Complete Phase 13 glossary module

2026-05-12 11:20:02 +00:00
parent fc3a7b7a67
commit 543a7ff8ef
14 changed files with 1049 additions and 97 deletions
--- a/internal/framework/validators/deterministic.go
+++ b/internal/framework/validators/deterministic.go
@@ -4,8 +4,6 @@ import (
 	"context"
 	"fmt"
 	"strings"
-
-	"gitea.maximumdirect.net/eric/audita/internal/framework/proposals"
 )

 type ConfidenceThresholdValidator struct{}
@@ -110,11 +108,12 @@ func (v ProtectedGlossaryTermValidator) Validate(_ context.Context, req Request)
 		return Result{ValidatorName: v.Name(), Decisions: decisions}, nil
 	}

-	terms := glossaryTerms(req)
+	vocab := NewProtectedVocabulary(req.Glossary)
 	decisions := make([]Decision, 0, len(req.CandidateProposal))
 	for _, c := range req.CandidateProposal {
-		if altersProtectedTerm(c.CorrectionProposal, terms) {
-			decisions = append(decisions, rejection(c.ProposalIndex, ReasonProtectedGlossaryTerm, "proposal may alter protected glossary terminology"))
+		reason := vocab.violationReason(c.OriginalText, c.CorrectedText)
+		if reason != "" {
+			decisions = append(decisions, rejection(c.ProposalIndex, ReasonProtectedGlossaryTerm, reason))
 			continue
 		}
 		decisions = append(decisions, approval(c.ProposalIndex))
@@ -125,37 +124,25 @@ func (v ProtectedGlossaryTermValidator) Validate(_ context.Context, req Request)
 	return Result{ValidatorName: v.Name(), Decisions: decisions}, nil
 }

-func glossaryTerms(req Request) []string {
-	if req.Glossary == nil {
-		return nil
-	}
-	out := make([]string, 0)
-	for _, e := range req.Glossary.Entries {
-		if t := strings.TrimSpace(strings.ToLower(e.Name)); t != "" {
-			out = append(out, t)
-		}
-		for _, a := range e.Aliases {
-			if t := strings.TrimSpace(strings.ToLower(a)); t != "" {
-				out = append(out, t)
-			}
-		}
-		if t := strings.TrimSpace(strings.ToLower(e.Plural)); t != "" {
-			out = append(out, t)
-		}
-	}
-	return out
+type GlossaryStageProtectedGlossaryTermValidator struct{}
+
+func (v GlossaryStageProtectedGlossaryTermValidator) Name() string {
+	return "glossary_stage_protected_glossary_terms"
 }

-func altersProtectedTerm(p proposals.CorrectionProposal, terms []string) bool {
-	if len(terms) == 0 {
-		return false
-	}
-	orig := strings.ToLower(p.OriginalText)
-	corr := strings.ToLower(p.CorrectedText)
-	for _, t := range terms {
-		if strings.Contains(orig, t) && !strings.Contains(corr, t) {
-			return true
+func (v GlossaryStageProtectedGlossaryTermValidator) Validate(_ context.Context, req Request) (Result, error) {
+	vocab := NewProtectedVocabulary(req.Glossary)
+	decisions := make([]Decision, 0, len(req.CandidateProposal))
+	for _, c := range req.CandidateProposal {
+		reason := vocab.glossaryStageViolationReason(c.OriginalText, c.CorrectedText)
+		if reason != "" {
+			decisions = append(decisions, rejection(c.ProposalIndex, ReasonProtectedGlossaryTerm, reason))
+			continue
 		}
+		decisions = append(decisions, approval(c.ProposalIndex))
 	}
-	return false
+	if err := EnforceDecisionCardinality(req.CandidateProposal, decisions); err != nil {
+		return Result{}, err
+	}
+	return Result{ValidatorName: v.Name(), Decisions: decisions}, nil
 }
--- a/internal/framework/validators/protected_terms.go
+++ b/internal/framework/validators/protected_terms.go
@@ -0,0 +1,188 @@
+package validators
+
+import (
+	"regexp"
+	"sort"
+	"strings"
+
+	"gitea.maximumdirect.net/eric/audita/internal/core/schema"
+)
+
+type protectedTermDef struct {
+	identity  int
+	canonical string
+}
+
+type protectedOccurrence struct {
+	text      string
+	identity  int
+	canonical string
+}
+
+// ProtectedVocabulary is a deterministic glossary-derived protected term set.
+type ProtectedVocabulary struct {
+	termsByFolded map[string]protectedTermDef
+	pattern       *regexp.Regexp
+}
+
+// ExtractProtectedTerms returns a stable, de-duplicated list of protected terms
+// derived from glossary names, aliases, synthetic plural forms, and explicit
+// plural fields.
+func ExtractProtectedTerms(glossary *schema.Glossary) []string {
+	vocab := NewProtectedVocabulary(glossary)
+	out := make([]string, 0, len(vocab.termsByFolded))
+	for _, def := range vocab.termsByFolded {
+		out = append(out, def.canonical)
+	}
+	sort.SliceStable(out, func(i, j int) bool {
+		li := strings.ToLower(out[i])
+		lj := strings.ToLower(out[j])
+		if li == lj {
+			return out[i] < out[j]
+		}
+		return li < lj
+	})
+	return out
+}
+
+// NewProtectedVocabulary builds a deterministic protected vocabulary from a glossary.
+func NewProtectedVocabulary(glossary *schema.Glossary) ProtectedVocabulary {
+	termsByFolded := make(map[string]protectedTermDef)
+	if glossary != nil {
+		for identity, entry := range glossary.Entries {
+			entryTerms := append([]string{entry.Name}, entry.Aliases...)
+			for _, term := range entryTerms {
+				trimmed := strings.TrimSpace(term)
+				if trimmed == "" {
+					continue
+				}
+				addProtectedTerm(termsByFolded, trimmed, identity)
+				addProtectedTerm(termsByFolded, trimmed+"s", identity)
+			}
+			addProtectedTerm(termsByFolded, entry.Plural, identity)
+		}
+	}
+
+	alternatives := make([]string, 0, len(termsByFolded))
+	for _, def := range termsByFolded {
+		alternatives = append(alternatives, regexp.QuoteMeta(def.canonical))
+	}
+	sort.SliceStable(alternatives, func(i, j int) bool { return len(alternatives[i]) > len(alternatives[j]) })
+	if len(alternatives) == 0 {
+		return ProtectedVocabulary{termsByFolded: termsByFolded}
+	}
+	pattern := regexp.MustCompile(`(?i)\b(?:` + strings.Join(alternatives, "|") + `)\b`)
+	return ProtectedVocabulary{termsByFolded: termsByFolded, pattern: pattern}
+}
+
+func addProtectedTerm(terms map[string]protectedTermDef, term string, identity int) {
+	trimmed := strings.TrimSpace(term)
+	if trimmed == "" {
+		return
+	}
+	folded := strings.ToLower(trimmed)
+	if _, ok := terms[folded]; ok {
+		return
+	}
+	terms[folded] = protectedTermDef{identity: identity, canonical: trimmed}
+}
+
+func (v ProtectedVocabulary) violationReason(before, after string) string {
+	beforeByID := v.occurrencesByIdentity(before)
+	afterByID := v.occurrencesByIdentity(after)
+	if reason := validateIdentityPreservation(beforeByID, afterByID); reason != "" {
+		return reason
+	}
+	if reason := validateCapitalizationTransitions(beforeByID, afterByID); reason != "" {
+		return reason
+	}
+	return ""
+}
+
+func (v ProtectedVocabulary) glossaryStageViolationReason(before, after string) string {
+	beforeByID := v.occurrencesByIdentity(before)
+	afterByID := v.occurrencesByIdentity(after)
+	if reason := validateGlossaryStageIdentityPreservation(beforeByID, afterByID); reason != "" {
+		return reason
+	}
+	if reason := validateCapitalizationTransitions(beforeByID, afterByID); reason != "" {
+		return reason
+	}
+	return ""
+}
+
+func (v ProtectedVocabulary) occurrencesByIdentity(text string) map[int][]protectedOccurrence {
+	byID := make(map[int][]protectedOccurrence)
+	for _, o := range v.occurrences(text) {
+		byID[o.identity] = append(byID[o.identity], o)
+	}
+	return byID
+}
+
+func (v ProtectedVocabulary) occurrences(text string) []protectedOccurrence {
+	if v.pattern == nil {
+		return nil
+	}
+	matches := v.pattern.FindAllStringIndex(text, -1)
+	if len(matches) == 0 {
+		return nil
+	}
+	out := make([]protectedOccurrence, 0, len(matches))
+	for _, idx := range matches {
+		matched := text[idx[0]:idx[1]]
+		def, ok := v.termsByFolded[strings.ToLower(matched)]
+		if !ok {
+			continue
+		}
+		out = append(out, protectedOccurrence{
+			text:      matched,
+			identity:  def.identity,
+			canonical: def.canonical,
+		})
+	}
+	return out
+}
+
+func validateIdentityPreservation(beforeByID, afterByID map[int][]protectedOccurrence) string {
+	for identity, beforeItems := range beforeByID {
+		if len(afterByID[identity]) < len(beforeItems) {
+			return "proposal may alter protected glossary terminology"
+		}
+	}
+	return ""
+}
+
+func validateGlossaryStageIdentityPreservation(beforeByID, afterByID map[int][]protectedOccurrence) string {
+	beforeTotal := 0
+	for _, items := range beforeByID {
+		beforeTotal += len(items)
+	}
+	afterTotal := 0
+	for _, items := range afterByID {
+		afterTotal += len(items)
+	}
+	if afterTotal < beforeTotal {
+		return "proposal may alter protected glossary terminology"
+	}
+	return ""
+}
+
+func validateCapitalizationTransitions(beforeByID, afterByID map[int][]protectedOccurrence) string {
+	for identity, afterItems := range afterByID {
+		beforeItems := beforeByID[identity]
+		for i, afterItem := range afterItems {
+			if i >= len(beforeItems) {
+				continue
+			}
+			beforeItem := beforeItems[i]
+			if afterItem.text == beforeItem.text {
+				continue
+			}
+			if afterItem.text == afterItem.canonical {
+				continue
+			}
+			return "proposal may alter protected glossary terminology"
+		}
+	}
+	return ""
+}
--- a/internal/framework/validators/protected_terms_test.go
+++ b/internal/framework/validators/protected_terms_test.go
@@ -0,0 +1,86 @@
+package validators
+
+import (
+	"context"
+	"reflect"
+	"testing"
+
+	"gitea.maximumdirect.net/eric/audita/internal/core/schema"
+	"gitea.maximumdirect.net/eric/audita/internal/framework/proposals"
+)
+
+func TestExtractProtectedTermsStableDeduplicatedWithPlurals(t *testing.T) {
+	glossary := &schema.Glossary{
+		Entries: []schema.GlossaryEntry{
+			{Name: "Jesters", Aliases: []string{"Jester", "  "}, Plural: "Jesters", Category: "faction", Summary: "Faction"},
+			{Name: "Hrank", Aliases: []string{"hrank", "Hrank"}, Plural: "Hranks", Category: "pc", Summary: "Character"},
+			{Name: "Lyra", Aliases: []string{}, Plural: "", Category: "npc", Summary: "NPC"},
+		},
+	}
+
+	got := ExtractProtectedTerms(glossary)
+	want := []string{"Hrank", "Hranks", "Jester", "Jesters", "Jesterss", "Lyra", "Lyras"}
+	if !reflect.DeepEqual(got, want) {
+		t.Fatalf("unexpected protected terms\n got: %v\nwant: %v", got, want)
+	}
+}
+
+func TestExtractProtectedTermsEmptyGlossary(t *testing.T) {
+	if terms := ExtractProtectedTerms(&schema.Glossary{}); len(terms) != 0 {
+		t.Fatalf("expected no terms, got %v", terms)
+	}
+}
+
+func TestProtectedGlossaryTermValidatorAppliesToNonGlossaryModule(t *testing.T) {
+	req := Request{
+		ModuleKey: "grammar",
+		Glossary: &schema.Glossary{
+			Entries: []schema.GlossaryEntry{{Name: "Jesters", Category: "faction", Summary: "Faction"}},
+		},
+		CandidateProposal: []proposals.EnrichedCorrectionProposal{
+			{
+				CorrectionProposal: proposals.CorrectionProposal{
+					TargetSegmentID: 1,
+					OriginalText:    "Jesters",
+					CorrectedText:   "Gestures",
+					Confidence:      0.9,
+				},
+				ProposalMetadata: proposals.ProposalMetadata{ProposalIndex: 0},
+			},
+		},
+	}
+	res, err := (ProtectedGlossaryTermValidator{}).Validate(context.Background(), req)
+	if err != nil {
+		t.Fatalf("validator error: %v", err)
+	}
+	if len(res.Decisions) != 1 || res.Decisions[0].Approved {
+		t.Fatalf("expected protected-term rejection, got %+v", res.Decisions)
+	}
+}
+
+func TestGlossaryStageProtectedGlossaryTermValidatorAllowsProtectedTermSwap(t *testing.T) {
+	req := Request{
+		ModuleKey: "glossary",
+		Glossary: &schema.Glossary{
+			Entries: []schema.GlossaryEntry{{Name: "Jesters", Category: "faction", Summary: "Faction"}},
+		},
+		CandidateProposal: []proposals.EnrichedCorrectionProposal{
+			{
+				CorrectionProposal: proposals.CorrectionProposal{
+					TargetSegmentID: 1,
+					OriginalText:    "gestures",
+					CorrectedText:   "Jesters",
+					Confidence:      0.9,
+				},
+				ProposalMetadata: proposals.ProposalMetadata{ProposalIndex: 0},
+			},
+		},
+	}
+	res, err := (GlossaryStageProtectedGlossaryTermValidator{}).Validate(context.Background(), req)
+	if err != nil {
+		t.Fatalf("validator error: %v", err)
+	}
+	if len(res.Decisions) != 1 || !res.Decisions[0].Approved {
+		t.Fatalf("expected approval for glossary-stage protected term correction, got %+v", res.Decisions)
+	}
+}