sbase/du.c

113 lines
2.0 KiB
C
Raw Normal View History

/* See LICENSE file for copyright and license details. */
2015-02-14 15:02:41 -05:00
#include <sys/stat.h>
#include <sys/types.h>
#include <errno.h>
#include <limits.h>
#include <stdint.h>
#include <stdlib.h>
#include <stdio.h>
#include "fs.h"
#include "util.h"
static size_t maxdepth = SIZE_MAX;
static size_t blksize = 512;
static int aflag = 0;
static int sflag = 0;
static int hflag = 0;
2014-01-23 16:16:05 -05:00
static void
printpath(size_t n, const char *path)
{
if (hflag)
printf("%s\t%s\n", humansize(n * blksize), path);
else
printf("%zu\t%s\n", n, path);
}
static size_t
nblks(blkcnt_t blocks)
{
return (512 * blocks + blksize - 1) / blksize;
}
void
Refactor recurse() again Okay, why yet another recurse()-refactor? The last one added the recursor-struct, which simplified things on the user-end, but there was still one thing that bugged me a lot: Previously, all fn()'s were forced to (l)stat the paths themselves. This does not work well when you try to keep up with H-, L- and P- flags at the same time, as each utility-function would have to set the right function-pointer for (l)stat every single time. This is not desirable. Furthermore, recurse should be easy to use and not involve trouble finding the right (l)stat-function to do it right. So, what we needed was a stat-argument for each fn(), so it is directly accessible. This was impossible to do though when the fn()'s are still directly called by the programs to "start" the recurse. Thus, the fundamental change is to make recurse() the function to go, while designing the fn()'s in a way they can "live" with st being NULL (we don't want a null-pointer-deref). What you can see in this commit is the result of this work. Why all this trouble instead of using nftw? The special thing about recurse() is that you tell the function when to recurse() in your fn(). You don't need special flags to tell nftw() to skip the subtree, just to give an example. The only single downside to this is that now, you are not allowed to unconditionally call recurse() from your fn(). It has to be a directory. However, that is a cost I think is easily weighed up by the advantages. Another thing is the history: I added a procedure at the end of the outmost recurse to free the history. This way we don't leak memory. A simple optimization on the side: - if (h->dev == st.st_dev && h->ino == st.st_ino) + if (h->ino == st.st_ino && h->dev == st.st_dev) First compare the likely difference in inode-numbers instead of checking the unlikely condition that the device-numbers are different.
2015-03-18 19:53:42 -04:00
du(const char *path, struct stat *st, void *total, struct recursor *r)
{
size_t subtotal = 0;
Refactor recurse() again Okay, why yet another recurse()-refactor? The last one added the recursor-struct, which simplified things on the user-end, but there was still one thing that bugged me a lot: Previously, all fn()'s were forced to (l)stat the paths themselves. This does not work well when you try to keep up with H-, L- and P- flags at the same time, as each utility-function would have to set the right function-pointer for (l)stat every single time. This is not desirable. Furthermore, recurse should be easy to use and not involve trouble finding the right (l)stat-function to do it right. So, what we needed was a stat-argument for each fn(), so it is directly accessible. This was impossible to do though when the fn()'s are still directly called by the programs to "start" the recurse. Thus, the fundamental change is to make recurse() the function to go, while designing the fn()'s in a way they can "live" with st being NULL (we don't want a null-pointer-deref). What you can see in this commit is the result of this work. Why all this trouble instead of using nftw? The special thing about recurse() is that you tell the function when to recurse() in your fn(). You don't need special flags to tell nftw() to skip the subtree, just to give an example. The only single downside to this is that now, you are not allowed to unconditionally call recurse() from your fn(). It has to be a directory. However, that is a cost I think is easily weighed up by the advantages. Another thing is the history: I added a procedure at the end of the outmost recurse to free the history. This way we don't leak memory. A simple optimization on the side: - if (h->dev == st.st_dev && h->ino == st.st_ino) + if (h->ino == st.st_ino && h->dev == st.st_dev) First compare the likely difference in inode-numbers instead of checking the unlikely condition that the device-numbers are different.
2015-03-18 19:53:42 -04:00
if (st && S_ISDIR(st->st_mode))
recurse(path, &subtotal, r);
Refactor recurse() again Okay, why yet another recurse()-refactor? The last one added the recursor-struct, which simplified things on the user-end, but there was still one thing that bugged me a lot: Previously, all fn()'s were forced to (l)stat the paths themselves. This does not work well when you try to keep up with H-, L- and P- flags at the same time, as each utility-function would have to set the right function-pointer for (l)stat every single time. This is not desirable. Furthermore, recurse should be easy to use and not involve trouble finding the right (l)stat-function to do it right. So, what we needed was a stat-argument for each fn(), so it is directly accessible. This was impossible to do though when the fn()'s are still directly called by the programs to "start" the recurse. Thus, the fundamental change is to make recurse() the function to go, while designing the fn()'s in a way they can "live" with st being NULL (we don't want a null-pointer-deref). What you can see in this commit is the result of this work. Why all this trouble instead of using nftw? The special thing about recurse() is that you tell the function when to recurse() in your fn(). You don't need special flags to tell nftw() to skip the subtree, just to give an example. The only single downside to this is that now, you are not allowed to unconditionally call recurse() from your fn(). It has to be a directory. However, that is a cost I think is easily weighed up by the advantages. Another thing is the history: I added a procedure at the end of the outmost recurse to free the history. This way we don't leak memory. A simple optimization on the side: - if (h->dev == st.st_dev && h->ino == st.st_ino) + if (h->ino == st.st_ino && h->dev == st.st_dev) First compare the likely difference in inode-numbers instead of checking the unlikely condition that the device-numbers are different.
2015-03-18 19:53:42 -04:00
*((size_t *)total) += subtotal + nblks(st ? st->st_blocks : 0);
Refactor recurse() again Okay, why yet another recurse()-refactor? The last one added the recursor-struct, which simplified things on the user-end, but there was still one thing that bugged me a lot: Previously, all fn()'s were forced to (l)stat the paths themselves. This does not work well when you try to keep up with H-, L- and P- flags at the same time, as each utility-function would have to set the right function-pointer for (l)stat every single time. This is not desirable. Furthermore, recurse should be easy to use and not involve trouble finding the right (l)stat-function to do it right. So, what we needed was a stat-argument for each fn(), so it is directly accessible. This was impossible to do though when the fn()'s are still directly called by the programs to "start" the recurse. Thus, the fundamental change is to make recurse() the function to go, while designing the fn()'s in a way they can "live" with st being NULL (we don't want a null-pointer-deref). What you can see in this commit is the result of this work. Why all this trouble instead of using nftw? The special thing about recurse() is that you tell the function when to recurse() in your fn(). You don't need special flags to tell nftw() to skip the subtree, just to give an example. The only single downside to this is that now, you are not allowed to unconditionally call recurse() from your fn(). It has to be a directory. However, that is a cost I think is easily weighed up by the advantages. Another thing is the history: I added a procedure at the end of the outmost recurse to free the history. This way we don't leak memory. A simple optimization on the side: - if (h->dev == st.st_dev && h->ino == st.st_ino) + if (h->ino == st.st_ino && h->dev == st.st_dev) First compare the likely difference in inode-numbers instead of checking the unlikely condition that the device-numbers are different.
2015-03-18 19:53:42 -04:00
if (!sflag && r->depth <= maxdepth && r->depth && st && (S_ISDIR(st->st_mode) || aflag))
printpath(subtotal + nblks(st->st_blocks), path);
}
static void
usage(void)
{
2015-02-18 12:24:21 -05:00
eprintf("usage: %s [-a | -s] [-d depth] [-h] [-k] [-H | -L | -P] [-x] [file ...]\n", argv0);
}
int
main(int argc, char *argv[])
{
struct recursor r = { .fn = du, .hist = NULL, .depth = 0, .follow = 'P', .flags = 0};
size_t n = 0;
int kflag = 0, dflag = 0;
char *bsize;
ARGBEGIN {
case 'a':
aflag = 1;
break;
case 'd':
dflag = 1;
maxdepth = estrtonum(EARGF(usage()), 0, MIN(LLONG_MAX, SIZE_MAX));
break;
case 'h':
hflag = 1;
break;
case 'k':
kflag = 1;
break;
case 's':
sflag = 1;
break;
case 'x':
r.flags |= SAMEDEV;
break;
case 'H':
case 'L':
case 'P':
r.follow = ARGC();
2015-02-18 12:24:21 -05:00
break;
default:
usage();
} ARGEND;
if ((aflag && sflag) || (dflag && sflag))
usage();
bsize = getenv("BLOCKSIZE");
if (bsize)
blksize = estrtonum(bsize, 1, MIN(LLONG_MAX, SIZE_MAX));
if (kflag)
blksize = 1024;
if (!argc) {
Refactor recurse() again Okay, why yet another recurse()-refactor? The last one added the recursor-struct, which simplified things on the user-end, but there was still one thing that bugged me a lot: Previously, all fn()'s were forced to (l)stat the paths themselves. This does not work well when you try to keep up with H-, L- and P- flags at the same time, as each utility-function would have to set the right function-pointer for (l)stat every single time. This is not desirable. Furthermore, recurse should be easy to use and not involve trouble finding the right (l)stat-function to do it right. So, what we needed was a stat-argument for each fn(), so it is directly accessible. This was impossible to do though when the fn()'s are still directly called by the programs to "start" the recurse. Thus, the fundamental change is to make recurse() the function to go, while designing the fn()'s in a way they can "live" with st being NULL (we don't want a null-pointer-deref). What you can see in this commit is the result of this work. Why all this trouble instead of using nftw? The special thing about recurse() is that you tell the function when to recurse() in your fn(). You don't need special flags to tell nftw() to skip the subtree, just to give an example. The only single downside to this is that now, you are not allowed to unconditionally call recurse() from your fn(). It has to be a directory. However, that is a cost I think is easily weighed up by the advantages. Another thing is the history: I added a procedure at the end of the outmost recurse to free the history. This way we don't leak memory. A simple optimization on the side: - if (h->dev == st.st_dev && h->ino == st.st_ino) + if (h->ino == st.st_ino && h->dev == st.st_dev) First compare the likely difference in inode-numbers instead of checking the unlikely condition that the device-numbers are different.
2015-03-18 19:53:42 -04:00
recurse(".", &n, &r);
printpath(nblks(n), ".");
} else {
for (; *argv; argc--, argv++) {
Refactor recurse() again Okay, why yet another recurse()-refactor? The last one added the recursor-struct, which simplified things on the user-end, but there was still one thing that bugged me a lot: Previously, all fn()'s were forced to (l)stat the paths themselves. This does not work well when you try to keep up with H-, L- and P- flags at the same time, as each utility-function would have to set the right function-pointer for (l)stat every single time. This is not desirable. Furthermore, recurse should be easy to use and not involve trouble finding the right (l)stat-function to do it right. So, what we needed was a stat-argument for each fn(), so it is directly accessible. This was impossible to do though when the fn()'s are still directly called by the programs to "start" the recurse. Thus, the fundamental change is to make recurse() the function to go, while designing the fn()'s in a way they can "live" with st being NULL (we don't want a null-pointer-deref). What you can see in this commit is the result of this work. Why all this trouble instead of using nftw? The special thing about recurse() is that you tell the function when to recurse() in your fn(). You don't need special flags to tell nftw() to skip the subtree, just to give an example. The only single downside to this is that now, you are not allowed to unconditionally call recurse() from your fn(). It has to be a directory. However, that is a cost I think is easily weighed up by the advantages. Another thing is the history: I added a procedure at the end of the outmost recurse to free the history. This way we don't leak memory. A simple optimization on the side: - if (h->dev == st.st_dev && h->ino == st.st_ino) + if (h->ino == st.st_ino && h->dev == st.st_dev) First compare the likely difference in inode-numbers instead of checking the unlikely condition that the device-numbers are different.
2015-03-18 19:53:42 -04:00
recurse(*argv, &n, &r);
printpath(n, *argv);
}
}
Refactor recurse() again Okay, why yet another recurse()-refactor? The last one added the recursor-struct, which simplified things on the user-end, but there was still one thing that bugged me a lot: Previously, all fn()'s were forced to (l)stat the paths themselves. This does not work well when you try to keep up with H-, L- and P- flags at the same time, as each utility-function would have to set the right function-pointer for (l)stat every single time. This is not desirable. Furthermore, recurse should be easy to use and not involve trouble finding the right (l)stat-function to do it right. So, what we needed was a stat-argument for each fn(), so it is directly accessible. This was impossible to do though when the fn()'s are still directly called by the programs to "start" the recurse. Thus, the fundamental change is to make recurse() the function to go, while designing the fn()'s in a way they can "live" with st being NULL (we don't want a null-pointer-deref). What you can see in this commit is the result of this work. Why all this trouble instead of using nftw? The special thing about recurse() is that you tell the function when to recurse() in your fn(). You don't need special flags to tell nftw() to skip the subtree, just to give an example. The only single downside to this is that now, you are not allowed to unconditionally call recurse() from your fn(). It has to be a directory. However, that is a cost I think is easily weighed up by the advantages. Another thing is the history: I added a procedure at the end of the outmost recurse to free the history. This way we don't leak memory. A simple optimization on the side: - if (h->dev == st.st_dev && h->ino == st.st_ino) + if (h->ino == st.st_ino && h->dev == st.st_dev) First compare the likely difference in inode-numbers instead of checking the unlikely condition that the device-numbers are different.
2015-03-18 19:53:42 -04:00
return recurse_status;
}