Update src/services/cv_service.py

src/services/cv_service.py

@@ -1,6 +1,9 @@
 import json
 import logging
+import os
+from datetime import datetime
 from typing import Dict, Any, List
+from pymongo import MongoClient
 from src.config import load_pdf
 from src.agents.cv_agents import CVAgentOrchestrator
 from src.agents.scoring_agent import SimpleScoringAgent
@@ -12,18 +15,31 @@ class CVParsingService:
         self.models = models
         self.orchestrator = CVAgentOrchestrator(models.get("llm"))
         self.scoring_agent = SimpleScoringAgent()
-    def parse_cv(self, pdf_path: str) -> Dict[str, Any]:
+        
+        # Initialisation MongoDB
+        try:
+            self.client = MongoClient(os.getenv("MONGO_URI"))
+            self.db = self.client[os.getenv("MONGO_DB_NAME")]
+            self.candidate_collection = self.db[os.getenv("MONGO_CV_COLLECTION")]
+        except:
+            self.client = None
+            self.candidate_collection = None
+
+    def parse_cv(self, pdf_path: str, user_id: str = None) -> Dict[str, Any]:
         cv_text = load_pdf(pdf_path)
         if not cv_text or not cv_text.strip():
             return self._create_fallback_data()    
+        
         logger.info(f"CV text loaded: {len(cv_text)} characters")
         sections = self.orchestrator.split_cv_sections(cv_text)
         logger.info(f"Sections extracted: {list(sections.keys())}")
         cv_data = self.orchestrator.extract_all_sections(sections)
         logger.info(f"CV data extracted: {cv_data is not None}")
+        
         if not cv_data or not cv_data.get("candidat") or not self._is_valid_extraction(cv_data):
             logger.warning("Agent extraction failed or incomplete, using fallback extraction")
-            return self.fallback_extractor.extract_basic_info(cv_text)
+            return self._create_fallback_data()
+        
         logger.info("Calculating skill levels...")
         scores = self.scoring_agent.calculate_scores(cv_data["candidat"])
         if scores and scores.get("analyse_competences"):
@@ -34,10 +50,30 @@ class CVParsingService:
         else:
             logger.warning("No skill levels calculated, adding empty analysis")
             cv_data["candidat"]["analyse_competences"] = []
+
+        # Stockage automatique dans MongoDB
+        self._save_profile(cv_data["candidat"], user_id)
+        
         return cv_data
-    
+
+    def _save_profile(self, candidat_data: Dict[str, Any], user_id: str = None):
+        if not self.candidate_collection or not isinstance(candidat_data, dict):
+            return
+        
+        try:
+            profile_data = candidat_data.copy()
+            profile_data["created_at"] = datetime.utcnow()
+            profile_data["updated_at"] = datetime.utcnow()
+            
+            if user_id:
+                profile_data["user_id"] = user_id
+            
+            self.candidate_collection.insert_one(profile_data)
+            logger.info("CV stocké dans MongoDB avec succès")
+        except Exception as e:
+            logger.error(f"Erreur stockage CV: {e}")
+
     def _get_levels_summary(self, competences: List[Dict[str, Any]]) -> str:
-        """Génère un résumé des niveaux de compétences"""
         levels_count = {}
         for comp in competences:
             level = comp.get("level", "unknown")
@@ -45,29 +81,9 @@ class CVParsingService:
         return ", ".join([f"{count} {level}" for level, count in levels_count.items()])
     
     def _is_valid_extraction(self, cv_data: Dict[str, Any]) -> bool:
-        """Vérifie si l'extraction contient des données valides"""
         candidat = cv_data.get("candidat", {})
         has_info = bool(candidat.get("informations_personnelles", {}).get("nom", "").strip())
         has_skills = bool(candidat.get("compétences", {}).get("hard_skills", []) or 
                          candidat.get("compétences", {}).get("soft_skills", []))
         has_experience = bool(candidat.get("expériences", []))
-        return has_info or has_skills or has_experience
-        logger.info("Calculating scores...")
-        scores = self.scoring_agent.calculate_scores(cv_data["candidat"])
-        if scores and scores.get("analyse_competences"):
-            cv_data["candidat"].update(scores)
-            logger.info(f"Scores calculated: {len(scores.get('analyse_competences', []))} skills scored")
-        else:
-            logger.warning("No scores calculated, adding empty analysis")
-            cv_data["candidat"]["analyse_competences"] = []
-        return cv_data
-    
-    def _is_valid_extraction(self, cv_data: Dict[str, Any]) -> bool:
-        """Vérifie si l'extraction contient des données valides"""
-        candidat = cv_data.get("candidat", {})
-        has_info = bool(candidat.get("informations_personnelles", {}).get("nom", "").strip())
-        has_skills = bool(candidat.get("compétences", {}).get("hard_skills", []) or 
-                         candidat.get("compétences", {}).get("soft_skills", []))
-        has_experience = bool(candidat.get("expériences", []))
-        
         return has_info or has_skills or has_experience