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
//! A library for the handling and analysis of Japanese text, particularly //! Kanji. It can be used to find the density of Kanji in given texts according //! to their *Level* classification, as defined by the Japan Kanji Aptitude //! Testing Foundation (日本漢字能力検定協会). //! //! The Kanji data presented here matches the Foundation's official 2020 //! February charts. Note that [some Kanji had their levels changed][changed] //! (pdf) as of 2020. //! //! # Usage //! //! Two main useful types are [`Character`] and [`Kanji`]. //! //! ### Reading Japanese Text //! //! To reinterpret every `char` of the input into a [`Character`] we can reason //! about: //! //! ``` //! use std::fs; //! use kanji::Character; //! //! let cs: Option<Vec<Character>> = fs::read_to_string("your-text.txt") //! .map(|content| content.chars().map(Character::new).collect()) //! .ok(); //! ``` //! //! But maybe we're just interested in the [`Kanji`]: //! //! ``` //! use std::fs; //! use kanji::Kanji; //! //! let ks: Option<Vec<Kanji>> = fs::read_to_string("your-text.txt") //! .map(|content| content.chars().filter_map(Kanji::new).collect()) //! .ok(); //! ``` //! //! Alongside normal pattern matching, the [`Character::kanji`] method can also //! help us extract [`Kanji`] values. //! //! ### Filtering //! //! In general, when we want to reduce a text to a single [`Character`] subtype, //! we can `filter`: //! //! ``` //! let orig = "そこで犬が寝ている"; //! //! let ks: String = orig.chars().filter(kanji::is_kanji).collect(); //! assert_eq!("犬寝", ks); //! //! let hs: String = orig.chars().filter(kanji::is_hiragana).collect(); //! assert_eq!("そこでがている", hs); //! ``` //! //! ### Level Analysis //! //! To find out how many Kanji of each exam level belong to some text: //! //! ``` //! let level_table = kanji::level_table(); //! let texts = vec![ //! "非常に面白い文章", //! "誰でも読んだ事のある名作", //! "飛行機で空を飛ぶ", //! ]; //! //! for t in texts { //! let counts = kanji::kanji_counts(t, &level_table); //! println!("{:#?}", counts); //! } //! ``` //! //! And if you want to know *what* the Kanji were from a particular level: //! //! ``` //! let level_table = kanji::level_table(); //! let text = "日常生活では、鮫に遭う事は基本的にない。"; //! //! let ks: String = text //! .chars() //! // Filter out all chars that aren't Kanji. //! .filter_map(kanji::Kanji::new) //! // Preserve only those that appear in Level 10. //! .filter_map(|k| match level_table.get(&k) { //! Some(kanji::Level::Ten) => Some(k.get()), //! _ => None, //! }) //! // Fold them all back into a String. //! .collect(); //! //! assert_eq!("日生本", ks); //! ``` //! //! # Notes on Unicode //! //! All Japanese characters, Kanji or otherwise, are a single Unicode Scalar //! Value, and thus can be safely represented by a single internal `char`. //! //! Further, the ordering of Kanji in the official Foundation lists is in no way //! related to their ordering in Unicode, since in Unicode, Kanji are grouped by //! radical. So: //! //! ``` //! use kanji::exam_lists; //! //! let same_as_uni = exam_lists::LEVEL_10.chars().max() < exam_lists::LEVEL_09.chars().min(); //! assert!(!same_as_uni); //! ``` //! //! # Resources //! - [CJK Unicode Chart](https://www.unicode.org/charts/PDF/U4E00.pdf) (pdf) //! - [StackOverflow: Unicode Ranges for Japanese](https://stackoverflow.com/q/19899554/643684) //! - [級別漢字表](https://www.kanken.or.jp/kanken/outline/data/outline_degree_national_list20200217.pdf) (pdf) //! //! [changed]: https://www.kanken.or.jp/kanken/topics/data/alterclassofkanji2020.pdf //! [`Character`]: enum.Character.html //! [`Character::kanji`]: enum.Character.html#method.kanji //! [`Kanji`]: struct.Kanji.html #![doc(html_root_url = "https://docs.rs/kanji/1.0.0")] use std::char; use std::collections::HashMap; /// A complete list of all Kanji in every level of the exam. pub mod exam_lists; /// A single symbol of Kanji, also known as a [CJK Unified Ideograph][cjk]. /// /// Japanese Kanji were borrowed from China over several waves during the last /// 1,500 years. Japan declares 2,136 of these as their standard set, with rarer /// characters being the domain of place names, academia and writers. /// /// Japanese has many Japan-only Kanji. Common ones include: /// /// - 畑 (a type of rice field) /// - 峠 (a narrow mountain pass) /// - 働 (to do physical labour) /// /// [cjk]: https://en.wikipedia.org/wiki/Han_unification #[derive(Debug, PartialEq, Eq, PartialOrd, Ord, Hash, Copy, Clone)] pub struct Kanji(char); impl Kanji { /// Attempt to form a `Kanji`. Will fail if the given `char` is out of the /// Unicode range that Japanese text inhabits. /// /// ``` /// use kanji::Kanji; /// /// assert_eq!(Some('志'), Kanji::new('志').map(|k| k.get())); /// assert_eq!(None, Kanji::new('a')); /// ``` pub fn new(c: char) -> Option<Kanji> { if is_kanji(&c) { Some(Kanji(c)) } else { None } } /// Pull out the inner `char`. pub fn get(&self) -> char { self.0 } } /// A Hiragana character, from あ to ん. /// /// These are learned first by Japanese school children and foreign learners, /// and are used most often for grammatical word endings and prepositions. Some /// women's first names are written purely in Hiragana, as the characters /// themselves have a soft, flowing feel to them (very much unlike the blocky, /// angular [`Katakana`](struct.Katakana.html)). #[derive(Debug, PartialEq, Eq, PartialOrd, Ord, Hash, Copy, Clone)] pub struct Hiragana(char); impl Hiragana { /// Attempt to form a `Hiragana`. Will fail if the given `char` is out of /// the expected Unicode range. /// /// ``` /// use kanji::Hiragana; /// /// assert_eq!(Some('あ'), Hiragana::new('あ').map(|k| k.get())); /// assert_eq!(None, Hiragana::new('鼠')); /// assert_eq!(None, Hiragana::new('a')); /// ``` pub fn new(c: char) -> Option<Hiragana> { if is_hiragana(&c) { Some(Hiragana(c)) } else { None } } /// Pull out the inner `char`. pub fn get(&self) -> char { self.0 } } /// A Katakana character, from ア to ン. /// /// These are typically learned after [`Hiragana`](struct.Hiragana.html), and /// are used to represent foreign names, sound effects, and occasionally words /// whose Kanji are "difficult". Two such examples are ネズミ (鼠) and アリ (蟻). /// /// It used to be common to use Katakana as Hiragana are used today, so the /// phrase君と街を歩きたい would have been written 君ト街ヲ歩キタイ. Admittedly /// strange to modern eyes! #[derive(Debug, PartialEq, Eq, PartialOrd, Ord, Hash, Copy, Clone)] pub struct Katakana(char); impl Katakana { /// Attempt to form a `Katakana`. Will fail if the given `char` is out of /// the expected Unicode range. /// /// ``` /// use kanji::Katakana; /// /// assert_eq!(Some('ア'), Katakana::new('ア').map(|k| k.get())); /// assert_eq!(None, Katakana::new('匙')); /// assert_eq!(None, Katakana::new('a')); /// ``` pub fn new(c: char) -> Option<Katakana> { if is_katakana(&c) { Some(Katakana(c)) } else { None } } /// Pull out the inner `char`. pub fn get(&self) -> char { self.0 } } /// Japanese symbols and punctuation. #[derive(Debug, PartialEq, Eq, PartialOrd, Ord, Hash, Copy, Clone)] pub struct Punctuation(char); impl Punctuation { /// Attempt to form a `Punctuation`. Will fail if the given `char` is out of /// the expected Unicode range. /// /// ``` /// use kanji::Punctuation; /// /// assert_eq!(Some('。'), Punctuation::new('。').map(|k| k.get())); /// assert_eq!(None, Punctuation::new('a')); /// ``` pub fn new(c: char) -> Option<Punctuation> { if is_japanese_punct(&c) { Some(Punctuation(c)) } else { None } } /// Pull out the inner `char`. pub fn get(&self) -> char { self.0 } } /// Japanese full-width alphanumeric characters and a few punctuation symbols. #[derive(Debug, PartialEq, Eq, PartialOrd, Ord, Hash, Copy, Clone)] pub struct AlphaNum(char); impl AlphaNum { /// Attempt to form a `AlphaNum`. Will fail if the given `char` is out of /// the expected Unicode range. /// /// ``` /// use kanji::AlphaNum; /// /// assert_eq!(Some('A'), AlphaNum::new('A').map(|k| k.get())); /// assert_eq!(Some('*'), AlphaNum::new('*').map(|k| k.get())); /// assert_eq!(None, AlphaNum::new('a')); /// ``` pub fn new(c: char) -> Option<AlphaNum> { if is_alphanum(&c) { Some(AlphaNum(c)) } else { None } } /// Pull out the inner `char`. pub fn get(&self) -> char { self.0 } } /// A standard ASCII character. #[derive(Debug, PartialEq, Eq, PartialOrd, Ord, Hash, Copy, Clone)] pub struct ASCII(char); impl ASCII { /// Attempt to form a `ASCII`. Will fail if the given `char` is out of /// the expected Unicode range. /// /// ``` /// use kanji::ASCII; /// /// assert_eq!(Some('a'), ASCII::new('a').map(|k| k.get())); /// assert_eq!(None, ASCII::new('あ')); /// ``` pub fn new(c: char) -> Option<ASCII> { if char::is_ascii(&c) { Some(ASCII(c)) } else { None } } /// Pull out the inner `char`. pub fn get(&self) -> char { self.0 } } /// General categories for characters, at least as is useful for thinking about /// Japanese. /// /// Japanese "full-width" numbers and letters are counted as `AlphaNum`, whereas /// "normal" ASCII characters have the `ASCII` variant. #[derive(Debug, PartialEq, Eq, PartialOrd, Ord, Hash, Copy, Clone)] pub enum Character { Kanji(Kanji), Hiragana(Hiragana), Katakana(Katakana), Punctuation(Punctuation), AlphaNum(AlphaNum), ASCII(ASCII), Other(char), } impl Character { /// Form a new `Character` from some `char`. pub fn new(c: char) -> Character { Kanji::new(c) .map(Character::Kanji) .or(Hiragana::new(c).map(Character::Hiragana)) .or(Katakana::new(c).map(Character::Katakana)) .or(Punctuation::new(c).map(Character::Punctuation)) .or(AlphaNum::new(c).map(Character::AlphaNum)) .or(ASCII::new(c).map(Character::ASCII)) .unwrap_or(Character::Other(c)) } /// A convenience method for attempting to extract a possible /// [`Kanji`](struct.Kanji.html). pub fn kanji(&self) -> Option<Kanji> { match self { Character::Kanji(k) => Some(*k), _ => None, } } } /// A level or "kyuu" (級) of Japanese Kanji ranking. /// /// There are 12 of these, /// from 10 to 1, including two "pre" levels between 3 and 2, and 2 and 1. /// /// Japanese students will typically have Level-5 ability by the time they /// finish elementary school. Level-5 accounts for 1,026 characters. By the end /// of middle school, they would have covered up to Level-3 (1,623 Kanji) in /// their Japanese class curriculum. /// /// While Level-2 (2,136 Kanji) is considered "standard adult" ability, many /// adults would not pass the Level-2, or even the Level-Pre2 exam without /// considerable study. It is not only the reading and writing of the characters /// themselves that is tested, but also their associated vocabularly, usage in /// real text, and appearance in classic Chinese idioms (四字熟語). #[derive(Debug, PartialEq, Eq, PartialOrd, Ord, Hash, Copy, Clone)] pub enum Level { Ten, Nine, Eight, Seven, Six, Five, Four, Three, PreTwo, Two, PreOne, One, } /// Kanji appear in the Unicode range 4e00 to 9ffc. /// The final Japanese Kanji is 9fef (鿯). /// /// For a chart of the full official range, see [this pdf] from the Unicode /// organization. /// /// A number of Level Pre-One Kanji appear in the [CJK Compatibility /// Ideographs][compat] list, so there is an extra check here for those. /// /// ``` /// assert!(kanji::is_kanji(&'澄')); // Obviously a legal Kanji. /// assert!(!kanji::is_kanji(&'a')); // Obviously not. /// ``` /// /// [compat]: https://www.unicode.org/charts/PDF/UF900.pdf /// [this pdf]: https://www.unicode.org/charts/PDF/U4E00.pdf pub fn is_kanji(c: &char) -> bool { (*c >= '\u{4e00}' && *c <= '\u{9ffc}') // Standard set. || (*c >= '\u{f900}' && *c <= '\u{faff}') // CJK Compatibility Ideographs. } /// Detect if a `char` is Kanji while accounting for all of the Unicode CJK /// extensions. /// /// [`is_kanji`](fn.is_kanji.html) should be enough for normal use. pub fn is_kanji_extended(c: &char) -> bool { (*c >= '\u{4e00}' && *c <= '\u{9ffc}') // Standard set. || (*c >= '\u{f900}' && *c <= '\u{faff}') // CJK Compatibility Ideographs. || (*c >= '\u{3400}' && *c <= '\u{4dbf}') // Extension A || (*c >= '\u{20000}' && *c <= '\u{2a6dd}') // Extension B || (*c >= '\u{2a700}' && *c <= '\u{2b734}') // Extension C || (*c >= '\u{2b740}' && *c <= '\u{2b81d}') // Extension D || (*c >= '\u{2b820}' && *c <= '\u{2cea1}') // Extension E || (*c >= '\u{2ceb0}' && *c <= '\u{2ebe0}') // Extension F || (*c >= '\u{30000}' && *c <= '\u{3134a}') // Extension G } /// Is a given `char` betwen あ and ん? /// /// ``` /// assert!(kanji::is_hiragana(&'あ')); /// assert!(!kanji::is_hiragana(&'a')); /// ``` pub fn is_hiragana(c: &char) -> bool { *c >= '\u{3041}' && *c <= '\u{309f}' } /// Is a given `char` between ア and ン? /// /// ``` /// assert!(kanji::is_katakana(&'ン')); /// assert!(!kanji::is_katakana(&'a')); /// ``` pub fn is_katakana(c: &char) -> bool { *c >= '\u{30a0}' && *c <= '\u{30ff}' } /// Does a given `char` belong to the set of Japanese symbols and punctuation? pub fn is_japanese_punct(c: &char) -> bool { *c >= '\u{3000}' && *c <= '\u{303f}' } /// Does a given `char` belong to the set of Japanese alphanumeric characters /// and western punctuation? pub fn is_alphanum(c: &char) -> bool { *c >= '\u{ff01}' && *c <= '\u{ff5e}' } /// All possible Kanji characters, as well as non-character radicals, in a /// heap-allocated UTF-8 `String`. /// /// ``` /// let ks = kanji::all_kanji(); /// /// assert_eq!(Some('一'), ks.chars().next()); /// assert_eq!(Some('\u{9ffc}'), ks.chars().last()); /// ``` pub fn all_kanji() -> String { let mut s = String::with_capacity(62967); // Capacity in bytes. (0x4e00..=0x9ffc) .filter_map(char::from_u32) .for_each(|c| s.push(c)); s } /// Using the data stored in the `LEVEL_*` constants, generate a lookup table /// for Kanji levels. pub fn level_table() -> HashMap<Kanji, Level> { let pairs = vec![ (exam_lists::LEVEL_10, Level::Ten), (exam_lists::LEVEL_09, Level::Nine), (exam_lists::LEVEL_08, Level::Eight), (exam_lists::LEVEL_07, Level::Seven), (exam_lists::LEVEL_06, Level::Six), (exam_lists::LEVEL_05, Level::Five), (exam_lists::LEVEL_04, Level::Four), (exam_lists::LEVEL_03, Level::Three), (exam_lists::LEVEL_02_PRE, Level::PreTwo), (exam_lists::LEVEL_02, Level::Two), (exam_lists::LEVEL_01, Level::One), // PreOne is added afterward to account for the 396 characters that // appear in both level One and PreOne. (exam_lists::LEVEL_01_PRE, Level::PreOne), ]; let mut hm = HashMap::new(); pairs.iter().for_each(|(c, l)| { c.chars().filter_map(Kanji::new).for_each(|k| { hm.insert(k, *l); }); }); hm } /// Determine how many Kanji of each exam level appear in some text, /// given a lookup table. /// /// The lookup table can be created via [`level_table`](fn.level_table.html). pub fn kanji_counts(s: &str, levels: &HashMap<Kanji, Level>) -> HashMap<Level, u32> { let mut counts: HashMap<Level, u32> = HashMap::new(); s.chars() .filter_map(Kanji::new) .filter_map(|k| levels.get(&k)) .for_each(|&l| { let counter = counts.entry(l).or_insert(0); *counter += 1; }); counts } #[cfg(test)] mod tests { use super::*; #[test] fn unicode_ranges() { let ks = all_kanji(); assert_eq!(20989, ks.chars().count()); assert_eq!(62967, ks.len()); // Bytes. } #[test] fn all_kanjiable() { assert!(exam_lists::LEVEL_10.chars().all(|c| is_kanji(&c))); assert!(exam_lists::LEVEL_09.chars().all(|c| is_kanji(&c))); assert!(exam_lists::LEVEL_08.chars().all(|c| is_kanji(&c))); assert!(exam_lists::LEVEL_07.chars().all(|c| is_kanji(&c))); assert!(exam_lists::LEVEL_06.chars().all(|c| is_kanji(&c))); assert!(exam_lists::LEVEL_05.chars().all(|c| is_kanji(&c))); assert!(exam_lists::LEVEL_04.chars().all(|c| is_kanji(&c))); assert!(exam_lists::LEVEL_03.chars().all(|c| is_kanji(&c))); assert!(exam_lists::LEVEL_02_PRE.chars().all(|c| is_kanji(&c))); assert!(exam_lists::LEVEL_02.chars().all(|c| is_kanji(&c))); assert!(exam_lists::LEVEL_01_PRE.chars().all(|c| is_kanji(&c))); assert!(exam_lists::LEVEL_01.chars().all(|c| is_kanji(&c))); } #[test] fn sane_overwrite() { let k = Kanji::new('氣').unwrap(); let m = level_table(); assert_eq!(Some(&Level::PreOne), m.get(&k)) } #[test] fn lookup_map_length() { let m = level_table(); assert_eq!(5906, m.len()); } }