Files
distributor/internal/app/prune_test.go

333 lines
12 KiB
Go

package app
import (
"context"
"encoding/json"
"strings"
"testing"
"time"
"gitea.maximumdirect.net/eric/distributor/internal/config"
"gitea.maximumdirect.net/eric/distributor/internal/state"
"gitea.maximumdirect.net/eric/distributor/internal/storage"
"gitea.maximumdirect.net/eric/distributor/internal/storage/fake"
"gitea.maximumdirect.net/eric/distributor/internal/testutil"
)
func TestPlanPruneDisabledPolicy(t *testing.T) {
document := state.StateDocument{Catalog: &state.CatalogState{}}
report, err := PlanPrune(document, config.PrunePolicy{}, PrunePlanOptions{
PipelineID: "reports",
DestinationID: "archive",
})
if err != nil {
t.Fatalf("PlanPrune() error = %v", err)
}
if report.Enabled || report.CheckedCount != 0 || len(report.PrunedOutputs) != 0 {
t.Fatalf("report = %#v, want disabled empty plan", report)
}
}
func TestPlanPruneCatalogOutputs(t *testing.T) {
now := time.Date(2026, 6, 8, 12, 0, 0, 0, time.UTC)
olderThan := config.Duration(48 * time.Hour)
catalog := pruneCatalogState(now)
report, err := PlanPrune(state.StateDocument{Catalog: &catalog}, config.PrunePolicy{
Enabled: true,
OlderThan: &olderThan,
}, PrunePlanOptions{
PipelineID: "reports",
DestinationID: "archive",
Now: now,
})
if err != nil {
t.Fatalf("PlanPrune() error = %v", err)
}
if got, want := pruneRecordPaths(report.PrunedOutputs), "old.txt"; got != want {
t.Fatalf("pruned = %q, want %q", got, want)
}
if got, want := pruneRecordPaths(report.PreservedOutputs), "fresh.txt"; got != want {
t.Fatalf("preserved = %q, want %q", got, want)
}
}
func TestPlanPruneCatalogCurrentOwnerOnly(t *testing.T) {
now := time.Date(2026, 6, 8, 12, 0, 0, 0, time.UTC)
keepLatest := 0
catalog := pruneCatalogState(now)
report, err := PlanPrune(state.StateDocument{Catalog: &catalog}, config.PrunePolicy{
Enabled: true,
KeepLatest: &keepLatest,
}, PrunePlanOptions{
PipelineID: "reports",
DestinationID: "archive",
Now: now,
})
if err != nil {
t.Fatalf("PlanPrune() error = %v", err)
}
if got, want := report.CheckedCount, 2; got != want {
t.Fatalf("checked count = %d, want %d", got, want)
}
if got, want := pruneRecordPaths(report.PrunedOutputs), "old.txt,fresh.txt"; got != want {
t.Fatalf("pruned = %q, want %q", got, want)
}
}
func TestPruneDryRunReportsPlannedDeletesWithoutDeletingOrRewritingState(t *testing.T) {
now := time.Date(2026, 6, 8, 12, 0, 0, 0, time.UTC)
backend := fake.New()
cfg := pruneS3Config(t, pruneOlderThanPolicy(48*time.Hour))
original := pruneCatalogState(now)
writeFakeCatalogState(t, backend, original)
testutil.WriteFakeFile(t, backend, "unmanaged.txt", "keep")
report, err := pruneConfigWithBackendFactory(context.Background(), cfg, PruneOptions{
PipelineID: "reports",
DestinationID: "archive",
DryRun: true,
Now: now,
}, fakeBackendFactoryProvider(t, map[string]storage.Backend{"s3:reports": backend}))
if err != nil {
t.Fatalf("pruneConfigWithBackendFactory() error = %v", err)
}
if !report.WouldChange || report.StateChanged || len(report.DeletedOutputs) != 0 {
t.Fatalf("report would_change=%t state_changed=%t deleted=%d, want dry-run only", report.WouldChange, report.StateChanged, len(report.DeletedOutputs))
}
if got, want := pruneRecordPaths(report.PlannedOutputs), "old.txt"; got != want {
t.Fatalf("planned outputs = %q, want %q", got, want)
}
testutil.AssertFakeFile(t, backend, "old.txt", "managed")
testutil.AssertFakeFile(t, backend, "fresh.txt", "managed")
testutil.AssertFakeFile(t, backend, "unmanaged.txt", "keep")
catalog := readFakeCatalogState(t, backend)
if got := strings.Join(state.CatalogManagedOutputPaths(catalog), ","); got != "old.txt,fresh.txt,html.txt" {
t.Fatalf("state outputs = %q, want original outputs", got)
}
if !catalog.UpdatedAt.Equal(original.UpdatedAt) {
t.Fatalf("state updated_at = %s, want original %s", catalog.UpdatedAt, original.UpdatedAt)
}
}
func TestPruneApplyDeletesOnlyManagedOutputsAndUpdatesState(t *testing.T) {
now := time.Date(2026, 6, 8, 12, 0, 0, 0, time.UTC)
backend := fake.New()
cfg := pruneS3Config(t, pruneOlderThanPolicy(48*time.Hour))
writeFakeCatalogState(t, backend, pruneCatalogState(now))
testutil.WriteFakeFile(t, backend, "unmanaged.txt", "keep")
report, err := pruneConfigWithBackendFactory(context.Background(), cfg, PruneOptions{
PipelineID: "reports",
DestinationID: "archive",
Now: now,
}, fakeBackendFactoryProvider(t, map[string]storage.Backend{"s3:reports": backend}))
if err != nil {
t.Fatalf("pruneConfigWithBackendFactory() error = %v", err)
}
if !report.StateChanged || report.WouldChange {
t.Fatalf("report state_changed=%t would_change=%t, want applied change", report.StateChanged, report.WouldChange)
}
if got, want := pruneRecordPaths(report.DeletedOutputs), "old.txt"; got != want {
t.Fatalf("deleted outputs = %q, want %q", got, want)
}
testutil.AssertFakeMissing(t, backend, "old.txt")
testutil.AssertFakeFile(t, backend, "fresh.txt", "managed")
testutil.AssertFakeFile(t, backend, "html.txt", "managed")
testutil.AssertFakeFile(t, backend, "unmanaged.txt", "keep")
assertFakeStateExists(t, backend)
catalog := readFakeCatalogState(t, backend)
if got := strings.Join(state.CatalogManagedOutputPaths(catalog), ","); got != "fresh.txt,html.txt" {
t.Fatalf("state outputs = %q, want fresh.txt", got)
}
if catalog.SchemaVersion != state.CatalogSchemaVersion {
t.Fatalf("state schema_version = %d, want %d", catalog.SchemaVersion, state.CatalogSchemaVersion)
}
if !catalog.UpdatedAt.Equal(now) {
t.Fatalf("state updated_at = %s, want %s", catalog.UpdatedAt, now)
}
}
func TestPruneApplyPreservesStateForFailedDeletes(t *testing.T) {
now := time.Date(2026, 6, 8, 12, 0, 0, 0, time.UTC)
backend := fake.New()
keepLatest := 0
cfg := pruneS3Config(t, config.PrunePolicy{Enabled: true, KeepLatest: &keepLatest})
writeFakeCatalogState(t, backend, pruneCatalogState(now))
failingBackend := failingDeleteBackend{Backend: backend, failPath: "fresh.txt"}
report, err := pruneConfigWithBackendFactory(context.Background(), cfg, PruneOptions{
PipelineID: "reports",
DestinationID: "archive",
Now: now,
}, fakeBackendFactoryProvider(t, map[string]storage.Backend{"s3:reports": failingBackend}))
if err == nil {
t.Fatal("pruneConfigWithBackendFactory() error = nil, want delete failure")
}
if report.FailedOutput == nil || report.FailedOutput.Path != "fresh.txt" {
t.Fatalf("failed output = %#v, want fresh.txt", report.FailedOutput)
}
if got, want := pruneRecordPaths(report.DeletedOutputs), "old.txt"; got != want {
t.Fatalf("deleted outputs = %q, want %q", got, want)
}
testutil.AssertFakeMissing(t, backend, "old.txt")
testutil.AssertFakeFile(t, backend, "fresh.txt", "managed")
assertFakeStateExists(t, backend)
catalog := readFakeCatalogState(t, backend)
if got := strings.Join(state.CatalogManagedOutputPaths(catalog), ","); got != "fresh.txt,html.txt" {
t.Fatalf("state outputs = %q, want only failed output preserved", got)
}
}
func TestPrunePreservesOtherOwnersWhenScopedToCurrentOwner(t *testing.T) {
now := time.Date(2026, 6, 8, 12, 0, 0, 0, time.UTC)
backend := fake.New()
cfg := pruneS3Config(t, pruneOlderThanPolicy(48*time.Hour))
writeFakeCatalogState(t, backend, pruneCatalogState(now))
testutil.WriteFakeFile(t, backend, "unmanaged.txt", "keep")
report, err := pruneConfigWithBackendFactory(context.Background(), cfg, PruneOptions{
PipelineID: "reports",
DestinationID: "archive",
Now: now,
}, fakeBackendFactoryProvider(t, map[string]storage.Backend{"s3:reports": backend}))
if err != nil {
t.Fatalf("pruneConfigWithBackendFactory() error = %v", err)
}
if got, want := pruneRecordPaths(report.DeletedOutputs), "old.txt"; got != want {
t.Fatalf("deleted outputs = %q, want %q", got, want)
}
testutil.AssertFakeMissing(t, backend, "old.txt")
testutil.AssertFakeFile(t, backend, "html.txt", "managed")
testutil.AssertFakeFile(t, backend, "unmanaged.txt", "keep")
catalog := readFakeCatalogState(t, backend)
if got := strings.Join(state.CatalogManagedOutputPaths(catalog), ","); got != "fresh.txt,html.txt" {
t.Fatalf("catalog outputs = %q, want other owner output preserved", got)
}
}
func pruneCatalogState(now time.Time) state.CatalogState {
manifest := testutil.ValidManifest(testutil.BundleOptions{})
createdAt := now.Add(-96 * time.Hour)
source := state.CatalogSourceIdentity{ID: manifest.ID, Digest: manifest.Digest, Created: manifest.Created}
return state.CatalogState{
SchemaVersion: state.CatalogSchemaVersion,
DistributorVersion: "test",
CreatedAt: createdAt,
UpdatedAt: createdAt,
State: state.StatePolicy{Mode: state.StateModeCatalog},
Outputs: []state.CatalogOutputFile{{
Path: "old.txt",
PipelineID: "reports",
DestinationID: "archive",
Source: source,
Kind: state.OutputKindSource,
SHA256: manifest.Files[0].SHA256,
Size: manifest.Files[0].Size,
CreatedAt: now.Add(-96 * time.Hour),
UpdatedAt: now.Add(-72 * time.Hour),
}, {
Path: "fresh.txt",
PipelineID: "reports",
DestinationID: "archive",
Source: source,
Kind: state.OutputKindSource,
SHA256: manifest.Files[0].SHA256,
Size: manifest.Files[0].Size,
CreatedAt: now.Add(-24 * time.Hour),
UpdatedAt: now.Add(-24 * time.Hour),
}, {
Path: "html.txt",
PipelineID: "reports",
DestinationID: "html",
Source: source,
Kind: state.OutputKindSource,
SHA256: manifest.Files[1].SHA256,
Size: manifest.Files[1].Size,
CreatedAt: now.Add(-96 * time.Hour),
UpdatedAt: now.Add(-72 * time.Hour),
}},
}
}
func pruneRecordPaths(records []PruneOutputRecord) string {
paths := make([]string, 0, len(records))
for _, record := range records {
paths = append(paths, record.Path)
}
return strings.Join(paths, ",")
}
func pruneS3Config(t *testing.T, policy config.PrunePolicy) config.Config {
t.Helper()
cfg := config.Config{Pipelines: []config.Pipeline{{
ID: "reports",
Source: config.Backend{Backend: config.BackendLocal, Path: t.TempDir()},
Destinations: []config.Destination{{
ID: "archive",
Backend: config.BackendS3,
Bucket: "reports",
Retention: config.RetentionPolicy{
Prune: policy,
},
}},
}}}
config.ApplyDefaults(&cfg)
return cfg
}
func pruneOlderThanPolicy(duration time.Duration) config.PrunePolicy {
value := config.Duration(duration)
return config.PrunePolicy{
Enabled: true,
OlderThan: &value,
}
}
func writeFakeCatalogState(t *testing.T, backend *fake.Backend, catalog state.CatalogState) {
t.Helper()
data, err := json.MarshalIndent(catalog, "", " ")
if err != nil {
t.Fatalf("marshal catalog state: %v", err)
}
testutil.WriteFakeFile(t, backend, storage.StateFileName, string(append(data, '\n')))
for _, output := range catalog.Outputs {
testutil.WriteFakeFile(t, backend, output.Path, "managed")
}
}
func readFakeCatalogState(t *testing.T, backend *fake.Backend) state.CatalogState {
t.Helper()
data, err := backend.ReadFile(context.Background(), storage.StateFileName)
if err != nil {
t.Fatalf("read catalog state: %v", err)
}
catalog, err := state.ParseCatalog(data)
if err != nil {
t.Fatalf("parse catalog state: %v", err)
}
return catalog
}
func assertFakeStateExists(t *testing.T, backend *fake.Backend) {
t.Helper()
if _, err := backend.Stat(context.Background(), storage.StateFileName); err != nil {
t.Fatalf("state file stat error = %v", err)
}
}
type failingDeleteBackend struct {
storage.Backend
failPath string
}
func (b failingDeleteBackend) DeleteManagedOutputs(ctx context.Context, bundlePath string, managedOutputPaths []string, opts storage.DeleteOptions) error {
for _, path := range managedOutputPaths {
if path == b.failPath {
return storage.NewError(storage.OpDeleteManagedOutputs, "fake", path, storage.ErrPermission, nil)
}
}
return b.Backend.DeleteManagedOutputs(ctx, bundlePath, managedOutputPaths, opts)
}