CloakBrowser/tests/test_cloakserve.py

"""Unit tests for cloakserve — parse_connection_params, parse_cli_args, URL rewriting."""

import importlib.machinery
import importlib.util
import sys
from pathlib import Path

import pytest

aiohttp = pytest.importorskip("aiohttp", reason="cloakserve requires aiohttp (install with .[serve])")

# Load cloakserve as a module from bin/ (no .py extension).
_bin_path = str(Path(__file__).resolve().parents[1] / "bin" / "cloakserve")
_loader = importlib.machinery.SourceFileLoader("cloakserve", _bin_path)
_spec = importlib.util.spec_from_file_location("cloakserve", _bin_path, loader=_loader)
_mod = importlib.util.module_from_spec(_spec)
sys.modules["cloakserve"] = _mod
_loader.exec_module(_mod)

parse_connection_params = _mod.parse_connection_params
parse_cli_args = _mod.parse_cli_args


# ---------------------------------------------------------------------------
# parse_connection_params
# ---------------------------------------------------------------------------


class TestParseConnectionParams:
    def test_empty_query(self):
        result = parse_connection_params("")
        assert result["seed"] is None
        assert result["extra_args"] == []

    def test_fingerprint_seed(self):
        result = parse_connection_params("fingerprint=12345")
        assert result["seed"] == "12345"

    def test_timezone_and_locale(self):
        result = parse_connection_params("fingerprint=1&timezone=Asia/Tokyo&locale=ja-JP")
        assert result["timezone"] == "Asia/Tokyo"
        assert result["locale"] == "ja-JP"

    def test_proxy(self):
        result = parse_connection_params("proxy=http://proxy:8080")
        assert result["proxy"] == "http://proxy:8080"

    def test_geoip_true_variants(self):
        for val in ("true", "1", "yes", "True", "YES"):
            result = parse_connection_params(f"geoip={val}")
            assert result["geoip"] is True, f"geoip={val} should be True"

    def test_geoip_false(self):
        for val in ("false", "0", "no", "anything"):
            result = parse_connection_params(f"geoip={val}")
            assert result["geoip"] is False, f"geoip={val} should be False"

    def test_generic_fingerprint_params(self):
        qs = "fingerprint=1&platform=windows&hardware-concurrency=8&gpu-vendor=NVIDIA"
        result = parse_connection_params(qs)
        assert "--fingerprint-platform=windows" in result["extra_args"]
        assert "--fingerprint-hardware-concurrency=8" in result["extra_args"]
        assert "--fingerprint-gpu-vendor=NVIDIA" in result["extra_args"]

    def test_special_params_not_in_extra_args(self):
        qs = "fingerprint=1&timezone=UTC&locale=en-US&proxy=http://x:1&geoip=true"
        result = parse_connection_params(qs)
        assert result["extra_args"] == []

    def test_multiple_values_takes_first(self):
        result = parse_connection_params("fingerprint=111&fingerprint=222")
        assert result["seed"] == "111"


# ---------------------------------------------------------------------------
# parse_cli_args
# ---------------------------------------------------------------------------


class TestParseCliArgs:
    def test_defaults(self):
        config, passthrough = parse_cli_args([])
        assert config["port"] == 9222
        assert config["headless"] is True
        assert passthrough == []

    def test_custom_port(self):
        config, _ = parse_cli_args(["--port=8080"])
        assert config["port"] == 8080

    def test_headless_false(self):
        config, passthrough = parse_cli_args(["--headless=false"])
        assert config["headless"] is False
        # headless flag still passed through to Chrome
        assert "--headless=false" in passthrough

    def test_strips_remote_debugging_flags(self):
        args = ["--remote-debugging-port=9999", "--remote-debugging-address=0.0.0.0", "--no-sandbox"]
        config, passthrough = parse_cli_args(args)
        assert passthrough == ["--no-sandbox"]

    def test_passthrough_args(self):
        args = ["--no-sandbox", "--disable-gpu", "--fingerprint=999"]
        _, passthrough = parse_cli_args(args)
        assert passthrough == args

    def test_port_not_in_passthrough(self):
        _, passthrough = parse_cli_args(["--port=9222", "--no-sandbox"])
        assert "--port=9222" not in passthrough
        assert "--no-sandbox" in passthrough


# ---------------------------------------------------------------------------
# URL rewriting logic (pure string manipulation, extracted from handlers)
# ---------------------------------------------------------------------------


class TestURLRewriting:
    """Test the URL rewriting logic used by /json/version and /json/list."""

    def _rewrite_version(self, orig_ws: str, host: str, seed: str | None, scheme: str = "ws") -> str:
        """Replicate the URL rewrite logic from handle_json_version."""
        if seed:
            ws_path = f"fingerprint/{seed}/devtools/browser"
        else:
            ws_path = "devtools/browser"
        guid = orig_ws.rsplit("/", 1)[-1] if "/devtools/" in orig_ws else ""
        return f"{scheme}://{host}/{ws_path}/{guid}"

    def _rewrite_list_entry(self, orig_ws: str, host: str, seed: str | None, scheme: str = "ws") -> str:
        """Replicate the URL rewrite logic from handle_json_list."""
        ws_tail = orig_ws.split("/devtools/")[-1]
        if seed:
            return f"{scheme}://{host}/fingerprint/{seed}/devtools/{ws_tail}"
        else:
            return f"{scheme}://{host}/devtools/{ws_tail}"

    def test_version_rewrite_with_seed(self):
        orig = "ws://127.0.0.1:5100/devtools/browser/abc-123"
        result = self._rewrite_version(orig, "container:9222", "12345")
        assert result == "ws://container:9222/fingerprint/12345/devtools/browser/abc-123"

    def test_version_rewrite_no_seed(self):
        orig = "ws://127.0.0.1:5100/devtools/browser/abc-123"
        result = self._rewrite_version(orig, "container:9222", None)
        assert result == "ws://container:9222/devtools/browser/abc-123"

    def test_list_rewrite_page_with_seed(self):
        orig = "ws://127.0.0.1:5100/devtools/page/DEF-456"
        result = self._rewrite_list_entry(orig, "host:9222", "99")
        assert result == "ws://host:9222/fingerprint/99/devtools/page/DEF-456"

    def test_list_rewrite_page_no_seed(self):
        orig = "ws://127.0.0.1:5100/devtools/page/DEF-456"
        result = self._rewrite_list_entry(orig, "host:9222", None)
        assert result == "ws://host:9222/devtools/page/DEF-456"

    def test_list_rewrite_browser(self):
        orig = "ws://127.0.0.1:5100/devtools/browser/XYZ"
        result = self._rewrite_list_entry(orig, "host:9222", "seed1")
        assert result == "ws://host:9222/fingerprint/seed1/devtools/browser/XYZ"

    def test_wss_scheme_version(self):
        orig = "ws://127.0.0.1:5100/devtools/browser/abc-123"
        result = self._rewrite_version(orig, "host:443", "seed1", scheme="wss")
        assert result == "wss://host:443/fingerprint/seed1/devtools/browser/abc-123"

    def test_wss_scheme_list(self):
        orig = "ws://127.0.0.1:5100/devtools/page/DEF-456"
        result = self._rewrite_list_entry(orig, "host:443", "seed1", scheme="wss")
        assert result == "wss://host:443/fingerprint/seed1/devtools/page/DEF-456"