言語処理100本ノック(2020): 24

"""
24. ファイル参照の抽出
記事から参照されているメディアファイルをすべて抜き出せ．
"""

import json
import re


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"]


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


# ans24
def get_file(string: str) -> list:
    """
    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'
        - (...)       matches whatever regular expression is inside the parentheses,
        - (?:...)     a non-capturing version of regular parentheses.
        - ?           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>'

    Input:
        - '[[ファイル:2019 Greenwich Peninsula & Canary Wharf.jpg|150px]]'
    Return:
        - '2019 Greenwich Peninsula & Canary Wharf.jpg'
    """
    pattern = re.compile(
        r"""
            (?:File|ファイル)  # 非キャプチャ、'File'か'ファイル'
            :
            (.+?)            # キャプチャ対象、任意の文字1文字以上、非貪欲
            \|
            """,
        re.MULTILINE | re.VERBOSE,
    )
    result = re.findall(pattern, string)
    return result


files = get_file(uk_text)

for f in files:
    print(f)
# Royal Coat of Arms of the United Kingdom.svg
# Descriptio Prime Tabulae Europae.jpg
# Lenepveu, Jeanne d'Arc au siège d'Orléans.jpg