Files
narratio/internal/stage/prepare.go

517 lines
16 KiB
Go

package stage
import (
"context"
"crypto/sha256"
"encoding/hex"
"fmt"
"os"
"path"
"path/filepath"
"sort"
"strings"
"gitea.maximumdirect.net/eric/narratio/internal/adapters/storage"
"gitea.maximumdirect.net/eric/narratio/internal/artifacts"
"gitea.maximumdirect.net/eric/narratio/internal/config"
"gitea.maximumdirect.net/eric/narratio/internal/manifest"
"gopkg.in/yaml.v3"
)
type prepareStage struct{}
func (prepareStage) Name() string { return "prepare" }
func (prepareStage) Declares() IODecl {
return IODecl{
Inputs: []artifacts.Ref{
{Kind: "config", Category: "inputs", RelativePath: "session.yml"},
{Kind: "config", Category: "inputs", RelativePath: "pipeline.resolved.yml"},
{Kind: "config", Category: "inputs", RelativePath: "speakers.yml"},
{Kind: "config", Category: "inputs", RelativePath: "autocorrect.yml"},
{Kind: "config", Category: "inputs", RelativePath: "glossary.yml"},
{Kind: "audio", Category: "audio", RelativePath: "*.flac"},
},
}
}
func (prepareStage) Run(ctx context.Context, env *Env, m *manifest.Manifest) (*StageResult, error) {
if env == nil || env.Config == nil {
return nil, fmt.Errorf("prepare: stage environment config is required")
}
if env.ArtifactStore == nil {
return nil, fmt.Errorf("prepare: artifact store is required")
}
if env.Config.Session == nil || env.Config.Pipeline == nil {
return nil, fmt.Errorf("prepare: resolved config must include pipeline and session")
}
sessionID := strings.TrimSpace(m.SessionID)
if sessionID == "" {
sessionID = strings.TrimSpace(env.Config.Session.SessionID)
}
if sessionID == "" {
return nil, fmt.Errorf("prepare: session id is required")
}
paths, err := ensureLayoutForEnv(env, sessionID)
if err != nil {
return nil, fmt.Errorf("prepare: ensure workdir layout: %w", err)
}
sessionSrc := env.Config.SessionPath
if err := requireFile(sessionSrc, "session.yml"); err != nil {
return nil, fmt.Errorf("prepare: %w", err)
}
sessionDir := filepath.Dir(sessionSrc)
speakersSrc, err := resolvePath(sessionDir, env.Config.Session.Inputs.SpeakersFile)
if err != nil {
return nil, fmt.Errorf("prepare: speakers path: %w", err)
}
autocorrectSrc, err := resolvePath(sessionDir, env.Config.Session.Inputs.AutocorrectFile)
if err != nil {
return nil, fmt.Errorf("prepare: autocorrect path: %w", err)
}
glossarySrc, err := resolvePath(sessionDir, env.Config.Session.Inputs.GlossaryFile)
if err != nil {
return nil, fmt.Errorf("prepare: glossary path: %w", err)
}
for _, required := range []struct {
path string
name string
}{
{path: speakersSrc, name: "speakers.yml"},
{path: autocorrectSrc, name: "autocorrect.yml"},
{path: glossarySrc, name: "glossary.yml"},
} {
if err := requireFile(required.path, required.name); err != nil {
return nil, fmt.Errorf("prepare: %w", err)
}
}
resolvedLocalAudio, useS3Audio, err := resolveAudioInputs(sessionDir, env.Config.Session.Inputs)
if err != nil {
return nil, fmt.Errorf("prepare: resolve audio inputs: %w", err)
}
inputs := make([]manifest.InputRecord, 0, 5+len(resolvedLocalAudio))
registerInput := func(kind, path, checksum string) {
inputs = append(inputs, manifest.InputRecord{Kind: kind, Path: path, Checksum: checksum})
}
sessionDst := filepath.Join(paths.InputsDir, "session.yml")
sessionChecksum, err := copyFileIfChanged(env.ArtifactStore, sessionSrc, sessionDst)
if err != nil {
return nil, fmt.Errorf("prepare: materialize session.yml: %w", err)
}
registerInput("session_config", sessionDst, sessionChecksum)
pipelineResolvedBytes, err := renderResolvedPipeline(env.Config.Pipeline)
if err != nil {
return nil, fmt.Errorf("prepare: render pipeline.resolved.yml: %w", err)
}
pipelineDst := filepath.Join(paths.InputsDir, "pipeline.resolved.yml")
pipelineChecksum, err := writeBytesIfChanged(env.ArtifactStore, pipelineDst, pipelineResolvedBytes)
if err != nil {
return nil, fmt.Errorf("prepare: materialize pipeline.resolved.yml: %w", err)
}
registerInput("pipeline_resolved", pipelineDst, pipelineChecksum)
for _, cfgFile := range []struct {
kind string
src string
dst string
}{
{kind: "speakers", src: speakersSrc, dst: filepath.Join(paths.InputsDir, "speakers.yml")},
{kind: "autocorrect", src: autocorrectSrc, dst: filepath.Join(paths.InputsDir, "autocorrect.yml")},
{kind: "glossary", src: glossarySrc, dst: filepath.Join(paths.InputsDir, "glossary.yml")},
} {
checksum, err := copyFileIfChanged(env.ArtifactStore, cfgFile.src, cfgFile.dst)
if err != nil {
return nil, fmt.Errorf("prepare: materialize %s: %w", cfgFile.kind, err)
}
registerInput(cfgFile.kind, cfgFile.dst, checksum)
}
if useS3Audio {
if err := materializeS3AudioInputs(ctx, env, m, sessionID, &inputs); err != nil {
return nil, fmt.Errorf("prepare: materialize s3 audio: %w", err)
}
} else {
if err := materializeLocalAudioInputs(env, paths, resolvedLocalAudio, registerInput); err != nil {
return nil, fmt.Errorf("prepare: %w", err)
}
}
previousRequirements := collectPreparePreviousRequirements(env.Config)
var previousHydration *previousSessionHydrationResult
if len(previousRequirements) > 0 {
if err := clearManagedPreviousState(paths); err != nil {
return nil, fmt.Errorf("prepare: clear previous-session cache: %w", err)
}
hydration, err := hydratePreviousSessionArtifacts(ctx, env, paths, previousRequirements)
if err != nil {
return nil, fmt.Errorf("prepare: hydrate previous-session artifacts: %w", err)
}
previousHydration = hydration
inputs = append(inputs, hydration.Inputs...)
}
sort.Slice(inputs, func(i, j int) bool {
if inputs[i].Kind != inputs[j].Kind {
return inputs[i].Kind < inputs[j].Kind
}
return inputs[i].Path < inputs[j].Path
})
m.Inputs = inputs
metadata := map[string]any{
"prepared": true,
"stage": "prepare",
"inputs_count": len(inputs),
"audio_files_resolved": countAudioInputs(inputs),
}
if len(previousRequirements) > 0 {
metadata["previous_requirements_count"] = len(previousRequirements)
if previousHydration != nil {
metadata["previous_artifacts_hydrated"] = append([]string(nil), previousHydration.Hydrated...)
metadata["previous_artifacts_hydrated_count"] = len(previousHydration.Hydrated)
metadata["previous_artifacts_missing_optional"] = append([]string(nil), previousHydration.SkippedMissing...)
metadata["previous_artifacts_missing_optional_count"] = len(previousHydration.SkippedMissing)
if strings.TrimSpace(previousHydration.PreviousRunID) != "" {
metadata["previous_session_run_id"] = strings.TrimSpace(previousHydration.PreviousRunID)
}
}
}
return &StageResult{
Metadata: metadata,
}, nil
}
func renderResolvedPipeline(cfg *config.PipelineConfig) ([]byte, error) {
return yaml.Marshal(cfg)
}
func resolveAudioInputs(sessionDir string, inputs config.SessionInputsConfig) ([]string, bool, error) {
hasLocal := strings.TrimSpace(inputs.AudioDir) != "" || len(inputs.AudioFiles) > 0
if inputs.AudioS3 != nil {
if hasLocal {
return nil, false, fmt.Errorf("audio_dir/audio_files and audio_s3 are mutually exclusive")
}
return nil, true, nil
}
local, err := resolveLocalAudioFiles(sessionDir, inputs)
if err != nil {
return nil, false, err
}
return local, false, nil
}
func resolveLocalAudioFiles(sessionDir string, inputs config.SessionInputsConfig) ([]string, error) {
if len(inputs.AudioFiles) > 0 {
out := make([]string, 0, len(inputs.AudioFiles))
for _, p := range inputs.AudioFiles {
resolved, err := resolvePath(sessionDir, p)
if err != nil {
return nil, err
}
if !isFlac(resolved) {
return nil, fmt.Errorf("audio file %q must have .flac extension", resolved)
}
if err := requireFile(resolved, "audio file"); err != nil {
return nil, err
}
out = append(out, resolved)
}
sort.Strings(out)
return out, nil
}
audioDir, err := resolvePath(sessionDir, inputs.AudioDir)
if err != nil {
return nil, err
}
entries, err := os.ReadDir(audioDir)
if err != nil {
return nil, fmt.Errorf("read audio directory %q: %w", audioDir, err)
}
out := make([]string, 0)
for _, entry := range entries {
if entry.IsDir() {
continue
}
name := entry.Name()
full := filepath.Join(audioDir, name)
if !isFlac(full) {
continue
}
if err := requireFile(full, "audio file"); err != nil {
return nil, err
}
out = append(out, full)
}
if len(out) == 0 {
return nil, fmt.Errorf("no .flac files found in audio directory %q", audioDir)
}
sort.Strings(out)
return out, nil
}
func materializeLocalAudioInputs(env *Env, paths artifacts.SessionPaths, resolvedAudio []string, registerInput func(kind, path, checksum string)) error {
copiedByDest := map[string]string{}
for _, src := range resolvedAudio {
base := filepath.Base(src)
if prev, exists := copiedByDest[base]; exists && prev != src {
return fmt.Errorf("duplicate audio basename %q from %q and %q", base, prev, src)
}
copiedByDest[base] = src
dst := filepath.Join(paths.AudioDir, base)
checksum, err := copyFileIfChanged(env.ArtifactStore, src, dst)
if err != nil {
return fmt.Errorf("materialize audio %q: %w", base, err)
}
registerInput("audio", dst, checksum)
}
return nil
}
func materializeS3AudioInputs(ctx context.Context, env *Env, m *manifest.Manifest, sessionID string, inputs *[]manifest.InputRecord) error {
if env.ObjectStore == nil {
return fmt.Errorf("s3 audio input requires object store backend")
}
if env.Config == nil || env.Config.Pipeline == nil || env.Config.Session == nil || env.Config.Pipeline.Storage.S3 == nil || env.Config.Session.Inputs.AudioS3 == nil {
return fmt.Errorf("s3 audio input requires pipeline.storage.s3 and session.inputs.audio_s3 configuration")
}
campaign := strings.TrimSpace(env.Config.Session.Campaign)
if campaign == "" {
return fmt.Errorf("session campaign is required for s3 audio input")
}
runID := strings.TrimSpace(m.RunID)
if runID == "" {
return fmt.Errorf("run id is required for s3 audio input")
}
sessionPrefix := artifacts.S3SessionPrefix(env.Config.Pipeline.Storage.S3.RootPrefix, campaign, sessionID)
audioPrefix := artifacts.S3AudioPrefix(sessionPrefix, env.Config.Session.Inputs.AudioS3.Prefix)
objects, err := env.ObjectStore.List(ctx, audioPrefix)
if err != nil {
return fmt.Errorf("list s3 audio objects under %q: %w", audioPrefix, err)
}
audioObjects := make([]storage.ObjectInfo, 0, len(objects))
for _, obj := range objects {
key := strings.TrimSpace(obj.Key)
if key == "" || strings.HasSuffix(key, "/") {
continue
}
if !isFlac(key) {
continue
}
audioObjects = append(audioObjects, obj)
}
sort.Slice(audioObjects, func(i, j int) bool {
return audioObjects[i].Key < audioObjects[j].Key
})
if len(audioObjects) == 0 {
return fmt.Errorf("no .flac files found under s3 audio prefix %q", audioPrefix)
}
spoolAudioDir := strings.TrimSpace(m.LocalSpoolDir)
if spoolAudioDir == "" {
spoolAudioDir = artifacts.SessionSpoolAudioDir(env.Config.Pipeline.Spool.Root, campaign, sessionID, runID)
}
workAudioDir := filepath.Join(pathsWorkDirForManifest(env, m, sessionID), "audio")
if err := os.MkdirAll(spoolAudioDir, 0o755); err != nil {
return fmt.Errorf("create spool audio directory %q: %w", spoolAudioDir, err)
}
if err := os.MkdirAll(workAudioDir, 0o755); err != nil {
return fmt.Errorf("create work audio directory %q: %w", workAudioDir, err)
}
seenBase := map[string]string{}
for _, obj := range audioObjects {
base := path.Base(obj.Key)
if prev, exists := seenBase[base]; exists && prev != obj.Key {
return fmt.Errorf("duplicate s3 audio basename %q from %q and %q", base, prev, obj.Key)
}
seenBase[base] = obj.Key
spoolPath := filepath.Join(spoolAudioDir, base)
if err := env.ObjectStore.Download(ctx, obj.Key, spoolPath); err != nil {
return fmt.Errorf("download s3 audio object %q: %w", obj.Key, err)
}
workPath := filepath.Join(workAudioDir, base)
checksum, err := copyFileIfChanged(env.ArtifactStore, spoolPath, workPath)
if err != nil {
return fmt.Errorf("materialize downloaded audio %q: %w", base, err)
}
*inputs = append(*inputs, manifest.InputRecord{
Kind: "audio",
Path: workPath,
Checksum: checksum,
Source: "s3",
S3Bucket: strings.TrimSpace(env.Config.Pipeline.Storage.S3.Bucket),
S3Key: obj.Key,
S3Size: obj.Size,
S3ETag: obj.ETag,
SpoolPath: spoolPath,
})
}
return nil
}
func countAudioInputs(inputs []manifest.InputRecord) int {
count := 0
for _, in := range inputs {
if in.Kind == "audio" {
count++
}
}
return count
}
func collectPreparePreviousRequirements(cfg *config.Config) []artifacts.PreviousArtifactRequirement {
if cfg == nil || cfg.Pipeline == nil || cfg.Pipeline.Scriptorium == nil {
return nil
}
return artifacts.CollectPreviousArtifactRequirements(cfg.Pipeline.Scriptorium.Artifacts)
}
func clearManagedPreviousState(paths artifacts.SessionPaths) error {
previousDir := filepath.Clean(paths.PreviousDir)
sessionRoot := filepath.Clean(paths.Root)
if strings.TrimSpace(previousDir) == "" || strings.TrimSpace(sessionRoot) == "" {
return fmt.Errorf("previous/session root paths are required")
}
if previousDir == sessionRoot {
return fmt.Errorf("refusing to clear session root as previous cache: %q", previousDir)
}
prefix := sessionRoot + string(filepath.Separator)
if !strings.HasPrefix(previousDir, prefix) {
return fmt.Errorf("refusing to clear path outside session root: %q", previousDir)
}
if filepath.Base(previousDir) != config.PathPreviousDirSegment {
return fmt.Errorf("refusing to clear non-previous path %q", previousDir)
}
if err := os.RemoveAll(previousDir); err != nil {
return err
}
return os.MkdirAll(previousDir, 0o755)
}
func pathsWorkDirForManifest(env *Env, m *manifest.Manifest, sessionID string) string {
if env == nil || env.Config == nil || env.Config.Pipeline == nil || env.Config.Session == nil {
return ""
}
campaign := strings.TrimSpace(env.Config.Session.Campaign)
if campaign == "" {
return ""
}
if m != nil && strings.TrimSpace(m.LocalWorkDir) != "" {
return strings.TrimSpace(m.LocalWorkDir)
}
runID := ""
if m != nil {
runID = strings.TrimSpace(m.RunID)
}
if runID != "" {
return artifacts.SessionRunRootForCampaign(env.Config.Pipeline.Workspace.Root, campaign, sessionID, runID)
}
return artifacts.SessionWorkDirForCampaign(env.Config.Pipeline.Workspace.Root, campaign, sessionID)
}
func resolvePath(baseDir, p string) (string, error) {
trimmed := strings.TrimSpace(p)
if trimmed == "" {
return "", fmt.Errorf("path is required")
}
if filepath.IsAbs(trimmed) {
return filepath.Clean(trimmed), nil
}
return filepath.Clean(filepath.Join(baseDir, trimmed)), nil
}
func requireFile(path string, label string) error {
if strings.TrimSpace(path) == "" {
return fmt.Errorf("%s path is required", label)
}
info, err := os.Stat(path)
if err != nil {
return fmt.Errorf("%s %q not found: %w", label, path, err)
}
if info.IsDir() {
return fmt.Errorf("%s %q is a directory", label, path)
}
return nil
}
func isFlac(path string) bool {
return strings.EqualFold(filepath.Ext(path), ".flac")
}
func copyFileIfChanged(store artifacts.Store, src, dst string) (string, error) {
srcChecksum, err := store.Checksum(src)
if err != nil {
return "", err
}
exists, err := store.Exists(dst)
if err != nil {
return "", err
}
if exists {
dstChecksum, err := store.Checksum(dst)
if err != nil {
return "", err
}
if dstChecksum == srcChecksum {
return srcChecksum, nil
}
}
data, err := os.ReadFile(src)
if err != nil {
return "", err
}
if err := store.WriteFileAtomic(dst, data, 0o644); err != nil {
return "", err
}
return srcChecksum, nil
}
func writeBytesIfChanged(store artifacts.Store, dst string, data []byte) (string, error) {
digest := sha256.Sum256(data)
targetChecksum := hex.EncodeToString(digest[:])
exists, err := store.Exists(dst)
if err != nil {
return "", err
}
if exists {
dstChecksum, err := store.Checksum(dst)
if err != nil {
return "", err
}
if dstChecksum == targetChecksum {
return targetChecksum, nil
}
}
if err := store.WriteFileAtomic(dst, data, 0o644); err != nil {
return "", err
}
return targetChecksum, nil
}