[FEAT] Update the database for the scores. And follow the new file format
This commit is contained in:
NADAL Jean-Baptiste
814
scripts/convert_final_v2.js
Normal file
814
scripts/convert_final_v2.js
Normal file
@@ -0,0 +1,814 @@
|
||||
#!/usr/bin/env node
|
||||
/**
|
||||
* Conversion finale avec gestion des instruments multiples (option A)
|
||||
* Format : instrument1_et_instrument2_ton_partie[_clef].pdf
|
||||
*/
|
||||
|
||||
const fs = require('fs');
|
||||
const path = require('path');
|
||||
|
||||
const scoresPath = process.argv[2] || path.join(__dirname, '..', 'legacy', 'Scores');
|
||||
const confirmed = process.argv[3] === 'confirm';
|
||||
|
||||
if (!fs.existsSync(scoresPath)) {
|
||||
console.error(`❌ Le dossier ${scoresPath} n'existe pas !`);
|
||||
process.exit(1);
|
||||
}
|
||||
|
||||
if (!confirmed) {
|
||||
console.log('Mode SIMULATION (ajoutez "confirm" pour exécuter)\n');
|
||||
}
|
||||
|
||||
const instruments = {
|
||||
'clarinet': 'clarinette', 'clarinette': 'clarinette', 'clarinettte': 'clarinette',
|
||||
'petite_clarinette': 'petite_clarinette', 'petite_clarineette': 'petite_clarinette', 'grande_clarinette': 'grande_clarinette', 'es_clarinette': 'petite_clarinette',
|
||||
'clarinette_alto': 'clarinette_alto', 'clarinet_alto': 'clarinette_alto', 'alto_clarinet': 'clarinette_alto', 'alto_clarinette': 'clarinette_alto',
|
||||
'clarinette_basse': 'clarinette_basse', 'clarinet_basse': 'clarinette_basse', 'clarinette_bass': 'clarinette_basse', 'basse_clarinet': 'clarinette_basse', 'bass_clarinet': 'clarinette_basse', 'bass_clarinette': 'clarinette_basse',
|
||||
'clarinette_basse': 'clarinette_basse', 'Bb_Clarinet_Bass': 'clarinette_basse', 'bb_clarinet_bass': 'clarinette_basse',
|
||||
'trumpet': 'trompette', 'trompette': 'trompette', 'trrumpet': 'trompette',
|
||||
'trombone': 'trombone',
|
||||
'tuba': 'tuba', 'tenor_tuba': 'tuba_tenor', 'tuba_tenor': 'tuba_tenor', 'contre_tuba': 'contre_tuba',
|
||||
'flute': 'flute', 'flauto': 'flute', 'grande_flute': 'grande_flute', 'petite_flute': 'petite_flute',
|
||||
'oboe': 'hautbois', 'hautbois': 'hautbois',
|
||||
'bassoon': 'basson', 'basson': 'basson',
|
||||
'contre_basson': 'contre_basson', 'contrebasson': 'contre_basson',
|
||||
'string_electric_bass': 'basse_electrique',
|
||||
'string': 'contrebasse', 'string_bass': 'contrebasse', 'contrebasse': 'contrebasse', 'contre_basse': 'contrebasse', 'contrabass': 'contrebasse',
|
||||
'doublebass': 'contrebasse', 'double_bass': 'contrebasse',
|
||||
'electric_bass': 'basse_electrique', 'electric_bass_guitar': 'basse_electrique', 'electric': 'electrique',
|
||||
'optional_electric_bass': 'basse_electrique', 'optional': '',
|
||||
'basse_a_cordes': 'basse_a_cordes',
|
||||
'guitar': 'guitare', 'electric_guitar': 'guitare_electrique',
|
||||
'cornet': 'cornet', 'bass': 'basse', 'basse': 'basse',
|
||||
'baritone': 'baryton', 'baryton': 'baryton', 'bariton': 'baryton', 'baritione': 'baryton', 'bartitone': 'baryton', 'tenorhorn': 'tenorhorn',
|
||||
'baryton_euphonium': 'baryton_et_euphonium', 'baritone_euphonium': 'baryton_et_euphonium',
|
||||
'horn': 'cor', 'french_horn': 'cor', 'frenchhorn': 'cor', 'corno': 'cor',
|
||||
'flugelhorn': 'bugle', 'flugel': 'bugle', 'flugel_horn': 'bugle', 'bugle': 'bugle', 'petit_bugle': 'petit_bugle', 'piccolo': 'piccolo',
|
||||
'euphonium': 'euphonium', 'euphononium': 'euphonium',
|
||||
'sax': 'saxophone', 'saxe': 'sax', 'saxophone': 'saxophone',
|
||||
'saxophone_tenor': 'sax_tenor', 'tenor_saxophone': 'sax_tenor', 'tenor_sax': 'sax_tenor',
|
||||
'saxophone_alto': 'sax_alto', 'alto_saxophone': 'sax_alto', 'alto_sax': 'sax_alto',
|
||||
'saxophone_basse': 'sax_basse', 'bass_saxophone': 'sax_basse', 'bass_sax': 'sax_basse',
|
||||
'bb_bass_saxophone': 'sax_basse', 'Bb_Bass_saxophone': 'sax_basse',
|
||||
'saxo': 'saxophone', 'saxo_alto': 'sax_alto', 'saxo_tenor': 'sax_tenor',
|
||||
'sax_soprano': 'sax_soprano', 'soprano_sax': 'sax_soprano', 'sax_alto': 'sax_alto', 'sax_tenor': 'sax_tenor', 'sax_baryton': 'sax_baryton',
|
||||
'saxbaryton': 'sax_baryton', 'saxalto': 'sax_alto', 'saxtenor': 'sax_tenor',
|
||||
'sax_bariton': 'sax_baryton', 'sax_baritone': 'sax_baryton',
|
||||
'bartitone_sax': 'sax_baryton', 'bartitone_saxophone': 'sax_baryton',
|
||||
'saxophone_baryton': 'sax_baryton', 'saxophone_baritone': 'sax_baryton', 'baritone_saxophone': 'sax_baryton', 'baritone_sax': 'sax_baryton',
|
||||
'saxe_baryton': 'sax_baryton', 'saxe_baritone': 'sax_baryton',
|
||||
'saxophone_basse': 'sax_basse', 'sax_basse': 'sax_basse',
|
||||
'bass_saxophone': 'sax_basse', 'bass_sax': 'sax_basse',
|
||||
'trombone_bass': 'trombone',
|
||||
'bass_saxophone': 'sax_basse', 'bass_sax': 'sax_basse',
|
||||
'saxophone_basse': 'sax_basse',
|
||||
'trombone_basse': 'trombone_basse', 'bass_trombone': 'trombone_basse', 'bas_trombone': 'trombone_basse',
|
||||
'trombone_a_piston': 'trombone',
|
||||
'bass_guitar': 'basse_electrique',
|
||||
'cornet_trumpet': 'cornet',
|
||||
'trumpet_cornet': 'cornet',
|
||||
'trumpet': 'trompette', 'trompette': 'trompette',
|
||||
'xylophone': 'xylophone', 'vibraphone': 'vibraphone',
|
||||
'glockenspiel': 'glockenspiel',
|
||||
'bass_saxophone': 'saxophone_basse', 'saxophone_basse': 'saxophone_basse',
|
||||
'bass_drum': 'grosse_caisse', 'grosse_caisse': 'grosse_caisse', 'grossecaisse': 'grosse_caisse',
|
||||
'tuba_basse': 'tuba',
|
||||
'bass_tuba': 'tuba',
|
||||
'maillet_percussion': 'malette_percussion', 'mallet_percussion': 'malette_percussion', 'malette_percussion': 'malette_percussion',
|
||||
'bombardon': 'bombardon',
|
||||
'percussion': 'percussion', 'drums': 'batterie', 'drum': 'batterie',
|
||||
'timbales': 'timbales', 'timbale': 'timbales',
|
||||
'cymbale': 'cymbale', 'cymbales': 'cymbale', 'cymbal': 'cymbale',
|
||||
'tambour': 'tambour', 'tambour_de_basque': 'tambour_de_basque', 'tom': 'tom', 'tom_grave': 'tom_grave',
|
||||
'triangle': 'triangle',
|
||||
'caisse_claire': 'caisse_claire', 'caisses_claires': 'caisse_claire', 'caisseclaire': 'caisse_claire',
|
||||
'timpani': 'timbales', 'timbales': 'timbales',
|
||||
'gong': 'gong', 'tam_tam': 'tam_tam', 'wind_chimes': 'carillon', 'windchimes': 'carillon', 'carillon_a_vent': 'carillon_a_vent',
|
||||
'woodblock': 'woodblock', 'claves': 'claves', 'batterie': 'batterie', 'maracas': 'maracas',
|
||||
'conducteur': 'conducteur', 'conducteur_bois': 'conducteur_bois', 'conducteur_cuivres': 'conducteur_cuivres', 'conducteur_cordes': 'conducteur_cordes',
|
||||
'chant': 'chant', 'en_attente': 'en_attente',
|
||||
};
|
||||
|
||||
const variantes = ['tenor', 'soprano', 'basse'];
|
||||
// Only unambiguous full names: sib, mib, fa, do (la is too ambiguous - matches "la" in titles)
|
||||
const tonalitesLong = { 'sib': 'sib', 'mib': 'mib', 'fa': 'fa', 'do': 'ut', 'ut': 'ut', 'sol': 'sol', 're': 're', 're_b': 'reb', 'mi': 'mi', 'si': 'si', 'en_sib': 'sib', 'en_mib': 'mib', 'en_fa': 'fa' };
|
||||
// Only unambiguous abbreviations: bb=bb, eb=eb, plus note letters when before instrument
|
||||
const tonalitesShort = { 'bb': 'sib', 'eb': 'mib', 'f': 'fa', 'c': 'ut' };
|
||||
const clefs = { 'clefsol': 'clesol', 'clesol': 'clesol', 'clefa': 'clefa', 'cle_ut': 'cle_ut', 'tc': 'tc' };
|
||||
|
||||
function removeAccents(str) {
|
||||
return str.normalize('NFD').replace(/[\u0300-\u036f]/g, '');
|
||||
}
|
||||
|
||||
function extractInstrument(parts) {
|
||||
for (let i = 0; i < parts.length; i++) {
|
||||
for (let len = 3; len >= 1; len--) {
|
||||
if (i + len <= parts.length) {
|
||||
const combined = parts.slice(i, i + len).join('_');
|
||||
if (instruments[combined]) {
|
||||
return { name: instruments[combined], endIndex: i + len };
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
return null;
|
||||
}
|
||||
|
||||
function normalizeFilename(filename, forcedPart = null) {
|
||||
let originalName = filename;
|
||||
let name = filename.replace(/\.pdf$/i, '');
|
||||
|
||||
// Remove "part_X_" prefix if present (not a real part number)
|
||||
name = name.replace(/^part_\d+_/i, '');
|
||||
|
||||
// Preprocessing: replace bugle_b, bugle_c to avoid being detected as tonalities
|
||||
// b = sib (si bémol), c = ut (do)
|
||||
let bugleTonalite = null;
|
||||
if (/bugle_b/i.test(name)) {
|
||||
bugleTonalite = 'sib';
|
||||
name = name.replace(/bugle_b/gi, 'BUGLETONALITY');
|
||||
} else if (/bugle_c/i.test(name)) {
|
||||
bugleTonalite = 'ut';
|
||||
name = name.replace(/bugle_c/gi, 'BUGLETONALITY');
|
||||
}
|
||||
|
||||
let voice = '';
|
||||
|
||||
// Extraire voix (A1, A2, B, C, etc.) AVANT extraction de partie
|
||||
// Pattern like _A1, _A2 at end - EXCEPT when part of "a_default/a_defaut" or when it's an instrument (cor, etc.)
|
||||
// ALSO skip if the letter is a tonality (c=C/ut, f=F/fa, etc.)
|
||||
const tonaliteLetters = ['c', 'f']; // Letters that are tonalities, not voices
|
||||
const voiceMatchOriginal = name.match(/_([A-Za-z])(\d+)$/);
|
||||
const instrumentLetters = ['cor', 'b', 'c']; // Letters that are also instrument names or bugle tonalities
|
||||
if (voiceMatchOriginal && !name.toLowerCase().includes('default') && !name.toLowerCase().includes('defaut') && !instrumentLetters.includes(voiceMatchOriginal[1].toLowerCase()) && !tonaliteLetters.includes(voiceMatchOriginal[1].toLowerCase())) {
|
||||
voice = voiceMatchOriginal[1].toLowerCase();
|
||||
name = name.replace(/_[A-Za-z]\d+$/, '_' + voiceMatchOriginal[2]);
|
||||
} else {
|
||||
// Pattern like _B at end (followed by & or nothing) - EXCEPT when part of "a_default/a_defaut" or when it's an instrument or tonality
|
||||
const voiceOnlyMatch = name.match(/_([A-Za-z])(?:&|_|$)/);
|
||||
if (voiceOnlyMatch && voiceOnlyMatch[1].length === 1 && !name.toLowerCase().includes('default') && !name.toLowerCase().includes('defaut') && !instrumentLetters.includes(voiceOnlyMatch[1].toLowerCase()) && !tonaliteLetters.includes(voiceOnlyMatch[1].toLowerCase())) {
|
||||
voice = voiceOnlyMatch[1].toLowerCase();
|
||||
name = name.replace(/_[A-Za-z](?:&|_|$)/, '');
|
||||
}
|
||||
}
|
||||
|
||||
// Detect & for multiple instruments (not for part numbers like 1&2)
|
||||
// Check if & appears between letters (instruments), not between digits
|
||||
// Can have underscores around & or not (like "Baritone_&_Tuba" or "Basse&Contrebasse")
|
||||
// More strict: & must be between actual words (not between a digit and a letter)
|
||||
const hasAmpersandBetweenInstruments = name.match(/[a-zA-Z]+[\s_-]*&[\s_-]*[a-zA-Z]+/);
|
||||
const hasAmpersand = !!hasAmpersandBetweenInstruments;
|
||||
|
||||
// Also check for multiple instruments without & (like "Bb_Baritone_1_Bb_Tenor_Tuba_1")
|
||||
// This is indicated by two different tonalities in the name
|
||||
// More strict: first tonality must be at start or after separator, second must be after some content
|
||||
const hasDualTonalitiesNoAmpersand = name.match(/^(Bb|Eb|F|Ut)_.+_(Bb|Eb|F|Ut)_/i);
|
||||
const hasDualInstrumentsNoAmpersand = !!hasDualTonalitiesNoAmpersand;
|
||||
|
||||
// Also check for & between digits (parts like 1&2, 2&3)
|
||||
const hasAmpersandBetweenDigits = name.match(/\d+&\d+/);
|
||||
|
||||
// Initialize segments - will be set in the segment processing block below
|
||||
let segments;
|
||||
|
||||
// Traiter les parties combinées (1&2, 3&4) - AVANT extraction de partie
|
||||
// Only for single instrument files (no & between instruments)
|
||||
let combinedPart = '';
|
||||
if (!hasAmpersand && hasAmpersandBetweenDigits) {
|
||||
const combinedMatch = name.match(/(\d+)&(\d+)/);
|
||||
if (combinedMatch) {
|
||||
combinedPart = `${combinedMatch[1]}_${combinedMatch[2]}`;
|
||||
name = name.replace(/\d+&\d+/, '');
|
||||
name = name.replace(/_+/g, '_').replace(/^_+|_+$/g, '');
|
||||
}
|
||||
}
|
||||
|
||||
// Extraire numéro de partie (milieu ou fin)
|
||||
// Si forcedPart est fourni (cas version_X), l'utiliser à la place
|
||||
let partie = forcedPart || '1';
|
||||
|
||||
// If filename starts with a number followed by underscore (like "1_Clarinette"),
|
||||
// this is likely a version/alternate prefix, NOT a part number. Strip it.
|
||||
if (!forcedPart && name.match(/^\d+_/)) {
|
||||
name = name.replace(/^\d+_/, '');
|
||||
}
|
||||
|
||||
// Remove "_page_X" patterns (file errors, not part numbers)
|
||||
if (!forcedPart && name.match(/_page_\d+/i)) {
|
||||
name = name.replace(/_page_\d+/gi, '');
|
||||
}
|
||||
|
||||
// Also remove patterns like _page_X (with different underscore patterns)
|
||||
if (!forcedPart && name.match(/_page\d+/i)) {
|
||||
name = name.replace(/_page\d+/gi, '');
|
||||
}
|
||||
|
||||
if (!forcedPart) {
|
||||
// Chercher d'abord un pattern _X_ au milieu (ex: Trombone_1_Sib)
|
||||
// But don't remove if what follows looks like a tonality (C, F, Bb, Eb, etc.)
|
||||
const middleMatch = name.match(/_(\d+)_([^_])/);
|
||||
if (middleMatch) {
|
||||
const potentialTonality = middleMatch[2].toLowerCase();
|
||||
// Check if this is a tonality abbreviation
|
||||
const isTonality = tonalitesLong[potentialTonality] || tonalitesShort[potentialTonality];
|
||||
if (!isTonality) {
|
||||
// Normal part, extract and remove
|
||||
partie = middleMatch[1];
|
||||
const regex = new RegExp('_' + partie + '_', 'g');
|
||||
name = name.replace(regex, '_');
|
||||
} else {
|
||||
// This is actually a tonality after the part number
|
||||
// Keep the tonality in the name for later extraction
|
||||
// But record the partie number
|
||||
partie = middleMatch[1];
|
||||
}
|
||||
} else {
|
||||
// Chercher à la fin
|
||||
const partieMatch = name.match(/_(\d+)$/);
|
||||
if ( partieMatch) {
|
||||
partie = partieMatch[1];
|
||||
name = name.slice(0, -partieMatch[0].length);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// "solo" = partie speciale - check for number after solo
|
||||
let soloPart = null;
|
||||
const soloMatch = name.toLowerCase().match(/solo[_\s]*(\d+)/i);
|
||||
if (soloMatch) {
|
||||
soloPart = 'solo_' + soloMatch[1];
|
||||
} else if (name.toLowerCase().includes('solo')) {
|
||||
soloPart = 'solo';
|
||||
}
|
||||
|
||||
// Détecter clef - only if not already handled as clefa/clesol part
|
||||
let clef = '';
|
||||
const lowerName = name.toLowerCase();
|
||||
if (!soloPart) {
|
||||
for (const [k, v] of Object.entries(clefs)) {
|
||||
if (lowerName.includes(k)) {
|
||||
clef = v;
|
||||
name = name.replace(new RegExp(k, 'gi'), '');
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Split into segments for multiple instruments
|
||||
// Case 1: has & between instruments
|
||||
// Case 2: has dual tonalities indicating multiple instruments (like "Bb_Baritone_1_Bb_Tenor_Tuba_1")
|
||||
if (hasAmpersand || hasDualInstrumentsNoAmpersand) {
|
||||
let rawSegments;
|
||||
if (hasAmpersand) {
|
||||
// Split by & but keep instrument groups together
|
||||
rawSegments = name.split(/&/).map(s => s.trim().replace(/^_+|_+$/g, '')).filter(s => s);
|
||||
} else {
|
||||
// Split by second tonality - find position of second tonality pattern
|
||||
// Look for pattern like _Bb_ or _Eb_ etc. after the first tonality
|
||||
const secondTonalityMatch = name.match(/[_-](Bb|Eb|F|Ut)[_-]/i);
|
||||
if (secondTonalityMatch) {
|
||||
const splitPos = secondTonalityMatch.index;
|
||||
const firstPart = name.substring(0, splitPos);
|
||||
const secondPart = name.substring(splitPos + 1);
|
||||
rawSegments = [firstPart, secondPart].map(s => s.trim().replace(/^_+|_+$/g, '')).filter(s => s);
|
||||
} else {
|
||||
rawSegments = [name];
|
||||
}
|
||||
}
|
||||
|
||||
// Process each segment to extract instrument-specific info
|
||||
segments = rawSegments;
|
||||
}
|
||||
|
||||
// Default segments if not set
|
||||
if (!segments) {
|
||||
segments = [name];
|
||||
}
|
||||
|
||||
// Extraire instruments de chaque segment
|
||||
const foundInstruments = [];
|
||||
const foundTonalites = [];
|
||||
const foundVariantes = [];
|
||||
const foundParties = [];
|
||||
let defaultInstrument = null;
|
||||
|
||||
// Extraire l'instrument qui suit "default" ou "defaut" (pour "a_default_cor" -> extraire "cor")
|
||||
// ET retire cette partie du nom pour éviter les doublons
|
||||
const defaultMatch = name.match(/_?a_?defaut(?:l)?_?([a-zA-Z]+)/i);
|
||||
if (defaultMatch) {
|
||||
const defaultInstr = defaultMatch[1].toLowerCase();
|
||||
const mappedInstr = instruments[defaultInstr];
|
||||
defaultInstrument = mappedInstr || defaultInstr;
|
||||
// Retirer la partie "a_defaut_..." du nom pour éviter les doublons
|
||||
name = name.replace(/_?a_?defaut(?:l)?_?[a-zA-Z]+/i, '');
|
||||
}
|
||||
|
||||
for (const segment of segments) {
|
||||
const parts = segment.split('_').filter(p => p && p !== 'et');
|
||||
|
||||
// Chercher TOUS les instruments (pas juste le premier)
|
||||
const seenInstruments = new Set();
|
||||
const usedIndices = new Set();
|
||||
|
||||
// First pass: check 3-word combinations
|
||||
for (let i = 0; i < parts.length; i++) {
|
||||
if (usedIndices.has(i)) continue;
|
||||
if (i + 3 <= parts.length) {
|
||||
const combined3 = parts.slice(i, i + 3).join('_').toLowerCase();
|
||||
if (instruments[combined3]) {
|
||||
foundInstruments.push(instruments[combined3]);
|
||||
seenInstruments.add(instruments[combined3]);
|
||||
usedIndices.add(i); usedIndices.add(i+1); usedIndices.add(i+2);
|
||||
}
|
||||
}
|
||||
}
|
||||
// Second pass: check 2-word combinations
|
||||
for (let i = 0; i < parts.length; i++) {
|
||||
if (usedIndices.has(i)) continue;
|
||||
if (i + 2 <= parts.length) {
|
||||
const combined2 = parts.slice(i, i + 2).join('_').toLowerCase();
|
||||
if (instruments[combined2]) {
|
||||
foundInstruments.push(instruments[combined2]);
|
||||
seenInstruments.add(instruments[combined2]);
|
||||
usedIndices.add(i); usedIndices.add(i+1);
|
||||
}
|
||||
}
|
||||
}
|
||||
// Third pass: check single words
|
||||
for (let i = 0; i < parts.length; i++) {
|
||||
if (usedIndices.has(i)) continue;
|
||||
const lowerPart = parts[i].toLowerCase();
|
||||
if (instruments[lowerPart]) {
|
||||
foundInstruments.push(instruments[lowerPart]);
|
||||
seenInstruments.add(instruments[lowerPart]);
|
||||
}
|
||||
}
|
||||
|
||||
// Chercher tonalité - prioritize full names (sib, mib, fa), then abbreviations only at start
|
||||
for (let i = 0; i < parts.length; i++) {
|
||||
const part = parts[i];
|
||||
const lowerPart = part.toLowerCase();
|
||||
|
||||
// First check for explicit full tonality names (exact match, any position)
|
||||
let found = false;
|
||||
for (const [key, val] of Object.entries(tonalitesLong)) {
|
||||
if (lowerPart === key) {
|
||||
// Only allow duplicates for multi-instrument files
|
||||
if (foundInstruments.length >= 2 || !foundTonalites.includes(val)) {
|
||||
foundTonalites.push(val);
|
||||
}
|
||||
found = true;
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
// Check abbreviations - only if not already found AND avoid duplicates with long forms
|
||||
if (!found) {
|
||||
for (const [key, val] of Object.entries(tonalitesShort)) {
|
||||
if (lowerPart === key) {
|
||||
// Only allow duplicates for multi-instrument files
|
||||
if (foundInstruments.length >= 2 || !foundTonalites.includes(val)) {
|
||||
foundTonalites.push(val);
|
||||
}
|
||||
found = true;
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Also check for tonality + number combo (like F1, Bb2, Eb3)
|
||||
// This handles cases like "French_Horn_F1" where F1 is not split
|
||||
if (!found) {
|
||||
const tonalityWithNumber = part.match(/^([A-Za-z]+)(\d+)$/);
|
||||
if (tonalityWithNumber) {
|
||||
const tonality = tonalityWithNumber[1].toLowerCase();
|
||||
const num = tonalityWithNumber[2];
|
||||
// Check if the letter part is a tonality
|
||||
for (const [key, val] of Object.entries(tonalitesShort)) {
|
||||
if (tonality === key) {
|
||||
if (!foundTonalites.includes(val)) {
|
||||
foundTonalites.push(val);
|
||||
}
|
||||
// Also extract the part number
|
||||
if (!foundParties.includes(num)) {
|
||||
foundParties.push(num);
|
||||
}
|
||||
found = true;
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Extraire partie de ce segment
|
||||
for (const part of parts) {
|
||||
if (/^\d+$/.test(part)) {
|
||||
foundParties.push(part);
|
||||
}
|
||||
}
|
||||
|
||||
// Chercher variante
|
||||
for (const part of parts) {
|
||||
if (variantes.includes(part) && !foundVariantes.includes(part)) {
|
||||
foundVariantes.push(part);
|
||||
}
|
||||
}
|
||||
|
||||
// Chercher qualificatifs spéciaux - TOUJOURS garder ces qualificatifs pour éviter les doublons
|
||||
const qualifiers = ['solo', 'tutti', 'petite', 'grande', 'bc', 'tc', 'i', 'ii', 'mini', 'junior'];
|
||||
for (const part of parts) {
|
||||
const lowerPart = part.toLowerCase();
|
||||
for (const q of qualifiers) {
|
||||
// Skip "solo" if we're already using it as soloPart
|
||||
if (q === 'solo' && soloPart) continue;
|
||||
// For short qualifiers (i, ii), use exact match only; for longer ones, allow partial
|
||||
if (q.length <= 2) {
|
||||
if (lowerPart === q) {
|
||||
if (!foundVariantes.includes(q)) {
|
||||
foundVariantes.push(q);
|
||||
}
|
||||
}
|
||||
} else {
|
||||
if (lowerPart === q || lowerPart.includes(q)) {
|
||||
if (!foundVariantes.includes(q)) {
|
||||
foundVariantes.push(q);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Construire le résultat - Interleave instruments with their tonalities and parties for multi-instrument files
|
||||
let result;
|
||||
|
||||
if (foundInstruments.length >= 2 && foundTonalites.length >= 2) {
|
||||
// Multiple instruments with separate tonalities: interleave them
|
||||
// Format: instrument1-tonality1-clef1-part1+instrument2-tonality2-clef2-part2
|
||||
const segmentResults = [];
|
||||
for (let i = 0; i < foundInstruments.length; i++) {
|
||||
let seg = foundInstruments[i];
|
||||
if (foundTonalites[i]) seg += '-' + foundTonalites[i];
|
||||
// Add clef before partie
|
||||
if (clef) seg += '-' + clef;
|
||||
// Add party - always add at least 1 for multi-instrument
|
||||
const party = foundParties[i] || '1';
|
||||
seg += '-' + party;
|
||||
segmentResults.push(seg);
|
||||
}
|
||||
result = segmentResults.join('+');
|
||||
|
||||
// Convert French "defaut" to English "default"
|
||||
result = result.replace(/defaut/g, 'default');
|
||||
result = result.toLowerCase();
|
||||
return result + '.pdf';
|
||||
}
|
||||
|
||||
// Original logic for single instrument or cases without separate tonalities
|
||||
if (foundInstruments.length >= 2) {
|
||||
// Several instruments - interleave with parties if we have them
|
||||
const segmentResults = [];
|
||||
for (let i = 0; i < foundInstruments.length; i++) {
|
||||
let seg = foundInstruments[i];
|
||||
// Add tonality: if each instrument has its own (foundTonalites.length >= foundInstruments.length), use that
|
||||
// Otherwise if there's one tonality, use it for all
|
||||
if (foundTonalites.length >= foundInstruments.length && foundTonalites[i]) {
|
||||
seg += '-' + foundTonalites[i];
|
||||
} else if (foundTonalites.length === 1 && foundTonalites[0]) {
|
||||
seg += '-' + foundTonalites[0];
|
||||
}
|
||||
// Add party for this segment - always add at least 1 for multi-instrument
|
||||
const party = foundParties[i] || '1';
|
||||
seg += '-' + party;
|
||||
segmentResults.push(seg);
|
||||
}
|
||||
result = segmentResults.join('+');
|
||||
} else if (foundInstruments.length === 1) {
|
||||
result = foundInstruments[0];
|
||||
} else {
|
||||
// Fallback : utiliser le nom nettoyé
|
||||
const fallbackParts = name.split('_').filter(p => p && p.length > 2);
|
||||
result = fallbackParts[0] || 'inconnu';
|
||||
}
|
||||
|
||||
// Skip tonality addition for multi-instrument case (already handled above)
|
||||
const skipTonality = foundInstruments.length >= 2;
|
||||
|
||||
// Ajouter variantes AVANT tonalité
|
||||
const uniqueVariantes = foundVariantes.filter(v => {
|
||||
if (result.includes(v)) return false;
|
||||
return !foundInstruments.some(instr => instr === v || instr.includes('-' + v));
|
||||
});
|
||||
if (uniqueVariantes.length > 0) {
|
||||
result += '-' + uniqueVariantes.join('-');
|
||||
}
|
||||
|
||||
// ALWAYS include tonalité if found (even if only one instrument) - skip for multi-instr
|
||||
if (!skipTonality && foundTonalites.length > 0) {
|
||||
result += '-' + foundTonalites.join('-');
|
||||
}
|
||||
|
||||
// Ajouter "default" et l'instrument qui suit (ex: default-cor)
|
||||
if (defaultInstrument) {
|
||||
result += '-default-' + defaultInstrument;
|
||||
}
|
||||
|
||||
// Skip adding parties for multi-instrument (already added in segment building)
|
||||
const isMultiInstrument = foundInstruments.length >= 2;
|
||||
|
||||
// Add clef BEFORE parte (according to spec: instrument-tonalité-clef-partie)
|
||||
if (clef && !isMultiInstrument) {
|
||||
result += '-' + clef;
|
||||
}
|
||||
|
||||
// Utiliser les parties des segments si plusieurs instruments OU si on a des parties collectées (cas tonalité+numéro comme F1, F2)
|
||||
if (isMultiInstrument) {
|
||||
// Already handled in segment building above
|
||||
} else if (foundParties.length > 0) {
|
||||
result += '-' + foundParties.join('-');
|
||||
} else if (combinedPart) {
|
||||
result += '-' + (voice ? voice : '') + combinedPart;
|
||||
} else if (soloPart) {
|
||||
// If soloPart has number (solo_1, solo_2), keep it; otherwise add parte number with separator
|
||||
if (soloPart.includes('_')) {
|
||||
result += '-' + soloPart;
|
||||
} else {
|
||||
result += '-' + soloPart + '-' + partie;
|
||||
}
|
||||
} else if (voice) {
|
||||
result += '-' + voice + partie;
|
||||
} else {
|
||||
result += '-' + partie;
|
||||
}
|
||||
|
||||
// Convert French "defaut" to English "default"
|
||||
result = result.replace(/defaut/g, 'default');
|
||||
|
||||
// Add bugle tonality if present
|
||||
if (bugleTonalite) {
|
||||
if (result.includes('BUGLETONALITY')) {
|
||||
result = result.replace('BUGLETONALITY', 'bugle-' + bugleTonalite);
|
||||
}
|
||||
}
|
||||
|
||||
// Always lowercase the result
|
||||
result = result.toLowerCase();
|
||||
|
||||
return result + '.pdf';
|
||||
}
|
||||
|
||||
// Collecter tous les changements
|
||||
// Structure: NUM/PIECE/INSTRUMENT/VERSION/PARTIE
|
||||
const changes = [];
|
||||
const scores = fs.readdirSync(scoresPath).filter(d => {
|
||||
const p = path.join(scoresPath, d);
|
||||
return fs.statSync(p).isDirectory() && /^\d+$/.test(d);
|
||||
});
|
||||
|
||||
for (const scoreId of scores) {
|
||||
const scorePath = path.join(scoresPath, scoreId);
|
||||
const pieceDirs = fs.readdirSync(scorePath).filter(d => {
|
||||
const p = path.join(scorePath, d);
|
||||
return fs.statSync(p).isDirectory() && d !== 'score.ini';
|
||||
});
|
||||
|
||||
for (const pieceId of pieceDirs) {
|
||||
const piecePath = path.join(scorePath, pieceId);
|
||||
const instrDirs = fs.readdirSync(piecePath).filter(d => {
|
||||
const p = path.join(piecePath, d);
|
||||
return fs.statSync(p).isDirectory();
|
||||
});
|
||||
|
||||
for (const instrId of instrDirs) {
|
||||
const instrPath = path.join(piecePath, instrId);
|
||||
const entries = fs.readdirSync(instrPath);
|
||||
const versionDirs = entries.filter(e => /^\d+$/.test(e));
|
||||
|
||||
for (const versionDir of versionDirs) {
|
||||
const versionPath = path.join(instrPath, versionDir);
|
||||
if (!fs.statSync(versionPath).isDirectory()) continue;
|
||||
|
||||
const files = fs.readdirSync(versionPath).filter(f => f.toLowerCase().endsWith('.pdf'));
|
||||
|
||||
for (const file of files) {
|
||||
// Pour les fichiers "version_X", utiliser le répertoire comme partie SEULEMENT si pas de numéro de partie dans le nom (après l'instrument)
|
||||
const isVersion = file.toLowerCase().startsWith('version');
|
||||
let forcedPart = null;
|
||||
let fileForNormalization = file;
|
||||
|
||||
if (isVersion) {
|
||||
// Enlever le prefixe version_X_ pour le check (sans le .pdf)
|
||||
const nameWithoutVersion = file.replace(/\.pdf$/i, '').replace(/^version_\d+_/i, '');
|
||||
// Chercher un numéro de partie SEULEMENT à la fin du nom (après l'instrument)
|
||||
const hasPartAfterInstrument = nameWithoutVersion.match(/_(\d+)$/);
|
||||
if (!hasPartAfterInstrument) {
|
||||
forcedPart = versionDir;
|
||||
}
|
||||
// Enlever le prefixe version_X_ pour le traitement (garder le .pdf)
|
||||
fileForNormalization = file.replace(/^version_\d+_/i, '');
|
||||
}
|
||||
|
||||
const newName = normalizeFilename(fileForNormalization, forcedPart);
|
||||
changes.push({
|
||||
oldPath: path.join(versionPath, file),
|
||||
newPath: path.join(piecePath, instrId, versionDir, newName),
|
||||
oldName: file,
|
||||
newName,
|
||||
scoreId,
|
||||
pieceId,
|
||||
instrId,
|
||||
versionDir
|
||||
});
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Gérer les conflits
|
||||
const usedNames = new Set();
|
||||
for (const change of changes) {
|
||||
let finalName = change.newName;
|
||||
let counter = 1;
|
||||
|
||||
while (usedNames.has(change.newPath)) {
|
||||
const base = change.newName.replace('.pdf', '');
|
||||
finalName = `${base}_alt${counter}.pdf`;
|
||||
change.newPath = path.join(scoresPath, change.scoreId, change.pieceId, change.instrId, change.versionDir, finalName);
|
||||
counter++;
|
||||
}
|
||||
|
||||
usedNames.add(change.newPath);
|
||||
change.finalName = finalName;
|
||||
}
|
||||
|
||||
// Validate against spec: {instrument}[-{variante}][-{tonalité}][-{clef}]{-partie}
|
||||
// Multi: instrument1[-variante1][-tonalité1][-clef1]{-partie1}+instrument2...
|
||||
// Combined parts: instrument-...-X_Y
|
||||
function validateSpec(filename) {
|
||||
const base = filename.replace('.pdf', '');
|
||||
|
||||
// Multi-instrument: split by +
|
||||
if (base.includes('+')) {
|
||||
const parts = base.split('+');
|
||||
for (const part of parts) {
|
||||
const subparts = part.split('-');
|
||||
if (subparts.length < 1) return false;
|
||||
|
||||
const instrument = subparts[0];
|
||||
if (!instrument || !/^[a-z_]+$/.test(instrument)) return false;
|
||||
|
||||
// Check each segment doesn't have duplicates
|
||||
for (let i = 0; i < subparts.length - 1; i++) {
|
||||
if (subparts[i] === subparts[i+1]) return false;
|
||||
}
|
||||
}
|
||||
return true;
|
||||
}
|
||||
|
||||
// Check if it's combined parts (single instrument with 1_2)
|
||||
// Pattern: instrument-...-X_Y where X and Y are numbers
|
||||
const combinedPartsMatch = base.match(/^([a-z_]+).*-(\d+)_(\d+)(-.+)?$/);
|
||||
if (combinedPartsMatch) {
|
||||
const instrument = combinedPartsMatch[1];
|
||||
if (!instrument || !/^[a-z_]+$/.test(instrument)) return false;
|
||||
return true;
|
||||
}
|
||||
|
||||
// Single instrument: must start with valid instrument name
|
||||
const firstPart = base.split('-')[0];
|
||||
if (!firstPart || !/^[a-z_]+$/.test(firstPart)) return false;
|
||||
|
||||
// Check for duplicates
|
||||
const comps = base.split('-');
|
||||
for (let i = 0; i < comps.length - 1; i++) {
|
||||
if (comps[i] === comps[i+1]) return false;
|
||||
}
|
||||
|
||||
return true;
|
||||
}
|
||||
|
||||
// Validate all generated names
|
||||
const invalidNames = [];
|
||||
for (const c of changes) {
|
||||
if (!validateSpec(c.finalName)) {
|
||||
invalidNames.push(c);
|
||||
}
|
||||
}
|
||||
|
||||
// Afficher résultats
|
||||
console.log(`Total fichiers : ${changes.length}\n`);
|
||||
|
||||
if (invalidNames.length > 0) {
|
||||
console.log(`⚠️ ${invalidNames.length} noms ne collent pas à la spec:\n`);
|
||||
for (const inv of invalidNames.slice(0, 20)) {
|
||||
console.log(` ${inv.oldName} → ${inv.finalName}`);
|
||||
}
|
||||
if (invalidNames.length > 20) {
|
||||
console.log(` ... et ${invalidNames.length - 20} autres`);
|
||||
}
|
||||
console.log('');
|
||||
}
|
||||
|
||||
// Afficher exemples
|
||||
console.log('=== EXEMPLES DE CONVERSIONS ===\n');
|
||||
const uniquePatterns = [];
|
||||
const seen = new Set();
|
||||
|
||||
for (const c of changes) {
|
||||
const pattern = `${c.oldName} → ${c.finalName}`;
|
||||
if (!seen.has(pattern) && uniquePatterns.length < 30) {
|
||||
seen.add(pattern);
|
||||
uniquePatterns.push(c);
|
||||
}
|
||||
}
|
||||
|
||||
for (const ex of uniquePatterns) {
|
||||
console.log(`${ex.oldName}`);
|
||||
console.log(` → ${ex.finalName}\n`);
|
||||
}
|
||||
|
||||
// Générer les fichiers CSV
|
||||
const conversionComplete = [];
|
||||
const duplicates = [];
|
||||
const nameToFiles = new Map();
|
||||
|
||||
for (const c of changes) {
|
||||
const key = `${c.scoreId}/${c.instrId}/${c.numDir}/${c.finalName}`;
|
||||
if (!nameToFiles.has(key)) {
|
||||
nameToFiles.set(key, []);
|
||||
}
|
||||
nameToFiles.get(key).push(c);
|
||||
}
|
||||
|
||||
for (const [key, files] of nameToFiles) {
|
||||
const [scoreId, instrId, numDir, finalName] = key.split('/');
|
||||
const oldPaths = files.map(f => f.oldName).join('; ');
|
||||
|
||||
if (files.length === 1) {
|
||||
conversionComplete.push(`${files[0].oldPath};${finalName}`);
|
||||
} else {
|
||||
for (const f of files) {
|
||||
duplicates.push(`${f.oldPath};${finalName}`);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
fs.writeFileSync(path.join(__dirname, 'conversion_complete.csv'), conversionComplete.join('\n'));
|
||||
fs.writeFileSync(path.join(__dirname, 'duplicates.csv'), duplicates.join('\n'));
|
||||
|
||||
console.log(`\nFichiers générés:`);
|
||||
console.log(`- conversion_complete.csv: ${conversionComplete.length} fichiers`);
|
||||
console.log(`- duplicates.csv: ${duplicates.length} fichiers (doublons)`);
|
||||
|
||||
// Exécuter si confirmé
|
||||
if (confirmed) {
|
||||
console.log('\nExécution...\n');
|
||||
let success = 0;
|
||||
let errors = 0;
|
||||
let removedDirs = 0;
|
||||
|
||||
for (const change of changes) {
|
||||
try {
|
||||
fs.renameSync(change.oldPath, change.newPath);
|
||||
success++;
|
||||
} catch (err) {
|
||||
console.error(`❌ ${change.oldName} : ${err.message}`);
|
||||
errors++;
|
||||
}
|
||||
}
|
||||
|
||||
// Supprimer répertoires vides
|
||||
for (const scoreId of scores) {
|
||||
const scorePath = path.join(scoresPath, scoreId);
|
||||
const instrDirs = fs.readdirSync(scorePath).filter(d => {
|
||||
const p = path.join(scorePath, d);
|
||||
return fs.statSync(p).isDirectory() && d !== 'score.ini';
|
||||
});
|
||||
|
||||
for (const instrId of instrDirs) {
|
||||
const instrPath = path.join(scorePath, instrId);
|
||||
const numDirs = fs.readdirSync(instrPath).filter(e => /^\d+$/.test(e));
|
||||
|
||||
for (const numDir of numDirs) {
|
||||
const numPath = path.join(instrPath, numDir);
|
||||
try {
|
||||
const remaining = fs.readdirSync(numPath);
|
||||
if (remaining.length === 0) {
|
||||
fs.rmdirSync(numPath);
|
||||
removedDirs++;
|
||||
}
|
||||
} catch (e) {}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
console.log(`\n✅ Terminé !`);
|
||||
console.log(`Fichiers convertis : ${success}`);
|
||||
console.log(`Erreurs : ${errors}`);
|
||||
console.log(`Répertoires supprimés : ${removedDirs}`);
|
||||
} else {
|
||||
console.log('\nPour confirmer la conversion :');
|
||||
console.log(`node scripts/convert_final_v2.js ${scoresPath} confirm`);
|
||||
}
|
||||
Reference in New Issue
Block a user