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.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.output.FileOutputFormat;
import org.apache.hadoop.util.StringUtils;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;
public class WordCountV020 extends Configured implements Tool {
static Set<String> patternsToSkip = new HashSet<String>();
static 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 static class Map extends
Mapper<LongWritable, Text, Text, IntWritable> {
static enum Counters {
INPUT_WORDS
}
boolean caseSensitive;
private final static IntWritable one = new IntWritable(1);
private Text word = new Text();
public void setup(Context context) {
Configuration conf = context.getConfiguration();
caseSensitive = conf.getBoolean("wordcount.case.sensitive", true);
}
public void map(LongWritable key, Text value, Context context)
throws IOException, InterruptedException {
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());
context.write(word, one);
}
}
}
public static class Reduce extends
Reducer<Text, IntWritable, Text, IntWritable> {
public void reduce(Text key, Iterator<IntWritable> values,
Context context) throws IOException, InterruptedException {
int sum = 0;
while (values.hasNext()) {
sum += values.next().get();
}
context.write(key, new IntWritable(sum));
}
}
public int run(String[] args) throws Exception {
Configuration conf = new Configuration();
// 宣告job 取得conf 並設定名稱 Hadoop Hello World
Job job = new Job(conf, "Hadoop Hello World");
// 設定此運算的主程式
job.setJarByClass(WordCountV020.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
job.setMapperClass(Map.class);
job.setCombinerClass(Reduce.class);
job.setReducerClass(Reduce.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]);
}
}
Path[] patternsFiles = null;
if (conf.getBoolean("wordcount.skip.patterns", false)) {
try {
patternsFiles = DistributedCache.getLocalCacheFiles(conf);
} catch (Exception ioe) {
System.err
.println("Caught exception while getting cached files: "
+ StringUtils.stringifyException(ioe));
}
if (patternsFiles != null) {
for (Path patternsFile : patternsFiles) {
System.err.println(patternsFile);
parseSkipFile(patternsFile);
}
} else {
System.err.print("no path");
}
}
FileInputFormat.setInputPaths(job, new Path(other_args.get(0)));
// 設定輸出路徑
FileOutputFormat.setOutputPath(job, new Path(other_args.get(1)));
// CheckAndDelete.checkAndDelete(other_args.get(1), conf);
job.waitForCompletion(true);
return 0;
}
public static void main(String[] args) throws Exception {
String[] argv = { "-Dwordcount.case.sensitive=false",
"/user/waue/input", "/user/waue/output-v020", "-skip",
"/user/waue/patterns" };
args = argv;
int res = ToolRunner
.run(new Configuration(), new WordCountV020(), args);
System.exit(res);
}
}