Files
booth/tests/test_embed.py
T
vh 87e2c5364c feat(u3): a verbatim report declares the seam, the Booth mounts into it
A booth that ships its own index.html was served through ten regular
expressions applied to markup the Booth did not write: six in
wrap_verbatim_html hunting for somewhere to hang a favicon and a chip, four
in booth/inline.py substituting rendered ask markup into the author's own
tags. Both worked. Both were the most fragile thing in the service, on the
path the operator uses most.

The whole class is replaced by a declared seam. A report carries one line —
<script src="/_booth/embed.js" defer></script> — and the chrome mounts
through DOM APIs. What the server does to author HTML is now, in full:

    return html if declares_embed(html) else html + EMBED_SCRIPT_TAG

Two substring tests and a concatenation. Both of the old wrapper's hard
constraints stop existing rather than being satisfied more carefully:
nothing can displace a leading doctype into quirks mode and nothing can push
the charset meta out of its detection window, because nothing in front of
them ever moves. A page that declares the seam is served exactly as written.

Fragments are still rendered by the _ask_inline.html macros and handed over
GET /b/<name>/embed.json; embed.js places them and decides nothing. Openness
comes from open_marks, order from (created, id), questions in declaration
order. A single-question pick normalizes to key None, so the payload carries
questions as a list rather than an object — keying by name would serialize
that as the string "null".

Placement is an anchor fill, not a replacement: el.insertAdjacentHTML(
'beforeend'), so an author's wrapper and its contents survive. The regex it
replaces was eating the opening tag of dfa-concepts' styled .ask blocks and
orphaning their headings, live, unreported.

data-booth-mark is canonical; data-booth-ask stays a kept alias because two
live reports use it. The comment placeholders are dropped — no users.

Declared cost: the verbatim path now needs JavaScript. The never-invisible
guarantee holds through the index badge and /b/<name>/marks, both of which
render server-side.

Deleted: booth/inline.py entire, wrap_verbatim_html and its six patterns,
_BACK_CHIP, asks_chip, inject_asks, FAVICON_LINK, the styles() macro.

Tests 410 -> 434. tests/test_embed_browser.py drives a real Chromium: the
placement algorithm and the form= binding of a scattered multi-question form
cannot be observed any other way, and that binding was measured rather than
assumed (N=3 per condition, with a form-first positive control and a
points-at-nothing negative control).

Contract: docs/contracts/u3_declared_embed_seam.contract.md, with the
in-session seam review and the cold contract panel both recorded. Two of the
panel's findings were code fixes: a vacuous INV-3 falsifier that a renamed
regex walked straight through, and a bare-substring seam detection that read
a report merely quoting the path as declaring it and silently served it with
no chrome.
2026-09-22 10:43:41 -07:00

341 lines
14 KiB
Python

"""U3 — the declared embed seam, server side.
The Booth used to reach into a verbatim report with ten regular expressions: six
to find somewhere to hang a favicon and a chip, four to substitute rendered ask
markup into the author's own tags. This unit replaces all of it with a seam the
page declares:
<script src="/_booth/embed.js" defer></script>
What is tested here is the SERVER half — the payload that crosses the seam, the
one static asset, and the single conditional append that is now the only thing
the Booth does to author HTML. The half that mounts fragments into a live DOM
lives in tests/test_embed_browser.py, because no amount of string assertion can
see whether a form actually submits.
Contract: docs/contracts/u3_declared_embed_seam.contract.md
"""
import json
import os
import time
import pytest
from fastapi.testclient import TestClient
from booth.app import EMBED_SCRIPT_TAG, EMBED_SRC, create_app
from booth.marks import answer_pick, declare_pick, set_flag, write_note
DECLARED = f'<!doctype html><title>r</title><body>hi<script src="{EMBED_SRC}" defer></script></body>'
@pytest.fixture
def client(tmp_path):
app = create_app(tmp_path, ttl_hours=24, start_sweeper=False)
return TestClient(app), tmp_path
def _pick(booth, stem="winner", **kw):
doc = {"prompt": "Which render wins?", "options": ["A — baseline", "B — async"]}
doc.update(kw)
booth.mkdir(parents=True, exist_ok=True)
declare_pick(booth, stem, doc)
return booth
def _multi(booth, stem="batch"):
booth.mkdir(parents=True, exist_ok=True)
declare_pick(booth, stem, {"title": "Round one", "questions": [
{"key": "r1", "prompt": "First?", "options": ["a", "b"]},
{"key": "r2", "prompt": "Second?", "options": ["a", "b"]},
]})
return booth
# ---- slice 1: the payload ----------------------------------------------------
def test_embed_payload_carries_a_fragment_for_every_shape(client):
c, data = client
_multi(data / "b")
body = c.get("/b/b/embed.json").json()
assert body["booth"] == "b" and body["home"] == "/"
assert body["favicon"].startswith("data:image/svg+xml,")
(m,) = body["marks"]
assert m["id"] == "batch" and m["error"] is None
assert "First?" in m["whole"] and "Second?" in m["whole"]
assert 'action="/b/b/answer"' in m["submit"]
assert [q["key"] for q in m["questions"]] == ["r1", "r2"] # declaration order
assert "First?" in m["questions"][0]["html"]
assert 'type="radio"' in m["questions"][0]["html"]
def test_a_single_question_pick_has_one_question_with_a_null_key(client):
"""SR-2. `normalize_ask` gives a single-question ask `key: None`, so the
payload cannot key questions by name — JSON would write that as "null" and
invent a name. Every one-question ask in the fleet hits this."""
c, data = client
_pick(data / "b")
(m,) = c.get("/b/b/embed.json").json()["marks"]
assert [q["key"] for q in m["questions"]] == [None]
assert "Which render wins?" in m["questions"][0]["html"]
def test_marks_are_ordered_created_then_id(client):
c, data = client
b = _pick(data / "b", "zebra")
_pick(b, "alpha")
# force identical creation stamps: the id is the tie-break, not json order
raw = json.loads((b / ".marks.json").read_text())
for e in raw["marks"]:
e["created"] = "2026-09-22T10:00:00.000000-07:00"
(b / ".marks.json").write_text(json.dumps(raw))
assert [m["id"] for m in c.get("/b/b/embed.json").json()["marks"]] == ["alpha", "zebra"]
def test_open_is_computed_by_the_server_not_the_page(client):
"""INV-4. The chip count follows `open_marks`, which is the ONE openness
predicate — a half-answered multi-question pick is still open."""
c, data = client
b = _multi(data / "b")
assert c.get("/b/b/embed.json").json()["open"] == ["batch"]
answer_pick(b, "batch", {"r1": "a"})
assert c.get("/b/b/embed.json").json()["open"] == ["batch"] # partial is OPEN
answer_pick(b, "batch", {"r1": "a", "r2": "b"})
assert c.get("/b/b/embed.json").json()["open"] == []
def test_the_payload_carries_picks_only(client):
"""SR-4. Notes and flags never reach it, which is also what keeps a flag's
`flag:<target>` id — the one mark id containing the anchor separator — out
of a payload whose specs split on the first colon."""
c, data = client
b = _pick(data / "b")
(b / "shot.png").write_bytes(b"x")
write_note(b, None, "a remark")
set_flag(b, "shot.png", True)
assert [m["id"] for m in c.get("/b/b/embed.json").json()["marks"]] == ["winner"]
def test_a_damaged_marks_file_does_not_500_the_report(client):
c, data = client
b = _pick(data / "b")
(b / ".marks.json").write_text("{not json")
r = c.get("/b/b/embed.json")
assert r.status_code == 200
assert r.json()["marks"] == [] and r.json()["error"]
def test_a_broken_pick_offers_whole_and_nothing_else(client):
c, data = client
b = _pick(data / "b")
raw = json.loads((b / ".marks.json").read_text())
raw["marks"][0]["declaration"] = {"prompt": "p"} # no options -> AskError
(b / ".marks.json").write_text(json.dumps(raw))
(m,) = c.get("/b/b/embed.json").json()["marks"]
assert m["error"] and m["questions"] == [] and m["submit"] == ""
assert "broken ask" in m["whole"]
def test_the_payload_does_not_record_a_view(client):
"""`booth_view` already recorded the look, above both of its early returns.
A script's fetch of the page it is already on must not count a second time
or reset the TTL on machinery instead of on the operator."""
c, data = client
b = _pick(data / "b")
(b / "index.html").write_text(DECLARED)
c.get("/b/b/")
before = os.stat(b / ".viewed").st_mtime_ns
time.sleep(0.01)
c.get("/b/b/embed.json")
assert os.stat(b / ".viewed").st_mtime_ns == before
def test_embed_payload_404s_for_an_unknown_booth(client):
c, _ = client
assert c.get("/b/nope/embed.json").status_code == 404
# ---- slice 2: the one static asset -------------------------------------------
def test_embed_js_is_served_as_javascript(client):
c, _ = client
r = c.get(EMBED_SRC)
assert r.status_code == 200
assert r.headers["content-type"].startswith("text/javascript")
assert "data-booth-mark" in r.text
def test_embed_js_does_not_hot_reload_from_disk(tmp_path):
"""INV-5, and the 2026-09-21 lesson restated. A live asset editable under a
running process is how 19 of 25 booths hit 500 with the Python from 22:03
and the templates from 23:40. One rule in this repo: nothing takes effect
until you restart."""
import pathlib
import booth.app as app_mod
src = pathlib.Path(app_mod.__file__).parent / "static" / "embed.js"
original = src.read_text()
app = create_app(tmp_path, ttl_hours=24, start_sweeper=False)
c = TestClient(app)
served = c.get(EMBED_SRC).text
try:
src.write_text("/* POISONED */\n")
assert c.get(EMBED_SRC).text == served, "embed.js is being re-read per request"
finally:
src.write_text(original)
# ---- slice 3: what the Booth does to author HTML -----------------------------
def test_declaring_page_is_served_untouched(client):
"""INV-1. Whole-body equality, not a substring absence: the promise is that
NOTHING is added, and an absence assertion cannot tell a clean page from one
carrying something nobody thought to look for."""
c, data = client
b = _pick(data / "b")
(b / "index.html").write_text(DECLARED)
assert c.get("/b/b/").text == DECLARED
def test_undeclared_page_gains_only_the_tag(client):
"""INV-2. Appended, so the source is a strict prefix — nothing is inserted,
nothing is prepended, and neither the doctype nor the charset window moves."""
c, data = client
b = _pick(data / "b")
src = "<!doctype html><meta charset=utf-8><title>r</title><h1>REPORT</h1>"
(b / "index.html").write_text(src)
out = c.get("/b/b/").text
assert out == src + EMBED_SCRIPT_TAG
assert out.startswith(src)
assert out.lower().lstrip().startswith("<!doctype")
assert out.index("charset") < 1024
def test_a_booth_with_no_marks_still_gets_the_seam(client):
"""The seam carries the way home and the icon too, so it is not conditional
on there being an ask — the old chip was not either."""
c, data = client
(data / "b").mkdir()
(data / "b" / "index.html").write_text("<h1>bare fragment</h1>")
assert c.get("/b/b/").text == "<h1>bare fragment</h1>" + EMBED_SCRIPT_TAG
def test_no_regex_touches_author_html():
"""INV-3, and the version that actually falsifies it.
The first draft of this test name-matched the six deleted patterns. A cold
panel pointed out — correctly, and on the contract's CENTRAL promise — that
reintroducing the same regex under a new name (`_TAIL_RE`, applied in the
verbatim branch) would leave it green. A test that guards names does not
guard behaviour, and this repo's own vacuity pass missed it because the
mutation it tried was the named one.
So: `booth/app.py` is allowed EXACTLY ONE regex operation, and it is
`ask_form_id`'s `re.sub` over a mark id — not over a page. Any other regex
anywhere in the module fails here, whatever it is called. If a future
change genuinely needs one, the failure is the conversation: say which
string it reads and why it is not author HTML.
"""
import ast
import pathlib
import booth.app as app_mod
root = pathlib.Path(app_mod.__file__).parent
assert not (root / "inline.py").exists(), "booth/inline.py survived U3"
tree = ast.parse((root / "app.py").read_text())
# every node -> the function it sits in, so a finding names its site
site = {}
for node in ast.walk(tree):
if isinstance(node, (ast.FunctionDef, ast.AsyncFunctionDef)):
for child in ast.walk(node):
site.setdefault(child, node.name)
# `re` reaches this module ONE way: a plain module-level `import re`. An
# alias (`import re as _r`) or a direct name import (`from re import sub`)
# would route around the call check below under a name it does not know —
# found by re-running the vacuity pass against the FIXED test, which is the
# only reason it is here and is the argument for running that pass on a fix
# and not only on a draft.
for node in ast.walk(tree):
if isinstance(node, ast.Import):
for a in node.names:
assert not (a.name == "re" and a.asname), f"`re` aliased as {a.asname}"
elif isinstance(node, ast.ImportFrom):
assert node.module != "re", f"names imported from re: {[a.name for a in node.names]}"
METHODS = {"search", "sub", "subn", "match", "fullmatch", "finditer",
"findall", "split", "compile", "escape"}
found = []
for node in ast.walk(tree):
if not (isinstance(node, ast.Call) and isinstance(node.func, ast.Attribute)):
continue
f = node.func
on_re = isinstance(f.value, ast.Name) and f.value.id == "re"
on_pattern = (isinstance(f.value, ast.Name) and f.value.id.endswith("_RE")
and f.attr in METHODS)
if on_re or on_pattern:
found.append((site.get(node, "<module level>"), f.attr))
assert found == [("ask_form_id", "sub")], (
f"booth/app.py performs regex operations outside ask_form_id: {found}"
)
# the six named patterns and the chips are gone, and stay gone
assigned = {
t.id
for node in ast.walk(tree)
if isinstance(node, ast.Assign)
for t in node.targets
if isinstance(t, ast.Name)
}
gone = {"_ICON_RE", "_HEAD_CLOSE_RE", "_HTML_OPEN_RE", "_DOCTYPE_RE",
"_BODY_CLOSE_RE", "_HTML_CLOSE_RE", "_BACK_CHIP", "FAVICON_LINK"}
assert not (assigned & gone), f"deleted names are back: {sorted(assigned & gone)}"
funcs = {n.name for n in ast.walk(tree) if isinstance(n, ast.FunctionDef)}
assert not ({"wrap_verbatim_html", "asks_chip", "inject_asks",
"_insert_before", "_insert_after"} & funcs)
def test_a_page_that_only_mentions_the_path_is_not_declaring_it(client):
"""A report that QUOTES the seam — a code sample, a comment, a sentence
about this very feature — is not declaring it, and the Booth's own design
reports are the pages most likely to do that. Read as declared, such a page
would be served untouched and show no chrome at all, silently.
The detection therefore fails the other way: an unrecognised spelling gets a
duplicate tag, and embed.js mounts once regardless.
"""
c, data = client
b = _pick(data / "b")
for body in (
"<!doctype html><body><p>add <code>/_booth/embed.js</code> to your report</p></body>",
"<!doctype html><body><!-- src=/_booth/embed.js --></body>",
'<!doctype html><body><script src="/_booth/embed.js?v=2"></script></body>',
):
(b / "index.html").write_text(body)
assert c.get("/b/b/").text == body + EMBED_SCRIPT_TAG, body
# and the real declaration, in either quote style, is honoured
for decl in (f'<script src="{EMBED_SRC}" defer></script>',
f"<script src='{EMBED_SRC}' defer></script>"):
body = f"<!doctype html><body>hi{decl}</body>"
(b / "index.html").write_text(body)
assert c.get("/b/b/").text == body
def test_an_oversize_verbatim_page_is_served_raw(client, monkeypatch):
"""WRAP_MAX_BYTES survives: a pathological file is still not pulled into
memory, and it loses its chrome exactly as it does today."""
import booth.app as app_mod
c, data = client
b = _pick(data / "b")
(b / "index.html").write_text("<h1>huge</h1>")
monkeypatch.setattr(app_mod, "WRAP_MAX_BYTES", 4)
assert c.get("/b/b/").text == "<h1>huge</h1>"