feat: text normalization with medical abbreviation expansion

src/normalize.rs

@@ -1 +1,23 @@
-// implemented in a later task
+/// (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"),
+];
+
+pub fn normalize(input: &str) -> String {
+    let lower = 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(" ")
+}

tests/normalize_tests.rs

@@ -0,0 +1,17 @@
+use alpha_id::normalize::normalize;
+
+#[test]
+fn lowercases_and_collapses_whitespace() {
+    assert_eq!(normalize("  Diabetes   Mellitus\tTyp 2 "), "diabetes mellitus typ 2");
+}
+
+#[test]
+fn expands_common_medical_abbreviations() {
+    assert_eq!(normalize("V.a. art. Hypertonie"), "verdacht auf arterielle hypertonie");
+    assert_eq!(normalize("Z.n. OP"), "zustand nach operation");
+}
+
+#[test]
+fn keeps_german_umlauts() {
+    assert_eq!(normalize("Ödem"), "ödem");
+}