1
0
Fork 0
mirror of https://github.com/git/git.git synced 2024-05-04 06:36:35 +02:00
git/builtin/diff-tree.c
Torsten Bögershausen 5c327502db MacOS: precompose_argv_prefix()
The following sequence leads to a "BUG" assertion running under MacOS:

  DIR=git-test-restore-p
  Adiarnfd=$(printf 'A\314\210')
  DIRNAME=xx${Adiarnfd}yy
  mkdir $DIR &&
  cd $DIR &&
  git init &&
  mkdir $DIRNAME &&
  cd $DIRNAME &&
  echo "Initial" >file &&
  git add file &&
  echo "One more line" >>file &&
  echo y | git restore -p .

 Initialized empty Git repository in /tmp/git-test-restore-p/.git/
 BUG: pathspec.c:495: error initializing pathspec_item
 Cannot close git diff-index --cached --numstat
 [snip]

The command `git restore` is run from a directory inside a Git repo.
Git needs to split the $CWD into 2 parts:
The path to the repo and "the rest", if any.
"The rest" becomes a "prefix" later used inside the pathspec code.

As an example, "/path/to/repo/dir-inside-repå" would determine
"/path/to/repo" as the root of the repo, the place where the
configuration file .git/config is found.

The rest becomes the prefix ("dir-inside-repå"), from where the
pathspec machinery expands the ".", more about this later.
If there is a decomposed form, (making the decomposing visible like this),
"dir-inside-rep°a" doesn't match "dir-inside-repå".

Git commands need to:

 (a) read the configuration variable "core.precomposeunicode"
 (b) precocompose argv[]
 (c) precompose the prefix, if there was any

The first commit,
76759c7dff "git on Mac OS and precomposed unicode"
addressed (a) and (b).

The call to precompose_argv() was added into parse-options.c,
because that seemed to be a good place when the patch was written.

Commands that don't use parse-options need to do (a) and (b) themselfs.

The commands `diff-files`, `diff-index`, `diff-tree` and `diff`
learned (a) and (b) in
commit 90a78b83e0 "diff: run arguments through precompose_argv"

Branch names (or refs in general) using decomposed code points
resulting in decomposed file names had been fixed in
commit 8e712ef6fc "Honor core.precomposeUnicode in more places"

The bug report from above shows 2 things:
- more commands need to handle precomposed unicode
- (c) should be implemented for all commands using pathspecs

Solution:
precompose_argv() now handles the prefix (if needed), and is renamed into
precompose_argv_prefix().

Inside this function the config variable core.precomposeunicode is read
into the global variable precomposed_unicode, as before.
This reading is skipped if precomposed_unicode had been read before.

The original patch for preocomposed unicode, 76759c7dff, placed
precompose_argv() into parse-options.c

Now add it into git.c::run_builtin() as well.  Existing precompose
calls in diff-files.c and others may become redundant, and if we
audit the callflows that reach these places to make sure that they
can never be reached without going through the new call added to
run_builtin(), we might be able to remove these existing ones.

But in this commit, we do not bother to do so and leave these
precompose callsites as they are.  Because precompose() is
idempotent and can be called on an already precomposed string
safely, this is safer than removing existing calls without fully
vetting the callflows.

There is certainly room for cleanups - this change intends to be a bug fix.
Cleanups needs more tests in e.g. t/t3910-mac-os-precompose.sh, and should
be done in future commits.

[1] git-bugreport-2021-01-06-1209.txt (git can't deal with special characters)
[2] https://lore.kernel.org/git/A102844A-9501-4A86-854D-E3B387D378AA@icloud.com/

Reported-by: Daniel Troger <random_n0body@icloud.com>
Helped-By: Philippe Blain <levraiphilippeblain@gmail.com>
Signed-off-by: Torsten Bögershausen <tboegi@web.de>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
2021-02-03 14:09:37 -08:00

221 lines
5.9 KiB
C

#define USE_THE_INDEX_COMPATIBILITY_MACROS
#include "cache.h"
#include "config.h"
#include "diff.h"
#include "commit.h"
#include "log-tree.h"
#include "builtin.h"
#include "submodule.h"
#include "repository.h"
static struct rev_info log_tree_opt;
static int diff_tree_commit_oid(const struct object_id *oid)
{
struct commit *commit = lookup_commit_reference(the_repository, oid);
if (!commit)
return -1;
return log_tree_commit(&log_tree_opt, commit);
}
/* Diff one or more commits. */
static int stdin_diff_commit(struct commit *commit, const char *p)
{
struct object_id oid;
struct commit_list **pptr = NULL;
/* Graft the fake parents locally to the commit */
while (isspace(*p++) && !parse_oid_hex(p, &oid, &p)) {
struct commit *parent = lookup_commit(the_repository, &oid);
if (!pptr) {
/* Free the real parent list */
free_commit_list(commit->parents);
commit->parents = NULL;
pptr = &(commit->parents);
}
if (parent) {
pptr = &commit_list_insert(parent, pptr)->next;
}
}
return log_tree_commit(&log_tree_opt, commit);
}
/* Diff two trees. */
static int stdin_diff_trees(struct tree *tree1, const char *p)
{
struct object_id oid;
struct tree *tree2;
if (!isspace(*p++) || parse_oid_hex(p, &oid, &p) || *p)
return error("Need exactly two trees, separated by a space");
tree2 = lookup_tree(the_repository, &oid);
if (!tree2 || parse_tree(tree2))
return -1;
printf("%s %s\n", oid_to_hex(&tree1->object.oid),
oid_to_hex(&tree2->object.oid));
diff_tree_oid(&tree1->object.oid, &tree2->object.oid,
"", &log_tree_opt.diffopt);
log_tree_diff_flush(&log_tree_opt);
return 0;
}
static int diff_tree_stdin(char *line)
{
int len = strlen(line);
struct object_id oid;
struct object *obj;
const char *p;
if (!len || line[len-1] != '\n')
return -1;
line[len-1] = 0;
if (parse_oid_hex(line, &oid, &p))
return -1;
obj = parse_object(the_repository, &oid);
if (!obj)
return -1;
if (obj->type == OBJ_COMMIT)
return stdin_diff_commit((struct commit *)obj, p);
if (obj->type == OBJ_TREE)
return stdin_diff_trees((struct tree *)obj, p);
error("Object %s is a %s, not a commit or tree",
oid_to_hex(&oid), type_name(obj->type));
return -1;
}
static const char diff_tree_usage[] =
"git diff-tree [--stdin] [-m] [-c | --cc] [-s] [-v] [--pretty] [-t] [-r] [--root] "
"[<common-diff-options>] <tree-ish> [<tree-ish>] [<path>...]\n"
" -r diff recursively\n"
" -c show combined diff for merge commits\n"
" --cc show combined diff for merge commits removing uninteresting hunks\n"
" --combined-all-paths\n"
" show name of file in all parents for combined diffs\n"
" --root include the initial commit as diff against /dev/null\n"
COMMON_DIFF_OPTIONS_HELP;
static void diff_tree_tweak_rev(struct rev_info *rev, struct setup_revision_opt *opt)
{
if (!rev->diffopt.output_format) {
if (rev->dense_combined_merges)
rev->diffopt.output_format = DIFF_FORMAT_PATCH;
else
rev->diffopt.output_format = DIFF_FORMAT_RAW;
}
}
int cmd_diff_tree(int argc, const char **argv, const char *prefix)
{
char line[1000];
struct object *tree1, *tree2;
static struct rev_info *opt = &log_tree_opt;
struct setup_revision_opt s_r_opt;
struct userformat_want w;
int read_stdin = 0;
int merge_base = 0;
if (argc == 2 && !strcmp(argv[1], "-h"))
usage(diff_tree_usage);
git_config(git_diff_basic_config, NULL); /* no "diff" UI options */
repo_init_revisions(the_repository, opt, prefix);
if (read_cache() < 0)
die(_("index file corrupt"));
opt->abbrev = 0;
opt->diff = 1;
opt->disable_stdin = 1;
memset(&s_r_opt, 0, sizeof(s_r_opt));
s_r_opt.tweak = diff_tree_tweak_rev;
prefix = precompose_argv_prefix(argc, argv, prefix);
argc = setup_revisions(argc, argv, opt, &s_r_opt);
memset(&w, 0, sizeof(w));
userformat_find_requirements(NULL, &w);
if (!opt->show_notes_given && w.notes)
opt->show_notes = 1;
if (opt->show_notes)
load_display_notes(&opt->notes_opt);
while (--argc > 0) {
const char *arg = *++argv;
if (!strcmp(arg, "--stdin")) {
read_stdin = 1;
continue;
}
if (!strcmp(arg, "--merge-base")) {
merge_base = 1;
continue;
}
usage(diff_tree_usage);
}
if (read_stdin && merge_base)
die(_("--stdin and --merge-base are mutually exclusive"));
if (merge_base && opt->pending.nr != 2)
die(_("--merge-base only works with two commits"));
/*
* NOTE! We expect "a..b" to expand to "^a b" but it is
* perfectly valid for revision range parser to yield "b ^a",
* which means the same thing. If we get the latter, i.e. the
* second one is marked UNINTERESTING, we recover the original
* order the user gave, i.e. "a..b", by swapping the trees.
*/
switch (opt->pending.nr) {
case 0:
if (!read_stdin)
usage(diff_tree_usage);
break;
case 1:
tree1 = opt->pending.objects[0].item;
diff_tree_commit_oid(&tree1->oid);
break;
case 2:
tree1 = opt->pending.objects[0].item;
tree2 = opt->pending.objects[1].item;
if (merge_base) {
struct object_id oid;
diff_get_merge_base(opt, &oid);
tree1 = lookup_object(the_repository, &oid);
} else if (tree2->flags & UNINTERESTING) {
SWAP(tree2, tree1);
}
diff_tree_oid(&tree1->oid, &tree2->oid, "", &opt->diffopt);
log_tree_diff_flush(opt);
break;
}
if (read_stdin) {
int saved_nrl = 0;
int saved_dcctc = 0;
if (opt->diffopt.detect_rename) {
if (!the_index.cache)
repo_read_index(the_repository);
opt->diffopt.setup |= DIFF_SETUP_USE_SIZE_CACHE;
}
while (fgets(line, sizeof(line), stdin)) {
struct object_id oid;
if (get_oid_hex(line, &oid)) {
fputs(line, stdout);
fflush(stdout);
}
else {
diff_tree_stdin(line);
if (saved_nrl < opt->diffopt.needed_rename_limit)
saved_nrl = opt->diffopt.needed_rename_limit;
if (opt->diffopt.degraded_cc_to_c)
saved_dcctc = 1;
}
}
opt->diffopt.degraded_cc_to_c = saved_dcctc;
opt->diffopt.needed_rename_limit = saved_nrl;
}
return diff_result_code(&opt->diffopt, 0);
}