git/object-name.c

#include "git-compat-util.h"
#include "object-name.h"
#include "advice.h"
#include "config.h"
#include "environment.h"
#include "gettext.h"
#include "hex.h"
#include "tag.h"
#include "commit.h"
#include "tree.h"
#include "blob.h"
#include "tree-walk.h"
#include "refs.h"
#include "remote.h"
#include "dir.h"
#include "oid-array.h"
#include "oidtree.h"
#include "packfile.h"
#include "pretty.h"
#include "object-store-ll.h"
#include "read-cache-ll.h"
#include "repository.h"
#include "setup.h"
#include "submodule.h"
#include "midx.h"
#include "commit-reach.h"
#include "date.h"

static int get_oid_oneline(struct repository *r, const char *, struct object_id *, struct commit_list *);

typedef int (*disambiguate_hint_fn)(struct repository *, const struct object_id *, void *);

struct disambiguate_state {
	int len; /* length of prefix in hex chars */
	char hex_pfx[GIT_MAX_HEXSZ + 1];
	struct object_id bin_pfx;

	struct repository *repo;
	disambiguate_hint_fn fn;
	void *cb_data;
	struct object_id candidate;
	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 struct object_id *current)
{
	if (ds->always_call_fn) {
		ds->ambiguous = ds->fn(ds->repo, current, ds->cb_data) ? 1 : 0;
		return;
	}
	if (!ds->candidate_exists) {
		/* this is the first candidate */
		oidcpy(&ds->candidate, current);
		ds->candidate_exists = 1;
		return;
	} else if (oideq(&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->repo, &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 satisfy fn */
		oidcpy(&ds->candidate, current);
		ds->candidate_checked = 0;
		return;
	}

	/* if we reach this point, we know ds->candidate satisfies fn */
	if (ds->fn(ds->repo, 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 int match_hash(unsigned, const unsigned char *, const unsigned char *);

static enum cb_next match_prefix(const struct object_id *oid, void *arg)
{
	struct disambiguate_state *ds = arg;
	/* no need to call match_hash, oidtree_each did prefix match */
	update_candidates(ds, oid);
	return ds->ambiguous ? CB_BREAK : CB_CONTINUE;
}

static void find_short_object_filename(struct disambiguate_state *ds)
{
	struct object_directory *odb;

	for (odb = ds->repo->objects->odb; odb && !ds->ambiguous; odb = odb->next)
		oidtree_each(odb_loose_cache(odb, &ds->bin_pfx),
				&ds->bin_pfx, ds->len, match_prefix, ds);
}

static int match_hash(unsigned len, const unsigned char *a, const unsigned char *b)
{
	do {
		if (*a != *b)
			return 0;
		a++;
		b++;
		len -= 2;
	} while (len > 1);
	if (len)
		if ((*a ^ *b) & 0xf0)
			return 0;
	return 1;
}

static void unique_in_midx(struct multi_pack_index *m,
			   struct disambiguate_state *ds)
{
	uint32_t num, i, first = 0;
	const struct object_id *current = NULL;
	num = m->num_objects;

	if (!num)
		return;

	bsearch_midx(&ds->bin_pfx, m, &first);

	/*
	 * 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++) {
		struct object_id oid;
		current = nth_midxed_object_oid(&oid, m, i);
		if (!match_hash(ds->len, ds->bin_pfx.hash, current->hash))
			break;
		update_candidates(ds, current);
	}
}

static void unique_in_pack(struct packed_git *p,
			   struct disambiguate_state *ds)
{
	uint32_t num, i, first = 0;

	if (p->multi_pack_index)
		return;

	if (open_pack_index(p) || !p->num_objects)
		return;

	num = p->num_objects;
	bsearch_pack(&ds->bin_pfx, p, &first);

	/*
	 * 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++) {
		struct object_id oid;
		nth_packed_object_id(&oid, p, i);
		if (!match_hash(ds->len, ds->bin_pfx.hash, oid.hash))
			break;
		update_candidates(ds, &oid);
	}
}

static void find_short_packed_object(struct disambiguate_state *ds)
{
	struct multi_pack_index *m;
	struct packed_git *p;

	for (m = get_multi_pack_index(ds->repo); m && !ds->ambiguous;
	     m = m->next)
		unique_in_midx(m, ds);
	for (p = get_packed_git(ds->repo); p && !ds->ambiguous;
	     p = p->next)
		unique_in_pack(p, ds);
}

static int finish_object_disambiguation(struct disambiguate_state *ds,
					struct object_id *oid)
{
	if (ds->ambiguous)
		return SHORT_NAME_AMBIGUOUS;

	if (!ds->candidate_exists)
		return MISSING_OBJECT;

	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->repo, &ds->candidate, ds->cb_data));

	if (!ds->candidate_ok)
		return SHORT_NAME_AMBIGUOUS;

	oidcpy(oid, &ds->candidate);
	return 0;
}

static int disambiguate_commit_only(struct repository *r,
				    const struct object_id *oid,
				    void *cb_data UNUSED)
{
	int kind = oid_object_info(r, oid, NULL);
	return kind == OBJ_COMMIT;
}

static int disambiguate_committish_only(struct repository *r,
					const struct object_id *oid,
					void *cb_data UNUSED)
{
	struct object *obj;
	int kind;

	kind = oid_object_info(r, oid, NULL);
	if (kind == OBJ_COMMIT)
		return 1;
	if (kind != OBJ_TAG)
		return 0;

	/* We need to do this the hard way... */
	obj = deref_tag(r, parse_object(r, oid), NULL, 0);
	if (obj && obj->type == OBJ_COMMIT)
		return 1;
	return 0;
}

static int disambiguate_tree_only(struct repository *r,
				  const struct object_id *oid,
				  void *cb_data UNUSED)
{
	int kind = oid_object_info(r, oid, NULL);
	return kind == OBJ_TREE;
}

static int disambiguate_treeish_only(struct repository *r,
				     const struct object_id *oid,
				     void *cb_data UNUSED)
{
	struct object *obj;
	int kind;

	kind = oid_object_info(r, oid, 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(r, parse_object(r, oid), NULL, 0);
	if (obj && (obj->type == OBJ_TREE || obj->type == OBJ_COMMIT))
		return 1;
	return 0;
}

static int disambiguate_blob_only(struct repository *r,
				  const struct object_id *oid,
				  void *cb_data UNUSED)
{
	int kind = oid_object_info(r, oid, NULL);
	return kind == OBJ_BLOB;
}

static disambiguate_hint_fn default_disambiguate_hint;

int set_disambiguate_hint_config(const char *var, const char *value)
{
	static const struct {
		const char *name;
		disambiguate_hint_fn fn;
	} hints[] = {
		{ "none", NULL },
		{ "commit", disambiguate_commit_only },
		{ "committish", disambiguate_committish_only },
		{ "tree", disambiguate_tree_only },
		{ "treeish", disambiguate_treeish_only },
		{ "blob", disambiguate_blob_only }
	};
	int i;

	if (!value)
		return config_error_nonbool(var);

	for (i = 0; i < ARRAY_SIZE(hints); i++) {
		if (!strcasecmp(value, hints[i].name)) {
			default_disambiguate_hint = hints[i].fn;
			return 0;
		}
	}

	return error("unknown hint type for '%s': %s", var, value);
}

static int init_object_disambiguation(struct repository *r,
				      const char *name, int len,
				      struct disambiguate_state *ds)
{
	int i;

	if (len < MINIMUM_ABBREV || len > the_hash_algo->hexsz)
		return -1;

	memset(ds, 0, sizeof(*ds));

	for (i = 0; i < len ;i++) {
		unsigned char c = name[i];
		unsigned char val;
		if (c >= '0' && c <= '9')
			val = c - '0';
		else if (c >= 'a' && c <= 'f')
			val = c - 'a' + 10;
		else if (c >= 'A' && c <='F') {
			val = c - 'A' + 10;
			c -= 'A' - 'a';
		}
		else
			return -1;
		ds->hex_pfx[i] = c;
		if (!(i & 1))
			val <<= 4;
		ds->bin_pfx.hash[i >> 1] |= val;
	}

	ds->len = len;
	ds->hex_pfx[len] = '\0';
	ds->repo = r;
	prepare_alt_odb(r);
	return 0;
}

struct ambiguous_output {
	const struct disambiguate_state *ds;
	struct strbuf advice;
	struct strbuf sb;
};

static int show_ambiguous_object(const struct object_id *oid, void *data)
{
	struct ambiguous_output *state = data;
	const struct disambiguate_state *ds = state->ds;
	struct strbuf *advice = &state->advice;
	struct strbuf *sb = &state->sb;
	int type;
	const char *hash;

	if (ds->fn && !ds->fn(ds->repo, oid, ds->cb_data))
		return 0;

	hash = repo_find_unique_abbrev(ds->repo, oid, DEFAULT_ABBREV);
	type = oid_object_info(ds->repo, oid, NULL);

	if (type < 0) {
		/*
		 * TRANSLATORS: This is a line of ambiguous object
		 * output shown when we cannot look up or parse the
		 * object in question. E.g. "deadbeef [bad object]".
		 */
		strbuf_addf(sb, _("%s [bad object]"), hash);
		goto out;
	}

	assert(type == OBJ_TREE || type == OBJ_COMMIT ||
	       type == OBJ_BLOB || type == OBJ_TAG);

	if (type == OBJ_COMMIT) {
		struct strbuf date = STRBUF_INIT;
		struct strbuf msg = STRBUF_INIT;
		struct commit *commit = lookup_commit(ds->repo, oid);

		if (commit) {
			struct pretty_print_context pp = {0};
			pp.date_mode.type = DATE_SHORT;
			repo_format_commit_message(the_repository, commit,
						   "%ad", &date, &pp);
			repo_format_commit_message(the_repository, commit,
						   "%s", &msg, &pp);
		}

		/*
		 * TRANSLATORS: This is a line of ambiguous commit
		 * object output. E.g.:
		 *
		 *    "deadbeef commit 2021-01-01 - Some Commit Message"
		 */
		strbuf_addf(sb, _("%s commit %s - %s"), hash, date.buf,
			    msg.buf);

		strbuf_release(&date);
		strbuf_release(&msg);
	} else if (type == OBJ_TAG) {
		struct tag *tag = lookup_tag(ds->repo, oid);

		if (!parse_tag(tag) && tag->tag) {
			/*
			 * TRANSLATORS: This is a line of ambiguous
			 * tag object output. E.g.:
			 *
			 *    "deadbeef tag 2022-01-01 - Some Tag Message"
			 *
			 * The second argument is the YYYY-MM-DD found
			 * in the tag.
			 *
			 * The third argument is the "tag" string
			 * from object.c.
			 */
			strbuf_addf(sb, _("%s tag %s - %s"), hash,
				    show_date(tag->date, 0, DATE_MODE(SHORT)),
				    tag->tag);
		} else {
			/*
			 * TRANSLATORS: This is a line of ambiguous
			 * tag object output where we couldn't parse
			 * the tag itself. E.g.:
			 *
			 *    "deadbeef [bad tag, could not parse it]"
			 */
			strbuf_addf(sb, _("%s [bad tag, could not parse it]"),
				    hash);
		}
	} else if (type == OBJ_TREE) {
		/*
		 * TRANSLATORS: This is a line of ambiguous <type>
		 * object output. E.g. "deadbeef tree".
		 */
		strbuf_addf(sb, _("%s tree"), hash);
	} else if (type == OBJ_BLOB) {
		/*
		 * TRANSLATORS: This is a line of ambiguous <type>
		 * object output. E.g. "deadbeef blob".
		 */
		strbuf_addf(sb, _("%s blob"), hash);
	}


out:
	/*
	 * TRANSLATORS: This is line item of ambiguous object output
	 * from describe_ambiguous_object() above. For RTL languages
	 * you'll probably want to swap the "%s" and leading " " space
	 * around.
	 */
	strbuf_addf(advice, _("  %s\n"), sb->buf);

	strbuf_reset(sb);
	return 0;
}

static int collect_ambiguous(const struct object_id *oid, void *data)
{
	oid_array_append(data, oid);
	return 0;
}

static int repo_collect_ambiguous(struct repository *r UNUSED,
				  const struct object_id *oid,
				  void *data)
{
	return collect_ambiguous(oid, data);
}

static int sort_ambiguous(const void *a, const void *b, void *ctx)
{
	struct repository *sort_ambiguous_repo = ctx;
	int a_type = oid_object_info(sort_ambiguous_repo, a, NULL);
	int b_type = oid_object_info(sort_ambiguous_repo, b, NULL);
	int a_type_sort;
	int b_type_sort;

	/*
	 * Sorts by hash within the same object type, just as
	 * oid_array_for_each_unique() would do.
	 */
	if (a_type == b_type)
		return oidcmp(a, b);

	/*
	 * Between object types show tags, then commits, and finally
	 * trees and blobs.
	 *
	 * The object_type enum is commit, tree, blob, tag, but we
	 * want tag, commit, tree blob. Cleverly (perhaps too
	 * cleverly) do that with modulus, since the enum assigns 1 to
	 * commit, so tag becomes 0.
	 */
	a_type_sort = a_type % 4;
	b_type_sort = b_type % 4;
	return a_type_sort > b_type_sort ? 1 : -1;
}

static void sort_ambiguous_oid_array(struct repository *r, struct oid_array *a)
{
	QSORT_S(a->oid, a->nr, sort_ambiguous, r);
}

static enum get_oid_result get_short_oid(struct repository *r,
					 const char *name, int len,
					 struct object_id *oid,
					 unsigned flags)
{
	int status;
	struct disambiguate_state ds;
	int quietly = !!(flags & GET_OID_QUIETLY);

	if (init_object_disambiguation(r, name, len, &ds) < 0)
		return -1;

	if (HAS_MULTI_BITS(flags & GET_OID_DISAMBIGUATORS))
		BUG("multiple get_short_oid disambiguator flags");

	if (flags & GET_OID_COMMIT)
		ds.fn = disambiguate_commit_only;
	else if (flags & GET_OID_COMMITTISH)
		ds.fn = disambiguate_committish_only;
	else if (flags & GET_OID_TREE)
		ds.fn = disambiguate_tree_only;
	else if (flags & GET_OID_TREEISH)
		ds.fn = disambiguate_treeish_only;
	else if (flags & GET_OID_BLOB)
		ds.fn = disambiguate_blob_only;
	else
		ds.fn = default_disambiguate_hint;

	find_short_object_filename(&ds);
	find_short_packed_object(&ds);