言語処理100本ノック(2020): 46

"""
## 46. 動詞の格フレーム情報の抽出[Permalink](https://nlp100.github.io/ja/ch05.html#46-動詞の格フレーム情報の抽出)

45のプログラムを改変し，述語と格パターンに続けて項（述語に係っている文節そのもの）をタブ区切り形式で出力せよ．45の仕様に加えて，以下の仕様を満たすようにせよ．

- 項は述語に係っている文節の単語列とする（末尾の助詞を取り除く必要はない）
- 述語に係る文節が複数あるときは，助詞と同一の基準・順序でスペース区切りで並べる

「吾輩はここで始めて人間というものを見た」という例文（neko.txt.cabochaの8文目）を考える． この文は「始める」と「見る」の２つの動詞を含み，「始める」に係る文節は「ここで」，「見る」に係る文節は「吾輩は」と「ものを」と解析された場合は，次のような出力になるはずである．


    始める  で      ここで
    見る    は を   吾輩は ものを


"""
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 get_surface(self) -> 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'
        """
        morphs = self.morphs
        res = ""
        for morph in morphs:
            if morph.pos != "記号":
                res += morph.surface
        return res

    def validate_pos(self, pos: str) -> bool:
        """Return Ture if '名詞' or '動詞' in chunk's morphs. Otherwise, return False."""
        morphs = self.morphs
        return any([morph.pos == pos for morph in 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 get_predicate_frame(chunks: List[Chunk]) -> List[dict]:
    """Get edges from sentence chunks.

    Terms:
        - 述語 (predicate)
        - 項 (argument)
        - 格 (case)

    Args:
        chunks (List[Chunk]): A sentence contains many chunks.
            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(。)] )]

    Returns:
        List[dict]: Predicate frame.
            e.g. [{'pred': '始める', 'case': ['で'], 'arg': ['ここで']},
                  {'pred': '見る', 'case': ['は', 'を'], 'arg': ['吾輩は', 'ものを']}]
    """
    patterns = []
    for chunk in chunks:
        # Skip if not valid
        if len(chunk.srcs) == 0 or all([morph.pos != "動詞" for morph in chunk.morphs]):
            continue

        # Initialize
        pred_frame = {"pred": None, "case": [], "arg": []}

        # Get predicate
        for morph in chunk.morphs:
            if morph.pos == "動詞":
                pred_frame["pred"] = morph.base
                break

        # Get case
        for src in chunk.srcs:
            src_chunk = chunks[int(src)]
            for morph in src_chunk.morphs:
                if morph.pos == "助詞":
                    pred_frame["case"].append(morph.base)
                    pred_frame["arg"].append(src_chunk.get_surface())

        # Add to patterns
        patterns.append(pred_frame)
    return patterns


def write_to_file(sents, path):
    """Write patterns to file.

    Args:
        pattern_sents ([type]): predicate-case patterns.
            e.g. [[{'pred': '生れる', 'case': ['で'], 'arg': ['どこで']},
                   {'pred': 'つく', 'case': ['か', 'が'], 'arg': ['生れたか', '見当が']}],
                  [{'pred': '泣く', 'case': ['で'], 'arg': ['所で']},
                   {'pred': 'する', 'case': ['て', 'だけ', 'は'], 'arg': ['泣いて', 'いた事だけは', 'いた事だけは']}]]
    """
    # convert_frame_to_text
    lines = []
    for sent in sents:
        for frame in sent:  # pattern: {'pred': '泣く', 'case': ['で'], 'arg': ['所で']}
            case_text = " ".join(frame["case"])
            arg_text = " ".join(frame["arg"])
            lines.append((frame["pred"], case_text, arg_text))

    # write_to_file
    with open(path, "w") as f:
        for line in lines:
            f.write(f"{line[0]}\t{line[1]}\t{line[2]}\n")


fpath = "neko.txt.cabocha"
sentences = read_file(fpath)
sentences = [convert_sent_to_chunks(sent) for sent in sentences]  # ans41

# ans46
pattern_sents = [get_predicate_frame(sent) for sent in sentences]
pattern_sents = list(filter(lambda x: len(x) != 0, pattern_sents))
write_to_file(pattern_sents, "predicate_frame.txt")

# "predicate_frame.txt":
# 生れる	で	どこで
# つく	か が	生れたか 見当が
# 泣く	で	所で
# する	て だけ は	泣いて いた事だけは いた事だけは
# 始める	で	ここで
# 見る	は を	吾輩は ものを
# 聞く	で	あとで
# 捕える	を	我々を