# Copyright (c) 2026 Krzysztof Rudnicki. MIT licence.
"""Reading the bot's own journal back, without copying names out of it."""

from __future__ import annotations

from signal_bot.analytics.journal import parse

PREFIX = "2026-08-31T21:28:26+02:00 archlinux run.sh[101862]:"
STAMP = "2026-08-31 21:28:26,217"


def running(command: str, who: str = "ala") -> str:
    """One real journal line, in the shape journalctl -o short-iso emits."""
    return f"{PREFIX} {STAMP} INFO signal_bot.dispatcher: running command {command} for {who}"


def test_a_running_line_is_read() -> None:
    (line,) = parse([running("cat")])
    assert (line.command, line.display_name, line.refused) == ("cat", "ala", False)


def test_the_timestamp_comes_from_the_journal_not_the_bot() -> None:
    """The journal's stamp carries an offset; the bot's asctime does not.

    A naive stamp read as UTC lands the whole import two hours out, which is
    exactly what the hour columns exist to get right.
    """
    (line,) = parse([running("cat")])
    # 2026-08-31T21:28:26+02:00 is 19:28:26 UTC.
    assert line.at_ms == 1_788_204_506_000


def test_an_album_command_keeps_its_pseudonym_key() -> None:
    """`pack:p1`, not `pack`. A \\w+ pattern silently truncates at the colon.

    That truncation would collapse thirteen different album commands into
    one, which is the difference between "who is asked for most" and a
    single meaningless total.
    """
    (line,) = parse([running("pack:p1")])
    assert line.command == "pack:p1"


def test_a_cooldown_refusal_is_read_as_one() -> None:
    text = (
        f"{PREFIX} {STAMP} INFO signal_bot.decorators: "
        "cooldown refused cat for ala: told them 8 sekund"
    )
    (line,) = parse([text])
    assert (line.command, line.refused) == ("cat", True)


def test_a_display_name_with_spaces_survives() -> None:
    """The pattern runs to end of line, because a display name is free text."""
    (line,) = parse([running("cat", "ala z basia")])
    assert line.display_name == "ala z basia"


def test_lines_that_are_not_about_commands_are_skipped() -> None:
    """Startup banners, tracebacks, envelope shapes, other units."""
    noise = [
        "2026-08-31T21:00:00+02:00 archlinux systemd[1474]: Started Signal group bot.",
        f"{PREFIX} {STAMP} DEBUG signal_bot.dispatcher: envelope shape: {{'a': 'str'}}",
        "not a journal line at all",
        "",
    ]
    assert list(parse(noise)) == []


def test_a_line_whose_stamp_is_not_a_timestamp_is_skipped() -> None:
    """Never guess a time. A wrong hour is worse than a missing row."""
    assert list(parse(["wednesday archlinux run.sh[1]: running command cat for ala"])) == []


def test_a_naive_stamp_is_refused() -> None:
    """Without an offset there is no way to know which hour this was."""
    text = "2026-08-31T21:28:26 archlinux run.sh[1]: running command cat for ala"
    assert list(parse([text])) == []


def test_a_dst_boundary_is_read_from_the_offset() -> None:
    """Warsaw is +02:00 in summer and +01:00 in winter, and both occur.

    Reading the wall clock and assuming one offset puts half the year's
    rows an hour out, in a column whose whole purpose is the hour.
    """
    summer = "2026-10-25T02:30:00+02:00 archlinux run.sh[1]: running command cat for ala"
    winter = "2026-10-25T02:30:00+01:00 archlinux run.sh[1]: running command cat for ala"
    (early,) = parse([summer])
    (late,) = parse([winter])
    assert late.at_ms - early.at_ms == 3_600_000