mirror of
https://github.com/kuhyx/signal-bot.git
synced 2026-11-10 18:17:02 +01:00
Krzysztof kuhy Rudnicki
aefffb2fd9
Some checks are pending
CI / check (push) Waiting to run
Send a photo captioned "!add_photo alfa wakacje" in one of the album's own groups and it lands in the pack tagged with both, retrievable through !alfa and the new !losowe immediately -- no restart, and no tagger session on the PC. A label matching nobody becomes a custom tag, and !losowe is the only door to one, which is what keeps a live swap a *data* swap: it can never register a trigger or widen a command's groups. No typed label travels. Labels become pseudonym keys in a new registry arg_resolver, at the dispatcher, before the line that logs the command name -- so no handler, journal entry, command_uses row or reply body ever holds a word somebody typed. The reply is counts and pseudonyms: "dodano · p1: 4 · t1: 1". Stripping is exiftool with a *positive* check on the output, never an exit code. ffmpeg was tried first and fails silently on photos: given a JPEG with a real APP1 Exif segment it returned a byte-identical file, GPS intact, exit 0. The surviving-tag allowlist is per tag *name* rather than per group, because measurement showed a group-level "must be empty" rule rejects every format except JPEG -- a valid PNG always reports its IHDR, an MP4 some fifty QuickTime tags that are the container itself. Codec configuration (CompressorName, VendorID, the HEVC parameter set) is on the list by decision: CompressorName lives in the avc1 sample description and exiftool cannot write it at all, so the alternative was refusing every video and every iPhone HEIC. Location and identity tags are still refused, and the e2e run re-reads the stored files to prove a QuickTime geotag did not survive. .webm and .svg stay on the format allowlist and are stored *unstripped*: exiftool 13.55 can write neither, and its SVG reader does not even surface <metadata>. That is a deliberate, documented hole, not an oversight. Two things this had to defuse along the way: - personal_data_sources now reads custom.json, so "!add_photo kot <photo>" would have outlawed the word "kot" and refused every future commit, fixable only by hand-editing an album the committer cannot see. Minting now refuses a word that is already a command, and the gate subtracts the repo's own alias vocabulary from custom labels only -- curated people.json names are never excused. - signal_bot/external.py is now the single subprocess site in the repository, so ruff's S603 needs exactly one scoped per-file-ignore instead of one per module that shells out. A test asserts nothing else imports subprocess. A failed add changes nothing: media and the three manifests are written, the album is reloaded, and only a load that succeeds is published; a load that fails rolls all four back and keeps serving the pack that was already working, without raising -- Restart=always would turn a ConfigError into a loop. 977 tests, 100% branch coverage, no omits and no suppressions. scripts/e2e.sh gains 8 scenarios driven against the real exiftool on media generated at run time, and asserts the invariants a reply cannot: that a refused upload is not stored, that a message with no attachment leaves custom.json byte-identical, and that signal-cli's own copy of every ingested attachment is gone. Closes TODO-add-photo.md. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01JqqE22jp94B1ypwxppdr1o
94 lines
2.6 KiB
Python
94 lines
2.6 KiB
Python
# Copyright (c) 2026 Krzysztof Rudnicki. MIT licence.
|
|
"""What an upload is decided to be, from its bytes and never its name."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import pytest
|
|
|
|
from signal_bot.media_sniff import (
|
|
AVIF,
|
|
GIF,
|
|
HEIC,
|
|
HEIF,
|
|
JPEG,
|
|
KINDS,
|
|
M4V,
|
|
MOV,
|
|
MP4,
|
|
PNG,
|
|
SVG,
|
|
WEBM,
|
|
WEBP,
|
|
MediaKind,
|
|
sniff,
|
|
)
|
|
from signal_bot.pack import MEDIA_TYPES
|
|
|
|
|
|
def _iso(brand: bytes) -> bytes:
|
|
return b"\x00\x00\x00\x20ftyp" + brand + b"\x00\x00\x02\x00rest"
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
("payload", "expected"),
|
|
[
|
|
(b"\xff\xd8\xff\xe0JFIF", JPEG),
|
|
(b"\x89PNG\r\n\x1a\n....", PNG),
|
|
(b"GIF87a....", GIF),
|
|
(b"GIF89a....", GIF),
|
|
(b"RIFF\x00\x00\x00\x00WEBPVP8 ", WEBP),
|
|
(b"\x1a\x45\xdf\xa3....", WEBM),
|
|
(_iso(b"isom"), MP4),
|
|
(_iso(b"mp42"), MP4),
|
|
(_iso(b"qt "), MOV),
|
|
(_iso(b"M4V "), M4V),
|
|
(_iso(b"heic"), HEIC),
|
|
(_iso(b"HEIX"), HEIC),
|
|
(_iso(b"mif1"), HEIF),
|
|
(_iso(b"avif"), AVIF),
|
|
(b'<?xml version="1.0"?><svg/>', SVG),
|
|
(b"<svg xmlns='x'/>", SVG),
|
|
(b"\xef\xbb\xbf <svg/>", SVG),
|
|
],
|
|
)
|
|
def test_every_allowlisted_format_is_recognised(payload: bytes, expected: MediaKind) -> None:
|
|
assert sniff(payload) is expected
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"payload",
|
|
[
|
|
b"",
|
|
b"just some text",
|
|
b"RIFF\x00\x00\x00\x00WAVEfmt ", # RIFF, but not a picture
|
|
b"RIFF", # truncated before the form type
|
|
b"%PDF-1.7",
|
|
b"\x00\x00\x00\x20ftyq" + b"isom", # "ftyq", not "ftyp"
|
|
b"MZ\x90\x00",
|
|
],
|
|
)
|
|
def test_anything_off_the_allowlist_is_refused(payload: bytes) -> None:
|
|
assert sniff(payload) is None
|
|
|
|
|
|
def test_a_jpeg_named_as_a_png_is_still_a_jpeg() -> None:
|
|
"""The filename is attacker-chosen and is never consulted."""
|
|
assert sniff(b"\xff\xd8\xff\xe0evil.png") is JPEG
|
|
|
|
|
|
def test_every_kind_has_a_media_type_the_pack_knows() -> None:
|
|
"""The gap that takes startup down: ingested here, refused by pack_load.
|
|
|
|
A file stored with a suffix MEDIA_TYPES does not carry uploads fine and
|
|
then fails the *next* load, so this is the check that has to exist.
|
|
"""
|
|
for kind in KINDS:
|
|
assert kind.suffix in MEDIA_TYPES, kind.suffix
|
|
assert MEDIA_TYPES[kind.suffix] == kind.media_type
|
|
|
|
|
|
def test_only_webm_and_svg_are_stored_unstripped() -> None:
|
|
"""kuhy's decision of 2026-08-31, pinned so it cannot spread silently."""
|
|
unstrippable = {kind.suffix for kind in KINDS if not kind.strippable}
|
|
assert unstrippable == {".webm", ".svg"}
|