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 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305
//! `textwrap` provides functions for word wrapping and filling text. //! //! Wrapping text can be very useful in commandline programs where you //! want to format dynamic output nicely so it looks good in a //! terminal. A quick example: //! //! ```no_run //! extern crate textwrap; //! use textwrap::fill; //! //! fn main() { //! let text = "textwrap: a small library for wrapping text."; //! println!("{}", fill(text, 18)); //! } //! ``` //! //! This will display the following output: //! //! ```text //! textwrap: a small //! library for //! wrapping text. //! ``` //! //! # Displayed Width vs Byte Size //! //! To word wrap text, one must know the width of each word so one can //! know when to break lines. This library measures the width of text //! using the [displayed width][unicode-width], not the size in bytes. //! //! This is important for non-ASCII text. ASCII characters such as `a` //! and `!` are simple and take up one column each. This means that //! the displayed width is equal to the string length in bytes. //! However, non-ASCII characters and symbols take up more than one //! byte when UTF-8 encoded: `é` is `0xc3 0xa9` (two bytes) and `⚙` is //! `0xe2 0x9a 0x99` (three bytes) in UTF-8, respectively. //! //! This is why we take care to use the displayed width instead of the //! byte count when computing line lengths. All functions in this //! library handle Unicode characters like this. //! //! [unicode-width]: https://docs.rs/unicode-width/ #![doc(html_root_url = "https://docs.rs/textwrap/0.10.0")] #![deny(missing_docs)] #![deny(missing_debug_implementations)] #[cfg(feature = "hyphenation")] extern crate hyphenation; #[cfg(feature = "term_size")] extern crate term_size; extern crate unicode_width; use std::borrow::Cow; use std::str::CharIndices; #[cfg(feature = "hyphenation")] use hyphenation::{Corpus, Hyphenation}; use unicode_width::UnicodeWidthChar; use unicode_width::UnicodeWidthStr; /// A non-breaking space. const NBSP: char = '\u{a0}'; /// An interface for splitting words. /// /// When the [`wrap_iter`] method will try to fit text into a line, it /// will eventually find a word that it too large the current text /// width. It will then call the currently configured `WordSplitter` to /// have it attempt to split the word into smaller parts. This trait /// describes that functionality via the [`split`] method. /// /// If the `textwrap` crate has been compiled with the `hyphenation` /// feature enabled, you will find an implementation of `WordSplitter` /// by the `hyphenation::language::Corpus` struct. Use this struct for /// language-aware hyphenation. See the [`hyphenation` documentation] /// for details. /// /// [`wrap_iter`]: struct.Wrapper.html#method.wrap_iter /// [`split`]: #tymethod.split /// [`hyphenation` documentation]: https://docs.rs/hyphenation/ pub trait WordSplitter { /// Return all possible splits of word. Each split is a triple /// with a head, a hyphen, and a tail where `head + &hyphen + /// &tail == word`. The hyphen can be empty if there is already a /// hyphen in the head. /// /// The splits should go from smallest to longest and should /// include no split at all. So the word "technology" could be /// split into /// /// ```no_run /// vec![("tech", "-", "nology"), /// ("technol", "-", "ogy"), /// ("technolo", "-", "gy"), /// ("technology", "", "")]; /// ``` fn split<'w>(&self, word: &'w str) -> Vec<(&'w str, &'w str, &'w str)>; } /// Use this as a [`Wrapper.splitter`] to avoid any kind of /// hyphenation: /// /// ``` /// use textwrap::{Wrapper, NoHyphenation}; /// /// let wrapper = Wrapper::with_splitter(8, NoHyphenation); /// assert_eq!(wrapper.wrap("foo bar-baz"), vec!["foo", "bar-baz"]); /// ``` /// /// [`Wrapper.splitter`]: struct.Wrapper.html#structfield.splitter #[derive(Clone, Debug)] pub struct NoHyphenation; /// `NoHyphenation` implements `WordSplitter` by not splitting the /// word at all. impl WordSplitter for NoHyphenation { fn split<'w>(&self, word: &'w str) -> Vec<(&'w str, &'w str, &'w str)> { vec![(word, "", "")] } } /// Simple and default way to split words: splitting on existing /// hyphens only. /// /// You probably don't need to use this type since it's already used /// by default by `Wrapper::new`. #[derive(Clone, Debug)] pub struct HyphenSplitter; /// `HyphenSplitter` is the default `WordSplitter` used by /// `Wrapper::new`. It will split words on any existing hyphens in the /// word. /// /// It will only use hyphens that are surrounded by alphanumeric /// characters, which prevents a word like "--foo-bar" from being /// split on the first or second hyphen. impl WordSplitter for HyphenSplitter { fn split<'w>(&self, word: &'w str) -> Vec<(&'w str, &'w str, &'w str)> { let mut triples = Vec::new(); // Split on hyphens, smallest split first. We only use hyphens // that are surrounded by alphanumeric characters. This is to // avoid splitting on repeated hyphens, such as those found in // --foo-bar. let mut char_indices = word.char_indices(); // Early return if the word is empty. let mut prev = match char_indices.next() { None => return vec![(word, "", "")], Some((_, ch)) => ch, }; // Find current word, or return early if the word only has a // single character. let (mut idx, mut cur) = match char_indices.next() { None => return vec![(word, "", "")], Some((idx, cur)) => (idx, cur), }; for (i, next) in char_indices { if prev.is_alphanumeric() && cur == '-' && next.is_alphanumeric() { let (head, tail) = word.split_at(idx + 1); triples.push((head, "", tail)); } prev = cur; idx = i; cur = next; } // Finally option is no split at all. triples.push((word, "", "")); triples } } /// A hyphenation Corpus can be used to do language-specific /// hyphenation using patterns from the hyphenation crate. #[cfg(feature = "hyphenation")] impl WordSplitter for Corpus { fn split<'w>(&self, word: &'w str) -> Vec<(&'w str, &'w str, &'w str)> { // Find splits based on language corpus. let mut triples = Vec::new(); for n in word.opportunities(self) { let (head, tail) = word.split_at(n); let hyphen = if head.ends_with('-') { "" } else { "-" }; triples.push((head, hyphen, tail)); } // Finally option is no split at all. triples.push((word, "", "")); triples } } /// A Wrapper holds settings for wrapping and filling text. Use it /// when the convenience [`wrap_iter`], [`wrap`] and [`fill`] functions /// are not flexible enough. /// /// [`wrap_iter`]: fn.wrap_iter.html /// [`wrap`]: fn.wrap.html /// [`fill`]: fn.fill.html /// /// The algorithm used by the `WrapIter` iterator (returned from the /// `wrap_iter` method) works by doing successive partial scans over /// words in the input string (where each single scan yields a single /// line) so that the overall time and memory complexity is O(*n*) where /// *n* is the length of the input string. #[derive(Clone, Debug)] pub struct Wrapper<'a, S: WordSplitter> { /// The width in columns at which the text will be wrapped. pub width: usize, /// Indentation used for the first line of output. pub initial_indent: &'a str, /// Indentation used for subsequent lines of output. pub subsequent_indent: &'a str, /// Allow long words to be broken if they cannot fit on a line. /// When set to `false`, some lines may be longer than /// `self.width`. pub break_words: bool, /// The method for splitting words. If the `hyphenation` feature /// is enabled, you can use a `hyphenation::language::Corpus` here /// to get language-aware hyphenation. pub splitter: S, } impl<'a> Wrapper<'a, HyphenSplitter> { /// Create a new Wrapper for wrapping at the specified width. By /// default, we allow words longer than `width` to be broken. A /// [`HyphenSplitter`] will be used by default for splitting /// words. See the [`WordSplitter`] trait for other options. /// /// [`HyphenSplitter`]: struct.HyphenSplitter.html /// [`WordSplitter`]: trait.WordSplitter.html pub fn new(width: usize) -> Wrapper<'a, HyphenSplitter> { Wrapper::with_splitter(width, HyphenSplitter) } /// Create a new Wrapper for wrapping text at the current terminal /// width. If the terminal width cannot be determined (typically /// because the standard input and output is not connected to a /// terminal), a width of 80 characters will be used. Other /// settings use the same defaults as `Wrapper::new`. /// /// Equivalent to: /// /// ```no_run /// # #![allow(unused_variables)] /// use textwrap::{Wrapper, termwidth}; /// /// let wrapper = Wrapper::new(termwidth()); /// ``` #[cfg(feature = "term_size")] pub fn with_termwidth() -> Wrapper<'a, HyphenSplitter> { Wrapper::new(termwidth()) } } impl<'w, 'a: 'w, S: WordSplitter> Wrapper<'a, S> { /// Use the given [`WordSplitter`] to create a new Wrapper for /// wrapping at the specified width. By default, we allow words /// longer than `width` to be broken. /// /// [`WordSplitter`]: trait.WordSplitter.html pub fn with_splitter(width: usize, splitter: S) -> Wrapper<'a, S> { Wrapper { width: width, initial_indent: "", subsequent_indent: "", break_words: true, splitter: splitter, } } /// Change [`self.initial_indent`]. The initial indentation is /// used on the very first line of output. /// /// # Examples /// /// Classic paragraph indentation can be achieved by specifying an /// initial indentation and wrapping each paragraph by itself: /// /// ```no_run /// # #![allow(unused_variables)] /// use textwrap::Wrapper; /// /// let wrapper = Wrapper::new(15).initial_indent(" "); /// ``` /// /// [`self.initial_indent`]: #structfield.initial_indent pub fn initial_indent(self, indent: &'a str) -> Wrapper<'a, S> { Wrapper { initial_indent: indent, ..self } } /// Change [`self.subsequent_indent`]. The subsequent indentation /// is used on lines following the first line of output. /// /// # Examples /// /// Combining initial and subsequent indentation lets you format a /// single paragraph as a bullet list: /// /// ```no_run /// # #![allow(unused_variables)] /// use textwrap::Wrapper; /// /// let wrapper = Wrapper::new(15) /// .initial_indent("* ") /// .subsequent_indent(" "); /// ``` /// /// [`self.subsequent_indent`]: #structfield.subsequent_indent pub fn subsequent_indent(self, indent: &'a str) -> Wrapper<'a, S> { Wrapper { subsequent_indent: indent, ..self } } /// Change [`self.break_words`]. This controls if words longer /// than `self.width` can be broken, or if they will be left /// sticking out into the right margin. /// /// [`self.break_words`]: #structfield.break_words pub fn break_words(self, setting: bool) -> Wrapper<'a, S> { Wrapper { break_words: setting, ..self } } /// Fill a line of text at `self.width` characters. Strings are /// wrapped based on their displayed width, not their size in /// bytes. /// /// The result is a string with newlines between each line. Use /// the `wrap` method if you need access to the individual lines. /// /// # Complexities /// /// This method simply joins the lines produced by `wrap_iter`. As /// such, it inherits the O(*n*) time and memory complexity where /// *n* is the input string length. /// /// # Examples /// /// ``` /// use textwrap::Wrapper; /// /// let wrapper = Wrapper::new(15); /// assert_eq!(wrapper.fill("Memory safety without garbage collection."), /// "Memory safety\nwithout garbage\ncollection."); /// ``` pub fn fill(&self, s: &str) -> String { // This will avoid reallocation in simple cases (no // indentation, no hyphenation). let mut result = String::with_capacity(s.len()); for (i, line) in self.wrap_iter(s).enumerate() { if i > 0 { result.push('\n'); } result.push_str(&line); } result } /// Wrap a line of text at `self.width` characters. Strings are /// wrapped based on their displayed width, not their size in /// bytes. /// /// # Complexities /// /// This method simply collects the lines produced by `wrap_iter`. /// As such, it inherits the O(*n*) overall time and memory /// complexity where *n* is the input string length. /// /// # Examples /// /// ``` /// use textwrap::Wrapper; /// /// let wrap15 = Wrapper::new(15); /// assert_eq!(wrap15.wrap("Concurrency without data races."), /// vec!["Concurrency", /// "without data", /// "races."]); /// /// let wrap20 = Wrapper::new(20); /// assert_eq!(wrap20.wrap("Concurrency without data races."), /// vec!["Concurrency without", /// "data races."]); /// ``` /// /// Notice that newlines in the input are preserved. This means /// that they force a line break, regardless of how long the /// current line is: /// /// ``` /// use textwrap::Wrapper; /// /// let wrapper = Wrapper::new(40); /// assert_eq!(wrapper.wrap("First line.\nSecond line."), /// vec!["First line.", "Second line."]); /// ``` /// pub fn wrap(&self, s: &'a str) -> Vec<Cow<'a, str>> { self.wrap_iter(s).collect::<Vec<_>>() } /// Lazily wrap a line of text at `self.width` characters. Strings /// are wrapped based on their displayed width, not their size in /// bytes. /// /// The [`WordSplitter`] stored in [`self.splitter`] is used /// whenever when a word is too large to fit on the current line. /// By changing the field, different hyphenation strategies can be /// implemented. /// /// # Complexities /// /// This method returns a [`WrapIter`] iterator which borrows this /// `Wrapper`. The algorithm used has a linear complexity, so /// getting the next line from the iterator will take O(*w*) time, /// where *w* is the wrapping width. Fully processing the iterator /// will take O(*n*) time for an input string of length *n*. /// /// When no indentation is used, each line returned is a slice of /// the input string and the memory overhead is thus constant. /// Otherwise new memory is allocated for each line returned. /// /// # Examples /// /// ``` /// use std::borrow::Cow; /// use textwrap::Wrapper; /// /// let wrap20 = Wrapper::new(20); /// let mut wrap20_iter = wrap20.wrap_iter("Zero-cost abstractions."); /// assert_eq!(wrap20_iter.next(), Some(Cow::from("Zero-cost"))); /// assert_eq!(wrap20_iter.next(), Some(Cow::from("abstractions."))); /// assert_eq!(wrap20_iter.next(), None); /// /// let wrap25 = Wrapper::new(25); /// let mut wrap25_iter = wrap25.wrap_iter("Zero-cost abstractions."); /// assert_eq!(wrap25_iter.next(), Some(Cow::from("Zero-cost abstractions."))); /// assert_eq!(wrap25_iter.next(), None); /// ``` /// /// [`self.splitter`]: #structfield.splitter /// [`WordSplitter`]: trait.WordSplitter.html /// [`WrapIter`]: struct.WrapIter.html pub fn wrap_iter(&'w self, s: &'a str) -> WrapIter<'w, 'a, S> { WrapIter { wrapper: self, inner: WrapIterImpl::new(self, s), } } /// Lazily wrap a line of text at `self.width` characters. Strings /// are wrapped based on their displayed width, not their size in /// bytes. /// /// The [`WordSplitter`] stored in [`self.splitter`] is used /// whenever when a word is too large to fit on the current line. /// By changing the field, different hyphenation strategies can be /// implemented. /// /// # Complexities /// /// This method consumes the `Wrapper` and returns a /// [`IntoWrapIter`] iterator. Fully processing the iterator has /// the same O(*n*) time complexity as [`wrap_iter`], where *n* is /// the length of the input string. /// /// # Examples /// /// ``` /// use std::borrow::Cow; /// use textwrap::Wrapper; /// /// let wrap20 = Wrapper::new(20); /// let mut wrap20_iter = wrap20.into_wrap_iter("Zero-cost abstractions."); /// assert_eq!(wrap20_iter.next(), Some(Cow::from("Zero-cost"))); /// assert_eq!(wrap20_iter.next(), Some(Cow::from("abstractions."))); /// assert_eq!(wrap20_iter.next(), None); /// ``` /// /// [`self.splitter`]: #structfield.splitter /// [`WordSplitter`]: trait.WordSplitter.html /// [`IntoWrapIter`]: struct.IntoWrapIter.html /// [`wrap_iter`]: #method.wrap_iter pub fn into_wrap_iter(self, s: &'a str) -> IntoWrapIter<'a, S> { let inner = WrapIterImpl::new(&self, s); IntoWrapIter { wrapper: self, inner: inner, } } } /// An iterator over the lines of the input string which owns a /// `Wrapper`. An instance of `IntoWrapIter` is typically obtained /// through either [`wrap_iter`] or [`Wrapper::into_wrap_iter`]. /// /// Each call of `.next()` method yields a line wrapped in `Some` if the /// input hasn't been fully processed yet. Otherwise it returns `None`. /// /// [`wrap_iter`]: fn.wrap_iter.html /// [`Wrapper::into_wrap_iter`]: struct.Wrapper.html#method.into_wrap_iter #[derive(Debug)] pub struct IntoWrapIter<'a, S: WordSplitter> { wrapper: Wrapper<'a, S>, inner: WrapIterImpl<'a>, } impl<'a, S: WordSplitter> Iterator for IntoWrapIter<'a, S> { type Item = Cow<'a, str>; fn next(&mut self) -> Option<Cow<'a, str>> { self.inner.next(&self.wrapper) } } /// An iterator over the lines of the input string which borrows a /// `Wrapper`. An instance of `WrapIter` is typically obtained /// through the [`Wrapper::wrap_iter`] method. /// /// Each call of `.next()` method yields a line wrapped in `Some` if the /// input hasn't been fully processed yet. Otherwise it returns `None`. /// /// [`Wrapper::wrap_iter`]: struct.Wrapper.html#method.wrap_iter #[derive(Debug)] pub struct WrapIter<'w, 'a: 'w, S: WordSplitter + 'w> { wrapper: &'w Wrapper<'a, S>, inner: WrapIterImpl<'a>, } impl<'w, 'a: 'w, S: WordSplitter> Iterator for WrapIter<'w, 'a, S> { type Item = Cow<'a, str>; fn next(&mut self) -> Option<Cow<'a, str>> { self.inner.next(self.wrapper) } } /// Like `char::is_whitespace`, but non-breaking spaces don't count. #[inline] fn is_whitespace(ch: char) -> bool { ch.is_whitespace() && ch != NBSP } /// Common implementation details for `WrapIter` and `IntoWrapIter`. #[derive(Debug)] struct WrapIterImpl<'a> { // String to wrap. source: &'a str, // CharIndices iterator over self.source. char_indices: CharIndices<'a>, // Byte index where the current line starts. start: usize, // Byte index of the last place where the string can be split. split: usize, // Size in bytes of the character at self.source[self.split]. split_len: usize, // Width of self.source[self.start..idx]. line_width: usize, // Width of self.source[self.start..self.split]. line_width_at_split: usize, // Tracking runs of whitespace characters. in_whitespace: bool, // Has iterator finished producing elements? finished: bool, } impl<'a> WrapIterImpl<'a> { fn new<S: WordSplitter>(wrapper: &Wrapper<'a, S>, s: &'a str) -> WrapIterImpl<'a> { WrapIterImpl { source: s, char_indices: s.char_indices(), start: 0, split: 0, split_len: 0, line_width: wrapper.initial_indent.width(), line_width_at_split: wrapper.initial_indent.width(), in_whitespace: false, finished: false, } } fn create_result_line<S: WordSplitter>(&self, wrapper: &Wrapper<'a, S>) -> Cow<'a, str> { if self.start == 0 { Cow::from(wrapper.initial_indent) } else { Cow::from(wrapper.subsequent_indent) } } fn next<S: WordSplitter>(&mut self, wrapper: &Wrapper<'a, S>) -> Option<Cow<'a, str>> { if self.finished { return None; } while let Some((idx, ch)) = self.char_indices.next() { let char_width = ch.width().unwrap_or(0); let char_len = ch.len_utf8(); if ch == '\n' { self.split = idx; self.split_len = char_len; self.line_width_at_split = self.line_width; self.in_whitespace = false; // If this is not the final line, return the current line. Otherwise, // we will return the line with its line break after exiting the loop if self.split + self.split_len < self.source.len() { let mut line = self.create_result_line(wrapper); line += &self.source[self.start..self.split]; self.start = self.split + self.split_len; self.line_width = wrapper.subsequent_indent.width(); return Some(line); } } else if is_whitespace(ch) { // Extend the previous split or create a new one. if self.in_whitespace { self.split_len += char_len; } else { self.split = idx; self.split_len = char_len; } self.line_width_at_split = self.line_width + char_width; self.in_whitespace = true; } else if self.line_width + char_width > wrapper.width { // There is no room for this character on the current // line. Try to split the final word. self.in_whitespace = false; let remaining_text = &self.source[self.split + self.split_len..]; let final_word = match remaining_text.find(is_whitespace) { Some(i) => &remaining_text[..i], None => remaining_text, }; let mut hyphen = ""; let splits = wrapper.splitter.split(final_word); for &(head, hyp, _) in splits.iter().rev() { if self.line_width_at_split + head.width() + hyp.width() <= wrapper.width { // We can fit head into the current line. // Advance the split point by the width of the // whitespace and the head length. self.split += self.split_len + head.len(); self.split_len = 0; hyphen = hyp; break; } } if self.start >= self.split { // The word is too big to fit on a single line, so we // need to split it at the current index. if wrapper.break_words { // Break work at current index. self.split = idx; self.split_len = 0; self.line_width_at_split = self.line_width; } else { // Add smallest split. self.split = self.start + splits[0].0.len(); self.split_len = 0; self.line_width_at_split = self.line_width; } } if self.start < self.split { let mut line = self.create_result_line(wrapper); line += &self.source[self.start..self.split]; line += hyphen; self.start = self.split + self.split_len; self.line_width += wrapper.subsequent_indent.width(); self.line_width -= self.line_width_at_split; self.line_width += char_width; return Some(line); } } else { self.in_whitespace = false; } self.line_width += char_width; } self.finished = true; // Add final line. if self.start < self.source.len() { let mut line = self.create_result_line(wrapper); line += &self.source[self.start..]; return Some(line); } None } } /// Return the current terminal width. If the terminal width cannot be /// determined (typically because the standard output is not connected /// to a terminal), a default width of 80 characters will be used. /// /// # Examples /// /// Create a `Wrapper` for the current terminal with a two column /// margin: /// /// ```no_run /// # #![allow(unused_variables)] /// use textwrap::{Wrapper, NoHyphenation, termwidth}; /// /// let width = termwidth() - 4; // Two columns on each side. /// let wrapper = Wrapper::with_splitter(width, NoHyphenation) /// .initial_indent(" ") /// .subsequent_indent(" "); /// ``` #[cfg(feature = "term_size")] pub fn termwidth() -> usize { term_size::dimensions_stdout().map_or(80, |(w, _)| w) } /// Fill a line of text at `width` characters. Strings are wrapped /// based on their displayed width, not their size in bytes. /// /// The result is a string with newlines between each line. Use /// [`wrap`] if you need access to the individual lines or /// [`wrap_iter`] for its iterator counterpart. /// /// ``` /// use textwrap::fill; /// /// assert_eq!(fill("Memory safety without garbage collection.", 15), /// "Memory safety\nwithout garbage\ncollection."); /// ``` /// /// This function creates a Wrapper on the fly with default settings. /// If you need to set a language corpus for automatic hyphenation, or /// need to fill many strings, then it is suggested to create a Wrapper /// and call its [`fill` method]. /// /// [`wrap`]: fn.wrap.html /// [`wrap_iter`]: fn.wrap_iter.html /// [`fill` method]: struct.Wrapper.html#method.fill pub fn fill(s: &str, width: usize) -> String { Wrapper::new(width).fill(s) } /// Wrap a line of text at `width` characters. Strings are wrapped /// based on their displayed width, not their size in bytes. /// /// This function creates a Wrapper on the fly with default settings. /// If you need to set a language corpus for automatic hyphenation, or /// need to wrap many strings, then it is suggested to create a Wrapper /// and call its [`wrap` method]. /// /// The result is a vector of strings. Use [`wrap_iter`] if you need an /// iterator version. /// /// # Examples /// /// ``` /// use textwrap::wrap; /// /// assert_eq!(wrap("Concurrency without data races.", 15), /// vec!["Concurrency", /// "without data", /// "races."]); /// /// assert_eq!(wrap("Concurrency without data races.", 20), /// vec!["Concurrency without", /// "data races."]); /// ``` /// /// [`wrap_iter`]: fn.wrap_iter.html /// [`wrap` method]: struct.Wrapper.html#method.wrap pub fn wrap(s: &str, width: usize) -> Vec<Cow<str>> { Wrapper::new(width).wrap(s) } /// Lazily wrap a line of text at `width` characters. Strings are /// wrapped based on their displayed width, not their size in bytes. /// /// This function creates a Wrapper on the fly with default settings. /// It then calls the [`into_wrap_iter`] method. Hence, the return /// value is an [`IntoWrapIter`], not a [`WrapIter`] as the function /// name would otherwise suggest. /// /// If you need to set a language corpus for automatic hyphenation, or /// need to wrap many strings, then it is suggested to create a Wrapper /// and call its [`wrap_iter`] or [`into_wrap_iter`] methods. /// /// # Examples /// /// ``` /// use std::borrow::Cow; /// use textwrap::wrap_iter; /// /// let mut wrap20_iter = wrap_iter("Zero-cost abstractions.", 20); /// assert_eq!(wrap20_iter.next(), Some(Cow::from("Zero-cost"))); /// assert_eq!(wrap20_iter.next(), Some(Cow::from("abstractions."))); /// assert_eq!(wrap20_iter.next(), None); /// /// let mut wrap25_iter = wrap_iter("Zero-cost abstractions.", 25); /// assert_eq!(wrap25_iter.next(), Some(Cow::from("Zero-cost abstractions."))); /// assert_eq!(wrap25_iter.next(), None); /// ``` /// /// [`wrap_iter`]: struct.Wrapper.html#method.wrap_iter /// [`into_wrap_iter`]: struct.Wrapper.html#method.into_wrap_iter /// [`IntoWrapIter`]: struct.IntoWrapIter.html /// [`WrapIter`]: struct.WrapIter.html pub fn wrap_iter(s: &str, width: usize) -> IntoWrapIter<HyphenSplitter> { Wrapper::new(width).into_wrap_iter(s) } /// Add prefix to each non-empty line. /// /// ``` /// use textwrap::indent; /// /// assert_eq!(indent(" /// Foo /// Bar /// ", " "), " /// Foo /// Bar /// "); /// ``` /// /// Empty lines (lines consisting only of whitespace) are not indented /// and the whitespace is replaced by a single newline (`\n`): /// /// ``` /// use textwrap::indent; /// /// assert_eq!(indent(" /// Foo /// /// Bar /// \t /// Baz /// ", "->"), " /// ->Foo /// /// ->Bar /// /// ->Baz /// "); /// ``` /// /// Leading and trailing whitespace on non-empty lines is kept /// unchanged: /// /// ``` /// use textwrap::indent; /// /// assert_eq!(indent(" \t Foo ", "->"), "-> \t Foo \n"); /// ``` pub fn indent(s: &str, prefix: &str) -> String { let mut result = String::new(); for line in s.lines() { if line.chars().any(|c| !c.is_whitespace()) { result.push_str(prefix); result.push_str(line); } result.push('\n'); } result } /// Removes common leading whitespace from each line. /// /// This function will look at each non-empty line and determine the /// maximum amount of whitespace that can be removed from all lines: /// /// ``` /// use textwrap::dedent; /// /// assert_eq!(dedent(" /// 1st line /// 2nd line /// 3rd line /// "), " /// 1st line /// 2nd line /// 3rd line /// "); /// ``` pub fn dedent(s: &str) -> String { let mut prefix = String::new(); let mut lines = s.lines(); // We first search for a non-empty line to find a prefix. for line in &mut lines { let whitespace = line.chars() .take_while(|c| c.is_whitespace()) .collect::<String>(); // Check if the line had anything but whitespace if whitespace.len() < line.len() { prefix = whitespace; break; } } // We then continue looking through the remaining lines to // possibly shorten the prefix. for line in &mut lines { let whitespace = line.chars() .zip(prefix.chars()) .take_while(|&(a, b)| a == b) .map(|(_, b)| b) .collect::<String>(); // Check if we have found a shorter prefix if whitespace.len() < prefix.len() { prefix = whitespace; } } // We now go over the lines a second time to build the result. let mut result = String::new(); for line in s.lines() { if line.starts_with(&prefix) && line.chars().any(|c| !c.is_whitespace()) { let (_, tail) = line.split_at(prefix.len()); result.push_str(tail); } result.push('\n'); } result } #[cfg(test)] mod tests { #[cfg(feature = "hyphenation")] extern crate hyphenation; use super::*; #[cfg(feature = "hyphenation")] use hyphenation::Language; /// Add newlines. Ensures that the final line in the vector also /// has a newline. fn add_nl(lines: &[&str]) -> String { lines.join("\n") + "\n" } #[test] fn no_wrap() { assert_eq!(wrap("foo", 10), vec!["foo"]); } #[test] fn simple() { assert_eq!(wrap("foo bar baz", 5), vec!["foo", "bar", "baz"]); } #[test] fn multi_word_on_line() { assert_eq!(wrap("foo bar baz", 10), vec!["foo bar", "baz"]); } #[test] fn long_word() { assert_eq!(wrap("foo", 0), vec!["f", "o", "o"]); } #[test] fn long_words() { assert_eq!(wrap("foo bar", 0), vec!["f", "o", "o", "b", "a", "r"]); } #[test] fn max_width() { assert_eq!(wrap("foo bar", usize::max_value()), vec!["foo bar"]); } #[test] fn leading_whitespace() { assert_eq!(wrap(" foo bar", 6), vec![" foo", "bar"]); } #[test] fn trailing_whitespace() { assert_eq!(wrap("foo bar ", 6), vec!["foo", "bar "]); } #[test] fn interior_whitespace() { assert_eq!(wrap("foo: bar baz", 10), vec!["foo: bar", "baz"]); } #[test] fn extra_whitespace_start_of_line() { // Whitespace is only significant inside a line. After a line // gets too long and is broken, the first word starts in // column zero and is not indented. The line before might end // up with trailing whitespace. assert_eq!(wrap("foo bar", 5), vec!["foo", "bar"]); } #[test] fn issue_99() { // We did not reset the in_whitespace flag correctly and did // not handle single-character words after a line break. assert_eq!( wrap("aaabbbccc x yyyzzzwww", 9), vec!["aaabbbccc", "x", "yyyzzzwww"] ); } #[test] fn issue_129() { // The dash is an em-dash which takes up four bytes. We used // to panic since we tried to index into the character. assert_eq!(wrap("x – x", 1), vec!["x", "–", "x"]); } #[test] fn wide_character_handling() { assert_eq!(wrap("Hello, World!", 15), vec!["Hello, World!"]); assert_eq!( wrap("Hello, World!", 15), vec!["Hello,", "World!"] ); } #[test] fn empty_input_not_indented() { let wrapper = Wrapper::new(10).initial_indent("!!!"); assert_eq!(wrapper.fill(""), ""); } #[test] fn indent_single_line() { let wrapper = Wrapper::new(10).initial_indent(">>>"); // No trailing space assert_eq!(wrapper.fill("foo"), ">>>foo"); } #[test] fn indent_multiple_lines() { let wrapper = Wrapper::new(6).initial_indent("* ").subsequent_indent(" "); assert_eq!(wrapper.wrap("foo bar baz"), vec!["* foo", " bar", " baz"]); } #[test] fn indent_break_words() { let wrapper = Wrapper::new(5).initial_indent("* ").subsequent_indent(" "); assert_eq!(wrapper.wrap("foobarbaz"), vec!["* foo", " bar", " baz"]); } #[test] fn hyphens() { assert_eq!(wrap("foo-bar", 5), vec!["foo-", "bar"]); } #[test] fn trailing_hyphen() { let wrapper = Wrapper::new(5).break_words(false); assert_eq!(wrapper.wrap("foobar-"), vec!["foobar-"]); } #[test] fn multiple_hyphens() { assert_eq!(wrap("foo-bar-baz", 5), vec!["foo-", "bar-", "baz"]); } #[test] fn hyphens_flag() { let wrapper = Wrapper::new(5).break_words(false); assert_eq!( wrapper.wrap("The --foo-bar flag."), vec!["The", "--foo-", "bar", "flag."] ); } #[test] fn repeated_hyphens() { let wrapper = Wrapper::new(4).break_words(false); assert_eq!(wrapper.wrap("foo--bar"), vec!["foo--bar"]); } #[test] fn hyphens_alphanumeric() { assert_eq!(wrap("Na2-CH4", 5), vec!["Na2-", "CH4"]); } #[test] fn hyphens_non_alphanumeric() { let wrapper = Wrapper::new(5).break_words(false); assert_eq!(wrapper.wrap("foo(-)bar"), vec!["foo(-)bar"]); } #[test] fn multiple_splits() { assert_eq!(wrap("foo-bar-baz", 9), vec!["foo-bar-", "baz"]); } #[test] fn forced_split() { let wrapper = Wrapper::new(5).break_words(false); assert_eq!(wrapper.wrap("foobar-baz"), vec!["foobar-", "baz"]); } #[test] fn no_hyphenation() { let wrapper = Wrapper::with_splitter(8, NoHyphenation); assert_eq!(wrapper.wrap("foo bar-baz"), vec!["foo", "bar-baz"]); } #[test] #[cfg(feature = "hyphenation")] fn auto_hyphenation() { let corpus = hyphenation::load(Language::English_US).unwrap(); let wrapper = Wrapper::new(10); assert_eq!( wrapper.wrap("Internationalization"), vec!["Internatio", "nalization"] ); let wrapper = Wrapper::with_splitter(10, corpus); assert_eq!( wrapper.wrap("Internationalization"), vec!["Interna-", "tionaliza-", "tion"] ); } #[test] #[cfg(feature = "hyphenation")] fn split_len_hyphenation() { // Test that hyphenation takes the width of the wihtespace // into account. let corpus = hyphenation::load(Language::English_US).unwrap(); let wrapper = Wrapper::with_splitter(15, corpus); assert_eq!( wrapper.wrap("garbage collection"), vec!["garbage col-", "lection"] ); } #[test] #[cfg(feature = "hyphenation")] fn borrowed_lines() { // Lines that end with an extra hyphen are owned, the final // line is borrowed. use std::borrow::Cow::{Borrowed, Owned}; let corpus = hyphenation::load(Language::English_US).unwrap(); let wrapper = Wrapper::with_splitter(10, corpus); let lines = wrapper.wrap("Internationalization"); if let Borrowed(s) = lines[0] { assert!(false, "should not have been borrowed: {:?}", s); } if let Borrowed(s) = lines[1] { assert!(false, "should not have been borrowed: {:?}", s); } if let Owned(ref s) = lines[2] { assert!(false, "should not have been owned: {:?}", s); } } #[test] #[cfg(feature = "hyphenation")] fn auto_hyphenation_with_hyphen() { let corpus = hyphenation::load(Language::English_US).unwrap(); let wrapper = Wrapper::new(8).break_words(false); assert_eq!(wrapper.wrap("over-caffinated"), vec!["over-", "caffinated"]); let wrapper = Wrapper::with_splitter(8, corpus).break_words(false); assert_eq!( wrapper.wrap("over-caffinated"), vec!["over-", "caffi-", "nated"] ); } #[test] fn break_words() { assert_eq!(wrap("foobarbaz", 3), vec!["foo", "bar", "baz"]); } #[test] fn break_words_wide_characters() { assert_eq!(wrap("Hello", 5), vec!["He", "ll", "o"]); } #[test] fn break_words_zero_width() { assert_eq!(wrap("foobar", 0), vec!["f", "o", "o", "b", "a", "r"]); } #[test] fn break_words_line_breaks() { assert_eq!(fill("ab\ncdefghijkl", 5), "ab\ncdefg\nhijkl"); assert_eq!(fill("abcdefgh\nijkl", 5), "abcde\nfgh\nijkl"); } #[test] fn preserve_line_breaks() { assert_eq!(fill("test\n", 11), "test\n"); assert_eq!(fill("test\n\na\n\n", 11), "test\n\na\n\n"); assert_eq!(fill("1 3 5 7\n1 3 5 7", 7), "1 3 5 7\n1 3 5 7"); } #[test] fn wrap_preserve_line_breaks() { assert_eq!(fill("1 3 5 7\n1 3 5 7", 5), "1 3 5\n7\n1 3 5\n7"); } #[test] fn non_breaking_space() { let wrapper = Wrapper::new(5).break_words(false); assert_eq!(wrapper.fill("foo bar baz"), "foo bar baz"); } #[test] fn non_breaking_hyphen() { let wrapper = Wrapper::new(5).break_words(false); assert_eq!(wrapper.fill("foo‑bar‑baz"), "foo‑bar‑baz"); } #[test] fn fill_simple() { assert_eq!(fill("foo bar baz", 10), "foo bar\nbaz"); } #[test] fn indent_empty() { assert_eq!(indent("\n", " "), "\n"); } #[test] #[cfg_attr(rustfmt, rustfmt_skip)] fn indent_nonempty() { let x = vec![" foo", "bar", " baz"]; let y = vec!["// foo", "//bar", "// baz"]; assert_eq!(indent(&add_nl(&x), "//"), add_nl(&y)); } #[test] #[cfg_attr(rustfmt, rustfmt_skip)] fn indent_empty_line() { let x = vec![" foo", "bar", "", " baz"]; let y = vec!["// foo", "//bar", "", "// baz"]; assert_eq!(indent(&add_nl(&x), "//"), add_nl(&y)); } #[test] fn dedent_empty() { assert_eq!(dedent(""), ""); } #[test] #[cfg_attr(rustfmt, rustfmt_skip)] fn dedent_multi_line() { let x = vec![" foo", " bar", " baz"]; let y = vec![" foo", "bar", " baz"]; assert_eq!(dedent(&add_nl(&x)), add_nl(&y)); } #[test] #[cfg_attr(rustfmt, rustfmt_skip)] fn dedent_empty_line() { let x = vec![" foo", " bar", " ", " baz"]; let y = vec![" foo", "bar", "", " baz"]; assert_eq!(dedent(&add_nl(&x)), add_nl(&y)); } #[test] #[cfg_attr(rustfmt, rustfmt_skip)] fn dedent_mixed_whitespace() { let x = vec!["\tfoo", " bar"]; let y = vec!["\tfoo", " bar"]; assert_eq!(dedent(&add_nl(&x)), add_nl(&y)); } }