2005-06-06 08:59:54 +04:00
|
|
|
#include "cache.h"
|
2006-04-02 16:44:09 +04:00
|
|
|
#include "blob.h"
|
2009-01-10 15:07:50 +03:00
|
|
|
#include "dir.h"
|
2005-06-06 08:59:54 +04:00
|
|
|
|
2007-04-25 18:18:08 +04:00
|
|
|
static void create_directories(const char *path, const struct checkout *state)
|
2005-06-06 08:59:54 +04:00
|
|
|
{
|
|
|
|
int len = strlen(path);
|
|
|
|
char *buf = xmalloc(len + 1);
|
|
|
|
const char *slash = path;
|
|
|
|
|
|
|
|
while ((slash = strchr(slash+1, '/')) != NULL) {
|
|
|
|
len = slash - path;
|
|
|
|
memcpy(buf, path, len);
|
|
|
|
buf[len] = 0;
|
Do not expect unlink(2) to fail on a directory.
When "git checkout-index" checks out path A/B/C, it makes sure A
and A/B are truly directories; if there is a regular file or
symlink at A, we prefer to remove it.
We used to do this by catching an error return from mkdir(2),
and on EEXIST did unlink(2), and when it succeeded, tried
another mkdir(2).
Thomas Glanzmann found out the above does not work on Solaris
for a root user, as unlink(2) was so old fashioned there that it
allowed to unlink a directory.
As pointed out, this still doesn't guarantee that git won't call
"unlink()" on a directory (race conditions etc), but that's
fundamentally true (there is no "funlink()" like there is
"fstat()"), and besides, that is in no way git-specific (ie it's
true of any application that gets run as root).
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-07-18 09:58:28 +04:00
|
|
|
|
2009-01-18 18:14:52 +03:00
|
|
|
/*
|
|
|
|
* For 'checkout-index --prefix=<dir>', <dir> is
|
|
|
|
* allowed to be a symlink to an existing directory,
|
|
|
|
* and we set 'state->base_dir_len' below, such that
|
|
|
|
* we test the path components of the prefix with the
|
|
|
|
* stat() function instead of the lstat() function.
|
|
|
|
*/
|
2009-02-09 23:54:06 +03:00
|
|
|
if (has_dirs_only_path(buf, len, state->base_dir_len))
|
Do not expect unlink(2) to fail on a directory.
When "git checkout-index" checks out path A/B/C, it makes sure A
and A/B are truly directories; if there is a regular file or
symlink at A, we prefer to remove it.
We used to do this by catching an error return from mkdir(2),
and on EEXIST did unlink(2), and when it succeeded, tried
another mkdir(2).
Thomas Glanzmann found out the above does not work on Solaris
for a root user, as unlink(2) was so old fashioned there that it
allowed to unlink a directory.
As pointed out, this still doesn't guarantee that git won't call
"unlink()" on a directory (race conditions etc), but that's
fundamentally true (there is no "funlink()" like there is
"fstat()"), and besides, that is in no way git-specific (ie it's
true of any application that gets run as root).
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-07-18 09:58:28 +04:00
|
|
|
continue; /* ok, it is already a directory. */
|
|
|
|
|
|
|
|
/*
|
2009-01-18 18:14:52 +03:00
|
|
|
* If this mkdir() would fail, it could be that there
|
|
|
|
* is already a symlink or something else exists
|
|
|
|
* there, therefore we then try to unlink it and try
|
|
|
|
* one more time to create the directory.
|
Do not expect unlink(2) to fail on a directory.
When "git checkout-index" checks out path A/B/C, it makes sure A
and A/B are truly directories; if there is a regular file or
symlink at A, we prefer to remove it.
We used to do this by catching an error return from mkdir(2),
and on EEXIST did unlink(2), and when it succeeded, tried
another mkdir(2).
Thomas Glanzmann found out the above does not work on Solaris
for a root user, as unlink(2) was so old fashioned there that it
allowed to unlink a directory.
As pointed out, this still doesn't guarantee that git won't call
"unlink()" on a directory (race conditions etc), but that's
fundamentally true (there is no "funlink()" like there is
"fstat()"), and besides, that is in no way git-specific (ie it's
true of any application that gets run as root).
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-07-18 09:58:28 +04:00
|
|
|
*/
|
2005-07-06 12:21:46 +04:00
|
|
|
if (mkdir(buf, 0777)) {
|
Do not expect unlink(2) to fail on a directory.
When "git checkout-index" checks out path A/B/C, it makes sure A
and A/B are truly directories; if there is a regular file or
symlink at A, we prefer to remove it.
We used to do this by catching an error return from mkdir(2),
and on EEXIST did unlink(2), and when it succeeded, tried
another mkdir(2).
Thomas Glanzmann found out the above does not work on Solaris
for a root user, as unlink(2) was so old fashioned there that it
allowed to unlink a directory.
As pointed out, this still doesn't guarantee that git won't call
"unlink()" on a directory (race conditions etc), but that's
fundamentally true (there is no "funlink()" like there is
"fstat()"), and besides, that is in no way git-specific (ie it's
true of any application that gets run as root).
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-07-18 09:58:28 +04:00
|
|
|
if (errno == EEXIST && state->force &&
|
|
|
|
!unlink(buf) && !mkdir(buf, 0777))
|
|
|
|
continue;
|
2005-06-06 08:59:54 +04:00
|
|
|
die("cannot create directory at %s", buf);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
free(buf);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void remove_subtree(const char *path)
|
|
|
|
{
|
|
|
|
DIR *dir = opendir(path);
|
|
|
|
struct dirent *de;
|
|
|
|
char pathbuf[PATH_MAX];
|
|
|
|
char *name;
|
2007-06-07 11:04:01 +04:00
|
|
|
|
2005-06-06 08:59:54 +04:00
|
|
|
if (!dir)
|
2007-04-25 18:17:56 +04:00
|
|
|
die("cannot opendir %s (%s)", path, strerror(errno));
|
2005-06-06 08:59:54 +04:00
|
|
|
strcpy(pathbuf, path);
|
|
|
|
name = pathbuf + strlen(path);
|
|
|
|
*name++ = '/';
|
|
|
|
while ((de = readdir(dir)) != NULL) {
|
|
|
|
struct stat st;
|
2009-01-10 15:07:50 +03:00
|
|
|
if (is_dot_or_dotdot(de->d_name))
|
2005-06-06 08:59:54 +04:00
|
|
|
continue;
|
|
|
|
strcpy(name, de->d_name);
|
|
|
|
if (lstat(pathbuf, &st))
|
2007-04-25 18:17:56 +04:00
|
|
|
die("cannot lstat %s (%s)", pathbuf, strerror(errno));
|
2005-06-06 08:59:54 +04:00
|
|
|
if (S_ISDIR(st.st_mode))
|
|
|
|
remove_subtree(pathbuf);
|
|
|
|
else if (unlink(pathbuf))
|
2007-04-25 18:17:56 +04:00
|
|
|
die("cannot unlink %s (%s)", pathbuf, strerror(errno));
|
2005-06-06 08:59:54 +04:00
|
|
|
}
|
|
|
|
closedir(dir);
|
|
|
|
if (rmdir(path))
|
2007-04-25 18:17:56 +04:00
|
|
|
die("cannot rmdir %s (%s)", path, strerror(errno));
|
2005-06-06 08:59:54 +04:00
|
|
|
}
|
|
|
|
|
2005-07-14 20:58:45 +04:00
|
|
|
static int create_file(const char *path, unsigned int mode)
|
2005-06-06 08:59:54 +04:00
|
|
|
{
|
|
|
|
mode = (mode & 0100) ? 0777 : 0666;
|
2006-01-05 11:58:06 +03:00
|
|
|
return open(path, O_WRONLY | O_CREAT | O_EXCL, mode);
|
2005-06-06 08:59:54 +04:00
|
|
|
}
|
|
|
|
|
2007-04-13 20:26:04 +04:00
|
|
|
static void *read_blob_entry(struct cache_entry *ce, const char *path, unsigned long *size)
|
|
|
|
{
|
|
|
|
enum object_type type;
|
|
|
|
void *new = read_sha1_file(ce->sha1, &type, size);
|
|
|
|
|
|
|
|
if (new) {
|
|
|
|
if (type == OBJ_BLOB)
|
|
|
|
return new;
|
|
|
|
free(new);
|
|
|
|
}
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
2007-04-25 18:18:08 +04:00
|
|
|
static int write_entry(struct cache_entry *ce, char *path, const struct checkout *state, int to_tempfile)
|
2005-06-06 08:59:54 +04:00
|
|
|
{
|
|
|
|
int fd;
|
|
|
|
long wrote;
|
|
|
|
|
2008-01-15 03:03:17 +03:00
|
|
|
switch (ce->ce_mode & S_IFMT) {
|
Rewrite convert_to_{git,working_tree} to use strbuf's.
* Now, those functions take an "out" strbuf argument, where they store their
result if any. In that case, it also returns 1, else it returns 0.
* those functions support "in place" editing, in the sense that it's OK to
call them this way:
convert_to_git(path, sb->buf, sb->len, sb);
When doable, conversions are done in place for real, else the strbuf
content is just replaced with the new one, transparentely for the caller.
If you want to create a new filter working this way, being the accumulation
of filter1, filter2, ... filtern, then your meta_filter would be:
int meta_filter(..., const char *src, size_t len, struct strbuf *sb)
{
int ret = 0;
ret |= filter1(...., src, len, sb);
if (ret) {
src = sb->buf;
len = sb->len;
}
ret |= filter2(...., src, len, sb);
if (ret) {
src = sb->buf;
len = sb->len;
}
....
return ret | filtern(..., src, len, sb);
}
That's why subfilters the convert_to_* functions called were also rewritten
to work this way.
Signed-off-by: Pierre Habouzit <madcoder@debian.org>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-09-16 17:51:04 +04:00
|
|
|
char *new;
|
|
|
|
struct strbuf buf;
|
2007-04-22 04:38:00 +04:00
|
|
|
unsigned long size;
|
Lazy man's auto-CRLF
It currently does NOT know about file attributes, so it does its
conversion purely based on content. Maybe that is more in the "git
philosophy" anyway, since content is king, but I think we should try to do
the file attributes to turn it off on demand.
Anyway, BY DEFAULT it is off regardless, because it requires a
[core]
AutoCRLF = true
in your config file to be enabled. We could make that the default for
Windows, of course, the same way we do some other things (filemode etc).
But you can actually enable it on UNIX, and it will cause:
- "git update-index" will write blobs without CRLF
- "git diff" will diff working tree files without CRLF
- "git checkout" will write files to the working tree _with_ CRLF
and things work fine.
Funnily, it actually shows an odd file in git itself:
git clone -n git test-crlf
cd test-crlf
git config core.autocrlf true
git checkout
git diff
shows a diff for "Documentation/docbook-xsl.css". Why? Because we have
actually checked in that file *with* CRLF! So when "core.autocrlf" is
true, we'll always generate a *different* hash for it in the index,
because the index hash will be for the content _without_ CRLF.
Is this complete? I dunno. It seems to work for me. It doesn't use the
filename at all right now, and that's probably a deficiency (we could
certainly make the "is_binary()" heuristics also take standard filename
heuristics into account).
I don't pass in the filename at all for the "index_fd()" case
(git-update-index), so that would need to be passed around, but this
actually works fine.
NOTE NOTE NOTE! The "is_binary()" heuristics are totally made-up by yours
truly. I will not guarantee that they work at all reasonable. Caveat
emptor. But it _is_ simple, and it _is_ safe, since it's all off by
default.
The patch is pretty simple - the biggest part is the new "convert.c" file,
but even that is really just basic stuff that anybody can write in
"Teaching C 101" as a final project for their first class in programming.
Not to say that it's bug-free, of course - but at least we're not talking
about rocket surgery here.
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Junio C Hamano <junkio@cox.net>
2007-02-13 22:07:23 +03:00
|
|
|
|
2005-06-06 08:59:54 +04:00
|
|
|
case S_IFREG:
|
2007-04-13 20:26:04 +04:00
|
|
|
new = read_blob_entry(ce, path, &size);
|
|
|
|
if (!new)
|
2008-08-31 20:39:19 +04:00
|
|
|
return error("git checkout-index: unable to read sha1 file of %s (%s)",
|
2007-04-13 20:26:04 +04:00
|
|
|
path, sha1_to_hex(ce->sha1));
|
2007-08-14 12:41:02 +04:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Convert from git internal format to working tree format
|
|
|
|
*/
|
Rewrite convert_to_{git,working_tree} to use strbuf's.
* Now, those functions take an "out" strbuf argument, where they store their
result if any. In that case, it also returns 1, else it returns 0.
* those functions support "in place" editing, in the sense that it's OK to
call them this way:
convert_to_git(path, sb->buf, sb->len, sb);
When doable, conversions are done in place for real, else the strbuf
content is just replaced with the new one, transparentely for the caller.
If you want to create a new filter working this way, being the accumulation
of filter1, filter2, ... filtern, then your meta_filter would be:
int meta_filter(..., const char *src, size_t len, struct strbuf *sb)
{
int ret = 0;
ret |= filter1(...., src, len, sb);
if (ret) {
src = sb->buf;
len = sb->len;
}
ret |= filter2(...., src, len, sb);
if (ret) {
src = sb->buf;
len = sb->len;
}
....
return ret | filtern(..., src, len, sb);
}
That's why subfilters the convert_to_* functions called were also rewritten
to work this way.
Signed-off-by: Pierre Habouzit <madcoder@debian.org>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-09-16 17:51:04 +04:00
|
|
|
strbuf_init(&buf, 0);
|
|
|
|
if (convert_to_working_tree(ce->name, new, size, &buf)) {
|
2007-10-21 13:23:49 +04:00
|
|
|
size_t newsize = 0;
|
2007-08-14 12:41:02 +04:00
|
|
|
free(new);
|
2007-10-21 13:23:49 +04:00
|
|
|
new = strbuf_detach(&buf, &newsize);
|
|
|
|
size = newsize;
|
2007-08-14 12:41:02 +04:00
|
|
|
}
|
|
|
|
|
2006-03-05 11:24:15 +03:00
|
|
|
if (to_tempfile) {
|
|
|
|
strcpy(path, ".merge_file_XXXXXX");
|
|
|
|
fd = mkstemp(path);
|
|
|
|
} else
|
2008-01-15 03:03:17 +03:00
|
|
|
fd = create_file(path, ce->ce_mode);
|
2005-06-06 08:59:54 +04:00
|
|
|
if (fd < 0) {
|
|
|
|
free(new);
|
2008-08-31 20:39:19 +04:00
|
|
|
return error("git checkout-index: unable to create file %s (%s)",
|
2005-06-06 08:59:54 +04:00
|
|
|
path, strerror(errno));
|
|
|
|
}
|
Lazy man's auto-CRLF
It currently does NOT know about file attributes, so it does its
conversion purely based on content. Maybe that is more in the "git
philosophy" anyway, since content is king, but I think we should try to do
the file attributes to turn it off on demand.
Anyway, BY DEFAULT it is off regardless, because it requires a
[core]
AutoCRLF = true
in your config file to be enabled. We could make that the default for
Windows, of course, the same way we do some other things (filemode etc).
But you can actually enable it on UNIX, and it will cause:
- "git update-index" will write blobs without CRLF
- "git diff" will diff working tree files without CRLF
- "git checkout" will write files to the working tree _with_ CRLF
and things work fine.
Funnily, it actually shows an odd file in git itself:
git clone -n git test-crlf
cd test-crlf
git config core.autocrlf true
git checkout
git diff
shows a diff for "Documentation/docbook-xsl.css". Why? Because we have
actually checked in that file *with* CRLF! So when "core.autocrlf" is
true, we'll always generate a *different* hash for it in the index,
because the index hash will be for the content _without_ CRLF.
Is this complete? I dunno. It seems to work for me. It doesn't use the
filename at all right now, and that's probably a deficiency (we could
certainly make the "is_binary()" heuristics also take standard filename
heuristics into account).
I don't pass in the filename at all for the "index_fd()" case
(git-update-index), so that would need to be passed around, but this
actually works fine.
NOTE NOTE NOTE! The "is_binary()" heuristics are totally made-up by yours
truly. I will not guarantee that they work at all reasonable. Caveat
emptor. But it _is_ simple, and it _is_ safe, since it's all off by
default.
The patch is pretty simple - the biggest part is the new "convert.c" file,
but even that is really just basic stuff that anybody can write in
"Teaching C 101" as a final project for their first class in programming.
Not to say that it's bug-free, of course - but at least we're not talking
about rocket surgery here.
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Junio C Hamano <junkio@cox.net>
2007-02-13 22:07:23 +03:00
|
|
|
|
2007-01-08 18:58:23 +03:00
|
|
|
wrote = write_in_full(fd, new, size);
|
2005-06-06 08:59:54 +04:00
|
|
|
close(fd);
|
|
|
|
free(new);
|
|
|
|
if (wrote != size)
|
2008-08-31 20:39:19 +04:00
|
|
|
return error("git checkout-index: unable to write file %s", path);
|
2005-06-06 08:59:54 +04:00
|
|
|
break;
|
|
|
|
case S_IFLNK:
|
2007-04-13 20:26:04 +04:00
|
|
|
new = read_blob_entry(ce, path, &size);
|
|
|
|
if (!new)
|
2008-08-31 20:39:19 +04:00
|
|
|
return error("git checkout-index: unable to read sha1 file of %s (%s)",
|
2007-04-13 20:26:04 +04:00
|
|
|
path, sha1_to_hex(ce->sha1));
|
2007-03-03 00:11:30 +03:00
|
|
|
if (to_tempfile || !has_symlinks) {
|
|
|
|
if (to_tempfile) {
|
|
|
|
strcpy(path, ".merge_link_XXXXXX");
|
|
|
|
fd = mkstemp(path);
|
|
|
|
} else
|
|
|
|
fd = create_file(path, 0666);
|
2006-03-05 11:24:15 +03:00
|
|
|
if (fd < 0) {
|
|
|
|
free(new);
|
2008-08-31 20:39:19 +04:00
|
|
|
return error("git checkout-index: unable to create "
|
2006-03-05 11:24:15 +03:00
|
|
|
"file %s (%s)", path, strerror(errno));
|
|
|
|
}
|
2007-01-08 18:58:23 +03:00
|
|
|
wrote = write_in_full(fd, new, size);
|
2006-03-05 11:24:15 +03:00
|
|
|
close(fd);
|
|
|
|
free(new);
|
|
|
|
if (wrote != size)
|
2008-08-31 20:39:19 +04:00
|
|
|
return error("git checkout-index: unable to write file %s",
|
2006-03-05 11:24:15 +03:00
|
|
|
path);
|
|
|
|
} else {
|
|
|
|
wrote = symlink(new, path);
|
2005-06-06 08:59:54 +04:00
|
|
|
free(new);
|
2006-03-05 11:24:15 +03:00
|
|
|
if (wrote)
|
2008-08-31 20:39:19 +04:00
|
|
|
return error("git checkout-index: unable to create "
|
2006-03-05 11:24:15 +03:00
|
|
|
"symlink %s (%s)", path, strerror(errno));
|
2005-06-06 08:59:54 +04:00
|
|
|
}
|
|
|
|
break;
|
2007-05-22 00:08:28 +04:00
|
|
|
case S_IFGITLINK:
|
2007-04-13 20:26:04 +04:00
|
|
|
if (to_tempfile)
|
2008-08-31 20:39:19 +04:00
|
|
|
return error("git checkout-index: cannot create temporary subproject %s", path);
|
2007-04-13 20:26:04 +04:00
|
|
|
if (mkdir(path, 0777) < 0)
|
2008-08-31 20:39:19 +04:00
|
|
|
return error("git checkout-index: cannot create subproject directory %s", path);
|
2007-04-13 20:26:04 +04:00
|
|
|
break;
|
2005-06-06 08:59:54 +04:00
|
|
|
default:
|
2008-08-31 20:39:19 +04:00
|
|
|
return error("git checkout-index: unknown file mode for %s", path);
|
2005-06-06 08:59:54 +04:00
|
|
|
}
|
|
|
|
|
2005-06-06 10:15:40 +04:00
|
|
|
if (state->refresh_cache) {
|
2005-06-06 08:59:54 +04:00
|
|
|
struct stat st;
|
|
|
|
lstat(ce->name, &st);
|
|
|
|
fill_stat_cache_info(ce, &st);
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2007-04-25 18:18:08 +04:00
|
|
|
int checkout_entry(struct cache_entry *ce, const struct checkout *state, char *topath)
|
2005-06-06 08:59:54 +04:00
|
|
|
{
|
2006-08-26 18:09:17 +04:00
|
|
|
static char path[PATH_MAX + 1];
|
2006-03-05 11:24:15 +03:00
|
|
|
struct stat st;
|
2005-06-06 08:59:54 +04:00
|
|
|
int len = state->base_dir_len;
|
|
|
|
|
2006-03-05 11:24:15 +03:00
|
|
|
if (topath)
|
|
|
|
return write_entry(ce, topath, state, 1);
|
|
|
|
|
2005-06-06 08:59:54 +04:00
|
|
|
memcpy(path, state->base_dir, len);
|
|
|
|
strcpy(path + len, ce->name);
|
|
|
|
|
|
|
|
if (!lstat(path, &st)) {
|
2007-11-10 11:15:03 +03:00
|
|
|
unsigned changed = ce_match_stat(ce, &st, CE_MATCH_IGNORE_VALID);
|
2005-06-06 08:59:54 +04:00
|
|
|
if (!changed)
|
|
|
|
return 0;
|
|
|
|
if (!state->force) {
|
|
|
|
if (!state->quiet)
|
2005-09-08 04:26:23 +04:00
|
|
|
fprintf(stderr, "git-checkout-index: %s already exists\n", path);
|
2005-10-03 23:44:48 +04:00
|
|
|
return -1;
|
2005-06-06 08:59:54 +04:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* We unlink the old file, to get the new one with the
|
|
|
|
* right permissions (including umask, which is nasty
|
|
|
|
* to emulate by hand - much easier to let the system
|
|
|
|
* just do the right thing)
|
|
|
|
*/
|
2005-07-14 20:58:45 +04:00
|
|
|
if (S_ISDIR(st.st_mode)) {
|
2007-04-13 20:26:04 +04:00
|
|
|
/* If it is a gitlink, leave it alone! */
|
2008-01-15 03:03:17 +03:00
|
|
|
if (S_ISGITLINK(ce->ce_mode))
|
2007-04-13 20:26:04 +04:00
|
|
|
return 0;
|
2005-07-14 20:58:45 +04:00
|
|
|
if (!state->force)
|
|
|
|
return error("%s is a directory", path);
|
|
|
|
remove_subtree(path);
|
2008-03-17 18:56:27 +03:00
|
|
|
} else if (unlink(path))
|
|
|
|
return error("unable to unlink old '%s' (%s)", path, strerror(errno));
|
2006-03-05 11:24:15 +03:00
|
|
|
} else if (state->not_new)
|
2005-06-06 08:59:54 +04:00
|
|
|
return 0;
|
|
|
|
create_directories(path, state);
|
2006-03-05 11:24:15 +03:00
|
|
|
return write_entry(ce, path, state, 0);
|
2005-06-06 08:59:54 +04:00
|
|
|
}
|