c - 从中​​字符串

Question

提取的话我是相当新的C，因此遇到比较严重的混乱与使用指针。

我试图从ASCII字符的字符串中提取的话。 例如，如果我有字符串@@ Hello..world >>，我想从字符串中获得单词“Hello”和“world”，并将它们添加到我的链接列表中。

一个字被定义为任何字母序列，并且每个字至多为64个字节。此外，函数isspace（）返回一个非零值的任何字符都被认为是空白。

基本上，我使用fscanf从文件中扫描字符串，然后为每个调用我的函数的字符串read_words（char * s）从字符串中获取正确的单词并将它们添加到我的链接列表中以供进一步使用。

这里是我的代码，这似乎是扔有一个指针做一个错误。

struct node { 
    char *val; 
    struct node *next; 
    int count; 
} *words = NULL; 


void read_words(char *s) 
{ 
    struct node *tmp; 
    char word[64+1]; 
    int i, check, wordStarted = 0, count = 0; 

    for (i = 0; s[i] != '\0'; i++) 
    { 
      if ((isspace(s[i]) != 0) || !isalpha(s[i])) 
      { 
        if (wordStarted == 1) 
        { 
          check = check_list(word); 
          if (check != 1) { 
            word[count] = '\0'; 
            tmp = malloc(sizeof(struct node)); 
            tmp->val = word; 
            tmp->count = 1; 
            tmp->next = words; 
            words = tmp; 
          } 
          count = 0; 
          wordStarted = 0; 
        } 
      } 
      else 
      { 
        word[count++] = s[i]; 
        wordStarted = 1; 
      } 
    } 

} 

任何帮助，将不胜感激！

谢谢！

Answer 1

您将要来标记字符串，而不是实现自己的算法和部分追加到链表。使用strtok（ref）。

从上面的链接..例如：

​​

输出：

Splitting string "- This, a sample string." into tokens: 
This 
a 
sample 
string 

Answer 2

为ANSI C.

用法strtok的更好的解决方案（）它并不总是好：

1. 它会改变原点数组。
2. 空格分隔符“”忽略类似字符：“\ n”，“\ t”等。

尝试下一个和阅读评论的细节：

#include <stdio.h>  // printf 
#include <string.h>  // strlen, strncpy 
#include <ctype.h>  // isalnum 
#include <stdlib.h>  // malloc, calloc 

/* 
    A logical type 
*/ 
typedef enum { 
    false, 
    true, 
} bool; 


/* 
    A Struct for hold 2D-array with count items 
*/ 
typedef struct _ListWithLength { 
    char **list; 
    size_t length; 
} ListWithLength; 


/* 
    Parse a text and return pointer to a ListWithLength words and count it 
*/ 
ListWithLength* getWords(char *text) { 

    // a variable for count words 
    int count = 0; 

    // keep length of the text 
    size_t text_len = strlen(text); 

    // a flag indicating the a beginning of a word 
    bool new_word = false; 

    // an index of a start found a word 
    int index_start_word = 0; 

    // 2D-array for found word 
    // it will be same memory size as the original text 
    char **words = malloc(text_len * sizeof(char)); 

    for (int i = 0; i <= text_len; ++i) { 

     // if found ascii letter or digits and new no traced early 
     // keep index of beginning a new word 
     // and change the flag 
     if (isalnum(text[i]) != 0) { 
      if (new_word == false) { 
       new_word = true; 
       index_start_word = i; 
      } 

     // if it is not ascii letter or digits and a word traced early 
     // it means the word ended 
     } else { 
      if (new_word == true) { 

       // allocate a memory for a new word in the array of words 
       words[count] = malloc(i - index_start_word * sizeof(char) + 1); 

       // copy the found word from the text by indexes 
       strncpy(words[count], text + index_start_word, i - index_start_word); 

       // change the flag 
       new_word = false; 

       // increase the counter of words 
       count++; 
      } 
     }; 
    } 

    // bind the found words and it count to a structure and return it 
    ListWithLength *list_with_length = malloc(sizeof(ListWithLength)); 

    list_with_length->length = count; 
    list_with_length->list = words; 

    return list_with_length; 
} 


/* 
    Print information of a ListWithLength 
*/ 
void printListWithLength(ListWithLength *list_with_length) { 
    printf("Total items: %li\n", list_with_length->length); 
    puts("----------------------"); 
    for (int i = 0; i < list_with_length->length; ++i) { 
     printf("%d. %s\n", i + 1, list_with_length->list[i]); 
    } 
} 


int main(int argc, char const *argv[]) 
{ 

    char c_keywords[300] = "auto else long switch\ 
    break\t enum \t register typedef\ 
    \ncase extern, return union\ 
    ?char float. short unsigned\ 
    const !for signed void\ 
    continue goto sizeof volatile\ 
    .default???? if static while\ 
    do int struct,,,, _Packed\ 
    double......."; 

    ListWithLength *list_with_length = getWords(c_keywords); 
    printListWithLength(list_with_length); 

    return 0; 
} 

编译看看结果：

$ gcc -Wall -ansi -std=c11 -o main main.c 
$ ./main 
Total items: 33 
---------------------- 
1. auto 
2. else 
3. long 
4. switch 
5. break 
6. enum 
7. register 
8. typedef 
9. case 
10. extern 
11. return 
12. union 
13. char 
14. float 
15. short 
16. unsigned 
17. const 
18. for 
19. signed 
20. void 
21. continue 
22. goto 
23. sizeof 
24. volatile 
25. default 
26. if 
27. static 
28. while 
29. do 
30. int 
31. struct 
32. Packed 
33. double