static int pcre2match(struct grep_pat *p, const char *line, const char *eol,
regmatch_t *match, int eflags)
{
int ret, flags = 0;
PCRE2_SIZE *ovector;
PCRE2_UCHAR errbuf[256];
if (eflags & REG_NOTBOL)
flags |= PCRE2_NOTBOL;
if (p->pcre2_jit_on)
ret = pcre2_jit_match(p->pcre2_pattern, (unsigned char *)line,
eol - line, 0, flags, p->pcre2_match_data,
NULL);
else
ret = pcre2_match(p->pcre2_pattern, (unsigned char *)line,
eol - line, 0, flags, p->pcre2_match_data,
NULL);
if (ret < 0 && ret != PCRE2_ERROR_NOMATCH) {
pcre2_get_error_message(ret, errbuf, sizeof(errbuf));
die("%s failed with error code %d: %s",
(p->pcre2_jit_on ? "pcre2_jit_match" : "pcre2_match"), ret,
errbuf);
}
if (ret > 0) {
ovector = pcre2_get_ovector_pointer(p->pcre2_match_data);
ret = 0;
match->rm_so = (int)ovector[0];
match->rm_eo = (int)ovector[1];
}
return ret;
}
/* PCRE 2 version */
gboolean
rspamd_regexp_search (rspamd_regexp_t *re, const gchar *text, gsize len,
const gchar **start, const gchar **end, gboolean raw,
GArray *captures)
{
pcre2_match_data *match_data;
pcre2_match_context *mcontext;
PCRE_T *r;
const gchar *mt;
gsize remain = 0, *ovec;
gint rc, match_flags, novec, i;
gboolean ret = FALSE;
g_assert (re != NULL);
g_assert (text != NULL);
if (len == 0) {
len = strlen (text);
}
if (end != NULL && *end != NULL) {
/* Incremental search */
mt = (*end);
if ((gint)len > (mt - text)) {
remain = len - (mt - text);
}
}
else {
mt = text;
remain = len;
}
if (remain == 0) {
return FALSE;
}
match_flags = 0;
if (raw || re->re == re->raw_re) {
r = re->raw_re;
mcontext = re->raw_mcontext;
}
else {
r = re->re;
mcontext = re->mcontext;
}
match_data = pcre2_match_data_create (re->ncaptures + 1, NULL);
#ifdef HAVE_PCRE_JIT
if (!(re->flags & RSPAMD_REGEXP_FLAG_DISABLE_JIT) && can_jit) {
if (re->re != re->raw_re && !g_utf8_validate (mt, remain, NULL)) {
msg_err ("bad utf8 input for JIT re");
return FALSE;
}
rc = pcre2_jit_match (r, mt, remain, 0, match_flags, match_data,
mcontext);
}
else {
rc = pcre2_match (r, mt, remain, 0, match_flags, match_data,
mcontext);
}
#else
rc = pcre2_match (r, mt, remain, 0, match_flags, match_data,
mcontext);
#endif
if (rc >= 0) {
novec = pcre2_get_ovector_count (match_data);
ovec = pcre2_get_ovector_pointer (match_data);
if (start) {
*start = mt + ovec[0];
}
if (end) {
*end = mt + ovec[1];
}
if (captures != NULL && novec > 1) {
struct rspamd_re_capture *elt;
g_assert (g_array_get_element_size (captures) ==
sizeof (struct rspamd_re_capture));
g_array_set_size (captures, novec);
for (i = 0; i < novec; i ++) {
elt = &g_array_index (captures, struct rspamd_re_capture, i);
elt->p = mt + ovec[i * 2];
elt->len = (mt + ovec[i * 2 + 1]) - elt->p;
}
}
ret = TRUE;
if (re->flags & RSPAMD_REGEXP_FLAG_FULL_MATCH) {
/* We also ensure that the match is full */
if (ovec[0] != 0 || (guint)ovec[1] < len) {
ret = FALSE;
}
}
}
