diff options
author | Junio C Hamano <gitster@pobox.com> | 2012-07-22 12:55:07 -0700 |
---|---|---|
committer | Junio C Hamano <gitster@pobox.com> | 2012-07-22 12:55:07 -0700 |
commit | 0958a24d7360759902f802744c0839c8029659d7 (patch) | |
tree | f22a0b0f2cb4dc8e7c4e0b5a053d0bac01c445bf | |
parent | 9a0231b395cb9720365b7066312eeaa86e37ed31 (diff) | |
parent | 31ffd0c0c1255cb7e9ba76192a70ae294faf95bf (diff) | |
download | git-0958a24d7360759902f802744c0839c8029659d7.tar.gz |
Merge branch 'jc/sha1-name-more'
Teaches the object name parser things like a "git describe" output
is always a commit object, "A" in "git log A" must be a committish,
and "A" and "B" in "git log A...B" both must be committish, etc., to
prolong the lifetime of abbreviated object names.
* jc/sha1-name-more: (27 commits)
t1512: match the "other" object names
t1512: ignore whitespaces in wc -l output
rev-parse --disambiguate=<prefix>
rev-parse: A and B in "rev-parse A..B" refer to committish
reset: the command takes committish
commit-tree: the command wants a tree and commits
apply: --build-fake-ancestor expects blobs
sha1_name.c: add support for disambiguating other types
revision.c: the "log" family, except for "show", takes committish
revision.c: allow handle_revision_arg() to take other flags
sha1_name.c: introduce get_sha1_committish()
sha1_name.c: teach lookup context to get_sha1_with_context()
sha1_name.c: many short names can only be committish
sha1_name.c: get_sha1_1() takes lookup flags
sha1_name.c: get_describe_name() by definition groks only commits
sha1_name.c: teach get_short_sha1() a commit-only option
sha1_name.c: allow get_short_sha1() to take other flags
get_sha1(): fix error status regression
sha1_name.c: restructure disambiguation of short names
sha1_name.c: correct misnamed "canonical" and "res"
...
-rw-r--r-- | Documentation/git-rev-parse.txt | 6 | ||||
-rw-r--r-- | builtin/apply.c | 2 | ||||
-rw-r--r-- | builtin/cat-file.c | 2 | ||||
-rw-r--r-- | builtin/commit-tree.c | 8 | ||||
-rw-r--r-- | builtin/log.c | 3 | ||||
-rw-r--r-- | builtin/pack-objects.c | 2 | ||||
-rw-r--r-- | builtin/reset.c | 10 | ||||
-rw-r--r-- | builtin/rev-parse.c | 14 | ||||
-rw-r--r-- | cache.h | 28 | ||||
-rw-r--r-- | commit.c | 2 | ||||
-rw-r--r-- | revision.c | 38 | ||||
-rw-r--r-- | revision.h | 5 | ||||
-rw-r--r-- | setup.c | 8 | ||||
-rw-r--r-- | sha1_name.c | 494 | ||||
-rwxr-xr-x | t/t1512-rev-parse-disambiguation.sh | 264 |
15 files changed, 714 insertions, 172 deletions
diff --git a/Documentation/git-rev-parse.txt b/Documentation/git-rev-parse.txt index 4cc3e9586f..3c63561f02 100644 --- a/Documentation/git-rev-parse.txt +++ b/Documentation/git-rev-parse.txt @@ -101,6 +101,12 @@ OPTIONS The option core.warnAmbiguousRefs is used to select the strict abbreviation mode. +--disambiguate=<prefix>:: + Show every object whose name begins with the given prefix. + The <prefix> must be at least 4 hexadecimal digits long to + avoid listing each and every object in the repository by + mistake. + --all:: Show all refs found in `refs/`. diff --git a/builtin/apply.c b/builtin/apply.c index ace04c453b..069cf341b6 100644 --- a/builtin/apply.c +++ b/builtin/apply.c @@ -3589,7 +3589,7 @@ static void build_fake_ancestor(struct patch *list, const char *filename) name = patch->old_name ? patch->old_name : patch->new_name; if (0 < patch->is_new) continue; - else if (get_sha1(patch->old_sha1_prefix, sha1)) + else if (get_sha1_blob(patch->old_sha1_prefix, sha1)) /* git diff has no index line for mode/type changes */ if (!patch->lines_added && !patch->lines_deleted) { if (get_current_sha1(patch->old_name, sha1)) diff --git a/builtin/cat-file.c b/builtin/cat-file.c index 36a9104433..af74e775a1 100644 --- a/builtin/cat-file.c +++ b/builtin/cat-file.c @@ -91,7 +91,7 @@ static int cat_one_file(int opt, const char *exp_type, const char *obj_name) unsigned long size; struct object_context obj_context; - if (get_sha1_with_context(obj_name, sha1, &obj_context)) + if (get_sha1_with_context(obj_name, 0, sha1, &obj_context)) die("Not a valid object name %s", obj_name); buf = NULL; diff --git a/builtin/commit-tree.c b/builtin/commit-tree.c index 164b655df9..cb982c5503 100644 --- a/builtin/commit-tree.c +++ b/builtin/commit-tree.c @@ -48,8 +48,8 @@ int cmd_commit_tree(int argc, const char **argv, const char *prefix) if (argc < 2 || !strcmp(argv[1], "-h")) usage(commit_tree_usage); - if (get_sha1(argv[1], tree_sha1)) - die("Not a valid object name %s", argv[1]); + if (get_sha1_tree(argv[1], tree_sha1)) + die("Not a valid tree object name %s", argv[1]); for (i = 1; i < argc; i++) { const char *arg = argv[i]; @@ -57,7 +57,7 @@ int cmd_commit_tree(int argc, const char **argv, const char *prefix) unsigned char sha1[20]; if (argc <= ++i) usage(commit_tree_usage); - if (get_sha1(argv[i], sha1)) + if (get_sha1_commit(argv[i], sha1)) die("Not a valid object name %s", argv[i]); assert_sha1_type(sha1, OBJ_COMMIT); new_parent(lookup_commit(sha1), &parents); @@ -104,7 +104,7 @@ int cmd_commit_tree(int argc, const char **argv, const char *prefix) continue; } - if (get_sha1(arg, tree_sha1)) + if (get_sha1_tree(arg, tree_sha1)) die("Not a valid object name %s", arg); if (got_tree) die("Cannot give more than one trees"); diff --git a/builtin/log.c b/builtin/log.c index adcbcf1f24..ecc2793690 100644 --- a/builtin/log.c +++ b/builtin/log.c @@ -367,6 +367,7 @@ int cmd_whatchanged(int argc, const char **argv, const char *prefix) rev.simplify_history = 0; memset(&opt, 0, sizeof(opt)); opt.def = "HEAD"; + opt.revarg_opt = REVARG_COMMITTISH; cmd_log_init(argc, argv, prefix, &rev, &opt); if (!rev.diffopt.output_format) rev.diffopt.output_format = DIFF_FORMAT_RAW; @@ -557,6 +558,7 @@ int cmd_log(int argc, const char **argv, const char *prefix) rev.always_show_header = 1; memset(&opt, 0, sizeof(opt)); opt.def = "HEAD"; + opt.revarg_opt = REVARG_COMMITTISH; cmd_log_init(argc, argv, prefix, &rev, &opt); return cmd_log_walk(&rev); } @@ -1132,6 +1134,7 @@ int cmd_format_patch(int argc, const char **argv, const char *prefix) rev.subject_prefix = fmt_patch_subject_prefix; memset(&s_r_opt, 0, sizeof(s_r_opt)); s_r_opt.def = "HEAD"; + s_r_opt.revarg_opt = REVARG_COMMITTISH; if (default_attach) { rev.mime_boundary = default_attach; diff --git a/builtin/pack-objects.c b/builtin/pack-objects.c index f3348208d8..782e7d0c38 100644 --- a/builtin/pack-objects.c +++ b/builtin/pack-objects.c @@ -2373,7 +2373,7 @@ static void get_object_list(int ac, const char **av) } die("not a rev '%s'", line); } - if (handle_revision_arg(line, &revs, flags, 1)) + if (handle_revision_arg(line, &revs, flags, REVARG_CANNOT_BE_FILENAME)) die("bad revision '%s'", line); } diff --git a/builtin/reset.c b/builtin/reset.c index 4cc34c9084..74442bd766 100644 --- a/builtin/reset.c +++ b/builtin/reset.c @@ -276,7 +276,7 @@ int cmd_reset(int argc, const char **argv, const char *prefix) * Otherwise, argv[i] could be either <rev> or <paths> and * has to be unambiguous. */ - else if (!get_sha1(argv[i], sha1)) { + else if (!get_sha1_committish(argv[i], sha1)) { /* * Ok, argv[i] looks like a rev; it should not * be a filename. @@ -289,9 +289,15 @@ int cmd_reset(int argc, const char **argv, const char *prefix) } } - if (get_sha1(rev, sha1)) + if (get_sha1_committish(rev, sha1)) die(_("Failed to resolve '%s' as a valid ref."), rev); + /* + * NOTE: As "git reset $treeish -- $path" should be usable on + * any tree-ish, this is not strictly correct. We are not + * moving the HEAD to any commit; we are merely resetting the + * entries in the index to that of a treeish. + */ commit = lookup_commit_reference(sha1); if (!commit) die(_("Could not parse object '%s'."), rev); diff --git a/builtin/rev-parse.c b/builtin/rev-parse.c index 13495b88f5..32788a9f86 100644 --- a/builtin/rev-parse.c +++ b/builtin/rev-parse.c @@ -195,6 +195,12 @@ static int anti_reference(const char *refname, const unsigned char *sha1, int fl return 0; } +static int show_abbrev(const unsigned char *sha1, void *cb_data) +{ + show_rev(NORMAL, sha1, NULL); + return 0; +} + static void show_datestring(const char *flag, const char *datestr) { static char buffer[100]; @@ -238,7 +244,7 @@ static int try_difference(const char *arg) next = "HEAD"; if (dotdot == arg) this = "HEAD"; - if (!get_sha1(this, sha1) && !get_sha1(next, end)) { + if (!get_sha1_committish(this, sha1) && !get_sha1_committish(next, end)) { show_rev(NORMAL, end, next); show_rev(symmetric ? NORMAL : REVERSED, sha1, this); if (symmetric) { @@ -278,7 +284,7 @@ static int try_parent_shorthands(const char *arg) return 0; *dotdot = 0; - if (get_sha1(arg, sha1)) + if (get_sha1_committish(arg, sha1)) return 0; if (!parents_only) @@ -589,6 +595,10 @@ int cmd_rev_parse(int argc, const char **argv, const char *prefix) for_each_ref(show_reference, NULL); continue; } + if (!prefixcmp(arg, "--disambiguate=")) { + for_each_abbrev(arg + 15, show_abbrev, NULL); + continue; + } if (!strcmp(arg, "--bisect")) { for_each_ref_in("refs/bisect/bad", show_reference, NULL); for_each_ref_in("refs/bisect/good", anti_reference, NULL); @@ -790,17 +790,25 @@ struct object_context { unsigned mode; }; +#define GET_SHA1_QUIETLY 01 +#define GET_SHA1_COMMIT 02 +#define GET_SHA1_COMMITTISH 04 +#define GET_SHA1_TREE 010 +#define GET_SHA1_TREEISH 020 +#define GET_SHA1_BLOB 040 +#define GET_SHA1_ONLY_TO_DIE 04000 + extern int get_sha1(const char *str, unsigned char *sha1); -extern int get_sha1_with_mode_1(const char *str, unsigned char *sha1, unsigned *mode, int only_to_die, const char *prefix); -static inline int get_sha1_with_mode(const char *str, unsigned char *sha1, unsigned *mode) -{ - return get_sha1_with_mode_1(str, sha1, mode, 0, NULL); -} -extern int get_sha1_with_context_1(const char *name, unsigned char *sha1, struct object_context *orc, int only_to_die, const char *prefix); -static inline int get_sha1_with_context(const char *str, unsigned char *sha1, struct object_context *orc) -{ - return get_sha1_with_context_1(str, sha1, orc, 0, NULL); -} +extern int get_sha1_commit(const char *str, unsigned char *sha1); +extern int get_sha1_committish(const char *str, unsigned char *sha1); +extern int get_sha1_tree(const char *str, unsigned char *sha1); +extern int get_sha1_treeish(const char *str, unsigned char *sha1); +extern int get_sha1_blob(const char *str, unsigned char *sha1); +extern void maybe_die_on_misspelt_object_name(const char *name, const char *prefix); +extern int get_sha1_with_context(const char *str, unsigned flags, unsigned char *sha1, struct object_context *orc); + +typedef int each_abbrev_fn(const unsigned char *sha1, void *); +extern int for_each_abbrev(const char *prefix, each_abbrev_fn, void *); /* * Try to read a SHA1 in hexadecimal format from the 40 characters @@ -68,7 +68,7 @@ struct commit *lookup_commit_reference_by_name(const char *name) unsigned char sha1[20]; struct commit *commit; - if (get_sha1(name, sha1)) + if (get_sha1_committish(name, sha1)) return NULL; commit = lookup_commit_reference(sha1); if (!commit || parse_commit(commit)) diff --git a/revision.c b/revision.c index 5b81a92e3a..c64bf68fa1 100644 --- a/revision.c +++ b/revision.c @@ -1000,7 +1000,7 @@ static int add_parents_only(struct rev_info *revs, const char *arg_, int flags) flags ^= UNINTERESTING; arg++; } - if (get_sha1(arg, sha1)) + if (get_sha1_committish(arg, sha1)) return 0; while (1) { it = get_reference(revs, arg, sha1, 0); @@ -1114,16 +1114,16 @@ static void prepare_show_merge(struct rev_info *revs) revs->limited = 1; } -int handle_revision_arg(const char *arg_, struct rev_info *revs, - int flags, - int cant_be_filename) +int handle_revision_arg(const char *arg_, struct rev_info *revs, int flags, unsigned revarg_opt) { - unsigned mode; + struct object_context oc; char *dotdot; struct object *object; unsigned char sha1[20]; int local_flags; const char *arg = arg_; + int cant_be_filename = revarg_opt & REVARG_CANNOT_BE_FILENAME; + unsigned get_sha1_flags = 0; dotdot = strstr(arg, ".."); if (dotdot) { @@ -1141,8 +1141,8 @@ int handle_revision_arg(const char *arg_, struct rev_info *revs, next = "HEAD"; if (dotdot == arg) this = "HEAD"; - if (!get_sha1(this, from_sha1) && - !get_sha1(next, sha1)) { + if (!get_sha1_committish(this, from_sha1) && + !get_sha1_committish(next, sha1)) { struct commit *a, *b; struct commit_list *exclude; @@ -1201,13 +1201,17 @@ int handle_revision_arg(const char *arg_, struct rev_info *revs, local_flags = UNINTERESTING; arg++; } - if (get_sha1_with_mode(arg, sha1, &mode)) + + if (revarg_opt & REVARG_COMMITTISH) + get_sha1_flags = GET_SHA1_COMMITTISH; + + if (get_sha1_with_context(arg, get_sha1_flags, sha1, &oc)) return revs->ignore_missing ? 0 : -1; if (!cant_be_filename) verify_non_filename(revs->prefix, arg); object = get_reference(revs, arg, sha1, flags ^ local_flags); add_rev_cmdline(revs, object, arg_, REV_CMD_REV, flags ^ local_flags); - add_pending_object_with_mode(revs, object, arg, mode); + add_pending_object_with_mode(revs, object, arg, oc.mode); return 0; } @@ -1257,7 +1261,7 @@ static void read_revisions_from_stdin(struct rev_info *revs, } die("options not supported in --stdin mode"); } - if (handle_revision_arg(sb.buf, revs, 0, 1)) + if (handle_revision_arg(sb.buf, revs, 0, REVARG_CANNOT_BE_FILENAME)) die("bad revision '%s'", sb.buf); } if (seen_dashdash) @@ -1708,7 +1712,7 @@ static int handle_revision_pseudo_opt(const char *submodule, */ int setup_revisions(int argc, const char **argv, struct rev_info *revs, struct setup_revision_opt *opt) { - int i, flags, left, seen_dashdash, read_from_stdin, got_rev_arg = 0; + int i, flags, left, seen_dashdash, read_from_stdin, got_rev_arg = 0, revarg_opt; struct cmdline_pathspec prune_data; const char *submodule = NULL; @@ -1736,6 +1740,9 @@ int setup_revisions(int argc, const char **argv, struct rev_info *revs, struct s /* Second, deal with arguments and options */ flags = 0; + revarg_opt = opt ? opt->revarg_opt : 0; + if (seen_dashdash) + revarg_opt |= REVARG_CANNOT_BE_FILENAME; read_from_stdin = 0; for (left = i = 1; i < argc; i++) { const char *arg = argv[i]; @@ -1771,7 +1778,8 @@ int setup_revisions(int argc, const char **argv, struct rev_info *revs, struct s continue; } - if (handle_revision_arg(arg, revs, flags, seen_dashdash)) { + + if (handle_revision_arg(arg, revs, flags, revarg_opt)) { int j; if (seen_dashdash || *arg == '^') die("bad revision '%s'", arg); @@ -1822,11 +1830,11 @@ int setup_revisions(int argc, const char **argv, struct rev_info *revs, struct s if (revs->def && !revs->pending.nr && !got_rev_arg) { unsigned char sha1[20]; struct object *object; - unsigned mode; - if (get_sha1_with_mode(revs->def, sha1, &mode)) + struct object_context oc; + if (get_sha1_with_context(revs->def, 0, sha1, &oc)) die("bad default revision '%s'", revs->def); object = get_reference(revs, revs->def, sha1, 0); - add_pending_object_with_mode(revs, object, revs->def, mode); + add_pending_object_with_mode(revs, object, revs->def, oc.mode); } /* Did the user ask for any diff output? Run the diff! */ diff --git a/revision.h b/revision.h index 863f4f6454..cb5ab3513b 100644 --- a/revision.h +++ b/revision.h @@ -184,6 +184,7 @@ struct setup_revision_opt { void (*tweak)(struct rev_info *, struct setup_revision_opt *); const char *submodule; int assume_dashdash; + unsigned revarg_opt; }; extern void init_revisions(struct rev_info *revs, const char *prefix); @@ -191,7 +192,9 @@ extern int setup_revisions(int argc, const char **argv, struct rev_info *revs, s extern void parse_revision_opt(struct rev_info *revs, struct parse_opt_ctx_t *ctx, const struct option *options, const char * const usagestr[]); -extern int handle_revision_arg(const char *arg, struct rev_info *revs,int flags,int cant_be_filename); +#define REVARG_CANNOT_BE_FILENAME 01 +#define REVARG_COMMITTISH 02 +extern int handle_revision_arg(const char *arg, struct rev_info *revs, int flags, unsigned revarg_opt); extern void reset_revision_walk(void); extern int prepare_revision_walk(struct rev_info *revs); @@ -77,9 +77,6 @@ static void NORETURN die_verify_filename(const char *prefix, const char *arg, int diagnose_misspelt_rev) { - unsigned char sha1[20]; - unsigned mode; - if (!diagnose_misspelt_rev) die("%s: no such path in the working tree.\n" "Use '-- <path>...' to specify paths that do not exist locally.", @@ -88,11 +85,10 @@ static void NORETURN die_verify_filename(const char *prefix, * Saying "'(icase)foo' does not exist in the index" when the * user gave us ":(icase)foo" is just stupid. A magic pathspec * begins with a colon and is followed by a non-alnum; do not - * let get_sha1_with_mode_1(only_to_die=1) to even trigger. + * let maybe_die_on_misspelt_object_name() even trigger. */ if (!(arg[0] == ':' && !isalnum(arg[1]))) - /* try a detailed diagnostic ... */ - get_sha1_with_mode_1(arg, sha1, &mode, 1, prefix); + maybe_die_on_misspelt_object_name(arg, prefix); /* ... or fall back the most general message. */ die("ambiguous argument '%s': unknown revision or path not in the working tree.\n" diff --git a/sha1_name.c b/sha1_name.c index 5d81ea0564..95003c77ea 100644 --- a/sha1_name.c +++ b/sha1_name.c @@ -9,14 +9,82 @@ static int get_sha1_oneline(const char *, unsigned char *, struct commit_list *); -static int find_short_object_filename(int len, const char *name, unsigned char *sha1) +typedef int (*disambiguate_hint_fn)(const unsigned char *, void *); + +struct disambiguate_state { + disambiguate_hint_fn fn; + void *cb_data; + unsigned char candidate[20]; + unsigned candidate_exists:1; + unsigned candidate_checked:1; + unsigned candidate_ok:1; + unsigned disambiguate_fn_used:1; + unsigned ambiguous:1; + unsigned always_call_fn:1; +}; + +static void update_candidates(struct disambiguate_state *ds, const unsigned char *current) +{ + if (ds->always_call_fn) { + ds->ambiguous = ds->fn(current, ds->cb_data) ? 1 : 0; + return; + } + if (!ds->candidate_exists) { + /* this is the first candidate */ + hashcpy(ds->candidate, current); + ds->candidate_exists = 1; + return; + } else if (!hashcmp(ds->candidate, current)) { + /* the same as what we already have seen */ + return; + } + + if (!ds->fn) { + /* cannot disambiguate between ds->candidate and current */ + ds->ambiguous = 1; + return; + } + + if (!ds->candidate_checked) { + ds->candidate_ok = ds->fn(ds->candidate, ds->cb_data); + ds->disambiguate_fn_used = 1; + ds->candidate_checked = 1; + } + + if (!ds->candidate_ok) { + /* discard the candidate; we know it does not satisify fn */ + hashcpy(ds->candidate, current); + ds->candidate_checked = 0; + return; + } + + /* if we reach this point, we know ds->candidate satisfies fn */ + if (ds->fn(current, ds->cb_data)) { + /* + * if both current and candidate satisfy fn, we cannot + * disambiguate. + */ + ds->candidate_ok = 0; + ds->ambiguous = 1; + } + + /* otherwise, current can be discarded and candidate is still good */ +} + +static void find_short_object_filename(int len, const char *hex_pfx, struct disambiguate_state *ds) { struct alternate_object_database *alt; char hex[40]; - int found = 0; static struct alternate_object_database *fakeent; if (!fakeent) { + /* + * Create a "fake" alternate object database that + * points to our own object database, to make it + * easier to get a temporary working space in + * alt->name/alt->base while iterating over the + * object databases including our own. + */ const char *objdir = get_object_directory(); int objdir_len = strlen(objdir); int entlen = objdir_len + 43; @@ -27,33 +95,28 @@ static int find_short_object_filename(int len, const char *name, unsigned char * } fakeent->next = alt_odb_list; - sprintf(hex, "%.2s", name); - for (alt = fakeent; alt && found < 2; alt = alt->next) { + sprintf(hex, "%.2s", hex_pfx); + for (alt = fakeent; alt && !ds->ambiguous; alt = alt->next) { struct dirent *de; DIR *dir; - sprintf(alt->name, "%.2s/", name); + sprintf(alt->name, "%.2s/", hex_pfx); dir = opendir(alt->base); if (!dir) continue; - while ((de = readdir(dir)) != NULL) { + + while (!ds->ambiguous && (de = readdir(dir)) != NULL) { + unsigned char sha1[20]; + if (strlen(de->d_name) != 38) continue; - if (memcmp(de->d_name, name + 2, len - 2)) + if (memcmp(de->d_name, hex_pfx + 2, len - 2)) continue; - if (!found) { - memcpy(hex + 2, de->d_name, 38); - found++; - } - else if (memcmp(hex + 2, de->d_name, 38)) { - found = 2; - break; - } + memcpy(hex + 2, de->d_name, 38); + if (!get_sha1_hex(hex, sha1)) + update_candidates(ds, sha1); } closedir(dir); } - if (found == 1) - return get_sha1_hex(hex, sha1) == 0; - return found; } static int match_sha(unsigned len, const unsigned char *a, const unsigned char *b) @@ -71,103 +134,157 @@ static int match_sha(unsigned len, const unsigned char *a, const unsigned char * return 1; } -static int find_short_packed_object(int len, const unsigned char *match, unsigned char *sha1) +static void unique_in_pack(int len, + const unsigned char *bin_pfx, + struct packed_git *p, + struct disambiguate_state *ds) { - struct packed_git *p; - const unsigned char *found_sha1 = NULL; - int found = 0; - - prepare_packed_git(); - for (p = packed_git; p && found < 2; p = p->next) { - uint32_t num, last; - uint32_t first = 0; - open_pack_index(p); - num = p->num_objects; - last = num; - while (first < last) { - uint32_t mid = (first + last) / 2; - const unsigned char *now; - int cmp; - - now = nth_packed_object_sha1(p, mid); - cmp = hashcmp(match, now); - if (!cmp) { - first = mid; - break; - } - if (cmp > 0) { - first = mid+1; - continue; - } - last = mid; + uint32_t num, last, i, first = 0; + const unsigned char *current = NULL; + + open_pack_index(p); + num = p->num_objects; + last = num; + while (first < last) { + uint32_t mid = (first + last) / 2; + const unsigned char *current; + int cmp; + + current = nth_packed_object_sha1(p, mid); + cmp = hashcmp(bin_pfx, current); + if (!cmp) { + first = mid; + break; } - if (first < num) { - const unsigned char *now, *next; - now = nth_packed_object_sha1(p, first); - if (match_sha(len, match, now)) { - next = nth_packed_object_sha1(p, first+1); - if (!next|| !match_sha(len, match, next)) { - /* unique within this pack */ - if (!found) { - found_sha1 = now; - found++; - } - else if (hashcmp(found_sha1, now)) { - found = 2; - break; - } - } - else { - /* not even unique within this pack */ - found = 2; - break; - } - } + if (cmp > 0) { + first = mid+1; + continue; } + last = mid; + } + + /* + * At this point, "first" is the location of the lowest object + * with an object name that could match "bin_pfx". See if we have + * 0, 1 or more objects that actually match(es). + */ + for (i = first; i < num && !ds->ambiguous; i++) { + current = nth_packed_object_sha1(p, i); + if (!match_sha(len, bin_pfx, current)) + break; + update_candidates(ds, current); } - if (found == 1) - hashcpy(sha1, found_sha1); - return found; +} + +static void find_short_packed_object(int len, const unsigned char *bin_pfx, + struct disambiguate_state *ds) +{ + struct packed_git *p; + + prepare_packed_git(); + for (p = packed_git; p && !ds->ambiguous; p = p->next) + unique_in_pack(len, bin_pfx, p, ds); } #define SHORT_NAME_NOT_FOUND (-1) #define SHORT_NAME_AMBIGUOUS (-2) -static int find_unique_short_object(int len, char *canonical, - unsigned char *res, unsigned char *sha1) +static int finish_object_disambiguation(struct disambiguate_state *ds, + unsigned char *sha1) { - int has_unpacked, has_packed; - unsigned char unpacked_sha1[20], packed_sha1[20]; + if (ds->ambiguous) + return SHORT_NAME_AMBIGUOUS; - prepare_alt_odb(); - has_unpacked = find_short_object_filename(len, canonical, unpacked_sha1); - has_packed = find_short_packed_object(len, res, packed_sha1); - if (!has_unpacked && !has_packed) + if (!ds->candidate_exists) return SHORT_NAME_NOT_FOUND; - if (1 < has_unpacked || 1 < has_packed) + + if (!ds->candidate_checked) + /* + * If this is the only candidate, there is no point + * calling the disambiguation hint callback. + * + * On the other hand, if the current candidate + * replaced an earlier candidate that did _not_ pass + * the disambiguation hint callback, then we do have + * more than one objects that match the short name + * given, so we should make sure this one matches; + * otherwise, if we discovered this one and the one + * that we previously discarded in the reverse order, + * we would end up showing different results in the + * same repository! + */ + ds->candidate_ok = (!ds->disambiguate_fn_used || + ds->fn(ds->candidate, ds->cb_data)); + + if (!ds->candidate_ok) return SHORT_NAME_AMBIGUOUS; - if (has_unpacked != has_packed) { - hashcpy(sha1, (has_packed ? packed_sha1 : unpacked_sha1)); + + hashcpy(sha1, ds->candidate); + return 0; +} + +static int disambiguate_commit_only(const unsigned char *sha1, void *cb_data_unused) +{ + int kind = sha1_object_info(sha1, NULL); + return kind == OBJ_COMMIT; +} + +static int disambiguate_committish_only(const unsigned char *sha1, void *cb_data_unused) +{ + struct object *obj; + int kind; + + kind = sha1_object_info(sha1, NULL); + if (kind == OBJ_COMMIT) + return 1; + if (kind != OBJ_TAG) return 0; - } - /* Both have unique ones -- do they match? */ - if (hashcmp(packed_sha1, unpacked_sha1)) - return SHORT_NAME_AMBIGUOUS; - hashcpy(sha1, packed_sha1); + + /* We need to do this the hard way... */ + obj = deref_tag(lookup_object(sha1), NULL, 0); + if (obj && obj->type == OBJ_COMMIT) + return 1; return 0; } -static int get_short_sha1(const char *name, int len, unsigned char *sha1, - int quietly) +static int disambiguate_tree_only(const unsigned char *sha1, void *cb_data_unused) { - int i, status; - char canonical[40]; - unsigned char res[20]; + int kind = sha1_object_info(sha1, NULL); + return kind == OBJ_TREE; +} - if (len < MINIMUM_ABBREV || len > 40) - return -1; - hashclr(res); - memset(canonical, 'x', 40); +static int disambiguate_treeish_only(const unsigned char *sha1, void *cb_data_unused) +{ + struct object *obj; + int kind; + + kind = sha1_object_info(sha1, NULL); + if (kind == OBJ_TREE || kind == OBJ_COMMIT) + return 1; + if (kind != OBJ_TAG) + return 0; + + /* We need to do this the hard way... */ + obj = deref_tag(lookup_object(sha1), NULL, 0); + if (obj && (obj->type == OBJ_TREE || obj->type == OBJ_COMMIT)) + return 1; + return 0; +} + +static int disambiguate_blob_only(const unsigned char *sha1, void *cb_data_unused) +{ + int kind = sha1_object_info(sha1, NULL); + return kind == OBJ_BLOB; +} + +static int prepare_prefixes(const char *name, int len, + unsigned char *bin_pfx, + char *hex_pfx) +{ + int i; + + hashclr(bin_pfx); + memset(hex_pfx, 'x', 40); for (i = 0; i < len ;i++) { unsigned char c = name[i]; unsigned char val; @@ -181,18 +298,76 @@ static int get_short_sha1(const char *name, int len, unsigned char *sha1, } else return -1; - canonical[i] = c; + hex_pfx[i] = c; if (!(i & 1)) val <<= 4; - res[i >> 1] |= val; + bin_pfx[i >> 1] |= val; } + return 0; +} + +static int get_short_sha1(const char *name, int len, unsigned char *sha1, + unsigned flags) +{ + int status; + char hex_pfx[40]; + unsigned char bin_pfx[20]; + struct disambiguate_state ds; + int quietly = !!(flags & GET_SHA1_QUIETLY); + + if (len < MINIMUM_ABBREV || len > 40) + return -1; + if (prepare_prefixes(name, len, bin_pfx, hex_pfx) < 0) + return -1; + + prepare_alt_odb(); + + memset(&ds, 0, sizeof(ds)); + if (flags & GET_SHA1_COMMIT) + ds.fn = disambiguate_commit_only; + else if (flags & GET_SHA1_COMMITTISH) + ds.fn = disambiguate_committish_only; + else if (flags & GET_SHA1_TREE) + ds.fn = disambiguate_tree_only; + else if (flags & GET_SHA1_TREEISH) + ds.fn = disambiguate_treeish_only; + else if (flags & GET_SHA1_BLOB) + ds.fn = disambiguate_blob_only; + + find_short_object_filename(len, hex_pfx, &ds); + find_short_packed_object(len, bin_pfx, &ds); + status = finish_object_disambiguation(&ds, sha1); - status = find_unique_short_object(i, canonical, res, sha1); if (!quietly && (status == SHORT_NAME_AMBIGUOUS)) - return error("short SHA1 %.*s is ambiguous.", len, canonical); + return error("short SHA1 %.*s is ambiguous.", len, hex_pfx); return status; } + +int for_each_abbrev(const char *prefix, each_abbrev_fn fn, void *cb_data) +{ + char hex_pfx[40]; + unsigned char bin_pfx[20]; + struct disambiguate_state ds; + int len = strlen(prefix); + + if (len < MINIMUM_ABBREV || len > 40) + return -1; + if (prepare_prefixes(prefix, len, bin_pfx, hex_pfx) < 0) + return -1; + + prepare_alt_odb(); + + memset(&ds, 0, sizeof(ds)); + ds.always_call_fn = 1; + ds.cb_data = cb_data; + ds.fn = fn; + + find_short_object_filename(len, hex_pfx, &ds); + find_short_packed_object(len, bin_pfx, &ds); + return ds.ambiguous; +} + const char *find_unique_abbrev(const unsigned char *sha1, int len) { int status, exists; @@ -204,7 +379,7 @@ const char *find_unique_abbrev(const unsigned char *sha1, int len) return hex; while (len < 40) { unsigned char sha1_ret[20]; - status = get_short_sha1(hex, len, sha1_ret, 1); + status = get_short_sha1(hex, len, sha1_ret, GET_SHA1_QUIETLY); if (exists ? !status : status == SHORT_NAME_NOT_FOUND) { @@ -255,7 +430,7 @@ static inline int upstream_mark(const char *string, int len) return 0; } -static int get_sha1_1(const char *name, int len, unsigned char *sha1); +static int get_sha1_1(const char *name, int len, unsigned char *sha1, unsigned lookup_flags); static int get_sha1_basic(const char *str, int len, unsigned char *sha1) { @@ -292,7 +467,7 @@ static int get_sha1_basic(const char *str, int len, unsigned char *sha1) ret = interpret_branch_name(str+at, &buf); if (ret > 0) { /* substitute this branch name and restart */ - return get_sha1_1(buf.buf, buf.len, sha1); + return get_sha1_1(buf.buf, buf.len, sha1, 0); } else if (ret == 0) { return -1; } @@ -362,7 +537,7 @@ static int get_parent(const char *name, int len, unsigned char *result, int idx) { unsigned char sha1[20]; - int ret = get_sha1_1(name, len, sha1); + int ret = get_sha1_1(name, len, sha1, GET_SHA1_COMMITTISH); struct commit *commit; struct commit_list *p; @@ -395,7 +570,7 @@ static int get_nth_ancestor(const char *name, int len, struct commit *commit; int ret; - ret = get_sha1_1(name, len, sha1); + ret = get_sha1_1(name, len, sha1, GET_SHA1_COMMITTISH); if (ret) return ret; commit = lookup_commit_reference(sha1); @@ -441,6 +616,7 @@ static int peel_onion(const char *name, int len, unsigned char *sha1) unsigned char outer[20]; const char *sp; unsigned int expected_type = 0; + unsigned lookup_flags = 0; struct object *o; /* @@ -476,7 +652,10 @@ static int peel_onion(const char *name, int len, unsigned char *sha1) else return -1; - if (get_sha1_1(name, sp - name - 2, outer)) + if (expected_type == OBJ_COMMIT) + lookup_flags = GET_SHA1_COMMITTISH; + + if (get_sha1_1(name, sp - name - 2, outer, lookup_flags)) return -1; o = parse_object(outer); @@ -525,6 +704,7 @@ static int peel_onion(const char *name, int len, unsigned char *sha1) static int get_describe_name(const char *name, int len, unsigned char *sha1) { const char *cp; + unsigned flags = GET_SHA1_QUIETLY | GET_SHA1_COMMIT; for (cp = name + len - 1; name + 2 <= cp; cp--) { char ch = *cp; @@ -535,14 +715,14 @@ static int get_describe_name(const char *name, int len, unsigned char *sha1) if (ch == 'g' && cp[-1] == '-') { cp++; len -= cp - name; - return get_short_sha1(cp, len, sha1, 1); + return get_short_sha1(cp, len, sha1, flags); } } } return -1; } -static int get_sha1_1(const char *name, int len, unsigned char *sha1) +static int get_sha1_1(const char *name, int len, unsigned char *sha1, unsigned lookup_flags) { int ret, has_suffix; const char *cp; @@ -587,7 +767,7 @@ static int get_sha1_1(const char *name, int len, unsigned char *sha1) if (!ret) return 0; - return get_short_sha1(name, len, sha1, 0); + return get_short_sha1(name, len, sha1, lookup_flags); } /* @@ -769,7 +949,7 @@ int get_sha1_mb(const char *name, unsigned char *sha1) struct strbuf sb; strbuf_init(&sb, dots - name); strbuf_add(&sb, name, dots - name); - st = get_sha1(sb.buf, sha1_tmp); + st = get_sha1_committish(sb.buf, sha1_tmp); strbuf_release(&sb); } if (st) @@ -778,7 +958,7 @@ int get_sha1_mb(const char *name, unsigned char *sha1) if (!one) return -1; - if (get_sha1(dots[3] ? (dots + 3) : "HEAD", sha1_tmp)) + if (get_sha1_committish(dots[3] ? (dots + 3) : "HEAD", sha1_tmp)) return -1; two = lookup_commit_reference_gently(sha1_tmp, 0); if (!two) @@ -905,7 +1085,52 @@ int strbuf_check_branch_ref(struct strbuf *sb, const char *name) int get_sha1(const char *name, unsigned char *sha1) { struct object_context unused; - return get_sha1_with_context(name, sha1, &unused); + return get_sha1_with_context(name, 0, sha1, &unused); +} + +/* + * Many callers know that the user meant to name a committish by + * syntactical positions where the object name appears. Calling this + * function allows the machinery to disambiguate shorter-than-unique + * abbreviated object names between committish and others. + * + * Note that this does NOT error out when the named object is not a + * committish. It is merely to give a hint to the disambiguation + * machinery. + */ +int get_sha1_committish(const char *name, unsigned char *sha1) +{ + struct object_context unused; + return get_sha1_with_context(name, GET_SHA1_COMMITTISH, + sha1, &unused); +} + +int get_sha1_treeish(const char *name, unsigned char *sha1) +{ + struct object_context unused; + return get_sha1_with_context(name, GET_SHA1_TREEISH, + sha1, &unused); +} + +int get_sha1_commit(const char *name, unsigned char *sha1) +{ + struct object_context unused; + return get_sha1_with_context(name, GET_SHA1_COMMIT, + sha1, &unused); +} + +int get_sha1_tree(const char *name, unsigned char *sha1) +{ + struct object_context unused; + return get_sha1_with_context(name, GET_SHA1_TREE, + sha1, &unused); +} + +int get_sha1_blob(const char *name, unsigned char *sha1) +{ + struct object_context unused; + return get_sha1_with_context(name, GET_SHA1_BLOB, + sha1, &unused); } /* Must be called only when object_name:filename doesn't exist. */ @@ -1004,16 +1229,6 @@ static void diagnose_invalid_index_path(int stage, } -int get_sha1_with_mode_1(const char *name, unsigned char *sha1, unsigned *mode, - int only_to_die, const char *prefix) -{ - struct object_context oc; - int ret; - ret = get_sha1_with_context_1(name, sha1, &oc, only_to_die, prefix); - *mode = oc.mode; - return ret; -} - static char *resolve_relative_path(const char *rel) { if (prefixcmp(rel, "./") && prefixcmp(rel, "../")) @@ -1031,20 +1246,24 @@ static char *resolve_relative_path(const char *rel) rel); } -int get_sha1_with_context_1(const char *name, unsigned char *sha1, - struct object_context *oc, - int only_to_die, const char *prefix) +static int get_sha1_with_context_1(const char *name, + unsigned flags, + const char *prefix, + unsigned char *sha1, + struct object_context *oc) { int ret, bracket_depth; int namelen = strlen(name); const char *cp; + int only_to_die = flags & GET_SHA1_ONLY_TO_DIE; memset(oc, 0, sizeof(*oc)); oc->mode = S_IFINVALID; - ret = get_sha1_1(name, namelen, sha1); + ret = get_sha1_1(name, namelen, sha1, flags); if (!ret) return ret; - /* sha1:path --> object name of path in ent sha1 + /* + * sha1:path --> object name of path in ent sha1 * :path -> object name of absolute path in index * :./path -> object name of path relative to cwd in index * :[0-3]:path -> object name of path in index at stage @@ -1119,7 +1338,7 @@ int get_sha1_with_context_1(const char *name, unsigned char *sha1, strncpy(object_name, name, cp-name); object_name[cp-name] = '\0'; } - if (!get_sha1_1(name, cp-name, tree_sha1)) { + if (!get_sha1_1(name, cp-name, tree_sha1, GET_SHA1_TREEISH)) { const char *filename = cp+1; char *new_filename = NULL; @@ -1146,3 +1365,22 @@ int get_sha1_with_context_1(const char *name, unsigned char *sha1, } return ret; } + +/* + * Call this function when you know "name" given by the end user must + * name an object but it doesn't; the function _may_ die with a better + * diagnostic message than "no such object 'name'", e.g. "Path 'doc' does not + * exist in 'HEAD'" when given "HEAD:doc", or it may return in which case + * you have a chance to diagnose the error further. + */ +void maybe_die_on_misspelt_object_name(const char *name, const char *prefix) +{ + struct object_context oc; + unsigned char sha1[20]; + get_sha1_with_context_1(name, GET_SHA1_ONLY_TO_DIE, prefix, sha1, &oc); +} + +int get_sha1_with_context(const char *str, unsigned flags, unsigned char *sha1, struct object_context *orc) +{ + return get_sha1_with_context_1(str, flags, NULL, sha1, orc); +} diff --git a/t/t1512-rev-parse-disambiguation.sh b/t/t1512-rev-parse-disambiguation.sh new file mode 100755 index 0000000000..6b3d797cea --- /dev/null +++ b/t/t1512-rev-parse-disambiguation.sh @@ -0,0 +1,264 @@ +#!/bin/sh + +test_description='object name disambiguation + +Create blobs, trees, commits and a tag that all share the same +prefix, and make sure "git rev-parse" can take advantage of +type information to disambiguate short object names that are +not necessarily unique. + +The final history used in the test has five commits, with the bottom +one tagged as v1.0.0. They all have one regular file each. + + +-------------------------------------------+ + | | + | .-------b3wettvi---- ad2uee | + | / / | + | a2onsxbvj---czy8f73t--ioiley5o | + | | + +-------------------------------------------+ + +' + +. ./test-lib.sh + +test_expect_success 'blob and tree' ' + test_tick && + ( + for i in 0 1 2 3 4 5 6 7 8 9 + do + echo $i + done + echo + echo b1rwzyc3 + ) >a0blgqsjc && + + # create one blob 0000000000b36 + git add a0blgqsjc && + + # create one tree 0000000000cdc + git write-tree +' + +test_expect_success 'warn ambiguity when no candidate matches type hint' ' + test_must_fail git rev-parse --verify 000000000^{commit} 2>actual && + grep "short SHA1 000000000 is ambiguous" actual +' + +test_expect_success 'disambiguate tree-ish' ' + # feed tree-ish in an unambiguous way + git rev-parse --verify 0000000000cdc:a0blgqsjc && + + # ambiguous at the object name level, but there is only one + # such tree-ish (the other is a blob) + git rev-parse --verify 000000000:a0blgqsjc +' + +test_expect_success 'disambiguate blob' ' + sed -e "s/|$//" >patch <<-EOF && + diff --git a/frotz b/frotz + index 000000000..ffffff 100644 + --- a/frotz + +++ b/frotz + @@ -10,3 +10,4 @@ + 9 + | + b1rwzyc3 + +irwry + EOF + ( + GIT_INDEX_FILE=frotz && + export GIT_INDEX_FILE && + git apply --build-fake-ancestor frotz patch && + git cat-file blob :frotz >actual + ) && + test_cmp a0blgqsjc actual +' + +test_expect_success 'disambiguate tree' ' + commit=$(echo "d7xm" | git commit-tree 000000000) && + test $(git rev-parse $commit^{tree}) = $(git rev-parse 0000000000cdc) +' + +test_expect_success 'first commit' ' + # create one commit 0000000000e4f + git commit -m a2onsxbvj +' + +test_expect_success 'disambiguate commit-ish' ' + # feed commit-ish in an unambiguous way + git rev-parse --verify 0000000000e4f^{commit} && + + # ambiguous at the object name level, but there is only one + # such commit (the others are tree and blob) + git rev-parse --verify 000000000^{commit} && + + # likewise + git rev-parse --verify 000000000^0 +' + +test_expect_success 'disambiguate commit' ' + commit=$(echo "hoaxj" | git commit-tree 0000000000cdc -p 000000000) && + test $(git rev-parse $commit^) = $(git rev-parse 0000000000e4f) +' + +test_expect_success 'log name1..name2 takes only commit-ishes on both ends' ' + git log 000000000..000000000 && + git log ..000000000 && + git log 000000000.. && + git log 000000000...000000000 && + git log ...000000000 && + git log 000000000... +' + +test_expect_success 'rev-parse name1..name2 takes only commit-ishes on both ends' ' + git rev-parse 000000000..000000000 && + git rev-parse ..000000000 && + git rev-parse 000000000.. +' + +test_expect_success 'git log takes only commit-ish' ' + git log 000000000 +' + +test_expect_success 'git reset takes only commit-ish' ' + git reset 000000000 +' + +test_expect_success 'first tag' ' + # create one tag 0000000000f8f + git tag -a -m j7cp83um v1.0.0 +' + +test_expect_failure 'two semi-ambiguous commit-ish' ' + # Once the parser becomes ultra-smart, it could notice that + # 110282 before ^{commit} name many different objects, but + # that only two (HEAD and v1.0.0 tag) can be peeled to commit, + # and that peeling them down to commit yield the same commit + # without ambiguity. + git rev-parse --verify 110282^{commit} && + + # likewise + git log 000000000..000000000 && + git log ..000000000 && + git log 000000000.. && + git log 000000000...000000000 && + git log ...000000000 && + git log 000000000... +' + +test_expect_failure 'three semi-ambiguous tree-ish' ' + # Likewise for tree-ish. HEAD, v1.0.0 and HEAD^{tree} share + # the prefix but peeling them to tree yields the same thing + git rev-parse --verify 000000000^{tree} +' + +test_expect_success 'parse describe name' ' + # feed an unambiguous describe name + git rev-parse --verify v1.0.0-0-g0000000000e4f && + + # ambiguous at the object name level, but there is only one + # such commit (others are blob, tree and tag) + git rev-parse --verify v1.0.0-0-g000000000 +' + +test_expect_success 'more history' ' + # commit 0000000000043 + git mv a0blgqsjc d12cr3h8t && + echo h62xsjeu >>d12cr3h8t && + git add d12cr3h8t && + + test_tick && + git commit -m czy8f73t && + + # commit 00000000008ec + git mv d12cr3h8t j000jmpzn && + echo j08bekfvt >>j000jmpzn && + git add j000jmpzn && + + test_tick && + git commit -m ioiley5o && + + # commit 0000000005b0 + git checkout v1.0.0^0 && + git mv a0blgqsjc f5518nwu && + + for i in h62xsjeu j08bekfvt kg7xflhm + do + echo $i + done >>f5518nwu && + git add f5518nwu && + + test_tick && + git commit -m b3wettvi && + side=$(git rev-parse HEAD) && + + # commit 000000000066 + git checkout master && + + # If you use recursive, merge will fail and you will need to + # clean up a0blgqsjc as well. If you use resolve, merge will + # succeed. + test_might_fail git merge --no-commit -s recursive $side && + git rm -f f5518nwu j000jmpzn && + + test_might_fail git rm -f a0blgqsjc && + ( + git cat-file blob $side:f5518nwu + echo j3l0i9s6 + ) >ab2gs879 && + git add ab2gs879 && + + test_tick && + git commit -m ad2uee + +' + +test_expect_failure 'parse describe name taking advantage of generation' ' + # ambiguous at the object name level, but there is only one + # such commit at generation 0 + git rev-parse --verify v1.0.0-0-g000000000 && + + # likewise for generation 2 and 4 + git rev-parse --verify v1.0.0-2-g000000000 && + git rev-parse --verify v1.0.0-4-g000000000 +' + +# Note: because rev-parse does not even try to disambiguate based on +# the generation number, this test currently succeeds for a wrong +# reason. When it learns to use the generation number, the previous +# test should succeed, and also this test should fail because the +# describe name used in the test with generation number can name two +# commits. Make sure that such a future enhancement does not randomly +# pick one. +test_expect_success 'parse describe name not ignoring ambiguity' ' + # ambiguous at the object name level, and there are two such + # commits at generation 1 + test_must_fail git rev-parse --verify v1.0.0-1-g000000000 +' + +test_expect_success 'ambiguous commit-ish' ' + # Now there are many commits that begin with the + # common prefix, none of these should pick one at + # random. They all should result in ambiguity errors. + test_must_fail git rev-parse --verify 110282^{commit} && + + # likewise + test_must_fail git log 000000000..000000000 && + test_must_fail git log ..000000000 && + test_must_fail git log 000000000.. && + test_must_fail git log 000000000...000000000 && + test_must_fail git log ...000000000 && + test_must_fail git log 000000000... +' + +test_expect_success 'rev-parse --disambiguate' ' + # The test creates 16 objects that share the prefix and two + # commits created by commit-tree in earlier tests share a + # different prefix. + git rev-parse --disambiguate=000000000 >actual && + test $(wc -l <actual) = 16 && + test "$(sed -e "s/^\(.........\).*/\1/" actual | sort -u)" = 000000000 +' + +test_done |