[thirdparty/git.git] / xdiff-interface.c

#include "cache.h"
#include "xdiff-interface.h"
#include "xdiff/xtypes.h"
#include "xdiff/xdiffi.h"
#include "xdiff/xemit.h"
#include "xdiff/xmacros.h"

struct xdiff_emit_state {
	xdiff_emit_consume_fn consume;
	void *consume_callback_data;
	struct strbuf remainder;
};

static int parse_num(char **cp_p, int *num_p)
{
	char *cp = *cp_p;
	int num = 0;

	while ('0' <= *cp && *cp <= '9')
		num = num * 10 + *cp++ - '0';
	if (!(cp - *cp_p))
		return -1;
	*cp_p = cp;
	*num_p = num;
	return 0;
}

int parse_hunk_header(char *line, int len,
		      int *ob, int *on,
		      int *nb, int *nn)
{
	char *cp;
	cp = line + 4;
	if (parse_num(&cp, ob)) {
	bad_line:
		return error("malformed diff output: %s", line);
	}
	if (*cp == ',') {
		cp++;
		if (parse_num(&cp, on))
			goto bad_line;
	}
	else
		*on = 1;
	if (*cp++ != ' ' || *cp++ != '+')
		goto bad_line;
	if (parse_num(&cp, nb))
		goto bad_line;
	if (*cp == ',') {
		cp++;
		if (parse_num(&cp, nn))
			goto bad_line;
	}
	else
		*nn = 1;
	return -!!memcmp(cp, " @@", 3);
}

static void consume_one(void *priv_, char *s, unsigned long size)
{
	struct xdiff_emit_state *priv = priv_;
	char *ep;
	while (size) {
		unsigned long this_size;
		ep = memchr(s, '\n', size);
		this_size = (ep == NULL) ? size : (ep - s + 1);
		priv->consume(priv->consume_callback_data, s, this_size);
		size -= this_size;
		s += this_size;
	}
}

static int xdiff_outf(void *priv_, mmbuffer_t *mb, int nbuf)
{
	struct xdiff_emit_state *priv = priv_;
	int i;

	for (i = 0; i < nbuf; i++) {
		if (mb[i].ptr[mb[i].size-1] != '\n') {
			/* Incomplete line */
			strbuf_add(&priv->remainder, mb[i].ptr, mb[i].size);
			continue;
		}

		/* we have a complete line */
		if (!priv->remainder.len) {
			consume_one(priv, mb[i].ptr, mb[i].size);
			continue;
		}
		strbuf_add(&priv->remainder, mb[i].ptr, mb[i].size);
		consume_one(priv, priv->remainder.buf, priv->remainder.len);
		strbuf_reset(&priv->remainder);
	}
	if (priv->remainder.len) {
		consume_one(priv, priv->remainder.buf, priv->remainder.len);
		strbuf_reset(&priv->remainder);
	}
	return 0;
}

/*
 * Trim down common substring at the end of the buffers,
 * but leave at least ctx lines at the end.
 */
static void trim_common_tail(mmfile_t *a, mmfile_t *b, long ctx)
{
	const int blk = 1024;
	long trimmed = 0, recovered = 0;
	char *ap = a->ptr + a->size;
	char *bp = b->ptr + b->size;
	long smaller = (a->size < b->size) ? a->size : b->size;

	if (ctx)
		return;

	while (blk + trimmed <= smaller && !memcmp(ap - blk, bp - blk, blk)) {
		trimmed += blk;
		ap -= blk;
		bp -= blk;
	}

	while (recovered < trimmed)
		if (ap[recovered++] == '\n')
			break;
	a->size -= trimmed - recovered;
	b->size -= trimmed - recovered;
}

int xdi_diff(mmfile_t *mf1, mmfile_t *mf2, xpparam_t const *xpp, xdemitconf_t const *xecfg, xdemitcb_t *xecb)
{
	mmfile_t a = *mf1;
	mmfile_t b = *mf2;

	trim_common_tail(&a, &b, xecfg->ctxlen);

	return xdl_diff(&a, &b, xpp, xecfg, xecb);
}

int xdi_diff_outf(mmfile_t *mf1, mmfile_t *mf2,
		  xdiff_emit_consume_fn fn, void *consume_callback_data,
		  xpparam_t const *xpp, xdemitconf_t const *xecfg)
{
	int ret;
	struct xdiff_emit_state state;
	xdemitcb_t ecb;

	memset(&state, 0, sizeof(state));
	state.consume = fn;
	state.consume_callback_data = consume_callback_data;
	memset(&ecb, 0, sizeof(ecb));
	ecb.outf = xdiff_outf;
	ecb.priv = &state;
	strbuf_init(&state.remainder, 0);
	ret = xdi_diff(mf1, mf2, xpp, xecfg, &ecb);
	strbuf_release(&state.remainder);
	return ret;
}

int read_mmfile(mmfile_t *ptr, const char *filename)
{
	struct stat st;
	FILE *f;
	size_t sz;

	if (stat(filename, &st))
		return error("Could not stat %s", filename);
	if ((f = fopen(filename, "rb")) == NULL)
		return error("Could not open %s", filename);
	sz = xsize_t(st.st_size);
	ptr->ptr = xmalloc(sz ? sz : 1);
	if (sz && fread(ptr->ptr, sz, 1, f) != 1) {
		fclose(f);
		return error("Could not read %s", filename);
	}
	fclose(f);
	ptr->size = sz;
	return 0;
}

void read_mmblob(mmfile_t *ptr, const unsigned char *sha1)
{
	unsigned long size;
	enum object_type type;

	if (!hashcmp(sha1, null_sha1)) {
		ptr->ptr = xstrdup("");
		ptr->size = 0;
		return;
	}

	ptr->ptr = read_sha1_file(sha1, &type, &size);
	if (!ptr->ptr || type != OBJ_BLOB)
		die("unable to read blob object %s", sha1_to_hex(sha1));
	ptr->size = size;
}

#define FIRST_FEW_BYTES 8000
int buffer_is_binary(const char *ptr, unsigned long size)
{
	if (FIRST_FEW_BYTES < size)
		size = FIRST_FEW_BYTES;
	return !!memchr(ptr, 0, size);
}

struct ff_regs {
	int nr;
	struct ff_reg {
		regex_t re;
		int negate;
	} *array;
};

static long ff_regexp(const char *line, long len,
		char *buffer, long buffer_size, void *priv)
{
	char *line_buffer;
	struct ff_regs *regs = priv;
	regmatch_t pmatch[2];
	int i;
	int result = -1;

	/* Exclude terminating newline (and cr) from matching */
	if (len > 0 && line[len-1] == '\n') {
		if (len > 1 && line[len-2] == '\r')
			len -= 2;
		else
			len--;
	}

	line_buffer = xstrndup(line, len); /* make NUL terminated */

	for (i = 0; i < regs->nr; i++) {
		struct ff_reg *reg = regs->array + i;
		if (!regexec(&reg->re, line_buffer, 2, pmatch, 0)) {
			if (reg->negate)
				goto fail;
			break;
		}
	}
	if (regs->nr <= i)
		goto fail;
	i = pmatch[1].rm_so >= 0 ? 1 : 0;
	line += pmatch[i].rm_so;
	result = pmatch[i].rm_eo - pmatch[i].rm_so;
	if (result > buffer_size)
		result = buffer_size;
	while (result > 0 && (isspace(line[result - 1])))
		result--;
	memcpy(buffer, line, result);
 fail:
	free(line_buffer);
	return result;
}

void xdiff_set_find_func(xdemitconf_t *xecfg, const char *value, int cflags)
{
	int i;
	struct ff_regs *regs;

	xecfg->find_func = ff_regexp;
	regs = xecfg->find_func_priv = xmalloc(sizeof(struct ff_regs));
	for (i = 0, regs->nr = 1; value[i]; i++)
		if (value[i] == '\n')
			regs->nr++;
	regs->array = xmalloc(regs->nr * sizeof(struct ff_reg));
	for (i = 0; i < regs->nr; i++) {
		struct ff_reg *reg = regs->array + i;
		const char *ep = strchr(value, '\n'), *expression;
		char *buffer = NULL;

		reg->negate = (*value == '!');
		if (reg->negate && i == regs->nr - 1)
			die("Last expression must not be negated: %s", value);
		if (*value == '!')
			value++;
		if (ep)
			expression = buffer = xstrndup(value, ep - value);
		else
			expression = value;
		if (regcomp(&reg->re, expression, cflags))
			die("Invalid regexp to look for hunk header: %s", expression);
		free(buffer);
		value = ep + 1;
	}
}

void xdiff_clear_find_func(xdemitconf_t *xecfg)
{
	if (xecfg->find_func) {
		int i;
		struct ff_regs *regs = xecfg->find_func_priv;

		for (i = 0; i < regs->nr; i++)
			regfree(&regs->array[i].re);
		free(regs->array);
		free(regs);
		xecfg->find_func = NULL;
		xecfg->find_func_priv = NULL;
	}
}

int git_xmerge_style = -1;

int git_xmerge_config(const char *var, const char *value, void *cb)
{
	if (!strcmp(var, "merge.conflictstyle")) {
		if (!value)
			die("'%s' is not a boolean", var);
		if (!strcmp(value, "diff3"))
			git_xmerge_style = XDL_MERGE_DIFF3;
		else if (!strcmp(value, "merge"))
			git_xmerge_style = 0;
		else
			die("unknown style '%s' given for '%s'",
			    value, var);
		return 0;
	}
	return git_default_config(var, value, cb);
}
Commit	Line	Data
d9ea73e0 JH	1	#include "cache.h"
d9ea73e0 JH	2	#include "xdiff-interface.h"
86295bb6 RS	3	#include "xdiff/xtypes.h"
	4	#include "xdiff/xdiffi.h"
	5	#include "xdiff/xemit.h"
	6	#include "xdiff/xmacros.h"
8a3f524b JH	7
	8	struct xdiff_emit_state {
	9	xdiff_emit_consume_fn consume;
	10	void *consume_callback_data;
	11	struct strbuf remainder;
	12	};
d9ea73e0	13
a0fd3146	14	static int parse_num(char *cp_p, int num_p)
c1e335a4 JH	15	{
c1e335a4 JH	16	char cp = cp_p;
a0fd3146	17	int num = 0;
c1e335a4 JH	18
	19	while ('0' <= cp && cp <= '9')
	20	num = num * 10 + *cp++ - '0';
eb3a9dd3	21	if (!(cp - *cp_p))
c1e335a4 JH	22	return -1;
	23	*cp_p = cp;
	24	*num_p = num;
	25	return 0;
	26	}
	27
	28	int parse_hunk_header(char *line, int len,
a0fd3146 JH	29	int ob, int on,
a0fd3146 JH	30	int nb, int nn)
c1e335a4 JH	31	{
	32	char *cp;
	33	cp = line + 4;
	34	if (parse_num(&cp, ob)) {
	35	bad_line:
	36	return error("malformed diff output: %s", line);
	37	}
	38	if (*cp == ',') {
	39	cp++;
	40	if (parse_num(&cp, on))
	41	goto bad_line;
	42	}
	43	else
	44	*on = 1;
	45	if (cp++ != ' ' \|\| cp++ != '+')
	46	goto bad_line;
	47	if (parse_num(&cp, nb))
	48	goto bad_line;
	49	if (*cp == ',') {
	50	cp++;
	51	if (parse_num(&cp, nn))
	52	goto bad_line;
	53	}
	54	else
	55	*nn = 1;
	56	return -!!memcmp(cp, " @@", 3);
	57	}
	58
d9ea73e0 JH	59	static void consume_one(void priv_, char s, unsigned long size)
	60	{
	61	struct xdiff_emit_state *priv = priv_;
	62	char *ep;
	63	while (size) {
	64	unsigned long this_size;
	65	ep = memchr(s, '\n', size);
	66	this_size = (ep == NULL) ? size : (ep - s + 1);
8a3f524b	67	priv->consume(priv->consume_callback_data, s, this_size);
d9ea73e0 JH	68	size -= this_size;
	69	s += this_size;
	70	}
	71	}
	72
c99db9d2	73	static int xdiff_outf(void priv_, mmbuffer_t mb, int nbuf)
d9ea73e0 JH	74	{
	75	struct xdiff_emit_state *priv = priv_;
	76	int i;
	77
	78	for (i = 0; i < nbuf; i++) {
	79	if (mb[i].ptr[mb[i].size-1] != '\n') {
	80	/* Incomplete line */
b4637760	81	strbuf_add(&priv->remainder, mb[i].ptr, mb[i].size);
d9ea73e0 JH	82	continue;
	83	}
	84
	85	/* we have a complete line */
b4637760	86	if (!priv->remainder.len) {
d9ea73e0 JH	87	consume_one(priv, mb[i].ptr, mb[i].size);
	88	continue;
	89	}
b4637760 BD	90	strbuf_add(&priv->remainder, mb[i].ptr, mb[i].size);
	91	consume_one(priv, priv->remainder.buf, priv->remainder.len);
	92	strbuf_reset(&priv->remainder);
d9ea73e0	93	}
b4637760 BD	94	if (priv->remainder.len) {
	95	consume_one(priv, priv->remainder.buf, priv->remainder.len);
	96	strbuf_reset(&priv->remainder);
d9ea73e0 JH	97	}
	98	return 0;
	99	}
7cab5883	100
913b45f5 JH	101	/*
	102	* Trim down common substring at the end of the buffers,
	103	* but leave at least ctx lines at the end.
	104	*/
29ab27f4	105	static void trim_common_tail(mmfile_t a, mmfile_t b, long ctx)
913b45f5 JH	106	{
913b45f5 JH	107	const int blk = 1024;
52499977	108	long trimmed = 0, recovered = 0;
913b45f5 JH	109	char *ap = a->ptr + a->size;
	110	char *bp = b->ptr + b->size;
	111	long smaller = (a->size < b->size) ? a->size : b->size;
	112
d2f82950 LT	113	if (ctx)
	114	return;
	115
913b45f5 JH	116	while (blk + trimmed <= smaller && !memcmp(ap - blk, bp - blk, blk)) {
	117	trimmed += blk;
	118	ap -= blk;
	119	bp -= blk;
	120	}
	121
d2f82950	122	while (recovered < trimmed)
52499977	123	if (ap[recovered++] == '\n')
d2f82950 LT	124	break;
	125	a->size -= trimmed - recovered;
	126	b->size -= trimmed - recovered;
913b45f5 JH	127	}
913b45f5 JH	128
c279d7e9 JH	129	int xdi_diff(mmfile_t mf1, mmfile_t mf2, xpparam_t const xpp, xdemitconf_t const xecfg, xdemitcb_t *xecb)
c279d7e9 JH	130	{
913b45f5 JH	131	mmfile_t a = *mf1;
	132	mmfile_t b = *mf2;
	133
	134	trim_common_tail(&a, &b, xecfg->ctxlen);
	135
	136	return xdl_diff(&a, &b, xpp, xecfg, xecb);
c279d7e9 JH	137	}
c279d7e9 JH	138
c99db9d2	139	int xdi_diff_outf(mmfile_t mf1, mmfile_t mf2,
8a3f524b	140	xdiff_emit_consume_fn fn, void *consume_callback_data,
dfea7900	141	xpparam_t const xpp, xdemitconf_t const xecfg)
c99db9d2 BD	142	{
c99db9d2 BD	143	int ret;
8a3f524b	144	struct xdiff_emit_state state;
dfea7900	145	xdemitcb_t ecb;
8a3f524b JH	146
	147	memset(&state, 0, sizeof(state));
	148	state.consume = fn;
	149	state.consume_callback_data = consume_callback_data;
dfea7900 RS	150	memset(&ecb, 0, sizeof(ecb));
	151	ecb.outf = xdiff_outf;
	152	ecb.priv = &state;
8a3f524b	153	strbuf_init(&state.remainder, 0);
dfea7900	154	ret = xdi_diff(mf1, mf2, xpp, xecfg, &ecb);
8a3f524b	155	strbuf_release(&state.remainder);
c99db9d2 BD	156	return ret;
	157	}
	158
7cab5883 JS	159	int read_mmfile(mmfile_t ptr, const char filename)
	160	{
	161	struct stat st;
	162	FILE *f;
dc49cd76	163	size_t sz;
7cab5883 JS	164
	165	if (stat(filename, &st))
	166	return error("Could not stat %s", filename);
	167	if ((f = fopen(filename, "rb")) == NULL)
	168	return error("Could not open %s", filename);
dc49cd76	169	sz = xsize_t(st.st_size);
381b851c	170	ptr->ptr = xmalloc(sz ? sz : 1);
5fd89814 RS	171	if (sz && fread(ptr->ptr, sz, 1, f) != 1) {
5fd89814 RS	172	fclose(f);
7cab5883	173	return error("Could not read %s", filename);
5fd89814	174	}
7cab5883	175	fclose(f);
dc49cd76	176	ptr->size = sz;
7cab5883 JS	177	return 0;
	178	}
	179
06b65939 ML	180	void read_mmblob(mmfile_t ptr, const unsigned char sha1)
	181	{
	182	unsigned long size;
	183	enum object_type type;
	184
	185	if (!hashcmp(sha1, null_sha1)) {
	186	ptr->ptr = xstrdup("");
	187	ptr->size = 0;
	188	return;
	189	}
	190
	191	ptr->ptr = read_sha1_file(sha1, &type, &size);
	192	if (!ptr->ptr \|\| type != OBJ_BLOB)
	193	die("unable to read blob object %s", sha1_to_hex(sha1));
	194	ptr->size = size;
	195	}
	196
6bfce93e JS	197	#define FIRST_FEW_BYTES 8000
	198	int buffer_is_binary(const char *ptr, unsigned long size)
	199	{
	200	if (FIRST_FEW_BYTES < size)
	201	size = FIRST_FEW_BYTES;
	202	return !!memchr(ptr, 0, size);
	203	}
f258475a JH	204
	205	struct ff_regs {
	206	int nr;
	207	struct ff_reg {
	208	regex_t re;
	209	int negate;
	210	} *array;
	211	};
	212
	213	static long ff_regexp(const char *line, long len,
	214	char buffer, long buffer_size, void priv)
	215	{
a5a5a048	216	char *line_buffer;
f258475a JH	217	struct ff_regs *regs = priv;
f258475a JH	218	regmatch_t pmatch[2];
3d8dccd7 JH	219	int i;
3d8dccd7 JH	220	int result = -1;
f258475a	221
a5a5a048 BC	222	/* Exclude terminating newline (and cr) from matching */
a5a5a048 BC	223	if (len > 0 && line[len-1] == '\n') {
46dc1b0e JH	224	if (len > 1 && line[len-2] == '\r')
	225	len -= 2;
	226	else
	227	len--;
	228	}
	229
	230	line_buffer = xstrndup(line, len); /* make NUL terminated */
f258475a JH	231
	232	for (i = 0; i < regs->nr; i++) {
	233	struct ff_reg *reg = regs->array + i;
3d8dccd7 JH	234	if (!regexec(&reg->re, line_buffer, 2, pmatch, 0)) {
	235	if (reg->negate)
	236	goto fail;
	237	break;
f258475a JH	238	}
f258475a JH	239	}
3d8dccd7 JH	240	if (regs->nr <= i)
3d8dccd7 JH	241	goto fail;
f258475a JH	242	i = pmatch[1].rm_so >= 0 ? 1 : 0;
	243	line += pmatch[i].rm_so;
	244	result = pmatch[i].rm_eo - pmatch[i].rm_so;
	245	if (result > buffer_size)
	246	result = buffer_size;
1b6ecbad BC	247	while (result > 0 && (isspace(line[result - 1])))
1b6ecbad BC	248	result--;
f258475a	249	memcpy(buffer, line, result);
3d8dccd7	250	fail:
f258475a JH	251	free(line_buffer);
	252	return result;
	253	}
	254
a013585b	255	void xdiff_set_find_func(xdemitconf_t xecfg, const char value, int cflags)
f258475a JH	256	{
	257	int i;
	258	struct ff_regs *regs;
	259
	260	xecfg->find_func = ff_regexp;
	261	regs = xecfg->find_func_priv = xmalloc(sizeof(struct ff_regs));
	262	for (i = 0, regs->nr = 1; value[i]; i++)
	263	if (value[i] == '\n')
	264	regs->nr++;
	265	regs->array = xmalloc(regs->nr * sizeof(struct ff_reg));
	266	for (i = 0; i < regs->nr; i++) {
	267	struct ff_reg *reg = regs->array + i;
	268	const char ep = strchr(value, '\n'), expression;
	269	char *buffer = NULL;
	270
	271	reg->negate = (*value == '!');
	272	if (reg->negate && i == regs->nr - 1)
	273	die("Last expression must not be negated: %s", value);
	274	if (*value == '!')
	275	value++;
	276	if (ep)
	277	expression = buffer = xstrndup(value, ep - value);
	278	else
	279	expression = value;
a013585b	280	if (regcomp(&reg->re, expression, cflags))
f258475a	281	die("Invalid regexp to look for hunk header: %s", expression);
8e0f7003	282	free(buffer);
f258475a JH	283	value = ep + 1;
	284	}
	285	}
b5412484	286
8cfe5f1c RS	287	void xdiff_clear_find_func(xdemitconf_t *xecfg)
	288	{
	289	if (xecfg->find_func) {
	290	int i;
	291	struct ff_regs *regs = xecfg->find_func_priv;
	292
	293	for (i = 0; i < regs->nr; i++)
	294	regfree(&regs->array[i].re);
	295	free(regs->array);
	296	free(regs);
	297	xecfg->find_func = NULL;
	298	xecfg->find_func_priv = NULL;
	299	}
	300	}
	301
b5412484 JH	302	int git_xmerge_style = -1;
	303
	304	int git_xmerge_config(const char var, const char value, void *cb)
	305	{
8c2be75f	306	if (!strcmp(var, "merge.conflictstyle")) {
b5412484 JH	307	if (!value)
	308	die("'%s' is not a boolean", var);
	309	if (!strcmp(value, "diff3"))
	310	git_xmerge_style = XDL_MERGE_DIFF3;
	311	else if (!strcmp(value, "merge"))
	312	git_xmerge_style = 0;
	313	else
	314	die("unknown style '%s' given for '%s'",
	315	value, var);
	316	return 0;
	317	}
	318	return git_default_config(var, value, cb);
	319	}