utils/spacy.py

import spacy 
import logging 
import json 
from utils.fileTotext import extract_text_based_on_format 
import re 
 
def is_valid_email(email): 
 email_regex = r'^[a-zA-Z0-9_.+-]+@[a-zA-Z0-9-]+\.[a-zA-Z0-9-.]+$' 
 return re.match(email_regex, email) is not None 
 
def is_valid_contact(contact): 
 patterns = [ 
 r'^\+91[\s\.\-\/]?\(?0?\)?[\s\-\.\/]?\d{5}[\s\-\.\/]?\d{5}$', # +91 with optional 0 and separators 
 r'^\+91[\s\.\-\/]?\d{5}[\s\-\.\/]?\d{5}$', # +91 with 10 digits separated 
 r'^\d{5}[\s\-\.\/]?\d{5}$', # Local format without country code 
 r'^\+91[\s\.\-\/]?\d{10}$', # +91 with 10 digits together 
 r'^\d{10}$', # 10 digits together 
 r'^\+91[\s\.\-\/]?\(?\d{5}\)?[\s\-\.\/]?\d{5}[\s\-\.\/]?\d{5}$' # +91 with varying separators 
 r'\+1\s\(\d{3}\)\s\d{3}-\d{4} ', # USA/Canada Intl +1 (XXX) XXX-XXXX 
 r'\(\d{3}\)\s\d{3}-\d{4} ', # USA/Canada STD (XXX) XXX-XXXX 
 r'\(\d{3}\)\s\d{3}\s\d{4} ', # USA/Canada (XXX) XXX XXXX 
 r'\(\d{3}\)\s\d{3}\s\d{3} ', # USA/Canada (XXX) XXX XXX 
 r'\+1\d{10} ', # +1 XXXXXXXXXX 
 r'\d{10} ', # XXXXXXXXXX 
 r'\+44\s\d{4}\s\d{6} ', # UK Intl +44 XXXX XXXXXX 
 r'\+44\s\d{3}\s\d{3}\s\d{4} ', # UK Intl +44 XXX XXX XXXX 
 r'0\d{4}\s\d{6} ', # UK STD 0XXXX XXXXXX 
 r'0\d{3}\s\d{3}\s\d{4} ', # UK STD 0XXX XXX XXXX 
 r'\+44\d{10} ', # +44 XXXXXXXXXX 
 r'0\d{10} ', # 0XXXXXXXXXX 
 r'\+61\s\d\s\d{4}\s\d{4} ', # Australia Intl +61 X XXXX XXXX 
 r'0\d\s\d{4}\s\d{4} ', # Australia STD 0X XXXX XXXX 
 r'\+61\d{9} ', # +61 XXXXXXXXX 
 r'0\d{9} ', # 0XXXXXXXXX 
 r'\+91\s\d{5}-\d{5} ', # India Intl +91 XXXXX-XXXXX 
 r'\+91\s\d{4}-\d{6} ', # India Intl +91 XXXX-XXXXXX 
 r'\+91\s\d{10} ', # India Intl +91 XXXXXXXXXX 
 r'0\d{2}-\d{7} ', # India STD 0XX-XXXXXXX 
 r'\+91\d{10} ', # +91 XXXXXXXXXX 
 r'\+49\s\d{4}\s\d{8} ', # Germany Intl +49 XXXX XXXXXXXX 
 r'\+49\s\d{3}\s\d{7} ', # Germany Intl +49 XXX XXXXXXX 
 r'0\d{3}\s\d{8} ', # Germany STD 0XXX XXXXXXXX 
 r'\+49\d{12} ', # +49 XXXXXXXXXXXX 
 r'\+49\d{10} ', # +49 XXXXXXXXXX 
 r'0\d{11} ', # 0XXXXXXXXXXX 
 r'\+86\s\d{3}\s\d{4}\s\d{4} ', # China Intl +86 XXX XXXX XXXX 
 r'0\d{3}\s\d{4}\s\d{4} ', # China STD 0XXX XXXX XXXX 
 r'\+86\d{11} ', # +86 XXXXXXXXXXX 
 r'\+81\s\d\s\d{4}\s\d{4} ', # Japan Intl +81 X XXXX XXXX 
 r'\+81\s\d{2}\s\d{4}\s\d{4} ', # Japan Intl +81 XX XXXX XXXX 
 r'0\d\s\d{4}\s\d{4} ', # Japan STD 0X XXXX XXXX 
 r'\+81\d{10} ', # +81 XXXXXXXXXX 
 r'\+81\d{9} ', # +81 XXXXXXXXX 
 r'0\d{9} ', # 0XXXXXXXXX 
 r'\+55\s\d{2}\s\d{5}-\d{4} ', # Brazil Intl +55 XX XXXXX-XXXX 
 r'\+55\s\d{2}\s\d{4}-\d{4} ', # Brazil Intl +55 XX XXXX-XXXX 
 r'0\d{2}\s\d{4}\s\d{4} ', # Brazil STD 0XX XXXX XXXX 
 r'\+55\d{11} ', # +55 XXXXXXXXXXX 
 r'\+55\d{10} ', # +55 XXXXXXXXXX 
 r'0\d{10} ', # 0XXXXXXXXXX 
 r'\+33\s\d\s\d{2}\s\d{2}\s\d{2}\s\d{2} ', # France Intl +33 X XX XX XX XX 
 r'0\d\s\d{2}\s\d{2}\s\d{2}\s\d{2} ', # France STD 0X XX XX XX XX 
 r'\+33\d{9} ', # +33 XXXXXXXXX 
 r'0\d{9} ', # 0XXXXXXXXX 
 r'\+7\s\d{3}\s\d{3}-\d{2}-\d{2} ', # Russia Intl +7 XXX XXX-XX-XX 
 r'8\s\d{3}\s\d{3}-\d{2}-\d{2} ', # Russia STD 8 XXX XXX-XX-XX 
 r'\+7\d{10} ', # +7 XXXXXXXXXX 
 r'8\d{10} ', # 8 XXXXXXXXXX 
 r'\+27\s\d{2}\s\d{3}\s\d{4} ', # South Africa Intl +27 XX XXX XXXX 
 r'0\d{2}\s\d{3}\s\d{4} ', # South Africa STD 0XX XXX XXXX 
 r'\+27\d{9} ', # +27 XXXXXXXXX 
 r'0\d{9} ', # 0XXXXXXXXX 
 r'\+52\s\d{3}\s\d{3}\s\d{4} ', # Mexico Intl +52 XXX XXX XXXX 
 r'\+52\s\d{2}\s\d{4}\s\d{4} ', # Mexico Intl +52 XX XXXX XXXX 
 r'01\s\d{3}\s\d{4} ', # Mexico STD 01 XXX XXXX 
 r'\+52\d{10} ', # +52 XXXXXXXXXX 
 r'01\d{7} ', # 01 XXXXXXX 
 r'\+234\s\d{3}\s\d{3}\s\d{4} ', # Nigeria Intl +234 XXX XXX XXXX 
 r'0\d{3}\s\d{3}\s\d{4} ', # Nigeria STD 0XXX XXX XXXX 
 r'\+234\d{10} ', # +234 XXXXXXXXXX 
 r'0\d{10} ', # 0XXXXXXXXXX 
 r'\+971\s\d\s\d{3}\s\d{4} ', # UAE Intl +971 X XXX XXXX 
 r'0\d\s\d{3}\s\d{4} ', # UAE STD 0X XXX XXXX 
 r'\+971\d{8} ', # +971 XXXXXXXX 
 r'0\d{8} ', # 0XXXXXXXX 
 r'\+54\s9\s\d{3}\s\d{3}\s\d{4} ', # Argentina Intl +54 9 XXX XXX XXXX 
 r'\+54\s\d{1}\s\d{4}\s\d{4} ', # Argentina Intl +54 X XXXX XXXX 
 r'0\d{3}\s\d{4} ', # Argentina STD 0XXX XXXX 
 r'\+54\d{10} ', # +54 9 XXXXXXXXXX 
 r'\+54\d{9} ', # +54 XXXXXXXXX 
 r'0\d{7} ', # 0XXXXXXX 
 r'\+966\s\d\s\d{3}\s\d{4} ', # Saudi Intl +966 X XXX XXXX 
 r'0\d\s\d{3}\s\d{4} ', # Saudi STD 0X XXX XXXX 
 r'\+966\d{8} ', # +966 XXXXXXXX 
 r'0\d{8} ', # 0XXXXXXXX 
 r'\+1\d{10} ', # +1 XXXXXXXXXX 
 r'\+1\s\d{3}\s\d{3}\s\d{4} ', # +1 XXX XXX XXXX 
 r'\d{5}\s\d{5} ', # XXXXX XXXXX  
 r'\d{10} ', # XXXXXXXXXX 
 r'\+44\d{10} ', # +44 XXXXXXXXXX 
 r'0\d{10} ', # 0XXXXXXXXXX 
 r'\+61\d{9} ', # +61 XXXXXXXXX 
 r'0\d{9} ', # 0XXXXXXXXX 
 r'\+91\d{10} ', # +91 XXXXXXXXXX 
 r'\+49\d{12} ', # +49 XXXXXXXXXXXX 
 r'\+49\d{10} ', # +49 XXXXXXXXXX 
 r'0\d{11} ', # 0XXXXXXXXXXX 
 r'\+86\d{11} ', # +86 XXXXXXXXXXX 
 r'\+81\d{10} ', # +81 XXXXXXXXXX 
 r'\+81\d{9} ', # +81 XXXXXXXXX 
 r'0\d{9} ', # 0XXXXXXXXX 
 r'\+55\d{11} ', # +55 XXXXXXXXXXX 
 r'\+55\d{10} ', # +55 XXXXXXXXXX 
 r'0\d{10} ', # 0XXXXXXXXXX 
 r'\+33\d{9} ', # +33 XXXXXXXXX 
 r'0\d{9} ', # 0XXXXXXXXX 
 r'\+7\d{10} ', # +7 XXXXXXXXXX 
 r'8\d{10} ', # 8 XXXXXXXXXX 
 r'\+27\d{9} ', # +27 XXXXXXXXX 
 r'0\d{9} ', # 0XXXXXXXXX (South Africa STD) 
 r'\+52\d{10} ', # +52 XXXXXXXXXX 
 r'01\d{7} ', # 01 XXXXXXX 
 r'\+234\d{10} ', # +234 XXXXXXXXXX 
 r'0\d{10} ', # 0XXXXXXXXXX 
 r'\+971\d{8} ', # +971 XXXXXXXX 
 r'0\d{8} ', # 0XXXXXXXX 
 r'\+54\s9\s\d{10} ', # +54 9 XXXXXXXXXX 
 r'\+54\d{9} ', # +54 XXXXXXXXX 
 r'0\d{7} ', # 0XXXXXXX 
 r'\+966\d{8} ', # +966 XXXXXXXX 
 r'0\d{8}' # 0XXXXXXXX 
 ] 
 
 # Check if the contact matches any of the patterns 
 return any(re.match(pattern, contact) for pattern in patterns) is not None 
 
# Function to parse resume with SpaCy 
# Function to parse resume with SpaCy 
def Parser_from_model(file_path): 
 result = { 
 "personal": { 
 "name": '', 
 "contact": '', 
 "email": '', 
 "location": '', 
 "link": '', 
 "invalid_email": '', 
 "invalid_contact": '' 
 }, 
 "professional": { 
 "technical_skills": [], 
 "non_technical_skills": [], 
 "tools": [], 
 "experience": [ 
 { 
 "company": '', 
 "projects": '', 
 "role": '', 
 "years": '', 
 "project_experience": [] 
 } 
 ], 
 "education": [ 
 { 
 "qualification": '', 
 "university": '', 
 "course": '', 
 "certificate": '' 
 } 
 ] 
 } 
 } 
 
 try: 
 nlp = spacy.load("Spacy_Models/ner_model_05_3") 
 logging.debug("Model loaded successfully.") 
 except Exception as e: 
 logging.error(f"Error loading model: {e}") 
 return {"error": "Model loading failed"} 
 
 try: 
 cleaned_text, hyperlinks = extract_text_based_on_format(file_path) 
 if not cleaned_text.strip(): 
 logging.error("No text extracted from the file.") 
 return {"error": "Text extraction failed"} 
 except Exception as e: 
 logging.error(f"Error extracting text from file: {e}") 
 return {"error": "Text extraction failed"} 
 
 try: 
 doc = nlp(cleaned_text) 
 except Exception as e: 
 logging.error(f"Error processing text with SpaCy: {e}") 
 return {"error": "Text processing failed"} 
 
 # Initialize entities as a dictionary with lists 
 entities = {label: [] for label in ['PERSON', 'EMAIL', 'CONTACT', 'LOCATION', 'SKILL', 'SOFT_SKILL', 'COMPANY', 'PROJECTS', 'JOB_TITLE', 'YEARS_EXPERIENCE', 'EXPERIENCE', 'QUALIFICATION', 'UNIVERSITY', 'COURSE', 'CERTIFICATE']} 
 
 # Process entities 
 for ent in doc.ents: 
 if ent.label_ in entities: 
 if ent.text not in entities[ent.label_]: # Avoid duplicates 
 entities[ent.label_].append(ent.text) 
 
 # Map entities to the result JSON 
 result['personal']['name'] = entities.get('PERSON', [''])[0] if entities.get('PERSON', []) else '' 
 
 # Validate email 
 extracted_email = entities.get('EMAIL', [''])[0] if entities.get('EMAIL', []) else '' 
 if is_valid_email(extracted_email): 
 result['personal']['email'] = extracted_email 
 else: 
 logging.warning(f"Invalid email detected: {extracted_email}") 
 result['personal']['email'] = "Invalid email" 
 result['personal']['invalid_email'] = extracted_email 
 
 # Validate contact 
 extracted_contact = entities.get('CONTACT', [''])[0] if entities.get('CONTACT', []) else '' 
 if is_valid_contact(extracted_contact): 
 result['personal']['contact'] = extracted_contact 
 else: 
 logging.warning(f"Invalid contact detected: {extracted_contact}") 
 result['personal']['contact'] = "Invalid contact" 
 result['personal']['invalid_contact'] = extracted_contact 
 
 result['personal']['location'] = entities.get('LOCATION', [''])[0] if entities.get('LOCATION', []) else '' 
 result['personal']['link'] = hyperlinks # Hyperlinks from extracted text 
 
 result['professional']['technical_skills'] = entities.get('SKILL', []) 
 result['professional']['non_technical_skills'] = entities.get('SOFT_SKILL', []) 
 result['professional']['tools'] = [] # Add logic if tools extraction is needed 
 
 result['professional']['experience'][0]['company'] = entities.get('COMPANY', [''])[0] if entities.get('COMPANY', []) else '' 
 result['professional']['experience'][0]['projects'] = entities.get('PROJECTS', [''])[0] if entities.get('PROJECTS', []) else '' 
 result['professional']['experience'][0]['role'] = entities.get('JOB_TITLE', [''])[0] if entities.get('JOB_TITLE', []) else '' 
 result['professional']['experience'][0]['years'] = entities.get('YEARS_EXPERIENCE', [''])[0] if entities.get('YEARS_EXPERIENCE', []) else '' 
 result['professional']['experience'][0]['project_experience'] = entities.get('EXPERIENCE', []) 
 
 result['professional']['education'][0]['qualification'] = entities.get('QUALIFICATION', [''])[0] if entities.get('QUALIFICATION', []) else '' 
 result['professional']['education'][0]['university'] = entities.get('UNIVERSITY', [''])[0] if entities.get('UNIVERSITY', []) else '' 
 result['professional']['education'][0]['course'] = entities.get('COURSE', [''])[0] if entities.get('COURSE', []) else '' 
 result['professional']['education'][0]['certificate'] = entities.get('CERTIFICATE', [''])[0] if entities.get('CERTIFICATE', []) else '' 
 
 print(result) 
 return result