tests/test_data_layer.py

"""
Covers the parts of data_layer.py that don't require network access:
validate_ohlcv (duplicate/invalid/NaN handling), LocalCache round-trip,
and data_freshness classification. fetch_ohlcv() itself needs a real
network call and is exercised only by the smoke-test script (expected
to fail here with DataSourceError -- see README).
"""
import numpy as np
import pandas as pd

from data_layer import LocalCache, data_freshness, validate_ohlcv


def test_validate_removes_duplicates_and_keeps_first():
    idx = pd.to_datetime(["2024-01-01", "2024-01-01", "2024-01-02"], utc=True)
    df = pd.DataFrame({
        "open": [1, 999, 2], "high": [1, 999, 2], "low": [1, 999, 2],
        "close": [1, 999, 2], "volume": [10, 10, 10],
    }, index=idx)
    out, report = validate_ohlcv(df)
    assert report.duplicates_removed == 1
    assert len(out) == 2
    assert out.iloc[0]["close"] == 1  # first occurrence kept, not the duplicate


def test_validate_removes_invalid_ohlc_relationship():
    idx = pd.date_range("2024-01-01", periods=3, freq="1h", tz="UTC")
    df = pd.DataFrame({
        "open": [10, 10, 10],
        "high": [11, 9, 11],     # row 1: high < open -> invalid
        "low": [9, 9, 9],
        "close": [10.5, 10.5, 10.5],
        "volume": [5, 5, 5],
    }, index=idx)
    out, report = validate_ohlcv(df)
    assert report.invalid_ohlc_removed == 1
    assert len(out) == 2


def test_validate_removes_nan_rows_and_reports_them():
    idx = pd.date_range("2024-01-01", periods=3, freq="1h", tz="UTC")
    df = pd.DataFrame({
        "open": [10, np.nan, 10], "high": [11, 11, 11], "low": [9, 9, 9],
        "close": [10.5, 10.5, 10.5], "volume": [5, 5, 5],
    }, index=idx)
    out, report = validate_ohlcv(df)
    assert report.nan_rows_removed == 1
    assert len(out) == 2


def test_validate_marks_negative_volume_unavailable_not_invented():
    idx = pd.date_range("2024-01-01", periods=2, freq="1h", tz="UTC")
    df = pd.DataFrame({
        "open": [10, 10], "high": [11, 11], "low": [9, 9],
        "close": [10.5, 10.5], "volume": [5, -3],
    }, index=idx)
    out, _ = validate_ohlcv(df)
    assert np.isnan(out.iloc[1]["volume"]), "negative volume must become NaN, never a guessed positive number"


def test_local_cache_round_trip(tmp_path_str="/tmp/_moirai_test_cache.sqlite3"):
    import os
    if os.path.exists(tmp_path_str):
        os.remove(tmp_path_str)
    cache = LocalCache(tmp_path_str)
    idx = pd.date_range("2024-01-01", periods=3, freq="1h", tz="UTC")
    df = pd.DataFrame({"open": [1, 2, 3], "high": [1, 2, 3], "low": [1, 2, 3],
                        "close": [1, 2, 3], "volume": [1, 2, 3]}, index=idx)

    assert cache.get("EURUSD=X", "1h", "yfinance", "2024-01-01", "2024-01-02") is None
    cache.set("EURUSD=X", "1h", "yfinance", "2024-01-01", "2024-01-02", df)
    round_tripped = cache.get("EURUSD=X", "1h", "yfinance", "2024-01-01", "2024-01-02")
    assert round_tripped is not None
    assert len(round_tripped) == 3
    assert list(round_tripped["close"]) == [1, 2, 3]
    os.remove(tmp_path_str)


def test_data_freshness_classification():
    now = pd.Timestamp.now(tz="UTC")
    fresh = data_freshness(now - pd.Timedelta(minutes=1), "1h")
    stale = data_freshness(now - pd.Timedelta(hours=10), "1h")
    assert fresh["status"] == "fresh"
    assert stale["status"] == "stale"


def test_resolve_history_window_days():
    from data_layer import resolve_history_window
    kind, value = resolve_history_window("1 day")
    assert kind == "start"
    kind, value = resolve_history_window("30 days")
    assert kind == "start"


def test_resolve_history_window_months_uses_calendar_months():
    from data_layer import resolve_history_window
    from datetime import datetime, timezone
    kind, value = resolve_history_window("3 months")
    assert kind == "start"
    now = datetime.now(timezone.utc)
    delta_days = (now - value).days
    # 3 calendar months is 89-92 days depending on which months are spanned --
    # NOT exactly 90 (which a naive 30*3 approximation would assume).
    assert 88 <= delta_days <= 93, f"expected ~3 calendar months, got {delta_days} days"


def test_resolve_history_window_max():
    from data_layer import resolve_history_window
    kind, value = resolve_history_window("max")
    assert kind == "period"
    assert value == "max"


def test_resolve_history_window_years():
    from data_layer import resolve_history_window
    kind, value = resolve_history_window("2 years")
    assert kind == "start"