vaultik/internal/vaultik/helpers.go

package vaultik

import (
	"errors"
	"fmt"
	"math"
	"regexp"
	"strconv"
	"strings"
	"time"

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

// percentScale converts a 0..1 ratio into a percentage.
const percentScale = 100

// progressLogEvery is how many processed items pass between progress
// log lines in long-running loops.
const progressLogEvery = 100

// ubytes renders a byte count with humanize.Bytes, clamping negative
// values to zero so the int64→uint64 conversion cannot overflow.
func ubytes(n int64) string {
	if n < 0 {
		n = 0
	}

	return humanize.Bytes(uint64(n))
}

// Sentinel errors for snapshot ID and duration parsing.
var (
	errMalformedSnapshotID = errors.New(
		"invalid snapshot ID format: expected hostname_snapshotname_timestamp")
	errInvalidDuration  = errors.New("invalid duration")
	errUnknownTimeUnit  = errors.New("unknown time unit")
	errNegativeDuration = errors.New("negative durations are not supported")
)

// Time-unit lengths used by parseDuration.
const (
	day   = 24 * time.Hour
	week  = 7 * day
	month = 30 * day
	year  = 365 * day
)

// maxDuration is the largest value a time.Duration can hold, about 292
// years.
const maxDuration = time.Duration(math.MaxInt64)

// A snapshot ID split on "_" has at least a hostname and a trailing
// timestamp.
const minSnapshotIDParts = 2

// SnapshotInfo contains information about a snapshot.
//
// LocallyTracked says which of the two sources this row came from, and
// therefore which fields are meaningful:
//
//   - true: the snapshot is in the local index. ID is its human
//     snapshot ID and UncompressedSize/NewChunkSize are populated.
//   - false: the snapshot was found only on the destination store. ID
//     is empty, because the human ID cannot be recovered from remote
//     storage without the age secret key (see RemoteKey), and
//     UncompressedSize/NewChunkSize are zero because they are computed
//     from local index rows that do not exist.
//
// RemoteKey is always populated: for a locally tracked snapshot it is
// the key the snapshot would occupy on the destination store, and for a
// remote-only snapshot it is the only identifier available.
//
// RemotePresent reports whether the snapshot's metadata was seen on the
// destination store. It is nil when the destination could not be
// listed, so "absent" and "unknown" stay distinguishable.
//
//nolint:tagliatelle // snake_case is the established output format
type SnapshotInfo struct {
	ID               types.SnapshotID `json:"id"`
	RemoteKey        string           `json:"remote_key"`
	Timestamp        time.Time        `json:"timestamp"`
	CompressedSize   int64            `json:"compressed_size"`
	UncompressedSize int64            `json:"uncompressed_size,omitempty"`
	NewChunkSize     int64            `json:"new_chunk_size,omitempty"`
	LocallyTracked   bool             `json:"locally_tracked"`
	RemotePresent    *bool            `json:"remote_present"`
}

// formatBytes formats bytes in a human-readable format
func formatBytes(bytes int64) string {
	const unit = 1024
	if bytes < unit {
		return fmt.Sprintf("%d B", bytes)
	}

	div, exp := int64(unit), 0
	for n := bytes / unit; n >= unit; n /= unit {
		div *= unit
		exp++
	}

	return fmt.Sprintf("%.1f %cB", float64(bytes)/float64(div), "KMGTPE"[exp])
}

// parseSnapshotTimestamp extracts the timestamp from a snapshot ID
// Format: hostname_snapshotname_2026-01-12T14:41:15Z
func parseSnapshotTimestamp(snapshotID string) (time.Time, error) {
	parts := strings.Split(snapshotID, "_")
	if len(parts) < minSnapshotIDParts {
		return time.Time{}, errMalformedSnapshotID
	}

	// Last part is the RFC3339 timestamp
	timestampStr := parts[len(parts)-1]

	timestamp, err := time.Parse(time.RFC3339, timestampStr)
	if err != nil {
		return time.Time{}, fmt.Errorf("invalid timestamp: %w", err)
	}

	return timestamp.UTC(), nil
}

// parseSnapshotName extracts the snapshot name from a snapshot ID of the
// form hostname_name_timestamp, given the hostname stored with that
// snapshot. The hostname and the name may both contain underscores, so the
// name is what is left after removing the short hostname and its "_" from
// the front and the last "_" and the timestamp from the end. Returns "" for
// an ID with no name (hostname_timestamp), and for an ID that does not start
// with that hostname, which CreateSnapshotWithName never writes.
func parseSnapshotName(snapshotID, hostname string) string {
	prefix := snapshot.ShortHostname(hostname) + "_"

	rest, ok := strings.CutPrefix(snapshotID, prefix)
	if !ok {
		return ""
	}

	end := strings.LastIndex(rest, "_")
	if end < 0 {
		return ""
	}

	return rest[:end]
}

// parseDuration parses a duration string with support for human-friendly units:
// d/day/days, w/week/weeks, mo/month/months, y/year/years, plus standard Go
// duration units. Following Go, m is minutes and mo is months. A bare number,
// an unknown unit, a negative value, and a total longer than maxDuration are
// all rejected. Outside the Go units the input must be whole numbers each
// followed directly by a unit (2w3d), so 1.0y and 30 days are errors;
// decimals work only in Go units (1.5h).
func parseDuration(s string) (time.Duration, error) {
	if strings.HasPrefix(strings.TrimSpace(s), "-") {
		return 0, errNegativeDuration
	}

	// A bare number has no unit, but time.ParseDuration accepts 0, which
	// would put the cutoff at now and select every snapshot.
	_, err := strconv.ParseFloat(s, 64)
	if err == nil {
		return 0, fmt.Errorf("%w: %q", errInvalidDuration, s)
	}

	d, err := time.ParseDuration(s)
	if err == nil {
		return d, nil
	}

	if !regexp.MustCompile(`^(\d+[a-zA-Z]+)+$`).MatchString(s) {
		return 0, fmt.Errorf("%w: %q", errInvalidDuration, s)
	}

	re := regexp.MustCompile(`(\d+)([a-zA-Z]+)`)
	matches := re.FindAllStringSubmatch(s, -1)

	var total time.Duration

	for _, match := range matches {
		n, err := strconv.Atoi(match[1])
		if err != nil {
			return 0, fmt.Errorf("invalid number %q: %w", match[1], err)
		}

		var unitLength time.Duration

		unit := strings.ToLower(match[2])
		switch unit {
		case "d", "day", "days":
			unitLength = day
		case "w", "week", "weeks":
			unitLength = week
		case "mo", "month", "months":
			unitLength = month
		case "y", "year", "years":
			unitLength = year
		default:
			return 0, fmt.Errorf("%w %q", errUnknownTimeUnit, unit)
		}

		// Past maxDuration the sum wraps to a negative value, which would
		// put the purge cutoff in the future.
		if time.Duration(n) > (maxDuration-total)/unitLength {
			return 0, fmt.Errorf("%w: %q is longer than about 292 years",
				errInvalidDuration, s)
		}

		total += time.Duration(n) * unitLength
	}

	return total, nil
}