static int look_ahead(struct grep_opt *opt,
unsigned long *left_p,
unsigned *lno_p,
char **bol_p)
{
unsigned lno = *lno_p;
char *bol = *bol_p;
struct grep_pat *p;
char *sp, *last_bol;
regoff_t earliest = -1;
for (p = opt->pattern_list; p; p = p->next) {
int hit;
regmatch_t m;
if (p->fixed)
hit = !fixmatch(p->pattern, bol, p->ignore_case, &m);
else {
#ifdef REG_STARTEND
m.rm_so = 0;
m.rm_eo = *left_p;
hit = !regexec(&p->regexp, bol, 1, &m, REG_STARTEND);
#else
hit = !regexec(&p->regexp, bol, 1, &m, 0);
#endif
}
if (!hit || m.rm_so < 0 || m.rm_eo < 0)
continue;
if (earliest < 0 || m.rm_so < earliest)
earliest = m.rm_so;
}
if (earliest < 0) {
*bol_p = bol + *left_p;
*left_p = 0;
return 1;
}
for (sp = bol + earliest; bol < sp && sp[-1] != '\n'; sp--)
; /* find the beginning of the line */
last_bol = sp;
for (sp = bol; sp < last_bol; sp++) {
if (*sp == '\n')
lno++;
}
*left_p -= last_bol - bol;
*bol_p = last_bol;
*lno_p = lno;
return 0;
}
static int patmatch(struct grep_pat *p, char *line, char *eol,
regmatch_t *match, int eflags)
{
int hit;
if (p->fixed)
hit = !fixmatch(p, line, eol, match);
else if (p->pcre_regexp)
hit = !pcrematch(p, line, eol, match, eflags);
else
hit = !regmatch(&p->regexp, line, eol, match, eflags);
return hit;
}
static int match_one_pattern(struct grep_pat *p, char *bol, char *eol,
enum grep_context ctx,
regmatch_t *pmatch, int eflags)
{
int hit = 0;
int saved_ch = 0;
const char *start = bol;
if ((p->token != GREP_PATTERN) &&
((p->token == GREP_PATTERN_HEAD) != (ctx == GREP_CONTEXT_HEAD)))
return 0;
if (p->token == GREP_PATTERN_HEAD) {
const char *field;
size_t len;
assert(p->field < ARRAY_SIZE(header_field));
field = header_field[p->field].field;
len = header_field[p->field].len;
if (strncmp(bol, field, len))
return 0;
bol += len;
saved_ch = strip_timestamp(bol, &eol);
}
again:
if (p->fixed)
hit = !fixmatch(p->pattern, bol, p->ignore_case, pmatch);
else
hit = !regexec(&p->regexp, bol, 1, pmatch, eflags);
if (hit && p->word_regexp) {
if ((pmatch[0].rm_so < 0) ||
(eol - bol) < pmatch[0].rm_so ||
(pmatch[0].rm_eo < 0) ||
(eol - bol) < pmatch[0].rm_eo)
die("regexp returned nonsense");
/* Match beginning must be either beginning of the
* line, or at word boundary (i.e. the last char must
* not be a word char). Similarly, match end must be
* either end of the line, or at word boundary
* (i.e. the next char must not be a word char).
*/
if ( ((pmatch[0].rm_so == 0) ||
!word_char(bol[pmatch[0].rm_so-1])) &&
((pmatch[0].rm_eo == (eol-bol)) ||
!word_char(bol[pmatch[0].rm_eo])) )
;
else
hit = 0;
/* Words consist of at least one character. */
if (pmatch->rm_so == pmatch->rm_eo)
hit = 0;
if (!hit && pmatch[0].rm_so + bol + 1 < eol) {
/* There could be more than one match on the
* line, and the first match might not be
* strict word match. But later ones could be!
* Forward to the next possible start, i.e. the
* next position following a non-word char.
*/
bol = pmatch[0].rm_so + bol + 1;
while (word_char(bol[-1]) && bol < eol)
bol++;
eflags |= REG_NOTBOL;
if (bol < eol)
goto again;
}
}
if (p->token == GREP_PATTERN_HEAD && saved_ch)
*eol = saved_ch;
if (hit) {
pmatch[0].rm_so += bol - start;
pmatch[0].rm_eo += bol - start;
}
return hit;
}
static int match_one_pattern(struct grep_opt *opt, struct grep_pat *p, char *bol, char *eol, enum grep_context ctx)
{
int hit = 0;
int at_true_bol = 1;
int saved_ch = 0;
regmatch_t pmatch[10];
if ((p->token != GREP_PATTERN) &&
((p->token == GREP_PATTERN_HEAD) != (ctx == GREP_CONTEXT_HEAD)))
return 0;
if (p->token == GREP_PATTERN_HEAD) {
const char *field;
size_t len;
assert(p->field < ARRAY_SIZE(header_field));
field = header_field[p->field].field;
len = header_field[p->field].len;
if (strncmp(bol, field, len))
return 0;
bol += len;
saved_ch = strip_timestamp(bol, &eol);
}
again:
if (!opt->fixed) {
regex_t *exp = &p->regexp;
hit = !regexec(exp, bol, ARRAY_SIZE(pmatch),
pmatch, 0);
}
else {
hit = !fixmatch(p->pattern, bol, pmatch);
}
if (hit && opt->word_regexp) {
if ((pmatch[0].rm_so < 0) ||
(eol - bol) <= pmatch[0].rm_so ||
(pmatch[0].rm_eo < 0) ||
(eol - bol) < pmatch[0].rm_eo)
die("regexp returned nonsense");
/* Match beginning must be either beginning of the
* line, or at word boundary (i.e. the last char must
* not be a word char). Similarly, match end must be
* either end of the line, or at word boundary
* (i.e. the next char must not be a word char).
*/
if ( ((pmatch[0].rm_so == 0 && at_true_bol) ||
!word_char(bol[pmatch[0].rm_so-1])) &&
((pmatch[0].rm_eo == (eol-bol)) ||
!word_char(bol[pmatch[0].rm_eo])) )
;
else
hit = 0;
if (!hit && pmatch[0].rm_so + bol + 1 < eol) {
/* There could be more than one match on the
* line, and the first match might not be
* strict word match. But later ones could be!
*/
bol = pmatch[0].rm_so + bol + 1;
at_true_bol = 0;
goto again;
}
}
if (p->token == GREP_PATTERN_HEAD && saved_ch)
*eol = saved_ch;
return hit;
}
