Spaces:
Paused
Paused
| from __future__ import annotations | |
| import os | |
| import re | |
| import subprocess | |
| import zipfile | |
| from typing import List | |
| from transformers import pipeline | |
| # Load the NER model for resume parsing | |
| ner = pipeline("ner", model="Kiet/ResumeParserBERT", aggregation_strategy="simple") | |
| def extract_text(file_path: str) -> str: | |
| """Extract text from PDF or DOCX.""" | |
| if not file_path or not os.path.isfile(file_path): | |
| return "" | |
| lower_name = file_path.lower() | |
| try: | |
| if lower_name.endswith('.pdf'): | |
| try: | |
| result = subprocess.run( | |
| ['pdftotext', '-layout', file_path, '-'], | |
| stdout=subprocess.PIPE, | |
| stderr=subprocess.PIPE, | |
| check=False | |
| ) | |
| return result.stdout.decode('utf-8', errors='ignore') | |
| except Exception: | |
| return "" | |
| elif lower_name.endswith('.docx'): | |
| try: | |
| with zipfile.ZipFile(file_path) as zf: | |
| with zf.open('word/document.xml') as docx_xml: | |
| xml_bytes = docx_xml.read() | |
| xml_text = xml_bytes.decode('utf-8', errors='ignore') | |
| xml_text = re.sub(r'<w:p[^>]*>', '\n', xml_text, flags=re.I) | |
| text = re.sub(r'<[^>]+>', ' ', xml_text) | |
| text = re.sub(r'\s+', ' ', text) | |
| return text | |
| except Exception: | |
| return "" | |
| else: | |
| return "" | |
| except Exception: | |
| return "" | |
| def extract_name(text: str, filename: str) -> str: | |
| """Extract candidate's name from text or filename.""" | |
| if text: | |
| lines = [ln.strip() for ln in text.splitlines() if ln.strip()] | |
| for line in lines[:10]: | |
| if re.match(r'(?i)resume|curriculum vitae', line): | |
| continue | |
| words = line.split() | |
| if 1 < len(words) <= 4: | |
| if all(re.match(r'^[A-ZÀ-ÖØ-Þ][\w\-]*', w) for w in words): | |
| return line | |
| base = os.path.basename(filename) | |
| base = re.sub(r'\.(pdf|docx|doc)$', '', base, flags=re.I) | |
| base = re.sub(r'[\._-]+', ' ', base) | |
| base = re.sub(r'(?i)\b(cv|resume)\b', '', base) | |
| base = re.sub(r'\s+', ' ', base).strip() | |
| return base.title() if base else '' | |
| def extract_entities(text: str) -> dict: | |
| """Extract structured info using NER model.""" | |
| entities = ner(text) | |
| skills, education, experience = [], [], [] | |
| for ent in entities: | |
| label = ent['entity_group'].upper() | |
| word = ent['word'].strip() | |
| if label in ["SKILL", "TECH", "TECHNOLOGY"]: | |
| skills.append(word) | |
| elif label in ["EDUCATION", "DEGREE", "QUALIFICATION"]: | |
| education.append(word) | |
| elif label in ["EXPERIENCE", "JOB", "ROLE"]: | |
| experience.append(word) | |
| return { | |
| "skills": list(dict.fromkeys(skills)), | |
| "education": list(dict.fromkeys(education)), | |
| "experience": list(dict.fromkeys(experience)) | |
| } | |
| def parse_resume(file_path: str, filename: str) -> dict: | |
| """Main function to parse resume fields.""" | |
| text = extract_text(file_path) | |
| name = extract_name(text, filename) | |
| ents = extract_entities(text) | |
| return { | |
| 'name': name or '', | |
| 'skills': ', '.join(ents["skills"]) if ents["skills"] else '', | |
| 'education': ', '.join(ents["education"]) if ents["education"] else '', | |
| 'experience': ', '.join(ents["experience"]) if ents["experience"] else '' | |
| } | |