"""Generators for activities of the sql2sf workflow."""

from snowflake_etl.flows.sql2sf import config
from snowflake_etl.flows.sql2sf import helpers


def _get_min_max_pk(primary_key, source_schema, source_table, mysqldb_config):
    """Get min and max primary key values from a source table table.

    Args:
        primary_key (str): Primary key of table from which data is retrieved.
        source_schema (str): The name of the source schema (e.g.,
            'production'.
        source_table (str): The name of the source table (e.g.,
            'contact'.
        mysqldb_config (tuple): Host, port, username and password for a db.

    Returns:
        tuple: Min and max values of primary key.
    """
    sql = """
        SELECT MIN({primary_key}) as min_id,
               MAX({primary_key}) as max_id
        FROM `{source_schema}`.`{source_table}`
        """.format(
        source_schema=source_schema,
        primary_key=primary_key,
        source_table=source_table)
    results = helpers.execute_with_mysql(sql, 'fetchone', *mysqldb_config)
    min_id, max_id = results

    return min_id, max_id


def get_columns(source_schema, source_table, mysqldb_config):
    """Return a list of column names.

    Args:
        source_schema (str): The name of the source schema (e.g.,
            'production'.
        source_table (str): The name of the source table (e.g.,
            'contact'.
        mysqldb_config (tuple): Host, port, username and password for a db.

    Returns:
        list: A list of column names.
    """
    types_to_wrap = {
        'char': True,
        'varchar': True,
        'text': True,
        'mediumtext': True,
        'longtext': True,
        'enum': True,
        'set': True}

    sql = """SELECT COLUMN_NAME, DATA_TYPE
        FROM information_schema.columns
        WHERE TABLE_SCHEMA = '{source_schema}'
          AND TABLE_NAME = '{source_table}'
        ORDER BY ORDINAL_POSITION;""".format(
        source_schema=source_schema, source_table=source_table)
    results = helpers.execute_with_mysql(sql, 'fetchall', *mysqldb_config)
    columns = [(column[0], types_to_wrap.get(column[1])) for column in results]
    return columns


def get_min_max_pairs(
        primary_key, chunk_size, source_schema, source_table, mysqldb_config):
    """Return a list of min_id and max_id pairs for each data chunk.

    Args:
        primary_key (str): Primary key of table from which data is retrieved.
        chunk_size (int): Chunk size from entity setting.
        source_schema (str): The name of the source schema (e.g.,
            'production'.
        source_table (str): The name of the source table (e.g.,
            'contact'.
        mysqldb_config (tuple): Host, port, username and password for a db.

    Returns:
        list: A list of dictionaries of min_max pairs.
    """
    min_id, max_id = _get_min_max_pk(
        primary_key, source_schema, source_table, mysqldb_config)

    pairs = [
        {
            'min_id': pk,
            'max_id': min(pk + chunk_size - 1, max_id)
        }
        for pk in range(min_id, max_id, chunk_size)]

    return pairs


def unload_mysql_data_params(context):
    """Prepare input params for the unload_mysql_data task.

    Args:
        context (dict): Dictionary which is being passed through the workflow.

    Yields:
        dict: min_id and max_id dictionary for being iterated through.
    """
    source_db_host = context.get('bootstrap_sql2sf.source_db_host')
    source_schema = context.get('bootstrap_sql2sf.source_schema')
    source_table = context.get('bootstrap_sql2sf.source_table')

    sources = config.SourcesConf()

    mysqldb_config = sources.get_db_credentials(source_db_host, source_schema)

    columns = get_columns(source_schema, source_table, mysqldb_config)

    if sources.is_unload_in_chunks(
            source_db_host, source_schema, source_table):
        chunk_size = sources.get_chunk_size(
            source_db_host, source_schema, source_table)
        primary_key = sources.get_primary_key(
            source_db_host, source_schema, source_table)

        min_max_pairs = get_min_max_pairs(
            primary_key, chunk_size, source_schema, source_table,
            mysqldb_config)

        for pair in min_max_pairs:
            yield {'generator.table': source_table,
                   'generator.columns': columns,
                   'generator.bucket': context.get(
                       'bootstrap_sql2sf.destination_s3_bucket'),
                   'generator.destination_s3_key': context.get(
                       'bootstrap_sql2sf.destination_s3_key'),
                   'generator.min_id': pair.get('min_id'),
                   'generator.max_id': pair.get('max_id')}
    else:
        yield {
            'generator.table': source_table,
            'generator.columns': columns,
            'generator.bucket': context.get(
                'bootstrap_sql2sf.destination_s3_bucket'),
            'generator.destination_s3_key': context.get(
                'bootstrap_sql2sf.destination_s3_key')}