from utils import s3
import utils.Google.Docs.read_sheet as gdoc

def get_keywords(df, which='Release'):
    '''
    Searches gDoc dataframe for keywords for ArtistName or ReleaseName.
    Returns line-delimted string of list of keywords.
    Called only from get_filters()
    '''
    keys = df[ df[config.gdoc_col].isin(['Both', which]) ]['Keywords'].tolist()
    if keys:
        return '|'.join(keys)
    else:
        return

def get_filters(sheet):
    '''
    Breaks keywords and catagory into a dictionary containing
    which field to search for which keywords.
    '''
    df_filter = gdoc.sheet_2_df(id=config.sheet_id,
                                sheet=sheet,
                                range=config.sheet_range)
    filter_dict = dict()
    
    df_filter[config.gdoc_col] = df_filter[config.gdoc_col].str.strip()
    df_filter['Keywords'] = df_filter['Keywords'].str.lstrip().str.rstrip()

    # search for Release and Both
    filter_dict['RELEASENAME'] = get_keywords(df_filter, which='Release')

    # search for Artist and Both
    filter_dict['ARTISTNAME'] = get_keywords(df_filter, which='Artist')
    
    for key in ['RELEASENAME', 'ARTISTNAME']:
        if not filter_dict[key]:
            filter_dict.pop(key, None)
    
    return filter_dict

def find_keywords(df, keywords):
    '''
    Takes the dictionary from get_filters() and the entire dataset.
    Searches the releasename and the artistname for keywords.
    True is returned if either row gets a hit.
    '''
    release_keys = keywords.get('RELEASENAME')
    artist_keys = keywords.get('ARTISTNAME')

    if release_keys and artist_keys:
        hits = df['RELEASENAME'].str.contains(release_keys, case=False) \
             | df['ARTISTNAME'].str.contains(artist_keys, case=False)
    
    elif release_keys and not artist_keys:
        hits = df['RELEASENAME'].str.contains(release_keys, case=False)

    elif artist_keys and not release_keys:
        hits = df['ARTISTNAME'].str.contains(artist_keys, case=False)
    
    return hits