"""
Making sure the browser runs the build we deployed.

A fix can be written, tested, deployed, and served, and still not be what runs.
`Cache-Control: no-cache` requires a browser to revalidate — but it only binds
one that asks, and a browser that cached the SPA *before* that header existed
applies heuristic freshness instead: a fraction of the file's age, which for a
file dated weeks ago is days. It does not ask, so it never learns.

That happened here. A phone ran a player without the read-ahead bound and filled
the browser's buffer ceiling at 106 MB — the exact symptom the bound was written
to remove — for an hour after the bounded player went live. Two sessions were
spent looking at the node.

So the URL now carries a fingerprint of what is being served, and the whole
module graph lives under it: `/a/<hash>/app.js` importing `./i18n.js` resolves
to `/a/<hash>/i18n.js`. A URL that changes with the content cannot serve
yesterday's build, and cannot serve half of each.
"""

import re

import pytest
from fastapi.testclient import TestClient
from meshbay_hub.api.webapp import ASSET_V, STATIC_DIR, _asset_version
from meshbay_hub.app import create_app


@pytest.fixture(scope="module")
def client():
    return TestClient(create_app())


def _shell_refs(html: str) -> list[str]:
    """What the shell loads: script sources and <link> files. Not the canonical
    link nor the <noscript> anchors, which name pages rather than fetch them."""
    return (re.findall(r'src="([^"]+)"', html)
            + re.findall(r'<link rel="(?!canonical")[^"]+" href="([^"]+)"', html))


def test_every_asset_the_shell_loads_is_versioned(client):
    refs = _shell_refs(client.get("/").text)
    assert refs, "the shell references nothing at all"
    stale = [u for u in refs if not u.startswith(f"/a/{ASSET_V}/")]
    assert not stale, (
        f"served from an unversioned URL, so a stale cache can win: {stale}")


def test_the_module_graph_resolves_under_the_same_prefix(client):
    """The point of a path prefix rather than a query string.

    `import './i18n.js'` from a versioned app.js resolves against the versioned
    directory. A query string on app.js alone would not: its imports would fall
    back to the bare paths, and the graph could be assembled from two builds —
    which does not render a stale page, it fails to link at all.
    """
    for path in ("app.js", "i18n.js", "locales/fr.js", "transport.js",
                 "vendor/argon2.min.js"):
        r = client.get(f"/a/{ASSET_V}/{path}")
        assert r.status_code == 200, f"{path} is not served under the version"


def test_versioned_assets_may_be_cached_hard(client):
    """Which is the trade the fingerprint buys."""
    cc = client.get(f"/a/{ASSET_V}/app.js").headers.get("cache-control", "")
    assert "immutable" in cc and "max-age=31536000" in cc, (
        f"versioned assets are served as {cc!r} — the whole point of a URL that "
        "changes with the content is that it need never be revalidated")


def test_the_unversioned_path_still_revalidates(client):
    """It still answers — old bookmarks, and sw.js has to live there."""
    r = client.get("/app.js")
    assert r.status_code == 200
    assert r.headers.get("cache-control") == "no-cache"


def test_the_service_worker_is_not_versioned(client):
    """Its scope is its own path.

    Served from /a/<hash>/sw.js it would only control /a/<hash>/, and the
    pages whose downloads it exists to intercept are not under there.
    """
    assert client.get("/sw.js").status_code == 200
    assert "/sw.js" not in _shell_refs(client.get("/").text)


def test_the_fingerprint_follows_the_content(tmp_path, monkeypatch):
    """Otherwise it is decoration.

    Pinning this to the file contents rather than to the package version is
    deliberate: a redeploy without a version bump is the common case during a
    debugging session, and that is exactly when a stale player costs the most.
    """
    before = _asset_version()
    target = STATIC_DIR / "app.js"
    original = target.read_bytes()
    try:
        target.write_bytes(original + b"\n// touched\n")
        assert _asset_version() != before, (
            "the fingerprint did not move when app.js did, so a redeploy "
            "serves the new file at the old URL")
    finally:
        target.write_bytes(original)
    assert _asset_version() == before, "the fingerprint is not reproducible"


@pytest.mark.parametrize("relative", ["locales/en.js", "vendor/htm-preact.js", "style.css"])
def test_a_change_anywhere_under_the_prefix_moves_the_fingerprint(relative):
    """
    Everything under the static directory is served at `/a/<hash>/` and cached
    as immutable, so everything has to feed the hash — subdirectories included.

    The fingerprint used to cover a hand-kept list of top-level modules, and
    the check that guarded the list globbed `*.js` at the top level only. The
    catalogues and `vendor/` were on neither: a change confined to the English
    catalogue shipped at the URL a phone already held, and it went on showing a
    heading that had been rewritten and deployed. Pull-to-refresh fetches the
    shell, which is `no-store` and was current; it does not refetch an
    immutable file whose URL has not moved.
    """
    before = _asset_version()
    target = STATIC_DIR / relative
    original = target.read_bytes()
    try:
        target.write_bytes(original + b"\n/* touched */\n")
        assert _asset_version() != before, (
            f"the fingerprint did not move when {relative} did, so a browser "
            "that cached it keeps the old copy for a year")
    finally:
        target.write_bytes(original)
    assert _asset_version() == before


def test_a_new_file_moves_the_fingerprint():
    """A rename or an addition changes what is served even when no existing
    file's bytes do."""
    before = _asset_version()
    extra = STATIC_DIR / "locales" / "zz-test-only.js"
    try:
        extra.write_text("export default {};\n", encoding="utf-8")
        assert _asset_version() != before
    finally:
        extra.unlink()
    assert _asset_version() == before