读取并输出一个文件中单词数量(java)

public static void main2(String[] args) {
	String path = MapUtil.class.getClassLoader().getSystemResource("word.txt").toString().substring(6);
	System.out.println(path);
	//<单词, 数量>
	Map<String, Integer> map = new HashMap<String, Integer>();
	String line;
	BufferedReader bufferedReader = null;
	try {
		bufferedReader = new BufferedReader(new FileReader(path));
		while (null != (line=bufferedReader.readLine())) {
			String[] words = line.split("\\s+");
	        for(String word :words){
	        	if (map.containsKey(word)) {
					map.put(word, map.get(word)+1);
				}else {
					map.put(word, 1);
				}
	        }
		}
		Set<String> wordSets = map.keySet();
		 for(String key : wordSets){
             System.out.println(key + "有:" + map.get(key) + "个.");
        }
	} catch (FileNotFoundException e) {
		e.printStackTrace();
	} catch (IOException e) {
		e.printStackTrace();
	}finally {
		if (null != bufferedReader) {
			try {
				bufferedReader.close();
			} catch (IOException e) {
				e.printStackTrace();
			}
		}
	}

}	
  • 1
    点赞
  • 4
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
好的,以下是一个简单的Java程序,实现从HDFS读取文件并计算文件单词数量: ``` import java.io.IOException; import java.util.StringTokenizer; import org.apache.hadoop.conf.Configuration; import org.apache.hadoop.fs.FileSystem; import org.apache.hadoop.fs.Path; import org.apache.hadoop.io.IntWritable; 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; public class WordCount { public static class TokenizerMapper extends Mapper<Object, Text, Text, IntWritable>{ private final static IntWritable one = new IntWritable(1); private Text word = new Text(); public void map(Object key, Text value, Context context) throws IOException, InterruptedException { StringTokenizer itr = new StringTokenizer(value.toString()); while (itr.hasMoreTokens()) { word.set(itr.nextToken()); context.write(word, one); } } } public static class IntSumReducer extends Reducer<Text,IntWritable,Text,IntWritable> { private IntWritable result = new IntWritable(); public void reduce(Text key, Iterable<IntWritable> values, Context context) throws IOException, InterruptedException { int sum = 0; for (IntWritable val : values) { sum += val.get(); } result.set(sum); context.write(key, result); } } public static void main(String[] args) throws Exception { Configuration conf = new Configuration(); FileSystem fs = FileSystem.get(conf); if (args.length < 2) { System.err.println("Usage: WordCount <input path> <output path>"); System.exit(-1); } Job job = Job.getInstance(conf, "word count"); job.setJarByClass(WordCount.class); job.setMapperClass(TokenizerMapper.class); job.setCombinerClass(IntSumReducer.class); job.setReducerClass(IntSumReducer.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(IntWritable.class); // 设置输入路径和输出路径 FileInputFormat.addInputPath(job, new Path(args[0])); Path outputPath = new Path(args[1]); if (fs.exists(outputPath)) { fs.delete(outputPath, true); } FileOutputFormat.setOutputPath(job, outputPath); System.exit(job.waitForCompletion(true) ? 0 : 1); } } ``` 在执行时,需要指定输入路径和输出路径,例如: ``` hadoop jar wordcount.jar WordCount /input/sample.txt /output ``` 其,/input/sample.txt表示输入文件的路径,/output表示输出路径。
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值