def extract_verb_surface():
morphines, sentences = morphines_read()
verb_surface = []
with open("verb_surface_31.txt", "w") as fp:
for morphine in morphines:
if morphine["pos"] == "動詞":
verb_surface.append(morphine["surface"])
fp.write(morphine["surface"] + "\n")
return verb_surface
def extract_sahen_noun():
'''サ変接続の名詞を抽出'''
morphines, sentences = morphines_read()
sahen_noun = []
with open("sahen_noun_33.txt", "w") as fp:
for line in morphines:
if line["pos"] == "名詞" and line["pos1"] == "sahen":
sahen_noun.append(line["surface"])
fp.write(line["surface"] + "\n")
return sahen_noun
def extract_A_B():
'''2つの名詞が「の」で連結されている名詞句を抽出'''
morphines, sentences = morphines_read()
A_B = []
with open("AのB.txt", "w") as fp:
for i in range(len(morphines) - 2):
if morphines[i]["pos"] == "名詞" and morphines[i+1]["surface"] == "の"\
and morphines[i+2]["pos"] == "名詞":
str_ = morphines[i]["surface"] + morphines[i+1]["surface"]\
+ morphines[i+2]["surface"]
A_B.append(str_)
fp.write(str_ + "\n")
return A_B
def noun_sequence():
morphines, sentences = morphines_read()
noun_seq = []
str_ = ""
with open("noun_seq.txt", "w") as fp:
for i in range(len(morphines) - 1):
j = i
while morphines[j]["pos"] == "名詞":
j += 1
if j > len(morphines):
break
str_ += morphines[j]["surface"]
if (j - i) >= 2:
noun_seq.append(str_)
fp.write(str_ + "\n")
str_ = ""
return noun_seq