OCR-Viewer (#1)

Co-authored-by: nathan <nathan.kehler@gmail.com>
Reviewed-on: #1

launch_viewer.py

@@ -0,0 +1,152 @@
+#!/usr/bin/env python3
+"""
+P44 OCR Viewer launcher.
+Starts a local HTTP server at port 5044 and opens the viewer in the default browser.
+Run from any directory; the server root is always the project folder (this file's location).
+If port 5044 is already in use (server already running), just opens the browser tab.
+"""
+import http.server
+import webbrowser
+import threading
+import socket
+import os
+import sys
+import json
+from urllib.parse import urlparse, parse_qs
+
+PORT = 5044
+ROOT     = os.path.dirname(os.path.abspath(__file__))
+DATA_DIR = os.path.join(ROOT, 'viewer', 'data')
+
+
+class QuietHandler(http.server.SimpleHTTPRequestHandler):
+    """Serve files from ROOT, suppress request logs, disable browser caching."""
+    def __init__(self, *args, **kwargs):
+        super().__init__(*args, directory=ROOT, **kwargs)
+
+    def log_message(self, fmt, *args):
+        pass  # silence per-request noise
+
+    def end_headers(self):
+        self.send_header('Cache-Control', 'no-store, no-cache, must-revalidate')
+        self.send_header('Pragma', 'no-cache')
+        self.send_header('Expires', '0')
+        super().end_headers()
+
+    def do_POST(self):
+        """Handle POST /save-flags, /save-pass2-flags, /save-corrections, /clear-all-data.
+        All endpoints accept an optional ?diary=ID query param to use per-diary files.
+        """
+        parsed = urlparse(self.path)
+        qs     = parse_qs(parsed.query)
+        diary  = qs.get('diary', ['unknown'])[0]
+        # Sanitize: only allow alphanumeric, hyphens, underscores
+        diary  = ''.join(c for c in diary if c.isalnum() or c in '-_')
+        if not diary:
+            diary = 'unknown'
+
+        length = int(self.headers.get('Content-Length', 0))
+        body   = self.rfile.read(length)
+        try:
+            data = json.loads(body)
+        except json.JSONDecodeError:
+            self.send_response(400); self.end_headers()
+            return
+
+        if parsed.path == '/save-flags':
+            os.makedirs(DATA_DIR, exist_ok=True)
+            dest = os.path.join(DATA_DIR, 'flags-' + diary + '.json')
+            with open(dest, 'w', encoding='utf-8') as f:
+                json.dump(data, f, indent=2)
+            self.send_response(200)
+            self.send_header('Content-Type', 'application/json')
+            self.end_headers()
+            self.wfile.write(b'{"ok":true}')
+
+        elif parsed.path == '/save-corrections':
+            os.makedirs(DATA_DIR, exist_ok=True)
+            dest = os.path.join(DATA_DIR, 'corrections-' + diary + '.json')
+            existing = {}
+            if os.path.exists(dest):
+                try:
+                    with open(dest, 'r', encoding='utf-8') as f:
+                        existing = json.load(f)
+                except Exception:
+                    pass
+            page       = str(data.get('page', ''))
+            correction = data.get('correction')
+            if correction:
+                existing[page] = correction
+            else:
+                existing.pop(page, None)
+            with open(dest, 'w', encoding='utf-8') as f:
+                json.dump(existing, f, indent=2)
+            self.send_response(200)
+            self.send_header('Content-Type', 'application/json')
+            self.end_headers()
+            self.wfile.write(b'{"ok":true}')
+
+        elif parsed.path == '/save-pass2-flags':
+            os.makedirs(DATA_DIR, exist_ok=True)
+            dest = os.path.join(DATA_DIR, 'pass2_flags-' + diary + '.json')
+            try:
+                with open(dest, 'w', encoding='utf-8') as f:
+                    json.dump(data, f, indent=2)
+            except Exception:
+                self.send_response(500); self.end_headers()
+                return
+            self.send_response(200)
+            self.send_header('Content-Type', 'application/json')
+            self.end_headers()
+            self.wfile.write(b'{"ok":true}')
+
+        elif parsed.path == '/clear-all-data':
+            for prefix in ['flags-', 'corrections-', 'pass2_flags-']:
+                fpath = os.path.join(DATA_DIR, prefix + diary + '.json')
+                if os.path.exists(fpath):
+                    try:
+                        os.remove(fpath)
+                    except Exception:
+                        pass
+            self.send_response(200)
+            self.send_header('Content-Type', 'application/json')
+            self.end_headers()
+            self.wfile.write(b'{"ok":true}')
+
+        else:
+            self.send_response(404); self.end_headers()
+
+
+def port_in_use(port):
+    with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as s:
+        return s.connect_ex(('localhost', port)) == 0
+
+
+def start_server():
+    server = http.server.HTTPServer(('localhost', PORT), QuietHandler)
+    server.serve_forever()
+
+
+if __name__ == '__main__':
+    url = 'http://localhost:{}/viewer/p44-landing.html'.format(PORT)
+
+    if port_in_use(PORT):
+        print('\n  P44 OCR Viewer  (server already running)')
+        print('  URL: {}\n'.format(url))
+        webbrowser.open(url)
+    else:
+        t = threading.Thread(target=start_server, daemon=True)
+        t.start()
+        print('\n  P44 OCR Viewer')
+        print('  Serving : {}'.format(ROOT))
+        print('  URL     : {}\n'.format(url))
+        webbrowser.open(url)
+
+    print('Press Enter (or Ctrl-C) to stop the server.\n')
+    try:
+        input()
+    except KeyboardInterrupt:
+        pass
+    print('Server stopped.')
+    sys.exit(0)
+