/// (pattern, replacement) — applied as whole-token, case-insensitive.
const ABBREV: &[(&str, &str)] = &[
    ("v.a.", "verdacht auf"),
    ("z.n.", "zustand nach"),
    ("art.", "arterielle"),
    ("op", "operation"),
    ("dd", "differentialdiagnose"),
    ("re.", "rechts"),
    ("li.", "links"),
];

/// Fold German umlauts and eszett to their ASCII digraph equivalents so that
/// "Hyperlipidämie" and "Hyperlipidaemie" collapse to one canonical token.
/// Operates on already-lowercased text (so only the lowercase forms appear).
/// Applied to BOTH the indexed corpus text and the query (see lexical.rs), so
/// the lexical path stays symmetric under either spelling. NOT applied to the
/// embedding path — bge-m3 is multilingual and handles umlauts natively.
fn fold_umlauts(s: &str) -> String {
    let mut out = String::with_capacity(s.len());
    for c in s.chars() {
        match c {
            'ä' => out.push_str("ae"),
            'ö' => out.push_str("oe"),
            'ü' => out.push_str("ue"),
            'ß' => out.push_str("ss"),
            _ => out.push(c),
        }
    }
    out
}

pub fn normalize(input: &str) -> String {
    let lower = fold_umlauts(&input.to_lowercase());
    let mut out: Vec<String> = Vec::new();
    for tok in lower.split_whitespace() {
        let replaced = ABBREV.iter()
            .find(|(p, _)| *p == tok)
            .map(|(_, r)| r.to_string())
            .unwrap_or_else(|| tok.to_string());
        out.push(replaced);
    }
    out.join(" ")
}