Update src/services/cv_service.py

src/services/cv_service.py

@@ -1,9 +1,10 @@
 import json
 import logging
-from typing import Dict, Any
+from typing import Dict, Any, List
 from src.config import load_pdf
 from src.agents.cv_agents import CVAgentOrchestrator
-from src.agents.scoring_agent import ScoringAgent
+from src.agents.scoring_agent import SimpleScoringAgent
+from src.utils.fallback_extractor import FallbackExtractor
 
 logger = logging.getLogger(__name__)
 
@@ -11,26 +12,64 @@ class CVParsingService:
     def __init__(self, models: Dict[str, Any]):
         self.models = models
         self.orchestrator = CVAgentOrchestrator(models.get("llm"))
-        self.scoring_agent = ScoringAgent()
-    
+        self.scoring_agent = SimpleScoringAgent()
+        self.fallback_extractor = FallbackExtractor()
     def parse_cv(self, pdf_path: str) -> Dict[str, Any]:
         cv_text = load_pdf(pdf_path)
-        
         if not cv_text or not cv_text.strip():
-            return self._create_fallback_data()
-        
+            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 cv_data and cv_data.get("candidat"):
-            logger.info("Calculating scores...")
-            scores = self.scoring_agent.calculate_scores(cv_data["candidat"])
+        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)
+        logger.info("Calculating skill levels...")
+        scores = self.scoring_agent.calculate_scores(cv_data["candidat"])
+        if scores and scores.get("analyse_competences"):
+            cv_data["candidat"].update(scores)
+            skills_count = len(scores.get("analyse_competences", []))
+            levels_summary = self._get_levels_summary(scores.get("analyse_competences", []))
+            logger.info(f"Skill levels calculated: {skills_count} skills - {levels_summary}")
+        else:
+            logger.warning("No skill levels calculated, adding empty analysis")
+            cv_data["candidat"]["analyse_competences"] = []
+        return cv_data
+    
+    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")
+            levels_count[level] = levels_count.get(level, 0) + 1
+        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 valid CV data extracted, using fallback")
-            return self._create_fallback_data()
+            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 cv_data
+        return has_info or has_skills or has_experience