fix: honor ValidModifierClass subset; inherit usage type; harden ordering

- Fix 1: capture <ValidModifierClass> codes from <ModifiedBy all="false">
  and filter each modifier level to only valid codes before cartesian
  product; eliminates ~194 phantom codes (e.g. M07.01–03) while keeping
  valid ones (M07.00/04/07/09). Split Start/Empty XML event arms to
  correctly track children of <ModifiedBy>.
- Fix 2: synthesized para295/para301 inherit parent values; "V" is
  promoted to "P" (parent "V" = needs subdivision, terminal is codeable).
  Other types ("P", "O", "Z", "") pass through unchanged.
- Fix 3: debug_assert in ModifierClass handler guards against ClaML
  document-order assumption changing silently in debug/test builds.
- Fix 4: add expands_single_modifier_chain regression test verifying
  C88.00/C88.01 synthesis from a single all="true" ModifiedBy (corpus-
  verified: Alpha-ID I30531, I31044).
This commit is contained in:
2026-05-18 17:58:22 +02:00
parent 4ee705e57d
commit 944a4bef4f
2 changed files with 257 additions and 17 deletions
+36
View File
@@ -14,3 +14,39 @@ fn expands_diabetes_5th_digit_codes_as_billable() {
assert!(a010.description.contains("Typhus abdominalis"));
assert_eq!(map.get("E11").expect("E11 root").para295, "V");
}
/// Regression test: a category with a single `<ModifiedBy all="true">` expands
/// correctly into its terminal 5th-digit leaves.
///
/// `C88.0` (Makroglobulinämie Waldenström) has exactly one `<ModifiedBy
/// all="true" code="S02C88_5"/>` with two `<ModifierClass>` codes ("0" and
/// "1"), yielding `C88.00` and `C88.01`. Both codes appear in the
/// Alpha-ID corpus (`data/icd10gm2026_alphaidse_edvtxt_20250926.txt`).
///
/// The parent `C88.0` carries `Para295 = "P"` (already billable at the 4th
/// digit) and `Para301 = "V"`. The synthesized terminals therefore inherit
/// `para295 = "P"` (parent value, not "V") and `para301 = "P"` ("V" promoted).
#[test]
fn expands_single_modifier_chain() {
let map = claml::load("icd-claml/Klassifikationsdateien/icd10gm2026syst_claml_20250912.xml").unwrap();
// C88.00 verified in corpus (e.g. Alpha-ID I30531 "Makroglobulinämie Waldenström").
let c8800 = map.get("C88.00").expect("C88.00 synthesized from single ModifiedBy");
assert_eq!(c8800.para295, "P",
"para295 inherited from parent C88.0 (which is already P, not V)");
// Parent label + modifier label joined by " - ".
assert!(c8800.description.contains("Waldenström"),
"description must contain parent label: {:?}", c8800.description);
assert!(c8800.description.contains("Remission"),
"description must contain modifier label: {:?}", c8800.description);
// C88.01 verified in corpus (Alpha-ID I31044 "Makroglobulinämie in kompletter Remission").
let c8801 = map.get("C88.01").expect("C88.01 synthesized");
assert_eq!(c8801.para295, "P");
assert!(c8801.description.contains("kompletter Remission"),
"description must include modifier label: {:?}", c8801.description);
// The 4th-digit parent itself must still be present and unchanged.
let c880 = map.get("C88.0").expect("C88.0 explicit parent still present");
assert_eq!(c880.para295, "P", "explicit parent entry must not be overwritten");
}