579 lines
18 KiB
JavaScript
579 lines
18 KiB
JavaScript
// ========================================
|
|
// SELECTIVE UTILS - UTILITAIRES MODULAIRES
|
|
// Responsabilité: Fonctions utilitaires partagées par tous les modules selective
|
|
// Architecture: Helper functions réutilisables et composables
|
|
// ========================================
|
|
|
|
const { logSh } = require('../ErrorReporting');
|
|
|
|
/**
|
|
* ANALYSEURS DE CONTENU SELECTIVE
|
|
*/
|
|
|
|
/**
|
|
* Analyser qualité technique d'un contenu
|
|
*/
|
|
function analyzeTechnicalQuality(content, contextualTerms = []) {
|
|
if (!content || typeof content !== 'string') return { score: 0, details: {} };
|
|
|
|
const analysis = {
|
|
score: 0,
|
|
details: {
|
|
technicalTermsFound: 0,
|
|
technicalTermsExpected: contextualTerms.length,
|
|
genericWordsCount: 0,
|
|
hasSpecifications: false,
|
|
hasDimensions: false,
|
|
contextIntegration: 0
|
|
}
|
|
};
|
|
|
|
const lowerContent = content.toLowerCase();
|
|
|
|
// 1. Compter termes techniques présents
|
|
contextualTerms.forEach(term => {
|
|
if (lowerContent.includes(term.toLowerCase())) {
|
|
analysis.details.technicalTermsFound++;
|
|
}
|
|
});
|
|
|
|
// 2. Détecter mots génériques
|
|
const genericWords = ['produit', 'solution', 'service', 'offre', 'article', 'élément'];
|
|
analysis.details.genericWordsCount = genericWords.filter(word =>
|
|
lowerContent.includes(word)
|
|
).length;
|
|
|
|
// 3. Vérifier spécifications techniques
|
|
analysis.details.hasSpecifications = /\b(norme|iso|din|ce)\b/i.test(content);
|
|
|
|
// 4. Vérifier dimensions/données techniques
|
|
analysis.details.hasDimensions = /\d+\s*(mm|cm|m|%|°|kg|g)\b/i.test(content);
|
|
|
|
// 5. Calculer score global (0-100)
|
|
const termRatio = contextualTerms.length > 0 ?
|
|
(analysis.details.technicalTermsFound / contextualTerms.length) * 40 : 20;
|
|
const genericPenalty = Math.min(20, analysis.details.genericWordsCount * 5);
|
|
const specificationBonus = analysis.details.hasSpecifications ? 15 : 0;
|
|
const dimensionBonus = analysis.details.hasDimensions ? 15 : 0;
|
|
const lengthBonus = content.length > 100 ? 10 : 0;
|
|
|
|
analysis.score = Math.max(0, Math.min(100,
|
|
termRatio + specificationBonus + dimensionBonus + lengthBonus - genericPenalty
|
|
));
|
|
|
|
return analysis;
|
|
}
|
|
|
|
/**
|
|
* Analyser fluidité des transitions
|
|
*/
|
|
function analyzeTransitionFluidity(content) {
|
|
if (!content || typeof content !== 'string') return { score: 0, details: {} };
|
|
|
|
const sentences = content.split(/[.!?]+/)
|
|
.map(s => s.trim())
|
|
.filter(s => s.length > 5);
|
|
|
|
if (sentences.length < 2) {
|
|
return { score: 100, details: { reason: 'Contenu trop court pour analyse transitions' } };
|
|
}
|
|
|
|
const analysis = {
|
|
score: 0,
|
|
details: {
|
|
sentencesCount: sentences.length,
|
|
connectorsFound: 0,
|
|
repetitiveConnectors: 0,
|
|
abruptTransitions: 0,
|
|
averageSentenceLength: 0,
|
|
lengthVariation: 0
|
|
}
|
|
};
|
|
|
|
// 1. Analyser connecteurs
|
|
const commonConnectors = ['par ailleurs', 'en effet', 'de plus', 'cependant', 'ainsi', 'donc', 'ensuite'];
|
|
const connectorCounts = {};
|
|
|
|
commonConnectors.forEach(connector => {
|
|
const matches = (content.match(new RegExp(`\\b${connector}\\b`, 'gi')) || []);
|
|
connectorCounts[connector] = matches.length;
|
|
analysis.details.connectorsFound += matches.length;
|
|
if (matches.length > 1) analysis.details.repetitiveConnectors++;
|
|
});
|
|
|
|
// 2. Détecter transitions abruptes
|
|
for (let i = 1; i < sentences.length; i++) {
|
|
const sentence = sentences[i].toLowerCase().trim();
|
|
const hasConnector = commonConnectors.some(connector =>
|
|
sentence.startsWith(connector) || sentence.includes(` ${connector} `)
|
|
);
|
|
|
|
if (!hasConnector && sentence.length > 20) {
|
|
analysis.details.abruptTransitions++;
|
|
}
|
|
}
|
|
|
|
// 3. Analyser variation de longueur
|
|
const lengths = sentences.map(s => s.split(/\s+/).length);
|
|
analysis.details.averageSentenceLength = lengths.reduce((a, b) => a + b, 0) / lengths.length;
|
|
|
|
const variance = lengths.reduce((acc, len) =>
|
|
acc + Math.pow(len - analysis.details.averageSentenceLength, 2), 0
|
|
) / lengths.length;
|
|
analysis.details.lengthVariation = Math.sqrt(variance);
|
|
|
|
// 4. Calculer score fluidité (0-100)
|
|
const connectorScore = Math.min(30, (analysis.details.connectorsFound / sentences.length) * 100);
|
|
const repetitionPenalty = Math.min(20, analysis.details.repetitiveConnectors * 5);
|
|
const abruptPenalty = Math.min(30, (analysis.details.abruptTransitions / sentences.length) * 50);
|
|
const variationScore = Math.min(20, analysis.details.lengthVariation * 2);
|
|
|
|
analysis.score = Math.max(0, Math.min(100,
|
|
connectorScore + variationScore - repetitionPenalty - abruptPenalty + 50
|
|
));
|
|
|
|
return analysis;
|
|
}
|
|
|
|
/**
|
|
* Analyser cohérence de style
|
|
*/
|
|
function analyzeStyleConsistency(content, expectedPersonality = null) {
|
|
if (!content || typeof content !== 'string') return { score: 0, details: {} };
|
|
|
|
const analysis = {
|
|
score: 0,
|
|
details: {
|
|
personalityAlignment: 0,
|
|
toneConsistency: 0,
|
|
vocabularyLevel: 'standard',
|
|
formalityScore: 0,
|
|
personalityWordsFound: 0
|
|
}
|
|
};
|
|
|
|
// 1. Analyser alignement personnalité
|
|
if (expectedPersonality && expectedPersonality.vocabulairePref) {
|
|
const personalityWords = expectedPersonality.vocabulairePref.toLowerCase().split(',');
|
|
const contentLower = content.toLowerCase();
|
|
|
|
personalityWords.forEach(word => {
|
|
if (word.trim() && contentLower.includes(word.trim())) {
|
|
analysis.details.personalityWordsFound++;
|
|
}
|
|
});
|
|
|
|
analysis.details.personalityAlignment = personalityWords.length > 0 ?
|
|
(analysis.details.personalityWordsFound / personalityWords.length) * 100 : 0;
|
|
}
|
|
|
|
// 2. Analyser niveau vocabulaire
|
|
const technicalWords = content.match(/\b\w{8,}\b/g) || [];
|
|
const totalWords = content.split(/\s+/).length;
|
|
const techRatio = technicalWords.length / totalWords;
|
|
|
|
if (techRatio > 0.15) analysis.details.vocabularyLevel = 'expert';
|
|
else if (techRatio < 0.05) analysis.details.vocabularyLevel = 'accessible';
|
|
else analysis.details.vocabularyLevel = 'standard';
|
|
|
|
// 3. Analyser formalité
|
|
const formalIndicators = ['il convient de', 'par conséquent', 'néanmoins', 'toutefois'];
|
|
const casualIndicators = ['du coup', 'sympa', 'cool', 'nickel'];
|
|
|
|
let formalCount = formalIndicators.filter(indicator =>
|
|
content.toLowerCase().includes(indicator)
|
|
).length;
|
|
|
|
let casualCount = casualIndicators.filter(indicator =>
|
|
content.toLowerCase().includes(indicator)
|
|
).length;
|
|
|
|
analysis.details.formalityScore = formalCount - casualCount; // Positif = formel, négatif = casual
|
|
|
|
// 4. Calculer score cohérence (0-100)
|
|
let baseScore = 50;
|
|
|
|
if (expectedPersonality) {
|
|
baseScore += analysis.details.personalityAlignment * 0.3;
|
|
|
|
// Ajustements selon niveau technique attendu
|
|
const expectedLevel = expectedPersonality.niveauTechnique || 'standard';
|
|
if (expectedLevel === analysis.details.vocabularyLevel) {
|
|
baseScore += 20;
|
|
} else {
|
|
baseScore -= 10;
|
|
}
|
|
}
|
|
|
|
// Bonus cohérence tonale
|
|
const sentences = content.split(/[.!?]+/).filter(s => s.length > 10);
|
|
if (sentences.length > 1) {
|
|
baseScore += Math.min(20, analysis.details.lengthVariation || 10);
|
|
}
|
|
|
|
analysis.score = Math.max(0, Math.min(100, baseScore));
|
|
|
|
return analysis;
|
|
}
|
|
|
|
/**
|
|
* COMPARATEURS ET MÉTRIQUES
|
|
*/
|
|
|
|
/**
|
|
* Comparer deux contenus et calculer taux amélioration
|
|
*/
|
|
function compareContentImprovement(original, enhanced, analysisType = 'general') {
|
|
if (!original || !enhanced) return { improvementRate: 0, details: {} };
|
|
|
|
const comparison = {
|
|
improvementRate: 0,
|
|
details: {
|
|
lengthChange: ((enhanced.length - original.length) / original.length) * 100,
|
|
wordCountChange: 0,
|
|
structuralChanges: 0,
|
|
contentPreserved: true
|
|
}
|
|
};
|
|
|
|
// 1. Analyser changements structurels
|
|
const originalSentences = original.split(/[.!?]+/).length;
|
|
const enhancedSentences = enhanced.split(/[.!?]+/).length;
|
|
comparison.details.structuralChanges = Math.abs(enhancedSentences - originalSentences);
|
|
|
|
// 2. Analyser changements de mots
|
|
const originalWords = original.toLowerCase().split(/\s+/).filter(w => w.length > 2);
|
|
const enhancedWords = enhanced.toLowerCase().split(/\s+/).filter(w => w.length > 2);
|
|
comparison.details.wordCountChange = enhancedWords.length - originalWords.length;
|
|
|
|
// 3. Vérifier préservation du contenu principal
|
|
const originalKeyWords = originalWords.filter(w => w.length > 4);
|
|
const preservedWords = originalKeyWords.filter(w => enhanced.toLowerCase().includes(w));
|
|
comparison.details.contentPreserved = (preservedWords.length / originalKeyWords.length) > 0.7;
|
|
|
|
// 4. Calculer taux amélioration selon type d'analyse
|
|
switch (analysisType) {
|
|
case 'technical':
|
|
const originalTech = analyzeTechnicalQuality(original);
|
|
const enhancedTech = analyzeTechnicalQuality(enhanced);
|
|
comparison.improvementRate = enhancedTech.score - originalTech.score;
|
|
break;
|
|
|
|
case 'transitions':
|
|
const originalFluid = analyzeTransitionFluidity(original);
|
|
const enhancedFluid = analyzeTransitionFluidity(enhanced);
|
|
comparison.improvementRate = enhancedFluid.score - originalFluid.score;
|
|
break;
|
|
|
|
case 'style':
|
|
const originalStyle = analyzeStyleConsistency(original);
|
|
const enhancedStyle = analyzeStyleConsistency(enhanced);
|
|
comparison.improvementRate = enhancedStyle.score - originalStyle.score;
|
|
break;
|
|
|
|
default:
|
|
// Amélioration générale (moyenne pondérée)
|
|
comparison.improvementRate = Math.min(50, Math.abs(comparison.details.lengthChange) * 0.1 +
|
|
(comparison.details.contentPreserved ? 20 : -20) +
|
|
Math.min(15, Math.abs(comparison.details.wordCountChange)));
|
|
}
|
|
|
|
return comparison;
|
|
}
|
|
|
|
/**
|
|
* UTILITAIRES DE CONTENU
|
|
*/
|
|
|
|
/**
|
|
* Nettoyer contenu généré par LLM
|
|
*/
|
|
function cleanGeneratedContent(content, cleaningLevel = 'standard') {
|
|
if (!content || typeof content !== 'string') return content;
|
|
|
|
let cleaned = content.trim();
|
|
|
|
// Nettoyage de base
|
|
cleaned = cleaned.replace(/^(voici\s+)?le\s+contenu\s+(amélioré|modifié|réécrit)[:\s]*/gi, '');
|
|
cleaned = cleaned.replace(/^(bon,?\s*)?(alors,?\s*)?(voici\s+)?/gi, '');
|
|
cleaned = cleaned.replace(/^(avec\s+les?\s+)?améliorations?\s*[:\s]*/gi, '');
|
|
|
|
// Nettoyage formatage
|
|
cleaned = cleaned.replace(/\*\*([^*]+)\*\*/g, '$1'); // Gras markdown → texte normal
|
|
cleaned = cleaned.replace(/\s{2,}/g, ' '); // Espaces multiples
|
|
cleaned = cleaned.replace(/([.!?])\s*([.!?])/g, '$1 '); // Double ponctuation
|
|
|
|
if (cleaningLevel === 'intensive') {
|
|
// Nettoyage intensif
|
|
cleaned = cleaned.replace(/^\s*[-*+]\s*/gm, ''); // Puces en début de ligne
|
|
cleaned = cleaned.replace(/^(pour\s+)?(ce\s+)?(contenu\s*)?[,:]?\s*/gi, '');
|
|
cleaned = cleaned.replace(/\([^)]*\)/g, ''); // Parenthèses et contenu
|
|
}
|
|
|
|
// Nettoyage final
|
|
cleaned = cleaned.replace(/^[,.\s]+/, ''); // Début
|
|
cleaned = cleaned.replace(/[,\s]+$/, ''); // Fin
|
|
cleaned = cleaned.trim();
|
|
|
|
return cleaned;
|
|
}
|
|
|
|
/**
|
|
* Valider contenu selective
|
|
*/
|
|
function validateSelectiveContent(content, originalContent, criteria = {}) {
|
|
const validation = {
|
|
isValid: true,
|
|
score: 0,
|
|
issues: [],
|
|
suggestions: []
|
|
};
|
|
|
|
const {
|
|
minLength = 20,
|
|
maxLengthChange = 50, // % de changement maximum
|
|
preserveContent = true,
|
|
checkTechnicalTerms = true
|
|
} = criteria;
|
|
|
|
// 1. Vérifier longueur
|
|
if (!content || content.length < minLength) {
|
|
validation.isValid = false;
|
|
validation.issues.push('Contenu trop court');
|
|
validation.suggestions.push('Augmenter la longueur du contenu généré');
|
|
} else {
|
|
validation.score += 25;
|
|
}
|
|
|
|
// 2. Vérifier changements de longueur
|
|
if (originalContent) {
|
|
const lengthChange = Math.abs((content.length - originalContent.length) / originalContent.length) * 100;
|
|
|
|
if (lengthChange > maxLengthChange) {
|
|
validation.issues.push('Changement de longueur excessif');
|
|
validation.suggestions.push('Réduire l\'intensité d\'amélioration');
|
|
} else {
|
|
validation.score += 25;
|
|
}
|
|
|
|
// 3. Vérifier préservation du contenu
|
|
if (preserveContent) {
|
|
const preservation = compareContentImprovement(originalContent, content);
|
|
|
|
if (!preservation.details.contentPreserved) {
|
|
validation.isValid = false;
|
|
validation.issues.push('Contenu original non préservé');
|
|
validation.suggestions.push('Améliorer conservation du sens original');
|
|
} else {
|
|
validation.score += 25;
|
|
}
|
|
}
|
|
}
|
|
|
|
// 4. Vérifications spécifiques
|
|
if (checkTechnicalTerms) {
|
|
const technicalQuality = analyzeTechnicalQuality(content);
|
|
|
|
if (technicalQuality.score > 60) {
|
|
validation.score += 25;
|
|
} else if (technicalQuality.score < 30) {
|
|
validation.issues.push('Qualité technique insuffisante');
|
|
validation.suggestions.push('Ajouter plus de termes techniques spécialisés');
|
|
}
|
|
}
|
|
|
|
// Score final et validation
|
|
validation.score = Math.min(100, validation.score);
|
|
validation.isValid = validation.isValid && validation.score >= 60;
|
|
|
|
return validation;
|
|
}
|
|
|
|
/**
|
|
* UTILITAIRES TECHNIQUES
|
|
*/
|
|
|
|
/**
|
|
* Chunk array avec gestion intelligente
|
|
*/
|
|
function chunkArray(array, chunkSize, smartChunking = false) {
|
|
if (!Array.isArray(array)) return [];
|
|
if (array.length <= chunkSize) return [array];
|
|
|
|
const chunks = [];
|
|
|
|
if (smartChunking) {
|
|
// Chunking intelligent : éviter de séparer éléments liés
|
|
let currentChunk = [];
|
|
|
|
for (let i = 0; i < array.length; i++) {
|
|
currentChunk.push(array[i]);
|
|
|
|
// Conditions de fin de chunk intelligente
|
|
const isChunkFull = currentChunk.length >= chunkSize;
|
|
const isLastElement = i === array.length - 1;
|
|
const nextElementRelated = i < array.length - 1 &&
|
|
array[i].tag && array[i + 1].tag &&
|
|
array[i].tag.includes('FAQ') && array[i + 1].tag.includes('FAQ');
|
|
|
|
if ((isChunkFull && !nextElementRelated) || isLastElement) {
|
|
chunks.push([...currentChunk]);
|
|
currentChunk = [];
|
|
}
|
|
}
|
|
|
|
// Ajouter chunk restant si non vide
|
|
if (currentChunk.length > 0) {
|
|
if (chunks.length > 0 && chunks[chunks.length - 1].length + currentChunk.length <= chunkSize * 1.2) {
|
|
// Merger avec dernier chunk si pas trop gros
|
|
chunks[chunks.length - 1].push(...currentChunk);
|
|
} else {
|
|
chunks.push(currentChunk);
|
|
}
|
|
}
|
|
} else {
|
|
// Chunking standard
|
|
for (let i = 0; i < array.length; i += chunkSize) {
|
|
chunks.push(array.slice(i, i + chunkSize));
|
|
}
|
|
}
|
|
|
|
return chunks;
|
|
}
|
|
|
|
/**
|
|
* Sleep avec logging optionnel
|
|
*/
|
|
async function sleep(ms, logMessage = null) {
|
|
if (logMessage) {
|
|
logSh(`⏳ ${logMessage} (${ms}ms)`, 'DEBUG');
|
|
}
|
|
|
|
return new Promise(resolve => setTimeout(resolve, ms));
|
|
}
|
|
|
|
/**
|
|
* Mesurer performance d'opération
|
|
*/
|
|
function measurePerformance(operationName, startTime = Date.now()) {
|
|
const endTime = Date.now();
|
|
const duration = endTime - startTime;
|
|
|
|
const performance = {
|
|
operationName,
|
|
startTime,
|
|
endTime,
|
|
duration,
|
|
durationFormatted: formatDuration(duration)
|
|
};
|
|
|
|
return performance;
|
|
}
|
|
|
|
/**
|
|
* Formater durée en format lisible
|
|
*/
|
|
function formatDuration(ms) {
|
|
if (ms < 1000) return `${ms}ms`;
|
|
if (ms < 60000) return `${(ms / 1000).toFixed(1)}s`;
|
|
return `${Math.floor(ms / 60000)}m ${Math.floor((ms % 60000) / 1000)}s`;
|
|
}
|
|
|
|
/**
|
|
* STATISTIQUES ET RAPPORTS
|
|
*/
|
|
|
|
/**
|
|
* Générer rapport amélioration
|
|
*/
|
|
function generateImprovementReport(originalContent, enhancedContent, layerType = 'general') {
|
|
const report = {
|
|
layerType,
|
|
timestamp: new Date().toISOString(),
|
|
summary: {
|
|
elementsProcessed: 0,
|
|
elementsImproved: 0,
|
|
averageImprovement: 0,
|
|
totalExecutionTime: 0
|
|
},
|
|
details: {
|
|
byElement: [],
|
|
qualityMetrics: {},
|
|
recommendations: []
|
|
}
|
|
};
|
|
|
|
// Analyser chaque élément
|
|
Object.keys(originalContent).forEach(tag => {
|
|
const original = originalContent[tag];
|
|
const enhanced = enhancedContent[tag];
|
|
|
|
if (original && enhanced) {
|
|
report.summary.elementsProcessed++;
|
|
|
|
const improvement = compareContentImprovement(original, enhanced, layerType);
|
|
|
|
if (improvement.improvementRate > 0) {
|
|
report.summary.elementsImproved++;
|
|
}
|
|
|
|
report.summary.averageImprovement += improvement.improvementRate;
|
|
|
|
report.details.byElement.push({
|
|
tag,
|
|
improvementRate: improvement.improvementRate,
|
|
lengthChange: improvement.details.lengthChange,
|
|
contentPreserved: improvement.details.contentPreserved
|
|
});
|
|
}
|
|
});
|
|
|
|
// Calculer moyennes
|
|
if (report.summary.elementsProcessed > 0) {
|
|
report.summary.averageImprovement = report.summary.averageImprovement / report.summary.elementsProcessed;
|
|
}
|
|
|
|
// Métriques qualité globales
|
|
const fullOriginal = Object.values(originalContent).join(' ');
|
|
const fullEnhanced = Object.values(enhancedContent).join(' ');
|
|
|
|
report.details.qualityMetrics = {
|
|
technical: analyzeTechnicalQuality(fullEnhanced),
|
|
transitions: analyzeTransitionFluidity(fullEnhanced),
|
|
style: analyzeStyleConsistency(fullEnhanced)
|
|
};
|
|
|
|
// Recommandations
|
|
if (report.summary.averageImprovement < 10) {
|
|
report.details.recommendations.push('Augmenter l\'intensité d\'amélioration');
|
|
}
|
|
|
|
if (report.details.byElement.some(e => !e.contentPreserved)) {
|
|
report.details.recommendations.push('Améliorer préservation du contenu original');
|
|
}
|
|
|
|
return report;
|
|
}
|
|
|
|
module.exports = {
|
|
// Analyseurs
|
|
analyzeTechnicalQuality,
|
|
analyzeTransitionFluidity,
|
|
analyzeStyleConsistency,
|
|
|
|
// Comparateurs
|
|
compareContentImprovement,
|
|
|
|
// Utilitaires contenu
|
|
cleanGeneratedContent,
|
|
validateSelectiveContent,
|
|
|
|
// Utilitaires techniques
|
|
chunkArray,
|
|
sleep,
|
|
measurePerformance,
|
|
formatDuration,
|
|
|
|
// Rapports
|
|
generateImprovementReport
|
|
}; |