MarketingTool/apps/web/server.py

#!/usr/bin/env python3
"""Same-origin static web server with a narrow internal API reverse proxy."""
from __future__ import annotations

import http.client
import json
import os
from http.server import SimpleHTTPRequestHandler, ThreadingHTTPServer
from urllib.parse import urlsplit

MAX_PROXY_BODY = 5 * 1024 * 1024
UPSTREAM_HOST = os.environ.get("API_UPSTREAM_HOST", "api")
UPSTREAM_PORT = int(os.environ.get("API_UPSTREAM_PORT", "8000"))


class ProxyStaticHandler(SimpleHTTPRequestHandler):
    proxy_api = True

    def _send_json_error(self, status: int, code: str) -> None:
        payload = json.dumps({"error": code}, separators=(",", ":")).encode()
        self.send_response(status)
        self.send_header("Content-Type", "application/json; charset=utf-8")
        self.send_header("Cache-Control", "no-store, private")
        self.send_header("Content-Length", str(len(payload)))
        self.end_headers()
        self.wfile.write(payload)

    def end_headers(self):
        # Always revalidate HTML and JS assets so new releases are picked up.
        content_type = self.headers.get("Content-Type", "")
        if "text/html" in content_type or "text/javascript" in content_type or "application/javascript" in content_type:
            self.send_header("Cache-Control", "no-cache, no-store, must-revalidate")
            self.send_header("Pragma", "no-cache")
            self.send_header("Expires", "0")
        super().end_headers()

    def _proxy_request(self) -> None:
        parsed = urlsplit(self.path)
        if parsed.path == "/api" or parsed.path.startswith("/api/"):
            target = self.path
        else:
            self._send_json_error(404, "not_found")
            return
        try:
            length = int(self.headers.get("Content-Length", "0"))
        except ValueError:
            self._send_json_error(400, "invalid_content_length")
            return
        if length > MAX_PROXY_BODY:
            self._send_json_error(413, "request_body_too_large")
            return
        body = self.rfile.read(length) if length else None
        headers = {
            key: value
            for key, value in self.headers.items()
            if key.lower() in {"accept", "content-type", "cookie", "user-agent", "x-request-id"}
        }
        headers["Host"] = f"{UPSTREAM_HOST}:{UPSTREAM_PORT}"
        connection = None
        try:
            connection = http.client.HTTPConnection(UPSTREAM_HOST, UPSTREAM_PORT, timeout=15)
            connection.request(self.command, target, body=body, headers=headers)
            response = connection.getresponse()
            payload = response.read(MAX_PROXY_BODY + 1)
            if len(payload) > MAX_PROXY_BODY:
                self._send_json_error(502, "upstream_response_too_large")
                return
            self.send_response(response.status, response.reason)
            for key, value in response.getheaders():
                if key.lower() in {"content-type", "content-length", "cache-control", "location", "set-cookie"}:
                    self.send_header(key, value)
            self.send_header("Cache-Control", "no-store, private")
            self.end_headers()
            self.wfile.write(payload)
        except (OSError, http.client.HTTPException) as exc:
            self._send_json_error(502, "api_upstream_unavailable")
        finally:
            if connection is not None:
                connection.close()

    def do_GET(self):
        if self.path.startswith("/api"):
            return self._proxy_request()
        return super().do_GET()

    def send_head(self):
        import os
        from urllib.parse import unquote
        from http import HTTPStatus
        path = self.translate_path(self.path)
        f = None
        if os.path.isdir(path):
            parts = self.path.split("?", 1)
            if not parts[0].endswith("/"):
                self.send_response(HTTPStatus.MOVED_PERMANENTLY)
                self.send_header("Location", parts[0] + "/")
                self.end_headers()
                return None
            for index in "index.html", "index.htm":
                index = os.path.join(path, index)
                if os.path.exists(index):
                    path = index
                    break
            else:
                return self.list_directory(path)
        ctype = self.guess_type(path)
        try:
            f = open(path, "rb")
        except OSError:
            self.send_error(HTTPStatus.NOT_FOUND, "File not found")
            return None
        try:
            fs = os.fstat(f.fileno())
            content_length = str(int(fs[6]))
            self.send_response(HTTPStatus.OK)
            self.send_header("Content-Type", ctype)
            self.send_header("Content-Length", content_length)
            if "text/html" in ctype or "text/javascript" in ctype or "application/javascript" in ctype:
                self.send_header("Cache-Control", "no-cache, no-store, must-revalidate")
                self.send_header("Pragma", "no-cache")
                self.send_header("Expires", "0")
            self.send_header("Last-Modified", self.date_time_string(fs.st_mtime))
            self.end_headers()
            return f
        except:
            f.close()
            raise
        return result

    def do_POST(self):
        if self.path.startswith("/api"):
            return self._proxy_request()
        return self.send_error(405)

    def do_PATCH(self):
        if self.path.startswith("/api"):
            return self._proxy_request()
        return self.send_error(405)

    def do_DELETE(self):
        if self.path.startswith("/api"):
            return self._proxy_request()
        return self.send_error(405)

    def do_OPTIONS(self):
        if self.path.startswith("/api"):
            return self._proxy_request()
        return super().do_OPTIONS()

    def log_message(self, format, *args):
        # Keep request logs useful without echoing cookies or bodies.
        super().log_message(format, *args)


if __name__ == "__main__":
    port = int(os.environ.get("WEB_PORT", "8080"))
    server = ThreadingHTTPServer(("0.0.0.0", port), ProxyStaticHandler)
    print(f"ProspectOS web server listening on http://0.0.0.0:{port}", flush=True)
    server.serve_forever()