mirror of
https://github.com/kuhyx/signal-bot.git
synced 2026-11-11 18:14:06 +01:00
Krzysztof kuhy Rudnicki
46db2e7753
The tally was one integer per person, deleted after each post. Nothing dated survived it, so weeks, months, records, streaks and weekday averages were all unanswerable. This replaces it with an append-only per-message log holding metadata only -- never a message body -- and rebuilds the nightly report on top. What changes for the group: a photo posted without a caption now counts (it was worth zero), stickers count, the bot's own messages no longer do, people who said nothing appear with a 0, and the report covers the previous full calendar day in Europe/Warsaw instead of "since the last post" -- which used to merge two days whenever a group went quiet. Notable decisions, each with the trap it avoids: - Events and people are PERMANENT_TABLES: neither forget_group nor a future SCHEMA_VERSION bump may drop them. Both paths used to cost a day's counter and would now cost the entire history, and forget_group fires on a listing that merely omits members. - is_own comes from which envelope branch carried the payload, not from comparing identities. The account is spelled as a uuid on some frames and a +E.164 number on others, so any comparison misses one of them. - The roster is stashed in refresh(), not _adopt(), which returns early once the watched set stops changing -- i.e. always, in the steady state. - The roster matches on uuid OR number because /v1/groups spells kuhy as +48516501330 while his messages carry an ACI uuid. Joining on uuid alone would have listed him twice every night, once with 0. - Members whose display name we have never seen are counted, not named: their only spellings are a uuid or a phone number. - (group, uuid, sent_at_ms) is the primary key, so a websocket redelivery after a reconnect cannot inflate the counts. - Days come from a stored Warsaw date string, never a timestamp range: 2026-03-29 is 23 hours long and 2026-10-25 is 25. - Polish number agreement is a real rule with a 12-14 exception, so "44 znaki" and "45 znaków" are both spelled correctly. config.py and startup.py were two lines under the 250-line cap and both had to grow, so config_env and startup_retry come out of them first, as pure moves. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_015d48t4qsQLBJnDwDeo2Nom
100 lines
3.4 KiB
Python
100 lines
3.4 KiB
Python
# Copyright (c) 2026 Krzysztof Rudnicki. MIT licence.
|
|
"""The database shape, kept apart from the code that queries it.
|
|
|
|
Split out of ``store.py`` so both stay under the 250-line cap, and because
|
|
"what the tables are" and "how the bot reads them" are two things.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from typing import Final
|
|
|
|
# Bumped whenever the shape below changes. See Store._apply_schema for why
|
|
# a version number is the only safe way to notice.
|
|
#
|
|
# Deliberately NOT bumped when a whole new table is added: CREATE TABLE IF
|
|
# NOT EXISTS is additive and harmless, whereas a bump drops every table and
|
|
# would throw away the live tallies to gain nothing.
|
|
SCHEMA_VERSION: Final = 2
|
|
|
|
# Every table is keyed by group first. The bot watches several groups, and a
|
|
# tally, a cooldown or a vote that leaked between them would mean a test
|
|
# message throttling the production group -- so the scope is in the primary
|
|
# key rather than in the callers' discipline.
|
|
SCHEMA: Final = """
|
|
CREATE TABLE IF NOT EXISTS command_uses (
|
|
group_id TEXT NOT NULL,
|
|
user_uuid TEXT NOT NULL,
|
|
command TEXT NOT NULL,
|
|
used_at REAL NOT NULL,
|
|
PRIMARY KEY (group_id, user_uuid, command)
|
|
);
|
|
CREATE TABLE IF NOT EXISTS daily_uses (
|
|
group_id TEXT NOT NULL,
|
|
user_uuid TEXT NOT NULL,
|
|
command TEXT NOT NULL,
|
|
day TEXT NOT NULL,
|
|
uses INTEGER NOT NULL DEFAULT 0,
|
|
PRIMARY KEY (group_id, user_uuid, command, day)
|
|
);
|
|
CREATE TABLE IF NOT EXISTS votes (
|
|
group_id TEXT NOT NULL,
|
|
command TEXT NOT NULL,
|
|
voter_uuid TEXT NOT NULL,
|
|
voted_at REAL NOT NULL,
|
|
PRIMARY KEY (group_id, command, voter_uuid)
|
|
);
|
|
CREATE TABLE IF NOT EXISTS group_meta (
|
|
group_id TEXT NOT NULL,
|
|
key TEXT NOT NULL,
|
|
value TEXT NOT NULL,
|
|
PRIMARY KEY (group_id, key)
|
|
);
|
|
CREATE TABLE IF NOT EXISTS message_events (
|
|
group_id TEXT NOT NULL,
|
|
uuid TEXT NOT NULL,
|
|
display_name TEXT NOT NULL,
|
|
sent_at_ms INTEGER NOT NULL,
|
|
day TEXT NOT NULL,
|
|
local_hour INTEGER NOT NULL,
|
|
media_kind TEXT NOT NULL DEFAULT '',
|
|
media_count INTEGER NOT NULL DEFAULT 0,
|
|
char_len INTEGER NOT NULL DEFAULT 0,
|
|
is_command INTEGER NOT NULL DEFAULT 0,
|
|
is_reply INTEGER NOT NULL DEFAULT 0,
|
|
PRIMARY KEY (group_id, uuid, sent_at_ms)
|
|
);
|
|
CREATE INDEX IF NOT EXISTS idx_events_group_day
|
|
ON message_events (group_id, day);
|
|
CREATE INDEX IF NOT EXISTS idx_events_group_uuid_day
|
|
ON message_events (group_id, uuid, day);
|
|
CREATE TABLE IF NOT EXISTS group_people (
|
|
group_id TEXT NOT NULL,
|
|
uuid TEXT NOT NULL,
|
|
display_name TEXT NOT NULL,
|
|
number TEXT NOT NULL DEFAULT '',
|
|
first_seen TEXT NOT NULL,
|
|
last_seen TEXT NOT NULL,
|
|
PRIMARY KEY (group_id, uuid)
|
|
);
|
|
"""
|
|
|
|
# Cleared when the bot leaves a group, and rebuilt on a schema-version bump.
|
|
# Losing any of these costs a cooldown or a vote in progress.
|
|
EPHEMERAL_TABLES: Final = (
|
|
"command_uses",
|
|
"daily_uses",
|
|
"votes",
|
|
"group_meta",
|
|
)
|
|
# Never dropped, by either path. These hold the whole statistical history,
|
|
# which cannot be recomputed from anything -- so a transient group listing
|
|
# that omits a member (the exact failure discovery._permitted guards against)
|
|
# must not be able to delete years of it, and neither must a future schema
|
|
# bump that only meant to reshape a cooldown table.
|
|
PERMANENT_TABLES: Final = (
|
|
"message_events",
|
|
"group_people",
|
|
)
|
|
TABLES: Final = EPHEMERAL_TABLES + PERMANENT_TABLES
|