c - 将每个以特殊单词开头和结尾的字符串存储到 C 中的数组中

Question

我有一个很长的字符串，我想将以特殊单词开头和结尾的每个字符串存储到一个数组中，然后删除重复的字符串。在我的长字符串中，单词之间没有空格、、 或任何其他分隔符，因此我无法使用 strtok。开始标记为 start，结束标记为 end。这是我到目前为止的代码(但它不起作用，因为它使用 strtok())。

char buf[] = "start-12-3.endstart-12-4.endstart-13-3.endstart-12-4.end";
char *array[5];
char *x;
int i = 0, j = 0;
array[i] = strtok(buf, "start");

while (array[i] != NULL) {
    array[++i] = strtok(NULL, "start");
}
//removeDuplicate(array[i]);
for (i = 0; i < 5; i++)
    for (j = 0; j < 5; j++)
        if (strcmp(array[i], array[j]) == 0)
            x[i++] = array[i];

printf("%s", x[i]);

输入示例:

start-12-3.endstart-12-4.endstart-13-3.endstart-12-4.end

输出相当于:

char *array[]= { "start-12-3.end", "start-12-4.end", "start-13-3.end" };

第二个 start-12-4.end 字符串已在输出中被删除。

*我也使用过 strstr 但有一些问题:

int main(int argc, char **argv)
 {
char string[] = "This-one.testthis-two.testthis-three.testthis-two.test";
int counter = 0;

while (counter < 4)
{
    char *result1 = strstr(string, "this");
    int start = result1 - string;
    char *result = strstr(string, "test");
    int end = result - string;
    end += 4;
    printf("\n%s\n", result);
    memmove(result, result1, end += 4);
    counter++;
}
}

To put string into array and remove duplicate string, I've tried following code but it has issue:

int main(void)
{
char string[] = "this-one.testthis-two.testthis-three.testthis-two.test";
int counter = 0;
const char *b_token = "this";
const char *e_token = "test";
int e_len = strlen(e_token);
char *buffer = string;
char *b_mark;
char *e_mark;
char *a[50];
int i=0, j;
char *s;

while ((b_mark = strstr(buffer, b_token)) != 0 && (e_mark =strstr(b_mark, e_token)) != 0)
{
    int length = e_mark + e_len - b_mark;

    s = (char *) malloc(length);

    strncpy(s, b_mark, length);

    a[i]=s;
    i++;
    buffer = e_mark + e_len;
}
for (i=0; i<strlen(s); i++)
       printf ("%s",a[i]);
free(s);
/*  
//remove duplicate string

for (i=0; i<4; i++)
  for (j=0; j<4; j++)
  {

    if (a[i] == NULL || a[j] == NULL || i == j)
         continue;

    if (strcmp (a[i], a[j]) == 0)  {
         free(a[i]);
         a[i] = NULL; 
   }
   printf("%s\n", a[i]);
*/

return 0; 
}

Answer 1

与您提供的示例一起使用，并在 Valgrind 中测试内存泄漏，但可能需要进一步测试。

#include <malloc.h>
#include <stdio.h>
#include <string.h>

unsigned tokens_find_amount( char const* const string, char const* const delim )
{
    unsigned counter = 0;
    char const* pos = string;
    while( pos != NULL )
    {
        if( ( pos = strstr( pos, delim ) ) != NULL )
        {
            pos++;
            counter++;
        }
    }

    return counter;
}

void tokens_remove_duplicate( char** const tokens, unsigned tokens_num )
{
    for( unsigned i = 0; i < tokens_num; i++ )
    {
        for( unsigned j = 0; j < tokens_num; j++ )
        {
            if( tokens[i] == NULL || tokens[j] == NULL || i == j )
                continue;

            if( strcmp( tokens[i], tokens[j] ) == 0 )
            {
                free( tokens[i] );
                tokens[i] = NULL;
            }
        }
    }
}

void tokens_split( char const* const string, char const* const delim, char** tokens )
{
    unsigned counter = 0;
    char const* pos, *lastpos;
    lastpos = string;
    pos = string + 1;

    while( pos != NULL )
    {
        if( ( pos = strstr( pos, delim ) ) != NULL )
        {
            *(tokens++) = strndup( lastpos, (unsigned long )( pos - lastpos ));
            lastpos = pos;
            pos++;
            counter++;
            continue;
        }

        *(tokens++) = strdup( lastpos );
    }
}

void tokens_free( char** tokens, unsigned tokens_number )
{
    for( unsigned i = 0; i < tokens_number; ++i )
    {
        free( tokens[ i ] );
    }
}

void tokens_print( char** tokens, unsigned tokens_number )
{
    for( unsigned i = 0; i < tokens_number; ++i )
    {
        if( tokens[i] == NULL )
            continue;
        printf( "%s ", tokens[i] );
    }
}

int main(void)
{
    char const* buf = "start-12-3.endstart-12-4.endstart-13-3.endstart-12-4.end";
    char const* const delim = "start";

    unsigned tokens_number = tokens_find_amount( buf, delim );
    char** tokens = malloc( tokens_number * sizeof( char* ) );
    tokens_split( buf, delim, tokens );

    tokens_remove_duplicate( tokens, tokens_number );
    tokens_print( tokens, tokens_number );

    tokens_free( tokens, tokens_number );
    free( tokens );

    return 0;
}