Update app.py

app.py

@@ -1,214 +1,33 @@
 import gradio as gr
-import sqlite3
-import re
-import numpy as np
 import pandas as pd
 from PyPDF2 import PdfReader
-from docx import Document
 from sentence_transformers import SentenceTransformer
-from sklearn.metrics.pairwise import cosine_similarity
 import spacy
-from datetime import datetime
-from fpdf import FPDF
-import hashlib
-import subprocess
 
-# ---------------------------
-# Load SpaCy model
-# ---------------------------
-try:
-    nlp = spacy.load("en_core_web_sm")
-except OSError:
-    subprocess.run(["python", "-m", "spacy", "download", "en_core_web_sm"])
-    nlp = spacy.load("en_core_web_sm")
-
-# ---------------------------
-# Load Sentence Transformer
-# ---------------------------
-model = SentenceTransformer('all-MiniLM-L6-v2')
-
-# ---------------------------
-# SQLite DB setup
-# ---------------------------
-conn = sqlite3.connect('resumes.db', check_same_thread=False)
-cursor = conn.cursor()
-
-cursor.execute("""
-CREATE TABLE IF NOT EXISTS users (
-    id INTEGER PRIMARY KEY,
-    username TEXT UNIQUE,
-    password_hash TEXT
-)
-""")
-
-cursor.execute("""
-CREATE TABLE IF NOT EXISTS analyses (
-    id INTEGER PRIMARY KEY,
-    user_id INTEGER,
-    resume_text TEXT,
-    jd_text TEXT,
-    final_score REAL,
-    keyword_score REAL,
-    semantic_score REAL,
-    section_scores TEXT,
-    tips TEXT,
-    date TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
-    FOREIGN KEY(user_id) REFERENCES users(id)
-)
-""")
-conn.commit()
-
-# ---------------------------
-# Authentication Functions
-# ---------------------------
-def hash_password(password):
-    return hashlib.sha256(password.encode()).hexdigest()
-
-def signup(username, password):
-    try:
-        cursor.execute("INSERT INTO users (username, password_hash) VALUES (?,?)",
-                       (username, hash_password(password)))
-        conn.commit()
-        return "✅ Signup successful! Please login."
-    except sqlite3.IntegrityError:
-        return "❌ Username already exists. Try a different one."
-
-def login(username, password):
-    cursor.execute("SELECT id, password_hash FROM users WHERE username=?", (username,))
-    row = cursor.fetchone()
-    if row and row[1] == hash_password(password):
-        return f"✅ Login successful! User ID: {row[0]}", row[0]
+# Load model
+nlp = spacy.load("en_core_web_sm")
+embedder = SentenceTransformer('all-MiniLM-L6-v2')  # lightweight embedding model
+
+def extract_text(file):
+    if file.name.endswith(".pdf"):
+        reader = PdfReader(file.name)
+        text = ""
+        for page in reader.pages:
+            text += page.extract_text()
+        return text
     else:
-        return "❌ Invalid username or password", None
-
-# ---------------------------
-# Resume Parsing
-# ---------------------------
-def extract_text_from_pdf(file):
-    reader = PdfReader(file)
-    text = ""
-    for page in reader.pages:
-        text += page.extract_text() or ""
-    return text
-
-def extract_text_from_docx(file):
-    doc = Document(file)
-    text = "\n".join([p.text for p in doc.paragraphs])
-    return text
-
-def extract_skills(jd_text):
-    skills = re.split(r"[,\n;]", jd_text)
-    return [s.strip() for s in skills if s.strip()]
-
-def split_sections(resume_text):
-    sections = {"Education":"","Experience":"","Skills":""}
-    edu = re.search(r'(Education|EDUCATION)(.*?)(Experience|EXPERIENCE|Skills|SKILLS|$)', resume_text, re.DOTALL)
-    exp = re.search(r'(Experience|EXPERIENCE)(.*?)(Skills|SKILLS|$)', resume_text, re.DOTALL)
-    skills = re.search(r'(Skills|SKILLS)(.*)', resume_text, re.DOTALL)
-    if edu: sections["Education"] = edu.group(2).strip()
-    if exp: sections["Experience"] = exp.group(2).strip()
-    if skills: sections["Skills"] = skills.group(2).strip()
-    return sections
-
-def compute_scores(resume_text, jd_text, required_skills):
-    present_skills = [kw for kw in required_skills if kw.lower() in resume_text.lower()]
-    keyword_score = len(present_skills)/max(len(required_skills),1)
-    res_vec = model.encode(resume_text)
-    jd_vec  = model.encode(jd_text)
-    semantic_score = cosine_similarity([res_vec],[jd_vec])[0][0]
-    sections = split_sections(resume_text)
-    section_scores = {}
-    for sec, text in sections.items():
-        sec_present = [kw for kw in required_skills if kw.lower() in text.lower()]
-        section_scores[sec] = len(sec_present)/max(len(required_skills),1)
-    final_score = 0.6*keyword_score + 0.4*semantic_score
-    tips = [f"⚠️ Add '{skill}' to improve ATS match" for skill in required_skills if skill.lower() not in resume_text.lower()]
-    return final_score, keyword_score, semantic_score, section_scores, tips
-
-# ---------------------------
-# CSV/PDF Export
-# ---------------------------
-def export_csv(df, filename="ats_report.csv"):
-    df.to_csv(filename, index=False)
-    return filename
-
-def export_pdf(df, filename="ats_report.pdf"):
-    pdf = FPDF()
-    pdf.add_page()
-    pdf.set_font("Arial", size=12)
-    pdf.cell(200, 10, txt="ATS Resume Screening Report", ln=True, align="C")
-    pdf.ln(10)
-    for i, row in df.iterrows():
-        pdf.cell(200, 10, txt=f"JD {i+1}: {row['JD']}", ln=True)
-        pdf.cell(200, 10, txt=f"Final Score: {row['Final Score']}", ln=True)
-        pdf.cell(200, 10, txt=f"Keyword Score: {row['Keyword Score']}", ln=True)
-        pdf.cell(200, 10, txt=f"Semantic Score: {row['Semantic Score']}", ln=True)
-        pdf.cell(200, 10, txt="Section Scores:", ln=True)
-        pdf.multi_cell(0, 10, row["Section Scores"])
-        pdf.cell(200, 10, txt="Tips:", ln=True)
-        pdf.multi_cell(0, 10, row["Tips"])
-        pdf.ln(5)
-    pdf.output(filename)
-    return filename
-
-# ---------------------------
-# AI Resume Rewriter
-# ---------------------------
-def ai_resume_rewriter(resume_text, jd_text):
-    required_skills = extract_skills(jd_text)
-    rewritten = resume_text
-    for skill in required_skills:
-        if skill.lower() not in resume_text.lower():
-            rewritten += f"\n- Experience with {skill}"
-    return rewritten
-
-# ---------------------------
-# Feedback Generator
-# ---------------------------
-skill_course_mapping = {
-    "Python": ["Complete 'Python for Everybody' on Coursera", "Try Python projects on GitHub"],
-    "Machine Learning": ["Take 'Machine Learning' by Andrew Ng on Coursera", "Kaggle ML competitions"],
-    "Deep Learning": ["DeepLearning.AI TensorFlow Developer Course", "Build neural network projects"],
-    "SQL": ["SQL for Data Science - Coursera", "Practice on LeetCode SQL problems"],
-    "AWS": ["AWS Certified Solutions Architect - Associate", "AWS Free Tier practice"],
-    "TensorFlow": ["TensorFlow in Practice Specialization - Coursera", "Hands-on DL projects"]
-}
-
-certification_mapping = {
-    "AWS": "AWS Certified Solutions Architect",
-    "ML": "Machine Learning by Andrew Ng",
-    "Python": "PCAP: Python Certified Associate Programmer",
-    "TensorFlow": "TensorFlow Developer Certificate"
-}
-
-def generate_feedback(resume_text, jd_text):
-    required_skills = extract_skills(jd_text)
-    resume_lower = resume_text.lower()
-    
-    missing_skills = [skill for skill in required_skills if skill.lower() not in resume_lower]
-    skill_suggestions = []
-    cert_suggestions = []
-    
-    for skill in missing_skills:
-        if skill in skill_course_mapping:
-            skill_suggestions.append(f"{skill}: {', '.join(skill_course_mapping[skill])}")
-        if skill in certification_mapping:
-            cert_suggestions.append(f"Consider certification: {certification_mapping[skill]}")
-    
-    resume_tips = []
-    if "Education" not in resume_text:
-        resume_tips.append("Include an Education section if missing.")
-    if "Experience" not in resume_text:
-        resume_tips.append("Include an Experience section with quantified achievements.")
-    if "Skills" not in resume_text:
-        resume_tips.append("Add a Skills section highlighting relevant skills.")
-    if len(resume_text.split()) < 200:
-        resume_tips.append("Consider expanding your resume to at least 1 page (200+ words).")
+        return "Unsupported file type"
+
+def analyze_text(text):
+    doc = nlp(text)
+    sentences = [sent.text for sent in doc.sents]
+    embeddings = embedder.encode(sentences)
+    return "\n".join(sentences[:5])  # first 5 sentences for demo
+
+with gr.Blocks() as demo:
+    gr.Markdown("# PDF Text Extractor & Analyzer")
+    pdf_input = gr.File(label="Upload PDF")
+    output_text = gr.Textbox(label="Extracted Text")
+    pdf_input.upload(extract_text, pdf_input, output_text)
     
-    feedback = {
-        "Missing Skills": missing_skills,
-        "Skill Suggestions": skill_suggestions,
-        "Certifications": cert_suggestions,
-        "Resume Tips": resume_tips
-    }
-    return feedback
+demo.launch()