C-帶有單詞和頻率的排序鏈表

Question

我在完成編程課程的代碼時遇到一些問題（我絕對是C語言的初學者）。 目的是從標准輸入（runfile <input.c）中讀取單詞，計數其頻率，並按字母順序對列表進行排序（首先是大寫單詞），例如輸出：

圖像樣本輸出

我在這里找到了經過修改的Stack上的代碼段，到目前為止，它產生的輸出帶有單詞及其頻率。 但是，我不知道如何像上面的示例中那樣對列表進行排序。 我們的老師建議，如果找到了一個新單詞，應立即將其插入到鏈表中，然后他給出了以下代碼示例（摘自該程序 ）：

void addSorted(link *n, int x) {
  if (*n == NULL || x < (*n)->data) {
    *n = cons(x, *n);
  } else {
    addSorted(&((*n)->next), x);
  }
}

據我了解，“ link * n”應為指向下一個節點的指針，在這種情況下，“ data”將保存整數，而“ cons”應為此代碼中的函數以構造新的節點或鏈接，不確定'int x'，我猜這是當前比較的整數。 就像我說的那樣，我很難在代碼中適應最后的要求。 我試圖改編我的addWord（）函數，但對我來說不起作用。 您可以在下面找到我到目前為止的工作代碼：

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

//=============== STRUCTURE ==================
typedef struct word {
    char *mywords;              // list node with word pointer 
    int freq;                   // Frequency count
    struct word *pNext;         // Pointer to next node in linked list 
    } Word;

//======= INITIATION OF FUNCTIONS ===========
int readWord(char *temp_word, int temp_size);   // Given function to get words
void addWord(char *pWord);                      // Adds a word to the list or updates exisiting word
void printmywords(Word *pListNodes);            // Output list of words and frequencies
Word* construct(char *word);                    // Constructs list nodes

//============GLOBAL VARIABLES================
Word *pFirst = NULL;                  // Pointer to first node in linked list

//================ MAIN ======================    
int main () {

    char temp_word[32]; // temporary buffer to hold words
    int size = 10000;

    Word *pNode = NULL; // pointer to word counter

    while (readWord(temp_word, size)) { // Read all words from standard input

        addWord(temp_word); // Add word to list
    }

    // List the words and their counts
    pNode = pFirst;
    while(pNode != NULL)
    {
        printmywords(pNode);
        pNode = pNode->pNext;
    }
    printf("\n");

    // Free the allocated  memory
    pNode = pFirst;
    while(pNode != NULL)
    {
        free(pNode->mywords);        
        pFirst = pNode;           
        pNode = pNode->pNext;  
        free(pFirst);                  
    }
     return 0;
}

//================ FUNCTIONS =================

void printmywords(Word *pListNodes)
{
    printf("\n%-20s   %5d", pListNodes->mywords,pListNodes->freq); // output word and frequency
}

void addWord(char *word)
{
  Word *pNode = NULL;
  Word *pLast = NULL;

  if(pFirst == NULL)
  {
    pFirst = construct(word);
    return;
  }

  // Update frequency, if word in list
  pNode = pFirst;
  while(pNode != NULL)
  {
    if(strcmp(word, pNode->mywords) == 0)
    {
      ++pNode->freq;
      return;
    }
    pLast = pNode;            
    pNode = pNode->pNext;  
  }

  // Add new word, if not in list
  pLast->pNext = construct(word);
}

Word* construct(char *word)
{
  Word *pNode = NULL;
  pNode = (Word*)malloc(sizeof(Word));
  pNode->mywords = (char*)malloc(strlen(word)+1);
  strcpy(pNode->mywords, word);
  pNode->freq = 1;
  pNode->pNext = NULL;
  return pNode;
}

int readWord(char *temp_word, int temp_size) {
    char *p = temp_word;
    char c;

    // skip all non-word characters
    do {
        c = getchar();
        if (c == EOF) 
            return 0;
        } while (!isalpha(c));

    // read word chars
    do {
        if (p - temp_word < temp_size - 1)
        *p++ = c;
        c = getchar();
        } while (isalpha(c));

        // finalize word
        *p = '\0';
        return 1;
        }

任何幫助表示贊賞。

Answer 1

好的，請嘗試以下兩個功能：

Word *cons(char *word, Word *next) {
  Word *result = construct(word);
  if (result) {
    result->pNext = next;
  }
  else {
    printf("Out of memory in cons\n");
    exit(1);
  }
  return result;
}

void addSorted(Word **nodeRef, char *word) {
  Word *node = *nodeRef;

  /* strcmp will do a binary comparison, which suits your purpose
     because you want capitalized words before lower-case; the order
     of the arguments is important - <0 means the first argument should
     come before the second argument. */

  if ((node == NULL) || (strcmp(word, node->mywords) < 0)) {
    *nodeRef = cons(word, node);
  }
  else if (strcmp(word, node->mywords) == 0) {
    ++node->freq;
  }
  else {
    /* there's not really any point to using recursion on a linked
       list, except for the fact that it's really easy to use recursion
       on a linked list. On a vary large list, iteration would most likely
       be faster; however, professors really like to show how clever they
       are, so you're better off using it anyway. */

    addSorted(&node->pNext, word);
  }
}

其他幾點：

char temp_word[32]; // temporary buffer to hold words
int size = 10000;

您有一個31個字符的緩沖區，但是您要告訴readWord函數它是10K個字符？

另外，不要malloc()的返回值。