Merge branch 'ab/ambiguous-object-name'

Error output given in response to an ambiguous object name has been
improved.

* ab/ambiguous-object-name:
  object-name: re-use "struct strbuf" in show_ambiguous_object()
  object-name: iterate ambiguous objects before showing header
  object-name: show date for ambiguous tag objects
  object-name: make ambiguous object output translatable
  object-name: explicitly handle bad tags in show_ambiguous_object()
  object-name: explicitly handle OBJ_BAD in show_ambiguous_object()
  object-name tests: add tests for ambiguous object blind spots

Author: gitster

object-name.c

@@ -351,35 +351,118 @@ static int init_object_disambiguation(struct repository *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)
 {
-	const struct disambiguate_state *ds = data;
-	struct strbuf desc = STRBUF_INIT;
+	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;
-			format_commit_message(commit, " %ad - %s", &desc, &pp);
+			format_commit_message(commit, "%ad", &date, &pp);
+			format_commit_message(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)
-			strbuf_addf(&desc, " %s", tag->tag);
+
+		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);
 	}
 
-	advise("  %s %s%s",
-	       repo_find_unique_abbrev(ds->repo, oid, DEFAULT_ABBREV),
-	       type_name(type) ? type_name(type) : "unknown type",
-	       desc.buf);
 
-	strbuf_release(&desc);
+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;
 }
 
@@ -476,6 +559,11 @@ static enum get_oid_result get_short_oid(struct repository *r,
 
 	if (!quietly && (status == SHORT_NAME_AMBIGUOUS)) {
 		struct oid_array collect = OID_ARRAY_INIT;
+		struct ambiguous_output out = {
+			.ds = &ds,
+			.sb = STRBUF_INIT,
+			.advice = STRBUF_INIT,
+		};
 
 		error(_("short object ID %s is ambiguous"), ds.hex_pfx);
 
@@ -488,13 +576,22 @@ static enum get_oid_result get_short_oid(struct repository *r,
 		if (!ds.ambiguous)
 			ds.fn = NULL;
 
-		advise(_("The candidates are:"));
 		repo_for_each_abbrev(r, ds.hex_pfx, collect_ambiguous, &collect);
 		sort_ambiguous_oid_array(r, &collect);
 
-		if (oid_array_for_each(&collect, show_ambiguous_object, &ds))
+		if (oid_array_for_each(&collect, show_ambiguous_object, &out))
 			BUG("show_ambiguous_object shouldn't return non-zero");
+
+		/*
+		 * TRANSLATORS: The argument is the list of ambiguous
+		 * objects composed in show_ambiguous_object(). See
+		 * its "TRANSLATORS" comments for details.
+		 */
+		advise(_("The candidates are:\n%s"), out.advice.buf);
+
 		oid_array_clear(&collect);
+		strbuf_release(&out.advice);
+		strbuf_release(&out.sb);
 	}
 
 	return status;

t/t1512-rev-parse-disambiguation.sh

@@ -25,6 +25,87 @@ export GIT_TEST_DEFAULT_INITIAL_BRANCH_NAME
 
 . ./test-lib.sh
 
+test_cmp_failed_rev_parse () {
+	dir=$1
+	rev=$2
+
+	cat >expect &&
+	test_must_fail git -C "$dir" rev-parse "$rev" 2>actual.raw &&
+	sed "s/\($rev\)[0-9a-f]*/\1.../" <actual.raw >actual &&
+	test_cmp expect actual
+}
+
+test_expect_success 'ambiguous blob output' '
+	git init --bare blob.prefix &&
+	(
+		cd blob.prefix &&
+
+		# Both start with "dead..", under both SHA-1 and SHA-256
+		echo brocdnra | git hash-object -w --stdin &&
+		echo brigddsv | git hash-object -w --stdin &&
+
+		# Both start with "beef.."
+		echo 1agllotbh | git hash-object -w --stdin &&
+		echo 1bbfctrkc | git hash-object -w --stdin
+	) &&
+
+	test_must_fail git -C blob.prefix rev-parse dead &&
+	test_cmp_failed_rev_parse blob.prefix beef <<-\EOF
+	error: short object ID beef... is ambiguous
+	hint: The candidates are:
+	hint:   beef... blob
+	hint:   beef... blob
+	fatal: ambiguous argument '\''beef...'\'': unknown revision or path not in the working tree.
+	Use '\''--'\'' to separate paths from revisions, like this:
+	'\''git <command> [<revision>...] -- [<file>...]'\''
+	EOF
+'
+
+test_expect_success 'ambiguous loose bad object parsed as OBJ_BAD' '
+	git init --bare blob.bad &&
+	(
+		cd blob.bad &&
+
+		# Both have the prefix "bad0"
+		echo xyzfaowcoh | git hash-object -t bad -w --stdin --literally &&
+		echo xyzhjpyvwl | git hash-object -t bad -w --stdin --literally
+	) &&
+
+	test_cmp_failed_rev_parse blob.bad bad0 <<-\EOF
+	error: short object ID bad0... is ambiguous
+	fatal: invalid object type
+	EOF
+'
+
+test_expect_success POSIXPERM 'ambigous zlib corrupt loose blob' '
+	git init --bare blob.corrupt &&
+	(
+		cd blob.corrupt &&
+
+		# Both have the prefix "cafe"
+		echo bnkxmdwz | git hash-object -w --stdin &&
+		oid=$(echo bmwsjxzi | git hash-object -w --stdin) &&
+
+		oidf=objects/$(test_oid_to_path "$oid") &&
+		chmod 755 $oidf &&
+		echo broken >$oidf
+	) &&
+
+	test_cmp_failed_rev_parse blob.corrupt cafe <<-\EOF
+	error: short object ID cafe... is ambiguous
+	error: inflate: data stream error (incorrect header check)
+	error: unable to unpack cafe... header
+	error: inflate: data stream error (incorrect header check)
+	error: unable to unpack cafe... header
+	hint: The candidates are:
+	hint:   cafe... [bad object]
+	hint:   cafe... blob
+	fatal: ambiguous argument '\''cafe...'\'': unknown revision or path not in the working tree.
+	Use '\''--'\'' to separate paths from revisions, like this:
+	'\''git <command> [<revision>...] -- [<file>...]'\''
+	EOF
+'
+
 if ! test_have_prereq SHA1
 then
 	skip_all='not using SHA-1 for objects'