Merge branch 'zh/ref-filter-raw-data'

Prepare the "ref-filter" machinery that drives the "--format"
option of "git for-each-ref" and its friends to be used in "git
cat-file --batch".

* zh/ref-filter-raw-data:
  ref-filter: add %(rest) atom
  ref-filter: use non-const ref_format in *_atom_parser()
  ref-filter: --format=%(raw) support --perl
  ref-filter: add %(raw) atom
  ref-filter: add obj-type check in grab contents

Documentation/git-for-each-ref.txt

@@ -235,6 +235,15 @@ and `date` to extract the named component.  For email fields (`authoremail`,
 without angle brackets, and `:localpart` to get the part before the `@` symbol
 out of the trimmed email.
 
+The raw data in an object is `raw`.
+
+raw:size::
+	The raw data size of the object.
+
+Note that `--format=%(raw)` can not be used with `--python`, `--shell`, `--tcl`,
+because such language may not support arbitrary binary data in their string
+variable type.
+
 The message in a commit or a tag object is `contents`, from which
 `contents:<part>` can be used to extract various parts out of:
 

builtin/tag.c

@@ -146,7 +146,7 @@ static int verify_tag(const char *name, const char *ref,
 		      const struct object_id *oid, void *cb_data)
 {
 	int flags;
-	const struct ref_format *format = cb_data;
+	struct ref_format *format = cb_data;
 	flags = GPG_VERIFY_VERBOSE;
 
 	if (format->format)

quote.c

@@ -471,6 +471,23 @@ void perl_quote_buf(struct strbuf *sb, const char *src)
 	strbuf_addch(sb, sq);
 }
 
+void perl_quote_buf_with_len(struct strbuf *sb, const char *src, size_t len)
+{
+	const char sq = '\'';
+	const char bq = '\\';
+	const char *c = src;
+	const char *end = src + len;
+
+	strbuf_addch(sb, sq);
+	while (c != end) {
+		if (*c == sq || *c == bq)
+			strbuf_addch(sb, bq);
+		strbuf_addch(sb, *c);
+		c++;
+	}
+	strbuf_addch(sb, sq);
+}
+
 void python_quote_buf(struct strbuf *sb, const char *src)
 {
 	const char sq = '\'';

quote.h

@@ -95,6 +95,7 @@ char *quote_path(const char *in, const char *prefix, struct strbuf *out, unsigne
 
 /* quoting as a string literal for other languages */
 void perl_quote_buf(struct strbuf *sb, const char *src);
+void perl_quote_buf_with_len(struct strbuf *sb, const char *src, size_t len);
 void python_quote_buf(struct strbuf *sb, const char *src);
 void tcl_quote_buf(struct strbuf *sb, const char *src);
 void basic_regex_quote_buf(struct strbuf *sb, const char *src);

ref-filter.c

@@ -144,6 +144,7 @@ enum atom_type {
 	ATOM_BODY,
 	ATOM_TRAILERS,
 	ATOM_CONTENTS,
+	ATOM_RAW,
 	ATOM_UPSTREAM,
 	ATOM_PUSH,
 	ATOM_SYMREF,
@@ -156,6 +157,7 @@ enum atom_type {
 	ATOM_IF,
 	ATOM_THEN,
 	ATOM_ELSE,
+	ATOM_REST,
 };
 
 /*
@@ -189,6 +191,9 @@ static struct used_atom {
 			struct process_trailer_options trailer_opts;
 			unsigned int nlines;
 		} contents;
+		struct {
+			enum { RAW_BARE, RAW_LENGTH } option;
+		} raw_data;
 		struct {
 			cmp_status cmp_status;
 			const char *str;
@@ -223,7 +228,7 @@ static int strbuf_addf_ret(struct strbuf *sb, int ret, const char *fmt, ...)
 	return ret;
 }
 
-static int color_atom_parser(const struct ref_format *format, struct used_atom *atom,
+static int color_atom_parser(struct ref_format *format, struct used_atom *atom,
 			     const char *color_value, struct strbuf *err)
 {
 	if (!color_value)
@@ -261,7 +266,7 @@ static int refname_atom_parser_internal(struct refname_atom *atom, const char *a
 	return 0;
 }
 
-static int remote_ref_atom_parser(const struct ref_format *format, struct used_atom *atom,
+static int remote_ref_atom_parser(struct ref_format *format, struct used_atom *atom,
 				  const char *arg, struct strbuf *err)
 {
 	struct string_list params = STRING_LIST_INIT_DUP;
@@ -308,7 +313,7 @@ static int remote_ref_atom_parser(const struct ref_format *format, struct used_a
 	return 0;
 }
 
-static int objecttype_atom_parser(const struct ref_format *format, struct used_atom *atom,
+static int objecttype_atom_parser(struct ref_format *format, struct used_atom *atom,
 				  const char *arg, struct strbuf *err)
 {
 	if (arg)
@@ -320,7 +325,7 @@ static int objecttype_atom_parser(const struct ref_format *format, struct used_a
 	return 0;
 }
 
-static int objectsize_atom_parser(const struct ref_format *format, struct used_atom *atom,
+static int objectsize_atom_parser(struct ref_format *format, struct used_atom *atom,
 				  const char *arg, struct strbuf *err)
 {
 	if (!arg) {
@@ -340,7 +345,7 @@ static int objectsize_atom_parser(const struct ref_format *format, struct used_a
 	return 0;
 }
 
-static int deltabase_atom_parser(const struct ref_format *format, struct used_atom *atom,
+static int deltabase_atom_parser(struct ref_format *format, struct used_atom *atom,
 				 const char *arg, struct strbuf *err)
 {
 	if (arg)
@@ -352,7 +357,7 @@ static int deltabase_atom_parser(const struct ref_format *format, struct used_at
 	return 0;
 }
 
-static int body_atom_parser(const struct ref_format *format, struct used_atom *atom,
+static int body_atom_parser(struct ref_format *format, struct used_atom *atom,
 			    const char *arg, struct strbuf *err)
 {
 	if (arg)
@@ -361,7 +366,7 @@ static int body_atom_parser(const struct ref_format *format, struct used_atom *a
 	return 0;
 }
 
-static int subject_atom_parser(const struct ref_format *format, struct used_atom *atom,
+static int subject_atom_parser(struct ref_format *format, struct used_atom *atom,
 			       const char *arg, struct strbuf *err)
 {
 	if (!arg)
@@ -373,7 +378,7 @@ static int subject_atom_parser(const struct ref_format *format, struct used_atom
 	return 0;
 }
 
-static int trailers_atom_parser(const struct ref_format *format, struct used_atom *atom,
+static int trailers_atom_parser(struct ref_format *format, struct used_atom *atom,
 				const char *arg, struct strbuf *err)
 {
 	atom->u.contents.trailer_opts.no_divider = 1;
@@ -399,7 +404,7 @@ static int trailers_atom_parser(const struct ref_format *format, struct used_ato
 	return 0;
 }
 
-static int contents_atom_parser(const struct ref_format *format, struct used_atom *atom,
+static int contents_atom_parser(struct ref_format *format, struct used_atom *atom,
 				const char *arg, struct strbuf *err)
 {
 	if (!arg)
@@ -427,7 +432,19 @@ static int contents_atom_parser(const struct ref_format *format, struct used_ato
 	return 0;
 }
 
-static int oid_atom_parser(const struct ref_format *format, struct used_atom *atom,
+static int raw_atom_parser(struct ref_format *format, struct used_atom *atom,
+				const char *arg, struct strbuf *err)
+{
+	if (!arg)
+		atom->u.raw_data.option = RAW_BARE;
+	else if (!strcmp(arg, "size"))
+		atom->u.raw_data.option = RAW_LENGTH;
+	else
+		return strbuf_addf_ret(err, -1, _("unrecognized %%(raw) argument: %s"), arg);
+	return 0;
+}
+
+static int oid_atom_parser(struct ref_format *format, struct used_atom *atom,
 			   const char *arg, struct strbuf *err)
 {
 	if (!arg)
@@ -446,7 +463,7 @@ static int oid_atom_parser(const struct ref_format *format, struct used_atom *at
 	return 0;
 }
 
-static int person_email_atom_parser(const struct ref_format *format, struct used_atom *atom,
+static int person_email_atom_parser(struct ref_format *format, struct used_atom *atom,
 				    const char *arg, struct strbuf *err)
 {
 	if (!arg)
@@ -460,7 +477,7 @@ static int person_email_atom_parser(const struct ref_format *format, struct used
 	return 0;
 }
 
-static int refname_atom_parser(const struct ref_format *format, struct used_atom *atom,
+static int refname_atom_parser(struct ref_format *format, struct used_atom *atom,
 			       const char *arg, struct strbuf *err)
 {
 	return refname_atom_parser_internal(&atom->u.refname, arg, atom->name, err);
@@ -477,7 +494,7 @@ static align_type parse_align_position(const char *s)
 	return -1;
 }
 
-static int align_atom_parser(const struct ref_format *format, struct used_atom *atom,
+static int align_atom_parser(struct ref_format *format, struct used_atom *atom,
 			     const char *arg, struct strbuf *err)
 {
 	struct align *align = &atom->u.align;
@@ -529,7 +546,7 @@ static int align_atom_parser(const struct ref_format *format, struct used_atom *
 	return 0;
 }
 
-static int if_atom_parser(const struct ref_format *format, struct used_atom *atom,
+static int if_atom_parser(struct ref_format *format, struct used_atom *atom,
 			  const char *arg, struct strbuf *err)
 {
 	if (!arg) {
@@ -544,7 +561,16 @@ static int if_atom_parser(const struct ref_format *format, struct used_atom *ato
 	return 0;
 }
 
-static int head_atom_parser(const struct ref_format *format, struct used_atom *atom,
+static int rest_atom_parser(struct ref_format *format, struct used_atom *atom,
+			    const char *arg, struct strbuf *err)
+{
+	if (arg)
+		return strbuf_addf_ret(err, -1, _("%%(rest) does not take arguments"));
+	format->use_rest = 1;
+	return 0;
+}
+
+static int head_atom_parser(struct ref_format *format, struct used_atom *atom,
 			    const char *arg, struct strbuf *unused_err)
 {
 	atom->u.head = resolve_refdup("HEAD", RESOLVE_REF_READING, NULL, NULL);
@@ -555,7 +581,7 @@ static struct {
 	const char *name;
 	info_source source;
 	cmp_type cmp_type;
-	int (*parser)(const struct ref_format *format, struct used_atom *atom,
+	int (*parser)(struct ref_format *format, struct used_atom *atom,
 		      const char *arg, struct strbuf *err);
 } valid_atom[] = {
 	[ATOM_REFNAME] = { "refname", SOURCE_NONE, FIELD_STR, refname_atom_parser },
@@ -587,6 +613,7 @@ static struct {
 	[ATOM_BODY] = { "body", SOURCE_OBJ, FIELD_STR, body_atom_parser },
 	[ATOM_TRAILERS] = { "trailers", SOURCE_OBJ, FIELD_STR, trailers_atom_parser },
 	[ATOM_CONTENTS] = { "contents", SOURCE_OBJ, FIELD_STR, contents_atom_parser },
+	[ATOM_RAW] = { "raw", SOURCE_OBJ, FIELD_STR, raw_atom_parser },
 	[ATOM_UPSTREAM] = { "upstream", SOURCE_NONE, FIELD_STR, remote_ref_atom_parser },
 	[ATOM_PUSH] = { "push", SOURCE_NONE, FIELD_STR, remote_ref_atom_parser },
 	[ATOM_SYMREF] = { "symref", SOURCE_NONE, FIELD_STR, refname_atom_parser },
@@ -599,6 +626,7 @@ static struct {
 	[ATOM_IF] = { "if", SOURCE_NONE, FIELD_STR, if_atom_parser },
 	[ATOM_THEN] = { "then", SOURCE_NONE },
 	[ATOM_ELSE] = { "else", SOURCE_NONE },
+	[ATOM_REST] = { "rest", SOURCE_NONE, FIELD_STR, rest_atom_parser },
 	/*
 	 * Please update $__git_ref_fieldlist in git-completion.bash
 	 * when you add new atoms
@@ -621,16 +649,23 @@ struct ref_formatting_state {
 
 struct atom_value {
 	const char *s;
+	ssize_t s_size;
 	int (*handler)(struct atom_value *atomv, struct ref_formatting_state *state,
 		       struct strbuf *err);
 	uintmax_t value; /* used for sorting when not FIELD_STR */
 	struct used_atom *atom;
 };
 
+#define ATOM_SIZE_UNSPECIFIED (-1)
+
+#define ATOM_VALUE_INIT { \
+	.s_size = ATOM_SIZE_UNSPECIFIED \
+}
+
 /*
  * Used to parse format string and sort specifiers
  */
-static int parse_ref_filter_atom(const struct ref_format *format,
+static int parse_ref_filter_atom(struct ref_format *format,
 				 const char *atom, const char *ep,
 				 struct strbuf *err)
 {
@@ -645,13 +680,6 @@ static int parse_ref_filter_atom(const struct ref_format *format,
 		return strbuf_addf_ret(err, -1, _("malformed field name: %.*s"),
 				       (int)(ep-atom), atom);
 
-	/* Do we have the atom already used elsewhere? */
-	for (i = 0; i < used_atom_cnt; i++) {
-		int len = strlen(used_atom[i].name);
-		if (len == ep - atom && !memcmp(used_atom[i].name, atom, len))
-			return i;
-	}
-
 	/*
 	 * If the atom name has a colon, strip it and everything after
 	 * it off - it specifies the format for this entry, and
@@ -661,6 +689,13 @@ static int parse_ref_filter_atom(const struct ref_format *format,
 	arg = memchr(sp, ':', ep - sp);
 	atom_len = (arg ? arg : ep) - sp;
 
+	/* Do we have the atom already used elsewhere? */
+	for (i = 0; i < used_atom_cnt; i++) {
+		int len = strlen(used_atom[i].name);
+		if (len == ep - atom && !memcmp(used_atom[i].name, atom, len))
+			return i;
+	}
+
 	/* Is the atom a valid one? */
 	for (i = 0; i < ARRAY_SIZE(valid_atom); i++) {
 		int len = strlen(valid_atom[i].name);
@@ -710,17 +745,23 @@ static int parse_ref_filter_atom(const struct ref_format *format,
 	return at;
 }
 
-static void quote_formatting(struct strbuf *s, const char *str, int quote_style)
+static void quote_formatting(struct strbuf *s, const char *str, ssize_t len, int quote_style)
 {
 	switch (quote_style) {
 	case QUOTE_NONE:
-		strbuf_addstr(s, str);
+		if (len < 0)
+			strbuf_addstr(s, str);
+		else
+			strbuf_add(s, str, len);
 		break;
 	case QUOTE_SHELL:
 		sq_quote_buf(s, str);
 		break;
 	case QUOTE_PERL:
-		perl_quote_buf(s, str);
+		if (len < 0)
+			perl_quote_buf(s, str);
+		else
+			perl_quote_buf_with_len(s, str, len);
 		break;
 	case QUOTE_PYTHON:
 		python_quote_buf(s, str);
@@ -741,9 +782,11 @@ static int append_atom(struct atom_value *v, struct ref_formatting_state *state,
 	 * encountered.
 	 */
 	if (!state->stack->prev)
-		quote_formatting(&state->stack->output, v->s, state->quote_style);
-	else
+		quote_formatting(&state->stack->output, v->s, v->s_size, state->quote_style);
+	else if (v->s_size < 0)
 		strbuf_addstr(&state->stack->output, v->s);
+	else
+		strbuf_add(&state->stack->output, v->s, v->s_size);
 	return 0;
 }
 
@@ -843,21 +886,23 @@ static int if_atom_handler(struct atom_value *atomv, struct ref_formatting_state
 	return 0;
 }
 
-static int is_empty(const char *s)
+static int is_empty(struct strbuf *buf)
 {
-	while (*s != '\0') {
-		if (!isspace(*s))
-			return 0;
-		s++;
-	}
-	return 1;
-}
+	const char *cur = buf->buf;
+	const char *end = buf->buf + buf->len;
+
+	while (cur != end && (isspace(*cur)))
+		cur++;
+
+	return cur == end;
+ }
 
 static int then_atom_handler(struct atom_value *atomv, struct ref_formatting_state *state,
 			     struct strbuf *err)
 {
 	struct ref_formatting_stack *cur = state->stack;
 	struct if_then_else *if_then_else = NULL;
+	size_t str_len = 0;
 
 	if (cur->at_end == if_then_else_handler)
 		if_then_else = (struct if_then_else *)cur->at_end_data;
@@ -868,18 +913,22 @@ static int then_atom_handler(struct atom_value *atomv, struct ref_formatting_sta
 	if (if_then_else->else_atom_seen)
 		return strbuf_addf_ret(err, -1, _("format: %%(then) atom used after %%(else)"));
 	if_then_else->then_atom_seen = 1;
+	if (if_then_else->str)
+		str_len = strlen(if_then_else->str);
 	/*
 	 * If the 'equals' or 'notequals' attribute is used then
 	 * perform the required comparison. If not, only non-empty
 	 * strings satisfy the 'if' condition.
 	 */
 	if (if_then_else->cmp_status == COMPARE_EQUAL) {
-		if (!strcmp(if_then_else->str, cur->output.buf))
+		if (str_len == cur->output.len &&
+		    !memcmp(if_then_else->str, cur->output.buf, cur->output.len))
 			if_then_else->condition_satisfied = 1;
 	} else if (if_then_else->cmp_status == COMPARE_UNEQUAL) {
-		if (strcmp(if_then_else->str, cur->output.buf))
+		if (str_len != cur->output.len ||
+		    memcmp(if_then_else->str, cur->output.buf, cur->output.len))
 			if_then_else->condition_satisfied = 1;
-	} else if (cur->output.len && !is_empty(cur->output.buf))
+	} else if (cur->output.len && !is_empty(&cur->output))
 		if_then_else->condition_satisfied = 1;
 	strbuf_reset(&cur->output);
 	return 0;
@@ -925,7 +974,7 @@ static int end_atom_handler(struct atom_value *atomv, struct ref_formatting_stat
 	 * only on the topmost supporting atom.
 	 */
 	if (!current->prev->prev) {
-		quote_formatting(&s, current->output.buf, state->quote_style);
+		quote_formatting(&s, current->output.buf, current->output.len, state->quote_style);
 		strbuf_swap(&current->output, &s);
 	}
 	strbuf_release(&s);
@@ -955,6 +1004,11 @@ static const char *find_next(const char *cp)
 	return NULL;
 }
 
+static int reject_atom(enum atom_type atom_type)
+{
+	return atom_type == ATOM_REST;
+}
+
 /*
  * Make sure the format string is well formed, and parse out
  * the used atoms.
@@ -975,6 +1029,16 @@ int verify_ref_format(struct ref_format *format)
 		at = parse_ref_filter_atom(format, sp + 2, ep, &err);
 		if (at < 0)
 			die("%s", err.buf);
+		if (reject_atom(used_atom[at].atom_type))
+			die(_("this command reject atom %%(%.*s)"), (int)(ep - sp - 2), sp + 2);
+
+		if ((format->quote_style == QUOTE_PYTHON ||
+		     format->quote_style == QUOTE_SHELL ||
+		     format->quote_style == QUOTE_TCL) &&
+		     used_atom[at].atom_type == ATOM_RAW &&
+		     used_atom[at].u.raw_data.option == RAW_BARE)
+			die(_("--format=%.*s cannot be used with"
+			      "--python, --shell, --tcl"), (int)(ep - sp - 2), sp + 2);
 		cp = ep + 1;
 
 		if (skip_prefix(used_atom[at].name, "color:", &color))
@@ -1357,25 +1421,42 @@ static void append_lines(struct strbuf *out, const char *buf, unsigned long size
 }
 
 /* See grab_values */
-static void grab_sub_body_contents(struct atom_value *val, int deref, void *buf)
+static void grab_sub_body_contents(struct atom_value *val, int deref, struct expand_data *data)
 {
 	int i;
 	const char *subpos = NULL, *bodypos = NULL, *sigpos = NULL;
 	size_t sublen = 0, bodylen = 0, nonsiglen = 0, siglen = 0;
+	void *buf = data->content;
 
 	for (i = 0; i < used_atom_cnt; i++) {
 		struct used_atom *atom = &used_atom[i];
 		const char *name = atom->name;
 		struct atom_value *v = &val[i];
+		enum atom_type atom_type = atom->atom_type;
 
 		if (!!deref != (*name == '*'))
 			continue;
 		if (deref)
 			name++;
-		if (strcmp(name, "body") &&
-		    !starts_with(name, "subject") &&
-		    !starts_with(name, "trailers") &&
-		    !starts_with(name, "contents"))
+
+		if (atom_type == ATOM_RAW) {
+			unsigned long buf_size = data->size;
+
+			if (atom->u.raw_data.option == RAW_BARE) {
+				v->s = xmemdupz(buf, buf_size);
+				v->s_size = buf_size;
+			} else if (atom->u.raw_data.option == RAW_LENGTH) {
+				v->s = xstrfmt("%"PRIuMAX, (uintmax_t)buf_size);
+			}
+			continue;
+		}
+
+		if ((data->type != OBJ_TAG &&
+		     data->type != OBJ_COMMIT) ||
+		    (strcmp(name, "body") &&
+		     !starts_with(name, "subject") &&
+		     !starts_with(name, "trailers") &&
+		     !starts_with(name, "contents")))
 			continue;
 		if (!subpos)
 			find_subpos(buf,
@@ -1439,25 +1520,29 @@ static void fill_missing_values(struct atom_value *val)
  * pointed at by the ref itself; otherwise it is the object the
  * ref (which is a tag) refers to.
  */
-static void grab_values(struct atom_value *val, int deref, struct object *obj, void *buf)
+static void grab_values(struct atom_value *val, int deref, struct object *obj, struct expand_data *data)
 {
+	void *buf = data->content;
+
 	switch (obj->type) {
 	case OBJ_TAG:
 		grab_tag_values(val, deref, obj);
-		grab_sub_body_contents(val, deref, buf);
+		grab_sub_body_contents(val, deref, data);
 		grab_person("tagger", val, deref, buf);
 		break;
 	case OBJ_COMMIT:
 		grab_commit_values(val, deref, obj);
-		grab_sub_body_contents(val, deref, buf);
+		grab_sub_body_contents(val, deref, data);
 		grab_person("author", val, deref, buf);
 		grab_person("committer", val, deref, buf);
 		break;
 	case OBJ_TREE:
 		/* grab_tree_values(val, deref, obj, buf, sz); */
+		grab_sub_body_contents(val, deref, data);
 		break;
 	case OBJ_BLOB:
 		/* grab_blob_values(val, deref, obj, buf, sz); */
+		grab_sub_body_contents(val, deref, data);
 		break;
 	default:
 		die("Eh?  Object of type %d?", obj->type);
@@ -1679,7 +1764,7 @@ static int get_object(struct ref_array_item *ref, int deref, struct object **obj
 			return strbuf_addf_ret(err, -1, _("parse_object_buffer failed on %s for %s"),
 					       oid_to_hex(&oi->oid), ref->refname);
 		}
-		grab_values(ref->value, deref, *obj, oi->content);
+		grab_values(ref->value, deref, *obj, oi);
 	}
 
 	grab_common_values(ref->value, deref, oi);
@@ -1761,6 +1846,7 @@ static int populate_value(struct ref_array_item *ref, struct strbuf *err)
 		const char *refname;
 		struct branch *branch = NULL;
 
+		v->s_size = ATOM_SIZE_UNSPECIFIED;
 		v->handler = append_atom;
 		v->atom = atom;
 
@@ -1864,6 +1950,12 @@ static int populate_value(struct ref_array_item *ref, struct strbuf *err)
 			v->handler = else_atom_handler;
 			v->s = xstrdup("");
 			continue;
+		} else if (atom_type == ATOM_REST) {
+			if (ref->rest)
+				v->s = xstrdup(ref->rest);
+			else
+				v->s = xstrdup("");
+			continue;
 		} else
 			continue;
 
@@ -2081,6 +2173,7 @@ static struct ref_array_item *new_ref_array_item(const char *refname,
 
 	FLEX_ALLOC_STR(ref, refname, refname);
 	oidcpy(&ref->objectname, oid);
+	ref->rest = NULL;
 
 	return ref;
 }
@@ -2368,6 +2461,19 @@ static int compare_detached_head(struct ref_array_item *a, struct ref_array_item
 	return 0;
 }
 
+static int memcasecmp(const void *vs1, const void *vs2, size_t n)
+{
+	const char *s1 = vs1, *s2 = vs2;
+	const char *end = s1 + n;
+
+	for (; s1 < end; s1++, s2++) {
+		int diff = tolower(*s1) - tolower(*s2);
+		if (diff)
+			return diff;
+	}
+	return 0;
+}
+
 static int cmp_ref_sorting(struct ref_sorting *s, struct ref_array_item *a, struct ref_array_item *b)
 {
 	struct atom_value *va, *vb;
@@ -2388,10 +2494,29 @@ static int cmp_ref_sorting(struct ref_sorting *s, struct ref_array_item *a, stru
 	} else if (s->sort_flags & REF_SORTING_VERSION) {
 		cmp = versioncmp(va->s, vb->s);
 	} else if (cmp_type == FIELD_STR) {
-		int (*cmp_fn)(const char *, const char *);
-		cmp_fn = s->sort_flags & REF_SORTING_ICASE
-			? strcasecmp : strcmp;
-		cmp = cmp_fn(va->s, vb->s);
+		if (va->s_size < 0 && vb->s_size < 0) {
+			int (*cmp_fn)(const char *, const char *);
+			cmp_fn = s->sort_flags & REF_SORTING_ICASE
+				? strcasecmp : strcmp;
+			cmp = cmp_fn(va->s, vb->s);
+		} else {
+			size_t a_size = va->s_size < 0 ?
+					strlen(va->s) : va->s_size;
+			size_t b_size = vb->s_size < 0 ?
+					strlen(vb->s) : vb->s_size;
+			int (*cmp_fn)(const void *, const void *, size_t);
+			cmp_fn = s->sort_flags & REF_SORTING_ICASE
+				? memcasecmp : memcmp;
+
+			cmp = cmp_fn(va->s, vb->s, b_size > a_size ?
+				     a_size : b_size);
+			if (!cmp) {
+				if (a_size > b_size)
+					cmp = 1;
+				else if (a_size < b_size)
+					cmp = -1;
+			}
+		}
 	} else {
 		if (va->value < vb->value)
 			cmp = -1;
@@ -2461,9 +2586,9 @@ static void append_literal(const char *cp, const char *ep, struct ref_formatting
 }
 
 int format_ref_array_item(struct ref_array_item *info,
-			   const struct ref_format *format,
-			   struct strbuf *final_buf,
-			   struct strbuf *error_buf)
+			  struct ref_format *format,
+			  struct strbuf *final_buf,
+			  struct strbuf *error_buf)
 {
 	const char *cp, *sp, *ep;
 	struct ref_formatting_state state = REF_FORMATTING_STATE_INIT;
@@ -2490,7 +2615,7 @@ int format_ref_array_item(struct ref_array_item *info,
 		append_literal(cp, sp, &state);
 	}
 	if (format->need_color_reset_at_eol) {
-		struct atom_value resetv;
+		struct atom_value resetv = ATOM_VALUE_INIT;
 		resetv.s = GIT_COLOR_RESET;
 		if (append_atom(&resetv, &state, error_buf)) {
 			pop_stack_element(&state.stack);
@@ -2507,7 +2632,7 @@ int format_ref_array_item(struct ref_array_item *info,
 }
 
 void pretty_print_ref(const char *name, const struct object_id *oid,
-		      const struct ref_format *format)
+		      struct ref_format *format)
 {
 	struct ref_array_item *ref_item;
 	struct strbuf output = STRBUF_INIT;

ref-filter.h

@@ -38,6 +38,7 @@ struct ref_sorting {
 
 struct ref_array_item {
 	struct object_id objectname;
+	const char *rest;
 	int flag;
 	unsigned int kind;
 	const char *symref;
@@ -76,14 +77,16 @@ struct ref_format {
 	 * verify_ref_format() afterwards to finalize.
 	 */
 	const char *format;
+	const char *rest;
 	int quote_style;
+	int use_rest;
 	int use_color;
 
 	/* Internal state to ref-filter */
 	int need_color_reset_at_eol;
 };
 
-#define REF_FORMAT_INIT { NULL, 0, -1 }
+#define REF_FORMAT_INIT { .use_color = -1 }
 
 /*  Macros for checking --merged and --no-merged options */
 #define _OPT_MERGED_NO_MERGED(option, filter, h) \
@@ -116,7 +119,7 @@ void ref_array_sort(struct ref_sorting *sort, struct ref_array *array);
 void ref_sorting_set_sort_flags_all(struct ref_sorting *sorting, unsigned int mask, int on);
 /*  Based on the given format and quote_style, fill the strbuf */
 int format_ref_array_item(struct ref_array_item *info,
-			  const struct ref_format *format,
+			  struct ref_format *format,
 			  struct strbuf *final_buf,
 			  struct strbuf *error_buf);
 /*  Parse a single sort specifier and add it to the list */
@@ -137,7 +140,7 @@ void setup_ref_filter_porcelain_msg(void);
  * name must be a fully qualified refname.
  */
 void pretty_print_ref(const char *name, const struct object_id *oid,
-		      const struct ref_format *format);
+		      struct ref_format *format);
 
 /*
  * Push a single ref onto the array; this can be used to construct your own

t/t3203-branch-output.sh

@@ -340,6 +340,10 @@ test_expect_success 'git branch --format option' '
 	test_cmp expect actual
 '
 
+test_expect_success 'git branch with --format=%(rest) must fail' '
+	test_must_fail git branch --format="%(rest)" >actual
+'
+
 test_expect_success 'worktree colors correct' '
 	cat >expect <<-EOF &&
 	* <GREEN>(HEAD detached from fromtag)<RESET>

t/t6300-for-each-ref.sh

@@ -130,6 +130,8 @@ test_atom head parent:short=10 ''
 test_atom head numparent 0
 test_atom head object ''
 test_atom head type ''
+test_atom head raw "$(git cat-file commit refs/heads/main)
+"
 test_atom head '*objectname' ''
 test_atom head '*objecttype' ''
 test_atom head author 'A U Thor <author@example.com> 1151968724 +0200'
@@ -221,6 +223,15 @@ test_atom tag contents 'Tagging at 1151968727
 '
 test_atom tag HEAD ' '
 
+test_expect_success 'basic atom: refs/tags/testtag *raw' '
+	git cat-file commit refs/tags/testtag^{} >expected &&
+	git for-each-ref --format="%(*raw)" refs/tags/testtag >actual &&
+	sanitize_pgp <expected >expected.clean &&
+	echo >>expected.clean &&
+	sanitize_pgp <actual >actual.clean &&
+	test_cmp expected.clean actual.clean
+'
+
 test_expect_success 'Check invalid atoms names are errors' '
 	test_must_fail git for-each-ref --format="%(INVALID)" refs/heads
 '
@@ -686,6 +697,15 @@ test_atom refs/tags/signed-empty contents:body ''
 test_atom refs/tags/signed-empty contents:signature "$sig"
 test_atom refs/tags/signed-empty contents "$sig"
 
+test_expect_success GPG 'basic atom: refs/tags/signed-empty raw' '
+	git cat-file tag refs/tags/signed-empty >expected &&
+	git for-each-ref --format="%(raw)" refs/tags/signed-empty >actual &&
+	sanitize_pgp <expected >expected.clean &&
+	echo >>expected.clean &&
+	sanitize_pgp <actual >actual.clean &&
+	test_cmp expected.clean actual.clean
+'
+
 test_atom refs/tags/signed-short subject 'subject line'
 test_atom refs/tags/signed-short subject:sanitize 'subject-line'
 test_atom refs/tags/signed-short contents:subject 'subject line'
@@ -695,6 +715,15 @@ test_atom refs/tags/signed-short contents:signature "$sig"
 test_atom refs/tags/signed-short contents "subject line
 $sig"
 
+test_expect_success GPG 'basic atom: refs/tags/signed-short raw' '
+	git cat-file tag refs/tags/signed-short >expected &&
+	git for-each-ref --format="%(raw)" refs/tags/signed-short >actual &&
+	sanitize_pgp <expected >expected.clean &&
+	echo >>expected.clean &&
+	sanitize_pgp <actual >actual.clean &&
+	test_cmp expected.clean actual.clean
+'
+
 test_atom refs/tags/signed-long subject 'subject line'
 test_atom refs/tags/signed-long subject:sanitize 'subject-line'
 test_atom refs/tags/signed-long contents:subject 'subject line'
@@ -708,6 +737,15 @@ test_atom refs/tags/signed-long contents "subject line
 body contents
 $sig"
 
+test_expect_success GPG 'basic atom: refs/tags/signed-long raw' '
+	git cat-file tag refs/tags/signed-long >expected &&
+	git for-each-ref --format="%(raw)" refs/tags/signed-long >actual &&
+	sanitize_pgp <expected >expected.clean &&
+	echo >>expected.clean &&
+	sanitize_pgp <actual >actual.clean &&
+	test_cmp expected.clean actual.clean
+'
+
 test_expect_success 'set up refs pointing to tree and blob' '
 	git update-ref refs/mytrees/first refs/heads/main^{tree} &&
 	git update-ref refs/myblobs/first refs/heads/main:one
@@ -720,6 +758,16 @@ test_atom refs/mytrees/first contents:body ""
 test_atom refs/mytrees/first contents:signature ""
 test_atom refs/mytrees/first contents ""
 
+test_expect_success 'basic atom: refs/mytrees/first raw' '
+	git cat-file tree refs/mytrees/first >expected &&
+	echo >>expected &&
+	git for-each-ref --format="%(raw)" refs/mytrees/first >actual &&
+	test_cmp expected actual &&
+	git cat-file -s refs/mytrees/first >expected &&
+	git for-each-ref --format="%(raw:size)" refs/mytrees/first >actual &&
+	test_cmp expected actual
+'
+
 test_atom refs/myblobs/first subject ""
 test_atom refs/myblobs/first contents:subject ""
 test_atom refs/myblobs/first body ""
@@ -727,6 +775,189 @@ test_atom refs/myblobs/first contents:body ""
 test_atom refs/myblobs/first contents:signature ""
 test_atom refs/myblobs/first contents ""
 
+test_expect_success 'basic atom: refs/myblobs/first raw' '
+	git cat-file blob refs/myblobs/first >expected &&
+	echo >>expected &&
+	git for-each-ref --format="%(raw)" refs/myblobs/first >actual &&
+	test_cmp expected actual &&
+	git cat-file -s refs/myblobs/first >expected &&
+	git for-each-ref --format="%(raw:size)" refs/myblobs/first >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'set up refs pointing to binary blob' '
+	printf "a\0b\0c" >blob1 &&
+	printf "a\0c\0b" >blob2 &&
+	printf "\0a\0b\0c" >blob3 &&
+	printf "abc" >blob4 &&
+	printf "\0 \0 \0 " >blob5 &&
+	printf "\0 \0a\0 " >blob6 &&
+	printf "  " >blob7 &&
+	>blob8 &&
+	obj=$(git hash-object -w blob1) &&
+	git update-ref refs/myblobs/blob1 "$obj" &&
+	obj=$(git hash-object -w blob2) &&
+	git update-ref refs/myblobs/blob2 "$obj" &&
+	obj=$(git hash-object -w blob3) &&
+	git update-ref refs/myblobs/blob3 "$obj" &&
+	obj=$(git hash-object -w blob4) &&
+	git update-ref refs/myblobs/blob4 "$obj" &&
+	obj=$(git hash-object -w blob5) &&
+	git update-ref refs/myblobs/blob5 "$obj" &&
+	obj=$(git hash-object -w blob6) &&
+	git update-ref refs/myblobs/blob6 "$obj" &&
+	obj=$(git hash-object -w blob7) &&
+	git update-ref refs/myblobs/blob7 "$obj" &&
+	obj=$(git hash-object -w blob8) &&
+	git update-ref refs/myblobs/blob8 "$obj"
+'
+
+test_expect_success 'Verify sorts with raw' '
+	cat >expected <<-EOF &&
+	refs/myblobs/blob8
+	refs/myblobs/blob5
+	refs/myblobs/blob6
+	refs/myblobs/blob3
+	refs/myblobs/blob7
+	refs/mytrees/first
+	refs/myblobs/first
+	refs/myblobs/blob1
+	refs/myblobs/blob2
+	refs/myblobs/blob4
+	refs/heads/main
+	EOF
+	git for-each-ref --format="%(refname)" --sort=raw \
+		refs/heads/main refs/myblobs/ refs/mytrees/first >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'Verify sorts with raw:size' '
+	cat >expected <<-EOF &&
+	refs/myblobs/blob8
+	refs/myblobs/first
+	refs/myblobs/blob7
+	refs/heads/main
+	refs/myblobs/blob4
+	refs/myblobs/blob1
+	refs/myblobs/blob2
+	refs/myblobs/blob3
+	refs/myblobs/blob5
+	refs/myblobs/blob6
+	refs/mytrees/first
+	EOF
+	git for-each-ref --format="%(refname)" --sort=raw:size \
+		refs/heads/main refs/myblobs/ refs/mytrees/first >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'validate raw atom with %(if:equals)' '
+	cat >expected <<-EOF &&
+	not equals
+	not equals
+	not equals
+	not equals
+	not equals
+	not equals
+	refs/myblobs/blob4
+	not equals
+	not equals
+	not equals
+	not equals
+	not equals
+	EOF
+	git for-each-ref --format="%(if:equals=abc)%(raw)%(then)%(refname)%(else)not equals%(end)" \
+		refs/myblobs/ refs/heads/ >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'validate raw atom with %(if:notequals)' '
+	cat >expected <<-EOF &&
+	refs/heads/ambiguous
+	refs/heads/main
+	refs/heads/newtag
+	refs/myblobs/blob1
+	refs/myblobs/blob2
+	refs/myblobs/blob3
+	equals
+	refs/myblobs/blob5
+	refs/myblobs/blob6
+	refs/myblobs/blob7
+	refs/myblobs/blob8
+	refs/myblobs/first
+	EOF
+	git for-each-ref --format="%(if:notequals=abc)%(raw)%(then)%(refname)%(else)equals%(end)" \
+		refs/myblobs/ refs/heads/ >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'empty raw refs with %(if)' '
+	cat >expected <<-EOF &&
+	refs/myblobs/blob1 not empty
+	refs/myblobs/blob2 not empty
+	refs/myblobs/blob3 not empty
+	refs/myblobs/blob4 not empty
+	refs/myblobs/blob5 not empty
+	refs/myblobs/blob6 not empty
+	refs/myblobs/blob7 empty
+	refs/myblobs/blob8 empty
+	refs/myblobs/first not empty
+	EOF
+	git for-each-ref --format="%(refname) %(if)%(raw)%(then)not empty%(else)empty%(end)" \
+		refs/myblobs/ >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success '%(raw) with --python must fail' '
+	test_must_fail git for-each-ref --format="%(raw)" --python
+'
+
+test_expect_success '%(raw) with --tcl must fail' '
+	test_must_fail git for-each-ref --format="%(raw)" --tcl
+'
+
+test_expect_success '%(raw) with --perl' '
+	git for-each-ref --format="\$name= %(raw);
+print \"\$name\"" refs/myblobs/blob1 --perl | perl >actual &&
+	cmp blob1 actual &&
+	git for-each-ref --format="\$name= %(raw);
+print \"\$name\"" refs/myblobs/blob3 --perl | perl >actual &&
+	cmp blob3 actual &&
+	git for-each-ref --format="\$name= %(raw);
+print \"\$name\"" refs/myblobs/blob8 --perl | perl >actual &&
+	cmp blob8 actual &&
+	git for-each-ref --format="\$name= %(raw);
+print \"\$name\"" refs/myblobs/first --perl | perl >actual &&
+	cmp one actual &&
+	git cat-file tree refs/mytrees/first > expected &&
+	git for-each-ref --format="\$name= %(raw);
+print \"\$name\"" refs/mytrees/first --perl | perl >actual &&
+	cmp expected actual
+'
+
+test_expect_success '%(raw) with --shell must fail' '
+	test_must_fail git for-each-ref --format="%(raw)" --shell
+'
+
+test_expect_success '%(raw) with --shell and --sort=raw must fail' '
+	test_must_fail git for-each-ref --format="%(raw)" --sort=raw --shell
+'
+
+test_expect_success '%(raw:size) with --shell' '
+	git for-each-ref --format="%(raw:size)" | while read line
+	do
+		echo "'\''$line'\''" >>expect
+	done &&
+	git for-each-ref --format="%(raw:size)" --shell >actual &&
+	test_cmp expect actual
+'
+
+test_expect_success 'for-each-ref --format compare with cat-file --batch' '
+	git rev-parse refs/mytrees/first | git cat-file --batch >expected &&
+	git for-each-ref --format="%(objectname) %(objecttype) %(objectsize)
+%(raw)" refs/mytrees/first >actual &&
+	test_cmp expected actual
+'
+
 test_expect_success 'set up multiple-sort tags' '
 	for when in 100000 200000
 	do
@@ -980,6 +1211,10 @@ test_expect_success 'basic atom: head contents:trailers' '
 	test_cmp expect actual.clean
 '
 
+test_expect_success 'basic atom: rest must fail' '
+	test_must_fail git for-each-ref --format="%(rest)" refs/heads/main
+'
+
 test_expect_success 'trailer parsing not fooled by --- line' '
 	git commit --allow-empty -F - <<-\EOF &&
 	this is the subject

t/t7004-tag.sh

@@ -1998,6 +1998,10 @@ test_expect_success '--format should list tags as per format given' '
 	test_cmp expect actual
 '
 
+test_expect_success 'git tag -l with --format="%(rest)" must fail' '
+	test_must_fail git tag -l --format="%(rest)" "v1*"
+'
+
 test_expect_success "set up color tests" '
 	echo "<RED>v1.0<RESET>" >expect.color &&
 	echo "v1.0" >expect.bare &&

t/t7030-verify-tag.sh

@@ -194,6 +194,10 @@ test_expect_success GPG 'verifying tag with --format' '
 	test_cmp expect actual
 '
 
+test_expect_success GPG 'verifying tag with --format="%(rest)" must fail' '
+	test_must_fail git verify-tag --format="%(rest)" "fourth-signed"
+'
+
 test_expect_success GPG 'verifying a forged tag with --format should fail silently' '
 	test_must_fail git verify-tag --format="tagname : %(tag)" $(cat forged1.tag) >actual-forged &&
 	test_must_be_empty actual-forged