feat: setup dataset enrichment app codebase and scripts

scripts/auto_pull.py

@@ -0,0 +1,46 @@
+#!/usr/bin/env python3
+"""Auto-pull service: monitors origin/main and pulls new commits automatically."""
+
+import os
+import subprocess
+import sys
+import time
+
+INTERVAL_SECONDS = int(os.environ.get("AUTO_PULL_INTERVAL", 30))
+REPO_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
+
+def run_git(args):
+    res = subprocess.run(["git"] + args, cwd=REPO_DIR, capture_output=True, text=True)
+    return res.returncode == 0, res.stdout.strip(), res.stderr.strip()
+
+def check_and_pull():
+    # Fetch latest remote changes quietly
+    ok, _, err = run_git(["fetch", "origin", "main"])
+    if not ok:
+        print(f"[Auto-Pull] Git fetch error: {err}")
+        return
+
+    _, incoming_commits, _ = run_git(["log", "HEAD..origin/main", "--oneline"])
+
+    if incoming_commits:
+        print(f"[Auto-Pull] Incoming commits detected:\n{incoming_commits}")
+        ok, out, err = run_git(["pull", "origin", "main"])
+        if ok:
+            print(f"[Auto-Pull] Successfully pulled:\n{out}")
+            print("[Auto-Pull] Restarting app services...")
+            restart_script = os.path.join(REPO_DIR, "scripts", "restart_app.sh")
+            subprocess.run(["bash", restart_script], cwd=REPO_DIR)
+        else:
+            print(f"[Auto-Pull] Pull failed:\n{err}")
+
+def main():
+    print(f"🔄 Auto-pull background poller started (Interval: {INTERVAL_SECONDS}s)")
+    while True:
+        try:
+            check_and_pull()
+        except Exception as exc:
+            print(f"[Auto-Pull] Error: {exc}")
+        time.sleep(INTERVAL_SECONDS)
+
+if __name__ == "__main__":
+    main()

scripts/restart_app.sh

@@ -0,0 +1,23 @@
+#!/bin/bash
+set -e
+
+REPO_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
+cd "$REPO_DIR"
+
+echo "🔄 Restarting app services..."
+
+# Kill running uvicorn and vite processes
+pkill -f "uvicorn backend.main:app" || true
+pkill -f "vite" || true
+sleep 1
+
+export PATH="$HOME/.local/bin:$PATH"
+
+# Run backend
+nohup uv run uvicorn backend.main:app --host 0.0.0.0 --port 8000 > "$REPO_DIR/data/backend.log" 2>&1 &
+
+# Run frontend
+cd "$REPO_DIR/frontend"
+nohup npm run dev > "$REPO_DIR/data/frontend.log" 2>&1 &
+
+echo "✅ Services restarted."

scripts/webhook.py

@@ -0,0 +1,67 @@
+#!/usr/bin/env python3
+"""GitHub Webhook Listener for Auto-Pull on Push."""
+
+import hmac
+import hashlib
+import json
+import os
+import subprocess
+from http.server import BaseHTTPRequestHandler, HTTPServer
+
+PORT = int(os.environ.get("WEBHOOK_PORT", 9000))
+SECRET = os.environ.get("WEBHOOK_SECRET", "").encode("utf-8")
+REPO_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
+
+class WebhookHandler(BaseHTTPRequestHandler):
+    def do_POST(self):
+        if self.path != "/webhook":
+            self.send_response(404)
+            self.end_headers()
+            return
+
+        content_length = int(self.headers.get("Content-Length", 0))
+        body = self.rfile.read(content_length)
+
+        if SECRET:
+            signature = self.headers.get("X-Hub-Signature-256", "")
+            expected = "sha256=" + hmac.new(SECRET, body, hashlib.sha256).hexdigest()
+            if not hmac.compare_digest(signature, expected):
+                self.send_response(403)
+                self.end_headers()
+                self.wfile.write(b"Invalid signature\n")
+                return
+
+        event = self.headers.get("X-GitHub-Event", "push")
+        if event == "push":
+            print("[Webhook] Received push event. Pulling latest code...")
+            try:
+                result = subprocess.run(
+                    ["git", "pull", "origin", "main"],
+                    cwd=REPO_DIR,
+                    capture_output=True,
+                    text=True,
+                    check=True,
+                )
+                output = result.stdout
+                print(f"[Webhook] Git pull success:\n{output}")
+                self.send_response(200)
+                self.end_headers()
+                self.wfile.write(f"Updated successfully:\n{output}".encode("utf-8"))
+            except subprocess.CalledProcessError as err:
+                error_msg = f"Git pull failed:\n{err.stderr}"
+                print(f"[Webhook] {error_msg}")
+                self.send_response(500)
+                self.end_headers()
+                self.wfile.write(error_msg.encode("utf-8"))
+        else:
+            self.send_response(200)
+            self.end_headers()
+            self.wfile.write(f"Ignored event: {event}\n".encode("utf-8"))
+
+def main():
+    server = HTTPServer(("0.0.0.0", PORT), WebhookHandler)
+    print(f"🚀 GitHub Webhook listener running on http://0.0.0.0:{PORT}/webhook")
+    server.serve_forever()
+
+if __name__ == "__main__":
+    main()