2021-10-31 15:25:04 +01:00
|
|
|
#include <glib-object.h>
|
|
|
|
|
2021-10-25 12:36:42 +02:00
|
|
|
#ifndef PCRE2_CODE_UNIT_WIDTH
|
|
|
|
#define PCRE2_CODE_UNIT_WIDTH 8
|
|
|
|
#include <pcre2.h>
|
|
|
|
#endif
|
|
|
|
|
2021-10-31 15:25:04 +01:00
|
|
|
#include <openmg/util/regex.h>
|
2021-10-31 14:55:39 +01:00
|
|
|
#include <openmg/util/string.h>
|
|
|
|
|
2021-10-31 15:25:04 +01:00
|
|
|
struct _MgUtilRegex {
|
|
|
|
GObject parent_instance;
|
|
|
|
};
|
|
|
|
|
|
|
|
G_DEFINE_TYPE (MgUtilRegex, mg_util_regex, G_TYPE_OBJECT)
|
2021-10-25 12:36:42 +02:00
|
|
|
|
2021-10-30 18:59:54 +02:00
|
|
|
static void
|
2021-10-31 15:25:04 +01:00
|
|
|
mg_util_regex_class_init (MgUtilRegexClass *class) {
|
|
|
|
}
|
|
|
|
static void
|
|
|
|
mg_util_regex_init (MgUtilRegex *class) {
|
|
|
|
}
|
|
|
|
|
|
|
|
static void
|
|
|
|
mg_util_regex_iterate_string_to_split (MgUtilRegex *self,
|
|
|
|
struct SplittedString *splitted_string,
|
2021-10-30 18:59:54 +02:00
|
|
|
pcre2_code *re, int *will_break, const char *subject,
|
|
|
|
size_t subject_size, size_t *start_pos, size_t *offset);
|
2021-10-25 12:36:42 +02:00
|
|
|
|
2021-10-31 15:25:04 +01:00
|
|
|
MgUtilRegex *
|
|
|
|
mg_util_regex_new () {
|
|
|
|
MgUtilRegex *self = NULL;
|
|
|
|
self = MG_UTIL_REGEX ((g_object_new (MG_TYPE_UTIL_REGEX, NULL)));
|
|
|
|
return self;
|
|
|
|
}
|
|
|
|
|
2021-10-25 12:36:42 +02:00
|
|
|
struct SplittedString *
|
2021-10-31 15:25:04 +01:00
|
|
|
mg_util_regex_split (MgUtilRegex *self,
|
|
|
|
char *re_str, size_t re_str_size, const char *subject, size_t subject_size) {
|
2021-10-25 12:36:42 +02:00
|
|
|
pcre2_code_8 *re;
|
|
|
|
size_t start_pos = 0;
|
|
|
|
size_t offset = 0;
|
|
|
|
int regex_compile_error;
|
|
|
|
PCRE2_SIZE error_offset;
|
|
|
|
struct SplittedString *splitted_string;
|
|
|
|
|
|
|
|
splitted_string = g_malloc (sizeof *splitted_string);
|
|
|
|
|
|
|
|
splitted_string->n_strings = 0;
|
|
|
|
splitted_string->substrings = NULL;
|
|
|
|
re = pcre2_compile ((PCRE2_SPTR8) re_str,
|
|
|
|
re_str_size, 0, ®ex_compile_error, &error_offset, NULL);
|
|
|
|
while (start_pos < subject_size) {
|
|
|
|
int will_break = 0;
|
2021-10-31 15:25:04 +01:00
|
|
|
mg_util_regex_iterate_string_to_split (self,
|
|
|
|
splitted_string, re, &will_break,
|
2021-10-25 12:36:42 +02:00
|
|
|
subject, subject_size, &start_pos, &offset);
|
|
|
|
if (will_break) {
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
pcre2_code_free (re);
|
|
|
|
re = NULL;
|
|
|
|
|
|
|
|
return splitted_string;
|
|
|
|
}
|
2021-10-31 15:25:04 +01:00
|
|
|
|
2021-10-25 12:36:42 +02:00
|
|
|
void
|
2021-10-31 15:25:04 +01:00
|
|
|
mg_util_regex_splitted_string_free (MgUtilRegex *self,
|
|
|
|
struct SplittedString *splitted_string) {
|
2021-10-25 12:36:42 +02:00
|
|
|
for (int i = 0; i<splitted_string->n_strings; i++) {
|
|
|
|
g_free (splitted_string->substrings[i].content);
|
|
|
|
}
|
|
|
|
|
|
|
|
g_free (splitted_string->substrings);
|
|
|
|
g_free (splitted_string);
|
|
|
|
}
|
|
|
|
|
2021-10-30 18:59:54 +02:00
|
|
|
static void
|
2021-10-31 15:25:04 +01:00
|
|
|
mg_util_regex_iterate_string_to_split (MgUtilRegex *self,
|
|
|
|
struct SplittedString *splitted_string,
|
|
|
|
pcre2_code *re, int *will_break, const char *subject,
|
2021-10-25 12:36:42 +02:00
|
|
|
size_t subject_size, size_t *start_pos, size_t *offset) {
|
|
|
|
pcre2_match_data_8 *match_data;
|
|
|
|
PCRE2_SIZE *ovector;
|
|
|
|
int rc;
|
2021-10-31 14:55:39 +01:00
|
|
|
MgUtilString *string_util = mg_util_string_new ();
|
2021-10-25 12:36:42 +02:00
|
|
|
|
|
|
|
splitted_string->n_strings++;
|
|
|
|
match_data = pcre2_match_data_create_from_pattern_8 (re, NULL);
|
|
|
|
rc = pcre2_match ( re, (PCRE2_SPTR8) subject, subject_size, *start_pos, 0, match_data,
|
|
|
|
NULL);
|
|
|
|
if (splitted_string->substrings) {
|
|
|
|
splitted_string->substrings = g_realloc (splitted_string->substrings,
|
|
|
|
(sizeof *splitted_string->substrings) * (*offset + 1));
|
|
|
|
} else {
|
|
|
|
splitted_string->substrings = g_malloc (sizeof *splitted_string->substrings);
|
|
|
|
}
|
|
|
|
if (rc < 0) {
|
|
|
|
struct String *current_substring =
|
|
|
|
&splitted_string->substrings [*offset];
|
2021-10-31 14:55:39 +01:00
|
|
|
current_substring->content = mg_util_string_alloc_string (string_util,
|
2021-10-25 12:36:42 +02:00
|
|
|
subject_size - *start_pos);
|
2021-10-31 14:55:39 +01:00
|
|
|
mg_util_string_copy_substring (string_util, subject,
|
|
|
|
current_substring->content, subject_size,
|
|
|
|
*start_pos, subject_size - *start_pos);
|
2021-10-25 12:36:42 +02:00
|
|
|
current_substring->size = subject_size - *start_pos;
|
|
|
|
|
|
|
|
*will_break = 1;
|
|
|
|
goto cleanup_iterate_string_to_split;
|
|
|
|
}
|
|
|
|
ovector = pcre2_get_ovector_pointer_8(match_data);
|
2021-10-31 14:55:39 +01:00
|
|
|
splitted_string->substrings[*offset].content =
|
|
|
|
mg_util_string_alloc_string (string_util, ovector[0] - *start_pos);
|
|
|
|
mg_util_string_copy_substring (string_util,
|
|
|
|
subject, splitted_string->substrings[*offset].content,
|
|
|
|
subject_size, *start_pos,
|
2021-10-25 12:36:42 +02:00
|
|
|
ovector[0] - *start_pos);
|
|
|
|
splitted_string->substrings[*offset].size =
|
|
|
|
ovector[0] - *start_pos;
|
|
|
|
|
|
|
|
*start_pos = ovector[1];
|
|
|
|
|
|
|
|
*offset += 1;
|
|
|
|
|
|
|
|
cleanup_iterate_string_to_split:
|
2021-11-22 01:02:00 +01:00
|
|
|
g_clear_object (&string_util);
|
2021-10-25 12:36:42 +02:00
|
|
|
pcre2_match_data_free (match_data);
|
|
|
|
}
|
|
|
|
|
2021-10-30 04:02:10 +02:00
|
|
|
char *
|
2021-10-31 15:25:04 +01:00
|
|
|
mg_util_regex_match_1 (MgUtilRegex *self,
|
2022-01-16 01:32:46 +01:00
|
|
|
const char *re_str, const char *subject) {
|
2021-10-30 04:02:10 +02:00
|
|
|
pcre2_code *re;
|
|
|
|
pcre2_match_data *match_data;
|
|
|
|
|
|
|
|
char *return_value;
|
|
|
|
int regex_compile_error;
|
|
|
|
int rc;
|
|
|
|
size_t len_match = 0;
|
|
|
|
|
|
|
|
return_value = NULL;
|
|
|
|
PCRE2_SIZE error_offset;
|
|
|
|
re = pcre2_compile ((PCRE2_SPTR8) re_str, strlen (re_str), 0,
|
|
|
|
®ex_compile_error, &error_offset, NULL);
|
|
|
|
match_data = pcre2_match_data_create_from_pattern (re, NULL);
|
|
|
|
if (!subject) {
|
|
|
|
goto cleanup_match;
|
|
|
|
}
|
|
|
|
rc = pcre2_match (re, (PCRE2_SPTR8) subject, strlen (subject),
|
|
|
|
0, 0, match_data, NULL);
|
|
|
|
if (rc < 0 ) {
|
|
|
|
goto cleanup_match;
|
|
|
|
}
|
|
|
|
pcre2_substring_get_bynumber (match_data, 1, (PCRE2_UCHAR8**)
|
|
|
|
&return_value, &len_match);
|
|
|
|
cleanup_match:
|
|
|
|
pcre2_match_data_free (match_data);
|
|
|
|
pcre2_code_free (re);
|
|
|
|
return return_value;
|
|
|
|
}
|