NovaSonic/backend/lib/romaji.js

const path        = require('path');
const { createHash } = require('crypto');

// ─── KUROMOJI TOKENIZER ───────────────────────────────────────────────────────
let _tokenizer = null;
try {
  const kuromoji = require('kuromoji');
  const dicPath  = path.join(path.dirname(require.resolve('kuromoji')), '..', 'dict');
  kuromoji.builder({ dicPath })
    .build((err, t) => {
      if (err) console.warn('⚠️  kuromoji failed to load:', err.message);
      else     { _tokenizer = t; console.log('✅ kuromoji tokenizer ready'); }
    });
} catch { console.warn('⚠️  kuromoji not installed — run: cd backend && npm install'); }

// ─── CONVERSION HELPERS ───────────────────────────────────────────────────────

function _kataToHira(s) { return s.replace(/[ァ-ヶ]/g, c => String.fromCharCode(c.charCodeAt(0) - 0x60)); }

const _H2R = {
  'あ':'a','い':'i','う':'u','え':'e','お':'o',
  'か':'ka','き':'ki','く':'ku','け':'ke','こ':'ko',
  'さ':'sa','し':'shi','す':'su','せ':'se','そ':'so',
  'た':'ta','ち':'chi','つ':'tsu','て':'te','と':'to',
  'な':'na','に':'ni','ぬ':'nu','ね':'ne','の':'no',
  'は':'ha','ひ':'hi','ふ':'fu','へ':'he','ほ':'ho',
  'ま':'ma','み':'mi','む':'mu','め':'me','も':'mo',
  'や':'ya','ゆ':'yu','よ':'yo',
  'ら':'ra','り':'ri','る':'ru','れ':'re','ろ':'ro',
  'わ':'wa','を':'wo','ん':'n',
  'が':'ga','ぎ':'gi','ぐ':'gu','げ':'ge','ご':'go',
  'ざ':'za','じ':'ji','ず':'zu','ぜ':'ze','ぞ':'zo',
  'だ':'da','ぢ':'di','づ':'du','で':'de','ど':'do',
  'ば':'ba','び':'bi','ぶ':'bu','べ':'be','ぼ':'bo',
  'ぱ':'pa','ぴ':'pi','ぷ':'pu','ぺ':'pe','ぽ':'po',
  'きゃ':'kya','きゅ':'kyu','きょ':'kyo',
  'しゃ':'sha','しゅ':'shu','しょ':'sho',
  'ちゃ':'cha','ちゅ':'chu','ちょ':'cho',
  'にゃ':'nya','にゅ':'nyu','にょ':'nyo',
  'ひゃ':'hya','ひゅ':'hyu','ひょ':'hyo',
  'みゃ':'mya','みゅ':'myu','みょ':'myo',
  'りゃ':'rya','りゅ':'ryu','りょ':'ryo',
  'ぎゃ':'gya','ぎゅ':'gyu','ぎょ':'gyo',
  'じゃ':'ja','じゅ':'ju','じょ':'jo',
  'びゃ':'bya','びゅ':'byu','びょ':'byo',
  'ぴゃ':'pya','ぴゅ':'pyu','ぴょ':'pyo',
  'ふぁ':'fa','ふぃ':'fi','ふぇ':'fe','ふぉ':'fo',
  'てぃ':'ti','でぃ':'di','とぅ':'tu','どぅ':'du',
  'ゐ':'i','ゑ':'e','ヴ':'vu',
};

function _hiraToRomaji(str) {
  let out = '', i = 0;
  while (i < str.length) {
    if (str[i] === 'っ') {
      const nxt = _H2R[str.slice(i+1,i+3)] || _H2R[str[i+1]] || '';
      out += nxt[0] || ''; i++; continue;
    }
    const two = _H2R[str.slice(i,i+2)];
    if (two) { out += two; i += 2; continue; }
    out += _H2R[str[i]] ?? str[i]; i++;
  }
  return out;
}

const JP_RE = /[぀-ヿ㐀-䶿一-鿿＀-￯]/;

const KATA_RE = /[ァ-ヶ]/;

function toRomaji(text) {
  if (!text || !_tokenizer || !JP_RE.test(text)) return text || '';
  const tokens = _tokenizer.tokenize(text);
  const hira = tokens.map(t => {
    const r = t.reading;
    if (r && r !== '*') return _kataToHira(r);
    if (KATA_RE.test(t.surface_form)) return _kataToHira(t.surface_form); // katakana proper noun
    return t.surface_form;
  }).join('');
  return _hiraToRomaji(hira).toLowerCase();
}

// Human-readable romaji for storage: spaces between words, Title Case, ASCII preserved as-is.
function romajiForStorage(text) {
  if (!text || !_tokenizer || !JP_RE.test(text)) return text || '';
  const tokens = _tokenizer.tokenize(text);
  const parts = tokens.map(t => {
    const r = t.reading;
    if (!r || r === '*') {
      if (KATA_RE.test(t.surface_form)) return _hiraToRomaji(_kataToHira(t.surface_form)); // katakana proper noun
      return t.surface_form; // ASCII — keep original
    }
    return _hiraToRomaji(_kataToHira(r));        // Japanese — convert (lowercase)
  });
  // Add space between adjacent alphabetic segments (word separation for names/titles)
  const joined = parts.reduce((acc, part, i) => {
    if (i === 0) return part;
    const needsSpace = /[a-zA-Z0-9]$/.test(parts[i - 1]) && /^[a-zA-Z]/.test(part);
    return acc + (needsSpace ? ' ' : '') + part;
  }, '');
  // Clean up Japanese punctuation that passes through as-is
  const cleaned = joined
    .replace(/[、。]/g, ' ')        // Japanese comma/period → space
    .replace(/[・･]/g, ' ')        // middle dot → space
    .replace(/[「」『』【】〔〕〈〉《》]/g, '') // Japanese brackets → remove
    .replace(/（/g, '(').replace(/）/g, ')');  // fullwidth parens → ASCII
  // Title-case: capitalize first lowercase letter of each word, preserve existing uppercase
  return cleaned.replace(/\b([a-z])/g, c => c.toUpperCase()).replace(/\s+/g, ' ').trim();
}

// ─── INDEX BUILDER ────────────────────────────────────────────────────────────

const romajiCache = new Map();
const ROMAJI_TTL  = 20 * 60 * 1000; // 20 min

async function _fetchNdSongs(ndUrl, user, pass) {
  const salt  = Math.random().toString(36).slice(2, 10);
  const token = createHash('md5').update(pass + salt).digest('hex');
  const base  = `${ndUrl}/rest/search3.view?u=${encodeURIComponent(user)}&t=${token}&s=${salt}&v=1.16.1&c=NovaSonic-Backend&f=json&albumCount=0&artistCount=0`;
  const songs = [];
  let offset = 0;
  while (true) {
    const r    = await fetch(`${base}&query=&songCount=500&songOffset=${offset}`).then(r => r.json());
    const page = r['subsonic-response']?.searchResult3?.song || [];
    songs.push(...page);
    if (page.length < 500) break;
    offset += 500;
  }
  return songs;
}

async function buildRomajiIndex(ndUrl, user, pass) {
  const key    = `${ndUrl}|${user}`;
  const cached = romajiCache.get(key);
  if (cached && Date.now() - cached.ts < ROMAJI_TTL) return { fromCache: true, index: cached.index };

  const songs = await _fetchNdSongs(ndUrl, user, pass);
  const index = songs
    .filter(s => JP_RE.test(s.title) || JP_RE.test(s.artist) || JP_RE.test(s.album))
    .map(s => ({
      id:           s.id,
      r:            [toRomaji(s.title), toRomaji(s.artist), toRomaji(s.album)].join(' '),
      title:        s.title,
      artist:       s.artist    || '',
      album:        s.album     || '',
      titleRomaji:  romajiForStorage(s.title)  || s.title,
      artistRomaji: romajiForStorage(s.artist) || s.artist || '',
      albumRomaji:  romajiForStorage(s.album)  || s.album  || '',
      coverArt:     s.coverArt  || '',
      duration:     s.duration  || 0,
      albumId:      s.albumId   || '',
      artistId:     s.artistId  || '',
    }));
  romajiCache.set(key, { ts: Date.now(), index });
  return { fromCache: false, index };
}

function clearRomajiCache() { romajiCache.clear(); }

function isTokenizerReady() { return !!_tokenizer; }

module.exports = { buildRomajiIndex, clearRomajiCache, isTokenizerReady, fetchNdSongs: _fetchNdSongs, romajiForStorage };