seogeneratorserver/lib/post-processing/TransitionHumanization.js

// ========================================
// PATTERN BREAKING - TECHNIQUE 3: TRANSITION HUMANIZATION
// Responsabilité: Remplacer connecteurs mécaniques par transitions naturelles
// Anti-détection: Éviter patterns de liaison typiques des LLMs
// ========================================

const { logSh } = require('../ErrorReporting');
const { tracer } = require('../trace');

/**
 * DICTIONNAIRE CONNECTEURS HUMANISÉS
 * Connecteurs LLM → Alternatives naturelles par contexte
 */
const TRANSITION_REPLACEMENTS = {
  // Connecteurs trop formels → versions naturelles
  'par ailleurs': {
    alternatives: ['d\'ailleurs', 'au fait', 'soit dit en passant', 'à propos', 'sinon'],
    weight: 0.8,
    contexts: ['casual', 'conversational']
  },
  
  'en effet': {
    alternatives: ['effectivement', 'c\'est vrai', 'tout à fait', 'absolument', 'exactement'],
    weight: 0.9,
    contexts: ['confirmative', 'agreement']
  },
  
  'de plus': {
    alternatives: ['aussi', 'également', 'qui plus est', 'en plus', 'et puis'],
    weight: 0.7,
    contexts: ['additive', 'continuation']
  },
  
  'cependant': {
    alternatives: ['mais', 'pourtant', 'néanmoins', 'malgré tout', 'quand même'],
    weight: 0.6,
    contexts: ['contrast', 'opposition']
  },
  
  'ainsi': {
    alternatives: ['donc', 'du coup', 'comme ça', 'par conséquent', 'résultat'],
    weight: 0.8,
    contexts: ['consequence', 'result']
  },
  
  'donc': {
    alternatives: ['du coup', 'alors', 'par conséquent', 'ainsi', 'résultat'],
    weight: 0.5,
    contexts: ['consequence', 'logical']
  },
  
  // Connecteurs de séquence
  'ensuite': {
    alternatives: ['puis', 'après', 'et puis', 'alors', 'du coup'],
    weight: 0.6,
    contexts: ['sequence', 'temporal']
  },
  
  'puis': {
    alternatives: ['ensuite', 'après', 'et puis', 'alors'],
    weight: 0.4,
    contexts: ['sequence', 'temporal']
  },
  
  // Connecteurs d'emphase
  'également': {
    alternatives: ['aussi', 'de même', 'pareillement', 'en plus'],
    weight: 0.6,
    contexts: ['similarity', 'addition']
  },
  
  'aussi': {
    alternatives: ['également', 'de même', 'en plus', 'pareillement'],
    weight: 0.3,
    contexts: ['similarity', 'addition']
  },
  
  // Connecteurs de conclusion
  'enfin': {
    alternatives: ['finalement', 'au final', 'pour finir', 'en dernier'],
    weight: 0.5,
    contexts: ['conclusion', 'final']
  },
  
  'finalement': {
    alternatives: ['au final', 'en fin de compte', 'pour finir', 'enfin'],
    weight: 0.4,
    contexts: ['conclusion', 'final']
  }
};

/**
 * PATTERNS DE TRANSITION NATURELLE
 * Selon le style de personnalité
 */
const PERSONALITY_TRANSITIONS = {
  'décontracté': {
    preferred: ['du coup', 'alors', 'bon', 'après', 'sinon'],
    avoided: ['par conséquent', 'néanmoins', 'toutefois']
  },
  
  'technique': {
    preferred: ['donc', 'ainsi', 'par conséquent', 'résultat'],
    avoided: ['du coup', 'bon', 'franchement']
  },
  
  'commercial': {
    preferred: ['aussi', 'de plus', 'également', 'qui plus est'],
    avoided: ['du coup', 'bon', 'franchement']
  },
  
  'familier': {
    preferred: ['du coup', 'bon', 'alors', 'après', 'franchement'],
    avoided: ['par conséquent', 'néanmoins', 'de surcroît']
  }
};

/**
 * MAIN ENTRY POINT - HUMANISATION TRANSITIONS
 * @param {Object} input - { content: {}, config: {}, context: {} }
 * @returns {Object} - { content: {}, stats: {}, debug: {} }
 */
async function humanizeTransitions(input) {
  return await tracer.run('TransitionHumanization.humanizeTransitions()', async () => {
    const { content, config = {}, context = {} } = input;
    
    const {
      intensity = 0.6,           // Probabilité de remplacement (60%)
      personalityStyle = null,   // Style de personnalité pour guidage
      avoidRepetition = true,    // Éviter répétitions excessives
      preserveFormal = false,    // Préserver style formel
      csvData = null             // Données pour personnalité
    } = config;
    
    await tracer.annotate({ 
      technique: 'transition_humanization',
      intensity,
      personalityStyle: personalityStyle || csvData?.personality?.style,
      elementsCount: Object.keys(content).length
    });

    const startTime = Date.now();
    logSh(`🔗 TECHNIQUE 3/3: Humanisation transitions (intensité: ${intensity})`, 'INFO');
    logSh(`   📊 ${Object.keys(content).length} éléments à humaniser`, 'DEBUG');
    
    try {
      const results = {};
      let totalProcessed = 0;
      let totalReplacements = 0;
      let humanizationDetails = [];
      
      // Extraire style de personnalité
      const effectivePersonalityStyle = personalityStyle || csvData?.personality?.style || 'neutral';
      
      // Analyser patterns globaux pour éviter répétitions
      const globalPatterns = analyzeGlobalTransitionPatterns(content);
      
      // Traiter chaque élément de contenu
      for (const [tag, text] of Object.entries(content)) {
        totalProcessed++;
        
        if (text.length < 30) {
          results[tag] = text;
          continue;
        }
        
        // Appliquer humanisation des transitions
        const humanizationResult = humanizeTextTransitions(text, {
          intensity,
          personalityStyle: effectivePersonalityStyle,
          avoidRepetition,
          preserveFormal,
          globalPatterns,
          tag
        });
        
        results[tag] = humanizationResult.text;
        
        if (humanizationResult.replacements.length > 0) {
          totalReplacements += humanizationResult.replacements.length;
          humanizationDetails.push({
            tag,
            replacements: humanizationResult.replacements,
            transitionsDetected: humanizationResult.transitionsFound
          });
          
          logSh(`   🔄 [${tag}]: ${humanizationResult.replacements.length} transitions humanisées`, 'DEBUG');
        } else {
          logSh(`   ➡️ [${tag}]: Transitions déjà naturelles`, 'DEBUG');
        }
      }
      
      const duration = Date.now() - startTime;
      const stats = {
        processed: totalProcessed,
        totalReplacements,
        avgReplacementsPerElement: Math.round(totalReplacements / totalProcessed * 100) / 100,
        elementsWithTransitions: humanizationDetails.length,
        personalityStyle: effectivePersonalityStyle,
        duration,
        technique: 'transition_humanization'
      };
      
      logSh(`✅ HUMANISATION TRANSITIONS: ${stats.totalReplacements} remplacements sur ${stats.elementsWithTransitions}/${stats.processed} éléments en ${duration}ms`, 'INFO');
      
      await tracer.event('Transition humanization terminée', stats);
      
      return {
        content: results,
        stats,
        debug: {
          technique: 'transition_humanization',
          config: { intensity, personalityStyle: effectivePersonalityStyle, avoidRepetition },
          humanizations: humanizationDetails,
          globalPatterns
        }
      };
      
    } catch (error) {
      const duration = Date.now() - startTime;
      logSh(`❌ HUMANISATION TRANSITIONS échouée après ${duration}ms: ${error.message}`, 'ERROR');
      throw new Error(`TransitionHumanization failed: ${error.message}`);
    }
  }, input);
}

/**
 * Humaniser les transitions d'un texte
 */
function humanizeTextTransitions(text, config) {
  const { intensity, personalityStyle, avoidRepetition, preserveFormal, globalPatterns, tag } = config;
  
  let humanizedText = text;
  const replacements = [];
  const transitionsFound = [];
  
  // Statistiques usage pour éviter répétitions
  const usageStats = {};
  
  // Traiter chaque connecteur du dictionnaire
  for (const [transition, transitionData] of Object.entries(TRANSITION_REPLACEMENTS)) {
    const { alternatives, weight, contexts } = transitionData;
    
    // Rechercher occurrences (insensible à la casse, mais préserver limites mots)
    const regex = new RegExp(`\\b${escapeRegex(transition)}\\b`, 'gi');
    const matches = [...text.matchAll(regex)];
    
    if (matches.length > 0) {
      transitionsFound.push(transition);
      
      // Décider si on remplace selon intensité et poids
      const shouldReplace = Math.random() < (intensity * weight);
      
      if (shouldReplace && !preserveFormal) {
        // Sélectionner meilleure alternative
        const selectedAlternative = selectBestTransitionAlternative(
          alternatives, 
          personalityStyle, 
          usageStats, 
          avoidRepetition
        );
        
        // Appliquer remplacement en préservant la casse
        humanizedText = humanizedText.replace(regex, (match) => {
          return preserveCase(match, selectedAlternative);
        });
        
        // Enregistrer usage
        usageStats[selectedAlternative] = (usageStats[selectedAlternative] || 0) + matches.length;
        
        replacements.push({
          original: transition,
          replacement: selectedAlternative,
          occurrences: matches.length,
          contexts,
          personalityMatch: isPersonalityAppropriate(selectedAlternative, personalityStyle)
        });
      }
    }
  }
  
  // Post-processing : éviter accumulations
  if (avoidRepetition) {
    const repetitionCleaned = reduceTransitionRepetition(humanizedText, usageStats);
    humanizedText = repetitionCleaned.text;
    replacements.push(...repetitionCleaned.additionalChanges);
  }
  
  return {
    text: humanizedText,
    replacements,
    transitionsFound
  };
}

/**
 * Sélectionner meilleure alternative de transition
 */
function selectBestTransitionAlternative(alternatives, personalityStyle, usageStats, avoidRepetition) {
  // Filtrer selon personnalité
  const personalityFiltered = alternatives.filter(alt => 
    isPersonalityAppropriate(alt, personalityStyle)
  );
  
  const candidateList = personalityFiltered.length > 0 ? personalityFiltered : alternatives;
  
  if (!avoidRepetition) {
    return candidateList[Math.floor(Math.random() * candidateList.length)];
  }
  
  // Éviter les alternatives déjà trop utilisées
  const lessUsedAlternatives = candidateList.filter(alt => 
    (usageStats[alt] || 0) < 2
  );
  
  const finalList = lessUsedAlternatives.length > 0 ? lessUsedAlternatives : candidateList;
  return finalList[Math.floor(Math.random() * finalList.length)];
}

/**
 * Vérifier si alternative appropriée pour personnalité
 */
function isPersonalityAppropriate(alternative, personalityStyle) {
  if (!personalityStyle || personalityStyle === 'neutral') return true;
  
  const styleMapping = {
    'décontracté': PERSONALITY_TRANSITIONS.décontracté,
    'technique': PERSONALITY_TRANSITIONS.technique,
    'commercial': PERSONALITY_TRANSITIONS.commercial,
    'familier': PERSONALITY_TRANSITIONS.familier
  };
  
  const styleConfig = styleMapping[personalityStyle.toLowerCase()];
  if (!styleConfig) return true;
  
  // Éviter les connecteurs inappropriés
  if (styleConfig.avoided.includes(alternative)) return false;
  
  // Privilégier les connecteurs préférés
  if (styleConfig.preferred.includes(alternative)) return true;
  
  return true;
}

/**
 * Réduire répétitions excessives de transitions
 */
function reduceTransitionRepetition(text, usageStats) {
  let processedText = text;
  const additionalChanges = [];
  
  // Identifier connecteurs surutilisés (>3 fois)
  const overusedTransitions = Object.entries(usageStats)
    .filter(([transition, count]) => count > 3)
    .map(([transition]) => transition);
  
  for (const overusedTransition of overusedTransitions) {
    // Remplacer quelques occurrences par des alternatives
    const regex = new RegExp(`\\b${escapeRegex(overusedTransition)}\\b`, 'g');
    let replacements = 0;
    
    processedText = processedText.replace(regex, (match, offset) => {
      // Remplacer 1 occurrence sur 3 environ
      if (Math.random() < 0.33 && replacements < 2) {
        replacements++;
        const alternatives = findAlternativesFor(overusedTransition);
        const alternative = alternatives[Math.floor(Math.random() * alternatives.length)];
        
        additionalChanges.push({
          type: 'repetition_reduction',
          original: overusedTransition,
          replacement: alternative,
          reason: 'overuse'
        });
        
        return preserveCase(match, alternative);
      }
      return match;
    });
  }
  
  return { text: processedText, additionalChanges };
}

/**
 * Trouver alternatives pour un connecteur donné
 */
function findAlternativesFor(transition) {
  // Chercher dans le dictionnaire
  for (const [key, data] of Object.entries(TRANSITION_REPLACEMENTS)) {
    if (data.alternatives.includes(transition)) {
      return data.alternatives.filter(alt => alt !== transition);
    }
  }
  
  // Alternatives génériques
  const genericAlternatives = {
    'du coup': ['alors', 'donc', 'ainsi'],
    'alors': ['du coup', 'donc', 'ensuite'],
    'donc': ['du coup', 'alors', 'ainsi'],
    'aussi': ['également', 'de plus', 'en plus'],
    'mais': ['cependant', 'pourtant', 'néanmoins']
  };
  
  return genericAlternatives[transition] || ['donc', 'alors'];
}

/**
 * Analyser patterns globaux de transitions
 */
function analyzeGlobalTransitionPatterns(content) {
  const allText = Object.values(content).join(' ');
  const transitionCounts = {};
  const repetitionPatterns = [];
  
  // Compter occurrences globales
  for (const transition of Object.keys(TRANSITION_REPLACEMENTS)) {
    const regex = new RegExp(`\\b${escapeRegex(transition)}\\b`, 'gi');
    const matches = allText.match(regex);
    if (matches) {
      transitionCounts[transition] = matches.length;
    }
  }
  
  // Identifier patterns de répétition problématiques
  const sortedTransitions = Object.entries(transitionCounts)
    .sort(([,a], [,b]) => b - a)
    .slice(0, 5); // Top 5 plus utilisées
  
  sortedTransitions.forEach(([transition, count]) => {
    if (count > 5) {
      repetitionPatterns.push({
        transition,
        count,
        severity: count > 10 ? 'high' : count > 7 ? 'medium' : 'low'
      });
    }
  });
  
  return {
    transitionCounts,
    repetitionPatterns,
    diversityScore: Object.keys(transitionCounts).length / Math.max(1, Object.values(transitionCounts).reduce((a,b) => a+b, 0))
  };
}

/**
 * Préserver la casse originale
 */
function preserveCase(original, replacement) {
  if (original === original.toUpperCase()) {
    return replacement.toUpperCase();
  } else if (original[0] === original[0].toUpperCase()) {
    return replacement.charAt(0).toUpperCase() + replacement.slice(1).toLowerCase();
  } else {
    return replacement.toLowerCase();
  }
}

/**
 * Échapper caractères regex
 */
function escapeRegex(text) {
  return text.replace(/[.*+?^${}()|[\]\\]/g, '\\$&');
}

/**
 * Analyser qualité des transitions d'un texte
 */
function analyzeTransitionQuality(text) {
  const sentences = text.split(/[.!?]+/).filter(s => s.trim().length > 5);
  
  if (sentences.length < 2) {
    return { score: 100, issues: [], naturalness: 'high' };
  }
  
  let mechanicalTransitions = 0;
  let totalTransitions = 0;
  const issues = [];
  
  // Analyser chaque transition
  sentences.forEach((sentence, index) => {
    if (index === 0) return;
    
    const trimmed = sentence.trim();
    const startsWithTransition = Object.keys(TRANSITION_REPLACEMENTS).some(transition => 
      trimmed.toLowerCase().startsWith(transition.toLowerCase())
    );
    
    if (startsWithTransition) {
      totalTransitions++;
      
      // Vérifier si transition mécanique
      const transition = Object.keys(TRANSITION_REPLACEMENTS).find(t => 
        trimmed.toLowerCase().startsWith(t.toLowerCase())
      );
      
      if (transition && TRANSITION_REPLACEMENTS[transition].weight > 0.7) {
        mechanicalTransitions++;
        issues.push({
          type: 'mechanical_transition',
          transition,
          suggestion: TRANSITION_REPLACEMENTS[transition].alternatives[0]
        });
      }
    }
  });
  
  const mechanicalRatio = totalTransitions > 0 ? mechanicalTransitions / totalTransitions : 0;
  const score = Math.max(0, 100 - (mechanicalRatio * 100));
  
  let naturalness = 'high';
  if (mechanicalRatio > 0.5) naturalness = 'low';
  else if (mechanicalRatio > 0.25) naturalness = 'medium';
  
  return { score: Math.round(score), issues, naturalness, mechanicalRatio };
}

module.exports = {
  humanizeTransitions,       // ← MAIN ENTRY POINT
  humanizeTextTransitions,
  analyzeTransitionQuality,
  analyzeGlobalTransitionPatterns,
  TRANSITION_REPLACEMENTS,
  PERSONALITY_TRANSITIONS
};