vaultik/internal/vaultik/info.go

package vaultik

import (
	"encoding/json"
	"fmt"
	"runtime"
	"sort"
	"strings"

	"github.com/dustin/go-humanize"
	"sneak.berlin/go/vaultik/internal/log"
)

// ShowInfo displays system and configuration information
func (v *Vaultik) ShowInfo() error {
	// The info report is the output this command exists to produce, so it
	// is written plain (markers would corrupt the aligned report) through
	// the UI writer's stdout; --quiet silences it like any other
	// non-error output.
	if v.UI.Quiet() {
		return nil
	}

	// System Information
	v.stdoutf("=== System Information ===\n")
	v.stdoutf("OS/Architecture: %s/%s\n", runtime.GOOS, runtime.GOARCH)
	v.stdoutf("Version:         %s\n", v.Globals.Version)
	v.stdoutf("Commit:          %s\n", v.Globals.Commit)
	v.stdoutf("Go Version:      %s\n", runtime.Version())
	v.printlnStdout()

	v.showStorageConfig()
	v.showBackupSettings()

	// Encryption Configuration
	v.stdoutf("=== Encryption Configuration ===\n")
	v.stdoutf("Recipients:\n")

	for _, recipient := range v.Config.AgeRecipients {
		v.stdoutf("  - %s\n", recipient)
	}

	v.printlnStdout()
	v.showLocalDatabase()

	return nil
}

// showStorageConfig prints the storage configuration section. The
// backend is selected by storage_url (s3://, file://, rclone://); the
// legacy s3.* fields are only printed when they're actually populated,
// since the URL scheme is the primary configuration.
func (v *Vaultik) showStorageConfig() {
	v.stdoutf("=== Storage Configuration ===\n")
	storageInfo := v.Storage.Info()
	v.stdoutf("Type:            %s\n", storageInfo.Type)
	v.stdoutf("Location:        %s\n", storageInfo.Location)

	if v.Config.StorageURL != "" {
		v.stdoutf("Storage URL:     %s\n", v.Config.StorageURL)
	}

	if v.Config.S3.Bucket != "" {
		v.stdoutf("S3 Bucket:       %s\n", v.Config.S3.Bucket)
	}

	if v.Config.S3.Prefix != "" {
		v.stdoutf("S3 Prefix:       %s\n", v.Config.S3.Prefix)
	}

	if v.Config.S3.Endpoint != "" {
		v.stdoutf("S3 Endpoint:     %s\n", v.Config.S3.Endpoint)
	}

	if v.Config.S3.Region != "" {
		v.stdoutf("S3 Region:       %s\n", v.Config.S3.Region)
	}

	v.printlnStdout()
}

// showBackupSettings prints the configured snapshots, exclude patterns,
// and chunking/compression settings.
func (v *Vaultik) showBackupSettings() {
	v.stdoutf("=== Backup Settings ===\n")

	// Show configured snapshots
	v.stdoutf("Snapshots:\n")

	for _, name := range v.Config.SnapshotNames() {
		snap := v.Config.Snapshots[name]
		v.stdoutf("  %s:\n", name)

		for _, path := range snap.Paths {
			v.stdoutf("    - %s\n", path)
		}

		if len(snap.Exclude) > 0 {
			v.stdoutf("    exclude: %s\n", strings.Join(snap.Exclude, ", "))
		}
	}

	// Global exclude patterns
	if len(v.Config.Exclude) > 0 {
		v.stdoutf("Global Exclude:  %s\n", strings.Join(v.Config.Exclude, ", "))
	}

	v.stdoutf("Compression:     zstd level %d\n", v.Config.CompressionLevel)
	v.stdoutf("Chunk Size:      %s\n", ubytes(int64(v.Config.ChunkSize)))
	v.stdoutf("Blob Size Limit: %s\n", ubytes(int64(v.Config.BlobSizeLimit)))
	v.printlnStdout()
}

// showLocalDatabase prints the local index database section, including
// record counts when the index exists.
func (v *Vaultik) showLocalDatabase() {
	v.stdoutf("=== Local Database ===\n")
	v.stdoutf("Index Path:      %s\n", v.Config.IndexPath)

	// Check if index file exists and get its size
	info, err := v.Fs.Stat(v.Config.IndexPath)
	if err != nil {
		v.stdoutf("Index Size:      (not created)\n")

		return
	}

	v.stdoutf("Index Size:      %s\n", ubytes(info.Size()))

	// Get snapshot count from database
	query := `SELECT COUNT(*) FROM snapshots WHERE completed_at IS NOT NULL`

	var snapshotCount int

	err = v.DB.Conn().QueryRowContext(v.ctx, query).Scan(&snapshotCount)
	if err == nil {
		v.stdoutf("Snapshots:       %d\n", snapshotCount)
	}

	// Get blob count from database
	query = `SELECT COUNT(*) FROM blobs`

	var blobCount int

	err = v.DB.Conn().QueryRowContext(v.ctx, query).Scan(&blobCount)
	if err == nil {
		v.stdoutf("Blobs:           %d\n", blobCount)
	}

	// Get file count from database
	query = `SELECT COUNT(*) FROM files`

	var fileCount int

	err = v.DB.Conn().QueryRowContext(v.ctx, query).Scan(&fileCount)
	if err == nil {
		v.stdoutf("Files:           %d\n", fileCount)
	}
}

// Table layout constants for the human-readable remote info output.
const (
	// snapshotIDColWidth is the SNAPSHOT column width in the remote
	// info table.
	snapshotIDColWidth = 45

	// metadataKeyParts is the minimum "/"-separated segment count of a
	// metadata object key (metadata/<snapshot-id>/<filename>).
	metadataKeyParts = 3

	// blobKeyParts is the minimum "/"-separated segment count of a blob
	// object key (blobs/<aa>/<bb>/<hash>).
	blobKeyParts = 4
)

// SnapshotMetadataInfo contains information about a single snapshot's metadata
//
//nolint:tagliatelle // snake_case is the established JSON output format
type SnapshotMetadataInfo struct {
	SnapshotID   string `json:"snapshot_id"`
	ManifestSize int64  `json:"manifest_size"`
	DatabaseSize int64  `json:"database_size"`
	TotalSize    int64  `json:"total_size"`
	BlobCount    int    `json:"blob_count"`
	BlobsSize    int64  `json:"blobs_size"`

	// Set when the listing holds this snapshot's manifest.json.zst. A
	// backup interrupted before its manifest upload leaves a directory
	// without one, which prune does not treat as a snapshot.
	hasManifest bool
}

// RemoteInfoResult contains all remote storage information
//
//nolint:tagliatelle // snake_case is the established JSON output format
type RemoteInfoResult struct {
	// Storage info
	StorageType     string `json:"storage_type"`
	StorageLocation string `json:"storage_location"`

	// Snapshot metadata
	Snapshots          []SnapshotMetadataInfo `json:"snapshots"`
	TotalMetadataSize  int64                  `json:"total_metadata_size"`
	TotalMetadataCount int                    `json:"total_metadata_count"`

	// All blobs on remote
	TotalBlobCount int   `json:"total_blob_count"`
	TotalBlobSize  int64 `json:"total_blob_size"`

	// Referenced blobs (from manifests)
	ReferencedBlobCount int   `json:"referenced_blob_count"`
	ReferencedBlobSize  int64 `json:"referenced_blob_size"`

	// Orphaned blobs. Both stay nil (null in the JSON) when a manifest
	// was listed but not read, since that snapshot's blobs would be
	// counted as orphaned.
	OrphanedBlobCount *int   `json:"orphaned_blob_count"`
	OrphanedBlobSize  *int64 `json:"orphaned_blob_size"`

	// Remote key of each snapshot whose manifest could not be read
	UnreadableManifests []string `json:"unreadable_manifests,omitempty"`

	// Number of manifests not read because the name above them under
	// metadata/ is not a remote key. The names themselves are not
	// reported: they come from the destination store and may hold
	// control characters.
	SkippedManifestCount int `json:"skipped_manifest_count,omitempty"`
}

// RemoteInfo displays information about remote storage
func (v *Vaultik) RemoteInfo(jsonOutput bool) error {
	log.Info("Starting remote storage info gathering")

	result := &RemoteInfoResult{}

	storageInfo := v.Storage.Info()
	result.StorageType = storageInfo.Type
	result.StorageLocation = storageInfo.Location

	// The human report is written only when it is neither the --json
	// document (which needs stdout to itself) nor silenced by --quiet. The
	// scan still runs in both cases so --json still gets a full result.
	showText := !jsonOutput && !v.UI.Quiet()

	if showText {
		v.stdoutf("=== Remote Storage ===\n")
		v.stdoutf("Type:     %s\n", storageInfo.Type)
		v.stdoutf("Location: %s\n", storageInfo.Location)
		v.printlnStdout()
		v.stdoutf("Scanning snapshot metadata...\n")
	}

	snapshotMetadata, snapshotIDs, skippedManifestCount, err := v.collectSnapshotMetadata()
	if err != nil {
		return err
	}

	result.SkippedManifestCount = skippedManifestCount

	if showText {
		manifestCount := 0

		for _, info := range snapshotMetadata {
			if info.hasManifest {
				manifestCount++
			}
		}

		v.stdoutf("Downloading %d manifest(s)...\n", manifestCount)
	}

	referencedBlobs, unreadableManifests := v.collectReferencedBlobsFromManifests(
		snapshotIDs, snapshotMetadata)
	result.UnreadableManifests = unreadableManifests

	v.populateRemoteInfoResult(result, snapshotMetadata, snapshotIDs, referencedBlobs)

	err = v.scanRemoteBlobStorage(result, referencedBlobs, showText)
	if err != nil {
		return err
	}

	log.Info("Remote info complete",
		"snapshots", result.TotalMetadataCount,
		"total_blobs", result.TotalBlobCount,
		"referenced_blobs", result.ReferencedBlobCount,
		"unreadable_manifests", len(result.UnreadableManifests))

	if jsonOutput {
		enc := json.NewEncoder(v.Stdout)
		enc.SetIndent("", "  ")

		return enc.Encode(result)
	}

	if showText {
		v.printRemoteInfoTable(result)
	}

	return nil
}

// collectSnapshotMetadata scans remote metadata and returns
// per-snapshot info, sorted IDs and the number of manifests it skipped
// because the name above them is not a remote key.
func (v *Vaultik) collectSnapshotMetadata() (
	map[string]*SnapshotMetadataInfo, []string, int, error,
) {
	snapshotMetadata := make(map[string]*SnapshotMetadataInfo)
	skippedManifestCount := 0

	metadataCh := v.Storage.ListStream(v.ctx, "metadata/")
	for obj := range metadataCh {
		if obj.Err != nil {
			return nil, nil, 0, fmt.Errorf("listing metadata: %w", obj.Err)
		}

		parts := strings.Split(obj.Key, "/")
		if len(parts) < metadataKeyParts {
			continue
		}

		snapshotID := parts[1]
		filename := parts[2]
		isManifest := filename == "manifest.json.zst"

		// The name comes from the destination store, which is not
		// trusted, and is printed in the report. Accept it only in the
		// form of a remote key.
		if !isBlobHash(snapshotID) {
			log.Warn("Skipping non-conforming key under metadata/",
				"key", obj.Key)

			if isManifest {
				skippedManifestCount++
			}

			continue
		}

		if _, exists := snapshotMetadata[snapshotID]; !exists {
			snapshotMetadata[snapshotID] = &SnapshotMetadataInfo{SnapshotID: snapshotID}
		}

		info := snapshotMetadata[snapshotID]

		if isManifest {
			info.hasManifest = true
		}

		if strings.HasPrefix(filename, "manifest") {
			info.ManifestSize = obj.Size
		} else if strings.HasPrefix(filename, "db") {
			info.DatabaseSize = obj.Size
		}

		info.TotalSize = info.ManifestSize + info.DatabaseSize
	}

	var snapshotIDs []string
	for id := range snapshotMetadata {
		snapshotIDs = append(snapshotIDs, id)
	}

	sort.Strings(snapshotIDs)

	return snapshotMetadata, snapshotIDs, skippedManifestCount, nil
}

// collectReferencedBlobsFromManifests downloads the listed manifests
// and returns referenced blob hashes with sizes, and the remote keys
// of the manifests it could not read.
func (v *Vaultik) collectReferencedBlobsFromManifests(
	snapshotIDs []string, snapshotMetadata map[string]*SnapshotMetadataInfo,
) (map[string]int64, []string) {
	referencedBlobs := make(map[string]int64)

	var unreadable []string

	for _, snapshotID := range snapshotIDs {
		info := snapshotMetadata[snapshotID]
		if !info.hasManifest {
			continue
		}

		// snapshotIDs here are remote keys, taken straight from the
		// metadata/ listing. downloadManifestByKey is the single reader
		// for remote manifests; see its doc comment.
		manifest, err := v.downloadManifestByKey(snapshotID)
		if err != nil {
			log.Warn("Failed to read manifest", "snapshot", snapshotID, "error", err)

			unreadable = append(unreadable, snapshotID)

			continue
		}

		info.BlobCount = manifest.BlobCount

		var blobsSize int64

		for _, blob := range manifest.Blobs {
			referencedBlobs[blob.Hash] = blob.CompressedSize
			blobsSize += blob.CompressedSize
		}

		info.BlobsSize = blobsSize
	}

	return referencedBlobs, unreadable
}

// populateRemoteInfoResult fills in the result's snapshot and
// referenced blob stats.
func (v *Vaultik) populateRemoteInfoResult(
	result *RemoteInfoResult,
	snapshotMetadata map[string]*SnapshotMetadataInfo,
	snapshotIDs []string,
	referencedBlobs map[string]int64,
) {
	var totalMetadataSize int64

	for _, id := range snapshotIDs {
		info := snapshotMetadata[id]
		result.Snapshots = append(result.Snapshots, *info)
		totalMetadataSize += info.TotalSize
	}

	result.TotalMetadataSize = totalMetadataSize
	result.TotalMetadataCount = len(snapshotIDs)

	for _, size := range referencedBlobs {
		result.ReferencedBlobCount++
		result.ReferencedBlobSize += size
	}
}

// scanRemoteBlobStorage lists all blobs on remote and computes orphan
// stats when every listed manifest was read. showText is true only
// when the human report is being printed (not --json, not --quiet),
// gating the progress line.
func (v *Vaultik) scanRemoteBlobStorage(
	result *RemoteInfoResult, referencedBlobs map[string]int64, showText bool,
) error {
	if showText {
		v.stdoutf("Scanning blobs...\n")
	}

	blobCh := v.Storage.ListStream(v.ctx, "blobs/")
	allBlobs := make(map[string]int64)

	for obj := range blobCh {
		if obj.Err != nil {
			return fmt.Errorf("listing blobs: %w", obj.Err)
		}

		parts := strings.Split(obj.Key, "/")
		if len(parts) < blobKeyParts {
			continue
		}

		hash := parts[3]
		allBlobs[hash] = obj.Size
		result.TotalBlobCount++
		result.TotalBlobSize += obj.Size
	}

	// A blob named only by a manifest that could not be read, or by one
	// under a skipped name, would be counted as orphaned, so the orphan
	// figures stay unknown.
	if len(result.UnreadableManifests) > 0 || result.SkippedManifestCount > 0 {
		return nil
	}

	var (
		orphanedCount int
		orphanedSize  int64
	)

	for hash, size := range allBlobs {
		if _, referenced := referencedBlobs[hash]; !referenced {
			orphanedCount++
			orphanedSize += size
		}
	}

	result.OrphanedBlobCount = &orphanedCount
	result.OrphanedBlobSize = &orphanedSize

	return nil
}

// printRemoteInfoTable renders the human-readable remote info output
func (v *Vaultik) printRemoteInfoTable(result *RemoteInfoResult) {
	const (
		rowFormat     = "%-45s %12s %12s %12s %10s %12s\n"
		sizeColWidth  = 12
		countColWidth = 10
	)

	v.stdoutf("\n=== Snapshot Metadata ===\n")

	if len(result.Snapshots) == 0 {
		v.stdoutf("No snapshots found\n")
	} else {
		separator := fmt.Sprintf(rowFormat,
			strings.Repeat("-", snapshotIDColWidth),
			strings.Repeat("-", sizeColWidth),
			strings.Repeat("-", sizeColWidth),
			strings.Repeat("-", sizeColWidth),
			strings.Repeat("-", countColWidth),
			strings.Repeat("-", sizeColWidth))

		v.stdoutf(rowFormat,
			"SNAPSHOT", "MANIFEST", "DATABASE", "TOTAL", "BLOBS", "BLOB SIZE")
		v.stdoutf("%s", separator)

		for _, info := range result.Snapshots {
			v.stdoutf(rowFormat,
				truncateString(info.SnapshotID, snapshotIDColWidth),
				ubytes(info.ManifestSize),
				ubytes(info.DatabaseSize),
				ubytes(info.TotalSize),
				humanize.Comma(int64(info.BlobCount)),
				ubytes(info.BlobsSize),
			)
		}

		v.stdoutf("%s", separator)
		v.stdoutf("%-45s %12s %12s %12s\n",
			fmt.Sprintf("Total (%d snapshots)", result.TotalMetadataCount),
			"", "", ubytes(result.TotalMetadataSize))
	}

	v.stdoutf("\n=== Blob Storage ===\n")
	v.stdoutf("Total blobs on remote:      %s (%s)\n",
		humanize.Comma(int64(result.TotalBlobCount)),
		ubytes(result.TotalBlobSize))
	v.stdoutf("Referenced by snapshots:    %s (%s)\n",
		humanize.Comma(int64(result.ReferencedBlobCount)),
		ubytes(result.ReferencedBlobSize))

	if result.OrphanedBlobCount == nil {
		v.stdoutf("Orphaned (unreferenced):    unknown "+
			"(%d manifest(s) could not be read, "+
			"%d manifest(s) under a non-conforming name skipped)\n",
			len(result.UnreadableManifests), result.SkippedManifestCount)

		return
	}

	v.stdoutf("Orphaned (unreferenced):    %s (%s)\n",
		humanize.Comma(int64(*result.OrphanedBlobCount)),
		ubytes(*result.OrphanedBlobSize))

	if *result.OrphanedBlobCount > 0 {
		v.stdoutf("\nRun 'vaultik prune' to remove orphaned blobs.\n")
	}
}

// ellipsis is appended by truncateString when it shortens a string.
const ellipsis = "..."

// truncateString truncates a string to maxLen, adding "..." if truncated
func truncateString(s string, maxLen int) string {
	if len(s) <= maxLen {
		return s
	}

	if maxLen <= len(ellipsis) {
		return s[:maxLen]
	}

	return s[:maxLen-len(ellipsis)] + ellipsis
}