言語処理100本ノック(2020): 42

"""
42. 係り元と係り先の文節の表示
係り元の文節と係り先の文節のテキストをタブ区切り形式ですべて抽出せよ．ただし，句読点などの記号は出力しないようにせよ．
"""
from collections import defaultdict
from typing import List


def read_file(fpath: str) -> List[List[str]]:
    """Get clear format of parsed sentences.

    Args:
        fpath (str): File path.

    Returns:
        List[List[str]]: List of sentences, and each sentence contains a word list.
                         e.g. result[1]:
                            ['* 0 2D 0/0 -0.764522',
                             '\u3000\t記号,空白,*,*,*,*,\u3000,\u3000,\u3000',
                             '* 1 2D 0/1 -0.764522',
                             '吾輩\t名詞,代名詞,一般,*,*,*,吾輩,ワガハイ,ワガハイ',
                             'は\t助詞,係助詞,*,*,*,*,は,ハ,ワ',
                             '* 2 -1D 0/2 0.000000',
                             '猫\t名詞,一般,*,*,*,*,猫,ネコ,ネコ',
                             'で\t助動詞,*,*,*,特殊・ダ,連用形,だ,デ,デ',
                             'ある\t助動詞,*,*,*,五段・ラ行アル,基本形,ある,アル,アル',
                             '。\t記号,句点,*,*,*,*,。,。,。']
    """
    with open(fpath, mode="rt", encoding="utf-8") as f:
        sentences = f.read().split("EOS\n")
    return [sent.strip().split("\n") for sent in sentences if sent.strip() != ""]


class Morph:
    """Morph information for each token.

    Args:
        data (dict): A dictionary contains necessary information.

    Attributes:
        surface (str): 表層形（surface）
        base (str): 基本形（base）
        pos (str): 品詞（base）
        pos1 (str): 品詞細分類1（pos1
    """

    def __init__(self, data):
        self.surface = data["surface"]
        self.base = data["base"]
        self.pos = data["pos"]
        self.pos1 = data["pos1"]

    def __repr__(self):
        return f"Morph({self.surface})"

    def __str__(self):
        return "surface[{}]\tbase[{}]\tpos[{}]\tpos1[{}]".format(
            self.surface, self.base, self.pos, self.pos1
        )


class Chunk:
    """Containing information for Clause/phrase.

    Args:
        data (dict): A dictionary contains necessary information.

    Attributes:
        chunk_id (str): The number of clause chunk (文節番号).
        morphs List[Morph]: Morph (形態素) list.
        dst (str): The index of dependency target (係り先文節インデックス番号).
        srcs (List[str]): The index list of dependency source. (係り元文節インデックス番号).
    """

    def __init__(self, chunk_id, dst):
        self.id = chunk_id
        self.morphs = []
        self.dst = dst
        self.srcs = []

    def __repr__(self):
        return "Chunk( id: {}, dst: {}, srcs: {}, morphs: {} )".format(
            self.id, self.dst, self.srcs, self.morphs
        )


def convert_sent_to_chunks(sent: List[str]) -> List[Morph]:
    """Extract word and convert to morph.

    Args:
        sent (List[str]): A sentence contains a word list.
                            e.g. sent:
                               ['* 0 1D 0/1 0.000000',
                                '吾輩\t名詞,代名詞,一般,*,*,*,吾輩,ワガハイ,ワガハイ',
                                'は\t助詞,係助詞,*,*,*,*,は,ハ,ワ',
                                '* 1 -1D 0/2 0.000000',
                                '猫\t名詞,一般,*,*,*,*,猫,ネコ,ネコ',
                                'で\t助動詞,*,*,*,特殊・ダ,連用形,だ,デ,デ',
                                'ある\t助動詞,*,*,*,五段・ラ行アル,基本形,ある,アル,アル',
                                '。\t記号,句点,*,*,*,*,。,。,。']

    Parsing format:
        e.g. "* 0 1D 0/1 0.000000"
        | カラム | 意味                                                         |
        | :----: | :----------------------------------------------------------- |
        |   1    | 先頭カラムは`*`。係り受け解析結果であることを示す。          |
        |   2    | 文節番号（0から始まる整数）                                  |
        |   3    | 係り先番号＋`D`                                              |
        |   4    | 主辞/機能語の位置と任意の個数の素性列                        |
        |   5    | 係り関係のスコア。係りやすさの度合で、一般に大きな値ほど係りやすい。 |

    Returns:
        List[Chunk]: List of chunks.
    """
    chunks = []
    chunk = None
    srcs = defaultdict(list)

    for i, word in enumerate(sent):
        if word[0] == "*":
            # Add chunk to chunks
            if chunk is not None:
                chunks.append(chunk)

            # eNw Chunk beggin
            chunk_id = word.split(" ")[1]
            dst = word.split(" ")[2].rstrip("D")
            chunk = Chunk(chunk_id, dst)
            srcs[dst].append(chunk_id)  # Add target->source to mapping list

        else:  # Add Morch to chunk.morphs
            features = word.split(",")
            dic = {
                "surface": features[0].split("\t")[0],
                "base": features[6],
                "pos": features[0].split("\t")[1],
                "pos1": features[1],
            }
            chunk.morphs.append(Morph(dic))

            if i == len(sent) - 1:  # Add the last chunk
                chunks.append(chunk)

    # Add srcs to each chunk
    for chunk in chunks:
        chunk.srcs = list(srcs[chunk.id])

    return chunks


def concat_morphs_surface(chunk: Chunk) -> str:
    """Concatenate morph surfaces in a chink.

    Args:
        chunk (Chunk): e.g. Chunk( id: 0, dst: 5, srcs: [], morphs: [Morph(吾輩), Morph(は)]
    Return:
        e.g. '吾輩は'
    """
    res = ""
    for morph in chunk.morphs:
        if morph.pos != "記号":
            res += morph.surface
    return res


def concat_chunks_surface(chunks: List[Chunk]):
    """Concatenate surface of dependency source and target between chunks.

    Args:
        chunks (List[Chunk]): chunks represent a sentences.
            e.g. [Chunk( id: 0, dst: 5, srcs: [], morphs: [Morph(吾輩), Morph(は)] ),
                  Chunk( id: 1, dst: 2, srcs: [], morphs: [Morph(ここ), Morph(で)] ),
                  Chunk( id: 2, dst: 3, srcs: ['1'], morphs: [Morph(始め), Morph(て)] ),
                  Chunk( id: 3, dst: 4, srcs: ['2'], morphs: [Morph(人間), Morph(という)] ),
                  Chunk( id: 4, dst: 5, srcs: ['3'], morphs: [Morph(もの), Morph(を)] ),
                  Chunk( id: 5, dst: -1, srcs: ['0', '4'], morphs: [Morph(見), Morph(た), Morph(。)] )]
    """
    chunks_surface = []
    for chunk in chunks:
        if len(chunk.srcs) == 0:
            continue
        else:
            current_chunk_surface = concat_morphs_surface(chunk)
            for src in chunk.srcs:
                src_chunk = chunks[int(src)]
                src_chunk_surface = concat_morphs_surface(src_chunk)
                chunks_surface.append(
                    "{}  {}".format(src_chunk_surface, current_chunk_surface)
                )
    return chunks_surface


fpath = "neko.txt.cabocha"
sentences = read_file(fpath)
chunks = [convert_sent_to_chunks(sent) for sent in sentences]  # ans41
result = [concat_chunks_surface(sent) for sent in chunks]  # ans42
result = list(filter(lambda x: len(x) != 0, result))  # filtering the empty list

for sent in result[:3]:
    print(sent)

# ['吾輩は  猫である']
# ['名前は  無い', 'まだ  無い']
# ['どこで  生れたか', '生れたか  つかぬ', 'とんと  つかぬ', '見当が  つかぬ']