def get_new_release_note_subsections()

in check-release-notes/main.py [0:0]

• 27 lines of code
• 5 McCabe index (conditional complexity)

def get_new_release_note_subsections(latest_release_note, stored_release_note):
    """
    Get the new release note subsections by comparing the new release note with the stored release note.
    Subsections are defined as any section that starts with <h3> header.
    Args:
        new_release_note: The new release note
        stored_release_note: The stored release note
    Returns:
        The new release note subsections
    """
    latest_release_note_subsections_html = re.split(
        r"\<h3\>.*?\<\/h3\>", latest_release_note.get("html")
    )[1:]
    latest_release_note_subsections_text_only = [
        BeautifulSoup(html, "html.parser").get_text()
        for html in latest_release_note_subsections_html
    ]
    latest_release_note_subsections_headers = re.findall(
        r"<h3>(.*)?</h3>", latest_release_note.get("html")
    )
    stored_release_note_subsections_html = re.split(
        r"\<h3\>.*?\<\/h3\>", stored_release_note.get("html")
    )[1:]
    stored_release_note_subsections_text_only = [
        BeautifulSoup(html, "html.parser").get_text()
        for html in stored_release_note_subsections_html
    ]
    stored_release_note_subsections_headers = re.findall(
        r"<h3>(.*)?</h3>", stored_release_note.get("html")
    )
    # Get only new subsections from the latest release note
    new_release_notes_subsections = ""
    for index, subsection_text in enumerate(latest_release_note_subsections_text_only):
        if subsection_text not in stored_release_note_subsections_text_only:
            new_release_notes_subsections += f"<h3>{latest_release_note_subsections_headers[index]}</h3>{latest_release_note_subsections_html[index]}"
    latest_release_note["html"] = new_release_notes_subsections
    return latest_release_note