1
0
mirror of https://github.com/git/git.git synced 2024-11-19 10:44:01 +01:00
git/builtin-add.c
Junio C Hamano fb63d7f889 git-add: make the entry stat-clean after re-adding the same contents
Earlier in commit 0781b8a9b2fe760fc4ed519a3a26e4b9bd6ccffe
(add_file_to_index: skip rehashing if the cached stat already
matches), add_file_to_index() were taught not to re-add the path
if it already matches the index.

The change meant well, but was not executed quite right.  It
used ie_modified() to see if the file on the work tree is really
different from the index, and skipped adding the contents if the
function says "not modified".

This was wrong.  There are three possible comparison results
between the index and the file in the work tree:

 - with lstat(2) we _know_ they are different.  E.g. if the
   length or the owner in the cached stat information is
   different from the length we just obtained from lstat(2), we
   can tell the file is modified without looking at the actual
   contents.

 - with lstat(2) we _know_ they are the same.  The same length,
   the same owner, the same everything (but this has a twist, as
   described below).

 - we cannot tell from lstat(2) information alone and need to go
   to the filesystem to actually compare.

The last case arises from what we call 'racy git' situation,
that can be caused with this sequence:

    $ echo hello >file
    $ git add file
    $ echo aeiou >file ;# the same length

If the second "echo" is done within the same filesystem
timestamp granularity as the first "echo", then the timestamp
recorded by "git add" and the timestamp we get from lstat(2)
will be the same, and we can mistakenly say the file is not
modified.  The path is called 'racily clean'.  We need to
reliably detect racily clean paths are in fact modified.

To solve this problem, when we write out the index, we mark the
index entry that has the same timestamp as the index file itself
(that is the time from the point of view of the filesystem) to
tell any later code that does the lstat(2) comparison not to
trust the cached stat info, and ie_modified() then actually goes
to the filesystem to compare the contents for such a path.

That's all good, but it should not be used for this "git add"
optimization, as the goal of "git add" is to actually update the
path in the index and make it stat-clean.  With the false
optimization, we did _not_ cause any data loss (after all, what
we failed to do was only to update the cached stat information),
but it made the following sequence leave the file stat dirty:

    $ echo hello >file
    $ git add file
    $ echo hello >file ;# the same contents
    $ git add file

The solution is not to use ie_modified() which goes to the
filesystem to see if it is really clean, but instead use
ie_match_stat() with "assume racily clean paths are dirty"
option, to force re-adding of such a path.

There was another problem with "git add -u".  The codepath
shares the same issue when adding the paths that are found to be
modified, but in addition, it asked "git diff-files" machinery
run_diff_files() function (which is "git diff-files") to list
the paths that are modified.  But "git diff-files" machinery
uses the same ie_modified() call so that it does not report
racily clean _and_ actually clean paths as modified, which is
not what we want.

The patch allows the callers of run_diff_files() to pass the
same "assume racily clean paths are dirty" option, and makes
"git-add -u" codepath to use that option, to discover and re-add
racily clean _and_ actually clean paths.

We could further optimize on top of this patch to differentiate
the case where the path really needs re-adding (i.e. the content
of the racily clean entry was indeed different) and the case
where only the cached stat information needs to be refreshed
(i.e. the racily clean entry was actually clean), but I do not
think it is worth it.

This patch applies to maint and all the way up.

Signed-off-by: Junio C Hamano <gitster@pobox.com>
2007-11-10 00:37:39 -08:00

276 lines
6.2 KiB
C

/*
* "git add" builtin command
*
* Copyright (C) 2006 Linus Torvalds
*/
#include "cache.h"
#include "builtin.h"
#include "dir.h"
#include "exec_cmd.h"
#include "cache-tree.h"
#include "diff.h"
#include "diffcore.h"
#include "commit.h"
#include "revision.h"
static const char builtin_add_usage[] =
"git-add [-n] [-v] [-f] [--interactive | -i] [-u] [--refresh] [--] <filepattern>...";
static int take_worktree_changes;
static const char *excludes_file;
static void prune_directory(struct dir_struct *dir, const char **pathspec, int prefix)
{
char *seen;
int i, specs;
struct dir_entry **src, **dst;
for (specs = 0; pathspec[specs]; specs++)
/* nothing */;
seen = xcalloc(specs, 1);
src = dst = dir->entries;
i = dir->nr;
while (--i >= 0) {
struct dir_entry *entry = *src++;
if (match_pathspec(pathspec, entry->name, entry->len,
prefix, seen))
*dst++ = entry;
}
dir->nr = dst - dir->entries;
for (i = 0; i < specs; i++) {
if (!seen[i] && !file_exists(pathspec[i]))
die("pathspec '%s' did not match any files",
pathspec[i]);
}
free(seen);
}
static void fill_directory(struct dir_struct *dir, const char **pathspec,
int ignored_too)
{
const char *path, *base;
int baselen;
/* Set up the default git porcelain excludes */
memset(dir, 0, sizeof(*dir));
if (!ignored_too) {
dir->collect_ignored = 1;
dir->exclude_per_dir = ".gitignore";
path = git_path("info/exclude");
if (!access(path, R_OK))
add_excludes_from_file(dir, path);
if (excludes_file != NULL && !access(excludes_file, R_OK))
add_excludes_from_file(dir, excludes_file);
}
/*
* Calculate common prefix for the pathspec, and
* use that to optimize the directory walk
*/
baselen = common_prefix(pathspec);
path = ".";
base = "";
if (baselen) {
char *common = xmalloc(baselen + 1);
memcpy(common, *pathspec, baselen);
common[baselen] = 0;
path = base = common;
}
/* Read the directory and prune it */
read_directory(dir, path, base, baselen, pathspec);
if (pathspec)
prune_directory(dir, pathspec, baselen);
}
static void update_callback(struct diff_queue_struct *q,
struct diff_options *opt, void *cbdata)
{
int i, verbose;
verbose = *((int *)cbdata);
for (i = 0; i < q->nr; i++) {
struct diff_filepair *p = q->queue[i];
const char *path = p->one->path;
switch (p->status) {
default:
die("unexpected diff status %c", p->status);
case DIFF_STATUS_UNMERGED:
case DIFF_STATUS_MODIFIED:
case DIFF_STATUS_TYPE_CHANGED:
add_file_to_cache(path, verbose);
break;
case DIFF_STATUS_DELETED:
remove_file_from_cache(path);
cache_tree_invalidate_path(active_cache_tree, path);
if (verbose)
printf("remove '%s'\n", path);
break;
}
}
}
static void update(int verbose, const char *prefix, const char **files)
{
struct rev_info rev;
init_revisions(&rev, prefix);
setup_revisions(0, NULL, &rev, NULL);
rev.prune_data = get_pathspec(prefix, files);
rev.diffopt.output_format = DIFF_FORMAT_CALLBACK;
rev.diffopt.format_callback = update_callback;
rev.diffopt.format_callback_data = &verbose;
if (read_cache() < 0)
die("index file corrupt");
run_diff_files(&rev, DIFF_RACY_IS_MODIFIED);
}
static void refresh(int verbose, const char **pathspec)
{
char *seen;
int i, specs;
for (specs = 0; pathspec[specs]; specs++)
/* nothing */;
seen = xcalloc(specs, 1);
if (read_cache() < 0)
die("index file corrupt");
refresh_index(&the_index, verbose ? 0 : REFRESH_QUIET, pathspec, seen);
for (i = 0; i < specs; i++) {
if (!seen[i])
die("pathspec '%s' did not match any files", pathspec[i]);
}
free(seen);
}
static int git_add_config(const char *var, const char *value)
{
if (!strcmp(var, "core.excludesfile")) {
if (!value)
die("core.excludesfile without value");
excludes_file = xstrdup(value);
return 0;
}
return git_default_config(var, value);
}
static struct lock_file lock_file;
static const char ignore_error[] =
"The following paths are ignored by one of your .gitignore files:\n";
int cmd_add(int argc, const char **argv, const char *prefix)
{
int i, newfd;
int verbose = 0, show_only = 0, ignored_too = 0, refresh_only = 0;
const char **pathspec;
struct dir_struct dir;
int add_interactive = 0;
for (i = 1; i < argc; i++) {
if (!strcmp("--interactive", argv[i]) ||
!strcmp("-i", argv[i]))
add_interactive++;
}
if (add_interactive) {
const char *args[] = { "add--interactive", NULL };
if (add_interactive != 1 || argc != 2)
die("add --interactive does not take any parameters");
execv_git_cmd(args);
exit(1);
}
git_config(git_add_config);
newfd = hold_locked_index(&lock_file, 1);
for (i = 1; i < argc; i++) {
const char *arg = argv[i];
if (arg[0] != '-')
break;
if (!strcmp(arg, "--")) {
i++;
break;
}
if (!strcmp(arg, "-n")) {
show_only = 1;
continue;
}
if (!strcmp(arg, "-f")) {
ignored_too = 1;
continue;
}
if (!strcmp(arg, "-v")) {
verbose = 1;
continue;
}
if (!strcmp(arg, "-u")) {
take_worktree_changes = 1;
continue;
}
if (!strcmp(arg, "--refresh")) {
refresh_only = 1;
continue;
}
usage(builtin_add_usage);
}
if (take_worktree_changes) {
update(verbose, prefix, argv + i);
goto finish;
}
if (argc <= i) {
fprintf(stderr, "Nothing specified, nothing added.\n");
fprintf(stderr, "Maybe you wanted to say 'git add .'?\n");
return 0;
}
pathspec = get_pathspec(prefix, argv + i);
if (refresh_only) {
refresh(verbose, pathspec);
goto finish;
}
fill_directory(&dir, pathspec, ignored_too);
if (show_only) {
const char *sep = "", *eof = "";
for (i = 0; i < dir.nr; i++) {
printf("%s%s", sep, dir.entries[i]->name);
sep = " ";
eof = "\n";
}
fputs(eof, stdout);
return 0;
}
if (read_cache() < 0)
die("index file corrupt");
if (dir.ignored_nr) {
fprintf(stderr, ignore_error);
for (i = 0; i < dir.ignored_nr; i++) {
fprintf(stderr, "%s\n", dir.ignored[i]->name);
}
fprintf(stderr, "Use -f if you really want to add them.\n");
die("no files added");
}
for (i = 0; i < dir.nr; i++)
add_file_to_cache(dir.entries[i]->name, verbose);
finish:
if (active_cache_changed) {
if (write_cache(newfd, active_cache, active_nr) ||
close(newfd) || commit_locked_index(&lock_file))
die("Unable to write new index file");
}
return 0;
}