furtka/tests/test_webinstaller_assets.py

"""Asset sourcing + install-flow tests for webinstaller.

Phase-2 slice 1a moved every HTML/CSS/script/unit payload out of inline
Python string constants and into real files under furtka/assets/. Slice 1b
then flipped Caddy to serve from /opt/furtka/current/assets/www/, retired
/srv/furtka/www/, and switched systemd units from hand-written files in
/etc/systemd/system/ to `systemctl link` against the shipped asset tree.

These tests lock the new contract:
  - the Caddyfile and the status.json placeholder still land via
    _write_file_cmd and match the on-disk asset bit-for-bit,
  - the resource-manager bootstrap extracts to /opt/furtka/versions/<ver>/,
    creates /opt/furtka/current, and systemctl-links every unit,
  - furtka.json is written with the installer's hostname,
  - no write ever targets /srv/furtka/www/ (that path is retired).
"""

import base64
import re
import sys
from pathlib import Path

import pytest

sys.path.insert(0, str(Path(__file__).resolve().parent.parent / "webinstaller"))
import app  # noqa: E402

REPO_ROOT = Path(__file__).resolve().parent.parent
ASSETS = REPO_ROOT / "assets"


# (install target path, asset path under furtka/assets/) — only the files we
# still copy bit-for-bit at install time. Scripts + unit files are no longer
# copied; they're reached via /opt/furtka/current and `systemctl link`. The
# Caddyfile is not in this list because it's written with the hostname
# placeholder substituted — see test_post_install_substitutes_hostname_in_caddyfile.
ASSET_TARGETS = [
    ("/var/lib/furtka/status.json", "www/status.json"),
]


def _extract_written_content(cmd, target):
    """Pull the base64 payload back out of a _write_file_cmd() shell string."""
    match = re.search(r"printf %s (\S+) \| base64 -d > " + re.escape(target), cmd)
    assert match, f"cmd didn't look like a write of {target}: {cmd[:100]}"
    return base64.b64decode(match.group(1)).decode("utf-8")


@pytest.fixture
def install_cmds(tmp_path, monkeypatch):
    # Make _resource_manager_commands return a non-empty list so the full
    # command tree is exercised. A fake payload file is enough since the
    # test only inspects the generated shell strings.
    fake = tmp_path / "payload.tar.gz"
    fake.write_bytes(b"not a real tarball")
    monkeypatch.setattr(app, "RESOURCE_MANAGER_PAYLOAD", fake)
    return app._post_install_commands("testhost", "daniel", "test-admin-pw")


@pytest.mark.parametrize("target,asset_relpath", ASSET_TARGETS)
def test_post_install_writes_asset_from_disk(install_cmds, target, asset_relpath):
    expected = (ASSETS / asset_relpath).read_text(encoding="utf-8")
    matching = [c for c in install_cmds if f" > {target}" in c]
    assert matching, f"no command writes {target}"
    assert _extract_written_content(matching[0], target) == expected


def test_no_command_writes_to_retired_srv_path(install_cmds):
    for c in install_cmds:
        assert "/srv/furtka/www" not in c, f"retired /srv/furtka/www write: {c[:120]}"


def test_resource_manager_extracts_to_versioned_slot(install_cmds):
    extract_cmd = next((c for c in install_cmds if "tar -xzf" in c), None)
    assert extract_cmd is not None, "no tar extract command"
    assert "/opt/furtka/versions" in extract_cmd
    assert "staging-" in extract_cmd  # mktemp -d pattern
    assert 'cat "$staging/VERSION"' in extract_cmd
    # An empty VERSION file must abort the install instead of silently
    # moving the staging dir into versions/ as a subdir.
    assert '[ -n "$ver" ]' in extract_cmd
    # Version dir must be 755 so Caddy (non-root) can traverse it.
    assert 'chmod 755 "/opt/furtka/versions/$ver"' in extract_cmd
    assert 'ln -sfn "/opt/furtka/versions/$ver" /opt/furtka/current' in extract_cmd


def test_furtka_json_cmd_uses_heredoc_and_interpolates_hostname(install_cmds):
    # Regression: the previous base64+sed version of this command was a
    # silent no-op on some installs due to archinstall-side quoting; the
    # heredoc version is the one that reliably writes furtka.json.
    cmd = next((c for c in install_cmds if "/var/lib/furtka/furtka.json" in c), None)
    assert cmd is not None
    assert "cat > /var/lib/furtka/furtka.json <<EOF" in cmd
    assert '"hostname": "testhost"' in cmd
    assert "date -Iseconds" in cmd
    assert "/opt/furtka/current/VERSION" in cmd


def test_resource_manager_systemctl_links_every_unit(install_cmds):
    link_cmd = next((c for c in install_cmds if c.startswith("systemctl link ")), None)
    assert link_cmd is not None, "no systemctl link command"
    for unit in app._FURTKA_UNITS:
        assert f"/opt/furtka/current/assets/systemd/{unit}" in link_cmd


def test_resource_manager_enables_all_units(install_cmds):
    enable_cmd = next((c for c in install_cmds if c.startswith("systemctl enable ")), None)
    assert enable_cmd is not None
    for unit in app._FURTKA_UNITS:
        assert unit in enable_cmd


def test_wrapper_script_points_at_current_symlink():
    assert "PYTHONPATH=/opt/furtka/current" in app._FURTKA_WRAPPER_SH


def test_caddyfile_asset_serves_from_current():
    caddy = (ASSETS / "Caddyfile").read_text()
    assert "root * /opt/furtka/current/assets/www" in caddy
    assert "/srv/furtka/www" not in caddy
    # Runtime JSON paths served from /var/lib/furtka/ so updates don't clobber.
    assert "root * /var/lib/furtka" in caddy


def _strip_caddy_comments(text: str) -> str:
    """Remove # comments + blank lines so string-match assertions can
    target actual Caddyfile directives, not the leading doc block.
    Comment intro is ``#`` at start-of-line or preceded by whitespace."""
    out = []
    for line in text.splitlines():
        stripped = line.split("#", 1)[0].rstrip()
        if stripped:
            out.append(stripped)
    return "\n".join(out)


def test_caddyfile_serves_http_by_default_https_opt_in():
    # 26.15-alpha: HTTPS is opt-in. The default Caddyfile has a :80 block
    # and imports /etc/caddy/furtka-https.d/*.caddyfile at top level —
    # the /settings HTTPS toggle drops the hostname+tls-internal block
    # into that dir when the user explicitly enables HTTPS. Default
    # Caddyfile therefore contains no `tls internal` directive anywhere;
    # if a future refactor puts it back, every fresh install regresses
    # to the 26.14-era BAD_SIGNATURE trap. Strip comments first because
    # the doc-block DOES mention `tls internal` in prose.
    caddy_full = (ASSETS / "Caddyfile").read_text()
    caddy = _strip_caddy_comments(caddy_full)
    assert ":80 {" in caddy
    assert "tls internal" not in caddy
    assert "__FURTKA_HOSTNAME__" not in caddy
    assert "import /etc/caddy/furtka-https.d/*.caddyfile" in caddy
    # Shared routes still live in a named snippet so the HTTPS toggle's
    # snippet can import the same routes without duplication.
    assert "(furtka_routes)" in caddy
    # Default Caddyfile imports it once (inside :80). The HTTPS snippet,
    # when written by the toggle, imports it a second time.
    assert caddy.count("import furtka_routes") == 1


def test_caddyfile_disables_caddy_auto_redirects():
    # Named-hostname :443 block makes Caddy want to add its own HTTP→HTTPS
    # redirect. The /settings toggle is the single source of truth, so the
    # built-in has to be off — otherwise the toggle and auto_https race.
    caddy = (ASSETS / "Caddyfile").read_text()
    assert "auto_https disable_redirects" in caddy


def test_caddyfile_imports_force_redirect_snippet_dir():
    # The /api/furtka/https/force endpoint toggles HTTP→HTTPS by writing or
    # removing a snippet file in this dir; the Caddyfile must glob-import it
    # inside the :80 block for the toggle to take effect.
    caddy = (ASSETS / "Caddyfile").read_text()
    assert "import /etc/caddy/furtka.d/*.caddyfile" in caddy


def test_caddyfile_exposes_root_ca_download():
    # /rootCA.crt is the download handle the UI uses. It must map to the
    # Caddy local-CA pki path and set a Content-Disposition so the browser
    # treats it as a download rather than trying to render it. Path is the
    # real one Caddy uses under XDG_DATA_HOME=/var/lib (see caddy.service
    # Environment= directive) — not the /var/lib/caddy/.local/share/caddy/
    # path Caddy docs show for non-systemd installs.
    caddy = (ASSETS / "Caddyfile").read_text()
    assert "handle /rootCA.crt" in caddy
    assert "/var/lib/caddy/pki/authorities/local" in caddy
    assert ".local/share/caddy" not in caddy
    assert "attachment; filename=furtka-local-rootCA.crt" in caddy


def test_post_install_writes_caddyfile_without_hostname_placeholder(install_cmds):
    # 26.15-alpha: the shipped Caddyfile no longer carries the
    # __FURTKA_HOSTNAME__ marker — HTTPS + hostname now live in the
    # opt-in snippet written by set_force_https(), not in the base
    # Caddyfile. Verify the post-install writes the file as-is (no
    # substitution expected) and it has the opt-in import glob.
    caddyfile_cmd = next((c for c in install_cmds if " > /etc/caddy/Caddyfile" in c), None)
    assert caddyfile_cmd is not None
    written_full = _extract_written_content(caddyfile_cmd, "/etc/caddy/Caddyfile")
    written = _strip_caddy_comments(written_full)
    assert "__FURTKA_HOSTNAME__" not in written
    assert "import /etc/caddy/furtka-https.d/*.caddyfile" in written
    assert "tls internal" not in written


def test_post_install_creates_https_snippet_dir(install_cmds):
    # The top-level HTTPS opt-in snippet dir must exist before Caddy's
    # first start — its glob import tolerates an empty directory, but
    # not a missing one on older Caddy builds. Parallel guarantee to
    # test_post_install_creates_furtka_d_snippet_dir below.
    matching = [c for c in install_cmds if "/etc/caddy/furtka-https.d" in c and "install -d" in c]
    assert matching, "no install -d command creates /etc/caddy/furtka-https.d"


def test_post_install_creates_furtka_d_snippet_dir(install_cmds):
    # Pre-existing installs pick up the import path via updater._refresh_caddyfile,
    # but fresh installs never run that — this command is the only guarantee
    # that the first Caddy start on a brand-new box has a dir to glob-import.
    matching = [c for c in install_cmds if "/etc/caddy/furtka.d" in c and "install -d" in c]
    assert matching, "no install -d command creates /etc/caddy/furtka.d"


def test_systemd_units_reference_current_paths():
    for unit in ("furtka-status.service", "furtka-welcome.service"):
        body = (ASSETS / "systemd" / unit).read_text()
        assert "/opt/furtka/current/assets/bin/" in body, (
            f"{unit} still references a /usr/local/bin path"
        )


def test_welcome_banner_is_timer_driven():
    """The console banner must keep refreshing so the IP fallback is always
    on screen. A oneshot with RemainAfterExit=yes never re-runs from a timer
    (the unit stays 'active'), and a network-online dependency would delay the
    first paint — both regressions the hardware bench hit in 26.19."""
    timer = (ASSETS / "systemd" / "furtka-welcome.timer").read_text()
    assert "OnUnitActiveSec=" in timer
    assert "furtka-welcome.timer" in app._FURTKA_UNITS
    service = (ASSETS / "systemd" / "furtka-welcome.service").read_text()
    assert "RemainAfterExit" not in service
    assert "network-online.target" not in service


def test_welcome_banner_always_prints_fallback_line():
    script = (ASSETS / "bin" / "furtka-welcome").read_text()
    assert "no IP address yet" in script
    assert "fallback" in script


def test_read_asset_raises_for_missing_file():
    with pytest.raises(FileNotFoundError):
        app._read_asset("does/not/exist.html")


def test_assets_dir_resolves_to_repo_tree():
    assert app._ASSETS_DIR == ASSETS


def test_post_install_writes_users_json_with_hashed_password(install_cmds):
    """The Furtka-admin users.json is created during the chroot post-install.

    Without this, a fresh-install box lands at /login in first-run setup
    mode and the user has to go through the browser to set a password —
    which defeats the "step-1 password works for everything" design. Also
    check that the file is chmod 0600 (the PBKDF2 hash is a secret even
    if it's slow to crack).
    """
    import json as _json

    from werkzeug.security import check_password_hash

    users_cmd = next((c for c in install_cmds if " > /var/lib/furtka/users.json" in c), None)
    assert users_cmd is not None, "no command writes /var/lib/furtka/users.json"
    assert "chmod 600" in users_cmd, "users.json must be chmod 0600"
    body = _extract_written_content(users_cmd, "/var/lib/furtka/users.json")
    parsed = _json.loads(body)
    assert "admin" in parsed
    assert parsed["admin"]["username"] == "daniel"  # matches fixture
    # Hash is a real werkzeug hash, not the plaintext password.
    assert parsed["admin"]["hash"] != "test-admin-pw"
    assert check_password_hash(parsed["admin"]["hash"], "test-admin-pw")