gistfile1.txt

def same_subtitle(current_subtitle, next_subtitle):
    '''Return true if the two given subtitles are the same (but can tolerate a bit difference)'''
    # convert the two subtitle into set e.g. '我很乖' -> {'我','很','乖'}
    current_set = set(current_subtitle)
    next_set = set(next_subtitle)
    current_set_len = len(current_set)
    next_set_len = len(next_set)
    intersect_set = current_set & next_set
    intersect_set_len = len(intersect_set)
    
    # if any of the two subtitle are of 70% the same with the intersected set return True
    if intersect_set_len >= 0.7 * current_set_len or intersect_set_len >= 0.7 * next_set_len:
        return True
    else:
        return False