从没有最大缓冲区长度的C中的stdin读取

Question

The following code sets a maximum line size read from stdin. I'd rather not hard-code a specific line length, and have the flexibility to handle any buffer length. What are good strategies to allow processing of any size?

If these strategies are much more complex, is there a way to at least guarantee that getline will not overflow? Thanks.

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

 #define P 20

 int main()
 {
   size_t size = 1920;
   char *line;
   // record row; /* structure to store fields */
   char tokens[P][41];
   int p;
   char delims[] = ",";     /* ", |" */
   char *result = NULL;

   line = ( char * ) malloc( size + 1 );

   while( getline(&line, &size, stdin) != -1 )
   {
      /* chomp */
      line[strlen(line)-1] = '\0';

      /* load char array */
      result = strtok( line , delims );
      p = 0;
      while( result != NULL && ( p < P ) ) 
      {
         strcpy( tokens[p++] , result );
         result = strtok( NULL, delims );
      }

      if (p != P)
      {
         fprintf(stderr,"Wrong number of input fields.\nFormat: ID,x1, ... ,x%d\n",P);
     exit(-1);
      }

      /* load record ( atol, atof etc... , skipped for brevity ) and work with record */

      return 0;
 }

Answer 1

You can have getline allocate memory for you (which is the whole point of using the non-standard getline function over the standard fgets function ). From the getline manual page:

If *lineptr is NULL , then getline() will allocate a buffer for storing the line, which should be freed by the user program. (The value in *n is ignored.)

Alternatively, before calling getline() , *lineptr can contain a pointer to a malloc -allocated buffer *n bytes in size. If the buffer is not large enough to hold the line, getline() resizes it with realloc , updating *lineptr and *n as necessary.

So you can do:

line = NULL;
while (getline(&line, &size, stdin))
{
    // ... Do stuff with `line`...
}
free(line);

(Or leave your code as-is, since getline will resize your allocated buffer for you.)

Answer 2

Here's the code I've been using - Fgetstr(FILE*, const char*). It roughly doubles the buffer size for each realloc, and won't crash on a failed malloc/realloc. Called like: char *text = Fgetstr(stdin, "\\n"); or whatever.

The library getdelim() function is similar, although mine might be much older. The manpage on getline and getdelim doesn't detail what happens if the malloc and realloc fail on my system, and only mention a possible error EINVAL (no ENOMEM). Hence, the behavior in the face of memory exhaustion may be undefined for getline/getdelim.

Also, as starrify points out, many systems don't have getline.

#include <sys/types.h>
#include <stdio.h>
#include <string.h>
#include <malloc.h>

#ifdef TEST
#define DEBUG
#endif

#ifdef DEBUG
#undef DEBUG
#define DEBUG(b) {b}
#else
#define DEBUG(b)  
#endif

#ifdef TEST
int main (int argc, char **argv)
{
    char *text = (char*)0;
    char *ends = "\n";

    if(argc > 1) ends = argv[1];

    while(text = Fgetstr(stdin, ends))
    {
        puts(text);
        free(text);
    }

    return 0;
}
#endif

/*  return specifications -
 *
 *  terminators include : ends, \0, and EOF
 *
 *  root    EOF?    text?   ended?  stat    returned value
 *          -       -       -       ... 
 *  1       -       -       1       return  ""
 *          -       1       -       ... 
 *  2       -       1       1       return  "text"
 *  3       1       -       -       return  -null-      EOF-*accepted*
 *  4       1       -       1       return  ""          EOF-postponed
 *  5       1       1       -       return  "text"      EOF-postponed/fake-end
 *  6       1       1       1       return  "text"      EOF-postponed/true-end
 *
 *  on ENOMEM, return -null-
 *
 */

static char *Fgetstr_R(FILE *ifp, const char *ends, unsigned int offset)
{
    char *s = (char*)0;                     /* the crucial string to return */
    unsigned int bufmax = offset;           /* as large as so far */
    unsigned int bufidx = 0;                /* index within buffer */
    char buffer[bufmax + 1];                /* on-stack allocation required */
    int ended = 0;                          /* end character seen ? */
    int eof = 0;                            /* e-o-f seen ? */

    DEBUG(fprintf(stderr, "(%d", offset););

    while(bufidx <= bufmax)     /* pre-recurse - attempt to fill buffer */
    {
        int c = getc(ifp);

        if( (ended = ( !c || (ends && strchr(ends,c)))) || (eof = (EOF==c)) )  
            break;

        buffer[bufidx++] = (char)c;
    }

    /* note - the buffer *must* at least have room for the terminal \0 */

    if(ended || (eof && offset))                    /* root 1,2,4,6 5 */
    {
        unsigned int offset_max = offset + bufidx;
        DEBUG(fprintf(stderr, " malloc %d", offset_max + 1););
        if(s = (char*)malloc((offset_max + 1) * sizeof(char)))
            s[offset_max] = '\0';
        else
            s = (char*)0, perror("Fgetstr_R - malloc");
    }
    else
    {
        if(eof && !offset)  /* && !ended */     /* root 3 */
            s = (char*)0;
        else
            s = Fgetstr_R(ifp, ends, offset + bufidx);  /* recurse */
    }

    /* post-recurse */

    if(s)
        strncpy(&s[offset], &buffer[0], bufidx);  /* cnv. idx to count */

    DEBUG(fprintf(stderr, ")", offset););
    return s;
}

char *Fgetstr (FILE *ifp, const char *ends)
{
    register char *s = (char*)0;
    DEBUG(fprintf(stderr, "Fgetstr "););
    s = Fgetstr_R(ifp, ends, 0);
    DEBUG(fprintf(stderr, ".\n"););
    return s;
}