for-each-ref: `:short` format for `refname`

Tries to shorten the refname to a non-ambiguous name.

Szeder Gábor noticed that the git bash completion takes a
tremendous amount of time to strip leading components from
heads and tags refs (i.e. refs/heads, refs/tags, ...). He
proposed a new atom called 'refbasename' which removes at
most two leading components from the ref name.

I myself, proposed a more dynamic solution, which strips off
common leading components with the matched pattern.

But the current bash solution and both proposals suffer from
one mayor problem: ambiguous refs.

A ref is ambiguous, if it resolves to more than one full refs.
I.e. given the refs refs/heads/xyzzy and refs/tags/xyzzy. The
(short) ref xyzzy can point to both refs.

( Note: Its irrelevant whether the referenced objects are the
  same or not. )

This proposal solves this by checking for ambiguity of the
shorten ref name.

The shortening is done with the same rules for resolving refs
but in the reverse order. The short name is checked if it
resolves to a different ref.

To continue the above example, the output would be like this:

heads/xyzzy
xyzzy

So, if you want just tags, xyzzy is not ambiguous, because it
will resolve to a tag. If you need the heads you get a also
a non-ambiguous short form of the ref.

To integrate this new format into the bash completion to get
only non-ambiguous refs is beyond the scope of this patch.
Signed-off-by: NBert Wesarg <bert.wesarg@googlemail.com>
Signed-off-by: NJunio C Hamano <gitster@pobox.com>

Documentation/git-for-each-ref.txt

@@ -74,6 +74,7 @@ For all objects, the following names can be used:
 
 refname::
 	The name of the ref (the part after $GIT_DIR/).
+	For a non-ambiguous short name of the ref append `:short`.
 
 objecttype::
 	The type of the object (`blob`, `tree`, `commit`, `tag`).

builtin-for-each-ref.c

@@ -545,6 +545,107 @@ static void grab_values(struct atom_value *val, int deref, struct object *obj, v
 	}
 }
 
+/*
+ * generate a format suitable for scanf from a ref_rev_parse_rules
+ * rule, that is replace the "%.*s" spec with a "%s" spec
+ */
+static void gen_scanf_fmt(char *scanf_fmt, const char *rule)
+{
+	char *spec;
+
+	spec = strstr(rule, "%.*s");
+	if (!spec || strstr(spec + 4, "%.*s"))
+		die("invalid rule in ref_rev_parse_rules: %s", rule);
+
+	/* copy all until spec */
+	strncpy(scanf_fmt, rule, spec - rule);
+	scanf_fmt[spec - rule] = '\0';
+	/* copy new spec */
+	strcat(scanf_fmt, "%s");
+	/* copy remaining rule */
+	strcat(scanf_fmt, spec + 4);
+
+	return;
+}
+
+/*
+ * Shorten the refname to an non-ambiguous form
+ */
+static char *get_short_ref(struct refinfo *ref)
+{
+	int i;
+	static char **scanf_fmts;
+	static int nr_rules;
+	char *short_name;
+
+	/* pre generate scanf formats from ref_rev_parse_rules[] */
+	if (!nr_rules) {
+		size_t total_len = 0;
+
+		/* the rule list is NULL terminated, count them first */
+		for (; ref_rev_parse_rules[nr_rules]; nr_rules++)
+			/* no +1 because strlen("%s") < strlen("%.*s") */
+			total_len += strlen(ref_rev_parse_rules[nr_rules]);
+
+		scanf_fmts = xmalloc(nr_rules * sizeof(char *) + total_len);
+
+		total_len = 0;
+		for (i = 0; i < nr_rules; i++) {
+			scanf_fmts[i] = (char *)&scanf_fmts[nr_rules]
+					+ total_len;
+			gen_scanf_fmt(scanf_fmts[i], ref_rev_parse_rules[i]);
+			total_len += strlen(ref_rev_parse_rules[i]);
+		}
+	}
+
+	/* bail out if there are no rules */
+	if (!nr_rules)
+		return ref->refname;
+
+	/* buffer for scanf result, at most ref->refname must fit */
+	short_name = xstrdup(ref->refname);
+
+	/* skip first rule, it will always match */
+	for (i = nr_rules - 1; i > 0 ; --i) {
+		int j;
+		int short_name_len;
+
+		if (1 != sscanf(ref->refname, scanf_fmts[i], short_name))
+			continue;
+
+		short_name_len = strlen(short_name);
+
+		/*
+		 * check if the short name resolves to a valid ref,
+		 * but use only rules prior to the matched one
+		 */
+		for (j = 0; j < i; j++) {
+			const char *rule = ref_rev_parse_rules[j];
+			unsigned char short_objectname[20];
+
+			/*
+			 * the short name is ambiguous, if it resolves
+			 * (with this previous rule) to a valid ref
+			 * read_ref() returns 0 on success
+			 */
+			if (!read_ref(mkpath(rule, short_name_len, short_name),
+				      short_objectname))
+				break;
+		}
+
+		/*
+		 * short name is non-ambiguous if all previous rules
+		 * haven't resolved to a valid ref
+		 */
+		if (j == i)
+			return short_name;
+	}
+
+	free(short_name);
+	return ref->refname;
+}
+
+
 /*
  * Parse the object referred by ref, and grab needed value.
  */
@@ -570,13 +671,33 @@ static void populate_value(struct refinfo *ref)
 	for (i = 0; i < used_atom_cnt; i++) {
 		const char *name = used_atom[i];
 		struct atom_value *v = &ref->value[i];
-		if (!strcmp(name, "refname"))
-			v->s = ref->refname;
-		else if (!strcmp(name, "*refname")) {
-			int len = strlen(ref->refname);
-			char *s = xmalloc(len + 4);
-			sprintf(s, "%s^{}", ref->refname);
-			v->s = s;
+		int deref = 0;
+		if (*name == '*') {
+			deref = 1;
+			name++;
+		}
+		if (!prefixcmp(name, "refname")) {
+			const char *formatp = strchr(name, ':');
+			const char *refname = ref->refname;
+
+			/* look for "short" refname format */
+			if (formatp) {
+				formatp++;
+				if (!strcmp(formatp, "short"))
+					refname = get_short_ref(ref);
+				else
+					die("unknown refname format %s",
+					    formatp);
+			}
+
+			if (!deref)
+				v->s = refname;
+			else {
+				int len = strlen(refname);
+				char *s = xmalloc(len + 4);
+				sprintf(s, "%s^{}", refname);
+				v->s = s;
+			}
 		}
 	}
 

t/t6300-for-each-ref.sh

@@ -262,6 +262,50 @@ for i in "--perl --shell" "-s --python" "--python --tcl" "--tcl --perl"; do
 	"
 done
 
+cat >expected <<\EOF
+master
+testtag
+EOF
+
+test_expect_success 'Check short refname format' '
+	(git for-each-ref --format="%(refname:short)" refs/heads &&
+	git for-each-ref --format="%(refname:short)" refs/tags) >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'Check for invalid refname format' '
+	test_must_fail git for-each-ref --format="%(refname:INVALID)"
+'
+
+cat >expected <<\EOF
+heads/master
+master
+EOF
+
+test_expect_success 'Check ambiguous head and tag refs' '
+	git checkout -b newtag &&
+	echo "Using $datestamp" > one &&
+	git add one &&
+	git commit -m "Branch" &&
+	setdate_and_increment &&
+	git tag -m "Tagging at $datestamp" master &&
+	git for-each-ref --format "%(refname:short)" refs/heads/master refs/tags/master >actual &&
+	test_cmp expected actual
+'
+
+cat >expected <<\EOF
+heads/ambiguous
+ambiguous
+EOF
+
+test_expect_success 'Check ambiguous head and tag refs II' '
+	git checkout master &&
+	git tag ambiguous testtag^0 &&
+	git branch ambiguous testtag^0 &&
+	git for-each-ref --format "%(refname:short)" refs/heads/ambiguous refs/tags/ambiguous >actual &&
+	test_cmp expected actual
+'
+
 test_expect_success 'an unusual tag with an incomplete line' '
 
 	git tag -m "bogo" bogo &&