// Package ontology ingests the GovCon vocabulary from free federal sources into the global ontology
// store. It mirrors the opportunity_intelligence ingestion shape: a streaming source contract, a single
// ingester that retains each raw payload and upserts the normalized record, and one audit event per run.
package ontology

import "encoding/json"

// TermKind is the closed set of vocabulary record kinds. A closed set keeps the global table queryable
// and lets the WS2 promotion step reason about provenance.
type TermKind string

const (
	KindSkill         TermKind = "skill"
	KindLaborCategory TermKind = "labor_category"
	KindWorkRole      TermKind = "work_role"
	KindKSA           TermKind = "ksa"
	KindPSC           TermKind = "psc_code"
	KindMissionArea   TermKind = "mission_area"
)

// Valid reports whether k is one of the allowed kinds (it must match the CHECK in migration 0021).
func (k TermKind) Valid() bool {
	switch k {
	case KindSkill, KindLaborCategory, KindWorkRole, KindKSA, KindPSC, KindMissionArea:
		return true
	}
	return false
}

// VocabRecord is one normalized vocabulary item from any ontology source. SourceName and SourceRecordID
// form the upsert key. Term is the canonical text, Code is the source's own identifier (a PSC code, a SOC
// code, a NICE element id), Category groups it, and Raw is the retained source payload.
type VocabRecord struct {
	SourceName     string
	SourceRecordID string
	Kind           TermKind
	Term           string
	Code           string
	Category       string
	Description    string
	Raw            json.RawMessage
}