ルビ付きテキストから読み仮名を抽出・除去する

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27

import re

PAREN_RUBY = re.compile(r"([一-龥々〆ヵヶ]+)（([ぁ-んァ-ン]+)）")
HTML_RUBY = re.compile(r"<ruby>(.+?)<rt>(.+?)</rt></ruby>")

def extract_ruby(text: str) -> tuple[str, list[tuple[str, str]]]:
    readings: list[tuple[str, str]] = []

    def replace_paren(match: re.Match[str]) -> str:
        kanji, ruby = match.groups()
        readings.append((kanji, ruby))
        return kanji

    text = PAREN_RUBY.sub(replace_paren, text)

    def replace_html(match: re.Match[str]) -> str:
        kanji, ruby = match.groups()
        readings.append((kanji, ruby))
        return kanji

    text = HTML_RUBY.sub(replace_html, text)
    return text, readings

sample = "機械学習（きかいがくしゅう）を支える<ruby>教師あり学習<rt>きょうしあり</rt></ruby>の基礎"
cleaned, ruby_list = extract_ruby(sample)
print(cleaned)
print(ruby_list)