英文统计

任务一：26个英文字母不分大小统计个数

代码：

package analyse_word;

import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.InputStreamReader;
import java.text.DecimalFormat;

public class English_letter {

 public static void main(String args[]) {
  DecimalFormat df = new DecimalFormat("0.00%");
  try {
   char shu[] = new char[100000];
   char zimu[] = new char[52];
   int j = 0;
      long count[] = new long [52];
   String pathname = "D:\Englis_letter.txt";
   File filename = new File(pathname);
   InputStreamReader reader = new InputStreamReader(new FileInputStream(filename));
   BufferedReader br = new BufferedReader(reader);
   String line[] = new String[100000];
   ;
   for (int i = 0; i < line.length; i++) {
    line[i] = br.readLine();
   }
   br.close();
   int k = 0;
   while (line[k] != null) {
    for (int i = 0; i < line[k].length(); i++) {
     shu[j] = line[k].charAt(i);
     j++;
    }
    k++;
   }
   for (int i = 0; i < shu.length; i++) {
    switch (shu[i]) {
    case 'a':
     zimu[0] = 'a';
     count[0]++;
     break;
    case 'b':
     zimu[1] = 'b';
     count[1]++;
     break;
    case 'c':
     zimu[2] = 'c';
     count[2]++;
     break;
    case 'd':
     zimu[3] = 'd';
     count[3]++;
     break;
    case 'e':
     zimu[4] = 'e';
     count[4]++;
     break;
    case 'f':
     zimu[5] = 'f';
     count[5]++;
     break;
    case 'g':
     zimu[6] = 'g';
     count[6]++;
     break;
    case 'h':
     zimu[7] = 'h';
     count[7]++;
     break;
    case 'i':
     zimu[8] = 'i';
     count[8]++;
     break;
    case 'j':
     zimu[9] = 'j';
     count[9]++;
     break;
    case 'k':
     zimu[10] = 'k';
     count[10]++;
     break;
    case 'l':
     zimu[11] = 'l';
     count[11]++;
     break;
    case 'm':
     zimu[12] = 'm';
     count[12]++;
     break;
    case 'n':
     zimu[13] = 'n';
     count[13]++;
     break;
    case 'o':
     zimu[14] = 'o';
     count[14]++;
     break;
    case 'p':
     zimu[15] = 'p';
     count[15]++;
     break;
    case 'q':
     zimu[16] = 'q';
     count[16]++;
     break;
    case 'r':
     zimu[17] = 'r';
     count[17]++;
     break;
    case 's':
     zimu[18] = 's';
     count[18]++;
     break;
    case 't':
     zimu[19] = 't';
     count[19]++;
     break;
    case 'u':
     zimu[20] = 'u';
     count[20]++;
     break;
    case 'v':
     zimu[21] = 'v';
     count[21]++;
     break;
    case 'w':
     zimu[22] = 'w';
     count[22]++;
     break;
    case 'x':
     zimu[23] = 'x';
     count[23]++;
     break;
    case 'y':
     zimu[24] = 'y';
     count[24]++;
     break;
    case 'z':
     zimu[25] = 'z';
     count[25]++;
     break;
    case 'A':
     zimu[26] = 'A';
     count[26]++;
     break;
    case 'B':
     zimu[27] = 'B';
     count[27]++;
     break;
    case 'C':
     zimu[28] = 'C';
     count[28]++;
     break;
    case 'D':
     zimu[29] = 'D';
     count[29]++;
     break;
    case 'E':
     zimu[30] = 'E';
     count[30]++;
     break;
    case 'F':
     zimu[31] = 'F';
     count[31]++;
     break;
    case 'G':
     zimu[32] = 'G';
     count[32]++;
     break;
    case 'H':
     zimu[33] = 'H';
     count[33]++;
     break;
    case 'I':
     zimu[34] = 'I';
     count[34]++;
     break;
    case 'J':
     zimu[35] = 'G';
     count[35]++;
     break;
    case 'K':
     zimu[36] = 'K';
     count[36]++;
     break;
    case 'L':
     zimu[37] = 'L';
     count[37]++;
     break;
    case 'M':
     zimu[38] = 'M';
     count[38]++;
     break;
    case 'N':
     zimu[39] = 'N';
     count[39]++;
     break;
    case 'O':
     zimu[40] = 'O';
     count[40]++;
     break;
    case 'P':
     zimu[41] = 'P';
     count[41]++;
     break;
    case 'Q':
     zimu[42] = 'Q';
     count[42]++;
     break;
    case 'R':
     zimu[43] = 'R';
     count[43]++;
     break;
    case 'S':
     zimu[44] = 'S';
     count[44]++;
     break;
    case 'T':
     zimu[45] = 'T';
     count[45]++;
     break;
    case 'U':
     zimu[46] = 'U';
     count[46]++;
     break;
    case 'V':
     zimu[47] = 'V';
     count[47]++;
     break;
    case 'W':
     zimu[48] = 'W';
     count[48]++;
     break;
    case 'X':
     zimu[49] = 'X';
     count[49]++;
     break;
    case 'Y':
     zimu[50] = 'Y';
     count[50]++;
     break;
    case 'Z':
     zimu[51] = 'Z';
     count[51]++;
    }
   }
   int ci = 0;
   int sum = 0;
   System.out.println("短文中各字母出现情况统计如下：");
   for (int i = 0; i < 26; i++) {
    count[i]+=count[i+26];
    if (count[i] != 0) {
     ci++;
     sum += count[i];
     System.out.println(ci + ".字母" + zimu[i] + "的出现次数是:" + count[i]);
    }
   }
   
   for (int i = 0; i < 26; i++) {
    System.out.println(zimu[i]+"出现的百分比为:"+df.format(count[i]*1.0/sum));
   }
   System.out.println("字母共计：" + sum + "个");
  } catch (Exception e) {
   e.printStackTrace();
  }
 }

}

截图:

任务二：统计单词出现的次数并在控制台设置输出前多少个频率最高的单词，“the,a”等无用字符不出现

package analyse_word;

import java.io.File;
import java.io.FileNotFoundException;
import java.util.HashMap;
import java.util.Iterator;
import java.util.Scanner;
import java.util.Set;

public class English_word {
 
 
 public static void main(String[] args) throws FileNotFoundException {
  File file = new File("D:\Englis_letter.txt");// 读取文件
  String words[] = new String [100000];
  int out_words[] = new int [100000];
  if (!file.exists()) {// 如果文件打不开或不存在则提示错误
   System.out.println("文件不存在");
   return;
  }
  Scanner x = new Scanner(file);
  HashMap<String, Integer> hashMap = new HashMap<String, Integer>();
  while (x.hasNextLine()) {
   String line = x.nextLine();
   String[] lineWords = line.split("[\s+ ”“();,.?! ]");
   Set<String> wordSet = hashMap.keySet();
   for (int i = 0; i < lineWords.length; i++) {
    if (wordSet.contains(lineWords[i])) {
     Integer number = hashMap.get(lineWords[i]);
     number++;
     hashMap.put(lineWords[i], number);
    } else {
     hashMap.put(lineWords[i], 1);
    }
   }
  }
  Iterator<String> iterator = hashMap.keySet().iterator();
  int max = 0,i=0;
  while (iterator.hasNext()) {
   String word = iterator.next();
   if(!"".equals(word)&&word!=null&&!"a".equals(word)&&!"the".equals(word)&&!"　　".equals(word)) {
    System.out.println(word);
    words[i]=word;
    out_words[i]=hashMap.get(word);
    i++;
   }
  }
  int change=0;
  String change_word=null;
  for(int j=0;j<=i;j++)
  {
   for(int k=j;k<=i;k++)
   {
    if(out_words[k]>out_words[j])
    {
     change=out_words[j];
     change_word=words[j];
     out_words[j]=out_words[k];
     words[j]=words[k];
     out_words[k]=change;
     words[k]=change_word;
    }
    
   }
  }
  Scanner scan = new Scanner(System.in);
  int ms = scan.nextInt();
  for(int j=0;j<ms;j++)
  {
   System.out.println(words[j]+" 出现次数:"+out_words[j]);
  }
  
 }
}

任务三：遍历目录下所有.txt文本并按任务二要求进行统计

package analyse_word;

import java.io.File;
import java.io.FileNotFoundException;
import java.util.HashMap;
import java.util.Iterator;
import java.util.Scanner;
import java.util.Set;

public class test {
 
    static String words[] = new String [100000];
    static   int out_words[] = new int [100000];
    static int i=0;
    static HashMap<String, Integer> hashMap = new HashMap<String, Integer>();
 
 public static void English_words(File ms) throws FileNotFoundException {
  File file = new File(ms.toString());// 读取文件
  if (!file.exists()) {// 如果文件打不开或不存在则提示错误
   System.out.println("文件不存在");
   return;
  }
  Scanner x = new Scanner(file);
  while (x.hasNextLine()) {
   String line = x.nextLine();
   String[] lineWords = line.split("[\s+ ”“();,.?! ]");
   Set<String> wordSet = hashMap.keySet();
   for (int i = 0; i < lineWords.length; i++) {
    if (wordSet.contains(lineWords[i])) {
     Integer number = hashMap.get(lineWords[i]);
     number++;
     hashMap.put(lineWords[i], number);
    } else {
     hashMap.put(lineWords[i], 1);
    }
   }
  }
  
  
  
 }
 
 public static void main(String[] args) throws FileNotFoundException {
  String path = "d:/";
  File file = new File(path);
  File[] tempList = file.listFiles();
  for (int i = 0; i < tempList.length; i++) {
   if (tempList[i].toString().endsWith("txt")) {
    System.out.println("文     件：" + tempList[i]);
    English_words(tempList[i]);
   }
  }
  Iterator<String> iterator = hashMap.keySet().iterator();
  int max = 0;
  while (iterator.hasNext()) {
   String word = iterator.next();
   if(!"".equals(word)&&word!=null&&!"a".equals(word)&&!"the".equals(word)&&!"　　".equals(word)) {
    words[i]=word;
    out_words[i]=hashMap.get(word);
    i++;
   }
  }
  int change=0;
  String change_word=null;
  for(int j=0;j<=i;j++)
  {
   for(int k=j;k<=i;k++)
   {
    if(out_words[k]>out_words[j])
    {
     change=out_words[j];
     change_word=words[j];
     out_words[j]=out_words[k];
     words[j]=words[k];
     out_words[k]=change;
     words[k]=change_word;
    }
    
   }
  }
  Scanner scan = new Scanner(System.in);
  int ms = scan.nextInt();
  for(int j=0;j<ms;j++)
  {
   System.out.println(words[j]+" 出现次数:"+out_words[j]);
  }
  
 }

}

任务四：统计目录下的所有子.txt文件以及子目录下.txt文件

package analyse_word;

import java.io.File;
import java.io.FileNotFoundException;
import java.util.HashMap;
import java.util.Iterator;
import java.util.Scanner;
import java.util.Set;

public class tests {
 
 static String words[] = new String [100000];
    static   int out_words[] = new int [100000];
    static int i=0;
    static HashMap<String, Integer> hashMap = new HashMap<String, Integer>();
 
 public static void English_words(File ms) throws FileNotFoundException {
  File file = new File(ms.toString());// 读取文件
  if (!file.exists()) {// 如果文件打不开或不存在则提示错误
   System.out.println("文件不存在");
   return;
  }
  Scanner x = new Scanner(file);
  while (x.hasNextLine()) {
   String line = x.nextLine();
   String[] lineWords = line.split("[\s+ ”“();,.?! ]");
   Set<String> wordSet = hashMap.keySet();
   for (int i = 0; i < lineWords.length; i++) {
    if (wordSet.contains(lineWords[i])) {
     Integer number = hashMap.get(lineWords[i]);
     number++;
     hashMap.put(lineWords[i], number);
    } else {
     hashMap.put(lineWords[i], 1);
    }
   }
  }
  
  
  
 }
 
 public static void main(String[] args) throws FileNotFoundException {
  String path = "d:/";
  File file = new File(path);
  File[] tempList = file.listFiles();
  for (int i = 0; i < tempList.length; i++) {
   if (tempList[i].toString().endsWith("txt")) {
    System.out.println("文     件：" + tempList[i]);
    English_words(tempList[i]);
   }
   if (tempList[i].isDirectory()) {
    File files = new File(tempList[i].toString() + "\");
    File[] tempLists = files.listFiles();
    if(tempLists!=null)
    for (int j = 0; j < tempLists.length; j++) {
     if (tempLists[j].toString().endsWith(".txt")) {
      System.out.println("文     件：" + tempLists[j]);
      English_words(tempLists[j]);
     }
    }
   }
  }
  Iterator<String> iterator = hashMap.keySet().iterator();
  int max = 0;
  while (iterator.hasNext()) {
   String word = iterator.next();
   if(!"".equals(word)&&word!=null&&!"a".equals(word)&&!"the".equals(word)&&!"　　".equals(word)) {
    words[i]=word;
    out_words[i]=hashMap.get(word);
    i++;
   }
  }
  int change=0;
  String change_word=null;
  for(int j=0;j<=i;j++)
  {
   for(int k=j;k<=i;k++)
   {
    if(out_words[k]>out_words[j])
    {
     change=out_words[j];
     change_word=words[j];
     out_words[j]=out_words[k];
     words[j]=words[k];
     out_words[k]=change;
     words[k]=change_word;
    }
    
   }
  }
  Scanner scan = new Scanner(System.in);
  int ms = scan.nextInt();
  for(int j=0;j<ms;j++)
  {
   System.out.println(words[j]+" 出现次数:"+out_words[j]);
  }
 }

}