Files
narratio/internal/app/clean.go
2026-05-21 22:48:18 -05:00

337 lines
11 KiB
Go

package app
import (
"context"
"flag"
"fmt"
"io"
"os"
"path/filepath"
"strings"
"gitea.maximumdirect.net/eric/narratio/internal/artifacts"
"gitea.maximumdirect.net/eric/narratio/internal/config"
)
// Clean removes local workspace/spool state while preserving durable cache
// state unless cache cleanup is explicitly requested.
func Clean(ctx context.Context, args []string, out io.Writer) error {
fs := flag.NewFlagSet("clean", flag.ContinueOnError)
fs.SetOutput(io.Discard)
var flags commonConfigFlags
var all bool
var dryRun bool
var clearCache bool
addCommonConfigFlags(fs, &flags)
fs.BoolVar(&all, "all", false, "clean all local session work/spool state")
fs.BoolVar(&dryRun, "dry-run", false, "print cleanup targets without deleting")
fs.BoolVar(&clearCache, "clear-cache", false, "also clear durable S3 audio cache entries")
if err := fs.Parse(args); err != nil {
return fmt.Errorf("clean: invalid flags: %w", err)
}
if fs.NArg() != 0 {
return fmt.Errorf("clean: unexpected positional arguments")
}
if all {
return cleanAllLocal(flags, dryRun, clearCache, out)
}
return cleanSession(ctx, flags, dryRun, clearCache, out)
}
func cleanSession(ctx context.Context, flags commonConfigFlags, dryRun, clearCache bool, out io.Writer) error {
if strings.TrimSpace(flags.sessionID) == "" {
return fmt.Errorf("clean: --session-id is required unless --all is set")
}
cfg, err := loadCommandConfig(ctx, flags.pipelinePath, flags.campaignPath, flags.sessionPath, flags.sessionOptions())
if err != nil {
return fmt.Errorf("clean: %w", err)
}
if cfg == nil || cfg.Pipeline == nil || cfg.Session == nil {
return fmt.Errorf("clean: resolved pipeline and session config are required")
}
campaign := strings.TrimSpace(cfg.Session.Campaign)
sessionID := strings.TrimSpace(cfg.Session.SessionID)
if campaign == "" || sessionID == "" {
return fmt.Errorf("clean: campaign and session_id are required")
}
if dryRun {
fmt.Fprintf(out, "Clean plan for %s/%s\n", campaign, sessionID)
} else {
fmt.Fprintf(out, "Cleaned %s/%s\n", campaign, sessionID)
}
workDir := artifacts.SessionWorkDirForCampaign(cfg.Pipeline.Workspace.Root, campaign, sessionID)
spoolDir := artifacts.SessionSpoolDir(cfg.Pipeline.Spool.Root, campaign, sessionID)
if err := reportCleanScopedDir(out, cfg.Pipeline.Workspace.Root, workDir, "clean.workspace.session", dryRun); err != nil {
return fmt.Errorf("clean: %w", err)
}
if err := reportCleanScopedDir(out, cfg.Pipeline.Spool.Root, spoolDir, "clean.spool.session", dryRun); err != nil {
return fmt.Errorf("clean: %w", err)
}
if clearCache {
if err := cleanSessionAudioCache(ctx, cfg, dryRun, out); err != nil {
return fmt.Errorf("clean: %w", err)
}
} else {
fmt.Fprintln(out, "Cache: preserved")
}
return nil
}
func cleanAllLocal(flags commonConfigFlags, dryRun, clearCache bool, out io.Writer) error {
if strings.TrimSpace(flags.campaignPath) != "" ||
strings.TrimSpace(flags.sessionPath) != "" ||
strings.TrimSpace(flags.sessionID) != "" ||
strings.TrimSpace(flags.previousSessionID) != "" {
return fmt.Errorf("clean: --all cannot be combined with --campaign, --session, --session-id, or --previous-session-id")
}
resolvedPipelinePath, err := resolvePipelineConfigPath(flags.pipelinePath)
if err != nil {
return fmt.Errorf("clean: %w", err)
}
pipelineCfg, err := config.LoadPipeline(resolvedPipelinePath)
if err != nil {
return fmt.Errorf("clean: %w", err)
}
if dryRun {
fmt.Fprintln(out, "Clean plan for all local sessions")
} else {
fmt.Fprintln(out, "Cleaned all local sessions")
}
workRoot := filepath.Join(pipelineCfg.Workspace.Root, config.PathWorkDirSegment)
if err := reportCleanScopedDir(out, pipelineCfg.Workspace.Root, workRoot, "clean.workspace.all", dryRun); err != nil {
return fmt.Errorf("clean: %w", err)
}
if err := reportCleanRootChildren(out, pipelineCfg.Spool.Root, "clean.spool.all", dryRun); err != nil {
return fmt.Errorf("clean: %w", err)
}
if clearCache {
if err := cleanAllAudioCache(pipelineCfg, dryRun, out); err != nil {
return fmt.Errorf("clean: %w", err)
}
} else {
fmt.Fprintln(out, "Cache: preserved")
}
return nil
}
func reportCleanScopedDir(out io.Writer, root, target, policy string, dryRun bool) error {
dir, err := validateScopedDir(root, target, policy)
if err != nil {
return err
}
if dryRun {
if dir.Exists {
fmt.Fprintf(out, "Would delete: %s\n", dir.TargetAbs)
} else {
fmt.Fprintf(out, "Would skip missing: %s\n", dir.TargetAbs)
}
return nil
}
if !dir.Exists {
fmt.Fprintf(out, "Missing: %s\n", dir.TargetAbs)
return nil
}
if err := os.RemoveAll(dir.TargetAbs); err != nil {
return fmt.Errorf("cleanup policy %s: remove %q: %w", policy, dir.TargetAbs, err)
}
fmt.Fprintf(out, "Deleted: %s\n", dir.TargetAbs)
return nil
}
func reportCleanRootChildren(out io.Writer, root, policy string, dryRun bool) error {
rootAbs, entries, err := cleanableRootChildren(root, policy)
if err != nil {
return err
}
if len(entries) == 0 {
if dryRun {
fmt.Fprintf(out, "Would skip empty: %s\n", rootAbs)
} else {
fmt.Fprintf(out, "Empty: %s\n", rootAbs)
}
return nil
}
for _, entry := range entries {
if dryRun {
fmt.Fprintf(out, "Would delete: %s\n", entry)
continue
}
if err := os.RemoveAll(entry); err != nil {
return fmt.Errorf("cleanup policy %s: remove %q: %w", policy, entry, err)
}
fmt.Fprintf(out, "Deleted: %s\n", entry)
}
return nil
}
func cleanableRootChildren(root, policy string) (string, []string, error) {
cleanRoot := strings.TrimSpace(root)
if cleanRoot == "" {
return "", nil, fmt.Errorf("cleanup policy %s: root path is required", policy)
}
rootAbs, err := filepath.Abs(cleanRoot)
if err != nil {
return "", nil, fmt.Errorf("cleanup policy %s: resolve root %q: %w", policy, cleanRoot, err)
}
info, err := os.Lstat(rootAbs)
if err != nil {
if os.IsNotExist(err) {
return rootAbs, nil, nil
}
return "", nil, fmt.Errorf("cleanup policy %s: stat root %q: %w", policy, rootAbs, err)
}
if info.Mode()&os.ModeSymlink != 0 {
return "", nil, fmt.Errorf("cleanup policy %s: refusing to clean symlink root %q", policy, rootAbs)
}
if !info.IsDir() {
return "", nil, fmt.Errorf("cleanup policy %s: root %q is not a directory", policy, rootAbs)
}
entries, err := os.ReadDir(rootAbs)
if err != nil {
return "", nil, fmt.Errorf("cleanup policy %s: read root %q: %w", policy, rootAbs, err)
}
out := make([]string, 0, len(entries))
for _, entry := range entries {
path := filepath.Join(rootAbs, entry.Name())
info, err := os.Lstat(path)
if err != nil {
return "", nil, fmt.Errorf("cleanup policy %s: stat child %q: %w", policy, path, err)
}
if info.Mode()&os.ModeSymlink != 0 {
return "", nil, fmt.Errorf("cleanup policy %s: refusing to delete symlink path %q", policy, path)
}
out = append(out, path)
}
return rootAbs, out, nil
}
func cleanSessionAudioCache(ctx context.Context, cfg *config.Config, dryRun bool, out io.Writer) error {
if cfg.Session.Inputs.AudioS3 == nil {
fmt.Fprintln(out, "Cache: skipped (session does not use audio_s3)")
return nil
}
if cfg.Pipeline.Storage.S3 == nil || strings.TrimSpace(cfg.Pipeline.Storage.S3.Bucket) == "" {
return fmt.Errorf("clear cache requires pipeline.storage.s3.bucket")
}
store, err := newCommandObjectStore(ctx, cfg, nil)
if err != nil {
return fmt.Errorf("initialize object store for cache cleanup: %w", err)
}
sessionPrefix := artifacts.S3SessionPrefix(cfg.Pipeline.Storage.S3.RootPrefix, cfg.Session.Campaign, cfg.Session.SessionID)
audioPrefix := artifacts.S3AudioPrefix(sessionPrefix, cfg.Session.Inputs.AudioS3.Prefix)
objects, err := store.List(ctx, audioPrefix)
if err != nil {
return fmt.Errorf("list s3 audio objects under %q: %w", audioPrefix, err)
}
count := 0
for _, obj := range objects {
key := strings.TrimSpace(obj.Key)
if key == "" || strings.HasSuffix(key, "/") || !cleanIsFlac(key) {
continue
}
cachePath, err := artifacts.S3AudioCachePath(cfg.Pipeline.Cache.Root, cfg.Pipeline.Storage.S3.Bucket, key)
if err != nil {
return err
}
deleted, err := reportCleanScopedFile(out, cfg.Pipeline.Cache.Root, cachePath, "clean.cache.session", dryRun)
if err != nil {
return err
}
if deleted {
count++
}
}
if count == 0 {
fmt.Fprintf(out, "Cache: no cached S3 audio files found for %s\n", audioPrefix)
}
return nil
}
func cleanAllAudioCache(cfg *config.PipelineConfig, dryRun bool, out io.Writer) error {
if cfg.Storage.S3 == nil || strings.TrimSpace(cfg.Storage.S3.Bucket) == "" {
return fmt.Errorf("clear cache requires pipeline.storage.s3.bucket")
}
namespaceDir, err := artifacts.S3AudioCacheNamespaceDir(cfg.Cache.Root, cfg.Storage.S3.Bucket, cfg.Storage.S3.RootPrefix)
if err != nil {
return err
}
return reportCleanScopedDir(out, cfg.Cache.Root, namespaceDir, "clean.cache.all", dryRun)
}
func reportCleanScopedFile(out io.Writer, root, target, policy string, dryRun bool) (bool, error) {
file, err := validateScopedFile(root, target, policy)
if err != nil {
return false, err
}
if dryRun {
if file.Exists {
fmt.Fprintf(out, "Would delete cache file: %s\n", file.TargetAbs)
return true, nil
}
fmt.Fprintf(out, "Would skip missing cache file: %s\n", file.TargetAbs)
return false, nil
}
if !file.Exists {
fmt.Fprintf(out, "Missing cache file: %s\n", file.TargetAbs)
return false, nil
}
if err := os.Remove(file.TargetAbs); err != nil {
return false, fmt.Errorf("cleanup policy %s: remove %q: %w", policy, file.TargetAbs, err)
}
fmt.Fprintf(out, "Deleted cache file: %s\n", file.TargetAbs)
return true, nil
}
func validateScopedFile(root, target, policy string) (scopedDir, error) {
cleanRoot := strings.TrimSpace(root)
cleanTarget := strings.TrimSpace(target)
if cleanRoot == "" {
return scopedDir{}, fmt.Errorf("cleanup policy %s: root path is required", policy)
}
if cleanTarget == "" {
return scopedDir{}, fmt.Errorf("cleanup policy %s: target path is required", policy)
}
rootAbs, err := filepath.Abs(cleanRoot)
if err != nil {
return scopedDir{}, fmt.Errorf("cleanup policy %s: resolve root %q: %w", policy, cleanRoot, err)
}
targetAbs, err := filepath.Abs(cleanTarget)
if err != nil {
return scopedDir{}, fmt.Errorf("cleanup policy %s: resolve target %q: %w", policy, cleanTarget, err)
}
rel, err := filepath.Rel(rootAbs, targetAbs)
if err != nil {
return scopedDir{}, fmt.Errorf("cleanup policy %s: relative path from %q to %q: %w", policy, rootAbs, targetAbs, err)
}
if rel == "." {
return scopedDir{}, fmt.Errorf("cleanup policy %s: refusing to delete root directory %q", policy, rootAbs)
}
if rel == ".." || strings.HasPrefix(rel, ".."+string(filepath.Separator)) {
return scopedDir{}, fmt.Errorf("cleanup policy %s: refusing to delete path outside root: root=%q target=%q", policy, rootAbs, targetAbs)
}
info, err := os.Lstat(targetAbs)
if err != nil {
if os.IsNotExist(err) {
return scopedDir{RootAbs: rootAbs, TargetAbs: targetAbs, Exists: false}, nil
}
return scopedDir{}, fmt.Errorf("cleanup policy %s: stat target %q: %w", policy, targetAbs, err)
}
if info.Mode()&os.ModeSymlink != 0 {
return scopedDir{}, fmt.Errorf("cleanup policy %s: refusing to delete symlink path %q", policy, targetAbs)
}
if info.IsDir() {
return scopedDir{}, fmt.Errorf("cleanup policy %s: target %q is a directory", policy, targetAbs)
}
return scopedDir{RootAbs: rootAbs, TargetAbs: targetAbs, Exists: true}, nil
}
func cleanIsFlac(path string) bool {
return strings.EqualFold(filepath.Ext(path), ".flac")
}