int
cre2_easy_match (const char * pattern, int pattern_len,
const char *text, int text_len,
cre2_string_t *match, int nmatch)
{
cre2_regexp_t * rex;
cre2_options_t * opt;
int retval; // 0 for no match, 1 for successful
// matching, 2 for wrong regexp
opt = cre2_opt_new();
if (!opt) return 2;
cre2_opt_set_log_errors(opt, 0);
rex = cre2_new(pattern, pattern_len, opt);
if (!rex) {
cre2_opt_delete(opt);
return 2;
}
{
if (!cre2_error_code(rex)) {
retval = cre2_match(rex, text, text_len, 0, text_len, CRE2_UNANCHORED, match, nmatch);
} else {
retval = 2;
}
}
cre2_delete(rex);
cre2_opt_delete(opt);
return retval;
}
u3_noun
u3qe_rexp(u3_noun lub, u3_noun rad)
{
c3_y* lub_y = u3r_tape(lub);
c3_y* rad_y = u3r_tape(rad);
u3k(lub);
int lub_l = u3kb_lent(lub);
if (lub_l != strlen((char *)lub_y)) {
free(lub_y);
free(rad_y);
return u3_nul;
}
char* rec = (char*)lub_y;
char* end;
while(*rec != 0) {
if(*rec > 127) {
free(lub_y);
free(rad_y);
return u3_nul;
}
else if(*rec == '\\') {
rec++;
switch (*rec) {
case 'P':
case 'p':
free(lub_y);
free(rad_y);
return u3_nul;
case 'Q':
end = strstr(rec, "\\E");
if(end == NULL) rec += strlen(rec) - 1;
else rec = end;
}
}
else if(*rec == '(') {
rec++;
if(*rec == '?') {
rec++;
if(*rec != ':') {
free(lub_y);
free(rad_y);
return u3_nul;
}
rec++;
}
}
else
rec++;
}
cre2_regexp_t * rex;
cre2_options_t * opt;
opt = cre2_opt_new();
if (opt) {
cre2_opt_set_log_errors(opt, 0);
cre2_opt_set_encoding(opt, CRE2_UTF8);
cre2_opt_set_perl_classes(opt, 1);
cre2_opt_set_one_line(opt, 1);
cre2_opt_set_longest_match(opt, 1);
rex = cre2_new((const char *)lub_y, strlen((char *)lub_y), opt);
if (rex) {
if (!cre2_error_code(rex)) {
int text_len = strlen((char *)rad_y);
int captures = cre2_num_capturing_groups(rex);
cre2_string_t matches[captures+1];
int match = cre2_match(rex, (const char*)rad_y, text_len, 0, text_len, CRE2_UNANCHORED, matches, captures+1);
if (!match) {
// No matches
cre2_opt_delete(opt);
cre2_delete(rex);
free(lub_y);
free(rad_y);
return u3i_cell(u3_nul, u3_nul);
}
u3_noun map = u3_nul;
int i;
for (i = 0; i < captures+1; i++) {
char * buf = malloc(matches[i].length + 1);
memcpy(buf, matches[i].data, matches[i].length);
buf[matches[i].length] = 0;
map = u3kdb_put(map, i, u3i_tape(buf));
free(buf);
}
cre2_opt_delete(opt);
cre2_delete(rex);
free(lub_y);
free(rad_y);
return u3i_cell(u3_nul, u3i_cell(u3_nul, map));
}
else {
// Compiling the regular expression failed
cre2_opt_delete(opt);
cre2_delete(rex);
free(lub_y);
free(rad_y);
return u3_nul;
}
cre2_delete(rex);
}
cre2_opt_delete(opt);
}
free(lub_y);
free(rad_y);
u3m_bail(c3__exit);
return u3_nul;
}
int
main (void)
{
cre2_regexp_t * rex;
cre2_options_t * opt;
const char * pattern;
/* ------------------------------------------------------------------ */
/* single match */
pattern = "ciao";
opt = cre2_opt_new();
cre2_opt_set_posix_syntax(opt, 1);
rex = cre2_new(pattern, strlen(pattern), opt);
{
if (cre2_error_code(rex))
goto error;
cre2_string_t match;
int nmatch = 1;
int e;
const char * text = "ciao";
int text_len = strlen(text);
e = cre2_match(rex, text, text_len, 0, text_len, CRE2_UNANCHORED, &match, nmatch);
if (1 != e)
goto error;
PRINTF("match: retval=%d, ", e);
FWRITE(match.data, match.length, 1);
PRINTF("\n");
}
cre2_delete(rex);
cre2_opt_delete(opt);
/* ------------------------------------------------------------------ */
/* two groups */
pattern = "(ciao) (hello)";
opt = cre2_opt_new();
rex = cre2_new(pattern, strlen(pattern), opt);
{
if (cre2_error_code(rex))
goto error;
int nmatch = 3;
cre2_string_t strings[nmatch];
cre2_range_t ranges[nmatch];
int e;
const char * text = "ciao hello";
int text_len = strlen(text);
e = cre2_match(rex, text, text_len, 0, text_len, CRE2_UNANCHORED, strings, nmatch);
if (1 != e)
goto error;
cre2_strings_to_ranges(text, ranges, strings, nmatch);
PRINTF("full match: ");
FWRITE(text+ranges[0].start, ranges[0].past-ranges[0].start, 1);
PRINTF("\n");
PRINTF("first group: ");
FWRITE(text+ranges[1].start, ranges[1].past-ranges[1].start, 1);
PRINTF("\n");
PRINTF("second group: ");
FWRITE(text+ranges[2].start, ranges[2].past-ranges[2].start, 1);
PRINTF("\n");
}
cre2_delete(rex);
cre2_opt_delete(opt);
/* ------------------------------------------------------------------ */
/* test literal option */
pattern = "(ciao) (hello)";
opt = cre2_opt_new();
cre2_opt_set_literal(opt, 1);
rex = cre2_new(pattern, strlen(pattern), opt);
{
if (cre2_error_code(rex))
goto error;
int nmatch = 0;
int e;
const char * text = "(ciao) (hello)";
int text_len = strlen(text);
e = cre2_match(rex, text, text_len, 0, text_len, CRE2_UNANCHORED, NULL, nmatch);
if (0 == e)
goto error;
}
cre2_delete(rex);
cre2_opt_delete(opt);
/* ------------------------------------------------------------------ */
/* test named groups */
pattern = "from (?P<S>.*) to (?P<D>.*)";
opt = cre2_opt_new();
rex = cre2_new(pattern, strlen(pattern), opt);
{
if (cre2_error_code(rex))
goto error;
int nmatch = cre2_num_capturing_groups(rex) + 1;
cre2_string_t strings[nmatch];
int e, SIndex, DIndex;
const char * text = "from Montreal, Canada to Lausanne, Switzerland";
int text_len = strlen(text);
e = cre2_match(rex, text, text_len, 0, text_len, CRE2_UNANCHORED, strings, nmatch);
if (0 == e)
goto error;
SIndex = cre2_find_named_capturing_groups(rex, "S");
if (0 != strncmp("Montreal, Canada", strings[SIndex].data, strings[SIndex].length))
goto error;
DIndex = cre2_find_named_capturing_groups(rex, "D");
if (0 != strncmp("Lausanne, Switzerland", strings[DIndex].data, strings[DIndex].length))
goto error;
}
cre2_delete(rex);
cre2_opt_delete(opt);
/* ------------------------------------------------------------------ */
exit(EXIT_SUCCESS);
error:
exit(EXIT_FAILURE);
}
u2_noun // produce
j2_mbc(Pt5, repg)(u2_wire wir_r,
u2_noun lub,
u2_noun rad,
u2_noun rep) // retain
{
c3_y* lub_y = u2_cr_tape(lub);
c3_y* rad_y = u2_cr_tape(rad);
c3_y* rep_y = u2_cr_tape(rep);
char* rec = (char*)lub_y;
char* end;
while(*rec != 0) {
if(*rec == '\\') {
rec++;
switch (*rec) {
case 'P':
case 'p':
free(lub_y);
free(rad_y);
return u2_nul;
case 'Q':
end = strstr(rec, "\\E");
if(end == NULL) rec += strlen(rec) - 1;
else rec = end;
}
rec++;
}
else if(*rec == '(') {
rec++;
if(*rec == '?') {
rec++;
if(*rec != ':') {
free(lub_y);
free(rad_y);
return u2_nul;
}
rec++;
}
}
else
rec++;
}
cre2_regexp_t * rex;
cre2_options_t * opt;
opt = cre2_opt_new();
if (opt) {
cre2_opt_set_log_errors(opt, 0);
cre2_opt_set_encoding(opt, CRE2_Latin1);
cre2_opt_set_perl_classes(opt, 1);
cre2_opt_set_one_line(opt, 1);
cre2_opt_set_longest_match(opt, 1);
rex = cre2_new((const char *)lub_y, strlen((char *)lub_y), opt);
if (rex) {
if (!cre2_error_code(rex)) {
int text_len = strlen((char *)rad_y);
cre2_string_t matches[1];
int ic = 0;
u2_noun ret = u2_nul;
while (ic <= text_len) {
int match = cre2_match(rex, (const char*)rad_y, text_len, ic, text_len, CRE2_ANCHOR_START, matches, 1);
if (!match) {
if(rad_y[ic])
ret = u2_cn_cell((u2_atom)rad_y[ic], ret);
ic++;
}
else {
int mlen = matches[0].length;
if (mlen == 0) {
ret = u2_ckb_weld(u2_ckb_flop(u2_ci_tape((char *) rad_y+ic)), u2_ckb_flop(u2_ci_tape((char *)rep_y)));
ic = text_len + 1;
}
else {
ret = u2_ckb_weld(u2_ckb_flop(u2_ci_tape((char *)rep_y)), ret);
ic += mlen;
}
}
}
cre2_opt_delete(opt);
cre2_delete(rex);
free(lub_y);
free(rad_y);
free(rep_y);
return u2_cn_cell(u2_nul, u2_ckb_flop(ret));
}
else {
// Compiling the regular expression failed
cre2_opt_delete(opt);
cre2_delete(rex);
free(lub_y);
free(rad_y);
return u2_nul;
}
cre2_opt_delete(opt);
cre2_delete(rex);
}
else {
// rex Allocation Error
cre2_opt_delete(opt);
free(lub_y);
free(rad_y);
u2_bl_bail(wir_r, c3__exit);
}
cre2_opt_delete(opt);
}
// opt Allocation Error
free(lub_y);
free(rad_y);
u2_bl_bail(wir_r, c3__exit);
return u2_nul;
}