arpabet-and-ipa-convertor-ts/dist/to-arpabet.js

Typescript code to convert between Arpabet and IPA phonetic transcriptions

"use strict";
Object.defineProperty(exports, "__esModule", { value: true });
exports.toArpabet = void 0;
var phonemes_1 = require("./phonemes");
var phoneme_error_1 = require("./phoneme-error");
var stress_1 = require("./model/stress");
var syllable_1 = require("./model/syllable");
var word_1 = require("./model/word");
/*
Stress and auxiliary symbols[3]
AB	Description
0	No stress
1	Primary stress
2	Secondary stress
3...	Tertiary and futher stress
-	Silence
!	Non-speech segment
+	Morpheme boundary
/	Word boundary
#	Utterance boundary
:	Tone group boundary
:1 or .	Falling or declining juncture
:2 or ?	Rising or internal juncture
:3 or .	Fall-rise or non-term juncture*/
var ConvertPriority;
(function (ConvertPriority) {
    ConvertPriority[ConvertPriority["American"] = 0] = "American";
    ConvertPriority[ConvertPriority["English"] = 1] = "English";
    ConvertPriority[ConvertPriority["IPA"] = 2] = "IPA";
})(ConvertPriority || (ConvertPriority = {}));
var ipaTree = {};
var kkTree = {};
var djTree = {};
phonemes_1.vowels.forEach(function (o) {
    ipaTree[o.ipa] = o;
    kkTree[o.american] = o;
    djTree[o.english] = o;
});
phonemes_1.consonants.forEach(function (o) {
    ipaTree[o.ipa] = o;
    kkTree[o.american] = o;
    djTree[o.english] = o;
});
var skip = [
    ["(", ")"],
    ["\uff08", "\uff09"],
];
var skipDict = {};
skip.forEach(function (skip) {
    skipDict[skip[0]] = skip[1];
});
var stressDict = {};
var primaryStressIpa = ["'", "\u02c8"];
primaryStressIpa.forEach(function (str) {
    stressDict[str] = stress_1.Stress.Primary;
});
var secondaryStressIpa = ["\u02cc"];
secondaryStressIpa.forEach(function (str) {
    stressDict[str] = stress_1.Stress.Secondary;
});
var ipaStops = [",", "-"];
function isStop(c) {
    return ipaStops.includes(c);
}
function findPhonemeInPhonemeTrees(phonemeString, phonemeTrees) {
    for (var _i = 0, phonemeTrees_1 = phonemeTrees; _i < phonemeTrees_1.length; _i++) {
        var phonemeTree = phonemeTrees_1[_i];
        var phoneme = phonemeTree[phonemeString];
        if (phoneme) {
            return phoneme;
        }
    }
    return null;
}
function createPhonemeTreesList(priority) {
    if ((ConvertPriority.American === priority)) {
        return [kkTree, ipaTree, djTree];
    }
    if ((ConvertPriority.English === priority)) {
        return [djTree, ipaTree, kkTree];
    }
    if ((ConvertPriority.IPA === priority)) {
        return [ipaTree, kkTree, djTree];
    }
    throw new Error('Priority not recognised');
}
function toArpabet(input, priority) {
    if (priority === void 0) { priority = ConvertPriority.American; }
    if ((!input)) {
        return null;
    }
    var tempCh = "";
    var skipStack = [];
    var phonemeTrees = createPhonemeTreesList(priority);
    var lastPhoneme = null;
    var word = new word_1.Word();
    var syllable = new syllable_1.Syllable();
    var tempSyllableStr = "";
    var chars = input.split('');
    chars.forEach(function (ch, index) {
        if (isStop(ch)) {
            return;
        }
        tempSyllableStr += ch;
        if (skipStack.length) {
            if ((ch === skipDict[skipStack.slice((-1))[0]])) {
                skipStack.pop();
            }
            return;
        }
        else {
            if (skipDict[ch]) {
                skipStack.push(ch);
                return;
            }
        }
        var stress = stressDict[ch];
        if (stress) {
            if (((!lastPhoneme) && (index > 0))) {
                // 存在不能识别的音标 ${temp_ch}
                throw new phoneme_error_1.PhonemeError("There is an unrecognized phonetic transcription " + tempCh);
            }
            else {
                /*
                遇到重音标识，说明前面是是一个音节，添加到word中，并清空last_phoneme及temp_ch
                */
                if (lastPhoneme) {
                    syllable.addPhoneme(lastPhoneme);
                    if ((!syllable.haveVowel)) {
                        // ${tempSyllableStr} 重音标识不合适，${ch}前一个音节没有元音！
                        throw new phoneme_error_1.PhonemeError(tempSyllableStr + " The accent mark is inappropriate, and the previous syllable of " + ch + " has no vowels!");
                    }
                    word.addSyllable(syllable);
                    syllable = new syllable_1.Syllable();
                }
                lastPhoneme = null;
                tempCh = "";
                tempSyllableStr = ch;
                syllable.stress = stress;
                return;
            }
        }
        tempCh += ch;
        var tempPhoneme = findPhonemeInPhonemeTrees(tempCh, phonemeTrees);
        if ((lastPhoneme && (!tempPhoneme))) {
            /*
            说明前面是是一个完整音标
            */
            syllable.addPhoneme(lastPhoneme);
            if (lastPhoneme.isVowel) {
                word.addSyllable(syllable);
                syllable = new syllable_1.Syllable();
                tempSyllableStr = ch;
            }
            tempCh = ch;
            lastPhoneme = findPhonemeInPhonemeTrees(tempCh, phonemeTrees);
        }
        else {
            lastPhoneme = tempPhoneme;
        }
    });
    if (lastPhoneme) {
        syllable.addPhoneme(lastPhoneme);
        if ((syllable.stress && (!syllable.haveVowel))) {
            // ${tempSyllableStr} 有重音标识但并没有元音！
            throw new phoneme_error_1.PhonemeError(tempSyllableStr + " has accent marks but no vowels!");
        }
        word.addSyllable(syllable);
    }
    else {
        // 存在不能识别的音标 ${temp_ch}
        throw new phoneme_error_1.PhonemeError("There is an unrecognized phonetic transcription " + tempCh);
    }
    return word.toArpabet();
}
exports.toArpabet = toArpabet;