"""Tests for the message-type normalization parser (Task 1.6).

The parser must be total — it never raises on weird input — because every
incoming WeChat record runs through it during a scrape, and one malformed
type code must not abort the whole pull. Unknown codes pass through as
``"unknown"`` so the message is still ingested (and recoverable via
``raw_json``); only the ``-2`` date-divider code maps to ``"divider"``,
which the scraper uses as its drop signal.
"""

from __future__ import annotations

import pytest

from app.scraper.parsers import normalize_wechat_type


@pytest.mark.parametrize(
    "raw,expected",
    [
        # Documented codes.
        (1, "text"),
        (-2, "divider"),
        # Phase-0 unknown codes — pass through as "unknown", never dropped.
        (3, "unknown"),    # image
        (34, "unknown"),   # voice
        (49, "unknown"),   # file / link / transfer
        (10000, "unknown"),
        # Stringified ints (the upstream API may send either form).
        ("1", "text"),
        ("-2", "divider"),
        ("34", "unknown"),
    ],
)
def test_normalize_wechat_type_maps_known_and_unknown(raw, expected):
    assert normalize_wechat_type(raw) == expected


def test_normalize_wechat_type_never_raises():
    """Whatever we throw at it, it returns a string — never raises."""
    for raw in (None, "", "junk", "1.5", [], {}, object(), float("nan")):
        out = normalize_wechat_type(raw)
        assert isinstance(out, str)
        assert out == "unknown"