[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
 */
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 (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 (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': %s", spec + 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 *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;

	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));

	start = nth_line_cb(cb_data, 0);

	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': no match", pattern);
	*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 *begin, long *end,
		    const char *path)
{
	*begin = *end = 0;

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

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