"""Tests for gen.py."""
from pathlib import Path

import pandas as pd
import pytest

from feed_ingestion.flows.youtube_monthly import gen

THIS_DIR = Path(__file__).parent


@pytest.mark.parametrize(
    'column_name, expected', [
        ('col1', 'col1'),
        ('Col 1', 'col_1'),
        ('Col : Header', 'col_header'),
    ]
)
def test_column_name_to_sql(column_name, expected):
    """Test column_name_to_sql."""
    converted = gen.sqlize_column_name(column_name)
    assert converted == expected


def test_df_to_ddl():
    """Test df_to_ddl."""
    data_dict = {
        'col1': [1, 0, 0],
        'col : Str': ['s1', 's2', 's3'],
        'Something Revenue': [0, 0, 0],
    }
    df = pd.DataFrame.from_dict(data_dict)
    expected = """
CREATE TABLE staging_raw_youtube_monthly_ (
col1 INTEGER,
  col_str TEXT,
  something_revenue REAL
)
    """.strip()

    ddl_create = gen.df_to_ddl(df)
    assert ddl_create == expected


@pytest.mark.parametrize(
    'csv_filename',
    [
        'music_summary.csv',
        'YouTube_dmgi_M_20230101_ADJ_claim_summary_v1-1.csv',
        'YouTube_theorchardmusic_M_20230101_ADJ_claim_summary_v1-1.csv',
    ]
)
def test_csv_to_ddl(csv_filename):
    """Test csv_to_ddl."""
    csv_file = THIS_DIR / 'files' / csv_filename
    ddl_file = THIS_DIR / 'files' / f'{csv_filename}.ddl.sql'

    result = gen.csv_to_ddl(str(csv_file))

    assert result == ddl_file.read_text()