vaultik/internal/vaultik/remote_info_test.go

package vaultik_test

import (
	"bytes"
	"context"
	"encoding/json"
	"testing"
	"time"

	"github.com/stretchr/testify/assert"
	"github.com/stretchr/testify/require"
	"sneak.berlin/go/vaultik/internal/log"
	"sneak.berlin/go/vaultik/internal/snapshot"
)

// testBlobHashB is a blob that the manifest written by addRemote does
// not reference.
const testBlobHashB = "bbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb" +
	"bbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb"

// TestRemoteInfo_UnreadableManifestLeavesOrphansUnknown checks that a
// manifest remote info cannot read makes the orphan figures unknown. A
// blob referenced only by that snapshot would otherwise be counted as
// orphaned, and the report would advise running prune.
func TestRemoteInfo_UnreadableManifestLeavesOrphansUnknown(t *testing.T) {
	log.Initialize(log.Config{})
	t.Parallel()

	env := newListEnv(t)

	// The readable manifest references blob A only.
	env.addRemote(t, listRemoteID, time.Date(2026, 3, 2, 0, 0, 0, 0, time.UTC))
	addBlob(t, env.store.testStorer, testBlobHashA)
	addBlob(t, env.store.testStorer, testBlobHashB)

	// With every manifest readable, blob B is orphaned.
	require.NoError(t, env.v.RemoteInfo(true))

	var doc map[string]any

	require.NoError(t, json.Unmarshal(env.stdout.Bytes(), &doc))
	assert.InDelta(t, 1, doc["orphaned_blob_count"], 0)

	// A second snapshot whose manifest cannot be decoded. Blob B may be
	// one of its blobs.
	unreadableKey := snapshot.RemoteSnapshotKey(listLocalID)
	require.NoError(t, env.store.Put(context.Background(),
		"metadata/"+unreadableKey+"/manifest.json.zst",
		bytes.NewReader([]byte("not a valid manifest"))))

	env.stdout.Reset()
	require.NoError(t, env.v.RemoteInfo(false))

	text := env.stdout.String()
	assert.Contains(t, text, "Orphaned (unreferenced):    unknown "+
		"(1 manifest(s) could not be read, "+
		"0 manifest(s) under a non-conforming name skipped)")
	assert.NotContains(t, text, "vaultik prune")

	env.stdout.Reset()
	require.NoError(t, env.v.RemoteInfo(true))

	doc = nil
	require.NoError(t, json.Unmarshal(env.stdout.Bytes(), &doc))
	assert.Contains(t, doc, "orphaned_blob_count")
	assert.Nil(t, doc["orphaned_blob_count"])
	assert.Contains(t, doc, "orphaned_blob_size")
	assert.Nil(t, doc["orphaned_blob_size"])
	assert.Equal(t, []any{unreadableKey}, doc["unreadable_manifests"])
}

// TestRemoteInfo_SkipsNonConformingMetadataName checks that a directory
// under metadata/ whose name is not a remote key is left out of the
// report, and that the orphan figures are unknown when it holds a
// manifest. The name comes from the destination store; printed raw, its
// control characters would reach the terminal. Its manifest is not
// read, so a blob only it references would otherwise be counted as
// orphaned.
func TestRemoteInfo_SkipsNonConformingMetadataName(t *testing.T) {
	log.Initialize(log.Config{})
	t.Parallel()

	env := newListEnv(t)
	env.addRemote(t, listRemoteID, time.Date(2026, 3, 2, 0, 0, 0, 0, time.UTC))
	addBlob(t, env.store.testStorer, testBlobHashA)
	addBlob(t, env.store.testStorer, testBlobHashB)
	require.NoError(t, env.store.Put(context.Background(),
		"metadata/\x1b[31mred/manifest.json.zst",
		bytes.NewReader([]byte("not a valid manifest"))))

	require.NoError(t, env.v.RemoteInfo(false))

	text := env.stdout.String()
	assert.NotContains(t, text, "\x1b")
	assert.NotContains(t, text, "31mred")
	assert.Contains(t, text, "Total (1 snapshots)")
	assert.Contains(t, text, "Orphaned (unreferenced):    unknown "+
		"(0 manifest(s) could not be read, "+
		"1 manifest(s) under a non-conforming name skipped)")
	assert.NotContains(t, text, "vaultik prune")

	env.stdout.Reset()
	require.NoError(t, env.v.RemoteInfo(true))

	out := env.stdout.String()
	assert.NotContains(t, out, "31mred")

	var doc map[string]any

	require.NoError(t, json.Unmarshal([]byte(out), &doc))
	assert.Contains(t, doc, "orphaned_blob_count")
	assert.Nil(t, doc["orphaned_blob_count"])
	assert.Contains(t, doc, "orphaned_blob_size")
	assert.Nil(t, doc["orphaned_blob_size"])
	assert.InDelta(t, 1, doc["skipped_manifest_count"], 0)
	assert.NotContains(t, doc, "unreadable_manifests")
}

// TestRemoteInfo_DirectoryWithoutManifestLeavesOrphansKnown checks that
// a directory under metadata/ holding no manifest.json.zst, such as one
// left by a backup interrupted before its manifest upload, leaves the
// orphan figures known. prune does not treat such a directory as a
// snapshot and deletes the blobs the report lists as orphaned.
func TestRemoteInfo_DirectoryWithoutManifestLeavesOrphansKnown(t *testing.T) {
	log.Initialize(log.Config{})
	t.Parallel()

	env := newListEnv(t)
	env.addRemote(t, listRemoteID, time.Date(2026, 3, 2, 0, 0, 0, 0, time.UTC))
	addBlob(t, env.store.testStorer, testBlobHashA)
	addBlob(t, env.store.testStorer, testBlobHashB)

	// One directory under a remote key and one under a non-conforming
	// name, each holding only a database.
	names := []string{snapshot.RemoteSnapshotKey(listLocalID), "\x1b[31mred"}
	for _, name := range names {
		require.NoError(t, env.store.Put(context.Background(),
			"metadata/"+name+"/db.zst.age",
			bytes.NewReader([]byte("not a valid database"))))
	}

	require.NoError(t, env.v.RemoteInfo(false))

	text := env.stdout.String()
	assert.NotContains(t, text, "\x1b")
	assert.Contains(t, text, "Downloading 1 manifest(s)...")
	assert.Contains(t, text, "Orphaned (unreferenced):    1 (")
	assert.Contains(t, text, "Run 'vaultik prune' to remove orphaned blobs.")

	env.stdout.Reset()
	require.NoError(t, env.v.RemoteInfo(true))

	var doc map[string]any

	require.NoError(t, json.Unmarshal(env.stdout.Bytes(), &doc))
	assert.InDelta(t, 1, doc["orphaned_blob_count"], 0)
	assert.NotContains(t, doc, "unreadable_manifests")
	assert.NotContains(t, doc, "skipped_manifest_count")
}