breakpilot-compliance/ai-compliance-sdk/internal/iace/pattern_domain_gates.go

package iace

import "strings"

// Capability-Domain-Gating — the cure for cross-domain leakage.
//
// Many domain-specific hazard patterns were authored gated only by a GENERIC
// capability tag (e.g. "rotating_part"), so they fire for every machine that
// has rotating parts — a lift, a robot cell — even though the hazard belongs to
// a press, a spinning machine or a PV array. This is the precision-killing
// inverse of ghost patterns; both stem from inconsistent applicability.
//
// The fix is capability-driven (NOT a machine-type whitelist hack): a pattern
// whose OWN scenario text names a foreign machine gets that domain's capability
// tag appended to its RequiredComponentTags. The same tag is emitted by the
// domain's narrative keywords (keyword_dictionary.go), so the pattern still
// fires for its real domain but no longer leaks into unrelated machines.
//
// INVARIANT: every tag below MUST be emittable via keyword_dictionary.go,
// otherwise the gated pattern becomes a ghost. TestTagVocabulary_GhostPatterns
// is the regression guard for this.

// domainGateTerms maps a machine-betraying term (umlaut-normalised, lowercase)
// to the domain capability tag that gates patterns mentioning it.
var domainGateTerms = map[string]string{
	// Pressen / Stanzen / Umformen
	"stanzhub": "dom_press", "pressenhub": "dom_press", "pressenstoessel": "dom_press",
	"dauerhub": "dom_press", "exzenterpresse": "dom_press", "beinpresse": "dom_press",
	"stanzpresse": "dom_press", "umformpresse": "dom_press",
	"pressenteil": "dom_press", "pressraum": "dom_press", "blechbearbeitung": "dom_press",
	"werkzeugraum der presse": "dom_press",
	// Glas-Bearbeitung
	"glasschneid": "dom_glass", "glasbearbeitung": "dom_glass", "glasscheibe": "dom_glass",
	"glaskante": "dom_glass",
	// Kunststoff / Spritzguss / Extrusion
	"spritzgie": "dom_plastics", "extruder": "dom_plastics", "extrusion": "dom_plastics",
	"kunststoffschmelze": "dom_plastics", "schliesseinheit": "dom_plastics",
	// Walzen / Kalander / Laminieren
	"walzenspalt": "dom_rolling", "zweiwalzenwerk": "dom_rolling", "kalander": "dom_rolling",
	"walzwerk": "dom_rolling", "laminieranlage": "dom_rolling", "laminier": "dom_rolling",
	// Textil
	"spinnmaschine": "dom_textile", "webmaschine": "dom_textile", "spinnerei": "dom_textile",
	// Schleifen
	"schleifscheibe": "dom_grinding", "schleifbock": "dom_grinding",
	// Schweissen
	"widerstandsschweiss": "dom_welding", "lichtbogenschweiss": "dom_welding",
	"schutzgasschweiss": "dom_welding", "punktschweiss": "dom_welding",
	"schweisselektrod": "dom_welding", "elektrodenspalt": "dom_welding",
	// Solar / PV
	"pv-modul": "dom_solar", "photovoltaik": "dom_solar", "pv-anlage": "dom_solar",
	"dc-steckverbindung": "dom_solar", "solarmodul": "dom_solar",
	// Windkraft
	"gondel": "dom_wind", "rotorblatt": "dom_wind", "windenergieanlage": "dom_wind",
	// CNC / Zerspanung
	"drehmaschine": "dom_cnc", "fraesmaschine": "dom_cnc",
	// Landwirtschaft
	"maehdrescher": "dom_agri", "ballenpresse": "dom_agri", "feldhaecksler": "dom_agri",
	// Roll-/Fahrtreppe
	"rolltreppe": "dom_escalator", "fahrtreppe": "dom_escalator",
	// Aussen-/Witterungs-/Bioarbeit (Forst, Bau im Freien)
	"zecke": "dom_outdoor", "zeckenstich": "dom_outdoor", "fsme": "dom_outdoor",
	"borreliose": "dom_outdoor", "im freien": "dom_outdoor", "freigelaende": "dom_outdoor",
	"aussengelaende": "dom_outdoor", "ausseneinsatz": "dom_outdoor", "witterung": "dom_outdoor",
	"winterarbeit": "dom_outdoor", "nagerkot": "dom_outdoor", "hantavirus": "dom_outdoor",
	// Lueftung/Feuchte (Schimmel)
	"schimmel": "dom_ventilation", "schimmelspor": "dom_ventilation",
	"lueftungsanlage": "dom_ventilation", "lueftungskanal": "dom_ventilation",
	// Zerspanung / Kuehlschmierstoff
	"kuehlschmierstoff": "dom_machining", "kss-kreislauf": "dom_machining",
	"kss-aufbereitung": "dom_machining", "kuehlturm": "dom_machining",
	"bearbeitungszentrum": "dom_machining",
	// Schuettgut / Silo / Gaerbehaelter (Confined Space mit Schuettgut)
	"silo": "dom_bulk", "schuettgut": "dom_bulk", "gaerbehaelter": "dom_bulk",
	"getreidesilo": "dom_bulk", "mehlsilo": "dom_bulk",
	// Palettierer
	"palettierer": "dom_palletizer", "palettieranlage": "dom_palletizer",
	// Spielplatz / Spielgeraet
	"klettergeraet": "dom_playground", "spielplatz": "dom_playground", "spielgeraet": "dom_playground",
	// Fitness / Kraftgeraet
	"gewichtstapel": "dom_fitness", "langhantel": "dom_fitness", "bankdrueck": "dom_fitness",
	"kniebeug": "dom_fitness", "kraftstation": "dom_fitness",
}

// applyDomainGates appends a domain capability tag to every pattern whose own
// text betrays that domain, so domain-specific hazards stop leaking into
// unrelated machines. Idempotent; safe to run once after pattern collection.
func applyDomainGates(patterns []HazardPattern) []HazardPattern {
	for i := range patterns {
		text := normalizeGateText(patterns[i].NameDE + " " + patterns[i].ScenarioDE + " " +
			patterns[i].TriggerDE + " " + patterns[i].HarmDE + " " + patterns[i].ZoneDE)

		present := make(map[string]bool, len(patterns[i].RequiredComponentTags))
		for _, t := range patterns[i].RequiredComponentTags {
			present[t] = true
		}
		for term, tag := range domainGateTerms {
			if present[tag] {
				continue
			}
			if strings.Contains(text, term) {
				patterns[i].RequiredComponentTags = append(patterns[i].RequiredComponentTags, tag)
				present[tag] = true
			}
		}
	}
	return patterns
}

// normalizeGateText lowercases and folds umlauts, matching keyword_dictionary's
// normalisation so gate terms and emit keywords use one vocabulary.
func normalizeGateText(s string) string {
	s = strings.ToLower(s)
	s = strings.ReplaceAll(s, "ä", "ae")
	s = strings.ReplaceAll(s, "ö", "oe")
	s = strings.ReplaceAll(s, "ü", "ue")
	s = strings.ReplaceAll(s, "ß", "ss")
	return s
}