统计每个单词出现的次数

Question

我正在尝试计算函数 countWords 中每个单词出现的次数我相信我在函数中正确启动了 for 循环但是我如何比较数组中的单词计算它们然后删除重复项？这不像斐波那契数列还是我弄错了？此外，int n 的值为 756，因为这是数组中的单词数，而 wordsArray 是数组中的元素。

#include <stdio.h>
#include <string.h>
#include <stdlib.h>
#include <ctype.h>

int *countWords( char **words, int n);
int main(int argc, char *argv[])
{
  char buffer[100];  //Maximum word size is 100 letters
  FILE *textFile;
  int numWords=0;
  int nextWord;
  int i, j, len, lastChar;
  char  *wordPtr;
  char  **wordArray;
  int *countArray;
  int *alphaCountArray;
  char **alphaWordArray;
  int *freqCountArray;
  char **freqWordArray;
  int choice=0;

  //Check to see if command line argument (file name)
  //was properly supplied.  If not, terminate program
  if(argc == 1)
  {
    printf ("Must supply a file name as command line argument\n");
    return (0);
  }

  //Open the input file.  Terminate program if open fails
  textFile=fopen(argv[1], "r");
  if(textFile == NULL)
  {
    printf("Error opening file. Program terminated.\n");
    return (0);
  }

  //Read file to count the number of words
  fscanf(textFile, "%s", buffer);
  while(!feof(textFile))
  {
    numWords++;
    fscanf(textFile, "%s", buffer);
  }

  printf("The total number of words is: %d\n", numWords);
  //Create array to hold pointers to words
  wordArray = (char **) malloc(numWords*sizeof(char *));
  if (wordArray == NULL)
  {
     printf("malloc of word Array failed.  Terminating program.\n");
     return (0);
  }
  //Rewind file pointer and read file again to create
  //wordArray
  rewind(textFile);
  for(nextWord=0; nextWord < numWords; nextWord++)
  {
    //read next word from file into buffer.
    fscanf(textFile, "%s", buffer);

    //Remove any punctuation at beginning of word
    i=0;
    while(!isalpha(buffer[i]))
    {
      i++;
    }
    if(i>0)
    {
      len = strlen(buffer);
      for(j=i; j<=len; j++)
      {
        buffer[j-i] = buffer[j];
      }
    }

    //Remove any punctuation at end of word
    len  = strlen(buffer);
    lastChar = len -1;
    while(!isalpha(buffer[lastChar]))
    {
      lastChar--;
    }
    buffer[lastChar+1] = '\0';

    //make sure all characters are lower case
    for(i=0; i < strlen(buffer); i++)
    {
      buffer[i] = tolower(buffer[i]);
    }

    //Now add the word to the wordArray.
    //Need to malloc an array of chars to hold the word.
    //Then copy the word from buffer into this array.
    //Place pointer to array holding the word into next
    //position of wordArray
    wordPtr = (char *) malloc((strlen(buffer)+1)*sizeof(char));
    if(wordPtr == NULL)
    {
      printf("malloc failure.  Terminating program\n");
      return (0);
    }
    strcpy(wordPtr, buffer);
    wordArray[nextWord] = wordPtr;
  }

  //Call countWords() to create countArray and replace
  //duplicate words in wordArray with NULL
  countArray = countWords(wordArray, numWords);
  if(countArray == NULL)
  {
    printf("countWords() function returned NULL; Terminating program\n");
    return (0);
  }

  //Now call compress to remove NULL entries from wordArray
  compress(&wordArray, &countArray, &numWords);
  if(wordArray == NULL)
  {
    printf("compress() function failed; Terminating program.\n");
    return(0);
  }
  printf("Number of words in wordArray after eliminating duplicates and compressing is: %d\n", numWords);

  //Create copy of compressed countArray and wordArray and then sort them alphabetically
  alphaCountArray = copyCountArray(countArray, numWords);
  freqCountArray = copyCountArray(alphaCountArray, numWords);
int *countWords( char **wordArray, int n)
{
  return NULL;
  int i=0;
  int n=0;

  for(i=0;i<n;i++)
  {
      for(n=0;n<wordArray[i];n++)
      {

      }
   }

}

Answer 1

假设您希望 countWords 的返回值是一个整数数组，其中包含每个唯一单词的单词计数，您需要有一个双循环。一个循环遍历整个数组，第二个循环遍历数组的其余部分(在当前单词之后)，寻找重复项。

你可以做类似这样的伪代码:

Allocate the return array countArray (n integers) 
Loop over all words (as you currently do in your `for i` loop)
   If the word at `i` is not null // Check we haven't already deleted this word
      // Found a new word
      Set countArray[i] to 1
      Loop through the rest of the words e.g. for (j = i + 1; j < n; j++)
         If the word at j is not NULL and matches the word at i (using strcmp)
            // Found a duplicate word
            Increment countArray[i] (the original word's count)
            // We don't want wordArray[j] anymore, so 
            Free wordArray[j]
            Set wordArray[j] to NULL
   Else
      // A null indicates this was a duplicate, set the count to 0 for consistency.
      Set countArray[i] to 0
Return wordArray