def main():
lines = open(sys.argv[1]).readlines()
text = nlp040.parse_text(lines)
for sentence in text:
for i in range(len(sentence)):
if sentence[i].contains('名詞'):
out = extract(sentence, i)
if len(out):
p(' -> '.join(out) + '\n')
def main():
lines = open(sys.argv[1]).readlines()
text = nlp040.parse_text(lines)
for sentence in text:
for chunk in sentence:
if len(chunk.srcs) > 0 and chunk.contains('動詞') \
and any([sentence[idx].contains('名詞') for idx in chunk.srcs]):
txt = ''
for src in chunk.srcs:
txt += sentence[src].text()
print(txt + '\t' + chunk.text())
def main():
lines = open(sys.argv[1]).readlines()
text = nlp040.parse_text(lines)
for sentence in text:
for chunk in sentence:
if len(chunk.srcs) > 0:
txt = ''
for src in chunk.srcs:
txt += sentence[src].text()
print(txt + '\t' + chunk.text())
def main():
lines = open(sys.argv[1]).readlines()
text = nlp040.parse_text(lines)
with open(sys.argv[2], 'w') as o:
i = 0
o.write('digraph 吾輩は猫である {\n')
for sentence in text[0:10]:
o.write('subgraph sentence{0} {{\n'.format(i))
for chunk in sentence:
if chunk.dst > 0:
o.write('"' + chunk.text() + '" -> "' +
sentence[chunk.dst].text() + '";\n')
o.write('}\n')
i += 1
o.write('}\n')
def main():
lines = open(sys.argv[1]).readlines()
text = nlp040.parse_text(lines)
with open(sys.argv[2], 'w') as o:
for sentence in text:
for chunk in sentence:
for x in chunk.get('動詞'):
ys = []
zs = []
for src in chunk.srcs:
for y in sentence[src].get('助詞'):
ys.append(y.base)
zs.append(sentence[src].text())
if len(ys) > 0:
lis = sorted(zip(ys, zs), key=lambda x: x[0])
ys = [x[0] for x in lis]
zs = [x[1] for x in lis]
o.write(x.base + '\t' + ' '.join(ys) + '\t' +
' '.join(zs) + '\n')