from adalflow.datasets.big_bench_hard import BigBenchHard
import difflib

def check_datasets():
    train_data = BigBenchHard(split="train")
    expected = r"Example(id='a6d1c6de-4ff5-4f7f-a316-723c566645ea', question='I have a flute, a piano, a trombone, four stoves, a violin, an accordion, a clarinet, a drum, two lamps, and a trumpet. How many musical instruments do I have?', answer='8')"

    cases = [(str(expected), str(train_data[0]))]
    if train_data[0] == expected :
        print("Winner, winner! Chicken dinner!")
    else:
        for a,b in cases:
            print('{} => {}'.format(a,b))  
            for i,s in enumerate(difflib.ndiff(a,b)):
                if s[0]==' ':
                    print(u'No change "{}" from position {}'.format(s[-1],i))
                elif s[0]=='-':
                    print(u'Delete "{}" from position {}'.format(s[-1],i))
                elif s[0]=='+':
                    print(u'Add "{}" to position {}'.format(s[-1],i))   
check_datasets()