import os
import re
import time

import pytest
from fastapi.testclient import TestClient

from booth.app import (
    FAVICON_LINK,
    KEEP_MARKER,
    build_gallery,
    classify,
    create_app,
    doc_kind,
    generate_pickup_id,
    human_dur,
    is_expired,
    is_kept,
    list_booths,
    render_doc,
    safe_upload_name,
    sweep_once,
    wrap_verbatim_html,
)

PICKUP_RE = re.compile(r"^(\d{1,2}-[a-z]+|[a-z]+-\d{1,2})$")


# ---- pure helpers -----------------------------------------------------------


def test_classify():
    assert classify("a.PNG") == "image"
    assert classify("clip.webm") == "video"
    assert classify("v.mp4") == "video"
    assert classify("song.mp3") == "audio"
    assert classify("notes.txt") == "other"
    assert classify("archive.tar.gz") == "other"


def test_human_dur():
    assert human_dur(0) == "expired"
    assert human_dur(-5) == "expired"
    assert human_dur(30) == "<1m"
    assert human_dur(90) == "1m"
    assert human_dur(3600) == "1h"
    assert human_dur(3660) == "1h 1m"


def _touch(path, when=None):
    path.parent.mkdir(parents=True, exist_ok=True)
    path.write_bytes(b"x")
    if when is not None:
        os.utime(path, (when, when))


def test_is_expired_uses_newest_mtime(tmp_path):
    booth = tmp_path / "b"
    _touch(booth / "old.png", when=time.time() - 10_000)
    # freshly touched second file keeps the booth alive despite the old one
    _touch(booth / "new.png")
    assert not is_expired(booth, ttl_seconds=3600)

    old = tmp_path / "stale"
    t = time.time() - 10_000
    _touch(old / "x.png", when=t)
    os.utime(old, (t, t))
    assert is_expired(old, ttl_seconds=3600)


def test_sweep_only_removes_expired(tmp_path):
    fresh = tmp_path / "fresh"
    _touch(fresh / "a.png")
    old = tmp_path / "old"
    t = time.time() - 10_000
    _touch(old / "a.png", when=t)
    os.utime(old, (t, t))
    dotdir = tmp_path / ".control"
    t2 = time.time() - 10_000
    dotdir.mkdir()
    os.utime(dotdir, (t2, t2))

    wiped = sweep_once(tmp_path, ttl_seconds=3600)

    assert wiped == ["old"]
    assert fresh.exists()
    assert not old.exists()
    assert dotdir.exists()  # dotfolders are never swept


def test_build_gallery_folds_caption_sidecars(tmp_path):
    booth = tmp_path / "b"
    _touch(booth / "a.png")
    (booth / "a.txt").write_text("variant A: cudaMalloc")
    _touch(booth / "b.png")
    (booth / "b.png.txt").write_text("variant B: cudaMallocAsync")
    _touch(booth / "loose.txt")  # no media partner -> shown as its own item

    items = build_gallery(booth)
    by_name = {it["name"]: it for it in items}

    assert by_name["a.png"]["caption"] == "variant A: cudaMalloc"
    assert by_name["b.png"]["caption"] == "variant B: cudaMallocAsync"
    assert "a.txt" not in by_name and "b.png.txt" not in by_name
    assert "loose.txt" in by_name  # a caption with nothing to caption stays visible


# ---- HTTP surface -----------------------------------------------------------


@pytest.fixture
def client(tmp_path):
    app = create_app(tmp_path, ttl_hours=24, start_sweeper=False)
    return TestClient(app), tmp_path


def test_index_empty(client):
    c, _ = client
    r = c.get("/")
    assert r.status_code == 200
    assert "No booths yet" in r.text


def test_index_lists_booth(client):
    c, data = client
    _touch(data / "run1" / "a.png")
    r = c.get("/")
    assert r.status_code == 200
    assert "run1" in r.text


def test_booth_autogallery_renders_media(client):
    c, data = client
    _touch(data / "run1" / "shot.png")
    r = c.get("/b/run1/")
    assert r.status_code == 200
    assert "<img" in r.text
    assert "shot.png" in r.text


def test_booth_serves_own_index_html(client):
    c, data = client
    d = data / "custom"
    d.mkdir()
    (d / "index.html").write_text("<h1>MY CUSTOM REPORT</h1>")
    r = c.get("/b/custom/")
    assert r.status_code == 200
    assert "MY CUSTOM REPORT" in r.text


def test_booth_serves_file(client):
    c, data = client
    (data / "run1").mkdir()
    (data / "run1" / "a.bin").write_bytes(b"\x00\x01payload")
    r = c.get("/b/run1/a.bin")
    assert r.status_code == 200
    assert r.content == b"\x00\x01payload"


def test_booth_zip_download(client):
    # a verbatim index.html booth (no per-file chrome) is still downloadable as a zip
    c, data = client
    d = data / "brief"
    d.mkdir()
    (d / "index.html").write_text("<h1>BRIEF</h1>")
    (d / "notes.md").write_text("# notes")
    r = c.get("/b/brief/?download=1")
    assert r.status_code == 200
    assert r.headers["content-type"] == "application/zip"
    assert "attachment" in r.headers["content-disposition"]
    assert "brief.zip" in r.headers["content-disposition"]
    import io as _io
    import zipfile as _zip
    assert set(_zip.ZipFile(_io.BytesIO(r.content)).namelist()) == {"index.html", "notes.md"}


def test_booth_file_force_download(client):
    # ?dl=1 forces attachment so html/md/text saves instead of rendering inline
    c, data = client
    d = data / "brief"
    d.mkdir()
    (d / "index.html").write_text("<h1>BRIEF</h1>")
    r = c.get("/b/brief/index.html")
    assert "attachment" not in r.headers.get("content-disposition", "")
    r2 = c.get("/b/brief/index.html?dl=1")
    assert r2.status_code == 200
    assert "attachment" in r2.headers["content-disposition"]
    assert "index.html" in r2.headers["content-disposition"]


def test_missing_booth_404(client):
    c, _ = client
    assert c.get("/b/nope/").status_code == 404


def test_traversal_rejected(client):
    c, data = client
    (data / "run1").mkdir()
    # a name with a slash or .. can never resolve to a direct child
    assert c.get("/b/..%2f..%2fetc/").status_code == 404
    assert c.get("/b/run1/../../../etc/passwd").status_code == 404


def test_delete_form_wipes(client):
    c, data = client
    _touch(data / "run1" / "a.png")
    r = c.post("/b/run1/delete", follow_redirects=False)
    assert r.status_code == 303
    assert not (data / "run1").exists()


def test_delete_api_wipes(client):
    c, data = client
    _touch(data / "run1" / "a.png")
    r = c.request("DELETE", "/b/run1")
    assert r.status_code == 200
    assert r.json() == {"wiped": "run1"}
    assert not (data / "run1").exists()


def test_healthz(client):
    c, data = client
    _touch(data / "run1" / "a.png")
    r = c.get("/healthz")
    assert r.status_code == 200
    body = r.json()
    assert body["ok"] is True and body["booths"] == 1


# ---- uploads / pickup -------------------------------------------------------


def test_generate_pickup_id_format():
    for _ in range(100):
        pid = generate_pickup_id(lambda n: False)
        assert PICKUP_RE.match(pid), pid


def test_generate_pickup_id_avoids_collision():
    taken = {"4-wombat", "star-84"}
    for _ in range(50):
        pid = generate_pickup_id(lambda n: n in taken)
        assert pid not in taken


def test_safe_upload_name():
    assert safe_upload_name("../../etc/passwd", "fb") == "passwd"
    assert safe_upload_name("C:\\Users\\x\\shot.png", "fb") == "shot.png"
    assert safe_upload_name("", "fb") == "fb"
    assert safe_upload_name("   ", "fb") == "fb"
    assert safe_upload_name(".hidden", "fb") == "hidden"
    assert safe_upload_name("...", "fb") == "fb"


def _upload(client, files):
    return client.post("/upload", files=files, follow_redirects=False)


def test_upload_creates_pickup_booth(client):
    c, data = client
    r = _upload(c, [
        ("files", ("a.png", b"\x89PNG\r\n\x1a\n" + b"0" * 20, "image/png")),
        ("files", ("notes.txt", b"pick me up", "text/plain")),
    ])
    assert r.status_code == 303
    loc = r.headers["location"]
    pid = loc.split("/b/")[1].rstrip("/")
    assert PICKUP_RE.match(pid), pid
    booth = data / pid
    assert (booth / "a.png").is_file()
    assert (booth / "notes.txt").read_bytes() == b"pick me up"
    assert (booth / ".uploaded").is_file()  # marker present


def test_upload_booth_renders_pickup_ui(client):
    c, data = client
    r = _upload(c, [("files", ("shot.png", b"\x89PNG" + b"0" * 30, "image/png"))])
    pid = r.headers["location"].split("/b/")[1].rstrip("/")
    page = c.get(f"/b/{pid}/")
    assert page.status_code == 200
    assert "pickup" in page.text.lower()      # badge / note
    assert 'download' in page.text            # per-item download link
    # and it shows up flagged as an upload on the index
    assert pid in c.get("/").text


def test_upload_sanitizes_traversal(client):
    c, data = client
    r = _upload(c, [("files", ("../../../etc/passwd", b"x", "text/plain"))])
    pid = r.headers["location"].split("/b/")[1].rstrip("/")
    booth = data / pid
    assert (booth / "passwd").is_file()               # basename only
    assert not (data.parent / "passwd").exists()       # nothing escaped upward


def test_upload_rejects_too_many_files(tmp_path):
    app = create_app(tmp_path, start_sweeper=False, max_files=2)
    c = TestClient(app)
    files = [("files", (f"f{i}.txt", b"x", "text/plain")) for i in range(3)]
    r = c.post("/upload", files=files, follow_redirects=False)
    assert r.status_code == 413
    # no partial booth left behind
    assert list(tmp_path.iterdir()) == []


def test_upload_rejects_too_large(tmp_path):
    app = create_app(tmp_path, start_sweeper=False, max_upload_mb=0.0001)  # ~104 bytes
    c = TestClient(app)
    r = c.post(
        "/upload",
        files=[("files", ("big.bin", b"0" * 500, "application/octet-stream"))],
        follow_redirects=False,
    )
    assert r.status_code == 413
    assert list(tmp_path.iterdir()) == []  # partial write cleaned up


def test_upload_dedupes_repeated_names(client):
    c, data = client
    r = _upload(c, [
        ("files", ("shot.png", b"a" * 10, "image/png")),
        ("files", ("shot.png", b"b" * 10, "image/png")),
    ])
    pid = r.headers["location"].split("/b/")[1].rstrip("/")
    names = sorted(p.name for p in (data / pid).iterdir() if not p.name.startswith("."))
    assert names == ["shot-1.png", "shot.png"]


# ---- image viewer -----------------------------------------------------------


def test_image_view_renders(client):
    c, data = client
    _touch(data / "run1" / "shot.png")
    r = c.get("/b/run1/view", params={"f": "shot.png"})
    assert r.status_code == 200
    assert 'id="vstage"' in r.text            # the viewer stage
    assert ">Fit<" in r.text and ">1:1<" in r.text
    assert "shot.png" in r.text


def test_gallery_image_links_to_viewer(client):
    c, data = client
    _touch(data / "run1" / "shot.png")
    page = c.get("/b/run1/")
    assert "view?f=shot.png" in page.text     # gallery routes images to the viewer, not the raw file


def test_image_view_missing_404(client):
    c, data = client
    (data / "run1").mkdir()
    assert c.get("/b/run1/view", params={"f": "nope.png"}).status_code == 404


def test_image_view_traversal_404(client):
    c, data = client
    (data / "run1").mkdir()
    assert c.get("/b/run1/view", params={"f": "../../etc/passwd"}).status_code == 404


def test_view_nonviewable_redirects_to_raw(client):
    c, data = client
    _touch(data / "run1" / "data.bin")  # not image/md/txt -> nothing to render, hand back raw
    r = c.get("/b/run1/view", params={"f": "data.bin"}, follow_redirects=False)
    assert r.status_code == 307
    assert r.headers["location"] == "/b/run1/data.bin"


# ---- verbatim-index.html wrapper --------------------------------------------


def test_wrap_injects_chip_and_favicon():
    html = "<html><head><title>Brief</title></head><body><h1>REPORT</h1></body></html>"
    out = wrap_verbatim_html(html)
    assert 'class="booth-nav-home"' in out       # floating back chip
    assert 'href="/"' in out                      # points at the main booth index
    assert "all booths" in out
    assert FAVICON_LINK in out                    # favicon inherited
    assert "<h1>REPORT</h1>" in out               # original content preserved
    # favicon lands in the head, chip lands in the body
    assert out.index(FAVICON_LINK) < out.index("</head>")
    assert out.index("booth-nav-home") > out.index("<body>")


def test_wrap_respects_existing_favicon():
    html = '<html><head><link rel="icon" href="data:image/png;base64,AAAA"></head><body>x</body></html>'
    out = wrap_verbatim_html(html)
    assert FAVICON_LINK not in out                # the page's own icon wins
    assert out.count('rel="icon"') == 1
    assert 'class="booth-nav-home"' in out        # chip is still added


def test_wrap_bare_fragment_appends_chip():
    out = wrap_verbatim_html("<h1>bare fragment</h1>")  # no doctype/head/body
    assert 'class="booth-nav-home"' in out
    assert out.rstrip().endswith("</style>")            # chip appended at the end
    assert FAVICON_LINK in out                           # no doctype -> safe to prepend the icon
    assert out.index(FAVICON_LINK) < out.index("bare")   # icon ahead of content (implied head)


def test_wrap_no_head_injects_favicon():
    out = wrap_verbatim_html("<body><h1>no head</h1></body>")
    assert 'class="booth-nav-home"' in out
    assert FAVICON_LINK in out                           # injected even without an explicit <head>


def test_wrap_compact_doctype_stays_first():
    # the real-booth shape: compact HTML, no explicit head/body. The injection must
    # not push anything ahead of the doctype (quirks mode) or past the charset window.
    html = "<!doctype html><meta charset=utf-8><title>T</title><style>body{margin:0}</style><h1>REPORT</h1>"
    out = wrap_verbatim_html(html)
    assert out.lstrip().lower().startswith("<!doctype")       # doctype still first -> standards mode
    assert FAVICON_LINK in out
    assert out.index(FAVICON_LINK) < out.index("<h1>")         # icon in the implied head, before content
    assert out.index("charset") < 1024                         # charset meta stays in the detection window
    assert 'class="booth-nav-home"' in out
    assert out.index("booth-nav-home") > out.index("<h1>REPORT</h1>")  # chip appended after content


def test_verbatim_booth_wrapped_with_back_chip(client):
    c, data = client
    d = data / "brief"
    d.mkdir()
    (d / "index.html").write_text("<html><head></head><body><h1>BRIEF</h1></body></html>")
    r = c.get("/b/brief/")
    assert r.status_code == 200
    assert "BRIEF" in r.text                       # content preserved
    assert 'class="booth-nav-home"' in r.text      # back chip injected
    assert 'href="/"' in r.text
    assert 'rel="icon"' in r.text                  # favicon inherited


def test_verbatim_index_raw_file_route_unwrapped(client):
    # the file route (/b/<name>/index.html) still serves the raw bytes — the chip
    # only rides on the booth view (/b/<name>/), so downloads/assets stay verbatim
    c, data = client
    d = data / "brief"
    d.mkdir()
    (d / "index.html").write_text("<html><body><h1>BRIEF</h1></body></html>")
    r = c.get("/b/brief/index.html")
    assert r.status_code == 200
    assert "booth-nav-home" not in r.text


# ---- .md / .txt in-booth doc viewer -----------------------------------------


def test_doc_kind():
    assert doc_kind("notes.md") == "markdown"
    assert doc_kind("a.markdown") == "markdown"
    assert doc_kind("log.txt") == "text"
    assert doc_kind("run.log") == "text"
    assert doc_kind("shot.png") is None
    assert doc_kind("data.bin") is None


def test_render_doc_markdown():
    html, is_html = render_doc("# Title\n\n- a\n- b\n", "markdown")
    assert is_html is True
    assert "<h1>" in html and "Title" in html
    assert "<li>" in html


def test_render_doc_text_is_verbatim():
    body, is_html = render_doc("plain\ntext", "text")
    assert is_html is False and body == "plain\ntext"


def test_view_markdown_renders(client):
    c, data = client
    d = data / "run1"; d.mkdir()
    (d / "notes.md").write_text("# Heading\n\nsome **bold** text\n")
    r = c.get("/b/run1/view", params={"f": "notes.md"})
    assert r.status_code == 200
    assert "<h1>" in r.text and "Heading" in r.text            # rendered, not raw markdown
    assert "<strong>bold</strong>" in r.text
    assert "attachment" not in r.headers.get("content-disposition", "")  # viewed, not downloaded


def test_view_text_shows_preformatted(client):
    c, data = client
    d = data / "run1"; d.mkdir()
    (d / "out.txt").write_text("line one\nline two")
    r = c.get("/b/run1/view", params={"f": "out.txt"})
    assert r.status_code == 200
    assert "<pre" in r.text and "line one" in r.text
    assert "attachment" not in r.headers.get("content-disposition", "")


def test_gallery_links_docs_to_view(client):
    c, data = client
    d = data / "run1"; d.mkdir()
    (d / "readme.md").write_text("# hi")
    (d / "notes.txt").write_text("hello")   # loose txt (no media partner) -> own item
    page = c.get("/b/run1/")
    assert "view?f=readme.md" in page.text   # md -> viewer
    assert "view?f=notes.txt" in page.text   # txt -> viewer
    assert 'href="readme.md" download' not in page.text   # not a forced download


# ---- image viewer prev/next nav ---------------------------------------------


def test_view_image_prev_next_nav(client):
    c, data = client
    d = data / "run1"; d.mkdir()
    for n in ("a.png", "b.png", "c.png"):
        _touch(d / n)
    r = c.get("/b/run1/view", params={"f": "b.png"})   # middle -> prev=a, next=c
    assert r.status_code == 200
    assert 'class="vnav vprev" href="?f=a.png"' in r.text
    assert 'class="vnav vnext" href="?f=c.png"' in r.text


def test_view_image_nav_wraps(client):
    c, data = client
    d = data / "run1"; d.mkdir()
    for n in ("a.png", "b.png", "c.png"):
        _touch(d / n)
    first = c.get("/b/run1/view", params={"f": "a.png"}).text
    assert 'vprev" href="?f=c.png"' in first and 'vnext" href="?f=b.png"' in first  # first wraps prev->last
    last = c.get("/b/run1/view", params={"f": "c.png"}).text
    assert 'vnext" href="?f=a.png"' in last and 'vprev" href="?f=b.png"' in last    # last wraps next->first


def test_view_single_image_no_nav(client):
    c, data = client
    d = data / "run1"; d.mkdir()
    _touch(d / "only.png")
    r = c.get("/b/run1/view", params={"f": "only.png"})
    assert r.status_code == 200
    # no arrow anchors with a single image (the .vnav CSS rule is always present)
    assert 'class="vnav vprev"' not in r.text and 'class="vnav vnext"' not in r.text


# ---- kept booths: the `.forever` sentinel -----------------------------------
#
# The Booth's whole contract is "wiped 24h after last activity". A kept booth is
# the deliberate exception: an operator-facing board (agent-posted links, a
# standing report) that must outlive the sweep and stay separated from the
# ephemeral traffic so it does not get lost in it.


def _stale(path, seconds=10_000):
    """Age a booth and everything in it well past any test TTL."""
    t = time.time() - seconds
    for p in sorted(path.rglob("*"), reverse=True):
        os.utime(p, (t, t))
    os.utime(path, (t, t))


def test_is_kept_detects_the_sentinel(tmp_path):
    plain = tmp_path / "plain"
    plain.mkdir()
    kept = tmp_path / "kept"
    _touch(kept / KEEP_MARKER)

    assert not is_kept(plain)
    assert is_kept(kept)


def test_kept_booth_survives_the_sweep(tmp_path):
    """The point of the whole feature: expiry does not apply to a kept booth."""
    doomed = tmp_path / "doomed"
    _touch(doomed / "a.png")
    _stale(doomed)

    kept = tmp_path / "links"
    _touch(kept / "a.png")
    _touch(kept / KEEP_MARKER)
    _stale(kept)

    wiped = sweep_once(tmp_path, ttl_seconds=3600)

    assert wiped == ["doomed"]
    assert not doomed.exists()
    assert kept.exists(), "a booth carrying the sentinel must never be swept"


def test_kept_booth_is_still_reported_expired_by_age(tmp_path):
    """is_expired stays a pure age question; only the sweeper honours the pin.

    Keeping these separate means `expires_in` arithmetic and the reaper policy
    cannot drift into each other.
    """
    kept = tmp_path / "links"
    _touch(kept / KEEP_MARKER)
    _stale(kept)

    assert is_expired(kept, ttl_seconds=3600)
    assert sweep_once(tmp_path, ttl_seconds=3600) == []


def test_list_booths_flags_kept(tmp_path):
    _touch(tmp_path / "ephemeral" / "a.png")
    _touch(tmp_path / "links" / "a.png")
    _touch(tmp_path / "links" / KEEP_MARKER)

    by_name = {b["name"]: b for b in list_booths(tmp_path, ttl_seconds=3600)}

    assert by_name["ephemeral"]["kept"] is False
    assert by_name["links"]["kept"] is True


def test_sentinel_is_not_counted_as_an_item(tmp_path):
    """It is a dotfile, so it must not inflate the item count or become a tile."""
    _touch(tmp_path / "links" / "a.png")
    _touch(tmp_path / "links" / KEEP_MARKER)

    booth = next(b for b in list_booths(tmp_path, ttl_seconds=3600) if b["name"] == "links")

    assert booth["count"] == 1


def test_index_separates_kept_from_ephemeral(client):
    c, data = client
    _touch(data / "scratch" / "a.png")
    _touch(data / "links" / "a.png")
    _touch(data / "links" / KEEP_MARKER)

    html = c.get("/").text

    # Assert on the lane's markup, not on the word "Kept" — that string also
    # appears in the stylesheet comment that is served on every page, so a bare
    # substring check passes for the wrong reason.
    assert 'class="grid kept-grid"' in html, "kept booths need their own lane"
    assert 'class="card card-kept"' in html
    # The kept lane is rendered before the ephemeral grid, so the operator sees
    # durable boards first rather than hunting for them among the churn.
    assert html.index("links") < html.index("scratch")


def test_kept_booth_shows_kept_instead_of_a_countdown(client):
    c, data = client
    _touch(data / "links" / "a.png")
    _touch(data / "links" / KEEP_MARKER)

    html = c.get("/").text

    assert "expires in" not in html, "a kept booth has no expiry to advertise"


def test_index_without_kept_booths_omits_the_lane(client):
    c, data = client
    _touch(data / "scratch" / "a.png")

    html = c.get("/").text

    # The full attribute form, because the bare class names also appear in the
    # inlined stylesheet that ships on every page.
    assert 'class="grid kept-grid"' not in html, "the lane must not render when nothing is kept"
    assert 'class="card card-kept"' not in html