glib/regex.rs
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759
// Take a look at the license at the top of the repository in the LICENSE file.
// rustdoc-stripper-ignore-next
//! This module is inefficient and should not be used by Rust programs except for
//! compatibility with GLib.Regex based APIs.
use crate::{
ffi, translate::*, GStr, GStringPtr, MatchInfo, PtrSlice, Regex, RegexCompileFlags,
RegexMatchFlags,
};
use std::{mem, ptr};
impl Regex {
/// Retrieves the number of the subexpression named @name.
/// ## `name`
/// name of the subexpression
///
/// # Returns
///
/// The number of the subexpression or -1 if @name
/// does not exists
#[doc(alias = "g_regex_get_string_number")]
#[doc(alias = "get_string_number")]
pub fn string_number(&self, name: impl IntoGStr) -> i32 {
name.run_with_gstr(|name| unsafe {
ffi::g_regex_get_string_number(self.to_glib_none().0, name.to_glib_none().0)
})
}
/// Escapes the nul characters in @string to "\x00". It can be used
/// to compile a regex with embedded nul characters.
///
/// For completeness, @length can be -1 for a nul-terminated string.
/// In this case the output string will be of course equal to @string.
/// ## `string`
/// the string to escape
/// ## `length`
/// the length of @string
///
/// # Returns
///
/// a newly-allocated escaped string
#[doc(alias = "g_regex_escape_nul")]
pub fn escape_nul(string: impl IntoGStr) -> crate::GString {
unsafe {
string.run_with_gstr(|string| {
from_glib_full(ffi::g_regex_escape_nul(
string.to_glib_none().0,
string.len() as _,
))
})
}
}
/// Escapes the special characters used for regular expressions
/// in @string, for instance "a.b*c" becomes "a\.b\*c". This
/// function is useful to dynamically generate regular expressions.
///
/// @string can contain nul characters that are replaced with "\0",
/// in this case remember to specify the correct length of @string
/// in @length.
/// ## `string`
/// the string to escape
/// ## `length`
/// the length of @string, in bytes, or -1 if @string is nul-terminated
///
/// # Returns
///
/// a newly-allocated escaped string
#[doc(alias = "g_regex_escape_string")]
pub fn escape_string(string: impl IntoGStr) -> crate::GString {
unsafe {
string.run_with_gstr(|string| {
from_glib_full(ffi::g_regex_escape_string(
string.to_glib_none().0,
string.len() as _,
))
})
}
}
/// Checks whether @replacement is a valid replacement string
/// (see g_regex_replace()), i.e. that all escape sequences in
/// it are valid.
///
/// If @has_references is not [`None`] then @replacement is checked
/// for pattern references. For instance, replacement text 'foo\n'
/// does not contain references and may be evaluated without information
/// about actual match, but '\0\1' (whole match followed by first
/// subpattern) requires valid #GMatchInfo object.
/// ## `replacement`
/// the replacement string
///
/// # Returns
///
/// whether @replacement is a valid replacement string
///
/// ## `has_references`
/// location to store information about
/// references in @replacement or [`None`]
#[doc(alias = "g_regex_check_replacement")]
pub fn check_replacement(replacement: impl IntoGStr) -> Result<bool, crate::Error> {
replacement.run_with_gstr(|replacement| unsafe {
let mut has_references = mem::MaybeUninit::uninit();
let mut error = ptr::null_mut();
let is_ok = ffi::g_regex_check_replacement(
replacement.to_glib_none().0,
has_references.as_mut_ptr(),
&mut error,
);
debug_assert_eq!(is_ok == crate::ffi::GFALSE, !error.is_null());
if error.is_null() {
Ok(from_glib(has_references.assume_init()))
} else {
Err(from_glib_full(error))
}
})
}
/// Scans for a match in @string for @pattern.
///
/// This function is equivalent to g_regex_match() but it does not
/// require to compile the pattern with g_regex_new(), avoiding some
/// lines of code when you need just to do a match without extracting
/// substrings, capture counts, and so on.
///
/// If this function is to be called on the same @pattern more than
/// once, it's more efficient to compile the pattern once with
/// g_regex_new() and then use g_regex_match().
/// ## `pattern`
/// the regular expression
/// ## `string`
/// the string to scan for matches
/// ## `compile_options`
/// compile options for the regular expression, or 0
/// ## `match_options`
/// match options, or 0
///
/// # Returns
///
/// [`true`] if the string matched, [`false`] otherwise
#[doc(alias = "g_regex_match_simple")]
pub fn match_simple(
pattern: impl IntoGStr,
string: impl IntoGStr,
compile_options: RegexCompileFlags,
match_options: RegexMatchFlags,
) -> bool {
pattern.run_with_gstr(|pattern| {
string.run_with_gstr(|string| unsafe {
from_glib(ffi::g_regex_match_simple(
pattern.to_glib_none().0,
string.to_glib_none().0,
compile_options.into_glib(),
match_options.into_glib(),
))
})
})
}
/// Replaces all occurrences of the pattern in @self with the
/// replacement text. Backreferences of the form `\number` or
/// `\g<number>` in the replacement text are interpolated by the
/// number-th captured subexpression of the match, `\g<name>` refers
/// to the captured subexpression with the given name. `\0` refers
/// to the complete match, but `\0` followed by a number is the octal
/// representation of a character. To include a literal `\` in the
/// replacement, write `\\\\`.
///
/// There are also escapes that changes the case of the following text:
///
/// - \l: Convert to lower case the next character
/// - \u: Convert to upper case the next character
/// - \L: Convert to lower case till \E
/// - \U: Convert to upper case till \E
/// - \E: End case modification
///
/// If you do not need to use backreferences use g_regex_replace_literal().
///
/// The @replacement string must be UTF-8 encoded even if [`RegexCompileFlags::RAW`][crate::RegexCompileFlags::RAW] was
/// passed to g_regex_new(). If you want to use not UTF-8 encoded strings
/// you can use g_regex_replace_literal().
///
/// Setting @start_position differs from just passing over a shortened
/// string and setting [`RegexMatchFlags::NOTBOL`][crate::RegexMatchFlags::NOTBOL] in the case of a pattern that
/// begins with any kind of lookbehind assertion, such as "\b".
/// ## `string`
/// the string to perform matches against
/// ## `start_position`
/// starting index of the string to match, in bytes
/// ## `replacement`
/// text to replace each match with
/// ## `match_options`
/// options for the match
///
/// # Returns
///
/// a newly allocated string containing the replacements
#[doc(alias = "g_regex_replace")]
pub fn replace(
&self,
string: impl IntoGStr,
start_position: i32,
replacement: impl IntoGStr,
match_options: RegexMatchFlags,
) -> Result<crate::GString, crate::Error> {
unsafe {
string.run_with_gstr(|string| {
replacement.run_with_gstr(|replacement| {
let mut error = ptr::null_mut();
let ret = ffi::g_regex_replace(
self.to_glib_none().0,
string.as_ptr() as *const _,
string.len() as _,
start_position,
replacement.to_glib_none().0,
match_options.into_glib(),
&mut error,
);
if error.is_null() {
Ok(from_glib_full(ret))
} else {
Err(from_glib_full(error))
}
})
})
}
}
/// Using the standard algorithm for regular expression matching only
/// the longest match in the string is retrieved. This function uses
/// a different algorithm so it can retrieve all the possible matches.
/// For more documentation see g_regex_match_all_full().
///
/// A #GMatchInfo structure, used to get information on the match, is
/// stored in @match_info if not [`None`]. Note that if @match_info is
/// not [`None`] then it is created even if the function returns [`false`],
/// i.e. you must free it regardless if regular expression actually
/// matched.
///
/// @string is not copied and is used in #GMatchInfo internally. If
/// you use any #GMatchInfo method (except g_match_info_free()) after
/// freeing or modifying @string then the behaviour is undefined.
/// ## `string`
/// the string to scan for matches
/// ## `match_options`
/// match options
///
/// # Returns
///
/// [`true`] is the string matched, [`false`] otherwise
///
/// ## `match_info`
/// pointer to location where to store
/// the #GMatchInfo, or [`None`] if you do not need it
#[doc(alias = "g_regex_match_all")]
pub fn match_all<'input>(
&self,
string: &'input GStr,
match_options: RegexMatchFlags,
) -> Option<MatchInfo<'input>> {
self.match_all_full(string, 0, match_options).ok()
}
/// Using the standard algorithm for regular expression matching only
/// the longest match in the @string is retrieved, it is not possible
/// to obtain all the available matches. For instance matching
/// `"<a> <b> <c>"` against the pattern `"<.*>"`
/// you get `"<a> <b> <c>"`.
///
/// This function uses a different algorithm (called DFA, i.e. deterministic
/// finite automaton), so it can retrieve all the possible matches, all
/// starting at the same point in the string. For instance matching
/// `"<a> <b> <c>"` against the pattern `"<.*>"`
/// you would obtain three matches: `"<a> <b> <c>"`,
/// `"<a> <b>"` and `"<a>"`.
///
/// The number of matched strings is retrieved using
/// g_match_info_get_match_count(). To obtain the matched strings and
/// their position you can use, respectively, g_match_info_fetch() and
/// g_match_info_fetch_pos(). Note that the strings are returned in
/// reverse order of length; that is, the longest matching string is
/// given first.
///
/// Note that the DFA algorithm is slower than the standard one and it
/// is not able to capture substrings, so backreferences do not work.
///
/// Setting @start_position differs from just passing over a shortened
/// string and setting [`RegexMatchFlags::NOTBOL`][crate::RegexMatchFlags::NOTBOL] in the case of a pattern
/// that begins with any kind of lookbehind assertion, such as "\b".
///
/// Unless [`RegexCompileFlags::RAW`][crate::RegexCompileFlags::RAW] is specified in the options, @string must be valid UTF-8.
///
/// A #GMatchInfo structure, used to get information on the match, is
/// stored in @match_info if not [`None`]. Note that if @match_info is
/// not [`None`] then it is created even if the function returns [`false`],
/// i.e. you must free it regardless if regular expression actually
/// matched.
///
/// @string is not copied and is used in #GMatchInfo internally. If
/// you use any #GMatchInfo method (except g_match_info_free()) after
/// freeing or modifying @string then the behaviour is undefined.
/// ## `string`
/// the string to scan for matches
/// ## `start_position`
/// starting index of the string to match, in bytes
/// ## `match_options`
/// match options
///
/// # Returns
///
/// [`true`] is the string matched, [`false`] otherwise
///
/// ## `match_info`
/// pointer to location where to store
/// the #GMatchInfo, or [`None`] if you do not need it
#[doc(alias = "g_regex_match_all_full")]
pub fn match_all_full<'input>(
&self,
string: &'input GStr,
start_position: i32,
match_options: RegexMatchFlags,
) -> Result<MatchInfo<'input>, crate::Error> {
unsafe {
let mut match_info = ptr::null_mut();
let mut error = ptr::null_mut();
let is_ok = ffi::g_regex_match_all_full(
self.to_glib_none().0,
string.to_glib_none().0,
string.len() as _,
start_position,
match_options.into_glib(),
&mut match_info,
&mut error,
);
debug_assert_eq!(is_ok == crate::ffi::GFALSE, !error.is_null());
if error.is_null() {
Ok(from_glib_full(match_info))
} else {
Err(from_glib_full(error))
}
}
}
/// Scans for a match in @string for the pattern in @self.
/// The @match_options are combined with the match options specified
/// when the @self structure was created, letting you have more
/// flexibility in reusing #GRegex structures.
///
/// Unless [`RegexCompileFlags::RAW`][crate::RegexCompileFlags::RAW] is specified in the options, @string must be valid UTF-8.
///
/// A #GMatchInfo structure, used to get information on the match,
/// is stored in @match_info if not [`None`]. Note that if @match_info
/// is not [`None`] then it is created even if the function returns [`false`],
/// i.e. you must free it regardless if regular expression actually matched.
///
/// To retrieve all the non-overlapping matches of the pattern in
/// string you can use g_match_info_next().
///
///
///
/// **⚠️ The following code is in C ⚠️**
///
/// ```C
/// static void
/// print_uppercase_words (const gchar *string)
/// {
/// // Print all uppercase-only words.
/// GRegex *regex;
/// GMatchInfo *match_info;
///
/// regex = g_regex_new ("[A-Z]+", G_REGEX_DEFAULT, G_REGEX_MATCH_DEFAULT, NULL);
/// g_regex_match (regex, string, 0, &match_info);
/// while (g_match_info_matches (match_info))
/// {
/// gchar *word = g_match_info_fetch (match_info, 0);
/// g_print ("Found: %s\n", word);
/// g_free (word);
/// g_match_info_next (match_info, NULL);
/// }
/// g_match_info_free (match_info);
/// g_regex_unref (regex);
/// }
/// ```
///
/// @string is not copied and is used in #GMatchInfo internally. If
/// you use any #GMatchInfo method (except g_match_info_free()) after
/// freeing or modifying @string then the behaviour is undefined.
/// ## `string`
/// the string to scan for matches
/// ## `match_options`
/// match options
///
/// # Returns
///
/// [`true`] is the string matched, [`false`] otherwise
///
/// ## `match_info`
/// pointer to location where to store
/// the #GMatchInfo, or [`None`] if you do not need it
#[doc(alias = "g_regex_match")]
pub fn match_<'input>(
&self,
string: &'input GStr,
match_options: RegexMatchFlags,
) -> Option<MatchInfo<'input>> {
self.match_full(string, 0, match_options).ok()
}
/// Scans for a match in @string for the pattern in @self.
/// The @match_options are combined with the match options specified
/// when the @self structure was created, letting you have more
/// flexibility in reusing #GRegex structures.
///
/// Setting @start_position differs from just passing over a shortened
/// string and setting [`RegexMatchFlags::NOTBOL`][crate::RegexMatchFlags::NOTBOL] in the case of a pattern
/// that begins with any kind of lookbehind assertion, such as "\b".
///
/// Unless [`RegexCompileFlags::RAW`][crate::RegexCompileFlags::RAW] is specified in the options, @string must be valid UTF-8.
///
/// A #GMatchInfo structure, used to get information on the match, is
/// stored in @match_info if not [`None`]. Note that if @match_info is
/// not [`None`] then it is created even if the function returns [`false`],
/// i.e. you must free it regardless if regular expression actually
/// matched.
///
/// @string is not copied and is used in #GMatchInfo internally. If
/// you use any #GMatchInfo method (except g_match_info_free()) after
/// freeing or modifying @string then the behaviour is undefined.
///
/// To retrieve all the non-overlapping matches of the pattern in
/// string you can use g_match_info_next().
///
///
///
/// **⚠️ The following code is in C ⚠️**
///
/// ```C
/// static void
/// print_uppercase_words (const gchar *string)
/// {
/// // Print all uppercase-only words.
/// GRegex *regex;
/// GMatchInfo *match_info;
/// GError *error = NULL;
///
/// regex = g_regex_new ("[A-Z]+", G_REGEX_DEFAULT, G_REGEX_MATCH_DEFAULT, NULL);
/// g_regex_match_full (regex, string, -1, 0, 0, &match_info, &error);
/// while (g_match_info_matches (match_info))
/// {
/// gchar *word = g_match_info_fetch (match_info, 0);
/// g_print ("Found: %s\n", word);
/// g_free (word);
/// g_match_info_next (match_info, &error);
/// }
/// g_match_info_free (match_info);
/// g_regex_unref (regex);
/// if (error != NULL)
/// {
/// g_printerr ("Error while matching: %s\n", error->message);
/// g_error_free (error);
/// }
/// }
/// ```
/// ## `string`
/// the string to scan for matches
/// ## `start_position`
/// starting index of the string to match, in bytes
/// ## `match_options`
/// match options
///
/// # Returns
///
/// [`true`] is the string matched, [`false`] otherwise
///
/// ## `match_info`
/// pointer to location where to store
/// the #GMatchInfo, or [`None`] if you do not need it
#[doc(alias = "g_regex_match_full")]
pub fn match_full<'input>(
&self,
string: &'input GStr,
start_position: i32,
match_options: RegexMatchFlags,
) -> Result<MatchInfo<'input>, crate::Error> {
unsafe {
let mut match_info = ptr::null_mut();
let mut error = ptr::null_mut();
let is_ok = ffi::g_regex_match_full(
self.to_glib_none().0,
string.to_glib_none().0,
string.len() as _,
start_position,
match_options.into_glib(),
&mut match_info,
&mut error,
);
debug_assert_eq!(is_ok == crate::ffi::GFALSE, !error.is_null());
if error.is_null() {
Ok(from_glib_full(match_info))
} else {
Err(from_glib_full(error))
}
}
}
/// Replaces all occurrences of the pattern in @self with the
/// replacement text. @replacement is replaced literally, to
/// include backreferences use g_regex_replace().
///
/// Setting @start_position differs from just passing over a
/// shortened string and setting [`RegexMatchFlags::NOTBOL`][crate::RegexMatchFlags::NOTBOL] in the
/// case of a pattern that begins with any kind of lookbehind
/// assertion, such as "\b".
/// ## `string`
/// the string to perform matches against
/// ## `start_position`
/// starting index of the string to match, in bytes
/// ## `replacement`
/// text to replace each match with
/// ## `match_options`
/// options for the match
///
/// # Returns
///
/// a newly allocated string containing the replacements
#[doc(alias = "g_regex_replace_literal")]
pub fn replace_literal(
&self,
string: impl IntoGStr,
start_position: i32,
replacement: impl IntoGStr,
match_options: RegexMatchFlags,
) -> Result<crate::GString, crate::Error> {
unsafe {
string.run_with_gstr(|string| {
replacement.run_with_gstr(|replacement| {
let mut error = ptr::null_mut();
let ret = ffi::g_regex_replace_literal(
self.to_glib_none().0,
string.to_glib_none().0,
string.len() as _,
start_position,
replacement.to_glib_none().0,
match_options.into_glib(),
&mut error,
);
if error.is_null() {
Ok(from_glib_full(ret))
} else {
Err(from_glib_full(error))
}
})
})
}
}
/// Breaks the string on the pattern, and returns an array of the tokens.
/// If the pattern contains capturing parentheses, then the text for each
/// of the substrings will also be returned. If the pattern does not match
/// anywhere in the string, then the whole string is returned as the first
/// token.
///
/// As a special case, the result of splitting the empty string "" is an
/// empty vector, not a vector containing a single string. The reason for
/// this special case is that being able to represent an empty vector is
/// typically more useful than consistent handling of empty elements. If
/// you do need to represent empty elements, you'll need to check for the
/// empty string before calling this function.
///
/// A pattern that can match empty strings splits @string into separate
/// characters wherever it matches the empty string between characters.
/// For example splitting "ab c" using as a separator "\s*", you will get
/// "a", "b" and "c".
/// ## `string`
/// the string to split with the pattern
/// ## `match_options`
/// match time option flags
///
/// # Returns
///
/// a [`None`]-terminated gchar ** array. Free
/// it using g_strfreev()
#[doc(alias = "g_regex_split")]
pub fn split(
&self,
string: impl IntoGStr,
match_options: RegexMatchFlags,
) -> PtrSlice<GStringPtr> {
self.split_full(string, 0, match_options, 0)
.unwrap_or_default()
}
/// Breaks the string on the pattern, and returns an array of the tokens.
/// If the pattern contains capturing parentheses, then the text for each
/// of the substrings will also be returned. If the pattern does not match
/// anywhere in the string, then the whole string is returned as the first
/// token.
///
/// As a special case, the result of splitting the empty string "" is an
/// empty vector, not a vector containing a single string. The reason for
/// this special case is that being able to represent an empty vector is
/// typically more useful than consistent handling of empty elements. If
/// you do need to represent empty elements, you'll need to check for the
/// empty string before calling this function.
///
/// A pattern that can match empty strings splits @string into separate
/// characters wherever it matches the empty string between characters.
/// For example splitting "ab c" using as a separator "\s*", you will get
/// "a", "b" and "c".
///
/// Setting @start_position differs from just passing over a shortened
/// string and setting [`RegexMatchFlags::NOTBOL`][crate::RegexMatchFlags::NOTBOL] in the case of a pattern
/// that begins with any kind of lookbehind assertion, such as "\b".
/// ## `string`
/// the string to split with the pattern
/// ## `start_position`
/// starting index of the string to match, in bytes
/// ## `match_options`
/// match time option flags
/// ## `max_tokens`
/// the maximum number of tokens to split @string into.
/// If this is less than 1, the string is split completely
///
/// # Returns
///
/// a [`None`]-terminated gchar ** array. Free
/// it using g_strfreev()
#[doc(alias = "g_regex_split_full")]
pub fn split_full(
&self,
string: impl IntoGStr,
start_position: i32,
match_options: RegexMatchFlags,
max_tokens: i32,
) -> Result<PtrSlice<GStringPtr>, crate::Error> {
unsafe {
let mut error = ptr::null_mut();
string.run_with_gstr(|string| {
let ret = ffi::g_regex_split_full(
self.to_glib_none().0,
string.to_glib_none().0,
string.len() as _,
start_position,
match_options.into_glib(),
max_tokens,
&mut error,
);
if error.is_null() {
Ok(FromGlibPtrContainer::from_glib_full(ret))
} else {
Err(from_glib_full(error))
}
})
}
}
/// Breaks the string on the pattern, and returns an array of
/// the tokens. If the pattern contains capturing parentheses,
/// then the text for each of the substrings will also be returned.
/// If the pattern does not match anywhere in the string, then the
/// whole string is returned as the first token.
///
/// This function is equivalent to g_regex_split() but it does
/// not require to compile the pattern with g_regex_new(), avoiding
/// some lines of code when you need just to do a split without
/// extracting substrings, capture counts, and so on.
///
/// If this function is to be called on the same @pattern more than
/// once, it's more efficient to compile the pattern once with
/// g_regex_new() and then use g_regex_split().
///
/// As a special case, the result of splitting the empty string ""
/// is an empty vector, not a vector containing a single string.
/// The reason for this special case is that being able to represent
/// an empty vector is typically more useful than consistent handling
/// of empty elements. If you do need to represent empty elements,
/// you'll need to check for the empty string before calling this
/// function.
///
/// A pattern that can match empty strings splits @string into
/// separate characters wherever it matches the empty string between
/// characters. For example splitting "ab c" using as a separator
/// "\s*", you will get "a", "b" and "c".
/// ## `pattern`
/// the regular expression
/// ## `string`
/// the string to scan for matches
/// ## `compile_options`
/// compile options for the regular expression, or 0
/// ## `match_options`
/// match options, or 0
///
/// # Returns
///
/// a [`None`]-terminated array of strings. Free
/// it using g_strfreev()
#[doc(alias = "g_regex_split_simple")]
pub fn split_simple(
pattern: impl IntoGStr,
string: impl IntoGStr,
compile_options: RegexCompileFlags,
match_options: RegexMatchFlags,
) -> PtrSlice<GStringPtr> {
pattern.run_with_gstr(|pattern| {
string.run_with_gstr(|string| unsafe {
FromGlibPtrContainer::from_glib_full(ffi::g_regex_split_simple(
pattern.to_glib_none().0,
string.to_glib_none().0,
compile_options.into_glib(),
match_options.into_glib(),
))
})
})
}
}
#[cfg(test)]
mod tests {
use super::*;
use crate::RegexCompileFlags;
#[test]
fn test_replace_literal() {
let regex = Regex::new(
"s[ai]mple",
RegexCompileFlags::OPTIMIZE,
RegexMatchFlags::DEFAULT,
)
.expect("Regex new")
.expect("Null regex");
let quote = "This is a simple sample.";
let result = regex
.replace_literal(quote, 0, "XXX", RegexMatchFlags::DEFAULT)
.expect("regex replace");
assert_eq!(result, "This is a XXX XXX.");
}
#[test]
fn test_split() {
let regex = Regex::new(
"s[ai]mple",
RegexCompileFlags::OPTIMIZE,
RegexMatchFlags::DEFAULT,
)
.expect("Regex new")
.expect("Null regex");
let quote = "This is a simple sample.";
let result = regex.split(quote, RegexMatchFlags::DEFAULT);
assert_eq!(result.len(), 3);
assert_eq!(result[0], "This is a ");
assert_eq!(result[1], " ");
assert_eq!(result[2], ".");
}
}