Update app.py

app.py

@@ -1,215 +1,100 @@
 import gradio as gr
-import json
-from pathlib import Path
-from utils.ai_analyzer import analyze_resume_with_openai
-from config.settings import ALLOWED_EXTENSIONS
+import pdfplumber
+import docx
 
-# Global state
-resume_text_state = ""
-analysis_result_state = None
+# -------- Resume Text Extraction -------- #
 
+def extract_text(file):
+    if file is None:
+        return "Please upload a resume."
 
-def process_resume_file(file_obj):
-    if file_obj is None:
-        return "❌ Please upload a resume file", ""
+    file_name = file.name
 
     try:
-        # file_obj is a filepath string from Gradio's File component
-        file_path = Path(file_obj)
-        file_ext = file_path.suffix.lower()
+        # PDF
+        if file_name.endswith(".pdf"):
+            text = ""
+            with pdfplumber.open(file) as pdf:
+                for page in pdf.pages:
+                    page_text = page.extract_text()
+                    if page_text:
+                        text += page_text
 
-        if file_ext not in ALLOWED_EXTENSIONS:
-            return f"❌ Unsupported file format. Supported: {', '.join(ALLOWED_EXTENSIONS)}", ""
+        # DOCX
+        elif file_name.endswith(".docx"):
+            doc = docx.Document(file)
+            text = "\n".join([p.text for p in doc.paragraphs])
 
-        # Read the file directly from the path
-        with open(file_path, 'rb') as f:
-            from utils.resume_parser import parse_resume
-            resume_text = parse_resume(f.read(), file_ext)
+        else:
+            return "Unsupported file format. Upload PDF or DOCX."
 
-        global resume_text_state
-        resume_text_state = resume_text
-
-        return f"✅ Resume loaded successfully: {file_path.name}", resume_text
-
-    except Exception as e:
-        return f"❌ Error reading file: {str(e)}", ""
-
-
-def analyze_with_ai(resume_text_input):
-    if not resume_text_input or resume_text_input.strip() == "":
-        return "❌ Please upload and load a resume first", "", "", "", "", ""
-
-    try:
-        global analysis_result_state
-        analysis = analyze_resume_with_openai(resume_text_input)
-        analysis_result_state = analysis
-
-        return (
-            format_overall_section(analysis),
-            format_skills_section(analysis),
-            format_experience_section(analysis),
-            format_education_section(analysis),
-            format_gaps_section(analysis),
-            format_recommendations_section(analysis),
-        )
+        return analyze_resume(text)
 
     except Exception as e:
-        return f"❌ Error during analysis: {str(e)}", "", "", "", "", ""
-
-
-def format_overall_section(analysis):
-    score = analysis.get("overall_score", {}).get("rating", 0)
-    explanation = analysis.get("overall_score", {}).get("explanation", "")
-    summary = analysis.get("summary", "")
-
-    return f"""## 📊 Overall Assessment
-
-**Score: {score}/100**
-
-**Explanation:** {explanation}
-
-### 📝 Executive Summary
-{summary}
-"""
-
-
-def format_skills_section(analysis):
-    skills = analysis.get("skills", {})
-    output = "## 🔧 Skills Analysis\n\n### Technical Skills\n"
-
-    technical = skills.get("technical", [])
-    output += "\n".join([f"- {s}" for s in technical]) if technical else "- No technical skills identified\n"
-
-    output += "\n\n### Soft Skills\n"
-    soft = skills.get("soft", [])
-    output += "\n".join([f"- {s}" for s in soft]) if soft else "- No soft skills identified\n"
-
-    output += "\n\n### Skills to Develop\n"
-    missing = skills.get("missing", [])
-    output += "\n".join([f"- ❌ {s}" for s in missing]) if missing else "- No significant gaps identified\n"
+        return f"Error reading file: {str(e)}"
 
-    return output
 
+# -------- Resume Analyzer -------- #
 
-def format_experience_section(analysis):
-    experience = analysis.get("experience", {})
-    output = "## 💼 Experience Review\n\n### Highlights\n"
+def analyze_resume(text):
 
-    for h in experience.get("highlights", []):
-        output += f"- ✅ {h}\n"
+    skills = [
+        "python","machine learning","deep learning","data science",
+        "sql","pandas","numpy","tensorflow","pytorch",
+        "nlp","git","docker","flask","fastapi"
+    ]
 
-    output += "\n### Concerns\n"
-    for c in experience.get("concerns", []):
-        output += f"- ⚠️ {c}\n"
+    found_skills = []
 
-    return output
+    for skill in skills:
+        if skill.lower() in text.lower():
+            found_skills.append(skill)
 
+    score = min(len(found_skills) * 10, 100)
 
-def format_education_section(analysis):
-    education = analysis.get("education", {})
-    return f"""## 🎓 Education Background
+    result = f"""
+Resume Score: {score}/100
 
-**Details:** {education.get('details', 'No education information provided')}
+Detected Skills:
+{', '.join(found_skills) if found_skills else 'No major skills detected'}
 
-**Relevance:** {education.get('relevant', 'N/A')}
+Suggestions:
+• Add more technical skills
+• Include projects
+• Mention measurable achievements
+• Use clear headings
 """
 
+    return result
 
-def format_gaps_section(analysis):
-    output = "## 🔍 Career Gaps & Concerns\n\n"
-
-    gaps = analysis.get("career_gaps", [])
-    output += "\n".join([f"- {g}" for g in gaps]) if gaps else "✅ No significant career gaps identified\n"
-
-    job_compat = analysis.get("job_compatibility", {})
-    output += "\n\n## 🎯 Job Market Compatibility\n\n### Strengths\n"
-
-    for s in job_compat.get("strengths", []):
-        output += f"- ✅ {s}\n"
-
-    output += "\n### Areas to Improve\n"
-    for w in job_compat.get("weaknesses", []):
-        output += f"- ⚠️ {w}\n"
-
-    return output
-
-
-def format_recommendations_section(analysis):
-    recs = analysis.get("recommendations", [])
-    output = "## 💡 Improvement Recommendations\n\n"
-
-    for i, r in enumerate(recs, 1):
-        output += f"{i}. {r}\n"
-
-    return output if recs else output + "No specific recommendations available\n"
-
-
-def export_json(_):
-    if analysis_result_state is None:
-        return "No analysis available to export"
-
-    return json.dumps(analysis_result_state, indent=2)
-
-
-def export_text(_):
-    if analysis_result_state is None:
-        return "No analysis available to export"
-
-    analysis = analysis_result_state
-    report = "RESUME ANALYSIS REPORT\n" + "=" * 60 + "\n\n"
-    report += f"OVERALL SCORE: {analysis.get('overall_score', {}).get('rating', 0)}/100\n"
-    report += f"Rating: {analysis.get('overall_score', {}).get('explanation', '')}\n\n"
-    report += analysis.get("summary", "")
-
-    return report
-
-
-def create_interface():
-    with gr.Blocks(title="Resume Analyzer", theme=gr.themes.Soft()) as demo:
 
-        gr.Markdown("""
-        # 📄 Resume Analyzer
-        ### AI-Powered Resume Analysis & Recommendations
-        """)
+# -------- Gradio UI -------- #
 
-        with gr.Tab("📤 Upload & Analyze"):
-            file_upload = gr.File(label="Upload Resume", file_types=[".pdf", ".docx", ".doc", ".txt"], type="filepath")
-            load_button = gr.Button("📖 Load Resume")
-            status_output = gr.Textbox(label="Status", interactive=False)
-            resume_preview = gr.Textbox(label="Resume Preview", lines=10, interactive=False)
-            analyze_button = gr.Button("🤖 Analyze with AI", variant="primary")
+with gr.Blocks(title="Resume Analyzer") as demo:
 
-            overall_output = gr.Markdown()
-            skills_output = gr.Markdown()
-            experience_output = gr.Markdown()
-            education_output = gr.Markdown()
-            gaps_output = gr.Markdown()
-            recommendations_output = gr.Markdown()
+    gr.Markdown("# 📄 AI Resume Analyzer")
+    gr.Markdown("Upload your resume and get instant feedback.")
 
-            load_button.click(process_resume_file, file_upload, [status_output, resume_preview])
-            analyze_button.click(
-                analyze_with_ai,
-                resume_preview,
-                [overall_output, skills_output, experience_output, education_output, gaps_output, recommendations_output]
-            )
+    resume_input = gr.File(
+        label="Upload Resume",
+        file_types=[".pdf", ".docx"]
+    )
 
-        with gr.Tab("📥 Export Results"):
-            json_btn = gr.Button("📋 Export as JSON")
-            json_output = gr.Textbox(lines=15, interactive=False)
+    analyze_btn = gr.Button("Analyze Resume")
 
-            text_btn = gr.Button("📄 Export as Text")
-            text_output = gr.Textbox(lines=15, interactive=False)
+    output_box = gr.Textbox(
+        label="Analysis Result",
+        lines=15
+    )
 
-            json_btn.click(export_json, inputs=[], outputs=json_output)
-            text_btn.click(export_text, inputs=[], outputs=text_output)
+    analyze_btn.click(
+        fn=extract_text,
+        inputs=resume_input,
+        outputs=output_box
+    )
 
-    return demo
 
+# -------- Launch App -------- #
 
 if __name__ == "__main__":
-    demo = create_interface()
-    demo.launch(
-        server_name="0.0.0.0",
-        server_port=7861,
-        share=True
-    )
+    demo.launch()