vChewing-macOS/Packages/vChewing_LangModelAssembly/Sources/LangModelAssembly/PinyinPhonaConverter.swift

124 lines
8.6 KiB
Swift
Raw Permalink Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

// (c) 2021 and onwards The vChewing Project (MIT-NTL License).
// ====================
// This code is released under the MIT license (SPDX-License-Identifier: MIT)
// ... with NTL restriction stating that:
// No trademark license is granted to use the trade names, trademarks, service
// marks, or product names of Contributor, except as required to fulfill notice
// requirements defined in MIT License.
import Foundation
// 使 LMAssembly Tekkon
private typealias LengthSortedDictionary = [Int: [String: String]]
private let mapHanyuPinyinToPhonabets: LengthSortedDictionary = {
let parsed = try? JSONDecoder().decode(LengthSortedDictionary.self, from: jsnHanyuPinyinToMPS.data(using: .utf8) ?? Data([]))
return parsed ?? [:]
}()
extension String {
mutating func convertToPhonabets(newToneOne: String = "") {
if isEmpty || contains("_") || !isNotPureAlphanumerical { return }
let lengths = mapHanyuPinyinToPhonabets.keys.sorted().reversed()
lengths.forEach { length in
mapHanyuPinyinToPhonabets[length]?.forEach { key, value in
self = replacingOccurrences(of: key, with: value)
}
}
self = replacingOccurrences(of: " ", with: newToneOne)
}
}
///
private extension String {
var isNotPureAlphanumerical: Bool {
let regex = ".*[^A-Za-z0-9].*"
let testString = NSPredicate(format: "SELF MATCHES %@", regex)
return testString.evaluate(with: self)
}
}
private let jsnHanyuPinyinToMPS = #"""
{
"1":{"1":" ","2":"ˊ","3":"ˇ","4":"ˋ","5":"˙","a":"","e":"","o":"","q":""},
"2":{"ai":"","an":"","ao":"","ba":"","bi":"","bo":"","bu":"",
"ca":"","ce":"","ci":"","cu":"","da":"","de":"","di":"",
"du":"","eh":"","ei":"","en":"","er":"","fa":"","fo":"",
"fu":"","ga":"","ge":"","gi":"","gu":"","ha":"","he":"",
"hu":"","ji":"","ju":"","ka":"","ke":"","ku":"","la":"",
"le":"","li":"","lo":"","lu":"","lv":"","ma":"","me":"",
"mi":"","mo":"","mu":"","na":"","ne":"","ni":"","nu":"",
"nv":"","ou":"","pa":"","pi":"","po":"","pu":"","qi":"",
"qu":"","re":"","ri":"","ru":"","sa":"","se":"","si":"",
"su":"","ta":"","te":"","ti":"","tu":"","wa":"","wo":"",
"wu":"","xi":"","xu":"","ya":"","ye":"","yi":"","yo":"",
"yu":"","za":"","ze":"","zi":"","zu":""},
"3":{"ang":"","bai":"","ban":"","bao":"","bei":"","ben":"",
"bie":"","bin":"","cai":"","can":"","cao":"","cei":"",
"cen":"","cha":"","che":"","chi":"","chu":"","cou":"",
"cui":"","cun":"","cuo":"","dai":"","dan":"","dao":"",
"dei":"","den":"","dia":"","die":"","diu":"","dou":"",
"dui":"","dun":"","duo":"","eng":"","fan":"","fei":"",
"fen":"","fou":"","gai":"","gan":"","gao":"","gei":"",
"gen":"","gin":"","gou":"","gua":"","gue":"","gui":"",
"gun":"","guo":"","hai":"","han":"","hao":"","hei":"",
"hen":"","hou":"","hua":"","hui":"","hun":"","huo":"",
"jia":"","jie":"","jin":"","jiu":"","jue":"",
"jun":"","kai":"","kan":"","kao":"","ken":"","kiu":"",
"kou":"","kua":"","kui":"","kun":"","kuo":"","lai":"",
"lan":"","lao":"","lei":"","lia":"","lie":"","lin":"",
"liu":"","lou":"","lun":"","luo":"","lve":"","mai":"",
"man":"","mao":"","mei":"","men":"","mie":"","min":"",
"miu":"","mou":"","nai":"","nan":"","nao":"","nei":"",
"nen":"","nie":"","nin":"","niu":"","nou":"","nui":"",
"nun":"","nuo":"","nve":"","pai":"","pan":"","pao":"",
"pei":"","pen":"","pia":"","pie":"","pin":"","pou":"",
"qia":"","qie":"","qin":"","qiu":"","que":"",
"qun":"","ran":"","rao":"","ren":"","rou":"","rui":"",
"run":"","ruo":"","sai":"","san":"","sao":"","sei":"",
"sen":"","sha":"","she":"","shi":"","shu":"","sou":"",
"sui":"","sun":"","suo":"","tai":"","tan":"","tao":"",
"tie":"","tou":"","tui":"","tun":"","tuo":"",
"wai":"","wan":"","wei":"","wen":"","xia":"","xie":"",
"xin":"","xiu":"","xue":"","xun":"","yai":"",
"yan":"","yao":"","yin":"","you":"","yue":"","yun":"",
"zai":"","zan":"","zao":"","zei":"","zen":"","zha":"",
"zhe":"","zhi":"","zhu":"","zou":"","zui":"","zun":"",
"zuo":""},
"4":{"bang":"","beng":"","bian":"","biao":"","bing":"",
"cang":"","ceng":"","chai":"","chan":"","chao":"","chen":"",
"chou":"","chua":"","chui":"","chun":"","chuo":"",
"cong":"","cuan":"","dang":"","deng":"","dian":"",
"diao":"","ding":"","dong":"","duan":"","fang":"",
"feng":"","fiao":"","fong":"","gang":"","geng":"",
"giao":"","gong":"","guai":"","guan":"","hang":"",
"heng":"","hong":"","huai":"","huan":"","jian":"",
"jiao":"","jing":"","juan":"","kang":"","keng":"",
"kong":"","kuai":"","kuan":"","lang":"","leng":"",
"lian":"","liao":"","ling":"","long":"","luan":"",
"lvan":"","mang":"","meng":"","mian":"","miao":"",
"ming":"","nang":"","neng":"","nian":"","niao":"",
"ning":"","nong":"","nuan":"","pang":"","peng":"",
"pian":"","piao":"","ping":"","qian":"","qiao":"",
"qing":"","quan":"","rang":"","reng":"","rong":"",
"ruan":"","sang":"","seng":"","shai":"","shan":"",
"shao":"","shei":"","shen":"","shou":"","shua":"",
"shui":"","shun":"","shuo":"","song":"","suan":"",
"tang":"","teng":"","tian":"","tiao":"","ting":"",
"tong":"","tuan":"","wang":"","weng":"","xian":"",
"xiao":"","xing":"","xuan":"","yang":"","ying":"",
"yong":"","yuan":"","zang":"","zeng":"","zhai":"",
"zhan":"","zhao":"","zhei":"","zhen":"","zhou":"",
"zhua":"","zhui":"","zhun":"","zhuo":"",
"zong":"","zuan":""},
"5":{"biang":"","chang":"","cheng":"","chong":"","chuai":"",
"chuan":"","duang":"","guang":"","huang":"","jiang":"",
"jiong":"","kiang":"","kuang":"","liang":"","niang":"",
"qiang":"","qiong":"","shang":"","sheng":"","shuai":"",
"shuan":"","xiang":"","xiong":"","zhang":"","zheng":"",
"zhong":"","zhuai":"","zhuan":""},
"6":{"chuang":"","shuang":"","zhuang":""}
}
"""#