[thirdparty/git.git] / line-range.c

#include "git-compat-util.h"
#include "line-range.h"
#include "xdiff-interface.h"
#include "strbuf.h"
#include "userdiff.h"

/*
 * Parse one item in the -L option
 *
 * 'begin' is applicable only to relative range anchors. Absolute anchors
 * ignore this value.
 *
 * When parsing "-L A,B", parse_loc() is called once for A and once for B.
 *
 * When parsing A, 'begin' must be a negative number, the absolute value of
 * which is the line at which relative start-of-range anchors should be
 * based. Beginning of file is represented by -1.
 *
 * When parsing B, 'begin' must be the positive line number immediately
 * following the line computed for 'A'.
 */
static const char *parse_loc(const char *spec, nth_line_fn_t nth_line,
			     void *data, long lines, long begin, long *ret)
{
	char *term;
	const char *line;
	long num;
	int reg_error;
	regex_t regexp;
	regmatch_t match[1];

	/* Allow "-L <something>,+20" to mean starting at <something>
	 * for 20 lines, or "-L <something>,-5" for 5 lines ending at
	 * <something>.
	 */
	if (1 <= begin && (spec[0] == '+' || spec[0] == '-')) {
		num = strtol(spec + 1, &term, 10);
		if (term != spec + 1) {
			if (!ret)
				return term;
			if (num == 0)
				die("-L invalid empty range");
			if (spec[0] == '-')
				num = 0 - num;
			if (0 < num)
				*ret = begin + num - 2;
			else if (!num)
				*ret = begin;
			else
				*ret = begin + num;
			return term;
		}
		return spec;
	}
	num = strtol(spec, &term, 10);
	if (term != spec) {
		if (ret)
			*ret = num;
		return term;
	}

	if (begin < 0) {
		if (spec[0] != '^')
			begin = -begin;
		else {
			begin = 1;
			spec++;
		}
	}

	if (spec[0] != '/')
		return spec;

	/* it could be a regexp of form /.../ */
	for (term = (char *) spec + 1; *term && *term != '/'; term++) {
		if (*term == '\\')
			term++;
	}
	if (*term != '/')
		return spec;

	/* in the scan-only case we are not interested in the regex */
	if (!ret)
		return term+1;

	/* try [spec+1 .. term-1] as regexp */
	*term = 0;
	begin--; /* input is in human terms */
	line = nth_line(data, begin);

	if (!(reg_error = regcomp(&regexp, spec + 1, REG_NEWLINE)) &&
	    !(reg_error = regexec(&regexp, line, 1, match, 0))) {
		const char *cp = line + match[0].rm_so;
		const char *nline;

		while (begin++ < lines) {
			nline = nth_line(data, begin);
			if (line <= cp && cp < nline)
				break;
			line = nline;
		}
		*ret = begin;
		regfree(&regexp);
		*term++ = '/';
		return term;
	}
	else {
		char errbuf[1024];
		regerror(reg_error, &regexp, errbuf, 1024);
		die("-L parameter '%s' starting at line %ld: %s",
		    spec + 1, begin + 1, errbuf);
	}
}

static int match_funcname(xdemitconf_t *xecfg, const char *bol, const char *eol)
{
	if (xecfg) {
		char buf[1];
		return xecfg->find_func(bol, eol - bol, buf, 1,
					xecfg->find_func_priv) >= 0;
	}

	if (bol == eol)
		return 0;
	if (isalpha(*bol) || *bol == '_' || *bol == '$')
		return 1;
	return 0;
}

static const char *find_funcname_matching_regexp(xdemitconf_t *xecfg, const char *start,
						 regex_t *regexp)
{
	int reg_error;
	regmatch_t match[1];
	while (1) {
		const char *bol, *eol;
		reg_error = regexec(regexp, start, 1, match, 0);
		if (reg_error == REG_NOMATCH)
			return NULL;
		else if (reg_error) {
			char errbuf[1024];
			regerror(reg_error, regexp, errbuf, 1024);
			die("-L parameter: regexec() failed: %s", errbuf);
		}
		/* determine extent of line matched */
		bol = start+match[0].rm_so;
		eol = start+match[0].rm_eo;
		while (bol > start && *bol != '\n')
			bol--;
		if (*bol == '\n')
			bol++;
		while (*eol && *eol != '\n')
			eol++;
		if (*eol == '\n')
			eol++;
		/* is it a funcname line? */
		if (match_funcname(xecfg, (char*) bol, (char*) eol))
			return bol;
		start = eol;
	}
}

static const char *parse_range_funcname(const char *arg, nth_line_fn_t nth_line_cb,
					void *cb_data, long lines, long anchor, long *begin, long *end,
					const char *path)
{
	char *pattern;
	const char *term;
	struct userdiff_driver *drv;
	xdemitconf_t *xecfg = NULL;
	const char *start;
	const char *p;
	int reg_error;
	regex_t regexp;

	if (*arg == '^') {
		anchor = 1;
		arg++;
	}

	assert(*arg == ':');
	term = arg+1;
	while (*term && *term != ':') {
		if (*term == '\\' && *(term+1))
			term++;
		term++;
	}
	if (term == arg+1)
		return NULL;
	if (!begin) /* skip_range_arg case */
		return term;

	pattern = xstrndup(arg+1, term-(arg+1));

	anchor--; /* input is in human terms */
	start = nth_line_cb(cb_data, anchor);

	drv = userdiff_find_by_path(path);
	if (drv && drv->funcname.pattern) {
		const struct userdiff_funcname *pe = &drv->funcname;
		xecfg = xcalloc(1, sizeof(*xecfg));
		xdiff_set_find_func(xecfg, pe->pattern, pe->cflags);
	}

	reg_error = regcomp(&regexp, pattern, REG_NEWLINE);
	if (reg_error) {
		char errbuf[1024];
		regerror(reg_error, &regexp, errbuf, 1024);
		die("-L parameter '%s': %s", pattern, errbuf);
	}

	p = find_funcname_matching_regexp(xecfg, (char*) start, &regexp);
	if (!p)
		die("-L parameter '%s' starting at line %ld: no match",
		    pattern, anchor + 1);
	*begin = 0;
	while (p > nth_line_cb(cb_data, *begin))
		(*begin)++;

	if (*begin >= lines)
		die("-L parameter '%s' matches at EOF", pattern);

	*end = *begin+1;
	while (*end < lines) {
		const char *bol = nth_line_cb(cb_data, *end);
		const char *eol = nth_line_cb(cb_data, *end+1);
		if (match_funcname(xecfg, bol, eol))
			break;
		(*end)++;
	}

	regfree(&regexp);
	free(xecfg);
	free(pattern);

	/* compensate for 1-based numbering */
	(*begin)++;

	return term;
}

int parse_range_arg(const char *arg, nth_line_fn_t nth_line_cb,
		    void *cb_data, long lines, long anchor,
		    long *begin, long *end, const char *path)
{
	*begin = *end = 0;

	if (anchor < 1)
		anchor = 1;
	if (anchor > lines)
		anchor = lines + 1;

	if (*arg == ':' || (*arg == '^' && *(arg + 1) == ':')) {
		arg = parse_range_funcname(arg, nth_line_cb, cb_data, lines, anchor, begin, end, path);
		if (!arg || *arg)
			return -1;
		return 0;
	}

	arg = parse_loc(arg, nth_line_cb, cb_data, lines, -anchor, begin);

	if (*arg == ',')
		arg = parse_loc(arg + 1, nth_line_cb, cb_data, lines, *begin + 1, end);

	if (*arg)
		return -1;

	if (*begin && *end && *end < *begin) {
		long tmp;
		tmp = *end; *end = *begin; *begin = tmp;
	}

	return 0;
}

const char *skip_range_arg(const char *arg)
{
	if (*arg == ':' || (*arg == '^' && *(arg + 1) == ':'))
		return parse_range_funcname(arg, NULL, NULL, 0, 0, NULL, NULL, NULL);

	arg = parse_loc(arg, NULL, NULL, 0, -1, NULL);

	if (*arg == ',')
		arg = parse_loc(arg+1, NULL, NULL, 0, 0, NULL);

	return arg;
}
Commit	Line	Data
25ed3412 BY	1	#include "git-compat-util.h"
25ed3412 BY	2	#include "line-range.h"
13b8f68c TR	3	#include "xdiff-interface.h"
	4	#include "strbuf.h"
	5	#include "userdiff.h"
25ed3412 BY	6
	7	/*
	8	* Parse one item in the -L option
815834e9 ES	9	*
	10	* 'begin' is applicable only to relative range anchors. Absolute anchors
	11	* ignore this value.
	12	*
	13	* When parsing "-L A,B", parse_loc() is called once for A and once for B.
	14	*
	15	* When parsing A, 'begin' must be a negative number, the absolute value of
	16	* which is the line at which relative start-of-range anchors should be
	17	* based. Beginning of file is represented by -1.
	18	*
	19	* When parsing B, 'begin' must be the positive line number immediately
	20	* following the line computed for 'A'.
25ed3412 BY	21	*/
	22	static const char parse_loc(const char spec, nth_line_fn_t nth_line,
	23	void data, long lines, long begin, long ret)
	24	{
	25	char *term;
	26	const char *line;
	27	long num;
	28	int reg_error;
	29	regex_t regexp;
	30	regmatch_t match[1];
	31
	32	/* Allow "-L <something>,+20" to mean starting at <something>
	33	* for 20 lines, or "-L <something>,-5" for 5 lines ending at
	34	* <something>.
	35	*/
5d57cac6	36	if (1 <= begin && (spec[0] == '+' \|\| spec[0] == '-')) {
25ed3412 BY	37	num = strtol(spec + 1, &term, 10);
25ed3412 BY	38	if (term != spec + 1) {
12da1d1f TR	39	if (!ret)
12da1d1f TR	40	return term;
abba3539 ES	41	if (num == 0)
abba3539 ES	42	die("-L invalid empty range");
25ed3412 BY	43	if (spec[0] == '-')
	44	num = 0 - num;
	45	if (0 < num)
	46	*ret = begin + num - 2;
	47	else if (!num)
	48	*ret = begin;
	49	else
	50	*ret = begin + num;
	51	return term;
	52	}
	53	return spec;
	54	}
	55	num = strtol(spec, &term, 10);
	56	if (term != spec) {
12da1d1f TR	57	if (ret)
12da1d1f TR	58	*ret = num;
25ed3412 BY	59	return term;
25ed3412 BY	60	}
815834e9	61
a6ac5f98 ES	62	if (begin < 0) {
	63	if (spec[0] != '^')
	64	begin = -begin;
	65	else {
	66	begin = 1;
	67	spec++;
	68	}
	69	}
815834e9	70
25ed3412 BY	71	if (spec[0] != '/')
	72	return spec;
	73
	74	/* it could be a regexp of form /.../ */
	75	for (term = (char ) spec + 1; term && *term != '/'; term++) {
	76	if (*term == '\\')
	77	term++;
	78	}
	79	if (*term != '/')
	80	return spec;
	81
12da1d1f TR	82	/* in the scan-only case we are not interested in the regex */
	83	if (!ret)
	84	return term+1;
	85
25ed3412 BY	86	/* try [spec+1 .. term-1] as regexp */
	87	*term = 0;
	88	begin--; /* input is in human terms */
	89	line = nth_line(data, begin);
	90
	91	if (!(reg_error = regcomp(&regexp, spec + 1, REG_NEWLINE)) &&
	92	!(reg_error = regexec(&regexp, line, 1, match, 0))) {
	93	const char *cp = line + match[0].rm_so;
	94	const char *nline;
	95
	96	while (begin++ < lines) {
	97	nline = nth_line(data, begin);
	98	if (line <= cp && cp < nline)
	99	break;
	100	line = nline;
	101	}
	102	*ret = begin;
	103	regfree(&regexp);
	104	*term++ = '/';
	105	return term;
	106	}
	107	else {
	108	char errbuf[1024];
	109	regerror(reg_error, &regexp, errbuf, 1024);
815834e9 ES	110	die("-L parameter '%s' starting at line %ld: %s",
815834e9 ES	111	spec + 1, begin + 1, errbuf);
25ed3412 BY	112	}
	113	}
	114
13b8f68c TR	115	static int match_funcname(xdemitconf_t xecfg, const char bol, const char *eol)
	116	{
	117	if (xecfg) {
	118	char buf[1];
	119	return xecfg->find_func(bol, eol - bol, buf, 1,
	120	xecfg->find_func_priv) >= 0;
	121	}
	122
	123	if (bol == eol)
	124	return 0;
	125	if (isalpha(bol) \|\| bol == '_' \|\| *bol == '$')
	126	return 1;
	127	return 0;
	128	}
	129
	130	static const char find_funcname_matching_regexp(xdemitconf_t xecfg, const char *start,
	131	regex_t *regexp)
	132	{
	133	int reg_error;
	134	regmatch_t match[1];
	135	while (1) {
	136	const char bol, eol;
	137	reg_error = regexec(regexp, start, 1, match, 0);
	138	if (reg_error == REG_NOMATCH)
	139	return NULL;
	140	else if (reg_error) {
	141	char errbuf[1024];
	142	regerror(reg_error, regexp, errbuf, 1024);
	143	die("-L parameter: regexec() failed: %s", errbuf);
	144	}
	145	/* determine extent of line matched */
	146	bol = start+match[0].rm_so;
	147	eol = start+match[0].rm_eo;
	148	while (bol > start && *bol != '\n')
	149	bol--;
	150	if (*bol == '\n')
	151	bol++;
	152	while (eol && eol != '\n')
	153	eol++;
	154	if (*eol == '\n')
	155	eol++;
	156	/* is it a funcname line? */
	157	if (match_funcname(xecfg, (char) bol, (char) eol))
	158	return bol;
	159	start = eol;
	160	}
	161	}
	162
	163	static const char parse_range_funcname(const char arg, nth_line_fn_t nth_line_cb,
1ce761a5	164	void cb_data, long lines, long anchor, long begin, long *end,
13b8f68c TR	165	const char *path)
	166	{
	167	char *pattern;
	168	const char *term;
	169	struct userdiff_driver *drv;
	170	xdemitconf_t *xecfg = NULL;
	171	const char *start;
	172	const char *p;
	173	int reg_error;
	174	regex_t regexp;
	175
215e76c7 ES	176	if (*arg == '^') {
	177	anchor = 1;
	178	arg++;
	179	}
	180
13b8f68c TR	181	assert(*arg == ':');
	182	term = arg+1;
	183	while (term && term != ':') {
	184	if (term == '\\' && (term+1))
	185	term++;
	186	term++;
	187	}
	188	if (term == arg+1)
	189	return NULL;
	190	if (!begin) /* skip_range_arg case */
	191	return term;
	192
	193	pattern = xstrndup(arg+1, term-(arg+1));
	194
1ce761a5 ES	195	anchor--; /* input is in human terms */
1ce761a5 ES	196	start = nth_line_cb(cb_data, anchor);
13b8f68c TR	197
	198	drv = userdiff_find_by_path(path);
	199	if (drv && drv->funcname.pattern) {
	200	const struct userdiff_funcname *pe = &drv->funcname;
	201	xecfg = xcalloc(1, sizeof(*xecfg));
	202	xdiff_set_find_func(xecfg, pe->pattern, pe->cflags);
	203	}
	204
	205	reg_error = regcomp(&regexp, pattern, REG_NEWLINE);
	206	if (reg_error) {
	207	char errbuf[1024];
	208	regerror(reg_error, &regexp, errbuf, 1024);
	209	die("-L parameter '%s': %s", pattern, errbuf);
	210	}
	211
	212	p = find_funcname_matching_regexp(xecfg, (char*) start, &regexp);
	213	if (!p)
1ce761a5 ES	214	die("-L parameter '%s' starting at line %ld: no match",
1ce761a5 ES	215	pattern, anchor + 1);
13b8f68c TR	216	*begin = 0;
	217	while (p > nth_line_cb(cb_data, *begin))
	218	(*begin)++;
	219
	220	if (*begin >= lines)
	221	die("-L parameter '%s' matches at EOF", pattern);
	222
	223	end = begin+1;
	224	while (*end < lines) {
	225	const char bol = nth_line_cb(cb_data, end);
	226	const char eol = nth_line_cb(cb_data, end+1);
	227	if (match_funcname(xecfg, bol, eol))
	228	break;
	229	(*end)++;
	230	}
	231
	232	regfree(&regexp);
	233	free(xecfg);
	234	free(pattern);
	235
	236	/* compensate for 1-based numbering */
	237	(*begin)++;
	238
	239	return term;
	240	}
	241
25ed3412	242	int parse_range_arg(const char *arg, nth_line_fn_t nth_line_cb,
815834e9 ES	243	void *cb_data, long lines, long anchor,
815834e9 ES	244	long begin, long end, const char *path)
25ed3412	245	{
3bf65f9e ES	246	begin = end = 0;
3bf65f9e ES	247
815834e9 ES	248	if (anchor < 1)
	249	anchor = 1;
	250	if (anchor > lines)
	251	anchor = lines + 1;
	252
215e76c7	253	if (arg == ':' \|\| (arg == '^' && *(arg + 1) == ':')) {
1ce761a5	254	arg = parse_range_funcname(arg, nth_line_cb, cb_data, lines, anchor, begin, end, path);
13b8f68c TR	255	if (!arg \|\| *arg)
	256	return -1;
	257	return 0;
	258	}
	259
815834e9	260	arg = parse_loc(arg, nth_line_cb, cb_data, lines, -anchor, begin);
25ed3412 BY	261
	262	if (*arg == ',')
	263	arg = parse_loc(arg + 1, nth_line_cb, cb_data, lines, *begin + 1, end);
	264
	265	if (*arg)
	266	return -1;
	267
3bf65f9e ES	268	if (begin && end && end < begin) {
	269	long tmp;
	270	tmp = end; end = begin; begin = tmp;
	271	}
	272
25ed3412 BY	273	return 0;
25ed3412 BY	274	}
12da1d1f TR	275
	276	const char skip_range_arg(const char arg)
	277	{
215e76c7	278	if (arg == ':' \|\| (arg == '^' && *(arg + 1) == ':'))
1ce761a5	279	return parse_range_funcname(arg, NULL, NULL, 0, 0, NULL, NULL, NULL);
13b8f68c	280
12da1d1f TR	281	arg = parse_loc(arg, NULL, NULL, 0, -1, NULL);
	282
	283	if (*arg == ',')
	284	arg = parse_loc(arg+1, NULL, NULL, 0, 0, NULL);
	285
	286	return arg;
	287	}