Compare commits
7 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| 79ad95e244 | |||
| a6f1020b2c | |||
| e50892a2aa | |||
| 9cfe6f83b1 | |||
| df7966656a | |||
| 05d75e8039 | |||
| e24a551ee4 |
@@ -211,6 +211,13 @@ func (h *IACEHandler) InitializeProject(c *gin.Context) {
|
|||||||
}
|
}
|
||||||
|
|
||||||
for _, cat := range mp.HazardCats {
|
for _, cat := range mp.HazardCats {
|
||||||
|
// Native cyber/AI categories (frontend groups I+J) belong to the
|
||||||
|
// CRA module, not the traditional CE (ISO 12100) hazard log.
|
||||||
|
// Enforced centrally here so it holds for EVERY project.
|
||||||
|
if isCyberSecurityCategory(cat) {
|
||||||
|
fmt.Printf("CYBER-SKIP: cat=%s pattern=%s — routed to CRA module\n", cat, mp.PatternID)
|
||||||
|
continue
|
||||||
|
}
|
||||||
maxForCat := categoryHazardCap(cat, len(comps))
|
maxForCat := categoryHazardCap(cat, len(comps))
|
||||||
if catCount[cat] >= maxForCat {
|
if catCount[cat] >= maxForCat {
|
||||||
continue
|
continue
|
||||||
|
|||||||
@@ -0,0 +1,45 @@
|
|||||||
|
package handlers
|
||||||
|
|
||||||
|
// Safety/Security separation for the IACE hazard log.
|
||||||
|
//
|
||||||
|
// The traditional CE risk assessment (Maschinenrichtlinie / EN ISO 12100) and
|
||||||
|
// the cybersecurity assessment (Cyber Resilience Act) are two distinct steps.
|
||||||
|
// IACE owns the traditional, physical + functional-safety hazards; the CRA
|
||||||
|
// module (/sdk/iace/{id}/cra) owns the native cyber/AI topics and re-examines
|
||||||
|
// which safety functions a cyber attack can re-open (see iace-safety-bridge).
|
||||||
|
//
|
||||||
|
// The split is by the NATURE of the hazard, not by the component: a control
|
||||||
|
// fault, bus failure or botched update is FUNCTIONAL safety (random/systematic
|
||||||
|
// fault) and stays in CE — independent of whether the controller is a bought-in
|
||||||
|
// CE-marked PLC or the manufacturer's own embedded control. Only the security
|
||||||
|
// PROPERTIES against malicious actors (access control, firmware/update
|
||||||
|
// integrity, SBOM, vulnerability handling, default passwords) are CRA.
|
||||||
|
//
|
||||||
|
// Functional-safety control categories (software_control, software_fault,
|
||||||
|
// safety_function_failure, configuration_error, communication_failure,
|
||||||
|
// update_failure, sensor_fault, …) therefore intentionally STAY in IACE — they
|
||||||
|
// are the safety functions whose loss the CRA bridge re-examines.
|
||||||
|
//
|
||||||
|
// Enforced centrally in InitializeProject so it holds for EVERY project.
|
||||||
|
var nativeCyberSecurityCategories = map[string]bool{
|
||||||
|
// I. Cyber / Netzwerk — security against malicious actors
|
||||||
|
"unauthorized_access": true,
|
||||||
|
"firmware_corruption": true,
|
||||||
|
"cyber_resilience": true,
|
||||||
|
"logging_audit_failure": true,
|
||||||
|
"cyber_network": true,
|
||||||
|
"sensor_spoofing": true,
|
||||||
|
// J. KI-spezifisch
|
||||||
|
"ai_specific": true,
|
||||||
|
"ai_misclassification": true,
|
||||||
|
"false_classification": true,
|
||||||
|
"model_drift": true,
|
||||||
|
"data_poisoning": true,
|
||||||
|
"unintended_bias": true,
|
||||||
|
}
|
||||||
|
|
||||||
|
// isCyberSecurityCategory reports whether a hazard category is a native cyber/AI
|
||||||
|
// topic that belongs to the CRA module rather than the traditional CE hazard log.
|
||||||
|
func isCyberSecurityCategory(category string) bool {
|
||||||
|
return nativeCyberSecurityCategories[category]
|
||||||
|
}
|
||||||
@@ -0,0 +1,37 @@
|
|||||||
|
package handlers
|
||||||
|
|
||||||
|
import "testing"
|
||||||
|
|
||||||
|
func TestIsCyberSecurityCategory_RoutedToCRA(t *testing.T) {
|
||||||
|
cyber := []string{
|
||||||
|
"unauthorized_access", "firmware_corruption", "cyber_resilience",
|
||||||
|
"logging_audit_failure", "cyber_network", "sensor_spoofing",
|
||||||
|
"ai_specific", "ai_misclassification", "false_classification",
|
||||||
|
"model_drift", "data_poisoning", "unintended_bias",
|
||||||
|
}
|
||||||
|
for _, c := range cyber {
|
||||||
|
if !isCyberSecurityCategory(c) {
|
||||||
|
t.Errorf("category %q must be routed to the CRA module, not the traditional IACE log", c)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
func TestIsCyberSecurityCategory_StaysInIACE(t *testing.T) {
|
||||||
|
// Physical + functional-safety categories must remain in the traditional CE
|
||||||
|
// hazard log. communication_failure (bus failure -> loss of control) and
|
||||||
|
// update_failure (botched update -> lost safety function) are FUNCTIONAL
|
||||||
|
// faults, not attacks, so they stay too.
|
||||||
|
keep := []string{
|
||||||
|
"mechanical_hazard", "electrical_hazard", "thermal_hazard",
|
||||||
|
"pneumatic_hydraulic", "noise_vibration", "ergonomic_hazard",
|
||||||
|
"material_environmental", "chemical_risk", "fire_explosion",
|
||||||
|
"software_control", "software_fault", "safety_function_failure",
|
||||||
|
"configuration_error", "sensor_fault", "hmi_error",
|
||||||
|
"communication_failure", "update_failure",
|
||||||
|
}
|
||||||
|
for _, c := range keep {
|
||||||
|
if isCyberSecurityCategory(c) {
|
||||||
|
t.Errorf("category %q must stay in the traditional IACE log, not be routed to CRA", c)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
@@ -0,0 +1,132 @@
|
|||||||
|
package iace
|
||||||
|
|
||||||
|
// GetWarewashingPatterns returns hazard patterns for commercial warewashing
|
||||||
|
// machines (gewerbliche Geschirrspuelmaschinen / Untertisch-, Hauben-, Korb-
|
||||||
|
// und Bandspuelmaschinen). These capture the machine-specific hazards a
|
||||||
|
// Fachmann immediately expects but that the generic library did not cover:
|
||||||
|
// hot-water/steam scalding on door opening, hot surfaces, hot ware, corrosive
|
||||||
|
// detergent/rinse-aid contact, door pinch and wet-floor slipping.
|
||||||
|
//
|
||||||
|
// Every pattern is gated by the capability tag "dom_warewashing" (emitted only
|
||||||
|
// by warewashing narrative keywords in keyword_dictionary.go), so none of these
|
||||||
|
// leak into unrelated machine classes.
|
||||||
|
//
|
||||||
|
// HP range: HP2200-HP2206. ISO 12100 Annex B section identifiers only (facts);
|
||||||
|
// product standard EN 60335-2-58 (commercial dishwashing machines).
|
||||||
|
func GetWarewashingPatterns() []HazardPattern {
|
||||||
|
return []HazardPattern{
|
||||||
|
{
|
||||||
|
ID: "HP2200", NameDE: "Verbruehung durch Heisswasser/Dampf beim Oeffnen der Tuer", NameEN: "Scalding by hot water/steam when opening the door",
|
||||||
|
RequiredComponentTags: []string{"dom_warewashing", "steam_emission"},
|
||||||
|
GeneratedHazardCats: []string{"thermal_hazard"},
|
||||||
|
SuggestedMeasureIDs: []string{"M2200", "M2201", "M2202", "M2208"},
|
||||||
|
Priority: 94,
|
||||||
|
ApplicableLifecycles: []string{"normal_operation", "cleaning"},
|
||||||
|
ScenarioDE: "Beim Oeffnen der Tuer waehrend oder unmittelbar nach dem Spuelgang tritt ein Schwall aus heissem Wasser und Wrasen (Dampf) aus der Spuelkammer aus und trifft Gesicht, Haende und Arme des Bedieners.",
|
||||||
|
TriggerDE: "Tuer wird vor Programmende oder bei noch vorhandenem Restdampf geoeffnet; Tuerverriegelung fehlt oder ist ueberbrueckt; Nachspueltemperatur ca. 85 Grad C.",
|
||||||
|
HarmDE: "Verbruehung 1.-2. Grades an Gesicht, Haenden und Unterarmen; Augenreizung durch heissen Dampf.",
|
||||||
|
AffectedDE: "Bedienpersonal (Spuelkraft)",
|
||||||
|
ZoneDE: "Tuer- und Beschickungsoeffnung der Spuelkammer",
|
||||||
|
ISO12100Section: "6.2.4",
|
||||||
|
DefaultSeverity: 3, DefaultExposure: 4,
|
||||||
|
},
|
||||||
|
{
|
||||||
|
ID: "HP2201", NameDE: "Verbrennung an heissen Oberflaechen (Boiler/Tank/Spuelkammer)", NameEN: "Burn on hot surfaces (boiler/tank/wash chamber)",
|
||||||
|
RequiredComponentTags: []string{"dom_warewashing", "high_temperature"},
|
||||||
|
GeneratedHazardCats: []string{"thermal_hazard"},
|
||||||
|
SuggestedMeasureIDs: []string{"M2202", "M055", "M2208"},
|
||||||
|
Priority: 90,
|
||||||
|
ApplicableLifecycles: []string{"cleaning", "maintenance"},
|
||||||
|
ScenarioDE: "Beruehrung heisser Oberflaechen von Boiler, Tankheizkoerper oder Spuelkammerwaenden bei Reinigung, Entkalkung oder Wartung fuehrt zu Kontaktverbrennungen.",
|
||||||
|
TriggerDE: "Reinigung/Entkalkung ohne Abkuehlzeit; Eingriff in die Spuelkammer bei betriebswarmem Geraet.",
|
||||||
|
HarmDE: "Kontaktverbrennung an Haenden und Unterarmen.",
|
||||||
|
AffectedDE: "Reinigungspersonal, Wartungspersonal",
|
||||||
|
ZoneDE: "Boiler, Tankheizkoerper, Spuelkammerwaende",
|
||||||
|
ISO12100Section: "6.2.4",
|
||||||
|
DefaultSeverity: 2, DefaultExposure: 3,
|
||||||
|
},
|
||||||
|
{
|
||||||
|
ID: "HP2202", NameDE: "Verbrennung an heissem Spuelgut beim Entladen", NameEN: "Burn on hot ware when unloading",
|
||||||
|
RequiredComponentTags: []string{"dom_warewashing", "hot_water"},
|
||||||
|
GeneratedHazardCats: []string{"thermal_hazard"},
|
||||||
|
SuggestedMeasureIDs: []string{"M2202", "M055", "M2208"},
|
||||||
|
Priority: 86,
|
||||||
|
ApplicableLifecycles: []string{"normal_operation"},
|
||||||
|
ScenarioDE: "Geschirr, Glaeser und Bestecke sind nach dem Spuelgang durch die Heisswasser-Nachspuelung sehr heiss; beim Entladen kommt es zu Verbrennungen.",
|
||||||
|
TriggerDE: "Sofortiges Entnehmen des Spuelguts nach Programmende ohne Abkuehl-/Trocknungszeit.",
|
||||||
|
HarmDE: "Verbrennung an Haenden/Fingern beim Greifen heisser Teile.",
|
||||||
|
AffectedDE: "Bedienpersonal (Spuelkraft)",
|
||||||
|
ZoneDE: "Spuelkammer, Entnahmebereich/Korb",
|
||||||
|
ISO12100Section: "6.2.4",
|
||||||
|
DefaultSeverity: 2, DefaultExposure: 3,
|
||||||
|
},
|
||||||
|
{
|
||||||
|
ID: "HP2203", NameDE: "Chemische Veraetzung (Haut/Augen) durch Reiniger-/Klarspueler-Konzentrat", NameEN: "Chemical burn (skin/eyes) from detergent/rinse-aid concentrate",
|
||||||
|
RequiredComponentTags: []string{"dom_warewashing", "corrosive_chemical"},
|
||||||
|
GeneratedHazardCats: []string{"chemical_risk"},
|
||||||
|
SuggestedMeasureIDs: []string{"M2203", "M2204", "M2208"},
|
||||||
|
Priority: 92,
|
||||||
|
ApplicableLifecycles: []string{"normal_operation", "maintenance"},
|
||||||
|
ScenarioDE: "Direkter Kontakt mit dem aetzenden (alkalischen) Reiniger- bzw. Klarspueler-Konzentrat beim Nachfuellen, Sauglanzenwechsel oder bei Leckage fuehrt zu Veraetzungen von Haut und Augen.",
|
||||||
|
TriggerDE: "Gebinde-/Sauglanzenwechsel ohne Schutzausruestung; Umfuellen von Konzentrat; undichte Dosierleitung.",
|
||||||
|
HarmDE: "Veraetzung von Haut und Augen (alkalische Verletzung), bleibende Augenschaeden moeglich.",
|
||||||
|
AffectedDE: "Bedienpersonal, Reinigungspersonal beim Chemikalien-Handling",
|
||||||
|
ZoneDE: "Dosiergeraet, Reiniger-/Klarspueler-Gebinde, Sauglanzen",
|
||||||
|
ISO12100Section: "6.2.4",
|
||||||
|
DefaultSeverity: 3, DefaultExposure: 3,
|
||||||
|
ClarificationQuestionsDE: []string{
|
||||||
|
"Liegt fuer alle eingesetzten Reiniger/Klarspueler/Entkalker ein aktuelles Sicherheitsdatenblatt (SDB) am Geraet vor?",
|
||||||
|
"Ist ein geschlossenes Dosiersystem mit Sauglanzen vorhanden, sodass kein Umfuellen noetig ist?",
|
||||||
|
},
|
||||||
|
},
|
||||||
|
{
|
||||||
|
ID: "HP2204", NameDE: "Reizung/Veraetzung der Atemwege durch Reinigungs-Aerosole/Daempfe", NameEN: "Respiratory irritation from cleaning aerosols/vapours",
|
||||||
|
RequiredComponentTags: []string{"dom_warewashing", "corrosive_chemical"},
|
||||||
|
GeneratedHazardCats: []string{"chemical_risk"},
|
||||||
|
SuggestedMeasureIDs: []string{"M2205", "M2203", "M2204"},
|
||||||
|
Priority: 82,
|
||||||
|
ApplicableLifecycles: []string{"normal_operation", "maintenance"},
|
||||||
|
ScenarioDE: "Aerosole und Daempfe der Reinigungschemie (insbesondere beim Oeffnen kurz nach dem Spuelgang oder bei der Entkalkung mit Saeure) gelangen in die Atemzone und reizen Atemwege und Schleimhaeute.",
|
||||||
|
TriggerDE: "Oeffnen bei laufender/heisser Chemie; Entkalkung mit Saeure; unzureichende Lueftung des Aufstellbereichs.",
|
||||||
|
HarmDE: "Reizung von Atemwegen, Augen und Schleimhaeuten; bei Saeure-/Laugen-Vermischung gefaehrliche Gase.",
|
||||||
|
AffectedDE: "Bedienpersonal, Reinigungspersonal",
|
||||||
|
ZoneDE: "Atemzone vor der Spuelkammer, Aufstellbereich",
|
||||||
|
ISO12100Section: "6.2.4",
|
||||||
|
DefaultSeverity: 2, DefaultExposure: 2,
|
||||||
|
ClarificationQuestionsDE: []string{
|
||||||
|
"Ist der Aufstellbereich ausreichend be-/entlueftet (Kuechenlueftung)?",
|
||||||
|
"Wird in der BA vor dem Vermischen von Reiniger und Entkalker/Saeure gewarnt?",
|
||||||
|
},
|
||||||
|
},
|
||||||
|
{
|
||||||
|
ID: "HP2205", NameDE: "Quetschen der Finger an der Tuer/Haube", NameEN: "Finger crushing at the door/hood",
|
||||||
|
RequiredComponentTags: []string{"dom_warewashing", "access_door"},
|
||||||
|
GeneratedHazardCats: []string{"mechanical_hazard"},
|
||||||
|
SuggestedMeasureIDs: []string{"M2206", "M003", "M2208"},
|
||||||
|
Priority: 78,
|
||||||
|
ApplicableLifecycles: []string{"normal_operation"},
|
||||||
|
ScenarioDE: "Beim Schliessen der Tuer bzw. Absenken der Haube werden Finger zwischen Tuer/Haube und Gehaeuse gequetscht.",
|
||||||
|
TriggerDE: "Greifen in den Schliessbereich beim Schliessen; hohe Schliesskraft der Haube; scharfe Kanten.",
|
||||||
|
HarmDE: "Quetschung und Prellung der Finger.",
|
||||||
|
AffectedDE: "Bedienpersonal (Spuelkraft)",
|
||||||
|
ZoneDE: "Tuer-/Haubenkante, Schliessbereich",
|
||||||
|
ISO12100Section: "6.2.3",
|
||||||
|
DefaultSeverity: 1, DefaultExposure: 3,
|
||||||
|
},
|
||||||
|
{
|
||||||
|
ID: "HP2206", NameDE: "Ausrutschen auf nassem Boden (Wasseraustritt/Leckage)", NameEN: "Slipping on wet floor (water leakage)",
|
||||||
|
RequiredComponentTags: []string{"dom_warewashing"},
|
||||||
|
GeneratedHazardCats: []string{"mechanical_hazard"},
|
||||||
|
SuggestedMeasureIDs: []string{"M2207", "M538", "M2208"},
|
||||||
|
Priority: 76,
|
||||||
|
ApplicableLifecycles: []string{"normal_operation", "cleaning", "maintenance"},
|
||||||
|
ScenarioDE: "Aus der Spuelmaschine austretendes Wasser (Beschickung, Tuer oeffnen, Leckage, Tankwasserwechsel) macht den Boden im Aufstellbereich rutschig; der Bediener rutscht aus.",
|
||||||
|
TriggerDE: "Wasseraustritt beim Oeffnen/Beschicken; undichter Ablauf; fehlender Bodenablauf.",
|
||||||
|
HarmDE: "Sturz mit Prellungen, Knochenbruechen oder Kopfaufprall.",
|
||||||
|
AffectedDE: "Bedienpersonal, Reinigungspersonal",
|
||||||
|
ZoneDE: "Aufstell- und Bedienbereich der Spuelmaschine",
|
||||||
|
ISO12100Section: "6.3.5.6",
|
||||||
|
DefaultSeverity: 2, DefaultExposure: 3,
|
||||||
|
},
|
||||||
|
}
|
||||||
|
}
|
||||||
@@ -0,0 +1,112 @@
|
|||||||
|
package iace
|
||||||
|
|
||||||
|
import "testing"
|
||||||
|
|
||||||
|
// firedSet runs the engine for the given custom tags and returns the set of
|
||||||
|
// fired pattern IDs.
|
||||||
|
func firedSet(customTags []string) map[string]bool {
|
||||||
|
engine := NewPatternEngine()
|
||||||
|
out := engine.Match(MatchInput{CustomTags: customTags})
|
||||||
|
fired := make(map[string]bool, len(out.MatchedPatterns))
|
||||||
|
for _, m := range out.MatchedPatterns {
|
||||||
|
fired[m.PatternID] = true
|
||||||
|
}
|
||||||
|
return fired
|
||||||
|
}
|
||||||
|
|
||||||
|
// A warewashing narrative emits these capability + functional tags.
|
||||||
|
var warewashingTags = []string{
|
||||||
|
"dom_warewashing", "steam_emission", "hot_water", "high_temperature",
|
||||||
|
"corrosive_chemical", "access_door", "rotating_part",
|
||||||
|
}
|
||||||
|
|
||||||
|
func TestWarewashing_PatternsFireForDishwasher(t *testing.T) {
|
||||||
|
fired := firedSet(warewashingTags)
|
||||||
|
want := []string{"HP2200", "HP2201", "HP2202", "HP2203", "HP2204", "HP2205", "HP2206"}
|
||||||
|
for _, id := range want {
|
||||||
|
if !fired[id] {
|
||||||
|
t.Errorf("expected warewashing pattern %s to fire for a dishwasher, but it did not", id)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
func TestWarewashing_PatternsDoNotLeakIntoOtherMachines(t *testing.T) {
|
||||||
|
// A machine with thermal + electrical + chemical capability but NOT a
|
||||||
|
// dishwasher must never produce warewashing hazards (dom_warewashing gate).
|
||||||
|
fired := firedSet([]string{"high_temperature", "electrical_part", "chemical_risk", "rotating_part", "moving_part"})
|
||||||
|
for _, id := range []string{"HP2200", "HP2201", "HP2202", "HP2203", "HP2204", "HP2205", "HP2206"} {
|
||||||
|
if fired[id] {
|
||||||
|
t.Errorf("warewashing pattern %s leaked into a non-dishwasher machine", id)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
func TestWarewashing_WeldingAndGlueDoNotLeakIntoDishwasher(t *testing.T) {
|
||||||
|
// The gate-term additions must stop the welding/flame/glue burn patterns
|
||||||
|
// from firing for a dishwasher (they previously leaked via high_temperature
|
||||||
|
// / electrical_part). dom_welding/dom_flame/dom_glue are absent here.
|
||||||
|
fired := firedSet(warewashingTags)
|
||||||
|
leak := map[string]string{
|
||||||
|
"HP530": "Lichtbogen-Verbrennung (Schweissen)",
|
||||||
|
"HP532": "Schweissrauch",
|
||||||
|
"HP533": "Brand durch Schweissfunken (Schweissen)",
|
||||||
|
}
|
||||||
|
for id, name := range leak {
|
||||||
|
if fired[id] {
|
||||||
|
t.Errorf("cross-domain pattern %s (%s) leaked into a dishwasher", id, name)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
func TestWarewashing_MeasureIDsExist(t *testing.T) {
|
||||||
|
lib := GetProtectiveMeasureLibrary()
|
||||||
|
have := make(map[string]bool, len(lib))
|
||||||
|
for _, m := range lib {
|
||||||
|
have[m.ID] = true
|
||||||
|
}
|
||||||
|
for _, p := range GetWarewashingPatterns() {
|
||||||
|
for _, mid := range p.SuggestedMeasureIDs {
|
||||||
|
if !have[mid] {
|
||||||
|
t.Errorf("pattern %s references measure %s which is not in the library", p.ID, mid)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
func TestWarewashing_NarrativeEmitsTags(t *testing.T) {
|
||||||
|
// Closes the loop: a realistic dishwasher description must emit the tags
|
||||||
|
// the warewashing patterns gate on (otherwise the patterns are dead).
|
||||||
|
narrative := "Gewerbliche Untertisch-Geschirrspuelmaschine mit Heisswasser-Boiler " +
|
||||||
|
"und Nachspuelung ca. 85 Grad C, Spuelpumpe mit rotierenden Spuelfeldern, " +
|
||||||
|
"Dampf-/Wrasenabgabe beim Oeffnen, Reiniger und Klarspueler ueber Dosiergeraet, " +
|
||||||
|
"Tuer mit Sicherheitsschalter, Eingreifen in die Spuelkammer."
|
||||||
|
res := ParseNarrative(narrative, "Gewerbliche Geschirrspuelmaschine")
|
||||||
|
got := make(map[string]bool, len(res.CustomTags))
|
||||||
|
for _, tag := range res.CustomTags {
|
||||||
|
got[tag] = true
|
||||||
|
}
|
||||||
|
for _, want := range []string{"dom_warewashing", "steam_emission", "hot_water", "corrosive_chemical", "access_door", "rotating_part"} {
|
||||||
|
if !got[want] {
|
||||||
|
t.Errorf("narrative did not emit expected tag %q (got %v)", want, res.CustomTags)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
// And it must NOT emit any welding/flame/glue domain that would re-open leaks.
|
||||||
|
for _, bad := range []string{"dom_welding", "dom_flame", "dom_glue"} {
|
||||||
|
if got[bad] {
|
||||||
|
t.Errorf("dishwasher narrative unexpectedly emitted cross-domain tag %q", bad)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
func TestWarewashing_NewMeasuresPresent(t *testing.T) {
|
||||||
|
lib := GetProtectiveMeasureLibrary()
|
||||||
|
have := make(map[string]bool, len(lib))
|
||||||
|
for _, m := range lib {
|
||||||
|
have[m.ID] = true
|
||||||
|
}
|
||||||
|
for _, mid := range []string{"M2200", "M2201", "M2202", "M2203", "M2204", "M2205", "M2206", "M2207", "M2208"} {
|
||||||
|
if !have[mid] {
|
||||||
|
t.Errorf("expected warewashing measure %s to be registered in the library", mid)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
@@ -88,6 +88,21 @@ func GetKeywordDictionary() []KeywordEntry {
|
|||||||
{Keywords: []string{"folienwickler", "wickelmaschine", "konfektioniermaschine", "folienverpackung", "wellpappe"}, ExtraTags: []string{"dom_converting"}},
|
{Keywords: []string{"folienwickler", "wickelmaschine", "konfektioniermaschine", "folienverpackung", "wellpappe"}, ExtraTags: []string{"dom_converting"}},
|
||||||
{Keywords: []string{"bergbau", "untertage", "tunnelbau", "off-grid"}, ExtraTags: []string{"dom_remote"}},
|
{Keywords: []string{"bergbau", "untertage", "tunnelbau", "off-grid"}, ExtraTags: []string{"dom_remote"}},
|
||||||
{Keywords: []string{"asbest", "asbestsanierung", "asbestexposition"}, ExtraTags: []string{"dom_asbestos"}},
|
{Keywords: []string{"asbest", "asbestsanierung", "asbestexposition"}, ExtraTags: []string{"dom_asbestos"}},
|
||||||
|
{Keywords: []string{"gasbrenner", "brennerbetrieb", "offene flamme", "flammhaert", "abflammen", "flammrichten"}, ExtraTags: []string{"dom_flame"}},
|
||||||
|
{Keywords: []string{"heissleim", "heissleimanlage", "schmelzkleber", "schmelzklebstoff", "klebstoffschmelzer", "leimwerk"}, ExtraTags: []string{"dom_glue"}},
|
||||||
|
|
||||||
|
// ── Gewerbliche Spuelmaschine / Warewashing ──────────────────────
|
||||||
|
// dom_warewashing gates the warewashing-specific patterns
|
||||||
|
// (hazard_patterns_warewashing.go) so they never leak into other
|
||||||
|
// machine classes. The functional tags (hot_water, steam_emission,
|
||||||
|
// corrosive_chemical, access_door) are the within-domain triggers.
|
||||||
|
{Keywords: []string{"spuelmaschine", "geschirrspuelmaschine", "geschirrspueler", "haubenspuelmaschine", "untertischspuelmaschine", "korbspuelmaschine", "bandspuelmaschine", "glaeserspuelmaschine", "bistrospuelmaschine", "warewashing", "dishwasher"}, ExtraTags: []string{"dom_warewashing"}},
|
||||||
|
{Keywords: []string{"heisswasser", "nachspuelung", "nachspueltemperatur", "spuelgang", "spuelzyklus", "thermostopp", "thermostop"}, ExtraTags: []string{"hot_water", "high_temperature"}},
|
||||||
|
{Keywords: []string{"dampf", "wrasen", "schwaden", "brueden"}, ExtraTags: []string{"steam_emission", "high_temperature"}},
|
||||||
|
{Keywords: []string{"boiler", "spuelboiler", "nachspuelboiler", "tankheiz", "boilerheiz"}, ComponentIDs: []string{"C094"}, ExtraTags: []string{"heating_element", "high_temperature"}},
|
||||||
|
{Keywords: []string{"reiniger", "klarspueler", "spuelmittel", "reinigungsmittel", "reinigerkonzentrat", "spuelchemie", "dosiergeraet", "dosierpumpe", "sauglanze", "entkalker"}, ExtraTags: []string{"corrosive_chemical"}},
|
||||||
|
{Keywords: []string{"spuelarm", "spuelfeld", "wascharm", "spruehfeld"}, ComponentIDs: []string{"C004"}, ExtraTags: []string{"rotating_part"}},
|
||||||
|
{Keywords: []string{"spuelkammer", "spueltuer", "geraetetuer", "haubentuer", "klapptuer"}, ExtraTags: []string{"access_door"}},
|
||||||
// Ghost-Closure (Emit-Seite): macht die 34 toten Required-Tags
|
// Ghost-Closure (Emit-Seite): macht die 34 toten Required-Tags
|
||||||
// emittierbar, jeweils NUR via domaenenspezifische Keywords -> die 120
|
// emittierbar, jeweils NUR via domaenenspezifische Keywords -> die 120
|
||||||
// Ghost-Patterns feuern wieder, aber nur fuer ihre echte Maschine (kein
|
// Ghost-Patterns feuern wieder, aber nur fuer ihre echte Maschine (kein
|
||||||
|
|||||||
@@ -22,6 +22,7 @@ func GetProtectiveMeasureLibrary() []ProtectiveMeasureEntry {
|
|||||||
all = append(all, getGTBremseMeasures()...) // GT-Bremse-Coverage-Gaps (M483-M522)
|
all = append(all, getGTBremseMeasures()...) // GT-Bremse-Coverage-Gaps (M483-M522)
|
||||||
all = append(all, GetCRAMeasures()...) // CRA / DIN EN 40000-1-2 cyber-resilience (M540-M548)
|
all = append(all, GetCRAMeasures()...) // CRA / DIN EN 40000-1-2 cyber-resilience (M540-M548)
|
||||||
all = append(all, getLiftEndstopMeasures()...) // Lift/hoist endstop (M600-M604) — bridges OSHA MD library
|
all = append(all, getLiftEndstopMeasures()...) // Lift/hoist endstop (M600-M604) — bridges OSHA MD library
|
||||||
|
all = append(all, getWarewashingMeasures()...) // Commercial dishwasher (M2200-M2208) — scald/chemical/door/slip
|
||||||
return all
|
return all
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|||||||
@@ -0,0 +1,69 @@
|
|||||||
|
package iace
|
||||||
|
|
||||||
|
// getWarewashingMeasures returns protective measures for commercial warewashing
|
||||||
|
// machines (gewerbliche Geschirrspuelmaschinen): hot-water/steam scalding,
|
||||||
|
// hot surfaces, corrosive cleaning chemicals, door pinch and wet-floor slip.
|
||||||
|
// They complement the generic thermal/mechanical/material measures with the
|
||||||
|
// machine-specific controls a Fachmann expects for this product class.
|
||||||
|
//
|
||||||
|
// M-ID range: M2200-M2208. Norm identifiers only (facts) — no norm text is
|
||||||
|
// reproduced (DIN/Beuth license). Lead standard: EN 60335-2-58 (safety of
|
||||||
|
// commercial electric dishwashing machines).
|
||||||
|
func getWarewashingMeasures() []ProtectiveMeasureEntry {
|
||||||
|
return []ProtectiveMeasureEntry{
|
||||||
|
{ID: "M2200", ReductionType: "design", SubType: "interlock",
|
||||||
|
Name: "Tuer-/Haubenverriegelung beendet Spuelgang vor dem Oeffnen",
|
||||||
|
Description: "Die Tuer bzw. Haube ist so mit der Steuerung verriegelt, dass beim Oeffnen Spuelpumpe und Nachspuelung sofort abschalten und ein Oeffnen erst nach Programmende (bzw. nach Abbau des Restdampfs) freigegeben wird. Verhindert den Schwall aus Heisswasser/Wrasen und den Kontakt mit noch rotierenden Spuelfeldern.",
|
||||||
|
HazardCategory: "thermal",
|
||||||
|
Examples: []string{"Tuerkontaktschalter schaltet Pumpe + Heizung beim Oeffnen ab", "Rastposition mit Restdampf-Verzoegerung vor Freigabe"},
|
||||||
|
NormReferences: []string{"EN 60335-2-58", "EN ISO 12100 — Inhaerent sichere Konstruktion"}},
|
||||||
|
{ID: "M2201", ReductionType: "design", SubType: "thermal",
|
||||||
|
Name: "Wrasen-/Dampfreduzierung (Kondensations- / Waermerueckgewinnungssystem)",
|
||||||
|
Description: "Der beim Oeffnen austretende Wrasen wird durch ein Kondensations- bzw. Waermerueckgewinnungssystem reduziert, sodass beim Entnehmen kein gefaehrlicher Dampfschwall entsteht. Senkt zugleich die Restwaerme- und Feuchtebelastung am Arbeitsplatz.",
|
||||||
|
HazardCategory: "thermal",
|
||||||
|
Examples: []string{"Umluft-Waermerueckgewinnung reduziert austretenden Wrasen", "Kondensationshaube ueber der Spuelkammer"},
|
||||||
|
NormReferences: []string{"EN 60335-2-58"}},
|
||||||
|
{ID: "M2202", ReductionType: "protection", SubType: "monitoring",
|
||||||
|
Name: "Thermostop / Temperaturueberwachung von Boiler und Tank",
|
||||||
|
Description: "Boiler- und Tanktemperatur werden ueberwacht; ein Thermostop gibt den naechsten Schritt erst frei, wenn die Solltemperatur erreicht ist, und begrenzt die maximale Nachspueltemperatur. Schuetzt vor Verbruehung durch unkontrolliert heisses Nachspuelwasser.",
|
||||||
|
HazardCategory: "thermal",
|
||||||
|
Examples: []string{"Temperatursensor in Boiler und Tank mit Abschaltgrenze", "Thermostop-Funktion im Spuelprogramm"},
|
||||||
|
NormReferences: []string{"EN 60335-2-58", "EN ISO 13732-1"}},
|
||||||
|
{ID: "M2203", ReductionType: "design", SubType: "containment",
|
||||||
|
Name: "Geschlossenes Dosiersystem mit Sauglanzen und Niveauueberwachung",
|
||||||
|
Description: "Reiniger und Klarspueler werden ausschliesslich ueber ein geschlossenes Dosiersystem mit Sauglanzen aus dem Originalgebinde gefoerdert (Niveau-Ueberwachung statt Umfuellen). Direkter Haut-/Augenkontakt mit dem aetzenden Konzentrat beim Nachfuellen wird konstruktiv vermieden.",
|
||||||
|
HazardCategory: "material_environmental",
|
||||||
|
Examples: []string{"Sauglanze mit Leermeldung im Reiniger-Kanister", "Kein Umfuellen — Gebindewechsel ohne offenen Chemiekontakt"},
|
||||||
|
NormReferences: []string{"EN 60335-2-58", "Verordnung (EG) Nr. 1272/2008 (CLP/GHS)"}},
|
||||||
|
{ID: "M2204", ReductionType: "information", SubType: "ppe",
|
||||||
|
Name: "PSA (Augen-/Hautschutz) + GHS-Kennzeichnung und Sicherheitsdatenblatt",
|
||||||
|
Description: "Fuer Handhabung, Gebindewechsel und Entkalkung werden Augen- und Handschutz vorgeschrieben; Reiniger/Klarspueler/Entkalker sind GHS-gekennzeichnet und das Sicherheitsdatenblatt liegt am Geraet vor. Stellt die sichere Handhabung der aetzenden Konzentrate sicher.",
|
||||||
|
HazardCategory: "material_environmental",
|
||||||
|
Examples: []string{"Schutzbrille + chemikalienbestaendige Handschuhe bei Gebindewechsel", "GHS-Etikett und SDB im Chemikalienschrank am Geraet"},
|
||||||
|
NormReferences: []string{"Verordnung (EG) Nr. 1272/2008 (CLP/GHS)", "TRGS 500"}},
|
||||||
|
{ID: "M2205", ReductionType: "protection", SubType: "ventilation",
|
||||||
|
Name: "Be-/Entlueftung bzw. geschlossene Haube gegen Chemie-Aerosole und Wrasen",
|
||||||
|
Description: "Der Aufstellbereich ist ausreichend be- und entlueftet bzw. die Spuelkammer bleibt waehrend des Programms geschlossen, sodass Reinigungs-Aerosole und heisser Wrasen nicht in die Atemzone des Bedieners gelangen.",
|
||||||
|
HazardCategory: "material_environmental",
|
||||||
|
Examples: []string{"Kuechenlueftung ueber dem Spuelbereich", "Programmstart nur bei geschlossener Haube"},
|
||||||
|
NormReferences: []string{"EN 60335-2-58", "TRGS 500"}},
|
||||||
|
{ID: "M2206", ReductionType: "design", SubType: "geometry",
|
||||||
|
Name: "Tuerkanten mit geringer Schliesskraft / Einklemmschutz",
|
||||||
|
Description: "Die Tuer-/Haubenmechanik ist so gestaltet (gefuehrte Bewegung, begrenzte Schliesskraft, abgerundete Kanten), dass beim Schliessen keine Finger gequetscht werden.",
|
||||||
|
HazardCategory: "mechanical",
|
||||||
|
Examples: []string{"Gefuehrte Haube mit gedaempfter Schliessbewegung", "Abgerundete Tuerkanten ohne Quetschspalt"},
|
||||||
|
NormReferences: []string{"EN 60335-2-58", "EN ISO 12100 — Geometrie und Anordnung"}},
|
||||||
|
{ID: "M2207", ReductionType: "design", SubType: "environment",
|
||||||
|
Name: "Rutschhemmender Bodenbelag + Ablauf/Leckagewanne im Aufstellbereich",
|
||||||
|
Description: "Im Aufstell- und Bedienbereich der Spuelmaschine sorgen rutschhemmender Bodenbelag und ein definierter Ablauf bzw. eine Leckagewanne dafuer, dass austretendes Wasser nicht zur Sturzgefahr wird.",
|
||||||
|
HazardCategory: "mechanical",
|
||||||
|
Examples: []string{"Rutschhemmender Industrieboden (Bewertungsgruppe R11/R12)", "Bodenablauf bzw. Leckagewanne unter dem Geraet"},
|
||||||
|
NormReferences: []string{"ASR A1.5/1,2", "DGUV Regel 108-003"}},
|
||||||
|
{ID: "M2208", ReductionType: "information", SubType: "signage",
|
||||||
|
Name: "Warnhinweis heisser Dampf/Heisswasser — Tuer erst nach Programmende oeffnen",
|
||||||
|
Description: "Am Geraet und in der Betriebsanleitung wird vor heissem Dampf und Heisswasser gewarnt und das Oeffnen der Tuer erst nach Programmende mit vorsichtigem Anheben vorgeschrieben. Sprachneutrale Piktogramme ergaenzen den Hinweis.",
|
||||||
|
HazardCategory: "general",
|
||||||
|
Examples: []string{"Warnpiktogramm 'Heisser Dampf' an der Tuer", "BA-Hinweis 'Tuer nach Programmende langsam oeffnen'"},
|
||||||
|
NormReferences: []string{"ISO 7010", "EN 60335-2-58"}},
|
||||||
|
}
|
||||||
|
}
|
||||||
@@ -46,6 +46,20 @@ var domainGateTerms = map[string]string{
|
|||||||
"widerstandsschweiss": "dom_welding", "lichtbogenschweiss": "dom_welding",
|
"widerstandsschweiss": "dom_welding", "lichtbogenschweiss": "dom_welding",
|
||||||
"schutzgasschweiss": "dom_welding", "punktschweiss": "dom_welding",
|
"schutzgasschweiss": "dom_welding", "punktschweiss": "dom_welding",
|
||||||
"schweisselektrod": "dom_welding", "elektrodenspalt": "dom_welding",
|
"schweisselektrod": "dom_welding", "elektrodenspalt": "dom_welding",
|
||||||
|
// Schweissen — Oberflaechenformen die bisher ungegatet leakten (z.B. in
|
||||||
|
// thermische Hazards einer Spuelmaschine ueber high_temperature/electrical_part)
|
||||||
|
"schweissarbeitsplatz": "dom_welding", "schweissfunke": "dom_welding",
|
||||||
|
"schweisshelm": "dom_welding", "schweisserschutz": "dom_welding",
|
||||||
|
"lichtbogenzone": "dom_welding", "lichtbogen-verbrennung": "dom_welding",
|
||||||
|
"schweissrauch": "dom_welding", "schweissgeraet": "dom_welding",
|
||||||
|
"schweisszone": "dom_welding", "schweissbrenner": "dom_welding",
|
||||||
|
"schweissspritzer": "dom_welding", "schweissstrom": "dom_welding",
|
||||||
|
// Offene Flamme / Brenner (Gasbrenner, Flammhaerten, Abflammen)
|
||||||
|
"offene flamme": "dom_flame", "brennerbereich": "dom_flame",
|
||||||
|
"flammenzone": "dom_flame", "gasbrenner": "dom_flame",
|
||||||
|
// Heissleim / Schmelzkleber
|
||||||
|
"heissleimanlage": "dom_glue", "klebstoffschmelzer": "dom_glue",
|
||||||
|
"heisskleber": "dom_glue", "schmelzkleber": "dom_glue",
|
||||||
// Solar / PV
|
// Solar / PV
|
||||||
"pv-modul": "dom_solar", "photovoltaik": "dom_solar", "pv-anlage": "dom_solar",
|
"pv-modul": "dom_solar", "photovoltaik": "dom_solar", "pv-anlage": "dom_solar",
|
||||||
"dc-steckverbindung": "dom_solar", "solarmodul": "dom_solar",
|
"dc-steckverbindung": "dom_solar", "solarmodul": "dom_solar",
|
||||||
|
|||||||
@@ -44,6 +44,7 @@ func collectAllPatterns() []HazardPattern {
|
|||||||
patterns = append(patterns, GetCRAPatterns()...) // HP1910-HP1918 CRA / DIN EN 40000-1-2 cyber-resilience spur
|
patterns = append(patterns, GetCRAPatterns()...) // HP1910-HP1918 CRA / DIN EN 40000-1-2 cyber-resilience spur
|
||||||
patterns = append(patterns, GetSecondaryHarmDemoPatterns()...) // HP2000-HP2001 secondary harm chain demos (Cola splitter, Pharma)
|
patterns = append(patterns, GetSecondaryHarmDemoPatterns()...) // HP2000-HP2001 secondary harm chain demos (Cola splitter, Pharma)
|
||||||
patterns = append(patterns, GetLiftEndstopPatterns()...) // HP2100-HP2102 lift body-part crush at endstops
|
patterns = append(patterns, GetLiftEndstopPatterns()...) // HP2100-HP2102 lift body-part crush at endstops
|
||||||
|
patterns = append(patterns, GetWarewashingPatterns()...) // HP2200-HP2206 commercial dishwasher (scald/chemical/door/slip)
|
||||||
patterns = applyMachineTypeOverrides(patterns) // Fill MachineTypes on legacy patterns to prevent drift
|
patterns = applyMachineTypeOverrides(patterns) // Fill MachineTypes on legacy patterns to prevent drift
|
||||||
patterns = applyDomainGates(patterns) // Capability-domain gate: stop domain-specific patterns leaking cross-machine
|
patterns = applyDomainGates(patterns) // Capability-domain gate: stop domain-specific patterns leaking cross-machine
|
||||||
return patterns
|
return patterns
|
||||||
|
|||||||
@@ -9,8 +9,8 @@ import (
|
|||||||
// authorityInfo is the normative classification of a search result, used internally
|
// authorityInfo is the normative classification of a search result, used internally
|
||||||
// for re-ranking only (Phase 1 changes ordering, not the response contract).
|
// for re-ranking only (Phase 1 changes ordering, not the response contract).
|
||||||
type authorityInfo struct {
|
type authorityInfo struct {
|
||||||
weight int // 100 binding_law, 70 guidance, 0 foreign_law, 50 unknown
|
weight int // 100 binding, 80 technical_standard, 70 guidance, 0 foreign, 50 unknown
|
||||||
sourceClass string // binding_law | supervisory_guidance | foreign_law | unknown
|
sourceClass string // binding_law | technical_standard | supervisory_guidance | foreign_law | unknown
|
||||||
jurisdiction string // DE | EU | CH
|
jurisdiction string // DE | EU | CH
|
||||||
}
|
}
|
||||||
|
|
||||||
@@ -18,7 +18,13 @@ var (
|
|||||||
guidanceMarkers = []string{
|
guidanceMarkers = []string{
|
||||||
"DSK", "EDPB", "BfDI", "BFDI", "BayLfD", "Baylfb", "ENISA", "BSI", "EUCC",
|
"DSK", "EDPB", "BfDI", "BFDI", "BayLfD", "Baylfb", "ENISA", "BSI", "EUCC",
|
||||||
"Standards Mapping", "Kpnr", "Orientierungshilfe", "Handreichung", "Beschluss",
|
"Standards Mapping", "Kpnr", "Orientierungshilfe", "Handreichung", "Beschluss",
|
||||||
"Leitlinie", "Guidance", "Empfehlung", "NIST", "OECD", "CISA", "Blue Guide",
|
"Leitlinie", "Guidance", "Empfehlung", "OECD", "CISA", "Blue Guide",
|
||||||
|
}
|
||||||
|
// Technical standards / control frameworks (best-practice controls). Checked BEFORE
|
||||||
|
// guidanceMarkers so a "BSI Grundschutz" chunk classifies as a standard, not BSI guidance.
|
||||||
|
standardMarkers = []string{
|
||||||
|
"NIST", "OWASP", "Grundschutz", "ISO 27001", "ISO/IEC 27001",
|
||||||
|
"CSA CCM", "Cloud Controls Matrix", "CIS Benchmark", "CIS Control",
|
||||||
}
|
}
|
||||||
foreignMarkers = []string{"RevDSG", "fedlex", "(CH)"}
|
foreignMarkers = []string{"RevDSG", "fedlex", "(CH)"}
|
||||||
deMarkers = []string{"BDSG", "DSK", "BfDI", "BFDI", "BayLfD", "Baylfb", "BSI"}
|
deMarkers = []string{"BDSG", "DSK", "BfDI", "BFDI", "BayLfD", "Baylfb", "BSI"}
|
||||||
@@ -48,6 +54,8 @@ func classifyAuthority(r LegalSearchResult) authorityInfo {
|
|||||||
switch {
|
switch {
|
||||||
case containsAny(hay, foreignMarkers):
|
case containsAny(hay, foreignMarkers):
|
||||||
return authorityInfo{weight: 0, sourceClass: "foreign_law", jurisdiction: "CH"}
|
return authorityInfo{weight: 0, sourceClass: "foreign_law", jurisdiction: "CH"}
|
||||||
|
case r.Category == "standard" || containsAny(hay, standardMarkers):
|
||||||
|
return authorityInfo{weight: 80, sourceClass: "technical_standard", jurisdiction: jur}
|
||||||
case r.Category == "guidance" || containsAny(hay, guidanceMarkers):
|
case r.Category == "guidance" || containsAny(hay, guidanceMarkers):
|
||||||
return authorityInfo{weight: 70, sourceClass: "supervisory_guidance", jurisdiction: jur}
|
return authorityInfo{weight: 70, sourceClass: "supervisory_guidance", jurisdiction: jur}
|
||||||
case r.Category == "regulation" || r.Category == "eu_recht" || normPattern.MatchString(r.ArticleLabel):
|
case r.Category == "regulation" || r.Category == "eu_recht" || normPattern.MatchString(r.ArticleLabel):
|
||||||
@@ -61,6 +69,8 @@ func sourceClassFromWeight(w int) string {
|
|||||||
switch {
|
switch {
|
||||||
case w >= 100:
|
case w >= 100:
|
||||||
return "binding_law"
|
return "binding_law"
|
||||||
|
case w >= 80:
|
||||||
|
return "technical_standard"
|
||||||
case w >= 70:
|
case w >= 70:
|
||||||
return "supervisory_guidance"
|
return "supervisory_guidance"
|
||||||
case w <= 0:
|
case w <= 0:
|
||||||
|
|||||||
@@ -7,17 +7,17 @@ import (
|
|||||||
|
|
||||||
// Re-ranking coefficients (validated in the offline golden harness; Phase A — conservative).
|
// Re-ranking coefficients (validated in the offline golden harness; Phase A — conservative).
|
||||||
const (
|
const (
|
||||||
authorityCoef = 0.40 // * weight/100
|
authorityCoef = 0.40 // * weight/100
|
||||||
jurisdictionGain = 0.05 // binding/guidance from DE or EU
|
jurisdictionGain = 0.05 // binding/guidance from DE or EU
|
||||||
foreignPenalty = 0.60 // foreign law on a DE/EU question (demoted, not removed)
|
foreignPenalty = 0.60 // foreign law on a DE/EU question (demoted, not removed)
|
||||||
unknownPenalty = 0.08
|
unknownPenalty = 0.08
|
||||||
domainMatchGain = 0.15
|
domainMatchGain = 0.15
|
||||||
offDomainPenalty = 0.10 // off-domain binding (demoted, not removed)
|
offDomainPenalty = 0.10 // off-domain binding (demoted, not removed)
|
||||||
scopePenalty = 0.25 // BDSG Teil 3 (law enforcement) on a general DP question
|
scopePenalty = 0.25 // BDSG Teil 3 (law enforcement) on a general DP question
|
||||||
topicGain = 0.18 // amplifier only
|
topicGain = 0.18 // amplifier only
|
||||||
supersededPenalty = 0.50 // superseded Alt-Quelle (pre-eu-v1): demoted, nicht versteckt
|
supersededPenalty = 0.50 // superseded Alt-Quelle (pre-eu-v1): demoted, nicht versteckt
|
||||||
guidanceIntentGain = 0.10 // epsilon a qualifying guideline is lifted ABOVE the best binding hit
|
intentLiftGain = 0.10 // epsilon a qualifying interpretative source is lifted ABOVE the best binding
|
||||||
guidanceIntentMargin = 0.05 // ...only if the guideline is semantically competitive with binding
|
intentLiftMargin = 0.05 // ...only if that source is semantically competitive with binding
|
||||||
)
|
)
|
||||||
|
|
||||||
// guidanceIntentSignals mark a query that EXPLICITLY asks for an interpretation /
|
// guidanceIntentSignals mark a query that EXPLICITLY asks for an interpretation /
|
||||||
@@ -29,10 +29,19 @@ var guidanceIntentSignals = []string{
|
|||||||
"auslegung", "empfiehlt", "empfehlung", "sagt", "laut",
|
"auslegung", "empfiehlt", "empfehlung", "sagt", "laut",
|
||||||
}
|
}
|
||||||
|
|
||||||
// queryWantsGuidance reports whether the query explicitly asks for guidance/interpretation.
|
// controlIntentSignals mark a query that asks HOW to implement / which controls or
|
||||||
func queryWantsGuidance(query string) bool {
|
// measures fit — rather than WHAT the binding obligation is. Only then may a
|
||||||
|
// (semantically competitive) technical_standard outrank the binding norm.
|
||||||
|
var controlIntentSignals = []string{
|
||||||
|
"control", "controls", "maßnahme", "massnahme", "schutzmaßnahme",
|
||||||
|
"best practice", "best-practice", "umsetzen", "implementier", "absicher",
|
||||||
|
"härt", "haert", "hardening", "nist", "owasp", "grundschutz",
|
||||||
|
"ccm", "iso 27001", "isms",
|
||||||
|
}
|
||||||
|
|
||||||
|
func queryMatchesAny(query string, signals []string) bool {
|
||||||
q := strings.ToLower(query)
|
q := strings.ToLower(query)
|
||||||
for _, sig := range guidanceIntentSignals {
|
for _, sig := range signals {
|
||||||
if strings.Contains(q, sig) {
|
if strings.Contains(q, sig) {
|
||||||
return true
|
return true
|
||||||
}
|
}
|
||||||
@@ -40,16 +49,22 @@ func queryWantsGuidance(query string) bool {
|
|||||||
return false
|
return false
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// queryWantsGuidance reports whether the query explicitly asks for guidance/interpretation.
|
||||||
|
func queryWantsGuidance(query string) bool { return queryMatchesAny(query, guidanceIntentSignals) }
|
||||||
|
|
||||||
|
// queryWantsControls reports whether the query asks for implementation controls/measures.
|
||||||
|
func queryWantsControls(query string) bool { return queryMatchesAny(query, controlIntentSignals) }
|
||||||
|
|
||||||
// bestBindingSemantic returns the highest RAW semantic score among binding-law
|
// bestBindingSemantic returns the highest RAW semantic score among binding-law
|
||||||
// results (0 if none / intent not requested). Used as the guard threshold so an
|
// results (0 if none / no intent). Used as the guard threshold so an off-topic
|
||||||
// off-topic guideline cannot ride the interpretation-intent boost.
|
// interpretative source cannot ride the intent boost.
|
||||||
func bestBindingSemantic(results []LegalSearchResult, wantsGuidance bool) float64 {
|
func bestBindingSemantic(results []LegalSearchResult, wantsIntent bool) float64 {
|
||||||
if !wantsGuidance {
|
if !wantsIntent {
|
||||||
return 0
|
return 0
|
||||||
}
|
}
|
||||||
best := 0.0
|
best := 0.0
|
||||||
for _, r := range results {
|
for _, r := range results {
|
||||||
if r.SourceClass == "binding_law" && r.Score > best {
|
if classifyAuthority(r).sourceClass == "binding_law" && r.Score > best {
|
||||||
best = r.Score
|
best = r.Score
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
@@ -104,6 +119,7 @@ func rerankByAuthority(query string, results []LegalSearchResult) []LegalSearchR
|
|||||||
qDomain := queryDomain(query)
|
qDomain := queryDomain(query)
|
||||||
qForeign := queryIsForeign(query)
|
qForeign := queryIsForeign(query)
|
||||||
wantsGuidance := queryWantsGuidance(query)
|
wantsGuidance := queryWantsGuidance(query)
|
||||||
|
wantsControls := queryWantsControls(query)
|
||||||
bestBindingSem := bestBindingSemantic(results, wantsGuidance)
|
bestBindingSem := bestBindingSemantic(results, wantsGuidance)
|
||||||
|
|
||||||
out := make([]LegalSearchResult, len(results))
|
out := make([]LegalSearchResult, len(results))
|
||||||
@@ -111,8 +127,15 @@ func rerankByAuthority(query string, results []LegalSearchResult) []LegalSearchR
|
|||||||
for i := range out {
|
for i := range out {
|
||||||
out[i].Score = authorityScore(query, out[i], qDomain, qForeign)
|
out[i].Score = authorityScore(query, out[i], qDomain, qForeign)
|
||||||
}
|
}
|
||||||
|
// Explicit interpretation intent → a competitive guideline may outrank binding (lift
|
||||||
|
// above the best binding FINAL). Explicit implementation intent → boost the CONTROL-POOL
|
||||||
|
// (operational/procedural requirement, control standard, implementation guidance) over
|
||||||
|
// the abstract obligation, soft-ordered by role. Norm questions (neither) stay untouched.
|
||||||
if wantsGuidance {
|
if wantsGuidance {
|
||||||
applyGuidanceIntent(out, results, bestBindingSem)
|
liftAboveBinding(out, results, bestBindingSem, "supervisory_guidance")
|
||||||
|
}
|
||||||
|
if wantsControls {
|
||||||
|
applyControlRoles(out)
|
||||||
}
|
}
|
||||||
sort.SliceStable(out, func(a, b int) bool {
|
sort.SliceStable(out, func(a, b int) bool {
|
||||||
return out[a].Score > out[b].Score
|
return out[a].Score > out[b].Score
|
||||||
@@ -120,24 +143,27 @@ func rerankByAuthority(query string, results []LegalSearchResult) []LegalSearchR
|
|||||||
return out
|
return out
|
||||||
}
|
}
|
||||||
|
|
||||||
// applyGuidanceIntent lifts semantically-competitive guidance just ABOVE the best
|
// liftAboveBinding lifts a semantically-competitive interpretative source (the given
|
||||||
// binding hit (ordered by semantic), so an EXPLICIT interpretation question can
|
// sourceClass — supervisory_guidance or technical_standard) just ABOVE the best binding
|
||||||
// return guidance Top-1. Obligation questions (no intent → not called) keep
|
// hit, ordered by semantic, so an EXPLICIT guidance/implementation question can return
|
||||||
// binding on top. Guidance below the semantic margin is left untouched, so an
|
// that source Top-1. A pure norm question (no intent → not called) keeps binding on top.
|
||||||
// off-topic guideline can never ride the override — and the lift is computed from
|
// Sources below the semantic margin are left untouched, so an off-topic source can never
|
||||||
// the binding FINAL score, so authority/topic/domain bonuses cannot edge it out.
|
// ride the override — and the lift is from the binding FINAL score, so authority/topic/
|
||||||
func applyGuidanceIntent(out, raw []LegalSearchResult, bestBindingSem float64) {
|
// domain bonuses cannot edge it out.
|
||||||
|
func liftAboveBinding(out, raw []LegalSearchResult, bestBindingSem float64, sourceClass string) {
|
||||||
bestBindingFinal := 0.0
|
bestBindingFinal := 0.0
|
||||||
for i := range out {
|
for i := range out {
|
||||||
if out[i].SourceClass == "binding_law" && out[i].Score > bestBindingFinal {
|
if classifyAuthority(out[i]).sourceClass == "binding_law" && out[i].Score > bestBindingFinal {
|
||||||
bestBindingFinal = out[i].Score
|
bestBindingFinal = out[i].Score
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
for i := range out {
|
for i := range out {
|
||||||
if out[i].SourceClass != "supervisory_guidance" || raw[i].Score < bestBindingSem-guidanceIntentMargin {
|
// Classify (not raw payload) so the untagged legacy corpus — e.g. NIST ingested
|
||||||
|
// before source_class tagging — is still recognized as its interpretative class.
|
||||||
|
if classifyAuthority(out[i]).sourceClass != sourceClass || raw[i].Score < bestBindingSem-intentLiftMargin {
|
||||||
continue
|
continue
|
||||||
}
|
}
|
||||||
lifted := bestBindingFinal + guidanceIntentGain + (raw[i].Score - bestBindingSem)
|
lifted := bestBindingFinal + intentLiftGain + (raw[i].Score - bestBindingSem)
|
||||||
if lifted > out[i].Score {
|
if lifted > out[i].Score {
|
||||||
out[i].Score = lifted
|
out[i].Score = lifted
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -14,6 +14,10 @@ func TestClassifyAuthority(t *testing.T) {
|
|||||||
{"tagged guidance DE", LegalSearchResult{AuthorityWeight: 70, SourceClass: "supervisory_guidance", Jurisdiction: "DE"}, 70, "supervisory_guidance", "DE"},
|
{"tagged guidance DE", LegalSearchResult{AuthorityWeight: 70, SourceClass: "supervisory_guidance", Jurisdiction: "DE"}, 70, "supervisory_guidance", "DE"},
|
||||||
{"tagged foreign CH", LegalSearchResult{AuthorityWeight: 0, SourceClass: "foreign_law", Jurisdiction: "CH"}, 0, "foreign_law", "CH"},
|
{"tagged foreign CH", LegalSearchResult{AuthorityWeight: 0, SourceClass: "foreign_law", Jurisdiction: "CH"}, 0, "foreign_law", "CH"},
|
||||||
{"untagged ENISA guidance", LegalSearchResult{RegulationShort: "ENISA", ArticleLabel: "ENISA CRA Standards Mapping"}, 70, "supervisory_guidance", "EU"},
|
{"untagged ENISA guidance", LegalSearchResult{RegulationShort: "ENISA", ArticleLabel: "ENISA CRA Standards Mapping"}, 70, "supervisory_guidance", "EU"},
|
||||||
|
{"untagged NIST standard", LegalSearchResult{RegulationShort: "NIST SP 800-82r3", ArticleLabel: "AU-8"}, 80, "technical_standard", "EU"},
|
||||||
|
{"BSI Grundschutz standard beats BSI guidance", LegalSearchResult{RegulationShort: "BSI Grundschutz", ArticleLabel: "BSI Grundschutz Baustein"}, 80, "technical_standard", "DE"},
|
||||||
|
{"weight-only 85 TRGS standard", LegalSearchResult{AuthorityWeight: 85, RegulationShort: "TRGS 529"}, 85, "technical_standard", "EU"},
|
||||||
|
{"tagged technical_standard", LegalSearchResult{AuthorityWeight: 80, SourceClass: "technical_standard", Jurisdiction: "EU"}, 80, "technical_standard", "EU"},
|
||||||
{"untagged CRA binding", LegalSearchResult{RegulationShort: "CRA", ArticleLabel: "Art. 13 CRA", Category: "regulation"}, 100, "binding_law", "EU"},
|
{"untagged CRA binding", LegalSearchResult{RegulationShort: "CRA", ArticleLabel: "Art. 13 CRA", Category: "regulation"}, 100, "binding_law", "EU"},
|
||||||
{"untagged BDSG binding DE", LegalSearchResult{RegulationShort: "BDSG", ArticleLabel: "§ 38 BDSG"}, 100, "binding_law", "DE"},
|
{"untagged BDSG binding DE", LegalSearchResult{RegulationShort: "BDSG", ArticleLabel: "§ 38 BDSG"}, 100, "binding_law", "DE"},
|
||||||
{"untagged RevDSG foreign", LegalSearchResult{RegulationShort: "RevDSG", ArticleLabel: "RevDSG (CH)"}, 0, "foreign_law", "CH"},
|
{"untagged RevDSG foreign", LegalSearchResult{RegulationShort: "RevDSG", ArticleLabel: "RevDSG (CH)"}, 0, "foreign_law", "CH"},
|
||||||
|
|||||||
@@ -0,0 +1,123 @@
|
|||||||
|
package ucca
|
||||||
|
|
||||||
|
import "strings"
|
||||||
|
|
||||||
|
// source_role is the FUNCTIONAL role of a chunk — WHAT must be done (obligation),
|
||||||
|
// HOW to implement it (operational/procedural requirement, control standard,
|
||||||
|
// implementation guidance), or how to READ the norm (interpretation/definition).
|
||||||
|
// It is ORTHOGONAL to source_class (legal authority): source_class decides RANK,
|
||||||
|
// source_role decides CONTROL-POOL membership for implementation questions.
|
||||||
|
// Derived deterministically from markers, so the untagged corpus needs no re-tag.
|
||||||
|
const (
|
||||||
|
roleObligation = "obligation" // the abstract duty (the WHAT)
|
||||||
|
roleOperationalReq = "operational_requirement" // concrete binding requirement (CRA Annex I)
|
||||||
|
roleProceduralReq = "procedural_requirement" // a process: notification/registration/DPIA/incident report
|
||||||
|
roleControlStandard = "control_standard" // best-practice control catalog (NIST/OWASP/ISO/CIS)
|
||||||
|
roleImplGuidance = "implementation_guidance" // advisory how-to (ENISA good practices, BSI)
|
||||||
|
roleInterpretation = "interpretation" // interprets the norm's MEANING (EDPB guideline)
|
||||||
|
roleDefinition = "definition" // definitions / scope / recitals
|
||||||
|
)
|
||||||
|
|
||||||
|
var (
|
||||||
|
proceduralMarkers = []string{
|
||||||
|
"Meldung", "Meldepflicht", "Notification", "Notifizierung", "Registrierung",
|
||||||
|
"Registration", "Konformitätserklärung", "Declaration of Conformity", "Incident",
|
||||||
|
"Berichterstattung", "Reporting", "Folgenabschätzung", "DSFA", "DPIA", "Anzeigepflicht",
|
||||||
|
}
|
||||||
|
annexMarkers = []string{"Anhang", "Annex", "Appendix", "Anlage"}
|
||||||
|
operationalMarkers = []string{"Anforderung", "Requirement", "essential", "wesentliche"}
|
||||||
|
implMarkers = []string{
|
||||||
|
"Good Practice", "Best Practice", "Standards Mapping", "Umsetzung", "Implementation",
|
||||||
|
"Handreichung", "Maßnahmenkatalog", "ICS", "SCADA", "Technical Guideline", "TIG",
|
||||||
|
}
|
||||||
|
definitionMarkers = []string{"Begriffsbestimmung", "Definition"}
|
||||||
|
)
|
||||||
|
|
||||||
|
// classifyRole derives the functional source_role from chunk metadata + the authority
|
||||||
|
// class. technical_standard is always a control_standard; guidance splits into
|
||||||
|
// implementation_guidance (how-to) vs interpretation (meaning); binding splits into
|
||||||
|
// procedural / operational requirement / definition / plain obligation.
|
||||||
|
func classifyRole(r LegalSearchResult) string {
|
||||||
|
cls := classifyAuthority(r).sourceClass
|
||||||
|
hay := strings.ToLower(r.ArticleLabel + " " + r.RegulationShort + " " + r.RegulationName + " " + r.Article)
|
||||||
|
switch {
|
||||||
|
case r.IsRecital:
|
||||||
|
return roleDefinition
|
||||||
|
case cls == "technical_standard":
|
||||||
|
return roleControlStandard
|
||||||
|
case cls == "supervisory_guidance":
|
||||||
|
if containsAnyLower(hay, implMarkers) {
|
||||||
|
return roleImplGuidance
|
||||||
|
}
|
||||||
|
return roleInterpretation
|
||||||
|
case cls == "binding_law":
|
||||||
|
switch {
|
||||||
|
case containsAnyLower(hay, definitionMarkers):
|
||||||
|
return roleDefinition
|
||||||
|
case containsAnyLower(hay, proceduralMarkers):
|
||||||
|
return roleProceduralReq
|
||||||
|
case containsAnyLower(hay, annexMarkers) || containsAnyLower(hay, operationalMarkers):
|
||||||
|
return roleOperationalReq
|
||||||
|
default:
|
||||||
|
return roleObligation
|
||||||
|
}
|
||||||
|
default:
|
||||||
|
return roleObligation
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
// controlRoleBonus is the soft intra-pool preference (User 2026-06-24):
|
||||||
|
// operational_requirement > procedural_requirement > control_standard > implementation_guidance.
|
||||||
|
var controlRoleBonus = map[string]float64{
|
||||||
|
roleOperationalReq: 0.100,
|
||||||
|
roleProceduralReq: 0.075,
|
||||||
|
roleControlStandard: 0.050,
|
||||||
|
roleImplGuidance: 0.000,
|
||||||
|
}
|
||||||
|
|
||||||
|
// controlPoolGain lifts EVERY control-pool role over the non-control roles (obligation/
|
||||||
|
// interpretation/definition) on an implementation question, so the binding abstract
|
||||||
|
// obligation does not dominate by authority alone. The obligation is not removed — it
|
||||||
|
// stays visible as "Rechtsgrundlage" context below the recommended measures.
|
||||||
|
const controlPoolGain = 0.15
|
||||||
|
|
||||||
|
// applyControlRoles boosts the control-pool (the four implementation roles) for an
|
||||||
|
// EXPLICIT implementation question, soft-ordered op_req > procedural > standard > guidance.
|
||||||
|
// Replaces the earlier "lift technical_standard above binding" — controls are not only
|
||||||
|
// technical_standard, and the binding operational_requirement (e.g. CRA Annex I) should win.
|
||||||
|
func applyControlRoles(out []LegalSearchResult) {
|
||||||
|
for i := range out {
|
||||||
|
if bonus, ok := controlRoleBonus[classifyRole(out[i])]; ok {
|
||||||
|
out[i].Score += controlPoolGain + bonus
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
// isControlPoolRole reports whether a role belongs to the control-pool surfaced on
|
||||||
|
// implementation questions (the four "how to implement" roles).
|
||||||
|
func isControlPoolRole(role string) bool {
|
||||||
|
switch role {
|
||||||
|
case roleOperationalReq, roleProceduralReq, roleControlStandard, roleImplGuidance:
|
||||||
|
return true
|
||||||
|
}
|
||||||
|
return false
|
||||||
|
}
|
||||||
|
|
||||||
|
// controlRoleOf classifies a raw Qdrant payload into a source_role, so searchControls can
|
||||||
|
// filter its deep dense pull to the control-pool BEFORE hits are mapped to LegalSearchResult.
|
||||||
|
func controlRoleOf(payload map[string]interface{}) string {
|
||||||
|
article := getString(payload, "article")
|
||||||
|
if article == "" {
|
||||||
|
article = getString(payload, "section")
|
||||||
|
}
|
||||||
|
return classifyRole(LegalSearchResult{
|
||||||
|
RegulationShort: getString(payload, "regulation_short"),
|
||||||
|
RegulationName: getString(payload, "regulation_name_de"),
|
||||||
|
ArticleLabel: getString(payload, "article_label"),
|
||||||
|
Article: article,
|
||||||
|
Category: getString(payload, "category"),
|
||||||
|
SourceClass: getString(payload, "source_class"),
|
||||||
|
AuthorityWeight: getInt(payload, "authority_weight"),
|
||||||
|
IsRecital: getBool(payload, "is_recital"),
|
||||||
|
})
|
||||||
|
}
|
||||||
@@ -0,0 +1,79 @@
|
|||||||
|
package ucca
|
||||||
|
|
||||||
|
import "testing"
|
||||||
|
|
||||||
|
func TestClassifyRole(t *testing.T) {
|
||||||
|
tests := []struct {
|
||||||
|
name string
|
||||||
|
r LegalSearchResult
|
||||||
|
want string
|
||||||
|
}{
|
||||||
|
{"NIST -> control_standard", LegalSearchResult{RegulationShort: "NIST SP 800-82r3", ArticleLabel: "AU-8"}, roleControlStandard},
|
||||||
|
{"OWASP -> control_standard", LegalSearchResult{RegulationShort: "OWASP ASVS"}, roleControlStandard},
|
||||||
|
{"CRA Anhang -> operational_requirement", LegalSearchResult{RegulationShort: "CRA", ArticleLabel: "CRA Anhang I", Category: "regulation"}, roleOperationalReq},
|
||||||
|
{"CRA Meldepflicht -> procedural_requirement", LegalSearchResult{RegulationShort: "CRA", ArticleLabel: "Art. 14 CRA Meldepflicht", Category: "regulation"}, roleProceduralReq},
|
||||||
|
{"ENISA Good Practices -> implementation_guidance", LegalSearchResult{RegulationShort: "ENISA Supply Chain Good Practices"}, roleImplGuidance},
|
||||||
|
{"EDPB Leitlinie -> interpretation", LegalSearchResult{RegulationShort: "EDPB DPO", ArticleLabel: "WP243 Leitlinien Datenschutzbeauftragte"}, roleInterpretation},
|
||||||
|
{"DORA article -> obligation", LegalSearchResult{RegulationShort: "DORA", ArticleLabel: "Art. 5 DORA", Category: "regulation"}, roleObligation},
|
||||||
|
{"DSGVO Begriffsbestimmungen -> definition", LegalSearchResult{RegulationShort: "DSGVO", ArticleLabel: "Art. 4 DSGVO Begriffsbestimmungen", Category: "regulation"}, roleDefinition},
|
||||||
|
{"recital -> definition", LegalSearchResult{RegulationShort: "CRA", IsRecital: true}, roleDefinition},
|
||||||
|
}
|
||||||
|
for _, tt := range tests {
|
||||||
|
t.Run(tt.name, func(t *testing.T) {
|
||||||
|
if got := classifyRole(tt.r); got != tt.want {
|
||||||
|
t.Errorf("classifyRole() = %q, want %q", got, tt.want)
|
||||||
|
}
|
||||||
|
})
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
func TestApplyControlRoles_PoolPreference(t *testing.T) {
|
||||||
|
// op_req > procedural > control_standard > impl_guidance; non-control roles get no boost.
|
||||||
|
roles := []struct {
|
||||||
|
r LegalSearchResult
|
||||||
|
wantGain float64
|
||||||
|
}{
|
||||||
|
{LegalSearchResult{ArticleLabel: "CRA Anhang I", Category: "regulation"}, controlPoolGain + 0.100},
|
||||||
|
{LegalSearchResult{ArticleLabel: "Art. 14 CRA Meldepflicht", Category: "regulation"}, controlPoolGain + 0.075},
|
||||||
|
{LegalSearchResult{RegulationShort: "NIST SP 800-53"}, controlPoolGain + 0.050},
|
||||||
|
{LegalSearchResult{RegulationShort: "ENISA Good Practices"}, controlPoolGain + 0.000},
|
||||||
|
{LegalSearchResult{ArticleLabel: "Art. 5 DORA", Category: "regulation"}, 0.0}, // obligation: no boost
|
||||||
|
}
|
||||||
|
for _, rc := range roles {
|
||||||
|
out := []LegalSearchResult{rc.r}
|
||||||
|
out[0].Score = 1.0
|
||||||
|
applyControlRoles(out)
|
||||||
|
if got := out[0].Score - 1.0; got < rc.wantGain-1e-9 || got > rc.wantGain+1e-9 {
|
||||||
|
t.Errorf("role %q: gain %.3f, want %.3f", classifyRole(rc.r), got, rc.wantGain)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
func TestIsControlPoolRole(t *testing.T) {
|
||||||
|
for _, r := range []string{roleOperationalReq, roleProceduralReq, roleControlStandard, roleImplGuidance} {
|
||||||
|
if !isControlPoolRole(r) {
|
||||||
|
t.Errorf("%q should be in the control-pool", r)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
for _, r := range []string{roleObligation, roleInterpretation, roleDefinition} {
|
||||||
|
if isControlPoolRole(r) {
|
||||||
|
t.Errorf("%q should NOT be in the control-pool", r)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
func TestControlRoleOf_Payload(t *testing.T) {
|
||||||
|
// searchControls filters its deep dense pull by classifying the raw Qdrant payload.
|
||||||
|
nist := map[string]interface{}{"regulation_short": "NIST SP 800-82r3", "article": "AU-8"}
|
||||||
|
if got := controlRoleOf(nist); got != roleControlStandard {
|
||||||
|
t.Errorf("untagged NIST payload role = %q, want control_standard", got)
|
||||||
|
}
|
||||||
|
craAnnex := map[string]interface{}{"regulation_short": "CRA", "article": "Anhang-I", "category": "regulation"}
|
||||||
|
if got := controlRoleOf(craAnnex); got != roleOperationalReq {
|
||||||
|
t.Errorf("CRA Anhang payload role = %q, want operational_requirement", got)
|
||||||
|
}
|
||||||
|
dora := map[string]interface{}{"regulation_short": "DORA", "article_label": "Art. 5 DORA", "category": "regulation"}
|
||||||
|
if got := controlRoleOf(dora); isControlPoolRole(got) {
|
||||||
|
t.Errorf("DORA abstract article role = %q must be excluded from the control-pool", got)
|
||||||
|
}
|
||||||
|
}
|
||||||
@@ -107,6 +107,15 @@ func (c *LegalRAGClient) searchInternal(ctx context.Context, collection string,
|
|||||||
hits = mergeDedupHits(hits, bindingHits)
|
hits = mergeDedupHits(hits, bindingHits)
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// Control-Augmentation: bei expliziter Umsetzungsfrage einen tiefen dense-Pool ziehen und
|
||||||
|
// nur die Control-Pool-Rollen behalten — so werden NIST/CRA-Anhang (dense rank ~8-9, unter
|
||||||
|
// dem kleinen top-K) Kandidaten. Re-Rank/applyControlRoles ordnen sie danach.
|
||||||
|
if queryWantsControls(query) {
|
||||||
|
if controlHits, cErr := c.searchControls(ctx, collection, embedding); cErr == nil {
|
||||||
|
hits = mergeDedupHits(hits, controlHits)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
// Graph-Augmentation: verbundene Normen (references_out/in) der Top-Hits ueber die
|
// Graph-Augmentation: verbundene Normen (references_out/in) der Top-Hits ueber die
|
||||||
// praezise Zitations-Kante in den Pool ziehen — z.B. Art. 13 CRA zieht Anhang I (die
|
// praezise Zitations-Kante in den Pool ziehen — z.B. Art. 13 CRA zieht Anhang I (die
|
||||||
// eigentliche Pflichtquelle). Pool-Augmentation only; Re-Rank + topK bleiben.
|
// eigentliche Pflichtquelle). Pool-Augmentation only; Re-Rank + topK bleiben.
|
||||||
|
|||||||
@@ -204,6 +204,34 @@ func (c *LegalRAGClient) searchBinding(ctx context.Context, collection string, e
|
|||||||
return c.doPointsSearch(ctx, collection, searchReq)
|
return c.doPointsSearch(ctx, collection, searchReq)
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// controlPoolDepth is how deep the dense control pull reaches. Measured: for an EU-cyber
|
||||||
|
// control query the relevant control sources sit at dense rank ~8-9 (NIST, CRA Annex), far
|
||||||
|
// below the client's small top-K — so a fixed dense depth of 60 reliably surfaces them.
|
||||||
|
const controlPoolDepth = 60
|
||||||
|
|
||||||
|
// searchControls fetches a DEEP dense pool and keeps only the control-pool roles, so control
|
||||||
|
// sources that the small top-K (hybrid) search misses become candidates on an implementation
|
||||||
|
// question. Role is derived in code (no source_role tag needed). AUGMENTS the pool — the
|
||||||
|
// caller gates it on control-intent.
|
||||||
|
func (c *LegalRAGClient) searchControls(ctx context.Context, collection string, embedding []float64) ([]qdrantSearchHit, error) {
|
||||||
|
searchReq := qdrantSearchRequest{
|
||||||
|
Vector: embedding,
|
||||||
|
Limit: controlPoolDepth,
|
||||||
|
WithPayload: true,
|
||||||
|
}
|
||||||
|
hits, err := c.doPointsSearch(ctx, collection, searchReq)
|
||||||
|
if err != nil {
|
||||||
|
return nil, err
|
||||||
|
}
|
||||||
|
kept := make([]qdrantSearchHit, 0, len(hits))
|
||||||
|
for _, h := range hits {
|
||||||
|
if isControlPoolRole(controlRoleOf(h.Payload)) {
|
||||||
|
kept = append(kept, h)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
return kept, nil
|
||||||
|
}
|
||||||
|
|
||||||
// doPointsSearch issues a POST /points/search and decodes the hits.
|
// doPointsSearch issues a POST /points/search and decodes the hits.
|
||||||
func (c *LegalRAGClient) doPointsSearch(ctx context.Context, collection string, searchReq qdrantSearchRequest) ([]qdrantSearchHit, error) {
|
func (c *LegalRAGClient) doPointsSearch(ctx context.Context, collection string, searchReq qdrantSearchRequest) ([]qdrantSearchHit, error) {
|
||||||
jsonBody, err := json.Marshal(searchReq)
|
jsonBody, err := json.Marshal(searchReq)
|
||||||
|
|||||||
@@ -70,3 +70,66 @@ func TestRerank_OffTopicGuidance_BlockedByGuard(t *testing.T) {
|
|||||||
t.Errorf("off-topic guidance must not win even with intent, got %s", out[0].SourceClass)
|
t.Errorf("off-topic guidance must not win even with intent, got %s", out[0].SourceClass)
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
func TestQueryWantsControls(t *testing.T) {
|
||||||
|
wants := []string{
|
||||||
|
"Welche Controls passen zu Security Updates?",
|
||||||
|
"Welche Maßnahmen sollten wir umsetzen?",
|
||||||
|
"Wie härten wir den Server ab?",
|
||||||
|
"Gibt es NIST-Controls dafür?",
|
||||||
|
"OWASP Best Practice für Logging?",
|
||||||
|
"BSI Grundschutz Bausteine",
|
||||||
|
}
|
||||||
|
plain := []string{
|
||||||
|
"Welche Anforderungen bestehen an Security Updates?",
|
||||||
|
"Ab wann braucht man einen Datenschutzbeauftragten?",
|
||||||
|
}
|
||||||
|
for _, q := range wants {
|
||||||
|
if !queryWantsControls(q) {
|
||||||
|
t.Errorf("should detect control/implementation intent: %q", q)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
for _, q := range plain {
|
||||||
|
if queryWantsControls(q) {
|
||||||
|
t.Errorf("should NOT detect control intent (norm question): %q", q)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
func TestRerank_ControlQuestion_OperationalReqTop(t *testing.T) {
|
||||||
|
// User priority for implementation questions: operational_requirement (binding concrete,
|
||||||
|
// CRA Anhang I) > control_standard (NIST). Both are in the control-pool; op_req wins.
|
||||||
|
results := []LegalSearchResult{
|
||||||
|
{RegulationShort: "NIST SP 800-82r3", ArticleLabel: "AU-8", SourceClass: "technical_standard", AuthorityWeight: 80, Jurisdiction: "EU", Score: 0.60},
|
||||||
|
{RegulationShort: "CRA", ArticleLabel: "CRA Anhang I", Category: "regulation", Score: 0.58},
|
||||||
|
}
|
||||||
|
out := rerankByAuthority("Welche Controls und Massnahmen passen zu Security Updates?", results)
|
||||||
|
if out[0].RegulationShort != "CRA" {
|
||||||
|
t.Errorf("operational_requirement (CRA Anhang I) should be Top-1 over control_standard, got %q", out[0].RegulationShort)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
func TestRerank_NormQuestion_BindingOverStandard(t *testing.T) {
|
||||||
|
// "Anforderungen" → no control intent → binding obligation stays Top-1 over the standard.
|
||||||
|
results := []LegalSearchResult{
|
||||||
|
intentRes("NIST SP 800-82", "technical_standard", 0.62, 80),
|
||||||
|
intentRes("CRA", "binding_law", 0.58, 100),
|
||||||
|
}
|
||||||
|
out := rerankByAuthority("Welche Anforderungen bestehen an Security Updates?", results)
|
||||||
|
if out[0].SourceClass != "binding_law" {
|
||||||
|
t.Errorf("norm question: binding must stay Top-1 over standard, got %s", out[0].SourceClass)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
func TestRerank_ControlQuestion_PoolBeatsBareObligation(t *testing.T) {
|
||||||
|
// A control-pool source (NIST control_standard) outranks an abstract obligation with no
|
||||||
|
// domain/topic advantage, because the implementation intent boosts the control-pool.
|
||||||
|
results := []LegalSearchResult{
|
||||||
|
{RegulationShort: "NIST SP 800-82r3", ArticleLabel: "AU-8", SourceClass: "technical_standard", AuthorityWeight: 80, Jurisdiction: "EU", Score: 0.55},
|
||||||
|
{RegulationShort: "XYZ", ArticleLabel: "Art. 5 XYZ", Category: "regulation", Score: 0.58},
|
||||||
|
}
|
||||||
|
out := rerankByAuthority("Welche Controls und Massnahmen passen zu Security Updates?", results)
|
||||||
|
if out[0].RegulationShort != "NIST SP 800-82r3" {
|
||||||
|
t.Errorf("control_standard should beat a bare abstract obligation on a control question, got %q", out[0].RegulationShort)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|||||||
Reference in New Issue
Block a user