def __init__(self, cacm_words_path, common_words_filename):
with open(cacm_words_path, 'r') as f:
self.lines = f.readlines()
self.current_line_number = 0
self.document_begin_regex = re.compile('^\.I\s(?P<id>\d*)')
self.category_markers = [
'.I', '.T', '.W', '.B', '.A', '.N', '.X', '.K', '.C'
]
self.documents = []
self.text_processor = Process_text(common_words_filename)
