per-directory-exclude: lazily read .gitignore files

Operations that walk directories or trees, which potentially need to
consult the .gitignore files, used to always try to open the .gitignore
file every time they entered a new directory, even when they ended up
not needing to call excluded() function to see if a path in the
directory is ignored.  This was done by push/pop exclude_per_directory()
functions that managed the data in a stack.

This changes the directory walking API to remove the need to call these
two functions.  Instead, the directory walk data structure caches the
data used by excluded() function the last time, and lazily reuses it as
much as possible.  Among the data the last check used, the ones from
deeper directories that the path we are checking is outside are
discarded, data from the common leading directories are reused, and then
the directories between the common directory and the directory the path
being checked is in are checked for .gitignore file.  This is very
similar to the way gitattributes are handled.

This API change also fixes "ls-files -c -i", which called excluded()
without setting up the gitignore data via the old push/pop functions.

Signed-off-by: Junio C Hamano <gitster@pobox.com>
This commit is contained in:
Junio C Hamano 2007-11-29 02:17:44 -08:00
parent 686a4a06b6
commit 63d285c849
3 changed files with 71 additions and 68 deletions

101
dir.c
View File

@ -151,6 +151,7 @@ void add_exclude(const char *string, const char *base,
static int add_excludes_from_file_1(const char *fname,
const char *base,
int baselen,
char **buf_p,
struct exclude_list *which)
{
struct stat st;
@ -171,6 +172,8 @@ static int add_excludes_from_file_1(const char *fname,
goto err;
close(fd);
if (buf_p)
*buf_p = buf;
buf[size++] = '\n';
entry = buf;
for (i = 0; i < size; i++) {
@ -192,31 +195,63 @@ static int add_excludes_from_file_1(const char *fname,
void add_excludes_from_file(struct dir_struct *dir, const char *fname)
{
if (add_excludes_from_file_1(fname, "", 0,
if (add_excludes_from_file_1(fname, "", 0, NULL,
&dir->exclude_list[EXC_FILE]) < 0)
die("cannot use %s as an exclude file", fname);
}
int push_exclude_per_directory(struct dir_struct *dir, const char *base, int baselen)
static void prep_exclude(struct dir_struct *dir, const char *base, int baselen)
{
char exclude_file[PATH_MAX];
struct exclude_list *el = &dir->exclude_list[EXC_DIRS];
int current_nr = el->nr;
struct exclude_list *el;
struct exclude_stack *stk = NULL;
int current;
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);
if ((!dir->exclude_per_dir) ||
(baselen + strlen(dir->exclude_per_dir) >= PATH_MAX))
return; /* too long a path -- ignore */
/* Pop the ones that are not the prefix of the path being checked. */
el = &dir->exclude_list[EXC_DIRS];
while ((stk = dir->exclude_stack) != NULL) {
if (stk->baselen <= baselen &&
!strncmp(dir->basebuf, base, stk->baselen))
break;
dir->exclude_stack = stk->prev;
while (stk->exclude_ix < el->nr)
free(el->excludes[--el->nr]);
free(stk->filebuf);
free(stk);
}
return current_nr;
}
void pop_exclude_per_directory(struct dir_struct *dir, int stk)
{
struct exclude_list *el = &dir->exclude_list[EXC_DIRS];
/* Read from the parent directories and push them down. */
current = stk ? stk->baselen : -1;
while (current < baselen) {
struct exclude_stack *stk = xcalloc(1, sizeof(*stk));
const char *cp;
while (stk < el->nr)
free(el->excludes[--el->nr]);
if (current < 0) {
cp = base;
current = 0;
}
else {
cp = strchr(base + current + 1, '/');
if (!cp)
die("oops in prep_exclude");
cp++;
}
stk->prev = dir->exclude_stack;
stk->baselen = cp - base;
stk->exclude_ix = el->nr;
memcpy(dir->basebuf + current, base + current,
stk->baselen - current);
strcpy(dir->basebuf + stk->baselen, dir->exclude_per_dir);
add_excludes_from_file_1(dir->basebuf,
dir->basebuf, stk->baselen,
&stk->filebuf, el);
dir->exclude_stack = stk;
current = stk->baselen;
}
dir->basebuf[baselen] = '\0';
}
/* Scan the list and let the last match determines the fate.
@ -283,6 +318,7 @@ int excluded(struct dir_struct *dir, const char *pathname)
const char *basename = strrchr(pathname, '/');
basename = (basename) ? basename+1 : pathname;
prep_exclude(dir, pathname, basename-pathname);
for (st = EXC_CMDL; st <= EXC_FILE; st++) {
switch (excluded_1(pathname, pathlen, basename, &dir->exclude_list[st])) {
case 0:
@ -500,13 +536,10 @@ static int read_directory_recursive(struct dir_struct *dir, const char *path, co
int contents = 0;
if (fdir) {
int exclude_stk;
struct dirent *de;
char fullname[PATH_MAX + 1];
memcpy(fullname, base, baselen);
exclude_stk = push_exclude_per_directory(dir, base, baselen);
while ((de = readdir(fdir)) != NULL) {
int len, dtype;
int exclude;
@ -580,8 +613,6 @@ static int read_directory_recursive(struct dir_struct *dir, const char *path, co
}
exit_early:
closedir(fdir);
pop_exclude_per_directory(dir, exclude_stk);
}
return contents;
@ -650,37 +681,9 @@ static void free_simplify(struct path_simplify *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);
char *pp = NULL;
/*
* 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;
}
}
}
read_directory_recursive(dir, path, base, baselen, 0, simplify);
free_simplify(simplify);
free(pp);
qsort(dir->entries, dir->nr, sizeof(struct dir_entry *), cmp_name);
qsort(dir->ignored, dir->ignored_nr, sizeof(struct dir_entry *), cmp_name);
return dir->nr;

32
dir.h
View File

@ -1,17 +1,6 @@
#ifndef DIR_H
#define DIR_H
/*
* We maintain three exclude pattern lists:
* EXC_CMDL lists patterns explicitly given on the command line.
* EXC_DIRS lists patterns obtained from per-directory ignore files.
* EXC_FILE lists patterns from fallback ignore files.
*/
#define EXC_CMDL 0
#define EXC_DIRS 1
#define EXC_FILE 2
struct dir_entry {
unsigned int len;
char name[FLEX_ARRAY]; /* more */
@ -34,6 +23,13 @@ struct exclude_list {
} **excludes;
};
struct exclude_stack {
struct exclude_stack *prev;
char *filebuf;
int baselen;
int exclude_ix;
};
struct dir_struct {
int nr, alloc;
int ignored_nr, ignored_alloc;
@ -48,6 +44,18 @@ struct dir_struct {
/* Exclude info */
const char *exclude_per_dir;
struct exclude_list exclude_list[3];
/*
* We maintain three exclude pattern lists:
* EXC_CMDL lists patterns explicitly given on the command line.
* EXC_DIRS lists patterns obtained from per-directory ignore files.
* EXC_FILE lists patterns from fallback ignore files.
*/
#define EXC_CMDL 0
#define EXC_DIRS 1
#define EXC_FILE 2
struct exclude_stack *exclude_stack;
char basebuf[PATH_MAX];
};
extern int common_prefix(const char **pathspec);
@ -58,8 +66,6 @@ extern int common_prefix(const char **pathspec);
extern int match_pathspec(const char **pathspec, const char *name, int namelen, int prefix, char *seen);
extern int read_directory(struct dir_struct *, const char *path, const char *base, int baselen, const char **pathspec);
extern int push_exclude_per_directory(struct dir_struct *, const char *, int);
extern void pop_exclude_per_directory(struct dir_struct *, int);
extern int excluded(struct dir_struct *, const char *);
extern void add_excludes_from_file(struct dir_struct *, const char *fname);

View File

@ -71,12 +71,8 @@ static int unpack_trees_rec(struct tree_entry_list **posns, int len,
int remove;
int baselen = strlen(base);
int src_size = len + 1;
int i_stk = i_stk;
int retval = 0;
if (o->dir)
i_stk = push_exclude_per_directory(o->dir, base, strlen(base));
do {
int i;
const char *first;
@ -255,8 +251,6 @@ static int unpack_trees_rec(struct tree_entry_list **posns, int len,
} while (1);
leave_directory:
if (o->dir)
pop_exclude_per_directory(o->dir, i_stk);
return retval;
}