174 lines
4.5 KiB
JavaScript
174 lines
4.5 KiB
JavaScript
/**
|
|
* Copyright (c) 2013-present, Facebook, Inc.
|
|
* All rights reserved.
|
|
*
|
|
* This source code is licensed under the BSD-style license found in the
|
|
* LICENSE file in the root directory of this source tree. An additional grant
|
|
* of patent rights can be found in the PATENTS file in the same directory.
|
|
*
|
|
* @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.
|
|
*/
|
|
|
|
var R_LATIN_ASCII = 'a-zA-Z';
|
|
var R_LATIN_FULLWIDTH = '\uFF21-\uFF3A\uFF41-\uFF5A';
|
|
var 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.
|
|
*/
|
|
var R_HIRAGANA = '\u3040-\u309F';
|
|
var R_KATAKANA = '\u30A0-\u30FF';
|
|
var R_KATAKANA_PHONETIC = '\u31F0-\u31FF';
|
|
var R_KATAKANA_HALFWIDTH = '\uFF65-\uFF9F';
|
|
// var R_KANA_SUPPLEMENT = '\U0001B000-\U0001B0FF';
|
|
var R_KATAKANA_ALL = R_KATAKANA + R_KATAKANA_PHONETIC + R_KATAKANA_HALFWIDTH;
|
|
var R_KANA = R_HIRAGANA + R_KATAKANA_ALL;
|
|
|
|
var I_HIRAGANA = [0x3040, 0x309F];
|
|
var I_KATAKANA = [0x30A0, 0x30FF];
|
|
var 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.
|
|
*/
|
|
var R_IDEO_MAIN = '\u4E00-\u9FCF';
|
|
var 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';
|
|
var 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';
|
|
var R_HANGUL_SYLLABLES = '\uAC00-\uD7AF';
|
|
|
|
/**
|
|
* Globals
|
|
*/
|
|
var R_IDEO_OR_SYLL = R_IDEO + R_KANA + R_HANGUL_SYLLABLES;
|
|
|
|
var REGEX_IDEO = null;
|
|
var REGEX_KANA = null;
|
|
var REGEX_IDEO_OR_SYLL = null;
|
|
var 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) {
|
|
var 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;
|
|
}
|
|
|
|
var UnicodeCJK = {
|
|
hasKana: hasKana,
|
|
hasIdeograph: hasIdeograph,
|
|
hasIdeoOrSyll: hasIdeoOrSyll,
|
|
hiraganaToKatakana: hiraganaToKatakana,
|
|
isKanaWithTrailingLatin: isKanaWithTrailingLatin,
|
|
kanaRemoveTrailingLatin: kanaRemoveTrailingLatin
|
|
};
|
|
|
|
module.exports = UnicodeCJK; |