言語処理100本ノック(2020): 34

"""
33. 「AのB」Permalink
2つの名詞が「の」で連結されている名詞句を抽出せよ

[[{'surface': '', 'base': '*', 'pos': 'BOS/EOS', 'pos1': '*'},
  {'surface': '一', 'base': '一', 'pos': '名詞', 'pos1': '数'},
  {'surface': '', 'base': '*', 'pos': 'BOS/EOS', 'pos1': '*'}],
 [{'surface': '', 'base': '*', 'pos': 'BOS/EOS', 'pos1': '*'},
  {'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': '*'},
  {'surface': '。', 'base': '。', 'pos': '記号', 'pos1': '句点'},
  {'surface': '', 'base': '*', 'pos': 'BOS/EOS', 'pos1': '*'}],
"""
import itertools
from typing import List

import utils


def get_none_phase(sentence: List[dict]) -> List[str]:
    result = []
    for i, word in enumerate(sentence):
        if (
            word["surface"] == "の"
            and sentence[i - 1]["pos"] == "名詞"
            and sentence[i + 1]["pos"] == "名詞"
        ):
            result.append(sentence[i - 1]["surface"] + "の" + sentence[i + 1]["surface"])
    return result


data = utils.read_json("30_neko_mecab.json")
none_phases = [get_none_phase(sentence) for sentence in data]
# In [75]: none_phases[:10]
# Out[75]: [[], [], [], [], [], [], [], [], [], ['彼の掌']]
flat = list(itertools.chain(*none_phases))
# ['彼の掌', '掌の上', '書生の顔', 'はずの顔', '顔の真中']