[PYTHON] 100 language processing knocks (2020): 22

"""
22.Extraction of category name
Extract the article category names (by name, not line by line).
"""

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"] == "England":
                data = line_data
                break
    return data["text"]


uk_text = get_uk_text("jawiki-country.json")
uk_text_list = uk_text.split("\n")
ans = [x for x in uk_text_list if "Category:" in x[:11]]
# ans:
# [[Category:Commonwealth of Nations]]
# [[Category:Commonwealth Kingdom|*]]
# [[Category:G8 member countries]]
# [[Category:European Union member states|Former]]
# [[Category:Maritime nation]]
# [[Category:Existing sovereign country]]
# [[Category:Island country]]
# [[Category:A nation / territory established in 1801]]


# ans22
def extract_category_value(string: str) -> str:
    """
    https://docs.python.org/3/library/re.html#regular-expression-syntax

    - re.VERBOSE  allow us add command to explain the regular expression
    - re.S        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: [[Category:England|*]]
    Output: 'England'
    """
    pattern = re.compile(
        r"""
        ^       #Beginning of line
        .*      #Any character 0 or more
        \[\[Category:
        (       #Start the group to be captured
        .*?     #Any character 0 or more, non-greedy match (when greedy, the latter half'|'Involves decorations that start with)
        )       #Group end
        (?:     #Start a group that is not captured
        \|.*    # '|'0 or more characters following
        )?      #Group end, 0 or 1 appearance
        \]\]
        .*      #Any character 0 or more
        $       #End of line
        """,
        re.VERBOSE | re.S,
    )
    result = re.findall(pattern, string)[0]
    return result


category_values = [extract_category_value(s) for s in ans]
print(category_values)
# ['England',
#  'Commonwealth of Nations',
#  'Commonwealth Kingdom',
#  'G8 member countries',
#  'European Union member states',
#  'Maritime nation',
#  'Existing sovereign country',
#  'Island country',
#  'A nation / territory established in 1801']