
+import java.io.IOException;
+import java.util.ArrayList;
+import java.util.HashSet;
+import java.util.Iterator;
+import java.util.List;
+import java.util.Set;
+import java.util.StringTokenizer;
+
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.conf.Configured;
+import org.apache.hadoop.filecache.DistributedCache;
+import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.io.IntWritable;
+import org.apache.hadoop.io.LongWritable;
+import org.apache.hadoop.io.Text;
+import org.apache.hadoop.mapred.OutputCollector;
+import org.apache.hadoop.mapred.Reporter;
+import org.apache.hadoop.mapreduce.Job;
+import org.apache.hadoop.mapreduce.Mapper;
+import org.apache.hadoop.mapreduce.Reducer;
+import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
+import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
+import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
+import org.apache.hadoop.mapreduce.lib.output.TextOutputFormat;
+import org.apache.hadoop.util.GenericOptionsParser;
+import org.apache.hadoop.util.StringUtils;
+import org.apache.hadoop.util.Tool;
+import org.apache.hadoop.util.ToolRunner;
+
+public class WordCountV2 extends Configured implements Tool {
+
+        public static class Map extends
+                        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 setup(Mapper.Context context) {
+                        Configuration conf = context.getConfiguration();
+                        caseSensitive = conf.getBoolean("wordcount.case.sensitive", true);
+                        inputFile = conf.get("map.input.file");
+
+                        if (conf.getBoolean("wordcount.skip.patterns", false)) {
+                                Path[] patternsFiles = new Path[0];
+                                try {
+                                        patternsFiles = DistributedCache.getLocalCacheFiles(conf);
+                                } 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
+                        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);
+                Configuration conf = new Configuration();
+                Job job = new Job();
+                job.setJobName("wordcount");
+                String[] otherArgs = new GenericOptionsParser(conf, args)
+                                .getRemainingArgs();
+                if (otherArgs.length < 2) {
+                        System.out
+                                        .println("WordCountV2 [-Dwordcount.case.sensitive=<false|true>] \\ ");
+                        System.out
+                                        .println("            <inDir> <outDir> [-skip Pattern_file]");
+                        return 0;
+                }
+                job.setOutputKeyClass(Text.class);
+                job.setOutputValueClass(IntWritable.class);
+
+                job.setMapperClass(Map.class);
+                job.setCombinerClass(Reduce.class);
+                job.setReducerClass(Reduce.class);
+
+                job.setInputFormatClass(TextInputFormat.class);
+                job.setOutputFormatClass(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(job, new Path(other_args.get(0)));
+                FileOutputFormat.setOutputPath(job, new Path(other_args.get(1)));
+                job.waitForCompletion(true);
+                return 0;
+        }
+
+        public static void main(String[] args) throws Exception {
+                // String[] argv = { "-Dwordcount.case.sensitive=false",
+                // "/user/hadoop/input",
+                // "/user/hadoop/output-wc2", "-skip",
+                // "/user/hadoop/patterns/patterns.txt" };
+                // args = argv;
+
+                int res = ToolRunner.run(new Configuration(), new WordCountV2(), args);
+                System.exit(res);
+        }
+}
+}}}