Question

在下面的代码中，我试图逐字加载一个单词的文本文件然后我试图在哈希表中保存每个字（字符串数组）但似乎strcpy保存了整个单词而不是单char，我不知道为什么。我是否误用了strcpy和strcat？

# include <stdio.h>
# include <stdlib.h>
# include <string.h>
# include <ctype.h>
# include <stdbool.h>
bool load(const char* dictionary);

#define LENGTH 45


int main (int argc, char* argv[])
{
  char* dictionary = argv[1];
  load(dictionary);
  return 0;
}

bool load(const char* dictionary)
{
  int index = 0, words = 0, kk = 0;
  int lastl = 0, midl = 0;
  char word[LENGTH + 1];
  char *wholeword[1001];

  FILE* dic = fopen(dictionary, "r");
  if (dic == NULL)
  {
    printf("Could not open %s.\n", dictionary);
    return false;
  }

  for (int c = fgetc(dic); c != EOF; c = fgetc(dic))
  {
    // allow only alphabetical characters and apostrophes
    if (isalpha(c) || (c == '\'' && index > 0))
    {
      // append character to word
      word[index] = c;
      index++;

      // ignore alphabetical strings too long to be words
      if (index > LENGTH)
      {
        // consume remainder of alphabetical string
        while ((c = fgetc(dic)) != EOF && isalpha(c));
        // prepare for new word
        index = 0;
      }
    }

    // ignore words with numbers (like MS Word can)
    else if (isdigit(c))
    {
      // consume remainder of alphanumeric string
      while ((c = fgetc(dic)) != EOF && isalnum(c));

      // prepare for new word
      index = 0;
    }

    // we must have found a whole word
    else if (index > 0)
    {
      // terminate current word
      word[index] = '\0';
      lastl = index - 1;
      midl = (index - 1) % 3;
      words++;
      index = 0;

      int hashi = (word[0] + word[lastl]) * (word[midl] + 17) % 1000;

      wholeword[hashi] = (char*) malloc(sizeof(char) * (lastl + 2));

      strcpy(wholeword[hashi], &word[0]);  // ***

      for (kk = 1; kk <= lastl + 1; kk++)
      {
        strcat(wholeword[words], &word[kk]);
      }
    }
  }
  fclose(dic);
  return true;
}

Answer 1

Strcpy不复制单个字符，它会复制所有字符，直到下一个空（'\0'）字节。要复制代码中的单个字符，请尝试：

wholeword[hashi] = &word[0];

而不是：

strcpy(wholeword[hashi], &word[0]);

Answer 2

是的，你误用strcpy和strcat：这些函数将整个源字符串复制到目标数组（在strcat的现有字符串的末尾。）

以下几行：

  wholeword[hashi] = (char*) malloc(sizeof(char) * (lastl + 2));

  strcpy(wholeword[hashi], &word[0]);  // ***

  for (kk = 1; kk <= lastl + 1; kk++)
  {
    strcat(wholeword[words], &word[kk]);
  }
}

可以通过一次调用来替换

   wholeword[hashi] = strdup(word);

strdup()分配内存，将参数字符串复制到它并返回指针。它适用于所有Posix系统，如果您没有，请使用以下两行：

  wholeword[hashi] = malloc(lastl + 2);
  strcpy(wholeword[hashi], word);

注意：

你假设你的哈希是完美的，没有碰撞。按照当前编码，碰撞会导致前一个单词从字典中删除，并且相应的内存将丢失。
字典char *wholeword[1001];是load函数中的局部变量。它是未初始化的，因此无法知道条目是否是指向单词的有效指针。它应该被分配，初始化为NULL并返回给调用者。

在C中使用strcpy，strcat的冲突？

2 个答案: