2006-05-17 04:02:14 +02:00
|
|
|
/*
|
|
|
|
* This handles recursive filename detection with exclude
|
|
|
|
* files, index knowledge etc..
|
|
|
|
*
|
|
|
|
* Copyright (C) Linus Torvalds, 2005-2006
|
|
|
|
* Junio Hamano, 2005-2006
|
|
|
|
*/
|
|
|
|
#include "cache.h"
|
|
|
|
#include "dir.h"
|
2007-04-11 23:49:44 +02:00
|
|
|
#include "refs.h"
|
2006-05-17 04:02:14 +02:00
|
|
|
|
Optimize directory listing with pathspec limiter.
The way things are set up, you can now pass a "pathspec" to the
"read_directory()" function. If you pass NULL, it acts exactly
like it used to do (read everything). If you pass a non-NULL
pointer, it will simplify it into a "these are the prefixes
without any special characters", and stop any readdir() early if
the path in question doesn't match any of the prefixes.
NOTE! This does *not* obviate the need for the caller to do the *exact*
pathspec match later. It's a first-level filter on "read_directory()", but
it does not do the full pathspec thing. Maybe it should. But in the
meantime, builtin-add.c really does need to do first
read_directory(dir, .., pathspec);
if (pathspec)
prune_directory(dir, pathspec, baselen);
ie the "prune_directory()" part will do the *exact* pathspec pruning,
while the "read_directory()" will use the pathspec just to do some quick
high-level pruning of the directories it will recurse into.
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Junio C Hamano <junkio@cox.net>
2007-03-31 05:39:30 +02:00
|
|
|
struct path_simplify {
|
|
|
|
int len;
|
|
|
|
const char *path;
|
|
|
|
};
|
|
|
|
|
2007-04-11 23:49:44 +02:00
|
|
|
static int read_directory_recursive(struct dir_struct *dir,
|
|
|
|
const char *path, const char *base, int baselen,
|
|
|
|
int check_only, const struct path_simplify *simplify);
|
|
|
|
|
2006-05-20 01:07:51 +02:00
|
|
|
int common_prefix(const char **pathspec)
|
|
|
|
{
|
|
|
|
const char *path, *slash, *next;
|
|
|
|
int prefix;
|
|
|
|
|
|
|
|
if (!pathspec)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
path = *pathspec;
|
|
|
|
slash = strrchr(path, '/');
|
|
|
|
if (!slash)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
prefix = slash - path + 1;
|
|
|
|
while ((next = *++pathspec) != NULL) {
|
|
|
|
int len = strlen(next);
|
2007-04-23 10:21:25 +02:00
|
|
|
if (len >= prefix && !memcmp(path, next, prefix))
|
2006-05-20 01:07:51 +02:00
|
|
|
continue;
|
2007-04-23 10:21:25 +02:00
|
|
|
len = prefix - 1;
|
2006-05-20 01:07:51 +02:00
|
|
|
for (;;) {
|
|
|
|
if (!len)
|
|
|
|
return 0;
|
|
|
|
if (next[--len] != '/')
|
|
|
|
continue;
|
|
|
|
if (memcmp(path, next, len+1))
|
|
|
|
continue;
|
|
|
|
prefix = len + 1;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return prefix;
|
|
|
|
}
|
|
|
|
|
2006-12-25 12:09:52 +01:00
|
|
|
/*
|
|
|
|
* Does 'match' matches the given name?
|
|
|
|
* A match is found if
|
|
|
|
*
|
|
|
|
* (1) the 'match' string is leading directory of 'name', or
|
|
|
|
* (2) the 'match' string is a wildcard and matches 'name', or
|
|
|
|
* (3) the 'match' string is exactly the same as 'name'.
|
|
|
|
*
|
|
|
|
* and the return value tells which case it was.
|
|
|
|
*
|
|
|
|
* It returns 0 when there is no match.
|
|
|
|
*/
|
2006-05-20 01:07:51 +02:00
|
|
|
static int match_one(const char *match, const char *name, int namelen)
|
|
|
|
{
|
|
|
|
int matchlen;
|
|
|
|
|
|
|
|
/* If the match was just the prefix, we matched */
|
|
|
|
matchlen = strlen(match);
|
|
|
|
if (!matchlen)
|
2006-12-25 12:09:52 +01:00
|
|
|
return MATCHED_RECURSIVELY;
|
2006-05-20 01:07:51 +02:00
|
|
|
|
|
|
|
/*
|
|
|
|
* If we don't match the matchstring exactly,
|
|
|
|
* we need to match by fnmatch
|
|
|
|
*/
|
|
|
|
if (strncmp(match, name, matchlen))
|
2006-12-25 12:09:52 +01:00
|
|
|
return !fnmatch(match, name, 0) ? MATCHED_FNMATCH : 0;
|
2006-05-20 01:07:51 +02:00
|
|
|
|
2006-12-25 12:09:52 +01:00
|
|
|
if (!name[matchlen])
|
|
|
|
return MATCHED_EXACTLY;
|
|
|
|
if (match[matchlen-1] == '/' || name[matchlen] == '/')
|
|
|
|
return MATCHED_RECURSIVELY;
|
|
|
|
return 0;
|
2006-05-20 01:07:51 +02:00
|
|
|
}
|
|
|
|
|
2006-12-25 12:09:52 +01:00
|
|
|
/*
|
|
|
|
* Given a name and a list of pathspecs, see if the name matches
|
|
|
|
* any of the pathspecs. The caller is also interested in seeing
|
|
|
|
* all pathspec matches some names it calls this function with
|
|
|
|
* (otherwise the user could have mistyped the unmatched pathspec),
|
|
|
|
* and a mark is left in seen[] array for pathspec element that
|
|
|
|
* actually matched anything.
|
|
|
|
*/
|
2006-05-20 01:07:51 +02:00
|
|
|
int match_pathspec(const char **pathspec, const char *name, int namelen, int prefix, char *seen)
|
|
|
|
{
|
|
|
|
int retval;
|
|
|
|
const char *match;
|
|
|
|
|
|
|
|
name += prefix;
|
|
|
|
namelen -= prefix;
|
|
|
|
|
|
|
|
for (retval = 0; (match = *pathspec++) != NULL; seen++) {
|
2006-12-25 12:09:52 +01:00
|
|
|
int how;
|
|
|
|
if (retval && *seen == MATCHED_EXACTLY)
|
2006-05-20 01:07:51 +02:00
|
|
|
continue;
|
|
|
|
match += prefix;
|
2006-12-25 12:09:52 +01:00
|
|
|
how = match_one(match, name, namelen);
|
|
|
|
if (how) {
|
|
|
|
if (retval < how)
|
|
|
|
retval = how;
|
|
|
|
if (*seen < how)
|
|
|
|
*seen = how;
|
2006-05-20 01:07:51 +02:00
|
|
|
}
|
|
|
|
}
|
|
|
|
return retval;
|
|
|
|
}
|
|
|
|
|
2006-05-17 04:02:14 +02:00
|
|
|
void add_exclude(const char *string, const char *base,
|
|
|
|
int baselen, struct exclude_list *which)
|
|
|
|
{
|
|
|
|
struct exclude *x = xmalloc(sizeof (*x));
|
|
|
|
|
|
|
|
x->pattern = string;
|
|
|
|
x->base = base;
|
|
|
|
x->baselen = baselen;
|
|
|
|
if (which->nr == which->alloc) {
|
|
|
|
which->alloc = alloc_nr(which->alloc);
|
2006-08-26 16:16:18 +02:00
|
|
|
which->excludes = xrealloc(which->excludes,
|
|
|
|
which->alloc * sizeof(x));
|
2006-05-17 04:02:14 +02:00
|
|
|
}
|
|
|
|
which->excludes[which->nr++] = x;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int add_excludes_from_file_1(const char *fname,
|
|
|
|
const char *base,
|
|
|
|
int baselen,
|
|
|
|
struct exclude_list *which)
|
|
|
|
{
|
2006-08-28 01:55:46 +02:00
|
|
|
struct stat st;
|
2006-05-17 04:02:14 +02:00
|
|
|
int fd, i;
|
2007-03-07 02:44:37 +01:00
|
|
|
size_t size;
|
2006-05-17 04:02:14 +02:00
|
|
|
char *buf, *entry;
|
|
|
|
|
|
|
|
fd = open(fname, O_RDONLY);
|
2006-08-28 01:55:46 +02:00
|
|
|
if (fd < 0 || fstat(fd, &st) < 0)
|
2006-05-17 04:02:14 +02:00
|
|
|
goto err;
|
2007-03-07 02:44:37 +01:00
|
|
|
size = xsize_t(st.st_size);
|
2006-05-17 04:02:14 +02:00
|
|
|
if (size == 0) {
|
|
|
|
close(fd);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
buf = xmalloc(size+1);
|
2007-01-08 16:58:08 +01:00
|
|
|
if (read_in_full(fd, buf, size) != size)
|
2006-05-17 04:02:14 +02:00
|
|
|
goto err;
|
|
|
|
close(fd);
|
|
|
|
|
|
|
|
buf[size++] = '\n';
|
|
|
|
entry = buf;
|
|
|
|
for (i = 0; i < size; i++) {
|
|
|
|
if (buf[i] == '\n') {
|
|
|
|
if (entry != buf + i && entry[0] != '#') {
|
|
|
|
buf[i - (i && buf[i-1] == '\r')] = 0;
|
|
|
|
add_exclude(entry, base, baselen, which);
|
|
|
|
}
|
|
|
|
entry = buf + i + 1;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
err:
|
|
|
|
if (0 <= fd)
|
|
|
|
close(fd);
|
|
|
|
return -1;
|
|
|
|
}
|
|
|
|
|
|
|
|
void add_excludes_from_file(struct dir_struct *dir, const char *fname)
|
|
|
|
{
|
|
|
|
if (add_excludes_from_file_1(fname, "", 0,
|
|
|
|
&dir->exclude_list[EXC_FILE]) < 0)
|
|
|
|
die("cannot use %s as an exclude file", fname);
|
|
|
|
}
|
|
|
|
|
2006-12-05 01:00:46 +01:00
|
|
|
int push_exclude_per_directory(struct dir_struct *dir, const char *base, int baselen)
|
2006-05-17 04:02:14 +02:00
|
|
|
{
|
|
|
|
char exclude_file[PATH_MAX];
|
|
|
|
struct exclude_list *el = &dir->exclude_list[EXC_DIRS];
|
|
|
|
int current_nr = el->nr;
|
|
|
|
|
|
|
|
if (dir->exclude_per_dir) {
|
|
|
|
memcpy(exclude_file, base, baselen);
|
|
|
|
strcpy(exclude_file + baselen, dir->exclude_per_dir);
|
|
|
|
add_excludes_from_file_1(exclude_file, base, baselen, el);
|
|
|
|
}
|
|
|
|
return current_nr;
|
|
|
|
}
|
|
|
|
|
2006-12-05 01:00:46 +01:00
|
|
|
void pop_exclude_per_directory(struct dir_struct *dir, int stk)
|
2006-05-17 04:02:14 +02:00
|
|
|
{
|
|
|
|
struct exclude_list *el = &dir->exclude_list[EXC_DIRS];
|
|
|
|
|
|
|
|
while (stk < el->nr)
|
|
|
|
free(el->excludes[--el->nr]);
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Scan the list and let the last match determines the fate.
|
|
|
|
* Return 1 for exclude, 0 for include and -1 for undecided.
|
|
|
|
*/
|
|
|
|
static int excluded_1(const char *pathname,
|
|
|
|
int pathlen,
|
|
|
|
struct exclude_list *el)
|
|
|
|
{
|
|
|
|
int i;
|
|
|
|
|
|
|
|
if (el->nr) {
|
|
|
|
for (i = el->nr - 1; 0 <= i; i--) {
|
|
|
|
struct exclude *x = el->excludes[i];
|
|
|
|
const char *exclude = x->pattern;
|
|
|
|
int to_exclude = 1;
|
|
|
|
|
|
|
|
if (*exclude == '!') {
|
|
|
|
to_exclude = 0;
|
|
|
|
exclude++;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!strchr(exclude, '/')) {
|
|
|
|
/* match basename */
|
|
|
|
const char *basename = strrchr(pathname, '/');
|
|
|
|
basename = (basename) ? basename+1 : pathname;
|
|
|
|
if (fnmatch(exclude, basename, 0) == 0)
|
|
|
|
return to_exclude;
|
|
|
|
}
|
|
|
|
else {
|
|
|
|
/* match with FNM_PATHNAME:
|
|
|
|
* exclude has base (baselen long) implicitly
|
|
|
|
* in front of it.
|
|
|
|
*/
|
|
|
|
int baselen = x->baselen;
|
|
|
|
if (*exclude == '/')
|
|
|
|
exclude++;
|
|
|
|
|
|
|
|
if (pathlen < baselen ||
|
|
|
|
(baselen && pathname[baselen-1] != '/') ||
|
|
|
|
strncmp(pathname, x->base, baselen))
|
|
|
|
continue;
|
|
|
|
|
|
|
|
if (fnmatch(exclude, pathname+baselen,
|
|
|
|
FNM_PATHNAME) == 0)
|
|
|
|
return to_exclude;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return -1; /* undecided */
|
|
|
|
}
|
|
|
|
|
|
|
|
int excluded(struct dir_struct *dir, const char *pathname)
|
|
|
|
{
|
|
|
|
int pathlen = strlen(pathname);
|
|
|
|
int st;
|
|
|
|
|
|
|
|
for (st = EXC_CMDL; st <= EXC_FILE; st++) {
|
|
|
|
switch (excluded_1(pathname, pathlen, &dir->exclude_list[st])) {
|
|
|
|
case 0:
|
|
|
|
return 0;
|
|
|
|
case 1:
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2007-06-11 15:39:44 +02:00
|
|
|
static struct dir_entry *dir_entry_new(const char *pathname, int len) {
|
2006-05-17 04:02:14 +02:00
|
|
|
struct dir_entry *ent;
|
|
|
|
|
|
|
|
ent = xmalloc(sizeof(*ent) + len + 1);
|
|
|
|
ent->len = len;
|
|
|
|
memcpy(ent->name, pathname, len);
|
|
|
|
ent->name[len] = 0;
|
2006-12-29 20:01:31 +01:00
|
|
|
return ent;
|
2006-05-17 04:02:14 +02:00
|
|
|
}
|
|
|
|
|
2007-06-11 15:39:44 +02:00
|
|
|
struct dir_entry *dir_add_name(struct dir_struct *dir, const char *pathname, int len)
|
|
|
|
{
|
|
|
|
if (cache_name_pos(pathname, len) >= 0)
|
|
|
|
return NULL;
|
|
|
|
|
2007-06-17 00:43:40 +02:00
|
|
|
ALLOC_GROW(dir->entries, dir->nr+1, dir->alloc);
|
2007-06-11 15:39:44 +02:00
|
|
|
return dir->entries[dir->nr++] = dir_entry_new(pathname, len);
|
|
|
|
}
|
|
|
|
|
2007-06-11 15:39:50 +02:00
|
|
|
struct dir_entry *dir_add_ignored(struct dir_struct *dir, const char *pathname, int len)
|
|
|
|
{
|
|
|
|
if (cache_name_pos(pathname, len) >= 0)
|
|
|
|
return NULL;
|
|
|
|
|
2007-06-17 00:43:40 +02:00
|
|
|
ALLOC_GROW(dir->ignored, dir->ignored_nr+1, dir->ignored_alloc);
|
2007-06-11 15:39:50 +02:00
|
|
|
return dir->ignored[dir->ignored_nr++] = dir_entry_new(pathname, len);
|
|
|
|
}
|
|
|
|
|
2007-04-11 23:49:44 +02:00
|
|
|
enum exist_status {
|
|
|
|
index_nonexistent = 0,
|
|
|
|
index_directory,
|
|
|
|
index_gitdir,
|
|
|
|
};
|
|
|
|
|
|
|
|
/*
|
|
|
|
* The index sorts alphabetically by entry name, which
|
|
|
|
* means that a gitlink sorts as '\0' at the end, while
|
|
|
|
* a directory (which is defined not as an entry, but as
|
|
|
|
* the files it contains) will sort with the '/' at the
|
|
|
|
* end.
|
|
|
|
*/
|
|
|
|
static enum exist_status directory_exists_in_index(const char *dirname, int len)
|
2006-05-17 04:02:14 +02:00
|
|
|
{
|
|
|
|
int pos = cache_name_pos(dirname, len);
|
2007-04-11 23:49:44 +02:00
|
|
|
if (pos < 0)
|
|
|
|
pos = -pos-1;
|
|
|
|
while (pos < active_nr) {
|
|
|
|
struct cache_entry *ce = active_cache[pos++];
|
|
|
|
unsigned char endchar;
|
|
|
|
|
|
|
|
if (strncmp(ce->name, dirname, len))
|
|
|
|
break;
|
|
|
|
endchar = ce->name[len];
|
|
|
|
if (endchar > '/')
|
|
|
|
break;
|
|
|
|
if (endchar == '/')
|
|
|
|
return index_directory;
|
2007-05-21 22:08:28 +02:00
|
|
|
if (!endchar && S_ISGITLINK(ntohl(ce->ce_mode)))
|
2007-04-11 23:49:44 +02:00
|
|
|
return index_gitdir;
|
|
|
|
}
|
|
|
|
return index_nonexistent;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* When we find a directory when traversing the filesystem, we
|
|
|
|
* have three distinct cases:
|
|
|
|
*
|
|
|
|
* - ignore it
|
|
|
|
* - see it as a directory
|
|
|
|
* - recurse into it
|
|
|
|
*
|
|
|
|
* and which one we choose depends on a combination of existing
|
|
|
|
* git index contents and the flags passed into the directory
|
|
|
|
* traversal routine.
|
|
|
|
*
|
|
|
|
* Case 1: If we *already* have entries in the index under that
|
|
|
|
* directory name, we always recurse into the directory to see
|
|
|
|
* all the files.
|
|
|
|
*
|
|
|
|
* Case 2: If we *already* have that directory name as a gitlink,
|
|
|
|
* we always continue to see it as a gitlink, regardless of whether
|
|
|
|
* there is an actual git directory there or not (it might not
|
|
|
|
* be checked out as a subproject!)
|
|
|
|
*
|
|
|
|
* Case 3: if we didn't have it in the index previously, we
|
|
|
|
* have a few sub-cases:
|
|
|
|
*
|
|
|
|
* (a) if "show_other_directories" is true, we show it as
|
|
|
|
* just a directory, unless "hide_empty_directories" is
|
|
|
|
* also true and the directory is empty, in which case
|
|
|
|
* we just ignore it entirely.
|
|
|
|
* (b) if it looks like a git directory, and we don't have
|
2007-05-21 22:08:28 +02:00
|
|
|
* 'no_gitlinks' set we treat it as a gitlink, and show it
|
2007-04-11 23:49:44 +02:00
|
|
|
* as a directory.
|
|
|
|
* (c) otherwise, we recurse into it.
|
|
|
|
*/
|
|
|
|
enum directory_treatment {
|
|
|
|
show_directory,
|
|
|
|
ignore_directory,
|
|
|
|
recurse_into_directory,
|
|
|
|
};
|
|
|
|
|
|
|
|
static enum directory_treatment treat_directory(struct dir_struct *dir,
|
|
|
|
const char *dirname, int len,
|
|
|
|
const struct path_simplify *simplify)
|
|
|
|
{
|
|
|
|
/* The "len-1" is to strip the final '/' */
|
|
|
|
switch (directory_exists_in_index(dirname, len-1)) {
|
|
|
|
case index_directory:
|
|
|
|
return recurse_into_directory;
|
|
|
|
|
|
|
|
case index_gitdir:
|
2007-04-12 23:32:21 +02:00
|
|
|
if (dir->show_other_directories)
|
|
|
|
return ignore_directory;
|
2007-04-11 23:49:44 +02:00
|
|
|
return show_directory;
|
|
|
|
|
|
|
|
case index_nonexistent:
|
|
|
|
if (dir->show_other_directories)
|
|
|
|
break;
|
2007-05-21 22:08:28 +02:00
|
|
|
if (!dir->no_gitlinks) {
|
2007-04-11 23:49:44 +02:00
|
|
|
unsigned char sha1[20];
|
|
|
|
if (resolve_gitlink_ref(dirname, "HEAD", sha1) == 0)
|
|
|
|
return show_directory;
|
|
|
|
}
|
|
|
|
return recurse_into_directory;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* This is the "show_other_directories" case */
|
|
|
|
if (!dir->hide_empty_directories)
|
|
|
|
return show_directory;
|
|
|
|
if (!read_directory_recursive(dir, dirname, dirname, len, 1, simplify))
|
|
|
|
return ignore_directory;
|
|
|
|
return show_directory;
|
2006-05-17 04:02:14 +02:00
|
|
|
}
|
|
|
|
|
Optimize directory listing with pathspec limiter.
The way things are set up, you can now pass a "pathspec" to the
"read_directory()" function. If you pass NULL, it acts exactly
like it used to do (read everything). If you pass a non-NULL
pointer, it will simplify it into a "these are the prefixes
without any special characters", and stop any readdir() early if
the path in question doesn't match any of the prefixes.
NOTE! This does *not* obviate the need for the caller to do the *exact*
pathspec match later. It's a first-level filter on "read_directory()", but
it does not do the full pathspec thing. Maybe it should. But in the
meantime, builtin-add.c really does need to do first
read_directory(dir, .., pathspec);
if (pathspec)
prune_directory(dir, pathspec, baselen);
ie the "prune_directory()" part will do the *exact* pathspec pruning,
while the "read_directory()" will use the pathspec just to do some quick
high-level pruning of the directories it will recurse into.
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Junio C Hamano <junkio@cox.net>
2007-03-31 05:39:30 +02:00
|
|
|
/*
|
|
|
|
* This is an inexact early pruning of any recursive directory
|
|
|
|
* reading - if the path cannot possibly be in the pathspec,
|
|
|
|
* return true, and we'll skip it early.
|
|
|
|
*/
|
|
|
|
static int simplify_away(const char *path, int pathlen, const struct path_simplify *simplify)
|
|
|
|
{
|
|
|
|
if (simplify) {
|
|
|
|
for (;;) {
|
|
|
|
const char *match = simplify->path;
|
|
|
|
int len = simplify->len;
|
|
|
|
|
|
|
|
if (!match)
|
|
|
|
break;
|
|
|
|
if (len > pathlen)
|
|
|
|
len = pathlen;
|
|
|
|
if (!memcmp(path, match, len))
|
|
|
|
return 0;
|
|
|
|
simplify++;
|
|
|
|
}
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
builtin-add: simplify (and increase accuracy of) exclude handling
Previously, the code would always set up the excludes, and then manually
pick through the pathspec we were given, assuming that non-added but
existing paths were just ignored. This was mostly correct, but would
erroneously mark a totally empty directory as 'ignored'.
Instead, we now use the collect_ignored option of dir_struct, which
unambiguously tells us whether a path was ignored. This simplifies the
code, and means empty directories are now just not mentioned at all.
Furthermore, we now conditionally ask dir_struct to respect excludes,
depending on whether the '-f' flag has been set. This means we don't have
to pick through the result, checking for an 'ignored' flag; ignored entries
were either added or not in the first place.
We can safely get rid of the special 'ignored' flags to dir_entry, which
were not used anywhere else.
Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Jonas Fonseca <fonseca@diku.dk>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-06-12 23:42:14 +02:00
|
|
|
static int in_pathspec(const char *path, int len, const struct path_simplify *simplify)
|
|
|
|
{
|
|
|
|
if (simplify) {
|
|
|
|
for (; simplify->path; simplify++) {
|
|
|
|
if (len == simplify->len
|
|
|
|
&& !memcmp(path, simplify->path, len))
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2006-05-17 04:02:14 +02:00
|
|
|
/*
|
|
|
|
* Read a directory tree. We currently ignore anything but
|
|
|
|
* directories, regular files and symlinks. That's because git
|
|
|
|
* doesn't handle them at all yet. Maybe that will change some
|
|
|
|
* day.
|
|
|
|
*
|
|
|
|
* Also, we ignore the name ".git" (even if it is not a directory).
|
|
|
|
* That likely will not change.
|
|
|
|
*/
|
Optimize directory listing with pathspec limiter.
The way things are set up, you can now pass a "pathspec" to the
"read_directory()" function. If you pass NULL, it acts exactly
like it used to do (read everything). If you pass a non-NULL
pointer, it will simplify it into a "these are the prefixes
without any special characters", and stop any readdir() early if
the path in question doesn't match any of the prefixes.
NOTE! This does *not* obviate the need for the caller to do the *exact*
pathspec match later. It's a first-level filter on "read_directory()", but
it does not do the full pathspec thing. Maybe it should. But in the
meantime, builtin-add.c really does need to do first
read_directory(dir, .., pathspec);
if (pathspec)
prune_directory(dir, pathspec, baselen);
ie the "prune_directory()" part will do the *exact* pathspec pruning,
while the "read_directory()" will use the pathspec just to do some quick
high-level pruning of the directories it will recurse into.
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Junio C Hamano <junkio@cox.net>
2007-03-31 05:39:30 +02:00
|
|
|
static int read_directory_recursive(struct dir_struct *dir, const char *path, const char *base, int baselen, int check_only, const struct path_simplify *simplify)
|
2006-05-17 04:02:14 +02:00
|
|
|
{
|
|
|
|
DIR *fdir = opendir(path);
|
|
|
|
int contents = 0;
|
|
|
|
|
|
|
|
if (fdir) {
|
|
|
|
int exclude_stk;
|
|
|
|
struct dirent *de;
|
2006-08-26 16:09:17 +02:00
|
|
|
char fullname[PATH_MAX + 1];
|
2006-05-17 04:02:14 +02:00
|
|
|
memcpy(fullname, base, baselen);
|
|
|
|
|
|
|
|
exclude_stk = push_exclude_per_directory(dir, base, baselen);
|
|
|
|
|
|
|
|
while ((de = readdir(fdir)) != NULL) {
|
|
|
|
int len;
|
2007-05-07 04:35:04 +02:00
|
|
|
int exclude;
|
2006-05-17 04:02:14 +02:00
|
|
|
|
|
|
|
if ((de->d_name[0] == '.') &&
|
|
|
|
(de->d_name[1] == 0 ||
|
|
|
|
!strcmp(de->d_name + 1, ".") ||
|
|
|
|
!strcmp(de->d_name + 1, "git")))
|
|
|
|
continue;
|
|
|
|
len = strlen(de->d_name);
|
2007-04-10 06:13:58 +02:00
|
|
|
/* Ignore overly long pathnames! */
|
|
|
|
if (len + baselen + 8 > sizeof(fullname))
|
|
|
|
continue;
|
2006-05-17 04:02:14 +02:00
|
|
|
memcpy(fullname + baselen, de->d_name, len+1);
|
Optimize directory listing with pathspec limiter.
The way things are set up, you can now pass a "pathspec" to the
"read_directory()" function. If you pass NULL, it acts exactly
like it used to do (read everything). If you pass a non-NULL
pointer, it will simplify it into a "these are the prefixes
without any special characters", and stop any readdir() early if
the path in question doesn't match any of the prefixes.
NOTE! This does *not* obviate the need for the caller to do the *exact*
pathspec match later. It's a first-level filter on "read_directory()", but
it does not do the full pathspec thing. Maybe it should. But in the
meantime, builtin-add.c really does need to do first
read_directory(dir, .., pathspec);
if (pathspec)
prune_directory(dir, pathspec, baselen);
ie the "prune_directory()" part will do the *exact* pathspec pruning,
while the "read_directory()" will use the pathspec just to do some quick
high-level pruning of the directories it will recurse into.
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Junio C Hamano <junkio@cox.net>
2007-03-31 05:39:30 +02:00
|
|
|
if (simplify_away(fullname, baselen + len, simplify))
|
|
|
|
continue;
|
2007-05-07 04:35:04 +02:00
|
|
|
|
|
|
|
exclude = excluded(dir, fullname);
|
builtin-add: simplify (and increase accuracy of) exclude handling
Previously, the code would always set up the excludes, and then manually
pick through the pathspec we were given, assuming that non-added but
existing paths were just ignored. This was mostly correct, but would
erroneously mark a totally empty directory as 'ignored'.
Instead, we now use the collect_ignored option of dir_struct, which
unambiguously tells us whether a path was ignored. This simplifies the
code, and means empty directories are now just not mentioned at all.
Furthermore, we now conditionally ask dir_struct to respect excludes,
depending on whether the '-f' flag has been set. This means we don't have
to pick through the result, checking for an 'ignored' flag; ignored entries
were either added or not in the first place.
We can safely get rid of the special 'ignored' flags to dir_entry, which
were not used anywhere else.
Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Jonas Fonseca <fonseca@diku.dk>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-06-12 23:42:14 +02:00
|
|
|
if (exclude && dir->collect_ignored
|
|
|
|
&& in_pathspec(fullname, baselen + len, simplify))
|
2007-06-11 15:39:50 +02:00
|
|
|
dir_add_ignored(dir, fullname, baselen + len);
|
2007-05-07 04:35:04 +02:00
|
|
|
if (exclude != dir->show_ignored) {
|
2006-12-29 19:08:19 +01:00
|
|
|
if (!dir->show_ignored || DTYPE(de) != DT_DIR) {
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
}
|
2006-05-17 04:02:14 +02:00
|
|
|
|
|
|
|
switch (DTYPE(de)) {
|
|
|
|
struct stat st;
|
|
|
|
default:
|
|
|
|
continue;
|
|
|
|
case DT_UNKNOWN:
|
|
|
|
if (lstat(fullname, &st))
|
|
|
|
continue;
|
|
|
|
if (S_ISREG(st.st_mode) || S_ISLNK(st.st_mode))
|
|
|
|
break;
|
|
|
|
if (!S_ISDIR(st.st_mode))
|
|
|
|
continue;
|
|
|
|
/* fallthrough */
|
|
|
|
case DT_DIR:
|
|
|
|
memcpy(fullname + baselen + len, "/", 2);
|
|
|
|
len++;
|
2007-04-11 23:49:44 +02:00
|
|
|
switch (treat_directory(dir, fullname, baselen + len, simplify)) {
|
|
|
|
case show_directory:
|
2007-05-07 04:35:04 +02:00
|
|
|
if (exclude != dir->show_ignored)
|
|
|
|
continue;
|
2006-05-17 04:02:14 +02:00
|
|
|
break;
|
2007-04-11 23:49:44 +02:00
|
|
|
case recurse_into_directory:
|
|
|
|
contents += read_directory_recursive(dir,
|
|
|
|
fullname, fullname, baselen + len, 0, simplify);
|
|
|
|
continue;
|
|
|
|
case ignore_directory:
|
|
|
|
continue;
|
2006-05-17 04:02:14 +02:00
|
|
|
}
|
2007-04-11 23:49:44 +02:00
|
|
|
break;
|
2006-05-17 04:02:14 +02:00
|
|
|
case DT_REG:
|
|
|
|
case DT_LNK:
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
contents++;
|
2006-09-28 02:44:30 +02:00
|
|
|
if (check_only)
|
|
|
|
goto exit_early;
|
|
|
|
else
|
2006-12-29 20:01:31 +01:00
|
|
|
dir_add_name(dir, fullname, baselen + len);
|
2006-05-17 04:02:14 +02:00
|
|
|
}
|
2006-09-28 02:44:30 +02:00
|
|
|
exit_early:
|
2006-05-17 04:02:14 +02:00
|
|
|
closedir(fdir);
|
|
|
|
|
|
|
|
pop_exclude_per_directory(dir, exclude_stk);
|
|
|
|
}
|
|
|
|
|
|
|
|
return contents;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int cmp_name(const void *p1, const void *p2)
|
|
|
|
{
|
|
|
|
const struct dir_entry *e1 = *(const struct dir_entry **)p1;
|
|
|
|
const struct dir_entry *e2 = *(const struct dir_entry **)p2;
|
|
|
|
|
|
|
|
return cache_name_compare(e1->name, e1->len,
|
|
|
|
e2->name, e2->len);
|
|
|
|
}
|
|
|
|
|
Optimize directory listing with pathspec limiter.
The way things are set up, you can now pass a "pathspec" to the
"read_directory()" function. If you pass NULL, it acts exactly
like it used to do (read everything). If you pass a non-NULL
pointer, it will simplify it into a "these are the prefixes
without any special characters", and stop any readdir() early if
the path in question doesn't match any of the prefixes.
NOTE! This does *not* obviate the need for the caller to do the *exact*
pathspec match later. It's a first-level filter on "read_directory()", but
it does not do the full pathspec thing. Maybe it should. But in the
meantime, builtin-add.c really does need to do first
read_directory(dir, .., pathspec);
if (pathspec)
prune_directory(dir, pathspec, baselen);
ie the "prune_directory()" part will do the *exact* pathspec pruning,
while the "read_directory()" will use the pathspec just to do some quick
high-level pruning of the directories it will recurse into.
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Junio C Hamano <junkio@cox.net>
2007-03-31 05:39:30 +02:00
|
|
|
/*
|
|
|
|
* Return the length of the "simple" part of a path match limiter.
|
|
|
|
*/
|
|
|
|
static int simple_length(const char *match)
|
2006-05-17 04:02:14 +02:00
|
|
|
{
|
Optimize directory listing with pathspec limiter.
The way things are set up, you can now pass a "pathspec" to the
"read_directory()" function. If you pass NULL, it acts exactly
like it used to do (read everything). If you pass a non-NULL
pointer, it will simplify it into a "these are the prefixes
without any special characters", and stop any readdir() early if
the path in question doesn't match any of the prefixes.
NOTE! This does *not* obviate the need for the caller to do the *exact*
pathspec match later. It's a first-level filter on "read_directory()", but
it does not do the full pathspec thing. Maybe it should. But in the
meantime, builtin-add.c really does need to do first
read_directory(dir, .., pathspec);
if (pathspec)
prune_directory(dir, pathspec, baselen);
ie the "prune_directory()" part will do the *exact* pathspec pruning,
while the "read_directory()" will use the pathspec just to do some quick
high-level pruning of the directories it will recurse into.
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Junio C Hamano <junkio@cox.net>
2007-03-31 05:39:30 +02:00
|
|
|
const char special[256] = {
|
|
|
|
[0] = 1, ['?'] = 1,
|
|
|
|
['\\'] = 1, ['*'] = 1,
|
|
|
|
['['] = 1
|
|
|
|
};
|
|
|
|
int len = -1;
|
|
|
|
|
|
|
|
for (;;) {
|
|
|
|
unsigned char c = *match++;
|
|
|
|
len++;
|
|
|
|
if (special[c])
|
|
|
|
return len;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
static struct path_simplify *create_simplify(const char **pathspec)
|
|
|
|
{
|
|
|
|
int nr, alloc = 0;
|
|
|
|
struct path_simplify *simplify = NULL;
|
|
|
|
|
|
|
|
if (!pathspec)
|
|
|
|
return NULL;
|
|
|
|
|
|
|
|
for (nr = 0 ; ; nr++) {
|
|
|
|
const char *match;
|
|
|
|
if (nr >= alloc) {
|
|
|
|
alloc = alloc_nr(alloc);
|
|
|
|
simplify = xrealloc(simplify, alloc * sizeof(*simplify));
|
|
|
|
}
|
|
|
|
match = *pathspec++;
|
|
|
|
if (!match)
|
|
|
|
break;
|
|
|
|
simplify[nr].path = match;
|
|
|
|
simplify[nr].len = simple_length(match);
|
|
|
|
}
|
|
|
|
simplify[nr].path = NULL;
|
|
|
|
simplify[nr].len = 0;
|
|
|
|
return simplify;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void free_simplify(struct path_simplify *simplify)
|
|
|
|
{
|
|
|
|
if (simplify)
|
|
|
|
free(simplify);
|
|
|
|
}
|
|
|
|
|
|
|
|
int read_directory(struct dir_struct *dir, const char *path, const char *base, int baselen, const char **pathspec)
|
|
|
|
{
|
|
|
|
struct path_simplify *simplify = create_simplify(pathspec);
|
|
|
|
|
2006-05-17 04:46:16 +02:00
|
|
|
/*
|
|
|
|
* Make sure to do the per-directory exclude for all the
|
|
|
|
* directories leading up to our base.
|
|
|
|
*/
|
|
|
|
if (baselen) {
|
|
|
|
if (dir->exclude_per_dir) {
|
|
|
|
char *p, *pp = xmalloc(baselen+1);
|
|
|
|
memcpy(pp, base, baselen+1);
|
|
|
|
p = pp;
|
|
|
|
while (1) {
|
|
|
|
char save = *p;
|
|
|
|
*p = 0;
|
|
|
|
push_exclude_per_directory(dir, pp, p-pp);
|
|
|
|
*p++ = save;
|
|
|
|
if (!save)
|
|
|
|
break;
|
|
|
|
p = strchr(p, '/');
|
|
|
|
if (p)
|
|
|
|
p++;
|
|
|
|
else
|
|
|
|
p = pp + baselen;
|
|
|
|
}
|
|
|
|
free(pp);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
Optimize directory listing with pathspec limiter.
The way things are set up, you can now pass a "pathspec" to the
"read_directory()" function. If you pass NULL, it acts exactly
like it used to do (read everything). If you pass a non-NULL
pointer, it will simplify it into a "these are the prefixes
without any special characters", and stop any readdir() early if
the path in question doesn't match any of the prefixes.
NOTE! This does *not* obviate the need for the caller to do the *exact*
pathspec match later. It's a first-level filter on "read_directory()", but
it does not do the full pathspec thing. Maybe it should. But in the
meantime, builtin-add.c really does need to do first
read_directory(dir, .., pathspec);
if (pathspec)
prune_directory(dir, pathspec, baselen);
ie the "prune_directory()" part will do the *exact* pathspec pruning,
while the "read_directory()" will use the pathspec just to do some quick
high-level pruning of the directories it will recurse into.
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Junio C Hamano <junkio@cox.net>
2007-03-31 05:39:30 +02:00
|
|
|
read_directory_recursive(dir, path, base, baselen, 0, simplify);
|
|
|
|
free_simplify(simplify);
|
2006-05-17 04:02:14 +02:00
|
|
|
qsort(dir->entries, dir->nr, sizeof(struct dir_entry *), cmp_name);
|
2007-06-11 15:39:50 +02:00
|
|
|
qsort(dir->ignored, dir->ignored_nr, sizeof(struct dir_entry *), cmp_name);
|
2006-05-17 04:02:14 +02:00
|
|
|
return dir->nr;
|
|
|
|
}
|
2006-09-08 10:05:34 +02:00
|
|
|
|
|
|
|
int
|
|
|
|
file_exists(const char *f)
|
|
|
|
{
|
|
|
|
struct stat sb;
|
|
|
|
return stat(f, &sb) == 0;
|
|
|
|
}
|
2007-08-01 02:29:17 +02:00
|
|
|
|
|
|
|
/*
|
|
|
|
* get_relative_cwd() gets the prefix of the current working directory
|
|
|
|
* relative to 'dir'. If we are not inside 'dir', it returns NULL.
|
2007-08-01 20:26:59 +02:00
|
|
|
*
|
|
|
|
* As a convenience, it also returns NULL if 'dir' is already NULL. The
|
|
|
|
* reason for this behaviour is that it is natural for functions returning
|
|
|
|
* directory names to return NULL to say "this directory does not exist"
|
|
|
|
* or "this directory is invalid". These cases are usually handled the
|
|
|
|
* same as if the cwd is not inside 'dir' at all, so get_relative_cwd()
|
|
|
|
* returns NULL for both of them.
|
|
|
|
*
|
|
|
|
* Most notably, get_relative_cwd(buffer, size, get_git_work_tree())
|
|
|
|
* unifies the handling of "outside work tree" with "no work tree at all".
|
2007-08-01 02:29:17 +02:00
|
|
|
*/
|
|
|
|
char *get_relative_cwd(char *buffer, int size, const char *dir)
|
|
|
|
{
|
|
|
|
char *cwd = buffer;
|
|
|
|
|
|
|
|
if (!dir)
|
|
|
|
return NULL;
|
|
|
|
if (!getcwd(buffer, size))
|
|
|
|
die("can't find the current directory: %s", strerror(errno));
|
|
|
|
|
|
|
|
if (!is_absolute_path(dir))
|
|
|
|
dir = make_absolute_path(dir);
|
|
|
|
|
|
|
|
while (*dir && *dir == *cwd) {
|
|
|
|
dir++;
|
|
|
|
cwd++;
|
|
|
|
}
|
|
|
|
if (*dir)
|
|
|
|
return NULL;
|
|
|
|
if (*cwd == '/')
|
|
|
|
return cwd + 1;
|
|
|
|
return cwd;
|
|
|
|
}
|
|
|
|
|
|
|
|
int is_inside_dir(const char *dir)
|
|
|
|
{
|
|
|
|
char buffer[PATH_MAX];
|
|
|
|
return get_relative_cwd(buffer, sizeof(buffer), dir) != NULL;
|
|
|
|
}
|