言語処理100本ノック(2020): 31

"""
31. 動詞
動詞の表層形をすべて抽出せよ．

[[{'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_verb(sentence: List[dict]) -> List:
    result = []
    for word in sentence:
        if word["pos"] == "動詞":
            result.append(word["surface"])
    return result


data = utils.read_json("30_neko_mecab.json")
verbs = [get_verb(sentence) for sentence in data if get_verb(sentence)]
# [['生れ', 'つか'], ['し', '泣い', 'し', 'いる'], ['始め', '見'], ['聞く'], ['捕え', '煮', '食う']]
flat = list(itertools.chain(*verbs))
#  ['生れ', 'つか', 'し', '泣い', 'し']