I want to calculate the size of the directory (path) recursively. In my current code I have a function that identifies if it's a directory or file, if it's a directory it calls the function with the subdirectory (file) and if it's a file it adds to the totalSize variable. However, my current code doesn't return anything meaning that there is an error somewhere. here is my code -

#include <sys/types.h>
#include <dirent.h>
#include <stdio.h>
#include <errno.h>
#include <unistd.h>
#include <sys/stat.h>

void getsize(const char *path,int* totalSize);

int main()
{
    int total = 0;
    char path [] = "C:\\Users\\abbas\\Desktop\\Leetcode airplane";
    getsize(path,&total);
    printf("%d",total);
    return total;

}


void getsize(const char *path,int* totalSize)
{
    struct dirent *pDirent;
    struct stat buf;
    struct stat info;
    DIR *pDir;
    int exists;
    char str[100];
    pDir = opendir (path);
    while ((pDirent = readdir(pDir)) != NULL)
    {
        stat(pDirent->d_name,&info);
        if(S_ISDIR(info.st_mode))
        {
            strcpy(str,path);
            strcat(str,"/");
            strcat(str,pDirent->d_name);
            getsize(str,totalSize);
        }
        else
        {
            strcpy(str,path);
            strcat(str,"/");
            strcat(str,pDirent->d_name);
            exists = stat(str,&buf);
            if (exists < 0)
            {
                continue;
            }
            else
            {
                (*totalSize)  = buf.st_size;
            }

        }
    }
    closedir(pDir);
}

CodePudding user response：

I think the major error of your code lies in the recursive logic.

To quote pp.183 of The C Programming Language:

Each directory always contains entries for itself, called ".", and its parent, ".."; these must be skipped, or the program will loop forever.

Therefore, maybe you can try adding the following if test at the beginning of the while loop:

while ((pDirent = readdir(pDir)) != NULL)
{
    if (strcmp(pDirent->d_name, ".") == 0
        || strcmp(pDirent->d_name, "..") == 0)
        continue;  /* skip self and parent */
    /* ... */
}

Still, there might be other errors, but I think this one is the most significant.

CodePudding user response：

1. Include string.h.
2. The arbitrary fixed sizestr[100] is problematic. If you are on Linux include linux/limits.h and use str[PATH_MAX]. Sorry, I don't have a way of testing Windows for you but I understand it has a PATH_MAX as well. Apparently it's still flawed so maybe add size checks as well, or give up on fixed strings and realloc() a dynamic one instead?
3. You need to exclude . and .. otherwise you end up with an infinite loop (path/../path/..).
4. stat(pDirent->d_name,&info) fails as you need to stat() path/pDirect->d_name not just pDirect->d_name.
5. (not fixed) Maybe snprintf(path2, "%s%s%s", path, PATH_SEP, pDirenv->d_name) instead of strcpy() and strcat()?
6. Check return values of functions otherwise you are wasting time.
7. No point of doing two stat() calls on the same path so just use (*totalSize) = buf.st_size;.
8. I assume you only want the size of files.
9. (not fixed) It would be more natural if getsize() returned the size instead of using int *totalSize out parameter.
10. (not fixed) Consider using nftw() (or the older ftw()) to walk the tree.

Note that program now accept path via command line for testing purposes.

#include <dirent.h>
#include <errno.h>
#include <linux/limits.h>
#include <stdio.h>
#include <string.h>
#include <sys/stat.h>
#include <sys/types.h>
#include <unistd.h>

const char PATH_SEP =
#ifdef _WIN32
    "\\";
#else
     "/";
#endif

void getsize(const char *path,int *totalSize) {
    struct dirent *pDirent;
    DIR *pDir = opendir (path);
    while ((pDirent = readdir(pDir)) != NULL) {
        if(
            !strcmp(pDirent->d_name, ".") ||
            !strcmp(pDirent->d_name, "..")
        )
            continue;

        char path2[PATH_MAX];
        strcpy(path2, path);
        strcat(path2, PATH_SEP);
        strcat(path2, pDirent->d_name);
        struct stat info;
        if(stat(path2, &info) == -1) {
            perror("stat");
            return;
        }
        if(S_ISDIR(info.st_mode))
            getsize(path2, totalSize);
        else if(S_ISREG(info.st_mode))
            (*totalSize)  = info.st_size;
    }
    closedir(pDir);
}

int main(argc, char *argv[]) {
    if(argc != 2) {
        printf("usage: your_program path\n");
        return 1;
    }
    int total = 0;
    getsize(argv[1], &total);
    printf("%d\n",total);
}

and example test:

$ mkdir -p 1/2
$ dd if=/dev/zero of=1/file count=123
123 0 records in
123 0 records out
62976 bytes (63 kB, 62 KiB) copied, 0.000336838 s, 187 MB/s
$ dd if=/dev/zero of=1/2/file count=234
234 0 records in
234 0 records out
119808 bytes (120 kB, 117 KiB) copied, 0.0015842 s, 75.6 MB/s
$ echo $((62976   119808))
182784
$ ./your_program 1
182784