Add standalone D&D combat turn extraction

internal/modules/dnd/validate/combatturns/source_relatedness/validator.go

@@ -0,0 +1,156 @@
+package sourcerelatedness
+
+import (
+	"context"
+	"fmt"
+	"strings"
+	"unicode"
+	"unicode/utf8"
+
+	"gitea.maximumdirect.net/eric/notarius/internal/core/source"
+	"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
+	"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
+	"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd"
+	"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/npcs/identity"
+	"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/shared/diagnostics"
+	combatshape "gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/validate/combatturns/shape"
+)
+
+const (
+	Key               = "extract/dnd/combat-turns/source_relatedness"
+	WarningReasonCode = "combat_turn_not_near_source"
+	policy            = "dnd.combat_turns.validator.source_relatedness.v1"
+)
+
+type Options struct{}
+type Validator struct{}
+
+var _ contracts.TypedValidator[dnd.CombatTurnList] = (*Validator)(nil)
+var _ pipeline.CheckpointFingerprintProvider = (*Validator)(nil)
+
+func New(Options) *Validator      { return &Validator{} }
+func (v *Validator) Name() string { return Key }
+func (v *Validator) ExecutionClass() contracts.ExecutionClass {
+	return contracts.ExecutionClassDeterministic
+}
+func (v *Validator) CheckpointFingerprints() []pipeline.CheckpointFingerprint {
+	return []pipeline.CheckpointFingerprint{{Name: "policy", Value: policy}}
+}
+
+func (v *Validator) Validate(_ context.Context, req contracts.TypedValidationRequest[dnd.CombatTurnList]) (contracts.ValidationResult, error) {
+	if combatshape.Validate(req.Value) != nil || !sourceRefsValid(req.Source, req.Value) {
+		return contracts.ValidationResult{Approved: true}, nil
+	}
+
+	warnings := make([]contracts.Warning, 0)
+	for turnIndex, turn := range req.Value.CombatTurns {
+		citedText := citedTextKey(req.Source, turn.SourceRefs)
+		issues := make([]string, 0)
+		if !actorAppearsInCitedText(citedText, turn.Actor) {
+			issues = append(issues, fmt.Sprintf("actor %s was not found in cited source text", diagnostics.Quote(turn.Actor)))
+		}
+		for actionIndex, action := range turn.Actions {
+			if !declarationAppearsInCitedText(citedText, action.Declaration) {
+				issues = append(issues, fmt.Sprintf("action %d declaration %s was not found in cited source text", actionIndex, diagnostics.Quote(action.Declaration)))
+			}
+		}
+		if len(issues) == 0 {
+			continue
+		}
+		warnings = append(warnings, contracts.Warning{
+			Scope:      fmt.Sprintf("combat_turns[%d]", turnIndex),
+			ReasonCode: WarningReasonCode,
+			Message:    diagnostics.Aggregate("combat turn not near source", issues),
+		})
+	}
+	return contracts.ValidationResult{Approved: true, Warnings: warnings}, nil
+}
+
+func sourceRefsValid(doc *source.SourceDocument, value dnd.CombatTurnList) bool {
+	for _, turn := range value.CombatTurns {
+		for _, ref := range turn.SourceRefs {
+			if source.ValidateRef(doc, ref) != nil {
+				return false
+			}
+		}
+	}
+	return true
+}
+
+func citedTextKey(doc *source.SourceDocument, refs []source.SourceRef) string {
+	if doc == nil {
+		return ""
+	}
+	included := make([]bool, len(doc.Units))
+	for _, ref := range refs {
+		start, _ := source.UnitIndex(doc, ref.StartUnitID)
+		end, _ := source.UnitIndex(doc, ref.EndUnitID)
+		for index := start; index <= end && index < len(included); index++ {
+			included[index] = true
+		}
+	}
+	parts := make([]string, 0)
+	for index, unit := range doc.Units {
+		if included[index] {
+			parts = append(parts, unit.Text)
+		}
+	}
+	return identity.ComparisonKey(strings.Join(parts, " "))
+}
+
+func actorAppearsInCitedText(citedText string, actor string) bool {
+	key := identity.ComparisonKey(actor)
+	return key != "" && strings.Contains(citedText, key)
+}
+
+func declarationAppearsInCitedText(citedText string, declaration string) bool {
+	citedTokens := tokenSet(citedText)
+	for _, token := range comparisonTokens(declaration) {
+		if utf8.RuneCountInString(token) >= 4 {
+			if _, ok := citedTokens[token]; ok {
+				return true
+			}
+		}
+	}
+	return false
+}
+
+func comparisonTokens(value string) []string {
+	value = identity.ComparisonKey(value)
+	if value == "" {
+		return nil
+	}
+	return strings.FieldsFunc(value, func(r rune) bool { return !unicode.IsLetter(r) && !unicode.IsDigit(r) })
+}
+
+func tokenSet(value string) map[string]struct{} {
+	tokens := comparisonTokens(value)
+	set := make(map[string]struct{}, len(tokens))
+	for _, token := range tokens {
+		set[token] = struct{}{}
+	}
+	return set
+}
+
+func Spec() pipeline.ValidatorSpec {
+	return pipeline.ValidatorSpec{Key: Key, ExecutionClass: contracts.ExecutionClassDeterministic}
+}
+
+func Register(registry *pipeline.ValidatorRegistry) error {
+	return pipeline.RegisterTypedValidatorBuilder(registry, dnd.CombatTurnListKind, Spec(), validateOptions, func(request pipeline.BuildRequest) (contracts.TypedValidator[dnd.CombatTurnList], error) {
+		options, err := DecodeOptions(request.Options)
+		if err != nil {
+			return nil, err
+		}
+		return New(options), nil
+	})
+}
+
+func DecodeOptions(options map[string]any) (Options, error) {
+	if err := pipeline.RejectUnknownOptions(options); err != nil {
+		return Options{}, err
+	}
+	return Options{}, nil
+}
+
+func validateOptions(options map[string]any) error { _, err := DecodeOptions(options); return err }