mirror of
https://github.com/kuhyx/signal-bot.git
synced 2026-11-11 12:57:32 +01:00
Krzysztof kuhy Rudnicki
dc1995b558
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 +48123456789 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
114 lines
3.4 KiB
Python
114 lines
3.4 KiB
Python
# Copyright (c) 2026 Krzysztof Rudnicki. MIT licence.
|
|
"""What happened on one Warsaw day.
|
|
|
|
Every query here groups on the stored ``day`` string rather than on a range of
|
|
timestamps. That is what makes the 23-hour and 25-hour days come out right --
|
|
see ``signal_bot.stats.periods`` for why the alternative silently does not.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from dataclasses import dataclass
|
|
from typing import TYPE_CHECKING
|
|
|
|
if TYPE_CHECKING:
|
|
from signal_bot.stats.events import EventStore
|
|
|
|
|
|
@dataclass(frozen=True, slots=True)
|
|
class DayRow:
|
|
"""One person's day."""
|
|
|
|
uuid: str
|
|
display_name: str
|
|
messages: int
|
|
media: int
|
|
commands: int
|
|
chars: int
|
|
|
|
@property
|
|
def is_silent(self) -> bool:
|
|
"""True when this person did not write at all."""
|
|
return self.messages == 0
|
|
|
|
|
|
@dataclass(frozen=True, slots=True)
|
|
class DayTotals:
|
|
"""The group's day, as one line of summary."""
|
|
|
|
messages: int
|
|
media: int
|
|
commands: int
|
|
chars: int
|
|
speakers: int
|
|
|
|
@property
|
|
def average_length(self) -> int:
|
|
"""Mean characters per message, rounded, or 0 on an empty day."""
|
|
if not self.messages:
|
|
return 0
|
|
return round(self.chars / self.messages)
|
|
|
|
|
|
def day_rows(events: EventStore, group_id: str, day: str) -> list[DayRow]:
|
|
"""Everyone who wrote on a day, most talkative first.
|
|
|
|
Ties break on display name so the order is stable between two renders of
|
|
the same day -- a leaderboard that reshuffles itself reads as a bug.
|
|
"""
|
|
rows = events.connection.execute(
|
|
"""
|
|
SELECT uuid,
|
|
display_name,
|
|
COUNT(*) AS messages,
|
|
SUM(media_count) AS media,
|
|
SUM(is_command) AS commands,
|
|
SUM(char_len) AS chars
|
|
FROM message_events
|
|
WHERE group_id = ? AND day = ?
|
|
GROUP BY uuid
|
|
ORDER BY messages DESC, display_name ASC
|
|
""",
|
|
(group_id, day),
|
|
).fetchall()
|
|
return [
|
|
DayRow(
|
|
uuid=r["uuid"],
|
|
display_name=r["display_name"],
|
|
messages=r["messages"],
|
|
media=r["media"],
|
|
commands=r["commands"],
|
|
chars=r["chars"],
|
|
)
|
|
for r in rows
|
|
]
|
|
|
|
|
|
def day_totals(rows: list[DayRow]) -> DayTotals:
|
|
"""Sum a day's rows. Derived from the rows so the two can never disagree."""
|
|
return DayTotals(
|
|
messages=sum(r.messages for r in rows),
|
|
media=sum(r.media for r in rows),
|
|
commands=sum(r.commands for r in rows),
|
|
chars=sum(r.chars for r in rows),
|
|
speakers=sum(1 for r in rows if r.messages),
|
|
)
|
|
|
|
|
|
def with_silent(rows: list[DayRow], roster: list[tuple[str, str]]) -> list[DayRow]:
|
|
"""Append a zero row for every named group member who did not write.
|
|
|
|
``roster`` is (uuid, display_name) for the people whose names are known.
|
|
Anyone in the group whose name we have never seen is deliberately absent:
|
|
they exist in the listing only as a raw uuid or a phone number, and
|
|
printing either into a group chat would leak it.
|
|
"""
|
|
spoke = {r.uuid for r in rows}
|
|
silent = [
|
|
DayRow(uuid=uuid, display_name=name, messages=0, media=0, commands=0, chars=0)
|
|
for uuid, name in roster
|
|
if uuid not in spoke
|
|
]
|
|
silent.sort(key=lambda r: r.display_name)
|
|
return rows + silent
|