import json
from datetime import datetime, timedelta
from pathlib import Path

import pytest

from app import cycle_day_estimate, parse_iso_date, split_legacy_knowledge


def test_parse_iso_date_accepts_today():
    today = datetime.now().astimezone().date()
    assert parse_iso_date(today.isoformat()) == today


def test_parse_iso_date_rejects_future_date():
    today = datetime.now().astimezone().date()
    future = (today + timedelta(days=1)).isoformat()
    with pytest.raises(ValueError, match="future"):
        parse_iso_date(future)


def test_cycle_estimate_is_transparent():
    today = datetime.now().astimezone().date()
    day, explanation = cycle_day_estimate(today.isoformat(), 28)
    assert day == 1
    assert "cannot confirm hormonal phase or ovulation" in explanation


def test_legacy_splitter_retains_stable_ids():
    text = (
        "A sufficiently long first paragraph that should become a source chunk.\n\n"
        "A sufficiently long second paragraph that should become another chunk."
    )
    chunks = split_legacy_knowledge(text)
    assert [chunk.source_id for chunk in chunks] == ["legacy-001", "legacy-002"]


def test_active_sources_are_traceable():
    source_path = Path(__file__).parents[1] / "knowledge" / "sources.json"
    records = json.loads(source_path.read_text(encoding="utf-8"))
    assert len(records) >= 5
    assert len({record["source_id"] for record in records}) == len(records)
    for record in records:
        assert record["url"].startswith("https://")
        assert record["reviewed_at"]
        assert len(record["text"]) >= 100