Complete Phase 8 deterministic validators

internal/framework/validators/deterministic.go

@@ -0,0 +1,161 @@
+package validators
+
+import (
+	"context"
+	"fmt"
+	"strings"
+
+	"gitea.maximumdirect.net/eric/audita/internal/framework/proposals"
+)
+
+type ConfidenceThresholdValidator struct{}
+
+func (v ConfidenceThresholdValidator) Name() string { return "confidence_threshold" }
+
+func (v ConfidenceThresholdValidator) Validate(_ context.Context, req Request) (Result, error) {
+	threshold := confidenceThresholdForModule(req.ModuleKey, req.Config)
+	decisions := make([]Decision, 0, len(req.CandidateProposal))
+	for _, c := range req.CandidateProposal {
+		if c.Confidence < threshold {
+			decisions = append(decisions, rejection(c.ProposalIndex, ReasonLowConfidence, fmt.Sprintf("confidence %.4f below threshold %.4f", c.Confidence, threshold)))
+			continue
+		}
+		decisions = append(decisions, approval(c.ProposalIndex))
+	}
+	if err := EnforceDecisionCardinality(req.CandidateProposal, decisions); err != nil {
+		return Result{}, err
+	}
+	return Result{ValidatorName: v.Name(), Decisions: decisions}, nil
+}
+
+type OriginalTextPresenceValidator struct{}
+
+func (v OriginalTextPresenceValidator) Name() string { return "original_text_presence" }
+
+func (v OriginalTextPresenceValidator) Validate(_ context.Context, req Request) (Result, error) {
+	byID := make(map[int]string)
+	if req.WorkingTranscript != nil {
+		for _, seg := range req.WorkingTranscript.Segments {
+			byID[seg.ID] = seg.Text
+		}
+	}
+
+	decisions := make([]Decision, 0, len(req.CandidateProposal))
+	for _, c := range req.CandidateProposal {
+		text, ok := byID[c.TargetSegmentID]
+		if !ok {
+			decisions = append(decisions, rejection(c.ProposalIndex, ReasonMissingTargetSegment, "target segment was not found"))
+			continue
+		}
+		if !strings.Contains(text, c.OriginalText) {
+			decisions = append(decisions, rejection(c.ProposalIndex, ReasonMissingOriginalText, "original_text was not found in current segment text"))
+			continue
+		}
+		decisions = append(decisions, approval(c.ProposalIndex))
+	}
+	if err := EnforceDecisionCardinality(req.CandidateProposal, decisions); err != nil {
+		return Result{}, err
+	}
+	return Result{ValidatorName: v.Name(), Decisions: decisions}, nil
+}
+
+type NonEmptyCorrectionValidator struct{}
+
+func (v NonEmptyCorrectionValidator) Name() string { return "non_empty_correction" }
+
+func (v NonEmptyCorrectionValidator) Validate(_ context.Context, req Request) (Result, error) {
+	decisions := make([]Decision, 0, len(req.CandidateProposal))
+	for _, c := range req.CandidateProposal {
+		if strings.TrimSpace(c.CorrectedText) == "" {
+			decisions = append(decisions, rejection(c.ProposalIndex, ReasonEmptyCorrectedText, "corrected_text must not be empty"))
+			continue
+		}
+		decisions = append(decisions, approval(c.ProposalIndex))
+	}
+	if err := EnforceDecisionCardinality(req.CandidateProposal, decisions); err != nil {
+		return Result{}, err
+	}
+	return Result{ValidatorName: v.Name(), Decisions: decisions}, nil
+}
+
+type NoEffectValidator struct{}
+
+func (v NoEffectValidator) Name() string { return "no_effect" }
+
+func (v NoEffectValidator) Validate(_ context.Context, req Request) (Result, error) {
+	decisions := make([]Decision, 0, len(req.CandidateProposal))
+	for _, c := range req.CandidateProposal {
+		if c.OriginalText == c.CorrectedText {
+			decisions = append(decisions, rejection(c.ProposalIndex, ReasonNoEffect, "original_text and corrected_text are identical"))
+			continue
+		}
+		decisions = append(decisions, approval(c.ProposalIndex))
+	}
+	if err := EnforceDecisionCardinality(req.CandidateProposal, decisions); err != nil {
+		return Result{}, err
+	}
+	return Result{ValidatorName: v.Name(), Decisions: decisions}, nil
+}
+
+type ProtectedGlossaryTermValidator struct{}
+
+func (v ProtectedGlossaryTermValidator) Name() string { return "protected_glossary_terms" }
+
+func (v ProtectedGlossaryTermValidator) Validate(_ context.Context, req Request) (Result, error) {
+	if req.ModuleKey == "glossary" {
+		decisions := make([]Decision, 0, len(req.CandidateProposal))
+		for _, c := range req.CandidateProposal {
+			decisions = append(decisions, approval(c.ProposalIndex))
+		}
+		return Result{ValidatorName: v.Name(), Decisions: decisions}, nil
+	}
+
+	terms := glossaryTerms(req)
+	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"))
+			continue
+		}
+		decisions = append(decisions, approval(c.ProposalIndex))
+	}
+	if err := EnforceDecisionCardinality(req.CandidateProposal, decisions); err != nil {
+		return Result{}, err
+	}
+	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
+}
+
+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
+		}
+	}
+	return false
+}