言語処理100本ノック(2020): 26

"""
26. 強調マークアップの除去
25の処理時に，テンプレートの値からMediaWikiの強調マークアップ（弱い強調，強調，強い強調のすべて）を除去してテキストに変換せよ（参考: マークアップ早見表）．
"""

import json
import re

import utils


def get_uk_text(path):
    with open(path) as f:
        for line in f:
            line_data = json.loads(line)
            if line_data["title"] == "イギリス":
                data = line_data
                break
    return data["text"]


def get_basic_info(string: str) -> str:
    """Get basic information section
    """
    pattern = re.compile(
        r"""
            ^\{\{基礎情報.*?$   # '{{基礎情報'で始まる行
            (.*?)       # キャプチャ対象、任意の0文字以上、非貪欲
            ^\}\}$      # '}}'で終わる行
        """,
        re.MULTILINE | re.DOTALL | re.VERBOSE,
    )

    return re.findall(pattern, string)[0]


def get_content(string: str) -> list:
    r"""
    https://docs.python.org/3/library/re.html#regular-expression-syntax

    RE:
        - re.X (re.VERBOSE)     Allow us add command to explain the regular expression
        - re.M (re.MULTILINE)   Apply match to each line. If not specified, only match the first line.
        - re.S (re.DOTALL)      Allow to recognize '\n'
        - ^\|       String begin with |
        - ?         Causes the resulting RE to match 0 or 1 repetitions

        - *?        The '*' qualifier is greedy.
                    Adding ? after the qualifier makes it perform the match in non-greedy or minimal fashion; as few characters as possible will be matched.
                    e.g. <.*> is matched against '<a> b <c>'
                    e.g. <.*?> will match only '<a>'

        - (...)     Matches whatever regular expression is inside the parentheses,
        - (?=...)   Matches if ... matches next, but doesn’t consume any of the string. This is called a lookahead assertion.
                    For example, Isaac (?=Asimov) will match 'Isaac ' only if it’s followed by 'Asimov'.
        - (?:...)   A non-capturing version of regular parentheses.

    Input:
        - '|国章リンク =（[[イギリスの国章|国章]]）'
    Return:
        - {'国章リンク': '（[[イギリスの国章|国章]]）'}
    """
    pattern = re.compile(
        r"""
            ^\|
            (.+?)
            \s*
            =
            \s*
            (.+?)
            (?:
                (?=\n\|)
                |
                (?=\n$)
                )
            """,
        re.MULTILINE | re.DOTALL | re.VERBOSE,
    )
    result = re.findall(pattern, string)
    return {k: v for k, v in result}  # dict is ordered when using python 3.7


def remove_markup(text: str) -> str:
    pattern = re.compile(
        r"""
            \'{2,5} # 2〜5個の'
        """,
        re.VERBOSE,
    )

    return re.sub(pattern, "", text)


uk_text = get_uk_text("jawiki-country.json")  # See uk_text.txt

# ans25
basic_info = get_basic_info(uk_text)
fields = get_content(basic_info)  # See 25_en_basic_info.json

# ans26
result = {k: remove_markup(v) for k, v in fields.items()}
utils.save_json(result, "26_no_markup.json")
# ('確立形態4', "現在の国号「'''グレートブリテン及び北アイルランド連合王国'''」に変更")
# ->
# ('確立形態4', '現在の国号「グレートブリテン及び北アイルランド連合王国」に変更')