"""
Filename token sanitiser — ported line-for-line in behaviour from your
existing Dokumenten_Beschrifter.html tool, so a name built here and a name
built in the browser tool always match.
"""

import re

UMLAUT_MAP = {
    "ä": "ae", "ö": "oe", "ü": "ue", "ß": "ss",
}


def sanitise(text: str) -> str:
    """Lowercase, fold umlauts, spaces -> hyphens, strip anything that
    isn't a-z/0-9/hyphen, collapse repeats, trim leading/trailing hyphens."""
    if not text:
        return ""
    result = text.strip().lower()
    for src, repl in UMLAUT_MAP.items():
        result = result.replace(src, repl)
    result = re.sub(r"\s+", "-", result)
    result = re.sub(r"[^a-z0-9\-]", "", result)
    result = re.sub(r"-+", "-", result)
    return result.strip("-")


def build_filename(date: str, topic: str = "", subtopic: str = "",
                    extra: str = "", more: str = "", version: str = "",
                    ext: str = "") -> str:
    """Assemble the final filename from parts. Empty fields are skipped,
    so a file only needs as many fields filled in as makes sense for it —
    same rule as the HTML tool ("fill in as many or as few boxes as needed")."""
    parts = [sanitise(p) for p in (topic, subtopic, extra, more)]
    parts = [p for p in parts if p]
    if version and sanitise(version):
        parts.append(sanitise(version))
    stem = "_".join([date] + parts) if parts else date
    return f"{stem}{ext}"