import re
import html


def normalize_whitespace(s: str | None) -> str:
    if not s:
        return ""
    return re.sub(r"\s+", " ", s).strip()


def truncate(s: str, max_len: int, ellipsis: str = "...") -> str:
    if len(s) <= max_len:
        return s
    return s[: max_len - len(ellipsis)] + ellipsis


def strip_html_tags(s: str | None) -> str:
    if not s:
        return ""
    # Unescape HTML entities first
    s = html.unescape(s)
    # Remove tags
    s = re.sub(r"<[^>]+>", " ", s)
    return normalize_whitespace(s)


def slugify(s: str) -> str:
    s = s.lower().strip()
    s = re.sub(r"[^\w\s-]", "", s)
    s = re.sub(r"[\s_-]+", "-", s)
    return s