breakpilot-compliance/ai-compliance-sdk/internal/ucca/control_mapping.go

package ucca

import (
	"bufio"
	"encoding/json"
	"fmt"
	"os"
	"path/filepath"
	"strings"
)

// ControlMapping is one persisted, versioned link from a legal obligation/requirement
// to a concrete framework control. The retriever only PROPOSES candidates
// (provenance=retriever_candidate); the curated mapping (human_curated/rule_based) is the
// audited truth the Advisor uses at runtime — never re-invented per query.
type ControlMapping struct {
	SourceNorm      string `json:"source_norm"`      // e.g. "CRA Annex I Part II"
	SourceRole      string `json:"source_role"`      // source_role of the norm (operational_requirement, ...)
	TargetFramework string `json:"target_framework"` // e.g. "OWASP ASVS"
	TargetControl   string `json:"target_control"`   // e.g. "V6.2.4"
	MappingType     string `json:"mapping_type"`     // supports | partially_supports | evidence_for | related
	Confidence      string `json:"confidence"`       // high | medium | low
	Provenance      string `json:"provenance"`       // retriever_candidate | human_curated | rule_based
	Rationale       string `json:"rationale"`
	Version         string `json:"version"` // YYYY-MM-DD
}

// Allowed enum values — the deterministic "rule" layer that keeps the curated store clean.
var (
	mappingTypeValues = map[string]bool{"supports": true, "partially_supports": true, "evidence_for": true, "related": true}
	confidenceValues  = map[string]bool{"high": true, "medium": true, "low": true}
	provenanceValues  = map[string]bool{"retriever_candidate": true, "human_curated": true, "rule_based": true}
)

// Validate checks required fields + enum membership, so the persisted audit store never
// holds garbage (fail-closed at load).
func (m ControlMapping) Validate() error {
	switch {
	case m.SourceNorm == "":
		return fmt.Errorf("control mapping: source_norm required")
	case m.TargetFramework == "":
		return fmt.Errorf("control mapping: target_framework required")
	case m.TargetControl == "":
		return fmt.Errorf("control mapping: target_control required")
	case !mappingTypeValues[m.MappingType]:
		return fmt.Errorf("control mapping: invalid mapping_type %q", m.MappingType)
	case !confidenceValues[m.Confidence]:
		return fmt.Errorf("control mapping: invalid confidence %q", m.Confidence)
	case !provenanceValues[m.Provenance]:
		return fmt.Errorf("control mapping: invalid provenance %q", m.Provenance)
	}
	return nil
}

// IsCurated reports whether this mapping is part of the audited truth (not a raw candidate).
func (m ControlMapping) IsCurated() bool {
	return m.Provenance == "human_curated" || m.Provenance == "rule_based"
}

// ControlMappingSet is the loaded, indexed mapping store (forward + reverse lookup).
type ControlMappingSet struct {
	All          []ControlMapping
	bySourceNorm map[string][]ControlMapping
	byControl    map[string][]ControlMapping
}

func controlKey(framework, control string) string { return framework + ":" + control }

// ControlsFor returns the controls mapped to a source norm. curatedOnly restricts to the
// audited truth (what the Advisor may treat as fact).
func (s *ControlMappingSet) ControlsFor(sourceNorm string, curatedOnly bool) []ControlMapping {
	return filterProvenance(s.bySourceNorm[sourceNorm], curatedOnly)
}

// ObligationsFor returns the norms mapped to a framework control (reverse lookup).
func (s *ControlMappingSet) ObligationsFor(framework, control string, curatedOnly bool) []ControlMapping {
	return filterProvenance(s.byControl[controlKey(framework, control)], curatedOnly)
}

func filterProvenance(in []ControlMapping, curatedOnly bool) []ControlMapping {
	if !curatedOnly {
		return in
	}
	out := make([]ControlMapping, 0, len(in))
	for _, m := range in {
		if m.IsCurated() {
			out = append(out, m)
		}
	}
	return out
}

// LoadControlMappings reads every *.jsonl file under dir (one mapping per line; blank and
// //-prefixed lines ignored), validates each row, and builds the index. An invalid row
// aborts the whole load — fail-closed, because this is the audit truth, not best-effort.
func LoadControlMappings(dir string) (*ControlMappingSet, error) {
	files, err := filepath.Glob(filepath.Join(dir, "*.jsonl"))
	if err != nil {
		return nil, err
	}
	set := &ControlMappingSet{
		bySourceNorm: map[string][]ControlMapping{},
		byControl:    map[string][]ControlMapping{},
	}
	for _, f := range files {
		fh, err := os.Open(f)
		if err != nil {
			return nil, err
		}
		sc := bufio.NewScanner(fh)
		sc.Buffer(make([]byte, 0, 64*1024), 1024*1024)
		line := 0
		for sc.Scan() {
			line++
			raw := strings.TrimSpace(sc.Text())
			if raw == "" || strings.HasPrefix(raw, "//") {
				continue
			}
			var m ControlMapping
			if err := json.Unmarshal([]byte(raw), &m); err != nil {
				fh.Close()
				return nil, fmt.Errorf("%s:%d: %w", f, line, err)
			}
			if err := m.Validate(); err != nil {
				fh.Close()
				return nil, fmt.Errorf("%s:%d: %w", f, line, err)
			}
			set.All = append(set.All, m)
			set.bySourceNorm[m.SourceNorm] = append(set.bySourceNorm[m.SourceNorm], m)
			k := controlKey(m.TargetFramework, m.TargetControl)
			set.byControl[k] = append(set.byControl[k], m)
		}
		fh.Close()
		if err := sc.Err(); err != nil {
			return nil, err
		}
	}
	return set, nil
}