def test_mecab_analysys_load(self):
"""
mecabファイルを読み込んで分析結果をdataに保持する
"""
test = "吾輩\t名詞,代名詞,一般,*,*,*,吾輩,ワガハイ,ワガハイ\n"
test += "は\t助詞,係助詞,*,*,*,*,は,ハ,ワ\n"
test += "EOS\n"
test += "猫\t名詞,一般,*,*,*,*,猫,ネコ,ネコ\n"
test += "で\t助動詞,*,*,*,特殊・ダ,連用形,だ,デ,デ\n"
test += "ある\t助動詞,*,*,*,五段・ラ行アル,基本形,ある,アル,アル\n"
test += "EOS"
ma = MecabAnalysys(test)
ma.load()
expection = [
[
{"surface": "吾輩", "base": "吾輩", "pos":"名詞", "pos1":"代名詞"},
{"surface": "は", "base": "は", "pos":"助詞", "pos1":"係助詞"},
],
[
{"surface": "猫", "base": "猫", "pos":"名詞", "pos1":"一般"},
{"surface": "で", "base": "だ", "pos":"助動詞", "pos1":"*"},
{"surface": "ある", "base": "ある", "pos":"助動詞", "pos1":"*"},
],
]
self.assertEqual(expection, ma.data)
def test_mecab_analysys_to_dict(self):
"""
一般的な動詞の解析
"""
test = "入っ\t動詞,自立,*,*,五段・ラ行,連用タ接続,入る,ハイッ,ハイッ"
ma = MecabAnalysys(test)
result = ma._to_dict(test)
expection = {"surface": "入っ", "base": "入る", "pos":"動詞", "pos1":"自立"}
self.assertEqual(expection, result)
def test_mecab_analysys_to_dict_comma(self):
"""
解析対象にカンマが入ったケース
"""
test = ",\t名詞,サ変接続,*,*,*,*,*"
ma = MecabAnalysys(test)
result = ma._to_dict(test)
expection = {"surface": ",", "base": "", "pos":"名詞", "pos1":"サ変接続"}
self.assertEqual(expection, result)
def test_mecab_analysys_get_all_morphemes(self):
"""
data全文の形態素解析結果を1つのリストにまとめて返す
"""
test = "吾輩\t名詞,代名詞,一般,*,*,*,吾輩,ワガハイ,ワガハイ\n"
test += "は\t助詞,係助詞,*,*,*,*,は,ハ,ワ\n"
test += "EOS\n"
test += "猫\t名詞,一般,*,*,*,*,猫,ネコ,ネコ\n"
test += "で\t助動詞,*,*,*,特殊・ダ,連用形,だ,デ,デ\n"
test += "ある\t助動詞,*,*,*,五段・ラ行アル,基本形,ある,アル,アル\n"
test += "EOS"
ma = MecabAnalysys(test)
ma.load()
expection = [
{"surface": "吾輩", "base": "吾輩", "pos":"名詞", "pos1":"代名詞"},
{"surface": "は", "base": "は", "pos":"助詞", "pos1":"係助詞"},
{"surface": "猫", "base": "猫", "pos":"名詞", "pos1":"一般"},
{"surface": "で", "base": "だ", "pos":"助動詞", "pos1":"*"},
{"surface": "ある", "base": "ある", "pos":"助動詞", "pos1":"*"},
]
self.assertEqual(expection, ma.get_all_morphemes())
# 32. 動詞の原形
# 動詞の原形をすべて抽出せよ．
import os
from mecabAnalysys import MecabAnalysys
if __name__ == "__main__":
src = os.path.join(os.path.dirname(__file__), r"../Output/Chapter4/neko.txt.mecab")
with open(src, encoding="utf-8") as f:
ma = MecabAnalysys("\n".join(f.readlines()))
ma.load()
morph = ma.get_all_morphemes()
verbs = list(filter(lambda x: x["pos"] == "動詞", morph))
disp = [v["base"] for v in verbs]
output = os.path.join(os.path.dirname(__file__), r"../Output/Chapter4/q32.txt")
with open(output, mode="w", encoding="utf-8") as f:
f.write("\n".join(disp))
# 30. 形態素解析結果の読み込み
# 形態素解析結果（neko.txt.mecab）を読み込むプログラムを実装せよ．
# ただし，各形態素は表層形（surface），基本形（base），品詞（pos），品詞細分類1（pos1）をキーとするマッピング型に格納し，
# 1文を形態素（マッピング型）のリストとして表現せよ．第4章の残りの問題では，ここで作ったプログラムを活用せよ．
import os
from mecabAnalysys import MecabAnalysys
if __name__ == "__main__":
src = os.path.join(os.path.dirname(__file__),
r"../Output/Chapter4/neko.txt.mecab")
with open(src, encoding="utf-8") as f:
ma = MecabAnalysys("\n".join(f.readlines()))
ma.load()
print(len(ma.data))
print(ma.sentence(2))