UnicodeCJK.js.flow 4.4 KB
Newer Older
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
/**
 * Copyright (c) 2013-present, Facebook, Inc.
 *
 * This source code is licensed under the MIT license found in the
 * LICENSE file in the root directory of this source tree.
 *
 * @providesModule UnicodeCJK
 * @typechecks
 */

/**
 * Unicode algorithms for CJK (Chinese, Japanese, Korean) writing systems.
 *
 * Utilities for Hanzi/Kanji/Hanja logographs and Kanas (Katakana and Hiragana)
 * syllables.
 *
 * For Korean Hangul see module `UnicodeHangulKorean`.
 */
'use strict';
/**
 * Latin
 *
 * NOTE: The code assumes these sets include only BMP characters.
 */

const R_LATIN_ASCII = 'a-zA-Z';
const R_LATIN_FULLWIDTH = '\uFF21-\uFF3A\uFF41-\uFF5A';
const R_LATIN = R_LATIN_ASCII + R_LATIN_FULLWIDTH;
/**
 * Hiragana & Katakana
 *
 * NOTE: Some ranges include non-BMP characters. We do not support those ranges
 * for now.
 */

const R_HIRAGANA = '\u3040-\u309F';
const R_KATAKANA = '\u30A0-\u30FF';
const R_KATAKANA_PHONETIC = '\u31F0-\u31FF';
const R_KATAKANA_HALFWIDTH = '\uFF65-\uFF9F'; // var R_KANA_SUPPLEMENT     = '\U0001B000-\U0001B0FF';

const R_KATAKANA_ALL = R_KATAKANA + R_KATAKANA_PHONETIC + R_KATAKANA_HALFWIDTH;
const R_KANA = R_HIRAGANA + R_KATAKANA_ALL;
const I_HIRAGANA = [0x3040, 0x309F];
const I_KATAKANA = [0x30A0, 0x30FF];
const I_HIRAGANA_TO_KATAKANA = I_KATAKANA[0] - I_HIRAGANA[0];
/**
 * Hanzi/Kanji/Hanja
 *
 * NOTE: Some ranges include non-BMP characters. We do not support those ranges
 * for now.
 */

const R_IDEO_MAIN = '\u4E00-\u9FCF';
const R_IDEO_EXT_A = '\u3400-\u4DBF'; // var R_IDEO_EXT_B = '\U00020000-\U0002A6DF';
// var R_IDEO_EXT_C = '\U0002A700-\U0002B73F';
// var R_IDEO_EXT_D = '\U0002B740-\U0002B81F';

const R_IDEO = R_IDEO_MAIN + R_IDEO_EXT_A;
/**
 * Hangul
 */
// var R_HANGUL_JAMO           = '\u1100-\u11FF';
// var R_HANGUL_JAMO_EXT_A     = '\uA960-\uA97F';
// var R_HANGUL_JAMO_EXT_B     = '\uD7B0-\uD7FF';
// var R_HANGUL_COMPATIBILITY  = '\u3130-\u318F';
// var R_HANGUL_COMP_HALFWIDTH = '\uFFA0-\uFFDF';

const R_HANGUL_SYLLABLES = '\uAC00-\uD7AF';
/**
 * Globals
 */

const R_IDEO_OR_SYLL = R_IDEO + R_KANA + R_HANGUL_SYLLABLES;
let REGEX_IDEO = null;
let REGEX_KANA = null;
let REGEX_IDEO_OR_SYLL = null;
let REGEX_IS_KANA_WITH_TRAILING_LATIN = null;
/**
 * Whether the string includes any Katakana or Hiragana characters.
 *
 * @param {string} str
 * @return {boolean}
 */

function hasKana(str) {
  REGEX_KANA = REGEX_KANA || new RegExp('[' + R_KANA + ']');
  return REGEX_KANA.test(str);
}
/**
 * Whether the string includes any CJK Ideograph characters.
 *
 * @param {string} str
 * @return {boolean}
 */


function hasIdeograph(str) {
  REGEX_IDEO = REGEX_IDEO || new RegExp('[' + R_IDEO + ']');
  return REGEX_IDEO.test(str);
}
/**
 * Whether the string includes any CJK Ideograph or Syllable characters.
 *
 * @param {string} str
 * @return {boolean}
 */


function hasIdeoOrSyll(str) {
  REGEX_IDEO_OR_SYLL = REGEX_IDEO_OR_SYLL || new RegExp('[' + R_IDEO_OR_SYLL + ']');
  return REGEX_IDEO_OR_SYLL.test(str);
}
/**
 * @param {string} chr
 * @output {string}
 */


function charCodeToKatakana(chr) {
  const charCode = chr.charCodeAt(0);
  return String.fromCharCode(charCode < I_HIRAGANA[0] || charCode > I_HIRAGANA[1] ? charCode : charCode + I_HIRAGANA_TO_KATAKANA);
}
/**
 * Replace any Hiragana character with the matching Katakana
 *
 * @param {string} str
 * @output {string}
 */


function hiraganaToKatakana(str) {
  if (!hasKana(str)) {
    return str;
  }

  return str.split('').map(charCodeToKatakana).join('');
}
/**
 * Whether the string is exactly a sequence of Kana characters followed by one
 * Latin character.
 *
 * @param {string} str
 * @output {string}
 */


function isKanaWithTrailingLatin(str) {
  REGEX_IS_KANA_WITH_TRAILING_LATIN = REGEX_IS_KANA_WITH_TRAILING_LATIN || new RegExp('^' + '[' + R_KANA + ']+' + '[' + R_LATIN + ']' + '$');
  return REGEX_IS_KANA_WITH_TRAILING_LATIN.test(str);
}
/**
 * Drops the trailing Latin character from a string that is exactly a sequence
 * of Kana characters followed by one Latin character.
 *
 * @param {string} str
 * @output {string}
 */


function kanaRemoveTrailingLatin(str) {
  if (isKanaWithTrailingLatin(str)) {
    return str.substr(0, str.length - 1);
  }

  return str;
}

const UnicodeCJK = {
  hasKana: hasKana,
  hasIdeograph: hasIdeograph,
  hasIdeoOrSyll: hasIdeoOrSyll,
  hiraganaToKatakana: hiraganaToKatakana,
  isKanaWithTrailingLatin: isKanaWithTrailingLatin,
  kanaRemoveTrailingLatin: kanaRemoveTrailingLatin
};
module.exports = UnicodeCJK;