Create dora_data_loss_prevention.py

tools/dora_data_loss_prevention.py

@@ -0,0 +1,124 @@
+# dora_data_loss_prevention.py
+import datetime
+import re
+from fpdf import FPDF
+from langdetect import detect
+import gradio as gr
+from tools.common import prepend_metadata_questions
+
+# === PDF Export ===
+def export_text_to_pdf(text, metadata=None, output_path=None, language="en"):
+    if output_path is None:
+        timestamp = datetime.datetime.now().strftime("%Y%m%d_%H%M%S")
+        output_path = f"data_loss_prevention_{timestamp}.pdf"
+
+    pdf = FPDF()
+    pdf.add_page()
+    pdf.set_auto_page_break(auto=True, margin=15)
+
+    pdf.set_font("Arial", 'B', 16)
+    pdf.set_text_color(0, 51, 102)
+    title = "Data Loss Prevention Strategy - DORA (Optional)" if language == "en" else "Stratégie de Prévention des Pertes de Données - DORA"
+    pdf.cell(0, 15, title, ln=True, align='C')
+    pdf.ln(10)
+
+    if metadata:
+        pdf.set_font("Arial", '', 12)
+        pdf.set_text_color(90, 90, 90)
+        pdf.multi_cell(0, 10, f"Organization: {metadata.get('organization_name', 'N/A')}")
+        pdf.multi_cell(0, 10, f"Completed by: {metadata.get('user_name', 'N/A')} ({metadata.get('user_role', 'N/A')})")
+        pdf.multi_cell(0, 10, f"Timestamp: {metadata.get('timestamp', 'N/A')}")
+        pdf.ln(5)
+
+    pdf.set_font("Arial", '', 12)
+    pdf.set_text_color(0, 0, 0)
+    for line in text.strip().split('\n'):
+        line = line.strip()
+        if line.startswith("## "):
+            section = line.replace("## ", "").strip()
+            pdf.set_font("Arial", 'B', 13)
+            pdf.set_text_color(30, 30, 120)
+            pdf.ln(8)
+            pdf.cell(0, 10, section, ln=True)
+            pdf.set_font("Arial", '', 12)
+            pdf.set_text_color(0, 0, 0)
+        elif line.startswith("- **"):
+            match = re.match(r"- \*\*(.+?)\*\*: (.+)", line)
+            if match:
+                label, value = match.groups()
+                pdf.set_font("Arial", 'B', 12)
+                pdf.cell(0, 10, f"{label}:", ln=True)
+                pdf.set_font("Arial", '', 12)
+                pdf.multi_cell(0, 10, value)
+        elif line == "---":
+            pdf.line(10, pdf.get_y(), 200, pdf.get_y())
+            pdf.ln(5)
+        else:
+            pdf.multi_cell(0, 10, line)
+    pdf.output(output_path)
+    return output_path
+
+# === Questions ===
+QUESTIONS = prepend_metadata_questions([
+    ("dlp_policies", "Describe the DLP policies currently in place."),
+    ("tools_technologies", "What tools and technologies are used for DLP?"),
+    ("sensitive_data_types", "Which types of sensitive data are protected?"),
+    ("data_exfiltration_prevention", "How do you prevent data exfiltration or leaks?"),
+    ("training_awareness", "Is DLP part of employee training or awareness programs?"),
+    ("incident_history", "Any previous incidents of data loss or leakage? What lessons were learned?")
+])
+
+
+def get_questions():
+    return QUESTIONS
+
+
+def run_tool():
+    state = {"step": 0, "answers": {}}
+
+    def step_by_step_agent(user_input, state):
+        step = state["step"]
+        answers = state["answers"]
+
+        if step > 0:
+            key, _ = QUESTIONS[step - 1]
+            answers[key] = user_input
+
+        if step < len(QUESTIONS):
+            next_question = QUESTIONS[step][1]
+            state["step"] += 1
+            return next_question, state, None
+
+        metadata = {
+            "user_name": answers.get("user_name", "N/A"),
+            "user_role": answers.get("user_role", "N/A"),
+            "organization_name": answers.get("organization_name", "N/A"),
+            "timestamp": datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")
+        }
+
+        content = "\n".join([f"- **{label}**: {answers.get(key, '')}" for key, label in QUESTIONS])
+        lang = detect(content if len(content.strip()) > 3 else "Placeholder content")
+        pdf_path = export_text_to_pdf(content, metadata=metadata, language=lang)
+        return "✅ Report generated. Download below.", {"done": True}, pdf_path
+
+    with gr.Blocks(title="DORA Data Loss Prevention Tool") as demo:
+        chatbot = gr.Chatbot(label="🛡️ DLP Strategy Assistant", value=[{"role": "assistant", "content": QUESTIONS[0][1]}], type="messages")
+        msg = gr.Textbox(label="Your answer")
+        state_var = gr.State(state)
+        file_output = gr.File(label="Download PDF")
+        reset_btn = gr.Button("🔁 Restart")
+
+        def chat_logic(msg_in, state_in):
+            reply, updated_state, file = step_by_step_agent(msg_in, state_in)
+            messages = [{"role": "user", "content": msg_in}]
+            if reply:
+                messages.append({"role": "assistant", "content": reply})
+            return messages, updated_state, file
+
+        def reset():
+            return [{"role": "assistant", "content": QUESTIONS[0][1]}], {"step": 0, "answers": {}}, None
+
+        msg.submit(chat_logic, [msg, state_var], [chatbot, state_var, file_output])
+        reset_btn.click(reset, outputs=[chatbot, state_var, file_output])
+
+    demo.launch(show_api=False)