import java.io.*; import java.util.*; public class WordCount { public static void main(String[] args) throws IOException { // 读取文件内容 FileReader reader = new FileReader("四级常用单词.txt"); BufferedReader br = new BufferedReader(reader); String line; //接收一行 StringBuilder sb = null; while ((line = br.readLine()) != null) { line.trim(); String[] split = line.split("[^a-zA-Z]"); if (split[0] != null){ sb.append(split[0]); } } String str = sb.toString(); br.close(); reader.close(); int temp; int [] letters=new int[26] ; String words = str.toLowerCase(); for (int i = 0; i < words.length(); i++) { char c = words.charAt(i); letters[c - 'a'] ++; for (int i1 = 0; i1 < 26; i1++) { System.out.println((char) (i1 + 'a') + letters[i]); } } 更改代码中存在的错误

在代码中存在一个错误，即StringBuilder对象sb未初始化，需要进行初始化，可以将其赋值为一个新的StringBuilder对象，如下所示：

StringBuilder sb = new StringBuilder();

另外，还需要将输出语句中的letters[i]改为letters[i1]，如下所示：

System.out.println((char) (i1 + 'a') + letters[i1]);

相关问题

package wc; import java.io.IOException; import org.apache.hadoop.mapreduce.Mapper; import org.apache.hadoop.conf.Configuration; 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.Reducer; import org.apache.hadoop.mapreduce.lib.input.FileInputFormat; import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat; import org.apache.hadoop.util.GenericOptionsParser; public class WordCountMain { public static void main(String[] args) throws Exception{ // TODO Auto-generated method stub Configuration conf = new Configuration(); conf.set("fs.default.name","hdfs://localhost:9000"); String[] otherArgs = new String[]{"input","output"}; /* 直接设置输入参数 */ if (otherArgs.length != 2) { System.err.println("Usage: wordcount <in><out>"); System.exit(2); } Job job = Job.getInstance(conf,"Merge and duplicate removal"); job.setJarByClass(WordCountMapper.class); job.setMapperClass(Map.class); job.setCombinerClass(WordCountReduce.class); job.setReducerClass(WordCountReduce.class); job.setOutputKeyClass(Text.class); job.setOutputValueClass(Text.class); FileInputFormat.addInputPath(job, new Path(otherArgs[0])); FileOutputFormat.setOutputPath(job, new Path(otherArgs[1])); System.exit(job.waitForCompletion(true) ? 0 : 1); } } package wc; import java.io.IOException; import org.apache.hadoop.mapreduce.Mapper; import org.apache.hadoop.io.Text; public class WordCountMapper{ public static class Map extends Mapper<Object, Text, Text, Text>{ private static Text text = new Text(); public void map(Object key, Text value, Context context) throws IOException,InterruptedException{ text = value; context.write(text, new Text("")); } } } job.setmapperclass出错

在您的代码中，您定义了一个名为 WordCountMapper 的类，该类实际上应该是一个 Mapper 类，并且应该继承 Mapper 接口。但是，在您的代码中，WordCountMapper 类没有继承 Mapper 接口，因此在设置 Mapper 类时出现了错误。

您需要将 WordCountMapper 类修改为一个 Mapper 类，并且让它继承 Mapper 接口，如下所示：

package wc;

import java.io.IOException;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.io.Text;

public class WordCountMapper extends Mapper<Object, Text, Text, Text> {

    private static Text text = new Text();

    public void map(Object key, Text value, Context context) throws IOException, InterruptedException {
        text = value;
        context.write(text, new Text(""));
    }
}

然后，您需要将 `job.setMapperClass(Map.class)` 修改为 `job.setMapperClass(WordCountMapper.class)`，以设置正确的 Mapper 类。

帮我解释下面的代码：import java.io.IOException; import java.util.StringTokenizer; import org.apache.hadoop.conf.Configuration; 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; import org.apache.hadoop.util.GenericOptionsParser; 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(); String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs(); if (otherArgs.length != 2) { System.err.println("Usage: wordcount <in> <out>"); System.exit(2); } Job job = new Job(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); FileInputFormat.addInputPath(job, new Path(otherArgs[0])); FileOutputFormat.setOutputPath(job, new Path(otherArgs[1])); System.exit(job.waitForCompletion(true) ? 0 : 1); } }

这段代码是一个 Hadoop MapReduce 的 WordCount（词频统计）程序，主要包括以下几个部分：

1. 引入需要用到的类库：

import java.io.IOException;
import java.util.StringTokenizer;
import org.apache.hadoop.conf.Configuration;
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;
import org.apache.hadoop.util.GenericOptionsParser;

2. 定义 Mapper 类：

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);
        }
    }
}

Mapper 类主要是将输入的文本分割成单词，然后对每个单词输出一个键值对，其中键为单词，值为 1。

3. 定义 Reducer 类：

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);
    }
}

Reducer 类主要是将 Mapper 输出的键值对按照键进行分组，然后对每组键值进行统计，输出每个单词出现的次数。

4. 定义主函数：

public static void main(String[] args) throws Exception {
    Configuration conf = new Configuration();
    String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
    if (otherArgs.length != 2) {
        System.err.println("Usage: wordcount <in> <out>");
        System.exit(2);
    }
    Job job = new Job(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);
    FileInputFormat.addInputPath(job, new Path(otherArgs[0]));
    FileOutputFormat.setOutputPath(job, new Path(otherArgs[1]));
    System.exit(job.waitForCompletion(true) ? 0 : 1);
}

主函数主要是设置 MapReduce 作业的相关参数，包括输入路径、输出路径、Mapper 类、Reducer 类、输出键值对类型等。最后调用 `waitForCompletion` 函数提交作业并等待作业完成。