"""Tests for src.loader — config loading and data normalization."""
import sys
from pathlib import Path
from unittest.mock import patch

import pandas as pd

sys.path.insert(0, str(Path(__file__).resolve().parent.parent))

from src.loader import load_config, normalize_columns, _clean_numeric, get_available_weeks


class TestLoadConfig:
    def test_loads_config(self):
        config_path = Path(__file__).resolve().parent.parent / "config.yaml"
        if config_path.exists():
            config = load_config(config_path)
            assert "google_sheets" in config
            assert "metrics" in config
            assert isinstance(config["metrics"], list)


class TestNormalizeColumns:
    def test_renames_by_index(self):
        df = pd.DataFrame({
            "A": ["US"], "B": ["Google"], "C": ["Awareness"],
            "D": ["campaign1"], "E": ["2026-01-01"],
        })
        config = {"columns": {
            "country_idx": 0, "platform_idx": 1,
            "campaign_type_idx": 2, "campaign_name_idx": 3,
            "date_idx": 4,
        }}
        result = normalize_columns(df, config)
        assert "country" in result.columns
        assert "platform" in result.columns
        assert "date" in result.columns
        assert result["country"].iloc[0] == "US"


class TestCleanNumeric:
    def test_plain_number(self):
        s = pd.Series(["100", "200.5", "0"])
        result = _clean_numeric(s)
        assert list(result) == [100.0, 200.5, 0.0]

    def test_dollar_sign(self):
        s = pd.Series(["$1,234.56", "$0.50"])
        result = _clean_numeric(s)
        assert abs(result.iloc[0] - 1234.56) < 0.01
        assert abs(result.iloc[1] - 0.50) < 0.01

    def test_percentage(self):
        s = pd.Series(["2.50%", "10.00%"])
        result = _clean_numeric(s)
        assert abs(result.iloc[0] - 0.025) < 0.001
        assert abs(result.iloc[1] - 0.10) < 0.001

    def test_nan_handling(self):
        s = pd.Series(["", "abc", "100"])
        result = _clean_numeric(s)
        assert pd.isna(result.iloc[0])
        assert pd.isna(result.iloc[1])
        assert result.iloc[2] == 100.0


class TestGetAvailableWeeks:
    def test_returns_sorted_pairs(self):
        df = pd.DataFrame({
            "year": [2026, 2026, 2025, 2026],
            "week": [2, 1, 52, 3],
        })
        result = get_available_weeks(df)
        assert result == [(2025, 52), (2026, 1), (2026, 2), (2026, 3)]