signal-bot/tests/test_stats_render_day.py
Krzysztof kuhy Rudnicki 37a27c6dff feat: refuse to commit personal data, learned from outside the repository
The leak this repository had was not carelessness with a secret. It was
somebody reaching for a real name because it was the example in front of
them -- a fixture built from a live database, an envelope pasted out of a
running container, a help text written while looking at the actual group.
Three different people-shaped mistakes, none of which a rule about "be
careful" would have stopped.

So it is a gate. The hard part is that the thing being checked must not
contain the list of what to refuse, or the check *is* the leak. It reads the
names at run time from outside: the photo pack's manifest, the message
database, the local .env. It never prints the word it matched, because this
output reaches CI logs. On a machine with none of that private data it says
"shapes only" out loud rather than passing quietly, and CI enforces the half
that needs nothing -- phone numbers, uuids and Signal group ids, compared
against an allowlist of values invented for the fixtures.

It runs on staged files, on the commit message -- where two of the leaks
actually travelled -- and over the whole tree in CI.

It paid for itself twice before it was wired up. The live test group's id was
in tests/test_config.py in two spellings, and truncated in three more files,
after four rounds of grepping by hand had pronounced the tree clean -- nobody
thinks to grep for base64. Then it refused the commit that introduced it,
because DOCS-privacy.md had used a real name as the example of a name.

An allowlist line may be scoped to one file, which is how the given names
that are also popes stay legal in popes.json and refused in every fixture
that has no business carrying them. The threshold is three characters,
because one of this group's given names is three characters long.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_017w1HZ3cZ7neL3rFdQ6VMBA
2026-08-30 23:28:29 +02:00

123 lines
4.4 KiB
Python

# Copyright (c) 2026 Krzysztof Rudnicki. MIT licence.
"""The nightly block: exact text, and the line budget."""
from __future__ import annotations
from signal_bot.stats.queries_day import DayRow, day_totals, with_silent
from signal_bot.stats.render_day import MAX_LINES, DayView, render_day, summary_line
# The real group, so the rendered example is a case that can actually occur.
GROUP = [
("Ala", 76, 12),
("Tomasz Nowak", 42, 3),
("kuhy", 38, 0),
("Basia", 33, 1),
("Franciszek Kowalczyk", 16, 0),
("Cezary Wiśniewski", 15, 0),
]
def rows(spec: list[tuple[str, int, int]], *, commands: int = 0) -> list[DayRow]:
"""Build day rows from (name, messages, media) triples."""
return [
DayRow(
uuid=f"u{i}",
display_name=name,
messages=messages,
media=media,
commands=commands if i == 0 else 0,
chars=messages * 47,
)
for i, (name, messages, media) in enumerate(spec)
]
def test_the_nightly_block_for_a_real_day() -> None:
"""Pinned exactly: this is the only assertion that proves the rendering."""
day_rows_ = with_silent(rows(GROUP), [("u9", "Celina")])
rendered = render_day(
"2026-09-01",
day_rows_,
day_totals(day_rows_),
DayView(since="2026-08-30", highlights=("🏆 Ala 76 — rekord życiowy (poprzedni 71)",)),
)
assert rendered == (
"📊 Wtorek, 1 września — 220 wiadomości (16 📷)\n"
"👑 Ala — 76 (12 📷)\n"
"2. Tomasz Nowak — 42 (3 📷)\n"
"3. kuhy — 38\n"
"4. Basia — 33 (1 📷)\n"
"5. Franciszek Kowalczyk — 16\n"
"6. Cezary Wiśniewski — 15\n"
"🏆 Ala 76 — rekord życiowy (poprzedni 71)\n"
"Cisza: Celina\n"
"Średnio 47 znaków na wiadomość.\n"
"(liczymy od 30 sierpnia)"
)
assert len(rendered.split("\n")) <= MAX_LINES
def test_a_day_with_no_media_shows_no_camera() -> None:
day = rows([("kuhy", 3, 0)])
rendered = render_day("2026-09-01", day, day_totals(day))
assert "📷" not in rendered
assert rendered.startswith("📊 Wtorek, 1 września — 3 wiadomości\n👑 kuhy — 3")
def test_commands_are_broken_out() -> None:
day = rows([("kuhy", 10, 0)], commands=4)
assert summary_line(day_totals(day)) == "Z tego 4 komendy, średnio 47 znaków na wiadomość."
def test_an_approximate_day_claims_no_average_length() -> None:
"""The backfilled day has counts but no lengths; 0 would be a lie."""
day = rows([("kuhy", 10, 0)])
assert summary_line(day_totals(day), approximate=True) == ""
with_commands = rows([("kuhy", 10, 0)], commands=4)
assert summary_line(day_totals(with_commands), approximate=True) == "Z tego 4 komendy."
def test_summary_is_empty_on_a_day_nobody_spoke() -> None:
assert summary_line(day_totals([])) == ""
assert day_totals([]).average_length == 0
def test_unnamed_members_are_counted_never_named() -> None:
"""Their only spellings are a uuid or a phone number; both would leak."""
day = with_silent(rows([("kuhy", 3, 0)]), [("u9", "Celina")])
rendered = render_day("2026-09-01", day, day_totals(day), DayView(unnamed=2))
assert "Cisza: Celina, i 2 osoby bez ani jednej wiadomości tutaj" in rendered
def test_a_big_group_is_truncated_and_still_fits() -> None:
"""The rule the current group size cannot reach, fixed before it can."""
big = rows([(f"Osoba {i:02d}", 30 - i, 0) for i in range(20)])
rendered = render_day(
"2026-09-01",
big,
day_totals(big),
DayView(since="2026-08-30", highlights=("🏆 rekord", "👑 korona", "📅 wtorki")),
)
lines = rendered.split("\n")
assert len(lines) <= MAX_LINES
assert any(line.startswith("…i ") for line in lines)
# The reserved highlight slot survives the truncation.
assert "🏆 rekord" in rendered
def test_the_hidden_tail_reports_its_own_total() -> None:
day = rows([("A", 10, 0), ("B", 5, 0), ("C", 3, 0), ("D", 2, 0)])
rendered = render_day(
"2026-09-01",
day,
day_totals(day),
DayView(since="2026-08-30", highlights=("h1", "h2", "h3")),
)
assert len(rendered.split("\n")) <= MAX_LINES
def test_a_custom_heading_replaces_the_date() -> None:
day = rows([("kuhy", 1, 0)])
rendered = render_day("2026-09-01", day, day_totals(day), DayView(heading="Dziś, na razie"))
assert rendered.startswith("Dziś, na razie\n")