Replace evidence context with source unit excerpts

This commit is contained in:
2026-08-09 19:42:33 +00:00
parent ad1cba41c2
commit 071a78ae22
10 changed files with 650 additions and 584 deletions

View File

@@ -6,7 +6,6 @@ import (
"encoding/json"
"fmt"
"io"
"regexp"
"strings"
"sync"
@@ -18,8 +17,6 @@ import (
//go:embed assets/schemas/source_evidence_context.v1.json
var schemaAssets embed.FS
var digestPattern = regexp.MustCompile(`^sha256:[0-9a-f]{64}$`)
var (
loadSchemaOnce sync.Once
loadedSchema []byte
@@ -78,24 +75,24 @@ func (c *Codec) Encode(value Document) ([]byte, error) {
func (c *Codec) Decode(content []byte) (Document, error) {
if _, err := c.schemaBytes(); err != nil {
return Document{}, err
return nil, err
}
if err := validateSchemaInstance(content); err != nil {
return Document{}, fmt.Errorf("decode evidence context: %w", err)
return nil, fmt.Errorf("decode evidence context: %w", err)
}
decoder := json.NewDecoder(bytes.NewReader(content))
decoder.DisallowUnknownFields()
var value Document
if err := decoder.Decode(&value); err != nil {
return Document{}, fmt.Errorf("decode evidence context: %w", err)
return nil, fmt.Errorf("decode evidence context: %w", err)
}
var trailing any
if err := decoder.Decode(&trailing); err != io.EOF {
return Document{}, fmt.Errorf("decode evidence context: multiple JSON values")
return nil, fmt.Errorf("decode evidence context: multiple JSON values")
}
canonical, err := canonicalizeOwned(value)
if err != nil {
return Document{}, fmt.Errorf("decode evidence context: %w", err)
return nil, fmt.Errorf("decode evidence context: %w", err)
}
return canonical, nil
}
@@ -115,17 +112,16 @@ func loadAndCompileSchema() {
return
}
var identity struct {
ID string `json:"$id"`
Title string `json:"title"`
Type string `json:"type"`
Required []string `json:"required"`
ID string `json:"$id"`
Title string `json:"title"`
Type string `json:"type"`
}
if err := json.Unmarshal(raw, &identity); err != nil {
loadSchemaErr = fmt.Errorf("decode source evidence context schema: %w", err)
return
}
if identity.ID != SchemaID || identity.Title != SchemaName || identity.Type != "object" || !hasRequiredFields(identity.Required) {
loadSchemaErr = fmt.Errorf("source evidence context schema identity or required fields are invalid")
if identity.ID != SchemaID || identity.Title != SchemaName || identity.Type != "array" {
loadSchemaErr = fmt.Errorf("source evidence context schema identity is invalid")
return
}
schemaDocument, err := jsonschema.UnmarshalJSON(bytes.NewReader(raw))
@@ -158,164 +154,59 @@ func validateSchemaInstance(content []byte) error {
return nil
}
func hasRequiredFields(required []string) bool {
want := map[string]bool{"source_id": true, "source_digest": true, "window_units": true, "selected_lanes": true, "contexts": true}
for _, field := range required {
delete(want, field)
}
return len(want) == 0
}
func canonicalize(value Document) (Document, error) {
owned, err := clone(value)
if err != nil {
return Document{}, err
return nil, err
}
return canonicalizeOwned(owned)
}
func canonicalizeOwned(value Document) (Document, error) {
if err := requireIdentity("source_id", value.SourceID); err != nil {
return Document{}, err
if value == nil {
return nil, fmt.Errorf("document must be a JSON array")
}
if !digestPattern.MatchString(value.SourceDigest) {
return Document{}, fmt.Errorf("source_digest must be a sha256 digest")
}
if value.WindowUnits < 0 {
return Document{}, fmt.Errorf("window_units must not be negative")
}
if err := validateSelectedLanes(value.SelectedLanes); err != nil {
return Document{}, err
}
if value.Contexts == nil {
value.Contexts = make([]Context, 0)
}
selected := make(map[string]struct{}, len(value.SelectedLanes))
for _, laneID := range value.SelectedLanes {
selected[laneID] = struct{}{}
}
seenUnits := make(map[int]struct{})
for contextIndex := range value.Contexts {
context, err := canonicalizeContext(value.SourceID, selected, seenUnits, value.Contexts[contextIndex], contextIndex)
if err != nil {
return Document{}, err
}
value.Contexts[contextIndex] = context
}
return value, nil
}
func validateSelectedLanes(lanes []string) error {
if len(lanes) == 0 {
return fmt.Errorf("selected_lanes must not be empty")
}
for index, laneID := range lanes {
if err := requireIdentity(fmt.Sprintf("selected_lanes[%d]", index), laneID); err != nil {
return err
}
if index > 0 && lanes[index-1] >= laneID {
return fmt.Errorf("selected_lanes must be unique and in lexical order")
}
}
return nil
}
func canonicalizeContext(sourceID string, selected map[string]struct{}, seenUnits map[int]struct{}, value Context, contextIndex int) (Context, error) {
prefix := fmt.Sprintf("contexts[%d]", contextIndex)
if len(value.EvidenceRefs) == 0 {
return Context{}, fmt.Errorf("%s.evidence_refs must not be empty", prefix)
}
if len(value.Units) == 0 {
return Context{}, fmt.Errorf("%s.units must not be empty", prefix)
}
if err := validateRefIdentity(sourceID, value.ContextRef, prefix+".context_ref"); err != nil {
return Context{}, err
}
positions := make(map[int]int, len(value.Units))
for unitIndex := range value.Units {
unit := value.Units[unitIndex]
seenUnitIDs := make(map[int]struct{}, len(value))
for unitIndex := range value {
unit := value[unitIndex]
if unit.ID <= 0 || strings.TrimSpace(unit.Kind) == "" || strings.TrimSpace(unit.Text) == "" {
return Context{}, fmt.Errorf("%s.units[%d] has invalid required fields", prefix, unitIndex)
return nil, fmt.Errorf("units[%d] has invalid required fields", unitIndex)
}
if err := validateRefIdentity(sourceID, unit.Ref, fmt.Sprintf("%s.units[%d].ref", prefix, unitIndex)); err != nil {
return Context{}, err
if err := validateUnitRef(unit, unitIndex); err != nil {
return nil, err
}
if unit.Ref.StartUnitID != unit.ID || unit.Ref.EndUnitID != unit.ID {
return Context{}, fmt.Errorf("%s.units[%d].ref must identify unit id %d", prefix, unitIndex, unit.ID)
}
if _, exists := positions[unit.ID]; exists {
return Context{}, fmt.Errorf("%s.units contains duplicate unit id %d", prefix, unit.ID)
}
if _, exists := seenUnits[unit.ID]; exists {
return Context{}, fmt.Errorf("contexts contain duplicate unit id %d", unit.ID)
}
positions[unit.ID] = unitIndex
seenUnits[unit.ID] = struct{}{}
}
if value.ContextRef.StartUnitID != value.Units[0].ID || value.ContextRef.EndUnitID != value.Units[len(value.Units)-1].ID {
return Context{}, fmt.Errorf("%s.context_ref must identify the first and last units", prefix)
}
for evidenceIndex := range value.EvidenceRefs {
evidence := value.EvidenceRefs[evidenceIndex]
if _, ok := selected[evidence.LaneID]; !ok {
return Context{}, fmt.Errorf("%s.evidence_refs[%d].lane_id is not selected", prefix, evidenceIndex)
}
if err := requireIdentity(fmt.Sprintf("%s.evidence_refs[%d].lane_id", prefix, evidenceIndex), evidence.LaneID); err != nil {
return Context{}, err
}
if err := validateRefIdentity(sourceID, evidence.SourceRef, fmt.Sprintf("%s.evidence_refs[%d].source_ref", prefix, evidenceIndex)); err != nil {
return Context{}, err
}
start, startOK := positions[evidence.SourceRef.StartUnitID]
end, endOK := positions[evidence.SourceRef.EndUnitID]
if !startOK || !endOK || start > end {
return Context{}, fmt.Errorf("%s.evidence_refs[%d].source_ref is outside context units", prefix, evidenceIndex)
}
if evidenceIndex > 0 && !lessEvidenceRef(value.EvidenceRefs[evidenceIndex-1], evidence) {
return Context{}, fmt.Errorf("%s.evidence_refs must be unique and in deterministic order", prefix)
if _, exists := seenUnitIDs[unit.ID]; exists {
return nil, fmt.Errorf("units contains duplicate unit id %d", unit.ID)
}
seenUnitIDs[unit.ID] = struct{}{}
}
return value, nil
}
func validateRefIdentity(sourceID string, ref source.SourceRef, field string) error {
if ref.SourceID != sourceID {
return fmt.Errorf("%s.source_id does not match source_id", field)
func validateUnitRef(unit source.SourceUnit, unitIndex int) error {
prefix := fmt.Sprintf("units[%d].ref", unitIndex)
if strings.TrimSpace(unit.Ref.SourceID) == "" || strings.TrimSpace(unit.Ref.SourceID) != unit.Ref.SourceID {
return fmt.Errorf("%s.source_id must be a non-empty trimmed string", prefix)
}
if ref.StartUnitID <= 0 || ref.EndUnitID <= 0 {
return fmt.Errorf("%s endpoints must be positive", field)
}
return nil
}
func requireIdentity(field, value string) error {
if strings.TrimSpace(value) == "" || strings.TrimSpace(value) != value {
return fmt.Errorf("%s must be a non-empty trimmed string", field)
if unit.Ref.StartUnitID != unit.ID || unit.Ref.EndUnitID != unit.ID {
return fmt.Errorf("%s must identify unit id %d", prefix, unit.ID)
}
return nil
}
func clone(value Document) (Document, error) {
value.SelectedLanes = append([]string(nil), value.SelectedLanes...)
if value.Contexts == nil {
value.Contexts = make([]Context, 0)
} else {
contexts := make([]Context, len(value.Contexts))
for contextIndex, context := range value.Contexts {
contexts[contextIndex].ContextRef = context.ContextRef
contexts[contextIndex].EvidenceRefs = append([]EvidenceRef(nil), context.EvidenceRefs...)
contexts[contextIndex].Units = make([]source.SourceUnit, len(context.Units))
for unitIndex, unit := range context.Units {
cloned, err := cloneSourceUnit(unit)
if err != nil {
return Document{}, fmt.Errorf("clone contexts[%d].units[%d]: %w", contextIndex, unitIndex, err)
}
contexts[contextIndex].Units[unitIndex] = cloned
}
}
value.Contexts = contexts
if value == nil {
return nil, nil
}
return value, nil
cloned := make(Document, len(value))
for unitIndex, unit := range value {
owned, err := cloneSourceUnit(unit)
if err != nil {
return nil, fmt.Errorf("clone units[%d]: %w", unitIndex, err)
}
cloned[unitIndex] = owned
}
return cloned, nil
}
func cloneSourceUnit(unit source.SourceUnit) (source.SourceUnit, error) {