from knock41 import Chunk, cabocha_chunk_data
import collections
with open('../data/neko.txt.cabocha', 'r') as data_in:
with open('result/knock46.txt', 'w') as data_out:
for i, line in enumerate(cabocha_chunk_data(data_in)):
print('[{}行目]'.format(i + 1), file=data_out)
for phrase in line:
verb_pattern = ''
temp_src = collections.defaultdict(lambda: '')
if '動詞' in phrase.get_phrase_pos():
verb_pattern += phrase.get_phrase_list()[
phrase.get_phrase_pos().index('動詞')] + '\t'
for src in phrase.srcs:
if '助詞' in line[src].get_phrase_pos():
if '格助詞' in line[src].get_phrase_pos1():
temp_index = max([
k for k, y in enumerate(
line[src].get_phrase_pos1())
if y == '格助詞'
])
temp_src[line[src].get_phrase_txt(
)] = line[src].get_phrase_list()[temp_index]
else:
temp_index = max([
k for k, y in enumerate(
line[src].get_phrase_pos())
if y == '助詞'
])
temp_src[line[src].get_phrase_txt(
)] = line[src].get_phrase_list()[temp_index]
from knock41 import Chunk, cabocha_chunk_data
if __name__ == '__main__':
with open('../data/neko.txt.cabocha', 'r') as data_in:
with open('result/knock42.txt', 'w') as data_out:
for line in cabocha_chunk_data(data_in):
for phrase in line:
if phrase.get_phrase_txt() == '' or line[
phrase.dst].get_phrase_txt() == '':
continue
if phrase.dst == -1:
if phrase.srcs == []:
data_out.write(phrase.get_phrase_txt() + '\n')
else:
continue
else:
data_out.write(phrase.get_phrase_txt() + '\t\t' +
line[phrase.dst].get_phrase_txt() +
'\n')
data_out.write('\n')