Compare commits

...
Author SHA1 Message Date
clawbot 13549a442c Print snapshot list and purge sizes like every other command (closes #312)
check / check (push) Waiting to run
`snapshot list`, the `snapshot purge` listing and the `bytes` value in
terminal log lines divided by 1024 while labelling the result KB or MB,
so 6,329,198 bytes read 6.0 MB there and 6.3 MB in every other command.
All three now use humanize.Bytes, as the rest of the program does, and
the 1024-based helper in internal/vaultik is removed.

The size shared by the list tests is now 5,000,000 bytes, which the two
ways of counting print differently.

Judgement call: the log handler's copy of the formatter is changed too,
since the issue asks that every command print a byte count the same way.

Model: opus-5-5
2026-10-13 11:50:42 +00:00
clawbot d1213ecb34 Make a leading **/ in an exclude pattern match at the top level (closes #303)
check / check (push) Waiting to run
An unanchored exclude pattern such as **/node_modules or **/*.pyc
needed a / before the name, so it excluded sub/node_modules and
sub/y.pyc but backed up node_modules/ and x.pyc directly under the
snapshot path. An unanchored pattern already matches at every depth,
so the leading **/ is now dropped when the pattern is compiled and,
as in gitignore, the pattern matches the top level too.

Judgement call: an anchored /**/x is left as it was; the issue covers
patterns that start with **/.

Model: opus-5-5
2026-10-13 13:50:11 +02:00
8 changed files with 115 additions and 36 deletions
+7 -10
View File
@@ -10,6 +10,8 @@ import (
"sync"
"time"
"unicode"
"github.com/dustin/go-humanize"
)
// groupSeparator joins an open group path to an attribute key. This
@@ -304,18 +306,13 @@ func formatDuration(d time.Duration) string {
}
}
// formatBytes formats bytes in a human-readable way
// formatBytes formats a byte count with humanize.Bytes, as every command
// prints one. humanize.Bytes takes no negative count, so one is printed
// as it is.
func formatBytes(b int64) string {
const unit = 1024
if b < unit {
if b < 0 {
return fmt.Sprintf("%d B", b)
}
div, exp := int64(unit), 0
for n := b / unit; n >= unit; n /= unit {
div *= unit
exp++
}
return fmt.Sprintf("%.1f %cB", float64(b)/float64(div), "KMGTPE"[exp])
return humanize.Bytes(uint64(b))
}
+5 -4
View File
@@ -200,7 +200,8 @@ func TestTTYHandlerWithGroupQualifiesKeys(t *testing.T) {
func TestTTYHandlerByteFormattingSurvivesGrouping(t *testing.T) {
t.Parallel()
const oneAndAHalfKiB = 1536
// Printed as "1.0 MB", in powers of 1000 like every other byte count.
const oneMegabyte = 1_000_000
for name, testCase := range map[string]struct {
derive func(*slog.Logger) *slog.Logger
@@ -223,13 +224,13 @@ func TestTTYHandlerByteFormattingSurvivesGrouping(t *testing.T) {
var buf bytes.Buffer
logger := slog.New(log.NewTTYHandler(&buf, debugHandlerOptions()))
testCase.derive(logger).Info("uploaded", "bytes", oneAndAHalfKiB)
testCase.derive(logger).Info("uploaded", "bytes", oneMegabyte)
line := ansiEscape.ReplaceAllString(buf.String(), "")
assert.Contains(t, line, testCase.key+"=1.5 KB",
assert.Contains(t, line, testCase.key+"=1.0 MB",
"a byte count must be human-readable however it is qualified")
assert.NotContains(t, line, strconv.Itoa(oneAndAHalfKiB),
assert.NotContains(t, line, strconv.Itoa(oneMegabyte),
"the raw number must not survive the formatting")
})
}
+47
View File
@@ -531,3 +531,50 @@ func TestExcludePatterns_UnanchoredPatternFile(t *testing.T) {
require.Equal(t, 1, result.FilesScanned,
"Unanchored pattern for file should match anywhere")
}
func TestExcludePatterns_DoubleStarDirectoryAtEveryDepth(t *testing.T) {
t.Parallel()
// As in gitignore, a leading **/ also matches directly under the source dir
fs := setupAnchoredTestFS(t)
scanner, repos, cleanup := createTestScanner(t, fs, []string{"**/projectname"})
defer cleanup()
ctx := context.Background()
createSnapshotRecord(ctx, t, repos, "test-snapshot")
result, err := scanner.Scan(ctx, "/backup", "test-snapshot")
require.NoError(t, err)
// **/projectname should exclude BOTH:
// - /backup/projectname/file.txt
// - /backup/otherproject/projectname/file.txt
// Total files: 4, excluded: 2
require.Equal(t, 2, result.FilesScanned,
"**/ directory pattern should match at the top level and nested")
}
func TestExcludePatterns_DoubleStarFileAtEveryDepth(t *testing.T) {
t.Parallel()
// As in gitignore, a leading **/ also matches directly under the source dir
fs := setupAnchoredTestFS(t)
scanner, repos, cleanup := createTestScanner(t, fs, []string{"**/*.txt"})
defer cleanup()
ctx := context.Background()
createSnapshotRecord(ctx, t, repos, "test-snapshot")
result, err := scanner.Scan(ctx, "/backup", "test-snapshot")
require.NoError(t, err)
// **/*.txt should exclude ALL .txt files:
// - /backup/file.txt
// - /backup/projectname/file.txt
// - /backup/otherproject/projectname/file.txt
// Total files: 4, excluded: 3
require.Equal(t, 1, result.FilesScanned,
"**/ file pattern should match at the top level and nested")
}
+8
View File
@@ -2018,6 +2018,14 @@ func compileExcludePatterns(patterns []string) []compiledPattern {
// Remove trailing slash if present (directory indicator)
pattern = strings.TrimSuffix(pattern, "/")
// A leading "**/" demands a "/" before the name and so misses an
// entry directly under the source path. An unanchored pattern
// already matches at every depth, so drop the prefix: as in
// gitignore, "**/x" then also matches a top-level "x".
if !anchored {
pattern = strings.TrimPrefix(pattern, "**/")
}
// Compile the glob pattern
// For patterns without path separators, we need to match them as components
// e.g., ".git" should match ".git" anywhere in the path
-16
View File
@@ -89,22 +89,6 @@ type SnapshotInfo struct {
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) {
+1 -1
View File
@@ -633,7 +633,7 @@ func (v *Vaultik) confirmAndExecutePurge(
v.stdoutf(" %s (%s, %s)\n",
snap.ID,
snap.Timestamp.Format("2006-01-02 15:04:05"),
formatBytes(snap.CompressedSize))
ubytes(snap.CompressedSize))
}
}
+3 -3
View File
@@ -553,8 +553,8 @@ func (v *Vaultik) printSnapshotTable(snapshots []SnapshotInfo) error {
if snap.LocallyTracked {
id = snap.ID.String()
uncompressed = formatBytes(snap.UncompressedSize)
newChunks = formatBytes(snap.NewChunkSize)
uncompressed = ubytes(snap.UncompressedSize)
newChunks = ubytes(snap.NewChunkSize)
} else {
id = formatRemoteOnlyID(snap.RemoteKey)
uncompressed = remoteOnlyCell
@@ -564,7 +564,7 @@ func (v *Vaultik) printSnapshotTable(snapshots []SnapshotInfo) error {
_, err = fmt.Fprintf(w, "%s\t%s\t%s\t%s\t%s\n",
id,
snap.Timestamp.Format("2006-01-02 15:04:05"),
formatBytes(snap.CompressedSize),
ubytes(snap.CompressedSize),
uncompressed,
newChunks)
if err != nil {
+44 -2
View File
@@ -212,8 +212,8 @@ const (
listConfiguredName = "home"
listLocalID = "testhost_home_2026-03-01T10:00:00Z"
listRemoteID = "otherhost_media_2026-03-02T11:22:33Z"
// fiveMegabytes formats as "5.0 MB" through formatBytes.
fiveMegabytes = 5 * 1024 * 1024
// fiveMegabytes is printed as "5.0 MB" by every command.
fiveMegabytes = 5_000_000
)
// TestListSnapshots_RemoteWithoutSecretKey is the regression guard for
@@ -306,6 +306,48 @@ func TestListSnapshots_RemoteOnlyRowRendering(t *testing.T) {
"are not in the local index")
}
// TestSnapshotListAndPurgePrintSizesLikeRemoteInfo checks that the
// `snapshot list` table and the purge listing print a byte count the way
// `remote info` does: in powers of 1000, as the MB label says.
func TestSnapshotListAndPurgePrintSizesLikeRemoteInfo(t *testing.T) {
log.Initialize(log.Config{})
t.Parallel()
const wantSize = "5.0 MB" // fiveMegabytes
env := newListEnv(t)
// A remote-only snapshot: `snapshot list` and `remote info` both take
// its size from the manifest.
remoteKey := env.addRemote(t, listRemoteID,
time.Date(2026, 3, 2, 11, 22, 33, 0, time.UTC))
// A locally tracked snapshot of the same size for the purge to list.
// The purge prints the snapshot's blob size, the last argument here.
start := time.Date(2026, 3, 1, 10, 0, 0, 0, time.UTC)
env.addLocal(t, listLocalID, start)
env.addRemote(t, listLocalID, start)
require.NoError(t, env.v.Repositories.Snapshots.UpdateCounts(
context.Background(), nil, listLocalID, 0, 0, 0, 0, fiveMegabytes))
require.NoError(t, env.v.RemoteInfo(false))
assert.Contains(t, findTableRow(t, env.stdout.String(), remoteKey[:16]),
wantSize, "remote info")
env.stdout.Reset()
require.NoError(t, env.v.ListSnapshots(false))
assert.Contains(t, findTableRow(t, env.stdout.String(),
"<remote only:"+remoteKey[:12]+">"), wantSize, "snapshot list")
// Without --force and with nothing on stdin the purge lists what it
// would delete, reads no confirmation, and deletes nothing.
env.stdout.Reset()
require.NoError(t, env.v.PurgeSnapshotsWithOptions(
&vaultik.SnapshotPurgeOptions{OlderThan: "1d"}))
assert.Contains(t, findTableRow(t, env.stdout.String(), listLocalID),
wantSize, "snapshot purge")
}
// findTableRow returns the single output line containing needle.
func findTableRow(t *testing.T, out, needle string) string {
t.Helper()