git-commit-vandalism/ref-filter.c

#include "builtin.h"
#include "cache.h"
#include "parse-options.h"
#include "refs.h"
#include "wildmatch.h"
#include "commit.h"
#include "remote.h"
#include "color.h"
#include "tag.h"
#include "quote.h"
#include "ref-filter.h"
#include "revision.h"
#include "utf8.h"
#include "git-compat-util.h"
#include "version.h"

typedef enum { FIELD_STR, FIELD_ULONG, FIELD_TIME } cmp_type;

static struct {
	const char *name;
	cmp_type cmp_type;
} valid_atom[] = {
	{ "refname" },
	{ "objecttype" },
	{ "objectsize", FIELD_ULONG },
	{ "objectname" },
	{ "tree" },
	{ "parent" },
	{ "numparent", FIELD_ULONG },
	{ "object" },
	{ "type" },
	{ "tag" },
	{ "author" },
	{ "authorname" },
	{ "authoremail" },
	{ "authordate", FIELD_TIME },
	{ "committer" },
	{ "committername" },
	{ "committeremail" },
	{ "committerdate", FIELD_TIME },
	{ "tagger" },
	{ "taggername" },
	{ "taggeremail" },
	{ "taggerdate", FIELD_TIME },
	{ "creator" },
	{ "creatordate", FIELD_TIME },
	{ "subject" },
	{ "body" },
	{ "contents" },
	{ "upstream" },
	{ "push" },
	{ "symref" },
	{ "flag" },
	{ "HEAD" },
	{ "color" },
	{ "align" },
	{ "end" },
};

#define REF_FORMATTING_STATE_INIT  { 0, NULL }

struct align {
	align_type position;
	unsigned int width;
};

struct contents {
	unsigned int lines;
	struct object_id oid;
};

struct ref_formatting_stack {
	struct ref_formatting_stack *prev;
	struct strbuf output;
	void (*at_end)(struct ref_formatting_stack *stack);
	void *at_end_data;
};

struct ref_formatting_state {
	int quote_style;
	struct ref_formatting_stack *stack;
};

struct atom_value {
	const char *s;
	union {
		struct align align;
		struct contents contents;
	} u;
	void (*handler)(struct atom_value *atomv, struct ref_formatting_state *state);
	unsigned long ul; /* used for sorting when not FIELD_STR */
};

/*
 * An atom is a valid field atom listed above, possibly prefixed with
 * a "*" to denote deref_tag().
 *
 * We parse given format string and sort specifiers, and make a list
 * of properties that we need to extract out of objects.  ref_array_item
 * structure will hold an array of values extracted that can be
 * indexed with the "atom number", which is an index into this
 * array.
 */
static const char **used_atom;
static cmp_type *used_atom_type;
static int used_atom_cnt, need_tagged, need_symref;
static int need_color_reset_at_eol;

/*
 * Used to parse format string and sort specifiers
 */
int parse_ref_filter_atom(const char *atom, const char *ep)
{
	const char *sp;
	int i, at;

	sp = atom;
	if (*sp == '*' && sp < ep)
		sp++; /* deref */
	if (ep <= sp)
		die("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]);
		if (len == ep - atom && !memcmp(used_atom[i], 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);
		/*
		 * If the atom name has a colon, strip it and everything after
		 * it off - it specifies the format for this entry, and
		 * shouldn't be used for checking against the valid_atom
		 * table.
		 */
		const char *formatp = strchr(sp, ':');
		if (!formatp || ep < formatp)
			formatp = ep;
		if (len == formatp - sp && !memcmp(valid_atom[i].name, sp, len))
			break;
	}

	if (ARRAY_SIZE(valid_atom) <= i)
		die("unknown field name: %.*s", (int)(ep-atom), atom);

	/* Add it in, including the deref prefix */
	at = used_atom_cnt;
	used_atom_cnt++;
	REALLOC_ARRAY(used_atom, used_atom_cnt);
	REALLOC_ARRAY(used_atom_type, used_atom_cnt);
	used_atom[at] = xmemdupz(atom, ep - atom);
	used_atom_type[at] = valid_atom[i].cmp_type;
	if (*atom == '*')
		need_tagged = 1;
	if (!strcmp(used_atom[at], "symref"))
		need_symref = 1;
	return at;
}

static void quote_formatting(struct strbuf *s, const char *str, int quote_style)
{
	switch (quote_style) {
	case QUOTE_NONE:
		strbuf_addstr(s, str);
		break;
	case QUOTE_SHELL:
		sq_quote_buf(s, str);
		break;
	case QUOTE_PERL:
		perl_quote_buf(s, str);
		break;
	case QUOTE_PYTHON:
		python_quote_buf(s, str);
		break;
	case QUOTE_TCL:
		tcl_quote_buf(s, str);
		break;
	}
}

static void append_atom(struct atom_value *v, struct ref_formatting_state *state)
{
	/*
	 * Quote formatting is only done when the stack has a single
	 * element. Otherwise quote formatting is done on the
	 * element's entire output strbuf when the %(end) atom is
	 * encountered.
	 */
	if (!state->stack->prev)
		quote_formatting(&state->stack->output, v->s, state->quote_style);
	else
		strbuf_addstr(&state->stack->output, v->s);
}

static void push_stack_element(struct ref_formatting_stack **stack)
{
	struct ref_formatting_stack *s = xcalloc(1, sizeof(struct ref_formatting_stack));

	strbuf_init(&s->output, 0);
	s->prev = *stack;
	*stack = s;
}

static void pop_stack_element(struct ref_formatting_stack **stack)
{
	struct ref_formatting_stack *current = *stack;
	struct ref_formatting_stack *prev = current->prev;

	if (prev)
		strbuf_addbuf(&prev->output, &current->output);
	strbuf_release(&current->output);
	free(current);
	*stack = prev;
}

static void end_align_handler(struct ref_formatting_stack *stack)
{
	struct align *align = (struct align *)stack->at_end_data;
	struct strbuf s = STRBUF_INIT;

	strbuf_utf8_align(&s, align->position, align->width, stack->output.buf);
	strbuf_swap(&stack->output, &s);
	strbuf_release(&s);
}

static void align_atom_handler(struct atom_value *atomv, struct ref_formatting_state *state)
{
	struct ref_formatting_stack *new;

	push_stack_element(&state->stack);
	new = state->stack;
	new->at_end = end_align_handler;
	new->at_end_data = &atomv->u.align;
}

static void end_atom_handler(struct atom_value *atomv, struct ref_formatting_state *state)
{
	struct ref_formatting_stack *current = state->stack;
	struct strbuf s = STRBUF_INIT;

	if (!current->at_end)
		die(_("format: %%(end) atom used without corresponding atom"));
	current->at_end(current);

	/*
	 * Perform quote formatting when the stack element is that of
	 * a supporting atom. If nested then perform quote formatting
	 * only on the topmost supporting atom.
	 */
	if (!state->stack->prev->prev) {
		quote_formatting(&s, current->output.buf, state->quote_style);
		strbuf_swap(&current->output, &s);
	}
	strbuf_release(&s);
	pop_stack_element(&state->stack);
}

static int match_atom_name(const char *name, const char *atom_name, const char **val)
{
	const char *body;

	if (!skip_prefix(name, atom_name, &body))
		return 0; /* doesn't even begin with "atom_name" */
	if (!body[0]) {
		*val = NULL; /* %(atom_name) and no customization */
		return 1;
	}
	if (body[0] != ':')
		return 0; /* "atom_namefoo" is not "atom_name" or "atom_name:..." */
	*val = body + 1; /* "atom_name:val" */
	return 1;
}

/*
 * In a format string, find the next occurrence of %(atom).
 */
static const char *find_next(const char *cp)
{
	while (*cp) {
		if (*cp == '%') {
			/*
			 * %( is the start of an atom;
			 * %% is a quoted per-cent.
			 */
			if (cp[1] == '(')
				return cp;
			else if (cp[1] == '%')
				cp++; /* skip over two % */
			/* otherwise this is a singleton, literal % */
		}
		cp++;
	}
	return NULL;
}

/*
 * Make sure the format string is well formed, and parse out
 * the used atoms.
 */
int verify_ref_format(const char *format)
{
	const char *cp, *sp;

	need_color_reset_at_eol = 0;
	for (cp = format; *cp && (sp = find_next(cp)); ) {
		const char *color, *ep = strchr(sp, ')');
		int at;

		if (!ep)
			return error("malformed format string %s", sp);
		/* sp points at "%(" and ep points at the closing ")" */
		at = parse_ref_filter_atom(sp + 2, ep);
		cp = ep + 1;

		if (skip_prefix(used_atom[at], "color:", &color))
			need_color_reset_at_eol = !!strcmp(color, "reset");
	}
	return 0;
}

/*
 * Given an object name, read the object data and size, and return a
 * "struct object".  If the object data we are returning is also borrowed
 * by the "struct object" representation, set *eaten as well---it is a
 * signal from parse_object_buffer to us not to free the buffer.
 */
static void *get_obj(const unsigned char *sha1, struct object **obj, unsigned long *sz, int *eaten)
{
	enum object_type type;
	void *buf = read_sha1_file(sha1, &type, sz);

	if (buf)
		*obj = parse_object_buffer(sha1, type, *sz, buf, eaten);
	else
		*obj = NULL;
	return buf;
}

static int grab_objectname(const char *name, const unsigned char *sha1,
			    struct atom_value *v)
{
	if (!strcmp(name, "objectname")) {
		char *s = xmalloc(41);
		strcpy(s, sha1_to_hex(sha1));
		v->s = s;
		return 1;
	}
	if (!strcmp(name, "objectname:short")) {
		v->s = xstrdup(find_unique_abbrev(sha1, DEFAULT_ABBREV));
		return 1;
	}
	return 0;
}

/* See grab_values */
static void grab_common_values(struct atom_value *val, int deref, struct object *obj, void *buf, unsigned long sz)
{
	int i;

	for (i = 0; i < used_atom_cnt; i++) {
		const char *name = used_atom[i];
		struct atom_value *v = &val[i];
		if (!!deref != (*name == '*'))
			continue;
		if (deref)
			name++;
		if (!strcmp(name, "objecttype"))
			v->s = typename(obj->type);
		else if (!strcmp(name, "objectsize")) {
			char *s = xmalloc(40);
			sprintf(s, "%lu", sz);
			v->ul = sz;
			v->s = s;
		}
		else if (deref)
			grab_objectname(name, obj->sha1, v);
	}
}

/* See grab_values */
static void grab_tag_values(struct atom_value *val, int deref, struct object *obj, void *buf, unsigned long sz)
{
	int i;
	struct tag *tag = (struct tag *) obj;

	for (i = 0; i < used_atom_cnt; i++) {
		const char *name = used_atom[i];
		struct atom_value *v = &val[i];
		if (!!deref != (*name == '*'))
			continue;
		if (deref)
			name++;
		if (!strcmp(name, "tag"))
			v->s = tag->tag;
		else if (!strcmp(name, "type") && tag->tagged)
			v->s = typename(tag->tagged->type);
		else if (!strcmp(name, "object") && tag->tagged) {
			char *s = xmalloc(41);
			strcpy(s, sha1_to_hex(tag->tagged->sha1));
			v->s = s;
		}
	}
}

/* See grab_values */
static void grab_commit_values(struct atom_value *val, int deref, struct object *obj, void *buf, unsigned long sz)
{
	int i;
	struct commit *commit = (struct commit *) obj;

	for (i = 0; i < used_atom_cnt; i++) {
		const char *name = used_atom[i];
		struct atom_value *v = &val[i];
		if (!!deref != (*name == '*'))
			continue;
		if (deref)
			name++;
		if (!strcmp(name, "tree")) {
			char *s = xmalloc(41);
			strcpy(s, sha1_to_hex(commit->tree->object.sha1));
			v->s = s;
		}
		if (!strcmp(name, "numparent")) {
			char *s = xmalloc(40);
			v->ul = commit_list_count(commit->parents);
			sprintf(s, "%lu", v->ul);
			v->s = s;
		}
		else if (!strcmp(name, "parent")) {
			int num = commit_list_count(commit->parents);
			int i;
			struct commit_list *parents;
			char *s = xmalloc(41 * num + 1);
			v->s = s;
			for (i = 0, parents = commit->parents;
			     parents;
			     parents = parents->next, i = i + 41) {
				struct commit *parent = parents->item;
				strcpy(s+i, sha1_to_hex(parent->object.sha1));
				if (parents->next)
					s[i+40] = ' ';
			}
			if (!i)
				*s = '\0';
		}
	}
}

static const char *find_wholine(const char *who, int wholen, const char *buf, unsigned long sz)
{
	const char *eol;
	while (*buf) {
		if (!strncmp(buf, who, wholen) &&
		    buf[wholen] == ' ')
			return buf + wholen + 1;
		eol = strchr(buf, '\n');
		if (!eol)
			return "";
		eol++;
		if (*eol == '\n')
			return ""; /* end of header */
		buf = eol;
	}
	return "";
}

static const char *copy_line(const char *buf)
{
	const char *eol = strchrnul(buf, '\n');
	return xmemdupz(buf, eol - buf);
}

static const char *copy_name(const char *buf)
{
	const char *cp;
	for (cp = buf; *cp && *cp != '\n'; cp++) {
		if (!strncmp(cp, " <", 2))
			return xmemdupz(buf, cp - buf);
	}
	return "";
}

static const char *copy_email(const char *buf)
{
	const char *email = strchr(buf, '<');
	const char *eoemail;
	if (!email)
		return "";
	eoemail = strchr(email, '>');
	if (!eoemail)
		return "";
	return xmemdupz(email, eoemail + 1 - email);
}

static char *copy_subject(const char *buf, unsigned long len)
{
	char *r = xmemdupz(buf, len);
	int i;

	for (i = 0; i < len; i++)
		if (r[i] == '\n')
			r[i] = ' ';

	return r;
}

static void grab_date(const char *buf, struct atom_value *v, const char *atomname)
{
	const char *eoemail = strstr(buf, "> ");
	char *zone;
	unsigned long timestamp;
	long tz;
	struct date_mode date_mode = { DATE_NORMAL };
	const char *formatp;

	/*
	 * We got here because atomname ends in "date" or "date<something>";
	 * it's not possible that <something> is not ":<format>" because
	 * parse_ref_filter_atom() wouldn't have allowed it, so we can assume that no
	 * ":" means no format is specified, and use the default.
	 */
	formatp = strchr(atomname, ':');
	if (formatp != NULL) {
		formatp++;
		parse_date_format(formatp, &date_mode);
	}

	if (!eoemail)
		goto bad;
	timestamp = strtoul(eoemail + 2, &zone, 10);
	if (timestamp == ULONG_MAX)
		goto bad;
	tz = strtol(zone, NULL, 10);
	if ((tz == LONG_MIN || tz == LONG_MAX) && errno == ERANGE)
		goto bad;
	v->s = xstrdup(show_date(timestamp, tz, &date_mode));
	v->ul = timestamp;
	return;
 bad:
	v->s = "";
	v->ul = 0;
}

/* See grab_values */
static void grab_person(const char *who, struct atom_value *val, int deref, struct object *obj, void *buf, unsigned long sz)
{
	int i;
	int wholen = strlen(who);
	const char *wholine = NULL;

	for (i = 0; i < used_atom_cnt; i++) {
		const char *name = used_atom[i];
		struct atom_value *v = &val[i];
		if (!!deref != (*name == '*'))
			continue;
		if (deref)
			name++;
		if (strncmp(who, name, wholen))
			continue;
		if (name[wholen] != 0 &&
		    strcmp(name + wholen, "name") &&
		    strcmp(name + wholen, "email") &&
		    !starts_with(name + wholen, "date"))
			continue;
		if (!wholine)
			wholine = find_wholine(who, wholen, buf, sz);
		if (!wholine)
			return; /* no point looking for it */
		if (name[wholen] == 0)
			v->s = copy_line(wholine);
		else if (!strcmp(name + wholen, "name"))
			v->s = copy_name(wholine);
		else if (!strcmp(name + wholen, "email"))
			v->s = copy_email(wholine);
		else if (starts_with(name + wholen, "date"))
			grab_date(wholine, v, name);
	}

	/*
	 * For a tag or a commit object, if "creator" or "creatordate" is
	 * requested, do something special.
	 */
	if (strcmp(who, "tagger") && strcmp(who, "committer"))
		return; /* "author" for commit object is not wanted */
	if (!wholine)
		wholine = find_wholine(who, wholen, buf, sz);
	if (!wholine)
		return;
	for (i = 0; i < used_atom_cnt; i++) {
		const char *name = used_atom[i];
		struct atom_value *v = &val[i];
		if (!!deref != (*name == '*'))
			continue;
		if (deref)
			name++;

		if (starts_with(name, "creatordate"))
			grab_date(wholine, v, name);
		else if (!strcmp(name, "creator"))
			v->s = copy_line(wholine);
	}
}

static void find_subpos(const char *buf, unsigned long sz,
			const char **sub, unsigned long *sublen,
			const char **body, unsigned long *bodylen,
			unsigned long *nonsiglen,
			const char **sig, unsigned long *siglen)
{
	const char *eol;
	/* skip past header until we hit empty line */
	while (*buf && *buf != '\n') {
		eol = strchrnul(buf, '\n');
		if (*eol)
			eol++;
		buf = eol;
	}
	/* skip any empty lines */
	while (*buf == '\n')
		buf++;

	/* parse signature first; we might not even have a subject line */
	*sig = buf + parse_signature(buf, strlen(buf));
	*siglen = strlen(*sig);

	/* subject is first non-empty line */
	*sub = buf;
	/* subject goes to first empty line */
	while (buf < *sig && *buf && *buf != '\n') {
		eol = strchrnul(buf, '\n');
		if (*eol)
			eol++;
		buf = eol;
	}
	*sublen = buf - *sub;
	/* drop trailing newline, if present */
	if (*sublen && (*sub)[*sublen - 1] == '\n')
		*sublen -= 1;

	/* skip any empty lines */
	while (*buf == '\n')
		buf++;
	*body = buf;
	*bodylen = strlen(buf);
	*nonsiglen = *sig - buf;
}

/*
 * If 'lines' is greater than 0, append that many lines from the given
 * 'buf' of length 'size' to the given strbuf.
 */
static void append_lines(struct strbuf *out, const char *buf, unsigned long size, int lines)
{
	int i;
	const char *sp, *eol;
	size_t len;

	sp = buf;

	for (i = 0; i < lines && sp < buf + size; i++) {
		if (i)
			strbuf_addstr(out, "\n    ");
		eol = memchr(sp, '\n', size - (sp - buf));
		len = eol ? eol - sp : size - (sp - buf);
		strbuf_add(out, sp, len);
		if (!eol)
			break;
		sp = eol + 1;
	}
}

/* See grab_values */
static void grab_sub_body_contents(struct atom_value *val, int deref, struct object *obj, void *buf, unsigned long sz)
{
	int i;
	const char *subpos = NULL, *bodypos = NULL, *sigpos = NULL;
	unsigned long sublen = 0, bodylen = 0, nonsiglen = 0, siglen = 0;

	for (i = 0; i < used_atom_cnt; i++) {
		const char *name = used_atom[i];
		struct atom_value *v = &val[i];
		const char *valp = NULL;
		if (!!deref != (*name == '*'))
			continue;
		if (deref)
			name++;
		if (strcmp(name, "subject") &&
		    strcmp(name, "body") &&
		    strcmp(name, "contents") &&
		    strcmp(name, "contents:subject") &&
		    strcmp(name, "contents:body") &&
		    strcmp(name, "contents:signature") &&
		    !starts_with(name, "contents:lines="))
			continue;
		if (!subpos)
			find_subpos(buf, sz,
				    &subpos, &sublen,
				    &bodypos, &bodylen, &nonsiglen,
				    &sigpos, &siglen);

		if (!strcmp(name, "subject"))
			v->s = copy_subject(subpos, sublen);
		else if (!strcmp(name, "contents:subject"))
			v->s = copy_subject(subpos, sublen);
		else if (!strcmp(name, "body"))
			v->s = xmemdupz(bodypos, bodylen);
		else if (!strcmp(name, "contents:body"))
			v->s = xmemdupz(bodypos, nonsiglen);
		else if (!strcmp(name, "contents:signature"))
			v->s = xmemdupz(sigpos, siglen);
		else if (!strcmp(name, "contents"))
			v->s = xstrdup(subpos);
		else if (skip_prefix(name, "contents:lines=", &valp)) {
			struct strbuf s = STRBUF_INIT;
			const char *contents_end = bodylen + bodypos - siglen;

			if (strtoul_ui(valp, 10, &v->u.contents.lines))
				die(_("positive value expected contents:lines=%s"), valp);
			/*  Size is the length of the message after removing the signature */
			append_lines(&s, subpos, contents_end - subpos, v->u.contents.lines);
			v->s = strbuf_detach(&s, NULL);
		}
	}
}

/*
 * We want to have empty print-string for field requests
 * that do not apply (e.g. "authordate" for a tag object)
 */
static void fill_missing_values(struct atom_value *val)
{
	int i;
	for (i = 0; i < used_atom_cnt; i++) {
		struct atom_value *v = &val[i];
		if (v->s == NULL)
			v->s = "";
	}
}

/*
 * val is a list of atom_value to hold returned values.  Extract
 * the values for atoms in used_atom array out of (obj, buf, sz).
 * when deref is false, (obj, buf, sz) is the object that is
 * 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, unsigned long sz)
{
	grab_common_values(val, deref, obj, buf, sz);
	switch (obj->type) {
	case OBJ_TAG:
		grab_tag_values(val, deref, obj, buf, sz);
		grab_sub_body_contents(val, deref, obj, buf, sz);
		grab_person("tagger", val, deref, obj, buf, sz);
		break;
	case OBJ_COMMIT:
		grab_commit_values(val, deref, obj, buf, sz);
		grab_sub_body_contents(val, deref, obj, buf, sz);
		grab_person("author", val, deref, obj, buf, sz);
		grab_person("committer", val, deref, obj, buf, sz);
		break;
	case OBJ_TREE:
		/* grab_tree_values(val, deref, obj, buf, sz); */
		break;
	case OBJ_BLOB:
		/* grab_blob_values(val, deref, obj, buf, sz); */
		break;
	default:
		die("Eh?  Object of type %d?", obj->type);
	}
}

static inline char *copy_advance(char *dst, const char *src)
{
	while (*src)
		*dst++ = *src++;
	return dst;
}

/*
 * Parse the object referred by ref, and grab needed value.
 */
static void populate_value(struct ref_array_item *ref)
{
	void *buf;
	struct object *obj;
	int eaten, i;
	unsigned long size;
	const unsigned char *tagged;

	ref->value = xcalloc(used_atom_cnt, sizeof(struct atom_value));

	if (need_symref && (ref->flag & REF_ISSYMREF) && !ref->symref) {
		unsigned char unused1[20];
		ref->symref = resolve_refdup(ref->refname, RESOLVE_REF_READING,
					     unused1, NULL);
		if (!ref->symref)
			ref->symref = "";
	}

	/* Fill in specials first */
	for (i = 0; i < used_atom_cnt; i++) {
		const char *name = used_atom[i];
		struct atom_value *v = &ref->value[i];
		int deref = 0;
		const char *refname;
		const char *formatp;
		const char *valp;
		struct branch *branch = NULL;

		v->handler = append_atom;

		if (*name == '*') {
			deref = 1;
			name++;
		}

		if (starts_with(name, "refname"))
			refname = ref->refname;
		else if (starts_with(name, "symref"))
			refname = ref->symref ? ref->symref : "";
		else if (starts_with(name, "upstream")) {
			const char *branch_name;
			/* only local branches may have an upstream */
			if (!skip_prefix(ref->refname, "refs/heads/",
					 &branch_name))
				continue;
			branch = branch_get(branch_name);

			refname = branch_get_upstream(branch, NULL);
			if (!refname)
				continue;
		} else if (starts_with(name, "push")) {
			const char *branch_name;
			if (!skip_prefix(ref->refname, "refs/heads/",
					 &branch_name))
				continue;
			branch = branch_get(branch_name);

			refname = branch_get_push(branch, NULL);
			if (!refname)
				continue;
		} else if (match_atom_name(name, "color", &valp)) {
			char color[COLOR_MAXLEN] = "";

			if (!valp)
				die(_("expected format: %%(color:<color>)"));
			if (color_parse(valp, color) < 0)
				die(_("unable to parse format"));
			v->s = xstrdup(color);
			continue;
		} else if (!strcmp(name, "flag")) {
			char buf[256], *cp = buf;
			if (ref->flag & REF_ISSYMREF)
				cp = copy_advance(cp, ",symref");
			if (ref->flag & REF_ISPACKED)
				cp = copy_advance(cp, ",packed");
			if (cp == buf)
				v->s = "";
			else {
				*cp = '\0';
				v->s = xstrdup(buf + 1);
			}
			continue;
		} else if (!deref && grab_objectname(name, ref->objectname, v)) {
			continue;
		} else if (!strcmp(name, "HEAD")) {
			const char *head;
			unsigned char sha1[20];

			head = resolve_ref_unsafe("HEAD", RESOLVE_REF_READING,
						  sha1, NULL);
			if (!strcmp(ref->refname, head))
				v->s = "*";
			else
				v->s = " ";
			continue;
		} else if (match_atom_name(name, "align", &valp)) {
			struct align *align = &v->u.align;
			struct strbuf **s, **to_free;
			int width = -1;

			if (!valp)
				die(_("expected format: %%(align:<width>,<position>)"));

			/*
			 * TODO: Implement a function similar to strbuf_split_str()
			 * which would omit the separator from the end of each value.
			 */
			s = to_free = strbuf_split_str(valp, ',', 0);

			align->position = ALIGN_LEFT;

			while (*s) {
				/*  Strip trailing comma */
				if (s[1])
					strbuf_setlen(s[0], s[0]->len - 1);
				if (!strtoul_ui(s[0]->buf, 10, (unsigned int *)&width))
					;
				else if (!strcmp(s[0]->buf, "left"))
					align->position = ALIGN_LEFT;
				else if (!strcmp(s[0]->buf, "right"))
					align->position = ALIGN_RIGHT;
				else if (!strcmp(s[0]->buf, "middle"))
					align->position = ALIGN_MIDDLE;
				else
					die(_("improper format entered align:%s"), s[0]->buf);
				s++;
			}

			if (width < 0)
				die(_("positive width expected with the %%(align) atom"));
			align->width = width;
			strbuf_list_free(to_free);
			v->handler = align_atom_handler;
			continue;
		} else if (!strcmp(name, "end")) {
			v->handler = end_atom_handler;
			continue;
		} else
			continue;

		formatp = strchr(name, ':');
		if (formatp) {
			int num_ours, num_theirs;

			formatp++;
			if (!strcmp(formatp, "short"))
				refname = shorten_unambiguous_ref(refname,
						      warn_ambiguous_refs);
			else if (!strcmp(formatp, "track") &&
				 (starts_with(name, "upstream") ||
				  starts_with(name, "push"))) {
				char buf[40];

				if (stat_tracking_info(branch, &num_ours,
						       &num_theirs, NULL))
					continue;

				if (!num_ours && !num_theirs)
					v->s = "";
				else if (!num_ours) {
					sprintf(buf, "[behind %d]", num_theirs);
					v->s = xstrdup(buf);
				} else if (!num_theirs) {
					sprintf(buf, "[ahead %d]", num_ours);
					v->s = xstrdup(buf);
				} else {
					sprintf(buf, "[ahead %d, behind %d]",
						num_ours, num_theirs);
					v->s = xstrdup(buf);
				}
				continue;
			} else if (!strcmp(formatp, "trackshort") &&
				   (starts_with(name, "upstream") ||
				    starts_with(name, "push"))) {
				assert(branch);

				if (stat_tracking_info(branch, &num_ours,
							&num_theirs, NULL))
					continue;

				if (!num_ours && !num_theirs)
					v->s = "=";
				else if (!num_ours)
					v->s = "<";
				else if (!num_theirs)
					v->s = ">";
				else
					v->s = "<>";
				continue;
			} else
				die("unknown %.*s format %s",
				    (int)(formatp - name), name, formatp);
		}

		if (!deref)
			v->s = refname;
		else {
			int len = strlen(refname);
			char *s = xmalloc(len + 4);
			sprintf(s, "%s^{}", refname);
			v->s = s;
		}
	}

	for (i = 0; i < used_atom_cnt; i++) {
		struct atom_value *v = &ref->value[i];
		if (v->s == NULL)
			goto need_obj;
	}
	return;

 need_obj:
	buf = get_obj(ref->objectname, &obj, &size, &eaten);
	if (!buf)
		die("missing object %s for %s",
		    sha1_to_hex(ref->objectname), ref->refname);
	if (!obj)
		die("parse_object_buffer failed on %s for %s",
		    sha1_to_hex(ref->objectname), ref->refname);

	grab_values(ref->value, 0, obj, buf, size);
	if (!eaten)
		free(buf);

	/*
	 * If there is no atom that wants to know about tagged
	 * object, we are done.
	 */
	if (!need_tagged || (obj->type != OBJ_TAG))
		return;

	/*
	 * If it is a tag object, see if we use a value that derefs
	 * the object, and if we do grab the object it refers to.
	 */
	tagged = ((struct tag *)obj)->tagged->sha1;

	/*
	 * NEEDSWORK: This derefs tag only once, which
	 * is good to deal with chains of trust, but
	 * is not consistent with what deref_tag() does
	 * which peels the onion to the core.
	 */
	buf = get_obj(tagged, &obj, &size, &eaten);
	if (!buf)
		die("missing object %s for %s",
		    sha1_to_hex(tagged), ref->refname);
	if (!obj)
		die("parse_object_buffer failed on %s for %s",
		    sha1_to_hex(tagged), ref->refname);
	grab_values(ref->value, 1, obj, buf, size);
	if (!eaten)
		free(buf);
}

/*
 * Given a ref, return the value for the atom.  This lazily gets value
 * out of the object by calling populate value.
 */
static void get_ref_atom_value(struct ref_array_item *ref, int atom, struct atom_value **v)
{
	if (!ref->value) {
		populate_value(ref);
		fill_missing_values(ref->value);
	}
	*v = &ref->value[atom];
}

enum contains_result {
	CONTAINS_UNKNOWN = -1,
	CONTAINS_NO = 0,
	CONTAINS_YES = 1
};

/*
 * Mimicking the real stack, this stack lives on the heap, avoiding stack
 * overflows.
 *
 * At each recursion step, the stack items points to the commits whose
 * ancestors are to be inspected.
 */
struct contains_stack {
	int nr, alloc;
	struct contains_stack_entry {
		struct commit *commit;
		struct commit_list *parents;
	} *contains_stack;
};

static int in_commit_list(const struct commit_list *want, struct commit *c)
{
	for (; want; want = want->next)
		if (!hashcmp(want->item->object.sha1, c->object.sha1))
			return 1;
	return 0;
}

/*
 * Test whether the candidate or one of its parents is contained in the list.
 * Do not recurse to find out, though, but return -1 if inconclusive.
 */
static enum contains_result contains_test(struct commit *candidate,
			    const struct commit_list *want)
{
	/* was it previously marked as containing a want commit? */
	if (candidate->object.flags & TMP_MARK)
		return 1;
	/* or marked as not possibly containing a want commit? */
	if (candidate->object.flags & UNINTERESTING)
		return 0;
	/* or are we it? */
	if (in_commit_list(want, candidate)) {
		candidate->object.flags |= TMP_MARK;
		return 1;
	}

	if (parse_commit(candidate) < 0)
		return 0;

	return -1;
}

static void push_to_contains_stack(struct commit *candidate, struct contains_stack *contains_stack)
{
	ALLOC_GROW(contains_stack->contains_stack, contains_stack->nr + 1, contains_stack->alloc);
	contains_stack->contains_stack[contains_stack->nr].commit = candidate;
	contains_stack->contains_stack[contains_stack->nr++].parents = candidate->parents;
}

static enum contains_result contains_tag_algo(struct commit *candidate,
		const struct commit_list *want)
{
	struct contains_stack contains_stack = { 0, 0, NULL };
	int result = contains_test(candidate, want);

	if (result != CONTAINS_UNKNOWN)
		return result;

	push_to_contains_stack(candidate, &contains_stack);
	while (contains_stack.nr) {
		struct contains_stack_entry *entry = &contains_stack.contains_stack[contains_stack.nr - 1];
		struct commit *commit = entry->commit;
		struct commit_list *parents = entry->parents;

		if (!parents) {
			commit->object.flags |= UNINTERESTING;
			contains_stack.nr--;
		}
		/*
		 * If we just popped the stack, parents->item has been marked,
		 * therefore contains_test will return a meaningful 0 or 1.
		 */
		else switch (contains_test(parents->item, want)) {
		case CONTAINS_YES:
			commit->object.flags |= TMP_MARK;
			contains_stack.nr--;
			break;
		case CONTAINS_NO:
			entry->parents = parents->next;
			break;
		case CONTAINS_UNKNOWN:
			push_to_contains_stack(parents->item, &contains_stack);
			break;
		}
	}
	free(contains_stack.contains_stack);
	return contains_test(candidate, want);
}

static int commit_contains(struct ref_filter *filter, struct commit *commit)
{
	if (filter->with_commit_tag_algo)
		return contains_tag_algo(commit, filter->with_commit);
	return is_descendant_of(commit, filter->with_commit);
}

/*
 * Return 1 if the refname matches one of the patterns, otherwise 0.
 * A pattern can be a literal prefix (e.g. a refname "refs/heads/master"
 * matches a pattern "refs/heads/mas") or a wildcard (e.g. the same ref
 * matches "refs/heads/mas*", too).
 */
static int match_pattern(const char **patterns, const char *refname)
{
	/*
	 * When no '--format' option is given we need to skip the prefix
	 * for matching refs of tags and branches.
	 */
	(void)(skip_prefix(refname, "refs/tags/", &refname) ||
	       skip_prefix(refname, "refs/heads/", &refname) ||
	       skip_prefix(refname, "refs/remotes/", &refname) ||
	       skip_prefix(refname, "refs/", &refname));

	for (; *patterns; patterns++) {
		if (!wildmatch(*patterns, refname, 0, NULL))
			return 1;
	}
	return 0;
}

/*
 * Return 1 if the refname matches one of the patterns, otherwise 0.
 * A pattern can be path prefix (e.g. a refname "refs/heads/master"
 * matches a pattern "refs/heads/" but not "refs/heads/m") or a
 * wildcard (e.g. the same ref matches "refs/heads/m*", too).
 */
static int match_name_as_path(const char **pattern, const char *refname)
{
	int namelen = strlen(refname);
	for (; *pattern; pattern++) {
		const char *p = *pattern;
		int plen = strlen(p);

		if ((plen <= namelen) &&
		    !strncmp(refname, p, plen) &&
		    (refname[plen] == '\0' ||
		     refname[plen] == '/' ||
		     p[plen-1] == '/'))
			return 1;
		if (!wildmatch(p, refname, WM_PATHNAME, NULL))
			return 1;
	}
	return 0;
}

/* Return 1 if the refname matches one of the patterns, otherwise 0. */
static int filter_pattern_match(struct ref_filter *filter, const char *refname)
{
	if (!*filter->name_patterns)
		return 1; /* No pattern always matches */
	if (filter->match_as_path)
		return match_name_as_path(filter->name_patterns, refname);
	return match_pattern(filter->name_patterns, refname);
}

/*
 * Given a ref (sha1, refname), check if the ref belongs to the array
 * of sha1s. If the given ref is a tag, check if the given tag points
 * at one of the sha1s in the given sha1 array.
 * the given sha1_array.
 * NEEDSWORK:
 * 1. Only a single level of inderection is obtained, we might want to
 * change this to account for multiple levels (e.g. annotated tags
 * pointing to annotated tags pointing to a commit.)
 * 2. As the refs are cached we might know what refname peels to without
 * the need to parse the object via parse_object(). peel_ref() might be a
 * more efficient alternative to obtain the pointee.
 */
static const unsigned char *match_points_at(struct sha1_array *points_at,
					    const unsigned char *sha1,
					    const char *refname)
{
	const unsigned char *tagged_sha1 = NULL;
	struct object *obj;

	if (sha1_array_lookup(points_at, sha1) >= 0)
		return sha1;
	obj = parse_object(sha1);
	if (!obj)
		die(_("malformed object at '%s'"), refname);
	if (obj->type == OBJ_TAG)
		tagged_sha1 = ((struct tag *)obj)->tagged->sha1;
	if (tagged_sha1 && sha1_array_lookup(points_at, tagged_sha1) >= 0)
		return tagged_sha1;
	return NULL;
}

/* Allocate space for a new ref_array_item and copy the objectname and flag to it */
static struct ref_array_item *new_ref_array_item(const char *refname,
						 const unsigned char *objectname,
						 int flag)
{
	size_t len = strlen(refname);
	struct ref_array_item *ref = xcalloc(1, sizeof(struct ref_array_item) + len + 1);
	memcpy(ref->refname, refname, len);
	ref->refname[len] = '\0';
	hashcpy(ref->objectname, objectname);
	ref->flag = flag;

	return ref;
}

static int filter_ref_kind(struct ref_filter *filter, const char *refname)
{
	unsigned int i;

	static struct {
		const char *prefix;
		unsigned int kind;
	} ref_kind[] = {
		{ "refs/heads/" , FILTER_REFS_BRANCHES },
		{ "refs/remotes/" , FILTER_REFS_REMOTES },
		{ "refs/tags/", FILTER_REFS_TAGS}
	};

	if (filter->kind == FILTER_REFS_BRANCHES ||
	    filter->kind == FILTER_REFS_REMOTES ||
	    filter->kind == FILTER_REFS_TAGS)
		return filter->kind;
	else if (!strcmp(refname, "HEAD"))
		return FILTER_REFS_DETACHED_HEAD;

	for (i = 0; i < ARRAY_SIZE(ref_kind); i++) {
		if (starts_with(refname, ref_kind[i].prefix))
			return ref_kind[i].kind;
	}

	return FILTER_REFS_OTHERS;
}

/*
 * A call-back given to for_each_ref().  Filter refs and keep them for
 * later object processing.
 */
static int ref_filter_handler(const char *refname, const struct object_id *oid, int flag, void *cb_data)
{
	struct ref_filter_cbdata *ref_cbdata = cb_data;
	struct ref_filter *filter = ref_cbdata->filter;
	struct ref_array_item *ref;
	struct commit *commit = NULL;
	unsigned int kind;

	if (flag & REF_BAD_NAME) {
		warning("ignoring ref with broken name %s", refname);
		return 0;
	}

	if (flag & REF_ISBROKEN) {
		warning("ignoring broken ref %s", refname);
		return 0;
	}

	/* Obtain the current ref kind from filter_ref_kind() and ignore unwanted refs. */
	kind = filter_ref_kind(filter, refname);
	if (!(kind & filter->kind))
		return 0;

	if (!filter_pattern_match(filter, refname))
		return 0;

	if (filter->points_at.nr && !match_points_at(&filter->points_at, oid->hash, refname))
		return 0;

	/*
	 * A merge filter is applied on refs pointing to commits. Hence
	 * obtain the commit using the 'oid' available and discard all
	 * non-commits early. The actual filtering is done later.
	 */
	if (filter->merge_commit || filter->with_commit || filter->verbose) {
		commit = lookup_commit_reference_gently(oid->hash, 1);
		if (!commit)
			return 0;
		/* We perform the filtering for the '--contains' option */
		if (filter->with_commit &&
		    !commit_contains(filter, commit))
			return 0;
	}

	/*
	 * We do not open the object yet; sort may only need refname
	 * to do its job and the resulting list may yet to be pruned
	 * by maxcount logic.
	 */
	ref = new_ref_array_item(refname, oid->hash, flag);
	ref->commit = commit;

	REALLOC_ARRAY(ref_cbdata->array->items, ref_cbdata->array->nr + 1);
	ref_cbdata->array->items[ref_cbdata->array->nr++] = ref;
	ref->kind = kind;
	return 0;
}

/*  Free memory allocated for a ref_array_item */
static void free_array_item(struct ref_array_item *item)
{
	free((char *)item->symref);
	free(item);
}

/* Free all memory allocated for ref_array */
void ref_array_clear(struct ref_array *array)
{
	int i;

	for (i = 0; i < array->nr; i++)
		free_array_item(array->items[i]);
	free(array->items);
	array->items = NULL;
	array->nr = array->alloc = 0;
}

static void do_merge_filter(struct ref_filter_cbdata *ref_cbdata)
{
	struct rev_info revs;
	int i, old_nr;
	struct ref_filter *filter = ref_cbdata->filter;
	struct ref_array *array = ref_cbdata->array;
	struct commit **to_clear = xcalloc(sizeof(struct commit *), array->nr);

	init_revisions(&revs, NULL);

	for (i = 0; i < array->nr; i++) {
		struct ref_array_item *item = array->items[i];
		add_pending_object(&revs, &item->commit->object, item->refname);
		to_clear[i] = item->commit;
	}

	filter->merge_commit->object.flags |= UNINTERESTING;
	add_pending_object(&revs, &filter->merge_commit->object, "");

	revs.limited = 1;
	if (prepare_revision_walk(&revs))
		die(_("revision walk setup failed"));

	old_nr = array->nr;
	array->nr = 0;

	for (i = 0; i < old_nr; i++) {
		struct ref_array_item *item = array->items[i];
		struct commit *commit = item->commit;

		int is_merged = !!(commit->object.flags & UNINTERESTING);

		if (is_merged == (filter->merge == REF_FILTER_MERGED_INCLUDE))
			array->items[array->nr++] = array->items[i];
		else
			free_array_item(item);
	}

	for (i = 0; i < old_nr; i++)
		clear_commit_marks(to_clear[i], ALL_REV_FLAGS);
	clear_commit_marks(filter->merge_commit, ALL_REV_FLAGS);
	free(to_clear);
}

/*
 * API for filtering a set of refs. Based on the type of refs the user
 * has requested, we iterate through those refs and apply filters
 * as per the given ref_filter structure and finally store the
 * filtered refs in the ref_array structure.
 */
int filter_refs(struct ref_array *array, struct ref_filter *filter, unsigned int type)
{
	struct ref_filter_cbdata ref_cbdata;
	int ret = 0;
	unsigned int broken = 0;

	ref_cbdata.array = array;
	ref_cbdata.filter = filter;

	if (type & FILTER_REFS_INCLUDE_BROKEN)
		broken = 1;
	filter->kind = type & FILTER_REFS_KIND_MASK;

	/*  Simple per-ref filtering */
	if (!filter->kind)
		die("filter_refs: invalid type");
	else {
		/*
		 * For common cases where we need only branches or remotes or tags,
		 * we only iterate through those refs. If a mix of refs is needed,
		 * we iterate over all refs and filter out required refs with the help
		 * of filter_ref_kind().
		 */
		if (filter->kind == FILTER_REFS_BRANCHES)
			ret = for_each_fullref_in("refs/heads/", ref_filter_handler, &ref_cbdata, broken);
		else if (filter->kind == FILTER_REFS_REMOTES)
			ret = for_each_fullref_in("refs/remotes/", ref_filter_handler, &ref_cbdata, broken);
		else if (filter->kind == FILTER_REFS_TAGS)
			ret = for_each_fullref_in("refs/tags/", ref_filter_handler, &ref_cbdata, broken);
		else if (filter->kind & FILTER_REFS_ALL)
			ret = for_each_fullref_in("", ref_filter_handler, &ref_cbdata, broken);
		if (!ret && (filter->kind & FILTER_REFS_DETACHED_HEAD))
			head_ref(ref_filter_handler, &ref_cbdata);
	}


	/*  Filters that need revision walking */
	if (filter->merge_commit)
		do_merge_filter(&ref_cbdata);

	return ret;
}

static int cmp_ref_sorting(struct ref_sorting *s, struct ref_array_item *a, struct ref_array_item *b)
{
	struct atom_value *va, *vb;
	int cmp;
	cmp_type cmp_type = used_atom_type[s->atom];

	get_ref_atom_value(a, s->atom, &va);
	get_ref_atom_value(b, s->atom, &vb);
	if (s->version)
		cmp = versioncmp(va->s, vb->s);
	else if (cmp_type == FIELD_STR)
		cmp = strcmp(va->s, vb->s);
	else {
		if (va->ul < vb->ul)
			cmp = -1;
		else if (va->ul == vb->ul)
			cmp = 0;
		else
			cmp = 1;
	}

	return (s->reverse) ? -cmp : cmp;
}

static struct ref_sorting *ref_sorting;
static int compare_refs(const void *a_, const void *b_)
{
	struct ref_array_item *a = *((struct ref_array_item **)a_);
	struct ref_array_item *b = *((struct ref_array_item **)b_);
	struct ref_sorting *s;

	for (s = ref_sorting; s; s = s->next) {
		int cmp = cmp_ref_sorting(s, a, b);
		if (cmp)
			return cmp;
	}
	return 0;
}

void ref_array_sort(struct ref_sorting *sorting, struct ref_array *array)
{
	ref_sorting = sorting;
	qsort(array->items, array->nr, sizeof(struct ref_array_item *), compare_refs);
}

static int hex1(char ch)
{
	if ('0' <= ch && ch <= '9')
		return ch - '0';
	else if ('a' <= ch && ch <= 'f')
		return ch - 'a' + 10;
	else if ('A' <= ch && ch <= 'F')
		return ch - 'A' + 10;
	return -1;
}
static int hex2(const char *cp)
{
	if (cp[0] && cp[1])
		return (hex1(cp[0]) << 4) | hex1(cp[1]);
	else
		return -1;
}

static void append_literal(const char *cp, const char *ep, struct ref_formatting_state *state)
{
	struct strbuf *s = &state->stack->output;

	while (*cp && (!ep || cp < ep)) {
		if (*cp == '%') {
			if (cp[1] == '%')
				cp++;
			else {
				int ch = hex2(cp + 1);
				if (0 <= ch) {
					strbuf_addch(s, ch);
					cp += 3;
					continue;
				}
			}
		}
		strbuf_addch(s, *cp);
		cp++;
	}
}

void show_ref_array_item(struct ref_array_item *info, const char *format, int quote_style)
{
	const char *cp, *sp, *ep;
	struct strbuf *final_buf;
	struct ref_formatting_state state = REF_FORMATTING_STATE_INIT;

	state.quote_style = quote_style;
	push_stack_element(&state.stack);

	for (cp = format; *cp && (sp = find_next(cp)); cp = ep + 1) {
		struct atom_value *atomv;

		ep = strchr(sp, ')');
		if (cp < sp)
			append_literal(cp, sp, &state);
		get_ref_atom_value(info, parse_ref_filter_atom(sp + 2, ep), &atomv);
		atomv->handler(atomv, &state);
	}
	if (*cp) {
		sp = cp + strlen(cp);
		append_literal(cp, sp, &state);
	}
	if (need_color_reset_at_eol) {
		struct atom_value resetv;
		char color[COLOR_MAXLEN] = "";

		if (color_parse("reset", color) < 0)
			die("BUG: couldn't parse 'reset' as a color");
		resetv.s = color;
		append_atom(&resetv, &state);
	}
	if (state.stack->prev)
		die(_("format: %%(end) atom missing"));
	final_buf = &state.stack->output;
	fwrite(final_buf->buf, 1, final_buf->len, stdout);
	pop_stack_element(&state.stack);
	putchar('\n');
}

/*  If no sorting option is given, use refname to sort as default */
struct ref_sorting *ref_default_sorting(void)
{
	static const char cstr_name[] = "refname";

	struct ref_sorting *sorting = xcalloc(1, sizeof(*sorting));

	sorting->next = NULL;
	sorting->atom = parse_ref_filter_atom(cstr_name, cstr_name + strlen(cstr_name));
	return sorting;
}

int parse_opt_ref_sorting(const struct option *opt, const char *arg, int unset)
{
	struct ref_sorting **sorting_tail = opt->value;
	struct ref_sorting *s;
	int len;

	if (!arg) /* should --no-sort void the list ? */
		return -1;

	s = xcalloc(1, sizeof(*s));
	s->next = *sorting_tail;
	*sorting_tail = s;

	if (*arg == '-') {
		s->reverse = 1;
		arg++;
	}
	if (skip_prefix(arg, "version:", &arg) ||
	    skip_prefix(arg, "v:", &arg))
		s->version = 1;
	len = strlen(arg);
	s->atom = parse_ref_filter_atom(arg, arg+len);
	return 0;
}

int parse_opt_merge_filter(const struct option *opt, const char *arg, int unset)
{
	struct ref_filter *rf = opt->value;
	unsigned char sha1[20];

	rf->merge = starts_with(opt->long_name, "no")
		? REF_FILTER_MERGED_OMIT
		: REF_FILTER_MERGED_INCLUDE;

	if (get_sha1(arg, sha1))
		die(_("malformed object name %s"), arg);

	rf->merge_commit = lookup_commit_reference_gently(sha1, 0);
	if (!rf->merge_commit)
		return opterror(opt, "must point to a commit", 0);

	return 0;
}