japanese.py 文件源码

def get_vocabulary(current_pos=1):
    """
    get_vocabulary returns a single record of the current_pos line position

    current_pos: up to number of records
    """
    vocabulary = {}
    with open(VOCABULARY_FILENAME, 'rb') as fobj:
        reader = csv.reader(fobj, delimiter=',', encoding='utf-8')
        num_of_lines = 0
        for line in reader:
            num_of_lines += 1
            if num_of_lines == current_pos:
                vocabulary = dict(zip(VOCABULARY_FIELDS, line))
                break
    # Convert to UTF-8
    for key, value in vocabulary.iteritems():
        vocabulary[key] = value.encode("utf-8")
    return vocabulary