updated

backend/services/resume_parser.py

@@ -1,58 +1,263 @@
 import json
+import re
 from pathlib import Path
-from typing import Dict
-
+from typing import Dict, List, Optional
 from pdfminer.high_level import extract_text as pdf_extract_text
 from docx import Document
 from transformers import AutoTokenizer, AutoModelForTokenClassification, pipeline
+import logging
+
+# Set up logging
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+class ResumeParser:
+    def __init__(self):
+        self.ner_pipeline = None
+        self.model_loaded = False
+        self._load_model()
+    
+    def _load_model(self):
+        """Load the NER model with error handling and fallbacks"""
+        try:
+            # Try the original model first
+            MODEL_NAME = "manishiitg/resume-ner"
+            logger.info(f"Attempting to load model: {MODEL_NAME}")
+            
+            tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+            model = AutoModelForTokenClassification.from_pretrained(MODEL_NAME)
+            self.ner_pipeline = pipeline(
+                "ner", 
+                model=model, 
+                tokenizer=tokenizer, 
+                aggregation_strategy="simple"
+            )
+            self.model_loaded = True
+            logger.info("Model loaded successfully")
+            
+        except Exception as e:
+            logger.warning(f"Failed to load primary model: {e}")
+            try:
+                # Fallback to a more reliable model
+                MODEL_NAME = "dbmdz/bert-large-cased-finetuned-conll03-english"
+                logger.info(f"Trying fallback model: {MODEL_NAME}")
+                
+                self.ner_pipeline = pipeline(
+                    "ner", 
+                    model=MODEL_NAME,
+                    aggregation_strategy="simple"
+                )
+                self.model_loaded = True
+                logger.info("Fallback model loaded successfully")
+                
+            except Exception as e2:
+                logger.error(f"Failed to load fallback model: {e2}")
+                self.model_loaded = False
+
+    def extract_text(self, file_path: str) -> str:
+        """Extract text from PDF or DOCX files with error handling"""
+        try:
+            path = Path(file_path)
+            
+            if not path.exists():
+                raise FileNotFoundError(f"File not found: {file_path}")
+            
+            if path.suffix.lower() == ".pdf":
+                text = pdf_extract_text(file_path)
+                logger.info(f"Extracted {len(text)} characters from PDF")
+                return text
+                
+            elif path.suffix.lower() == ".docx":
+                doc = Document(file_path)
+                text = "\n".join([p.text for p in doc.paragraphs if p.text.strip()])
+                logger.info(f"Extracted {len(text)} characters from DOCX")
+                return text
+                
+            else:
+                raise ValueError(f"Unsupported file format: {path.suffix}")
+                
+        except Exception as e:
+            logger.error(f"Error extracting text: {e}")
+            raise
+
+    def extract_with_regex(self, text: str) -> Dict[str, List[str]]:
+        """Fallback extraction using regex patterns"""
+        patterns = {
+            'email': r'\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Z|a-z]{2,}\b',
+            'phone': r'(\+\d{1,3}[-.\s]?)?$$?\d{3}$$?[-.\s]?\d{3}[-.\s]?\d{4}',
+            'skills': r'(?i)(?:skills?|technologies?|tools?)[:\-\s]*([^\n]+)',
+            'education': r'(?i)(?:education|degree|university|college|bachelor|master|phd)[:\-\s]*([^\n]+)',
+            'experience': r'(?i)(?:experience|work|employment|job)[:\-\s]*([^\n]+)'
+        }
+        
+        results = {}
+        for key, pattern in patterns.items():
+            matches = re.findall(pattern, text, re.MULTILINE)
+            results[key] = [match.strip() for match in matches if match.strip()]
+        
+        return results
+
+    def extract_name_from_text(self, text: str) -> str:
+        """Extract name using heuristics"""
+        lines = text.split('\n')
+        # Usually name is in the first few lines
+        for line in lines[:5]:
+            line = line.strip()
+            if line and len(line.split()) <= 4 and len(line) > 2:
+                # Check if it looks like a name (not email, phone, etc.)
+                if not re.search(r'[@\d]', line) and not line.lower().startswith(('resume', 'cv', 'curriculum')):
+                    return line
+        return "Not Found"
+
+    def process_ner_entities(self, entities: List[Dict]) -> Dict[str, List[str]]:
+        """Process NER entities with improved logic"""
+        name, skills, education, experience = [], [], [], []
+        
+        logger.info(f"Processing {len(entities)} entities")
+        
+        for ent in entities:
+            label = ent.get("entity_group", "").upper()
+            value = ent.get("word", "").strip()
+            confidence = ent.get("score", 0)
+            
+            logger.debug(f"Entity: {label} = {value} (confidence: {confidence:.2f})")
+            
+            # Only consider high-confidence entities
+            if confidence < 0.5:
+                continue
+                
+            if label in ["PERSON", "PER", "NAME"]:
+                name.append(value)
+            elif label in ["SKILL", "TECH", "TECHNOLOGY"]:
+                skills.append(value)
+            elif label in ["EDUCATION", "DEGREE", "EDU", "ORG"]:
+                education.append(value)
+            elif label in ["EXPERIENCE", "JOB", "ROLE", "POSITION", "WORK"]:
+                experience.append(value)
+        
+        return {
+            "name": name,
+            "skills": skills,
+            "education": education,
+            "experience": experience
+        }
+
+    def parse_resume(self, file_path: str, filename: str = None) -> Dict[str, str]:
+        """Parse resume with multiple extraction methods"""
+        try:
+            # Extract text
+            text = self.extract_text(file_path)
+            
+            if not text or len(text.strip()) < 10:
+                raise ValueError("Extracted text is too short or empty")
+            
+            logger.info(f"Text preview: {text[:200]}...")
+            
+            # Initialize results
+            results = {
+                "name": "Not Found",
+                "skills": "Not Found",
+                "education": "Not Found",
+                "experience": "Not Found"
+            }
+            
+            # Method 1: Try NER model if available
+            if self.model_loaded and self.ner_pipeline:
+                try:
+                    logger.info("Using NER model for extraction")
+                    entities = self.ner_pipeline(text)
+                    ner_results = self.process_ner_entities(entities)
+                    
+                    # Update results with NER findings
+                    for key in results.keys():
+                        if ner_results.get(key):
+                            unique_items = list(dict.fromkeys(ner_results[key]))
+                            results[key] = ", ".join(unique_items)
+                            
+                except Exception as e:
+                    logger.warning(f"NER extraction failed: {e}")
+            
+            # Method 2: Regex fallback
+            logger.info("Using regex patterns for extraction")
+            regex_results = self.extract_with_regex(text)
+            
+            # Fill in missing information with regex results
+            if results["name"] == "Not Found":
+                results["name"] = self.extract_name_from_text(text)
+            
+            if results["skills"] == "Not Found" and regex_results.get("skills"):
+                results["skills"] = ", ".join(regex_results["skills"][:3])  # Limit to first 3
+            
+            if results["education"] == "Not Found" and regex_results.get("education"):
+                results["education"] = ", ".join(regex_results["education"][:2])  # Limit to first 2
+            
+            if results["experience"] == "Not Found" and regex_results.get("experience"):
+                results["experience"] = ", ".join(regex_results["experience"][:3])  # Limit to first 3
+            
+            # Add email and phone if found
+            if regex_results.get("email"):
+                results["email"] = regex_results["email"][0]
+            if regex_results.get("phone"):
+                results["phone"] = regex_results["phone"][0]
+            
+            logger.info("Parsing completed successfully")
+            return results
+            
+        except Exception as e:
+            logger.error(f"Error parsing resume: {e}")
+            return {
+                "name": "Error",
+                "skills": "Error",
+                "education": "Error",
+                "experience": "Error",
+                "error": str(e)
+            }
+
+# Create global instance
+resume_parser = ResumeParser()
 
-# --------------------
-# Load PyTorch Resume NER Model
-# --------------------
-MODEL_NAME = "manishiitg/resume-ner"
-
-tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
-model = AutoModelForTokenClassification.from_pretrained(MODEL_NAME)
-ner_pipeline = pipeline("ner", model=model, tokenizer=tokenizer, aggregation_strategy="simple")
-
-# --------------------
-# Extract Text from PDF/DOCX
-# --------------------
-def extract_text(file_path: str) -> str:
-    path = Path(file_path)
-    if path.suffix.lower() == ".pdf":
-        return pdf_extract_text(file_path)
-    elif path.suffix.lower() == ".docx":
-        doc = Document(file_path)
-        return "\n".join([p.text for p in doc.paragraphs])
-    else:
-        raise ValueError("Unsupported file format")
-
-# --------------------
-# Parse Resume
-# --------------------
 def parse_resume(file_path: str, filename: str = None) -> Dict[str, str]:
-    text = extract_text(file_path)
-    entities = ner_pipeline(text)
-
-    name, skills, education, experience = [], [], [], []
-
-    for ent in entities:
-        label = ent["entity_group"].upper()
-        value = ent["word"].strip()
-
-        if label == "NAME":
-            name.append(value)
-        elif label == "SKILL":
-            skills.append(value)
-        elif label in ["EDUCATION", "DEGREE"]:
-            education.append(value)
-        elif label in ["EXPERIENCE", "JOB", "ROLE", "POSITION"]:
-            experience.append(value)
-
-    return {
-        "name": " ".join(dict.fromkeys(name)) or "Not Found",
-        "skills": ", ".join(dict.fromkeys(skills)) or "Not Found",
-        "education": ", ".join(dict.fromkeys(education)) or "Not Found",
-        "experience": ", ".join(dict.fromkeys(experience)) or "Not Found"
-    }
+    """Main function to parse resume"""
+    return resume_parser.parse_resume(file_path, filename)
+
+# Test function
+def test_parser():
+    """Test the parser with sample text"""
+    sample_text = """
+    John Doe
+    Software Engineer
+    [email protected]
+    (555) 123-4567
+    
+    Skills: Python, JavaScript, React, Node.js, SQL
+    
+    Education:
+    Bachelor of Science in Computer Science
+    University of Technology, 2020
+    
+    Experience:
+    Senior Software Developer at Tech Corp (2021-2023)
+    - Developed web applications using React and Node.js
+    - Managed database systems and APIs
+    """
+    
+    # Create a temporary file for testing
+    import tempfile
+    with tempfile.NamedTemporaryFile(mode='w', suffix='.txt', delete=False) as f:
+        f.write(sample_text)
+        temp_path = f.name
+    
+    try:
+        # Test regex extraction
+        regex_results = resume_parser.extract_with_regex(sample_text)
+        print("Regex Results:", json.dumps(regex_results, indent=2))
+        
+        # Test name extraction
+        name = resume_parser.extract_name_from_text(sample_text)
+        print(f"Extracted Name: {name}")
+        
+    except Exception as e:
+        print(f"Test error: {e}")
+    finally:
+        Path(temp_path).unlink(missing_ok=True)
+