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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193
use std::error; use std::fmt; use std::iter; use std::ops; use std::ptr; use std::str; use std::vec; use bstr::BStr; use utf8::{self, Utf8Error}; /// Concatenate the elements given by the iterator together into a single /// `BString`. /// /// The elements may be any type that can be cheaply converted into an `&[u8]`. /// This includes, but is not limited to, `&str`, `&BStr` and `&[u8]` itself. /// /// # Examples /// /// Basic usage: /// /// ``` /// use bstr; /// /// let s = bstr::concat(&["foo", "bar", "baz"]); /// assert_eq!(s, "foobarbaz"); /// ``` pub fn concat<T, I>( elements: I, ) -> BString where T: AsRef<[u8]>, I: IntoIterator<Item=T> { let mut dest = BString::new(); for element in elements { dest.push(element); } dest } /// Join the elements given by the iterator with the given separator into a /// single `BString`. /// /// Both the separator and the elements may be any type that can be cheaply /// converted into an `&[u8]`. This includes, but is not limited to, /// `&str`, `&BStr` and `&[u8]` itself. /// /// # Examples /// /// Basic usage: /// /// ``` /// use bstr; /// /// let s = bstr::join(",", &["foo", "bar", "baz"]); /// assert_eq!(s, "foo,bar,baz"); /// ``` pub fn join<B, T, I>( separator: B, elements: I, ) -> BString where B: AsRef<[u8]>, T: AsRef<[u8]>, I: IntoIterator<Item=T> { let mut it = elements.into_iter(); let mut dest = BString::new(); match it.next() { None => return dest, Some(first) => { dest.push(first); } } for element in it { dest.push(&separator); dest.push(element); } dest } /// A growable byte string that is conventionally UTF-8. /// /// A `BString` has ownership over its contents and corresponds to /// a growable or shrinkable buffer. Its borrowed counterpart is a /// [`BStr`](struct.BStr.html), called a byte string slice. /// /// # Examples /// /// You can create a new `BString` from a literal Unicode string or a literal /// byte string with `BString::from`: /// /// ``` /// use bstr::BString; /// /// let s = BString::from("Hello, world!"); /// ``` /// /// You can append bytes, characters or other strings to a `BString`: /// /// ``` /// use bstr::BString; /// /// let mut s = BString::from("Hello, "); /// s.push_byte(b'w'); /// s.push_char('o'); /// s.push("rl"); /// s.push(b"d!"); /// assert_eq!(s, "Hello, world!"); /// ``` /// /// If you have a `String` or a `Vec<u8>`, then you can create a `BString` /// from it with zero cost: /// /// ``` /// use bstr::BString; /// /// let s = BString::from(vec![b'f', b'o', b'o']); /// let s = BString::from("foo".to_string()); /// ``` /// /// A `BString` can be freely converted back to a `Vec<u8>`: /// /// ``` /// use bstr::BString; /// /// let s = BString::from("foo"); /// let vector = s.into_vec(); /// assert_eq!(vector, vec![b'f', b'o', b'o']); /// ``` /// /// However, converting from a `BString` to a `String` requires UTF-8 /// validation: /// /// ``` /// use bstr::BString; /// /// # fn example() -> Result<(), ::bstr::FromUtf8Error> { /// let bytes = BString::from("hello"); /// let string = bytes.into_string()?; /// /// assert_eq!("hello", string); /// # Ok(()) }; example().unwrap() /// ``` /// /// # UTF-8 /// /// Like byte string slices (`BStr`), a `BString` is only conventionally /// UTF-8. This is in constrast to the standard library's `String` type, which /// is guaranteed to be valid UTF-8. /// /// Because of this relaxation, types such as `Vec<u8>`, `&[u8]`, `String` and /// `&str` can all be converted to a `BString` (or `BStr`) at zero cost without /// any validation step. /// /// Moreover, this relaxation implies that many of the restrictions around /// mutating a `String` do not apply to `BString`. Namely, if your `BString` /// is valid UTF-8, then the various methods that mutate the `BString` do not /// necessarily prevent you from causing the bytes to become invalid UTF-8. /// For example: /// /// ``` /// use bstr::{B, BString}; /// /// let mut s = BString::from("hello"); /// s[1] = b'\xFF'; /// // `s` was valid UTF-8, but now it's now. /// assert_eq!(s, B(b"h\xFFllo")); /// ``` /// /// # Deref /// /// The `BString` type implements `Deref` and `DerefMut`, where the target /// types are `&BStr` and `&mut BStr`, respectively. `Deref` permits all of the /// methods defined on `BStr` to be implicitly callable on any `BString`. /// For example, the `contains` method is defined on `BStr` and not `BString`, /// but values of type `BString` can still use it directly: /// /// ``` /// use bstr::BString; /// /// let s = BString::from("foobarbaz"); /// assert!(s.contains("bar")); /// ``` /// /// For more information about how deref works, see the documentation for the /// [`std::ops::Deref`](https://doc.rust-lang.org/std/ops/trait.Deref.html) /// trait. /// /// # Representation /// /// A `BString` has the same representation as a `Vec<u8>` and a `String`. /// That is, it is made up of three word sized components: a pointer to a /// region of memory containing the bytes, a length and a capacity. #[derive(Clone, Hash)] pub struct BString { bytes: Vec<u8>, } impl BString { /// Creates a new empty `BString`. /// /// Given that the `BString` is empty, this will not allocate any initial /// buffer. While that means that this initial operation is very /// inexpensive, it may cause excessive allocation later when you add /// data. If you have an idea of how much data the `String` will hold, /// consider the [`with_capacity`] method to prevent excessive /// re-allocation. /// /// [`with_capacity`]: #method.with_capacity /// /// # Examples /// /// Basic usage: /// /// ``` /// use bstr::BString; /// /// let s = BString::new(); /// ``` pub fn new() -> BString { BString { bytes: vec![] } } /// Creates a new empty `BString` with a particular capacity. /// /// `BString`s have an internal buffer to hold their data. The capacity is /// the length of that buffer, and can be queried with the [`capacity`] /// method. This method creates an empty `BString`, but one with an initial /// buffer that can hold `capacity` bytes. This is useful when you may be /// appending a bunch of data to the `BString`, reducing the number of /// reallocations it needs to do. /// /// [`capacity`]: #method.capacity /// /// If the given capacity is `0`, no allocation will occur, and this method /// is identical to the [`new`] method. /// /// [`new`]: #method.new /// /// # Examples /// /// Basic usage: /// /// ``` /// use bstr::BString; /// /// let mut s = BString::with_capacity(10); /// /// // The String contains no chars, even though it has capacity for more /// assert_eq!(s.len(), 0); /// /// // These are all done without reallocating... /// let cap = s.capacity(); /// for i in 0..10 { /// s.push_char('a'); /// } /// /// assert_eq!(s.capacity(), cap); /// /// // ...but this may make the vector reallocate /// s.push_char('a'); /// ``` pub fn with_capacity(capacity: usize) -> BString { BString { bytes: Vec::with_capacity(capacity) } } /// Create a new byte string from the given bytes. /// /// # Examples /// /// Basic usage: /// /// ``` /// use bstr::BString; /// /// let bytes = vec![b'a', b'b', b'c']; /// let s = BString::from_vec(bytes); /// assert_eq!("abc", s); /// ``` pub fn from_vec(bytes: Vec<u8>) -> BString { BString { bytes } } /// Create a new byte string by copying the given slice. /// /// # Examples /// /// Basic usage: /// /// ``` /// use bstr::BString; /// /// let s = BString::from_slice(b"abc"); /// assert_eq!("abc", s); /// ``` pub fn from_slice<B: AsRef<[u8]>>(slice: B) -> BString { BString::from_vec(slice.as_ref().to_vec()) } /// Appends the given byte to the end of this byte string. /// /// # Examples /// /// Basic usage: /// /// ``` /// use bstr::BString; /// /// let mut s = BString::from("abc"); /// s.push_byte(b'\xE2'); /// s.push_byte(b'\x98'); /// s.push_byte(b'\x83'); /// assert_eq!("abc☃", s); /// ``` pub fn push_byte(&mut self, byte: u8) { self.bytes.push(byte); } /// Appends the given `char` to the end of this byte string. /// /// # Examples /// /// Basic usage: /// /// ``` /// use bstr::BString; /// /// let mut s = BString::from("abc"); /// s.push_char('1'); /// s.push_char('2'); /// s.push_char('3'); /// assert_eq!("abc123", s); /// ``` pub fn push_char(&mut self, ch: char) { if ch.len_utf8() == 1 { self.bytes.push(ch as u8); return; } self.bytes.extend_from_slice(ch.encode_utf8(&mut [0; 4]).as_bytes()); } /// Appends the given slice to the end of this byte string. This accepts /// any type that be converted to a `&[u8]`. This includes, but is not /// limited to, `&str`, `&BStr`, and of course, `&[u8]` itself. /// /// # Examples /// /// Basic usage: /// /// ``` /// use bstr::BString; /// /// let mut s = BString::from("abc"); /// s.push(b"123"); /// assert_eq!("abc123", s); /// ``` pub fn push<B: AsRef<[u8]>>(&mut self, bytes: B) { self.bytes.extend_from_slice(bytes.as_ref()); } /// Extracts a byte string slice containing the entire `BString`. /// /// # Examples /// /// Basic usage: /// /// ``` /// use bstr::{BStr, BString}; /// /// let s = BString::from("foo"); /// /// assert_eq!(BStr::new("foo"), s.as_bstr()); /// ``` pub fn as_bstr(&self) -> &BStr { BStr::from_bytes(&self.bytes) } /// Returns this `BString` as a borrowed byte vector. /// /// # Examples /// /// Basic usage: /// /// ``` /// use bstr::BString; /// /// let bs = BString::from("ab"); /// assert!(bs.as_vec().capacity() >= 2); /// ``` pub fn as_vec(&self) -> &Vec<u8> { &self.bytes } /// Converts a `BString` into a mutable string slice. /// /// # Examples /// /// Basic usage: /// /// ``` /// use bstr::BString; /// /// let mut s = BString::from("foobar"); /// let s_mut_str = s.as_mut_bstr(); /// /// s_mut_str[0] = b'F'; /// /// assert_eq!("Foobar", s_mut_str); /// ``` pub fn as_mut_bstr(&mut self) -> &mut BStr { BStr::from_bytes_mut(&mut self.bytes) } /// Returns this `BString` as a mutable byte vector. /// /// # Examples /// /// Basic usage: /// /// ``` /// use bstr::BString; /// /// let mut bs = BString::from("ab"); /// bs.as_mut_vec().push(b'c'); /// assert_eq!("abc", bs); /// ``` pub fn as_mut_vec(&mut self) -> &mut Vec<u8> { &mut self.bytes } /// Converts a `BString` into a byte vector. /// /// This consumes the `BString`, and thus the contents are not copied. /// /// # Examples /// /// Basic usage: /// /// ``` /// use bstr::BString; /// /// let s = BString::from("hello"); /// let bytes = s.into_vec(); /// /// assert_eq!(vec![104, 101, 108, 108, 111], &bytes[..]); /// ``` pub fn into_vec(self) -> Vec<u8> { self.bytes } /// Converts a `BString` into a `String` if and only if this byte string is /// valid UTF-8. /// /// If it is not valid UTF-8, then the error `std::string::FromUtf8Error` /// is returned. (This error can be used to examine why UTF-8 validation /// failed, or to regain the original byte string.) /// /// # Examples /// /// Basic usage: /// /// ``` /// use bstr::BString; /// /// # fn example() -> Result<(), ::bstr::FromUtf8Error> { /// let bytes = BString::from("hello"); /// let string = bytes.into_string()?; /// /// assert_eq!("hello", string); /// # Ok(()) }; example().unwrap() /// ``` /// /// If this byte string is not valid UTF-8, then an error will be returned. /// That error can then be used to inspect the location at which invalid /// UTF-8 was found, or to regain the original byte string: /// /// ``` /// use bstr::{B, BString}; /// /// let bytes = BString::from_slice(b"foo\xFFbar"); /// let err = bytes.into_string().unwrap_err(); /// /// assert_eq!(err.utf8_error().valid_up_to(), 3); /// assert_eq!(err.utf8_error().error_len(), Some(1)); /// /// // At no point in this example is an allocation performed. /// let bytes = BString::from(err.into_bstring()); /// assert_eq!(bytes, B(b"foo\xFFbar")); /// ``` pub fn into_string(self) -> Result<String, FromUtf8Error> { match utf8::validate(self.as_bytes()) { Err(err) => { Err(FromUtf8Error { original: self, err: err }) } Ok(()) => { // SAFETY: This is safe because of the guarantees provided by // utf8::validate. unsafe { Ok(self.into_string_unchecked()) } } } } /// Unsafely convert this byte string into a `String`, without checking for /// valid UTF-8. /// /// # Safety /// /// Callers *must* ensure that this byte string is valid UTF-8 before /// calling this method. Converting a byte string into a `String` that is /// not valid UTF-8 is considered undefined behavior. /// /// This routine is useful in performance sensitive contexts where the /// UTF-8 validity of the byte string is already known and it is /// undesirable to pay the cost of an additional UTF-8 validation check /// that [`into_string`](#method.into_string) performs. /// /// # Examples /// /// Basic usage: /// /// ``` /// use bstr::BString; /// /// // SAFETY: This is safe because string literals are guaranteed to be /// // valid UTF-8 by the Rust compiler. /// let s = unsafe { BString::from("☃βツ").into_string_unchecked() }; /// assert_eq!("☃βツ", s); /// ``` pub unsafe fn into_string_unchecked(self) -> String { String::from_utf8_unchecked(self.into_vec()) } /// Converts this `BString` into a `Box<BStr>`. /// /// This will drop any excess capacity. /// /// # Examples /// /// Basic usage: /// /// ``` /// use bstr::BString; /// /// let s = BString::from("foobar"); /// let b = s.into_boxed_bstr(); /// assert_eq!(6, b.len()); /// ``` pub fn into_boxed_bstr(self) -> Box<BStr> { unsafe { let slice = self.bytes.into_boxed_slice(); Box::from_raw(Box::into_raw(slice) as *mut BStr) } } /// Returns this byte string's capacity, in bytes. /// /// # Examples /// /// Basic usage: /// /// ``` /// use bstr::BString; /// /// let s = BString::with_capacity(10); /// assert_eq!(10, s.capacity()); /// ``` pub fn capacity(&self) -> usize { self.bytes.capacity() } /// Truncates this byte string, removing all contents. /// /// The resulting byte string will always have length `0`, but its capacity /// remains unchanged. pub fn clear(&mut self) { self.bytes.clear(); } /// Ensures that this `BString`'s capacity is at least `additional` /// bytes larger than its length. /// /// The capacity may be increased by more than `additional` bytes if it /// chooses, to prevent frequent reallocations. /// /// If you do not want this "at least" behavior, use the /// [`reserve_exact`](#method.reserve_exact) method instead. /// /// # Panics /// /// Panics if the new capacity overflows `usize`. /// /// # Examples /// /// Basic usage: /// /// ``` /// use bstr::BString; /// /// let mut s = BString::new(); /// s.reserve(10); /// assert!(s.capacity() >= 10); /// ``` pub fn reserve(&mut self, additional: usize) { self.bytes.reserve(additional); } /// Ensures that this `BString`'s capacity is exactly `additional` /// bytes larger than its length. /// /// Consider using the [`reserve`](#method.reserve) method unless you /// absolutely know better than the allocator. /// /// # Panics /// /// Panics if the new capacity overflows `usize`. /// /// # Examples /// /// Basic usage: /// /// ``` /// use bstr::BString; /// /// let mut s = BString::new(); /// s.reserve_exact(10); /// assert!(s.capacity() >= 10); /// ``` pub fn reserve_exact(&mut self, additional: usize) { self.bytes.reserve_exact(additional); } /// Shrinks the capacity of this `BString` to match its length. /// /// Examples /// /// Basic usage: /// /// ``` /// use bstr::BString; /// /// let mut s = BString::from("foo"); /// s.reserve(10); /// assert!(s.capacity() >= 10); /// s.shrink_to_fit(); /// assert_eq!(3, s.capacity()); /// ``` pub fn shrink_to_fit(&mut self) { self.bytes.shrink_to_fit(); } /// Shortens this `BString` to the specified length, in bytes. /// /// If `new_len` is greater than or equal to this byte string's current /// length, then this has no effect. /// /// Note that this does _not_ panic if the result is not on a valid /// `char` boundary. /// /// # Examples /// /// Basic usage: /// /// ``` /// use bstr::BString; /// /// let mut s = BString::from("foobar"); /// s.truncate(3); /// assert_eq!("foo", s); /// ``` pub fn truncate(&mut self, new_len: usize) { if new_len < self.len() { self.bytes.truncate(new_len); } } /// Resizes this byte string in place so that the length of this byte /// string is equivalent to `new_len`. /// /// If `new_len` is greater than the length of this byte string, then /// the byte string is extended by the difference, which each additional /// byte filled with the given value. If `new_len` is less than the length /// of this byte string, then it is simply truncated. /// /// # Examples /// /// Basic usage: /// /// ``` /// use bstr::BString; /// /// let mut s = BString::from("f"); /// s.resize(3, b'o'); /// assert_eq!(s, "foo"); /// s.resize(1, b'o'); /// assert_eq!(s, "f"); /// ``` pub fn resize(&mut self, new_len: usize, value: u8) { self.bytes.resize(new_len, value); } /// Removes the last codepoint from this `BString` and returns it. /// /// If this string is empty, then `None` is returned. If the last bytes /// of this string do not correspond to a valid UTF-8 code unit sequence, /// then the Unicode replacement codepoint is yielded instead in /// accordance with the /// [replacement codepoint substitution policy](index.html#handling-of-invalid-utf8-8). /// /// # Examples /// /// Basic usage: /// /// ``` /// use bstr::BString; /// /// let mut s = BString::from("foo"); /// assert_eq!(s.pop(), Some('o')); /// assert_eq!(s.pop(), Some('o')); /// assert_eq!(s.pop(), Some('f')); /// assert_eq!(s.pop(), None); /// ``` /// /// This shows the replacement codepoint substitution policy. Note that /// the first pop yields a replacement codepoint but actually removes two /// bytes. This is in contrast with subsequent pops when encountering /// `\xFF` since `\xFF` is never a valid prefix for any valid UTF-8 /// code unit sequence. /// /// ``` /// use bstr::BString; /// /// let mut s = BString::from_slice(b"f\xFF\xFF\xFFoo\xE2\x98"); /// assert_eq!(s.pop(), Some('\u{FFFD}')); /// assert_eq!(s.pop(), Some('o')); /// assert_eq!(s.pop(), Some('o')); /// assert_eq!(s.pop(), Some('\u{FFFD}')); /// assert_eq!(s.pop(), Some('\u{FFFD}')); /// assert_eq!(s.pop(), Some('\u{FFFD}')); /// assert_eq!(s.pop(), Some('f')); /// assert_eq!(s.pop(), None); /// ``` pub fn pop(&mut self) -> Option<char> { let (ch, size) = utf8::decode_last_lossy(self.as_bytes()); if size == 0 { return None; } let new_len = self.len() - size; self.truncate(new_len); Some(ch) } /// Removes a `char` from this `BString` at the given byte position and /// returns it. /// /// If the bytes at the given position do not lead to a valid UTF-8 code /// unit sequence, then a /// [replacement codepoint is returned instead](index.html#handling-of-invalid-utf8-8). /// /// # Panics /// /// Panics if `at` is larger than or equal to this byte string's length. /// /// # Examples /// /// Basic usage: /// /// ``` /// use bstr::BString; /// /// let mut s = BString::from("foo☃bar"); /// assert_eq!('☃', s.remove(3)); /// assert_eq!("foobar", s); /// ``` /// /// This example shows how the Unicode replacement codepoint policy is /// used: /// /// ``` /// use bstr::BString; /// /// let mut s = BString::from_slice(b"foo\xFFbar"); /// assert_eq!('\u{FFFD}', s.remove(3)); /// assert_eq!("foobar", s); /// ``` pub fn remove(&mut self, at: usize) -> char { let (ch, size) = utf8::decode_lossy(self[at..].as_bytes()); assert!(size > 0, "expected {} to be less than {}", at, self.len()); self.bytes.drain(at..at + size); ch } /// Inserts the given codepoint into this `BString` at a particular byte /// position. /// /// This is an `O(n)` operation as it may copy a number of elements in this /// byte string proportional to its length. /// /// # Panics /// /// Panics if `at` is larger than the byte string's length. /// /// # Examples /// /// Basic usage: /// /// ``` /// use bstr::BString; /// /// let mut s = BString::from("foobar"); /// s.insert_char(3, '☃'); /// assert_eq!("foo☃bar", s); /// ``` pub fn insert_char(&mut self, at: usize, ch: char) { self.insert(at, ch.encode_utf8(&mut [0; 4]).as_bytes()); } /// Inserts the given byte string into this byte string at a particular /// byte position. /// /// This is an `O(n)` operation as it may copy a number of elements in this /// byte string proportional to its length. /// /// Note that the type parameter `B` on this method means that it can /// accept anything that can be cheaply converted to a `&[u8]`. This /// includes, but is not limited to, `&str`, `&BStr` and `&[u8]` itself. /// /// # Panics /// /// Panics if `at` is larger than the byte string's length. /// /// # Examples /// /// Basic usage: /// /// ``` /// use bstr::BString; /// /// let mut s = BString::from("foobar"); /// s.insert(3, "☃☃☃"); /// assert_eq!("foo☃☃☃bar", s); /// ``` pub fn insert<B: AsRef<[u8]>>(&mut self, at: usize, bytes: B) { assert!(at <= self.len(), "expected {} to be <= {}", at, self.len()); let bytes = bytes.as_ref(); let len = self.len(); // SAFETY: We'd like to efficiently splice in the given bytes into // this byte string. Since we are only working with `u8` elements here, // we only need to consider whether our bounds are correct and whether // our byte string has enough space. self.reserve(bytes.len()); unsafe { // Shift bytes after `at` over by the length of `bytes` to make // room for it. This requires referencing two regions of memory // that may overlap, so we use ptr::copy. ptr::copy( self.bytes.as_ptr().add(at), self.bytes.as_mut_ptr().add(at + bytes.len()), len - at, ); // Now copy the bytes given into the room we made above. In this // case, we know that the given bytes cannot possibly overlap // with this byte string since we have a mutable borrow of the // latter. Thus, we can use a nonoverlapping copy. ptr::copy_nonoverlapping( bytes.as_ptr(), self.bytes.as_mut_ptr().add(at), bytes.len(), ); self.bytes.set_len(len + bytes.len()); } } /// Splits this `BString` into two separate byte strings at the given /// index. /// /// This returns a newly allocated `BString`, while `self` retans bytes /// `[0, at)` and the returned `BString` contains bytes `[at, len)`. /// /// The capacity of `self` does not change. /// /// # Panics /// /// Panics if `at` is beyond the end of this byte string. /// /// # Examples /// /// Basic usage: /// /// ``` /// use bstr::BString; /// /// let mut s = BString::from("foobar"); /// let bar = s.split_off(3); /// assert_eq!(s, "foo"); /// assert_eq!(bar, "bar"); /// ``` pub fn split_off(&mut self, at: usize) -> BString { BString::from(self.bytes.split_off(at)) } /// Removes the specified range in this byte string and replaces it with /// the given bytes. The given bytes do not need to have the same length /// as the range provided. /// /// # Panics /// /// Panics if the given range is invalid. /// /// # Examples /// /// Basic usage: /// /// ``` /// use bstr::BString; /// /// let mut s = BString::from("foobar"); /// s.replace_range(2..4, "xxxxx"); /// assert_eq!(s, "foxxxxxar"); /// ``` pub fn replace_range<R, B>( &mut self, range: R, replace_with: B, ) where R: ops::RangeBounds<usize>, B: AsRef<[u8]> { self.bytes.splice(range, replace_with.as_ref().iter().cloned()); } /// Creates a draining iterator that removes the specified range in this /// `BString` and yields each of the removed bytes. /// /// Note that the elements specified by the given range are removed /// regardless of whether the returned iterator is fully exhausted. /// /// Also note that is is unspecified how many bytes are removed from the /// `BString` if the `DrainBytes` iterator is leaked. /// /// # Panics /// /// Panics if the given range is not valid. /// /// # Examples /// /// Basic usage: /// /// ``` /// use bstr::BString; /// /// let mut s = BString::from("foobar"); /// { /// let mut drainer = s.drain_bytes(2..4); /// assert_eq!(drainer.next(), Some(b'o')); /// assert_eq!(drainer.next(), Some(b'b')); /// assert_eq!(drainer.next(), None); /// } /// assert_eq!(s, "foar"); /// ``` pub fn drain_bytes<R>( &mut self, range: R, ) -> DrainBytes where R: ops::RangeBounds<usize> { DrainBytes { it: self.bytes.drain(range) } } } /// A draining byte oriented iterator for `BString`. /// /// This iterator is created by /// [`BString::drain`](struct.BString.html#method.drain). /// /// # Examples /// /// Basic usage: /// /// ``` /// use bstr::BString; /// /// let mut s = BString::from("foobar"); /// { /// let mut drainer = s.drain_bytes(2..4); /// assert_eq!(drainer.next(), Some(b'o')); /// assert_eq!(drainer.next(), Some(b'b')); /// assert_eq!(drainer.next(), None); /// } /// assert_eq!(s, "foar"); /// ``` #[derive(Debug)] pub struct DrainBytes<'a> { it: vec::Drain<'a, u8>, } impl<'a> iter::FusedIterator for DrainBytes<'a> {} impl<'a> Iterator for DrainBytes<'a> { type Item = u8; fn next(&mut self) -> Option<u8> { self.it.next() } } impl<'a> DoubleEndedIterator for DrainBytes<'a> { fn next_back(&mut self) -> Option<u8> { self.it.next_back() } } impl<'a> ExactSizeIterator for DrainBytes<'a> { fn len(&self) -> usize { self.it.len() } } /// An error that may occur when converting a `BString` to a `String`. /// /// This error includes the original `BString` that failed to convert to a /// `String`. This permits callers to recover the allocation used even if it /// it not valid UTF-8. /// /// # Examples /// /// Basic usage: /// /// ``` /// use bstr::{B, BString}; /// /// let bytes = BString::from_slice(b"foo\xFFbar"); /// let err = bytes.into_string().unwrap_err(); /// /// assert_eq!(err.utf8_error().valid_up_to(), 3); /// assert_eq!(err.utf8_error().error_len(), Some(1)); /// /// // At no point in this example is an allocation performed. /// let bytes = BString::from(err.into_bstring()); /// assert_eq!(bytes, B(b"foo\xFFbar")); /// ``` #[derive(Debug, Eq, PartialEq)] pub struct FromUtf8Error { original: BString, err: Utf8Error, } impl FromUtf8Error { /// Return the original bytes as a slice that failed to convert to a /// `String`. /// /// # Examples /// /// Basic usage: /// /// ``` /// use bstr::{B, BString}; /// /// let bytes = BString::from_slice(b"foo\xFFbar"); /// let err = bytes.into_string().unwrap_err(); /// /// // At no point in this example is an allocation performed. /// assert_eq!(err.as_bstr(), B(b"foo\xFFbar")); /// ``` pub fn as_bstr(&self) -> &BStr { &self.original } /// Consume this error and return the original byte string that failed to /// convert to a `String`. /// /// # Examples /// /// Basic usage: /// /// ``` /// use bstr::{B, BString}; /// /// let bytes = BString::from_slice(b"foo\xFFbar"); /// let err = bytes.into_string().unwrap_err(); /// let original = err.into_bstring(); /// /// // At no point in this example is an allocation performed. /// assert_eq!(original, B(b"foo\xFFbar")); /// ``` pub fn into_bstring(self) -> BString { self.original } /// Return the underlying UTF-8 error that occurred. This error provides /// information on the nature and location of the invalid UTF-8 detected. /// /// # Examples /// /// Basic usage: /// /// ``` /// use bstr::{B, BString}; /// /// let bytes = BString::from_slice(b"foo\xFFbar"); /// let err = bytes.into_string().unwrap_err(); /// /// assert_eq!(err.utf8_error().valid_up_to(), 3); /// assert_eq!(err.utf8_error().error_len(), Some(1)); /// ``` pub fn utf8_error(&self) -> &Utf8Error { &self.err } } impl error::Error for FromUtf8Error { fn description(&self) -> &str { "invalid UTF-8 vector" } } impl fmt::Display for FromUtf8Error { fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result { write!(f, "{}", self.err) } } #[cfg(test)] mod tests { use bstr::B; use super::*; #[test] fn insert() { let mut s = BString::new(); s.insert(0, "foo"); assert_eq!("foo", s); let mut s = BString::from("a"); s.insert(0, "foo"); assert_eq!("fooa", s); let mut s = BString::from("a"); s.insert(1, "foo"); assert_eq!("afoo", s); let mut s = BString::from("foobar"); s.insert(3, "quux"); assert_eq!("fooquuxbar", s); let mut s = BString::from("foobar"); s.insert(3, "x"); assert_eq!("fooxbar", s); let mut s = BString::from("foobar"); s.insert(0, "x"); assert_eq!("xfoobar", s); let mut s = BString::from("foobar"); s.insert(6, "x"); assert_eq!("foobarx", s); let mut s = BString::from("foobar"); s.insert(3, "quuxbazquux"); assert_eq!("fooquuxbazquuxbar", s); } #[test] #[should_panic] fn insert_fail1() { let mut s = BString::new(); s.insert(1, "foo"); } #[test] #[should_panic] fn insert_fail2() { let mut s = BString::from("a"); s.insert(2, "foo"); } #[test] #[should_panic] fn insert_fail3() { let mut s = BString::from("foobar"); s.insert(7, "foo"); } #[test] fn collect() { let s: BString = vec!['a', 'b', 'c'].into_iter().collect(); assert_eq!(s, "abc"); let s: BString = vec!["a", "b", "c"].into_iter().collect(); assert_eq!(s, "abc"); let s: BString = vec![B("a"), B("b"), B("c")].into_iter().collect(); assert_eq!(s, "abc"); } }