INNER CODE UNIT · Python

clean_release_notes

sameerasw/essentials · .github/scripts/clean_release_notes.py:14

def clean_release_notes(raw: str) -> str:
    text = re.sub(r"<img\b[^>]*\/?>", "", raw, flags=re.IGNORECASE)
    text = re.sub(r"<a\b[^>]*>\s*</a>", "", text, flags=re.IGNORECASE)
    text = re.sub(r"^[-\*_]{3,}\s*$", "", text, flags=re.MULTILINE)
    text = re.sub(r"</?(?:details|summary|h[1-6]|p|div|span|align)\b[^>]*>", "", text, flags=re.IGNORECASE)
    text = re.sub(r"!\[.*?\]\(.*?\)", "", text)

    def convert_md_link(match):
        return f'<a href="{match.group(2)}">{match.group(1)}</a>'

    text = re.sub(r"\[(.*?)\]\((.*?)\)", convert_md_link, text)
    text = re.sub(r"\*\*(.*?)\*\*", r"<b>\1</b>", text)

    cleaned_lines = []
    in_quote = False
    quote_buf = []

    for line in text.splitlines():

View source record →

📰 Research Paper
Loading…
⏳ Fetching content…