fix(iace): narrative extractor ignored most Grenzen fields (field-name mismatch)
CI / test-go (push) Failing after 36s
CI / iace-gt-coverage (push) Successful in 23s
CI / test-python-backend (push) Has been skipped
CI / test-python-document-crawler (push) Has been skipped
CI / test-python-dsms-gateway (push) Has been skipped
CI / detect-changes (push) Successful in 6s
CI / branch-name (push) Has been skipped
CI / guardrail-integrity (push) Has been skipped
CI / secret-scan (push) Has been skipped
CI / dep-audit (push) Has been skipped
CI / sbom-scan (push) Has been skipped
CI / build-sha-integrity (push) Failing after 5s
CI / validate-canonical-controls (push) Successful in 12s
CI / loc-budget (push) Failing after 14s
CI / go-lint (push) Has been skipped
CI / python-lint (push) Has been skipped
CI / nodejs-lint (push) Has been skipped
CI / nodejs-build (push) Has been skipped

extractNarrativeFromMetadata looked for field names that don't exist in the real
limits-form schema (interfaces_description, control_system_description,
energy_sources, space_limits, foreseeable_misuse), so it effectively read only
general_description + intended_purpose. The electrical/mechanical/pneumatic/
software interface fields — each a hazard source — were silently dropped, which
is why electrical hazard coverage was 9% for the Kistenhubgeraet.

Now reads the actual schema fields incl. electrical_interfaces /
mechanical_interfaces / pneumatic_hydraulic_interfaces / software_interfaces /
energy_supply / spatial_limits / foreseeable_misuses, plus array fields
(operating_modes, person_groups, industry_sectors). Legacy names kept.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
Benjamin Admin
2026-06-09 16:44:29 +02:00
parent 6ca4dcde3e
commit 1ffdb99650
@@ -26,23 +26,51 @@ func extractNarrativeFromMetadata(metadata json.RawMessage) string {
return ""
}
// Every limits-form field that carries machine-describing text. Field
// names MUST match the real form schema — the per-interface fields
// (electrical/mechanical/pneumatic/software) each contribute hazards, not
// just the prose. Legacy names are kept so older projects still parse.
textFields := []string{
"general_description", "intended_purpose", "foreseeable_misuse",
"space_limits", "time_limits", "environmental_conditions",
"energy_sources", "materials_processed", "operating_modes",
"maintenance_requirements", "personnel_requirements",
"interfaces_description", "control_system_description",
"safety_functions_description",
// description / purpose
"general_description", "machine_designation", "intended_purpose",
"foreseeable_misuse", "foreseeable_misuses", "variants", "area_of_use",
// limits
"space_limits", "spatial_limits", "time_limits", "temporal_limits",
"environmental_conditions", "operating_conditions",
// energy + materials
"energy_sources", "energy_supply", "materials_processed",
// interfaces (the previously-ignored ones)
"interfaces_description", "control_system_description", "safety_functions_description",
"electrical_interfaces", "mechanical_interfaces",
"pneumatic_hydraulic_interfaces", "software_interfaces",
// people / maintenance
"maintenance_requirements", "personnel_requirements", "qualification_requirements",
}
var result string
arrayFields := []string{"operating_modes", "person_groups", "industry_sectors"}
var sb strings.Builder
for _, field := range textFields {
if v, ok := limits[field]; ok {
if s, ok := v.(string); ok && s != "" {
result += s + "\n\n"
if s, ok := v.(string); ok && strings.TrimSpace(s) != "" {
sb.WriteString(s)
sb.WriteString("\n\n")
}
}
}
return result
for _, field := range arrayFields {
if v, ok := limits[field]; ok {
if arr, ok := v.([]interface{}); ok {
for _, e := range arr {
if s, ok := e.(string); ok && s != "" {
sb.WriteString(s)
sb.WriteString(", ")
}
}
sb.WriteString("\n\n")
}
}
}
return sb.String()
}
// acceptableMeasureCategories returns the set of measure HazardCategory values