Compare commits
3
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
2b46d374b1 | ||
|
|
ee09cda355 | ||
|
|
aa99b37b99 |
@@ -29,6 +29,29 @@
|
||||
|
||||
# Completed Steps
|
||||
|
||||
- `README.md` rewritten from scratch, sentence by sentence, as a newcomer reads
|
||||
it. It leads with what the program is and how to use it. A reference section
|
||||
covers every setting and every subcommand. Development and testing come last.
|
||||
Every statement was checked against the code on `next`. Five comments in
|
||||
`main_test.go` cite "Settings", where their rules now live. One comment each
|
||||
in `scan_test.go`, `trees_test.go` and `exclude_test.go` cites what the README
|
||||
now says (2026-10-26, https://git.eeqj.de/sneak/sfdupes/issues/135)
|
||||
|
||||
- an operand at or inside a directory named `.zfs` is never scanned, whether
|
||||
given alone or under another operand. `scan` warns about it, counts it as
|
||||
skipped and does not walk it (2026-10-26,
|
||||
https://git.eeqj.de/sneak/sfdupes/issues/142)
|
||||
|
||||
- a file or directory removed while the scan runs is not an error, in the walk
|
||||
or in the hash phase. The scan prints no line for it and does not count it as
|
||||
skipped. When the first of several hard links to a file is gone, the hash
|
||||
phase reads the next one instead. On a terminal every progress display starts
|
||||
with the spinner, the hash phase's included. A phase with an exact total ends
|
||||
its line with its percent and a 10-column bar at the terminal's right edge,
|
||||
which no longer moves as the line's length changes. A line too wide for the
|
||||
terminal now loses its rate before its bar. The time remaining is labelled
|
||||
`remain`, not `eta` (2026-10-26, https://git.eeqj.de/sneak/sfdupes/issues/133)
|
||||
|
||||
- the `head`, `tail` and `content` columns are BLOBs, each holding the raw 32
|
||||
bytes of a SHA-256, half the size of the hex text they held. The hashes stay
|
||||
raw from the hash phase through the database to `report` and `trees`. Reading
|
||||
|
||||
+3
-1
@@ -17,7 +17,9 @@ import (
|
||||
func TestDefaultExcludes(t *testing.T) {
|
||||
t.Parallel()
|
||||
|
||||
// README "Rules for the walk": each system's list.
|
||||
// README "Rules for the walk": the Linux and macOS lists, and none
|
||||
// on any other system. The Windows list exists in the code only: the
|
||||
// binary does not build for Windows, so the README leaves it out.
|
||||
cases := map[string][]string{
|
||||
goosLinux: {"/proc", "/sys", "/dev", "/run", "/tmp", "/var/tmp"},
|
||||
goosDarwin: {
|
||||
|
||||
+2
-2
@@ -12,13 +12,13 @@ import (
|
||||
// infoOpenLine is the plain line of info's open phase when it opens the
|
||||
// database at once; it prints it as the phase starts and as it ends.
|
||||
const infoOpenLine = "[1/2] open: opening the database, elapsed 0s, " +
|
||||
"eta unknown"
|
||||
"remain unknown"
|
||||
|
||||
// infoCountLine is the plain line of info's count phase when the count
|
||||
// takes under a second; it prints it as the phase starts and as it
|
||||
// ends.
|
||||
const infoCountLine = "[2/2] count: counting the records, elapsed 0s, " +
|
||||
"eta unknown"
|
||||
"remain unknown"
|
||||
|
||||
// infoRecs are four records: a duplicate pair, a file of 20 MiB and
|
||||
// another small file.
|
||||
|
||||
+136
-25
@@ -393,7 +393,7 @@ func TestRunNamesRelativeDatabase(t *testing.T) {
|
||||
}
|
||||
|
||||
func TestRunUsesDatabaseThroughSymlinkedDirectory(t *testing.T) {
|
||||
// README §Database: the path names the file exactly. With link a
|
||||
// README §Settings: the path names the file exactly. With link a
|
||||
// symlink to the directory real/sub, link/../db.sqlite names
|
||||
// real/db.sqlite, not db.sqlite beside link. Every subcommand must
|
||||
// use that file, relative or absolute, and its first line must name
|
||||
@@ -648,7 +648,7 @@ func TestRunUsageErrors(t *testing.T) {
|
||||
}
|
||||
|
||||
func TestRunScanRejectsWorkersBelowOne(t *testing.T) {
|
||||
// README §scan mode: --workers below 1 is a usage error reported in
|
||||
// README §Settings: --workers below 1 is a usage error reported in
|
||||
// one line on stderr, before the scan opens the database.
|
||||
for _, workers := range []string{"0", "-1"} {
|
||||
t.Run(workers, func(t *testing.T) {
|
||||
@@ -686,8 +686,8 @@ func TestRunScanRejectsWorkersBelowOne(t *testing.T) {
|
||||
func TestRunHelp(t *testing.T) {
|
||||
t.Parallel()
|
||||
|
||||
// README §Subcommands: help goes to stderr, exits 0, and leaves
|
||||
// stdout empty.
|
||||
// README §Settings: help goes to stderr, exits 0, and leaves stdout
|
||||
// empty.
|
||||
cases := [][]string{{"--help"}, {"-h"}, {cmdScan, "--help"}}
|
||||
|
||||
for _, args := range cases {
|
||||
@@ -713,8 +713,8 @@ func TestRunHelp(t *testing.T) {
|
||||
func TestRunVersion(t *testing.T) {
|
||||
t.Parallel()
|
||||
|
||||
// README §Subcommands: the version is one line on stdout, with
|
||||
// nothing on stderr, and exits 0.
|
||||
// README §Settings: the version is one line on stdout, with nothing
|
||||
// on stderr, and exits 0.
|
||||
info, _ := debug.ReadBuildInfo()
|
||||
|
||||
for _, arg := range []string{"--version", "-v"} {
|
||||
@@ -773,8 +773,8 @@ func TestBuildVersion(t *testing.T) {
|
||||
func TestRunVersionWriteFailureIsFatal(t *testing.T) {
|
||||
t.Parallel()
|
||||
|
||||
// README §Error handling: a stdout write failure exits 1, reported
|
||||
// in one line on stderr.
|
||||
// README §Error handling: a failed write to stdout is a fatal error,
|
||||
// exit 1, reported on stderr starting with "sfdupes:".
|
||||
var stderr bytes.Buffer
|
||||
|
||||
code := run([]string{"--version"}, failingWriter{}, &stderr)
|
||||
@@ -928,24 +928,21 @@ func TestRunScanWalksOperandUnderSymlinkOperand(t *testing.T) {
|
||||
}
|
||||
|
||||
func TestRunScanSkipsZFSOperand(t *testing.T) {
|
||||
path := testDBPath(t)
|
||||
t.Setenv(databaseEnv, path)
|
||||
|
||||
zfs := filepath.Join(t.TempDir(), ".zfs")
|
||||
snapshot := filepath.Join(zfs, "snapshot", "hourly")
|
||||
f := writeFile(t, snapshot, "f", pattern(1, 10))
|
||||
f := writeFile(t, zfs, "snapshot/hourly/f", pattern(1, 10))
|
||||
|
||||
// An operand beneath a .zfs directory is walked, because it is not
|
||||
// itself named .zfs.
|
||||
scanOK(t, snapshot)
|
||||
// No scan records a file inside a .zfs directory, so the record
|
||||
// beneath the operand is written straight into the database.
|
||||
path := seedDatabase(t, []scanRec{{size: 10, path: f}})
|
||||
t.Setenv(databaseEnv, path)
|
||||
|
||||
assertOperandSkipped(t, path, zfs, ".zfs directory", f)
|
||||
}
|
||||
|
||||
// assertOperandSkipped scans operand alone and checks that it is skipped
|
||||
// as kind: a warning naming it, one skip in the summary, exit 0, and the
|
||||
// record for kept, which an earlier scan stored beneath operand, still
|
||||
// in the database at dbPath.
|
||||
// record for kept, stored beneath operand before this scan, still in the
|
||||
// database at dbPath.
|
||||
func assertOperandSkipped(t *testing.T, dbPath, operand, kind,
|
||||
kept string,
|
||||
) {
|
||||
@@ -974,6 +971,121 @@ func assertOperandSkipped(t *testing.T, dbPath, operand, kind,
|
||||
recordByPath(t, dbRecords(t, db), kept)
|
||||
}
|
||||
|
||||
// TestRunScanSkipsOperandInsideZFS scans a directory inside a .zfs
|
||||
// directory, first alone and then under another operand. Each time it
|
||||
// is warned about and counted as skipped, and nothing in it is walked.
|
||||
// The other operand is scanned as usual.
|
||||
func TestRunScanSkipsOperandInsideZFS(t *testing.T) {
|
||||
path := testDBPath(t)
|
||||
t.Setenv(databaseEnv, path)
|
||||
|
||||
dir := t.TempDir()
|
||||
hourly := filepath.Join(dir, ".zfs", "snapshot", "hourly")
|
||||
writeFile(t, hourly, "f", pattern(1, 10))
|
||||
f := writeFile(t, dir, "f", pattern(2, 10))
|
||||
|
||||
warning := "walk " + hourly + ": skipping operand inside a .zfs directory\n"
|
||||
|
||||
for _, tc := range []struct {
|
||||
operands []string
|
||||
summary string
|
||||
}{
|
||||
{
|
||||
[]string{hourly},
|
||||
"scan: 0 files seen (0 added, 0 updated, 0 removed, " +
|
||||
"0 unchanged), 1 skipped\n",
|
||||
},
|
||||
{
|
||||
[]string{dir, hourly},
|
||||
"scan: 1 files seen (1 added, 0 updated, 0 removed, " +
|
||||
"0 unchanged), 1 skipped\n",
|
||||
},
|
||||
} {
|
||||
stderr := scanOK(t, tc.operands...)
|
||||
if !strings.Contains(stderr, warning) ||
|
||||
!strings.Contains(stderr, tc.summary) {
|
||||
t.Errorf("scan %q: stderr = %q, want %q and %q", tc.operands,
|
||||
stderr, warning, tc.summary)
|
||||
}
|
||||
}
|
||||
|
||||
db, err := openDB(path, reportParams)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
t.Cleanup(func() { _ = db.Close() })
|
||||
|
||||
if got := recordPaths(dbRecords(t, db)); !slices.Equal(got, []string{f}) {
|
||||
t.Errorf("records = %q, want %q", got, []string{f})
|
||||
}
|
||||
}
|
||||
|
||||
// TestRunScanSkipsOperandThroughSymlinkIntoZFS scans snaps/daily, where
|
||||
// snaps is a symlink to pool/.zfs/snapshot. The operand is warned about
|
||||
// by the path given, counted as skipped, and not walked.
|
||||
func TestRunScanSkipsOperandThroughSymlinkIntoZFS(t *testing.T) {
|
||||
t.Setenv(databaseEnv, testDBPath(t))
|
||||
|
||||
dir := t.TempDir()
|
||||
writeFile(t, dir, "pool/.zfs/snapshot/daily/f", pattern(1, 10))
|
||||
|
||||
snaps := filepath.Join(dir, "snaps")
|
||||
|
||||
err := os.Symlink(filepath.Join(dir, "pool", ".zfs", "snapshot"), snaps)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
daily := filepath.Join(snaps, "daily")
|
||||
stderr := scanOK(t, daily)
|
||||
|
||||
warning := "walk " + daily + ": skipping operand inside a .zfs directory\n"
|
||||
summary := "scan: 0 files seen (0 added, 0 updated, 0 removed, " +
|
||||
"0 unchanged), 1 skipped\n"
|
||||
|
||||
if !strings.Contains(stderr, warning) ||
|
||||
!strings.Contains(stderr, summary) {
|
||||
t.Errorf("stderr = %q, want %q and %q", stderr, warning, summary)
|
||||
}
|
||||
}
|
||||
|
||||
// TestRunScanWalksOperandThroughSymlink scans data/daily, where data is
|
||||
// a symlink to a directory outside any .zfs directory. The operand is
|
||||
// scanned as usual, and its file is recorded by the path given.
|
||||
func TestRunScanWalksOperandThroughSymlink(t *testing.T) {
|
||||
path := testDBPath(t)
|
||||
t.Setenv(databaseEnv, path)
|
||||
|
||||
dir := t.TempDir()
|
||||
writeFile(t, dir, "pool/data/daily/f", pattern(1, 10))
|
||||
|
||||
data := filepath.Join(dir, "data")
|
||||
|
||||
err := os.Symlink(filepath.Join(dir, "pool", "data"), data)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
daily := filepath.Join(data, "daily")
|
||||
stderr := scanOK(t, daily)
|
||||
|
||||
summary := "scan: 1 files seen (1 added, 0 updated, 0 removed, " +
|
||||
"0 unchanged), 0 skipped\n"
|
||||
if !strings.Contains(stderr, summary) {
|
||||
t.Errorf("stderr = %q, want %q", stderr, summary)
|
||||
}
|
||||
|
||||
db, err := openDB(path, reportParams)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
t.Cleanup(func() { _ = db.Close() })
|
||||
|
||||
recordByPath(t, dbRecords(t, db), filepath.Join(daily, "f"))
|
||||
}
|
||||
|
||||
func TestRunReportSucceeds(t *testing.T) {
|
||||
path := testDBPath(t)
|
||||
t.Setenv(databaseEnv, path)
|
||||
@@ -1122,7 +1234,7 @@ func assertRunsUseDatabase(t *testing.T, dir, name string) {
|
||||
}
|
||||
|
||||
func TestRunDatabasePathUsedAsGiven(t *testing.T) {
|
||||
// README §Database: the path names the database file exactly. In
|
||||
// README §Settings: the path names the database file exactly. In
|
||||
// SQLite's connection string an unescaped ? or # would end the file
|
||||
// name and % would start an escape, and a path starting with //
|
||||
// could be read as a host name. %25 is a valid escape, so unescaped
|
||||
@@ -1167,9 +1279,8 @@ func holdScanLock(t *testing.T, path string) {
|
||||
}
|
||||
|
||||
func TestRunSecondScanFails(t *testing.T) {
|
||||
// README §Database: while one scan holds the lock, a second scan
|
||||
// fails at once, naming the lock file, without opening the
|
||||
// database.
|
||||
// README §Database: a second scan that finds the lock held fails
|
||||
// at once, naming the lock file, without opening the database.
|
||||
path := testDBPath(t)
|
||||
t.Setenv(databaseEnv, path)
|
||||
|
||||
@@ -1228,7 +1339,7 @@ func assertSecondScanFails(t *testing.T, path string) {
|
||||
}
|
||||
|
||||
func TestRunSecondScanThroughSymlinkFails(t *testing.T) {
|
||||
// README §Database: every path to one database names the same lock
|
||||
// README §Database: a path through a symlink names the same lock
|
||||
// file, so while a scan holds it through one path, a scan through
|
||||
// another fails, naming the lock file beside the database's real
|
||||
// path.
|
||||
@@ -1333,8 +1444,8 @@ func TestRunReportsDuringScan(t *testing.T) {
|
||||
}
|
||||
|
||||
func TestRunStdoutClosedIsFatal(t *testing.T) {
|
||||
// README §Error handling: a stdout write failure exits 1, reported
|
||||
// in one line on stderr.
|
||||
// README §Error handling: a failed write to stdout is a fatal error,
|
||||
// exit 1, reported on stderr starting with "sfdupes:".
|
||||
for _, name := range []string{cmdReport, cmdTrees, cmdInfo} {
|
||||
t.Run(name, func(t *testing.T) {
|
||||
t.Setenv(databaseEnv, testDBPath(t))
|
||||
|
||||
+102
-90
@@ -9,6 +9,7 @@ import (
|
||||
"strings"
|
||||
"sync"
|
||||
"time"
|
||||
"unicode/utf8"
|
||||
|
||||
"github.com/schollz/progressbar/v3"
|
||||
"golang.org/x/term"
|
||||
@@ -34,10 +35,17 @@ const stallTime = 10 * time.Second
|
||||
// spinnerType selects the progressbar library's spinner style.
|
||||
const spinnerType = 14
|
||||
|
||||
// barWidth is the width of the progressbar library's bar between its
|
||||
// two ends, as in the example line in README "Progress".
|
||||
// barWidth is the width of a phase's bar between its two ends, as in
|
||||
// the example line in README "Progress".
|
||||
const barWidth = 10
|
||||
|
||||
// barCell is one column of the filled part of a bar.
|
||||
const barCell = "█"
|
||||
|
||||
// barColumns is the width of what percentBar returns: the percent in
|
||||
// four columns and its sign, a space, and the bar with its two ends.
|
||||
const barColumns = barWidth + 8
|
||||
|
||||
// percentScale converts a fraction to a percentage.
|
||||
const percentScale = 100
|
||||
|
||||
@@ -45,17 +53,12 @@ const percentScale = 100
|
||||
// read, as the progressbar library takes it.
|
||||
const fallbackWidth = 80
|
||||
|
||||
// spinnerMargin is the columns of a spinner's line besides its text:
|
||||
// the spinner and the three spaces the library draws around the text,
|
||||
// and the terminal's last column, which every line stays clear of so
|
||||
// that no terminal wraps it.
|
||||
// spinnerMargin is the columns of a line besides its text: the spinner
|
||||
// and the three spaces the library draws around the text, and the
|
||||
// terminal's last column, which every line stays clear of so that no
|
||||
// terminal wraps it.
|
||||
const spinnerMargin = 5
|
||||
|
||||
// barMargin is the columns of a bar's line besides its text: the
|
||||
// percent and the bar the library draws after the text, the spaces
|
||||
// around them, and the terminal's last column.
|
||||
const barMargin = barWidth + 11
|
||||
|
||||
// countingRecords is what the display of a phase that reads the records
|
||||
// says while it counts them, before it has its total.
|
||||
const countingRecords = "counting the records"
|
||||
@@ -109,13 +112,13 @@ type drawnCount struct {
|
||||
}
|
||||
|
||||
// progress renders one phase's progress on stderr. On a TTY the
|
||||
// progressbar library draws line, fitted to the terminal's width: after
|
||||
// the library's spinner, or, for a phase with an exact total, before the
|
||||
// library's bar when the terminal has room for the bar beside it. It is
|
||||
// drawn again every redrawInterval, so its elapsed time keeps moving
|
||||
// while the phase waits for its next item. When stderr is not a TTY it
|
||||
// emits no ANSI redraws: it prints line as the phase starts, every
|
||||
// plainInterval while it runs, and as it ends.
|
||||
// progressbar library draws its spinner and then line, fitted to the
|
||||
// terminal's width. A phase with an exact total ends the line with its
|
||||
// percent and bar, at the terminal's right edge, when the terminal has
|
||||
// room for them. It is drawn again every redrawInterval, so its elapsed
|
||||
// time keeps moving while the phase waits for its next item. When
|
||||
// stderr is not a TTY it emits no ANSI redraws: it prints line as the
|
||||
// phase starts, every plainInterval while it runs, and as it ends.
|
||||
//
|
||||
// The draws come from a goroutine of their own, so mu guards the fields
|
||||
// below it. Every method must be called from the main goroutine. A nil
|
||||
@@ -131,7 +134,6 @@ type progress struct {
|
||||
|
||||
mu sync.Mutex
|
||||
bar *progressbar.ProgressBar // what the library draws; nil until then
|
||||
withBar bool // bar is the library's bar, not its spinner
|
||||
widest int // the widest line bar has drawn, in columns
|
||||
label string
|
||||
unit string
|
||||
@@ -141,7 +143,7 @@ type progress struct {
|
||||
stalledOn string
|
||||
count int64
|
||||
start time.Time // when the phase started, for the elapsed time
|
||||
rateStart time.Time // when the count started, for the ETA
|
||||
rateStart time.Time // when the count started, for the time remaining
|
||||
lastItem time.Time // when the last item was completed, or the count started
|
||||
// drawn holds the count at each draw over the last rateWindow, oldest
|
||||
// first; the rate counts from the first. It keeps the draw before the
|
||||
@@ -215,55 +217,34 @@ func (p *progress) draw() {
|
||||
}
|
||||
|
||||
if p.width == nil {
|
||||
fmt.Fprintln(os.Stderr, p.line(now, math.MaxInt, true))
|
||||
fmt.Fprintln(os.Stderr, p.line(now, math.MaxInt, false))
|
||||
|
||||
return
|
||||
}
|
||||
|
||||
width := p.width()
|
||||
text := p.line(now, width-spinnerMargin, true)
|
||||
|
||||
// A phase with an exact total gets the library's bar when its whole
|
||||
// line, without the percent the bar shows, fits beside the bar: the
|
||||
// bar gives way before any part of the line. A total of 0 leaves the
|
||||
// bar nothing to fill.
|
||||
text, withBar := "", false
|
||||
if p.total > 0 && !p.estimate {
|
||||
text = p.line(now, math.MaxInt, false)
|
||||
withBar = len(text) <= width-barMargin
|
||||
}
|
||||
|
||||
margin := barMargin
|
||||
if !withBar {
|
||||
margin = spinnerMargin
|
||||
text = p.line(now, width-margin, true)
|
||||
}
|
||||
|
||||
// The library makes a bar or a spinner, and before each draw erases
|
||||
// its line with as many spaces as the widest line it has drawn. A
|
||||
// display gets a new one when it turns from one to the other, as its
|
||||
// line grows or the terminal is resized, and when the terminal has
|
||||
// been made too narrow for that erase, which would wrap and leave a
|
||||
// line behind at every draw.
|
||||
if p.bar == nil || p.withBar != withBar || p.widest >= width {
|
||||
p.newBar(withBar, width)
|
||||
}
|
||||
|
||||
if withBar {
|
||||
_ = p.bar.Set64(p.count)
|
||||
// Before each draw the library erases its line with as many spaces as
|
||||
// the widest line it has drawn. A display gets a new one when the
|
||||
// terminal has been made too narrow for that erase, which would wrap
|
||||
// and leave a line behind at every draw.
|
||||
if p.bar == nil || p.widest >= width {
|
||||
p.newBar(width)
|
||||
}
|
||||
|
||||
p.bar.Describe(text)
|
||||
|
||||
// The library drew the text and its margin, less the terminal's last
|
||||
// column, which the margin keeps clear.
|
||||
p.widest = max(p.widest, len(text)+margin-1)
|
||||
// The library drew the spinner, the text and the spaces around it,
|
||||
// less the terminal's last column, which spinnerMargin keeps clear. A
|
||||
// bar's cells take one column each but more than one byte.
|
||||
p.widest = max(p.widest, utf8.RuneCountInString(text)+spinnerMargin-1)
|
||||
}
|
||||
|
||||
// newBar has the library make what draw draws: a bar for the phase's
|
||||
// total when withBar is set, and a spinner when not. Either shows the
|
||||
// text draw gives it, and nothing of its own besides the spinner, or
|
||||
// the bar and its percent. p.mu must be held.
|
||||
func (p *progress) newBar(withBar bool, width int) {
|
||||
// newBar has the library make what draw draws: its spinner, followed by
|
||||
// the text draw gives it and nothing of the library's own. p.mu must be
|
||||
// held.
|
||||
func (p *progress) newBar(width int) {
|
||||
if p.bar != nil {
|
||||
// Erase what was drawn before, short of the last column of a
|
||||
// terminal that may have been made narrower since: the library's
|
||||
@@ -272,29 +253,36 @@ func (p *progress) newBar(withBar bool, width int) {
|
||||
fmt.Fprint(os.Stderr, "\r"+blank+"\r")
|
||||
}
|
||||
|
||||
total := int64(-1) // the library's spinner
|
||||
if withBar {
|
||||
total = p.total
|
||||
}
|
||||
|
||||
p.bar = progressbar.NewOptions64(total,
|
||||
// A total of -1 gives the library's spinner.
|
||||
p.bar = progressbar.NewOptions64(-1,
|
||||
progressbar.OptionSetWriter(os.Stderr),
|
||||
progressbar.OptionSetWidth(barWidth),
|
||||
progressbar.OptionSpinnerType(spinnerType),
|
||||
// The spinner turns at each draw, not on a timer of the
|
||||
// library's own.
|
||||
progressbar.OptionSetSpinnerChangeInterval(0),
|
||||
// The text carries the elapsed time and the ETA.
|
||||
// The text carries the elapsed time and the time remaining.
|
||||
progressbar.OptionSetElapsedTime(false),
|
||||
progressbar.OptionSetPredictTime(false),
|
||||
)
|
||||
p.withBar, p.widest = withBar, 0
|
||||
p.widest = 0
|
||||
}
|
||||
|
||||
// percentBar returns the percent and the bar that end the text of a
|
||||
// phase with an exact total, as " 25% |██ |": the bar's
|
||||
// barWidth columns fill in proportion to the items done. A count past
|
||||
// the total, as when a scan adds records while trees reads them, shows
|
||||
// as 100%. p.mu must be held.
|
||||
func (p *progress) percentBar() string {
|
||||
done := min(float64(p.count)/float64(p.total), 1)
|
||||
filled := strings.Repeat(barCell, int(done*barWidth))
|
||||
|
||||
return fmt.Sprintf("%4.0f%% |%-*s|", done*percentScale, barWidth, filled)
|
||||
}
|
||||
|
||||
// setTotal gives a phase that started without a total its total, once
|
||||
// it is known. The rate, the ETA and the time with no item completed
|
||||
// count from then on: the time spent waiting for the total says nothing
|
||||
// about how fast items go.
|
||||
// it is known. The rate, the time remaining and the time with no item
|
||||
// completed count from then on: the time spent waiting for the total
|
||||
// says nothing about how fast items go.
|
||||
func (p *progress) setTotal(total int64) {
|
||||
if p == nil {
|
||||
return
|
||||
@@ -438,22 +426,26 @@ func (p *progress) finish() {
|
||||
// line formats the phase's progress as of now in at most room columns,
|
||||
// as
|
||||
//
|
||||
// [3/4] hash: [1234/5000] 25%, 300 files/s, elapsed 4s, eta 13s
|
||||
// [3/4] hash: [1234/5000] 25%, 300 files/s, elapsed 4s, remain 13s
|
||||
//
|
||||
// where "files" is the phase's unit, without the percent when percent
|
||||
// is false, as before the library's bar, which shows its own. A phase
|
||||
// with no total shows the items done instead, or what it waits for. The
|
||||
// rate is that since the first draw in drawn, and the ETA comes from
|
||||
// the rate since the count started. Once no item has been completed for
|
||||
// stallTime, the rate, which would read 0, gives way to the word
|
||||
// "stalled" and where the phase waits, as "stalled disk/db".
|
||||
// where "files" is the phase's unit. A phase with no total shows the
|
||||
// items done instead, or what it waits for. The rate is that since the
|
||||
// first draw in drawn, and the time remaining comes from the rate since
|
||||
// the count started. Once no item has been completed for stallTime, the
|
||||
// rate, which would read 0, gives way to the word "stalled" and where
|
||||
// the phase waits, as "stalled disk/db".
|
||||
//
|
||||
// The phase and its place, the progress, the elapsed time and the ETA
|
||||
// are kept whole. A line wider than room leaves out the rate, the words
|
||||
// of a stalled phase, or what the phase waits for; only if it is still
|
||||
// wider is it cut at room. Every part is ASCII, so its length is its
|
||||
// width in columns. p.mu must be held.
|
||||
func (p *progress) line(now time.Time, room int, percent bool) string {
|
||||
// When bar is true, as on a terminal, a phase with an exact total ends
|
||||
// the line with its percent and bar, in place of the percent after its
|
||||
// count. A total of 0 leaves the bar nothing to fill.
|
||||
//
|
||||
// The phase and its place, the progress, the elapsed time and the time
|
||||
// remaining are kept whole. A line wider than room first leaves out the
|
||||
// rate, the words of a stalled phase, or what the phase waits for. Next
|
||||
// it leaves out the bar. Only if it is still wider is it cut at room.
|
||||
// Every part but the bar is ASCII, so its length is its width in
|
||||
// columns. p.mu must be held.
|
||||
func (p *progress) line(now time.Time, room int, bar bool) string {
|
||||
elapsed := now.Sub(p.start).Round(time.Second)
|
||||
|
||||
// head and tail hold the parts kept whole; extra, between them, is
|
||||
@@ -462,21 +454,41 @@ func (p *progress) line(now time.Time, room int, percent bool) string {
|
||||
|
||||
if p.total < 0 && p.waitingFor != "" {
|
||||
head, extra = p.label+": ", p.waitingFor+", "
|
||||
tail = fmt.Sprintf("elapsed %s, eta unknown", elapsed)
|
||||
tail = fmt.Sprintf("elapsed %s, remain unknown", elapsed)
|
||||
} else {
|
||||
since := p.drawn[0]
|
||||
rate := perSecond(p.count-since.count, now.Sub(since.at))
|
||||
average := perSecond(p.count, now.Sub(p.rateStart))
|
||||
|
||||
head = p.label + ": " + p.itemsDone(percent) + ", "
|
||||
head = p.label + ": " + p.itemsDone(true) + ", "
|
||||
extra = fmt.Sprintf("%.0f %s/s, ", rate, p.unit)
|
||||
tail = fmt.Sprintf("elapsed %s, eta %s", elapsed, p.eta(average))
|
||||
tail = fmt.Sprintf("elapsed %s, remain %s", elapsed, p.remain(average))
|
||||
|
||||
if now.Sub(p.lastItem) >= stallTime {
|
||||
extra = "stalled " + p.stalledOn + ", "
|
||||
}
|
||||
}
|
||||
|
||||
if bar && p.total > 0 && !p.estimate {
|
||||
// Beside the bar, which shows the percent, the count shows none.
|
||||
// The line is padded to the room the bar leaves it, so the bar
|
||||
// stays at room's right edge however long the line is.
|
||||
beside := room - barColumns
|
||||
barHead := p.label + ": " + p.itemsDone(false) + ", "
|
||||
|
||||
switch {
|
||||
case len(barHead+extra+tail) <= beside:
|
||||
return fmt.Sprintf("%-*s%s", beside, barHead+extra+tail,
|
||||
p.percentBar())
|
||||
case len(barHead+tail) <= beside:
|
||||
return fmt.Sprintf("%-*s%s", beside, barHead+tail, p.percentBar())
|
||||
}
|
||||
|
||||
// The bar gives way. The rate, or the words of a stalled phase,
|
||||
// gave way before it and stay out.
|
||||
extra = ""
|
||||
}
|
||||
|
||||
full, kept := head+extra+tail, head+tail
|
||||
|
||||
switch {
|
||||
@@ -526,10 +538,10 @@ func (p *progress) itemsDone(percent bool) string {
|
||||
return fmt.Sprintf("%s %.0f%%", done, pct)
|
||||
}
|
||||
|
||||
// eta returns the time the phase has left at rate items a second, or
|
||||
// remain returns the time the phase has left at rate items a second, or
|
||||
// "unknown": with no total, before the first item, and once the count
|
||||
// passes an estimate. p.mu must be held.
|
||||
func (p *progress) eta(rate float64) string {
|
||||
func (p *progress) remain(rate float64) string {
|
||||
switch {
|
||||
case p.total < 0, p.estimate && p.count > p.total:
|
||||
return "unknown"
|
||||
@@ -539,8 +551,8 @@ func (p *progress) eta(rate float64) string {
|
||||
return "unknown"
|
||||
}
|
||||
|
||||
remaining := time.Duration(
|
||||
left := time.Duration(
|
||||
float64(p.total-p.count) / rate * float64(time.Second))
|
||||
|
||||
return remaining.Round(time.Second).String()
|
||||
return left.Round(time.Second).String()
|
||||
}
|
||||
|
||||
+261
-101
@@ -117,24 +117,24 @@ func TestProgressLine(t *testing.T) {
|
||||
label: scanPhase("load"), total: -1,
|
||||
waitingFor: countingRecords,
|
||||
},
|
||||
want: "[1/4] load: counting the records, elapsed 10s, eta unknown",
|
||||
want: "[1/4] load: counting the records, elapsed 10s, remain unknown",
|
||||
}, {
|
||||
p: &progress{
|
||||
label: scanPhase("hash"), unit: scanUnit, total: 100, count: 20,
|
||||
},
|
||||
want: "[3/4] hash: [20/100] 20%, 2 files/s, elapsed 10s, eta 40s",
|
||||
want: "[3/4] hash: [20/100] 20%, 2 files/s, elapsed 10s, remain 40s",
|
||||
}, {
|
||||
p: &progress{label: scanPhase("hash"), unit: scanUnit, total: 100},
|
||||
want: "[3/4] hash: [0/100] 0%, 0 files/s, elapsed 10s, eta unknown",
|
||||
want: "[3/4] hash: [0/100] 0%, 0 files/s, elapsed 10s, remain unknown",
|
||||
}, {
|
||||
p: &progress{label: scanPhase("update"), unit: scanUnit, total: 0},
|
||||
want: "[4/4] update: [0/0] 100%, 0 files/s, elapsed 10s, eta 0s",
|
||||
want: "[4/4] update: [0/0] 100%, 0 files/s, elapsed 10s, remain 0s",
|
||||
}, {
|
||||
p: &progress{
|
||||
label: scanPhase("walk"), unit: scanUnit, total: 100,
|
||||
estimate: true, count: 20,
|
||||
},
|
||||
want: "[2/4] walk: [20/~100] 20%, 2 files/s, elapsed 10s, eta 40s",
|
||||
want: "[2/4] walk: [20/~100] 20%, 2 files/s, elapsed 10s, remain 40s",
|
||||
}, {
|
||||
// Past the estimate the walk cannot tell how long it has left.
|
||||
p: &progress{
|
||||
@@ -142,13 +142,13 @@ func TestProgressLine(t *testing.T) {
|
||||
estimate: true, count: 120,
|
||||
},
|
||||
want: "[2/4] walk: [120/~100] 120%, 12 files/s, elapsed 10s, " +
|
||||
"eta unknown",
|
||||
"remain unknown",
|
||||
}, {
|
||||
// A first scan's walk has no estimate.
|
||||
p: &progress{
|
||||
label: scanPhase("walk"), unit: scanUnit, total: -1, count: 20,
|
||||
},
|
||||
want: "[2/4] walk: 20 files, 2 files/s, elapsed 10s, eta unknown",
|
||||
want: "[2/4] walk: 20 files, 2 files/s, elapsed 10s, remain unknown",
|
||||
}, {
|
||||
// The rate is in what the phase counts.
|
||||
p: &progress{
|
||||
@@ -156,14 +156,14 @@ func TestProgressLine(t *testing.T) {
|
||||
count: 20,
|
||||
},
|
||||
want: "[3/4] group: [20/100] 20%, 2 directories/s, elapsed 10s, " +
|
||||
"eta 40s",
|
||||
"remain 40s",
|
||||
}}
|
||||
|
||||
for _, tc := range cases {
|
||||
tc.p.start, tc.p.rateStart, tc.p.lastItem = ago, ago, now
|
||||
tc.p.drawn = []drawnCount{{at: ago}}
|
||||
|
||||
if got := tc.p.line(now, math.MaxInt, true); got != tc.want {
|
||||
if got := tc.p.line(now, math.MaxInt, false); got != tc.want {
|
||||
t.Errorf("line = %q, want %q", got, tc.want)
|
||||
}
|
||||
}
|
||||
@@ -198,48 +198,49 @@ func TestLineFitsRoom(t *testing.T) {
|
||||
}
|
||||
|
||||
cases := []struct {
|
||||
p *progress
|
||||
room int
|
||||
percent bool
|
||||
want string
|
||||
p *progress
|
||||
room int
|
||||
bar bool
|
||||
want string
|
||||
}{{
|
||||
p: hash, room: 57, percent: true,
|
||||
want: "[3/4] hash: [20/100] 20%, 2 files/s, elapsed 10s, eta 40s",
|
||||
p: hash, room: 60,
|
||||
want: "[3/4] hash: [20/100] 20%, 2 files/s, elapsed 10s, remain 40s",
|
||||
}, {
|
||||
p: hash, room: 56, percent: true,
|
||||
want: "[3/4] hash: [20/100] 20%, elapsed 10s, eta 40s",
|
||||
p: hash, room: 59,
|
||||
want: "[3/4] hash: [20/100] 20%, elapsed 10s, remain 40s",
|
||||
}, {
|
||||
p: hash, room: 45, percent: true,
|
||||
want: "[3/4] hash: [20/100] 20%, elapsed 10s, eta 40",
|
||||
p: hash, room: 48,
|
||||
want: "[3/4] hash: [20/100] 20%, elapsed 10s, remain 40",
|
||||
}, {
|
||||
// Before the library's bar, which shows the percent.
|
||||
p: hash, room: 57, percent: false,
|
||||
want: "[3/4] hash: [20/100], 2 files/s, elapsed 10s, eta 40s",
|
||||
// The bar shows the percent.
|
||||
p: hash, room: 74, bar: true,
|
||||
want: "[3/4] hash: [20/100], 2 files/s, elapsed 10s, remain 40s" +
|
||||
" 20% |██ |",
|
||||
}, {
|
||||
p: load, room: 40, percent: true,
|
||||
want: "[1/4] load: elapsed 10s, eta unknown",
|
||||
p: load, room: 43,
|
||||
want: "[1/4] load: elapsed 10s, remain unknown",
|
||||
}, {
|
||||
p: stalled, room: 65, percent: true,
|
||||
p: stalled, room: 68,
|
||||
want: "[3/4] hash: [20/100] 20%, stalled disk/db, elapsed 50s, " +
|
||||
"eta 3m20s",
|
||||
"remain 3m20s",
|
||||
}, {
|
||||
p: stalled, room: 64, percent: true,
|
||||
want: "[3/4] hash: [20/100] 20%, elapsed 50s, eta 3m20s",
|
||||
p: stalled, room: 67,
|
||||
want: "[3/4] hash: [20/100] 20%, elapsed 50s, remain 3m20s",
|
||||
}}
|
||||
|
||||
for _, tc := range cases {
|
||||
if got := tc.p.line(now, tc.room, tc.percent); got != tc.want {
|
||||
t.Errorf("line(%d, %t) = %q, want %q",
|
||||
tc.room, tc.percent, got, tc.want)
|
||||
if got := tc.p.line(now, tc.room, tc.bar); got != tc.want {
|
||||
t.Errorf("line(%d, %t) = %q, want %q", tc.room, tc.bar, got,
|
||||
tc.want)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// TestSetTotalStartsRate checks that setTotal starts a phase's rate,
|
||||
// its ETA and its time with no record read from when the total becomes
|
||||
// known, not from when the phase started waiting for it: after 20
|
||||
// seconds of waiting for the total, the phase has not stalled 5 seconds
|
||||
// after it, and has 10 seconds after it with no record read.
|
||||
// its time remaining and its time with no record read from when the
|
||||
// total becomes known, not from when the phase started waiting for it:
|
||||
// after 20 seconds of waiting for the total, the phase has not stalled 5
|
||||
// seconds after it, and has 10 seconds after it with no record read.
|
||||
func TestSetTotalStartsRate(t *testing.T) {
|
||||
t.Parallel()
|
||||
|
||||
@@ -255,15 +256,15 @@ func TestSetTotalStartsRate(t *testing.T) {
|
||||
|
||||
clock.Add(5 * time.Second)
|
||||
|
||||
want := "[1/4] load: [0/100] 0%, 0 files/s, elapsed 25s, eta unknown"
|
||||
if got := p.line(clock.Now(), math.MaxInt, true); got != want {
|
||||
want := "[1/4] load: [0/100] 0%, 0 files/s, elapsed 25s, remain unknown"
|
||||
if got := p.line(clock.Now(), math.MaxInt, false); got != want {
|
||||
t.Errorf("line = %q, want %q", got, want)
|
||||
}
|
||||
|
||||
clock.Add(5 * time.Second)
|
||||
|
||||
want = "[1/4] load: [0/100] 0%, stalled db, elapsed 30s, eta unknown"
|
||||
if got := p.line(clock.Now(), math.MaxInt, true); got != want {
|
||||
want = "[1/4] load: [0/100] 0%, stalled db, elapsed 30s, remain unknown"
|
||||
if got := p.line(clock.Now(), math.MaxInt, false); got != want {
|
||||
t.Errorf("line = %q, want %q", got, want)
|
||||
}
|
||||
|
||||
@@ -272,8 +273,8 @@ func TestSetTotalStartsRate(t *testing.T) {
|
||||
p.increment()
|
||||
}
|
||||
|
||||
want = "[1/4] load: [20/100] 20%, 2 files/s, elapsed 30s, eta 40s"
|
||||
if got := p.line(clock.Now(), math.MaxInt, true); got != want {
|
||||
want = "[1/4] load: [20/100] 20%, 2 files/s, elapsed 30s, remain 40s"
|
||||
if got := p.line(clock.Now(), math.MaxInt, false); got != want {
|
||||
t.Errorf("line = %q, want %q", got, want)
|
||||
}
|
||||
}
|
||||
@@ -316,7 +317,7 @@ func TestPlainProgressPrintsAtStartAndEnd(t *testing.T) {
|
||||
|
||||
lines := strings.Split(strings.TrimSuffix(stderr(), "\n"), "\n")
|
||||
|
||||
want := "[3/4] hash: [0/1000] 0%, 0 files/s, elapsed 0s, eta unknown"
|
||||
want := "[3/4] hash: [0/1000] 0%, 0 files/s, elapsed 0s, remain unknown"
|
||||
if len(lines) != 2 || lines[0] != want ||
|
||||
!strings.HasPrefix(lines[1], "[3/4] hash: [1000/1000] 100%, ") {
|
||||
t.Errorf("stderr lines = %q, want %q, then the line at 1000",
|
||||
@@ -336,7 +337,7 @@ func TestPlainProgressPrintsWhileWaiting(t *testing.T) {
|
||||
}, nil, testRedraw, time.Now)
|
||||
|
||||
awaitOutput(t, stderr,
|
||||
"[1/4] load: counting the records, elapsed 0s, eta unknown\n", 3)
|
||||
"[1/4] load: counting the records, elapsed 0s, remain unknown\n", 3)
|
||||
p.finish()
|
||||
}
|
||||
|
||||
@@ -366,23 +367,23 @@ func TestPlainProgressStalledProducer(t *testing.T) {
|
||||
|
||||
clock.Add(5 * time.Second)
|
||||
awaitOutput(t, stderr,
|
||||
"[3/4] hash: [20/100] 20%, 4 files/s, elapsed 5s, eta 20s\n", 3)
|
||||
"[3/4] hash: [20/100] 20%, 4 files/s, elapsed 5s, remain 20s\n", 3)
|
||||
|
||||
clock.Add(time.Second)
|
||||
awaitOutput(t, stderr,
|
||||
"[3/4] hash: [20/100] 20%, 0 files/s, elapsed 6s, eta 24s\n", 3)
|
||||
"[3/4] hash: [20/100] 20%, 0 files/s, elapsed 6s, remain 24s\n", 3)
|
||||
|
||||
clock.Add(4 * time.Second)
|
||||
awaitOutput(t, stderr,
|
||||
"[3/4] hash: [20/100] 20%, stalled disk/db, elapsed 10s, eta 40s\n",
|
||||
"[3/4] hash: [20/100] 20%, stalled disk/db, elapsed 10s, remain 40s\n",
|
||||
3)
|
||||
}
|
||||
|
||||
// TestPlainProgressRateAfterStall draws a phase's plain line by hand, a
|
||||
// little over plainInterval after the line before, as a late tick
|
||||
// does, through a stall and a burst of files after it: the rate covers
|
||||
// the files read since the line before, while the ETA comes from the
|
||||
// phase's average.
|
||||
// the files read since the line before, while the time remaining comes
|
||||
// from the phase's average.
|
||||
//
|
||||
//nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
|
||||
func TestPlainProgressRateAfterStall(t *testing.T) {
|
||||
@@ -410,10 +411,10 @@ func TestPlainProgressRateAfterStall(t *testing.T) {
|
||||
p.finish()
|
||||
|
||||
want := []string{
|
||||
"[3/4] hash: [0/1000] 0%, 0 files/s, elapsed 0s, eta unknown",
|
||||
"[3/4] hash: [0/1000] 0%, 0 files/s, elapsed 5s, eta unknown",
|
||||
"[3/4] hash: [0/1000] 0%, stalled disk/db, elapsed 10s, eta unknown",
|
||||
"[3/4] hash: [100/1000] 10%, 20 files/s, elapsed 15s, eta 2m15s",
|
||||
"[3/4] hash: [0/1000] 0%, 0 files/s, elapsed 0s, remain unknown",
|
||||
"[3/4] hash: [0/1000] 0%, 0 files/s, elapsed 5s, remain unknown",
|
||||
"[3/4] hash: [0/1000] 0%, stalled disk/db, elapsed 10s, remain unknown",
|
||||
"[3/4] hash: [100/1000] 10%, 20 files/s, elapsed 15s, remain 2m15s",
|
||||
}
|
||||
|
||||
lines := strings.Split(strings.TrimSuffix(stderr(), "\n"), "\n")
|
||||
@@ -426,8 +427,8 @@ func TestPlainProgressRateAfterStall(t *testing.T) {
|
||||
// redrawInterval, as a terminal does, through a stall of stallTime and
|
||||
// a burst of files after it: the rate covers the files read over the
|
||||
// last rateWindow, and falls to 0 once the burst is older than that,
|
||||
// while the ETA comes from the phase's average. Plain lines show each
|
||||
// draw.
|
||||
// while the time remaining comes from the phase's average. Plain lines
|
||||
// show each draw.
|
||||
//
|
||||
//nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
|
||||
func TestProgressRateAfterStallRedrawn(t *testing.T) {
|
||||
@@ -457,8 +458,8 @@ func TestProgressRateAfterStallRedrawn(t *testing.T) {
|
||||
redraw(rateWindow + redrawInterval)
|
||||
p.finish()
|
||||
|
||||
want := "[3/4] hash: [50/1000] 5%, 10 files/s, elapsed 15s, eta 4m45s\n" +
|
||||
"[3/4] hash: [50/1000] 5%, 0 files/s, elapsed 15s, eta 4m47s\n"
|
||||
want := "[3/4] hash: [50/1000] 5%, 10 files/s, elapsed 15s, remain 4m45s\n" +
|
||||
"[3/4] hash: [50/1000] 5%, 0 files/s, elapsed 15s, remain 4m47s\n"
|
||||
if !strings.Contains(stderr(), want) {
|
||||
t.Errorf("stderr = %q, want the lines %q", stderr(), want)
|
||||
}
|
||||
@@ -480,10 +481,10 @@ func lastFrame(out string) string {
|
||||
}
|
||||
|
||||
// TestTerminalRedrawsWhileWaiting checks that the terminal display of a
|
||||
// phase, spinner or bar, keeps being drawn while the phase waits for its
|
||||
// next item, with the elapsed time as of now, and shows every item
|
||||
// completed before the wait. stderr is not a terminal here, so the
|
||||
// displays take it to be fallbackWidth wide.
|
||||
// phase, with a bar or without, keeps being drawn while the phase waits
|
||||
// for its next item, with the elapsed time as of now, and shows every
|
||||
// item completed before the wait. The terminal is 120 columns wide, so
|
||||
// the hash phase's display has room for its bar.
|
||||
//
|
||||
//nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
|
||||
func TestTerminalRedrawsWhileWaiting(t *testing.T) {
|
||||
@@ -506,7 +507,8 @@ func TestTerminalRedrawsWhileWaiting(t *testing.T) {
|
||||
for _, tc := range cases {
|
||||
before := len(stderr())
|
||||
since := func() string { return stderr()[before:] }
|
||||
p := startProgress(tc.params, terminalWidth, testRedraw, time.Now)
|
||||
p := startProgress(tc.params, func() int { return 120 }, testRedraw,
|
||||
time.Now)
|
||||
|
||||
for range 50 {
|
||||
p.increment()
|
||||
@@ -552,13 +554,13 @@ func drawLate(stderr func() string, params progressParams, width int,
|
||||
return stderr()[before:]
|
||||
}
|
||||
|
||||
// TestTerminalLinesKeepETA checks the line each display shows on an
|
||||
// 80-column terminal at a large scan's counts and times, and the line
|
||||
// of trees' read phase at the same counts: the rate is left out, so
|
||||
// that the elapsed time and the ETA stay whole.
|
||||
// TestTerminalLinesKeepTimeRemaining checks the line each display shows
|
||||
// on an 80-column terminal at a large scan's counts and times, and the
|
||||
// line of trees' read phase at the same counts: the rate is left out,
|
||||
// so that the elapsed time and the time remaining stay whole.
|
||||
//
|
||||
//nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
|
||||
func TestTerminalLinesKeepETA(t *testing.T) {
|
||||
func TestTerminalLinesKeepTimeRemaining(t *testing.T) {
|
||||
stderr := captureStderr(t)
|
||||
|
||||
cases := []struct {
|
||||
@@ -571,19 +573,19 @@ func TestTerminalLinesKeepETA(t *testing.T) {
|
||||
estimate: true,
|
||||
},
|
||||
want: "[2/4] walk: [1234567/~1200000] 103%, elapsed 2h30m0s, " +
|
||||
"eta unknown",
|
||||
"remain unknown",
|
||||
}, {
|
||||
params: progressParams{
|
||||
label: scanPhase("hash"), unit: scanUnit, total: 9876543,
|
||||
},
|
||||
want: "[3/4] hash: [1234567/9876543] 12%, elapsed 2h30m0s, " +
|
||||
"eta 17h30m0s",
|
||||
"remain 17h30m0s",
|
||||
}, {
|
||||
params: progressParams{
|
||||
label: treesPhase("read"), unit: "records", total: 9876543,
|
||||
},
|
||||
want: "[2/4] read: [1234567/9876543] 12%, elapsed 2h30m0s, " +
|
||||
"eta 17h30m0s",
|
||||
"remain 17h30m0s",
|
||||
}}
|
||||
|
||||
for _, tc := range cases {
|
||||
@@ -594,30 +596,32 @@ func TestTerminalLinesKeepETA(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
// TestTerminalStalledLines draws every phase's line on an 80-column
|
||||
// terminal once the phase has stalled, its last item done 42 seconds
|
||||
// before. At an ordinary scan's counts and times, 12345 of 45678 items
|
||||
// done four and a half minutes in, the line shows where the phase waits
|
||||
// whole, beside the phase, progress, elapsed time and ETA. At a large
|
||||
// scan's, 1234567 of 9876543 two and a half hours in, those four still
|
||||
// show whole, as the words give way first where they do not fit.
|
||||
// TestTerminalStalledLines draws every phase's line once the phase has
|
||||
// stalled, its last item done 42 seconds before. At an ordinary scan's
|
||||
// counts and times, 12345 of 45678 items done four and a half minutes
|
||||
// in, on a terminal 100 columns wide, the line shows where the phase
|
||||
// waits whole, beside the phase, progress, elapsed time and time
|
||||
// remaining. At a large scan's, 1234567 of 9876543 two and a half hours
|
||||
// in, on an 80-column terminal, those four still show whole, as the
|
||||
// words give way first where they do not fit.
|
||||
//
|
||||
//nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
|
||||
func TestTerminalStalledLines(t *testing.T) {
|
||||
stderr := captureStderr(t)
|
||||
|
||||
// drawStalled draws the display params describes as it starts and
|
||||
// once more as it ends, with count of total items done elapsed into
|
||||
// the phase, and returns what the terminal shows.
|
||||
drawStalled := func(params progressParams, total, count int64,
|
||||
elapsed time.Duration,
|
||||
// drawStalled draws the display params describes on a terminal width
|
||||
// columns wide as it starts and once more as it ends, with count of
|
||||
// total items done elapsed into the phase, and returns what the
|
||||
// terminal shows.
|
||||
drawStalled := func(params progressParams, width int, total,
|
||||
count int64, elapsed time.Duration,
|
||||
) string {
|
||||
before := len(stderr())
|
||||
clock := &testClock{now: time.Now()}
|
||||
params.total = total
|
||||
|
||||
// No timed draws come between the two.
|
||||
p := startProgress(params, func() int { return 80 }, time.Hour,
|
||||
p := startProgress(params, func() int { return width }, time.Hour,
|
||||
clock.Now)
|
||||
|
||||
clock.Add(elapsed - 42*time.Second)
|
||||
@@ -649,19 +653,22 @@ func TestTerminalStalledLines(t *testing.T) {
|
||||
approx = "~"
|
||||
}
|
||||
|
||||
shown := drawStalled(params, 45678, 12345,
|
||||
// The percent is in the line, or beside the bar.
|
||||
shown := drawStalled(params, 100, 45678, 12345,
|
||||
4*time.Minute+30*time.Second)
|
||||
want := params.label + ": [12345/" + approx + "45678] 27%, stalled " +
|
||||
params.stalledOn + ", elapsed 4m30s, eta 12m9s"
|
||||
|
||||
if !strings.Contains(shown, want) {
|
||||
t.Errorf("terminal shows %q, want %q", shown, want)
|
||||
for _, want := range []string{
|
||||
params.label + ": [12345/" + approx + "45678]",
|
||||
", stalled " + params.stalledOn + ", elapsed 4m30s, remain 12m9s",
|
||||
} {
|
||||
if !strings.Contains(shown, want) {
|
||||
t.Errorf("terminal shows %q, want %q", shown, want)
|
||||
}
|
||||
}
|
||||
|
||||
shown = drawStalled(params, 9876543, 1234567, 150*time.Minute)
|
||||
shown = drawStalled(params, 80, 9876543, 1234567, 150*time.Minute)
|
||||
for _, want := range []string{
|
||||
params.label + ": [1234567/" + approx + "9876543] 12%, ",
|
||||
", elapsed 2h30m0s, eta 17h30m0s",
|
||||
", elapsed 2h30m0s, remain 17h30m0s",
|
||||
} {
|
||||
if !strings.Contains(shown, want) {
|
||||
t.Errorf("terminal shows %q, want %q", shown, want)
|
||||
@@ -706,13 +713,164 @@ func TestTerminalLinesFitWidth(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
// TestTerminalLinesStartWithSpinner draws a display with no total and
|
||||
// one with a bar, two and a half hours into the phase, on a terminal 120
|
||||
// columns wide. Each line must start with the library's spinner in the
|
||||
// first column, then a space and the phase's label.
|
||||
//
|
||||
//nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
|
||||
func TestTerminalLinesStartWithSpinner(t *testing.T) {
|
||||
stderr := captureStderr(t)
|
||||
|
||||
for _, params := range []progressParams{
|
||||
{label: scanPhase("walk"), unit: scanUnit, total: -1},
|
||||
{label: scanPhase("hash"), unit: scanUnit, total: 9876543},
|
||||
} {
|
||||
shown := lastFrame(drawLate(stderr, params, 120, 1234567))
|
||||
spinner, rest, _ := strings.Cut(shown, " ")
|
||||
|
||||
if utf8.RuneCountInString(spinner) != 1 ||
|
||||
!strings.HasPrefix(rest, params.label+": ") {
|
||||
t.Errorf("terminal shows %q, want the spinner, a space and %q",
|
||||
shown, params.label)
|
||||
}
|
||||
|
||||
if params.total > 0 && !strings.Contains(shown, "% |") {
|
||||
t.Errorf("terminal shows %q, want a bar", shown)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// TestTerminalBarStaysAtRightEdge draws the hash phase's display two
|
||||
// and a half hours in, at two counts whose lines differ in length, on
|
||||
// terminals 110 and 120 columns wide. The bar is partly filled at the
|
||||
// first count and full at the second. It must start the same number of
|
||||
// columns from the terminal's right edge each time, and end the same
|
||||
// number of columns from it: a line that grows or shrinks, as its time
|
||||
// remaining does, never moves the bar, and nor do the bar's filled
|
||||
// cells.
|
||||
//
|
||||
//nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
|
||||
func TestTerminalBarStaysAtRightEdge(t *testing.T) {
|
||||
stderr := captureStderr(t)
|
||||
params := progressParams{
|
||||
label: scanPhase("hash"), unit: scanUnit, total: 9876543,
|
||||
}
|
||||
|
||||
widths := []int{110, 120}
|
||||
counts := []int64{1234567, 9876543}
|
||||
startFromEdge := make([]int, 0, len(widths)*len(counts))
|
||||
endFromEdge := make([]int, 0, len(widths)*len(counts))
|
||||
|
||||
for _, width := range widths {
|
||||
for _, count := range counts {
|
||||
shown := lastFrame(drawLate(stderr, params, width, count))
|
||||
|
||||
beforeBar, _, found := strings.Cut(shown, "% |")
|
||||
if !found {
|
||||
t.Fatalf("terminal %d wide shows %q, want a bar", width, shown)
|
||||
}
|
||||
|
||||
// The bar ends with the last "|".
|
||||
throughBar := shown[:strings.LastIndex(shown, "|")+1]
|
||||
|
||||
startFromEdge = append(startFromEdge,
|
||||
width-utf8.RuneCountInString(beforeBar))
|
||||
endFromEdge = append(endFromEdge,
|
||||
width-utf8.RuneCountInString(throughBar))
|
||||
}
|
||||
}
|
||||
|
||||
if slices.Min(startFromEdge) != slices.Max(startFromEdge) {
|
||||
t.Errorf("bar starts %v columns from the right edge, want the same "+
|
||||
"every time", startFromEdge)
|
||||
}
|
||||
|
||||
if slices.Min(endFromEdge) != slices.Max(endFromEdge) {
|
||||
t.Errorf("bar ends %v columns from the right edge, want the same "+
|
||||
"every time", endFromEdge)
|
||||
}
|
||||
}
|
||||
|
||||
// TestTerminalRateGivesWayBeforeBar draws the hash phase's display two
|
||||
// and a half hours in. On a terminal 90 columns wide the line fits
|
||||
// beside the bar without its rate, but not with it: the bar is drawn
|
||||
// and the rate is not. On a terminal 85 columns wide the line does not
|
||||
// fit beside the bar even without its rate: neither is drawn, though
|
||||
// the rate would fit where the bar was.
|
||||
//
|
||||
//nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
|
||||
func TestTerminalRateGivesWayBeforeBar(t *testing.T) {
|
||||
stderr := captureStderr(t)
|
||||
params := progressParams{
|
||||
label: scanPhase("hash"), unit: scanUnit, total: 9876543,
|
||||
}
|
||||
|
||||
shown := lastFrame(drawLate(stderr, params, 90, 1234567))
|
||||
if !strings.Contains(shown, "% |") || strings.Contains(shown, "files/s") {
|
||||
t.Errorf("terminal 90 wide shows %q, want the bar and no rate", shown)
|
||||
}
|
||||
|
||||
shown = lastFrame(drawLate(stderr, params, 85, 1234567))
|
||||
if strings.Contains(shown, "% |") || strings.Contains(shown, "files/s") {
|
||||
t.Errorf("terminal 85 wide shows %q, want neither bar nor rate", shown)
|
||||
}
|
||||
}
|
||||
|
||||
// TestTerminalSpinnerTurnsBesideBar draws the hash phase's display, its
|
||||
// bar partly filled, several times on a terminal 120 columns wide. The
|
||||
// spinner must turn at every draw. A filled cell of the bar takes one
|
||||
// column but three bytes. A line measured in bytes would seem too wide
|
||||
// for the terminal, and every draw would start the display over, its
|
||||
// spinner included.
|
||||
//
|
||||
//nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
|
||||
func TestTerminalSpinnerTurnsBesideBar(t *testing.T) {
|
||||
stderr := captureStderr(t)
|
||||
params := progressParams{
|
||||
label: scanPhase("hash"), unit: scanUnit, total: 9876543,
|
||||
}
|
||||
|
||||
// No timed draws: the test draws.
|
||||
p := startProgress(params, func() int { return 120 }, time.Hour,
|
||||
time.Now)
|
||||
|
||||
p.mu.Lock()
|
||||
p.count = 1234567
|
||||
p.mu.Unlock()
|
||||
|
||||
const draws = 4
|
||||
|
||||
spinners := make([]string, 0, draws)
|
||||
|
||||
for range draws {
|
||||
before := len(stderr())
|
||||
|
||||
p.draw()
|
||||
|
||||
spinner, _, _ := strings.Cut(lastFrame(stderr()[before:]), " ")
|
||||
spinners = append(spinners, spinner)
|
||||
}
|
||||
|
||||
p.finish()
|
||||
|
||||
for i := 1; i < len(spinners); i++ {
|
||||
if spinners[i] == spinners[i-1] {
|
||||
t.Errorf("spinners at successive draws are %q, want each to "+
|
||||
"differ from the one before", spinners)
|
||||
|
||||
break
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// TestTerminalNarrowedRedrawsInPlace draws a large scan's display, two
|
||||
// and a half hours into the phase, on a terminal 120 columns wide, then
|
||||
// makes the terminal narrower than that line and draws it again a few
|
||||
// times. Nothing written after that, the erase before each redraw
|
||||
// included, may reach the narrower terminal's last column: it would
|
||||
// wrap, and every redraw would leave a line behind. At these widths the
|
||||
// spinner stays a spinner and the bar gives way to the spinner.
|
||||
// wrap, and every redraw would leave a line behind. At the narrower
|
||||
// width the hash phase's bar gives way.
|
||||
//
|
||||
//nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
|
||||
func TestTerminalNarrowedRedrawsInPlace(t *testing.T) {
|
||||
@@ -730,7 +888,7 @@ func TestTerminalNarrowedRedrawsInPlace(t *testing.T) {
|
||||
progressParams{
|
||||
label: scanPhase("hash"), unit: scanUnit, total: 9876543,
|
||||
},
|
||||
90,
|
||||
80,
|
||||
},
|
||||
}
|
||||
|
||||
@@ -770,10 +928,10 @@ func TestTerminalNarrowedRedrawsInPlace(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
// TestProgressWarningsOnOwnLines drives the terminal displays, spinner
|
||||
// and bar, through a run of warnings with no items between them, as when
|
||||
// the walk meets many unreadable paths, for many redraws: every warning
|
||||
// must land on a line of its own, never inside a redraw.
|
||||
// TestProgressWarningsOnOwnLines drives the terminal displays, with a
|
||||
// bar and without, through a run of warnings with no items between
|
||||
// them, as when the walk meets many unreadable paths, for many redraws:
|
||||
// every warning must land on a line of its own, never inside a redraw.
|
||||
//
|
||||
//nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
|
||||
func TestProgressWarningsOnOwnLines(t *testing.T) {
|
||||
@@ -819,11 +977,12 @@ func TestProgressWarningsOnOwnLines(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
// TestProgressWriterRowsOnOwnLines drives the terminal displays,
|
||||
// spinner and bar, through a run of rows written through the display's
|
||||
// TestProgressWriterRowsOnOwnLines drives the terminal displays, with a
|
||||
// bar and without, through a run of rows written through the display's
|
||||
// writer to the same terminal, as stdout is in a plain "sfdupes trees",
|
||||
// each written out at once, for many redraws: the terminal must show
|
||||
// every row whole, in order, on a line of its own.
|
||||
// every row whole, in order, on a line of its own. The terminal is 120
|
||||
// columns wide, so the write phase's display has room for its bar.
|
||||
//
|
||||
//nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
|
||||
func TestProgressWriterRowsOnOwnLines(t *testing.T) {
|
||||
@@ -840,7 +999,8 @@ func TestProgressWriterRowsOnOwnLines(t *testing.T) {
|
||||
var want []string
|
||||
|
||||
for _, params := range cases {
|
||||
p := startProgress(params, terminalWidth, testRedraw, time.Now)
|
||||
p := startProgress(params, func() int { return 120 }, testRedraw,
|
||||
time.Now)
|
||||
out := p.writer(os.Stderr)
|
||||
|
||||
// No pause between rows: one is garbled only if a redraw lands
|
||||
|
||||
+2
-2
@@ -187,7 +187,7 @@ func TestReportStdoutFailsWhileReading(t *testing.T) {
|
||||
// reportOpenLine is the plain line of report's open phase when it opens
|
||||
// the database at once; it prints it as the phase starts and as it ends.
|
||||
const reportOpenLine = "[1/2] open: opening the database, elapsed 0s, " +
|
||||
"eta unknown"
|
||||
"remain unknown"
|
||||
|
||||
// smokeReport is report's stdout for the smoke-test records.
|
||||
const smokeReport = "first\tdupe\tsize\n" +
|
||||
@@ -225,7 +225,7 @@ func TestRunReportProgressNamesEachPhase(t *testing.T) {
|
||||
"report: database " + path + " (from " + databaseEnv + ")",
|
||||
reportOpenLine,
|
||||
reportOpenLine,
|
||||
"[2/2] read: counting the records, elapsed 0s, eta unknown",
|
||||
"[2/2] read: counting the records, elapsed 0s, remain unknown",
|
||||
"[2/2] read: [6/6] 100%, ",
|
||||
"report: 6 records read, 2 duplicate groups, 4 dupe files, " +
|
||||
"6.1 KiB reclaimable",
|
||||
|
||||
@@ -383,7 +383,8 @@ func (s *scanState) runPhases(ctx context.Context, roots []string,
|
||||
) error {
|
||||
// Types and filesystems are checked before pruning so that an
|
||||
// operand under a dropped one is still scanned, not dropped as lying
|
||||
// under it.
|
||||
// under it, and so that an operand inside a .zfs directory gets its
|
||||
// warning even when it lies under another operand.
|
||||
roots = pruneRoots(s.walkableRoots(roots, rules), oneFS, rules,
|
||||
deviceOfPath)
|
||||
|
||||
@@ -411,14 +412,15 @@ func (s *scanState) runPhases(ctx context.Context, roots []string,
|
||||
}
|
||||
|
||||
// walkableRoots returns the operands the walk can start from: regular
|
||||
// files, and directories not named .zfs. Every other operand is warned
|
||||
// about, counted as skipped, and dropped. A dropped operand is no
|
||||
// longer a root, so the records stored beneath it are treated as if it
|
||||
// had not been given: those under no other root count as outside the
|
||||
// roots and are not deleted as unverified. An operand on a filesystem
|
||||
// in rules that is not persistent is dropped the same way, with a line
|
||||
// saying so that is not a warning, and is not counted as skipped. An
|
||||
// operand that fails lstat here is kept, and the walk warns about it.
|
||||
// files, and directories not named .zfs, none of them inside a
|
||||
// directory named .zfs. Every other operand is warned about, counted as
|
||||
// skipped, and dropped. A dropped operand is no longer a root, so the
|
||||
// records stored beneath it are treated as if it had not been given:
|
||||
// those under no other root count as outside the roots and are not
|
||||
// deleted as unverified. An operand on a filesystem in rules that is not
|
||||
// persistent is dropped the same way, with a line saying so that is not
|
||||
// a warning, and is not counted as skipped. An operand that fails lstat
|
||||
// here is kept, and the walk warns about it unless it no longer exists.
|
||||
func (s *scanState) walkableRoots(roots []string, rules walkRules) []string {
|
||||
kept := make([]string, 0, len(roots))
|
||||
|
||||
@@ -629,8 +631,9 @@ func isDatabaseFile(f fileRec, rules walkRules) bool {
|
||||
// (an interrupted scan resumes cheaply: the next run skips everything
|
||||
// already recorded). A run that fails to hash is warned about and
|
||||
// counted as skipped; stale records for its paths, if any, are deleted
|
||||
// by the update phase. The total counts actual reads, so the display
|
||||
// shows a real ETA.
|
||||
// by the update phase. A run whose file no longer exists gets no record
|
||||
// and no warning, and is not counted as skipped. The total counts actual
|
||||
// reads, so the display's time remaining is meaningful.
|
||||
//
|
||||
// Returning early — a failed database write, or a cancelled scan — must
|
||||
// not strand the pool: the feeder would park forever on a full jobs
|
||||
@@ -662,6 +665,11 @@ func (s *scanState) hashPhase(ctx context.Context, workers int) error {
|
||||
|
||||
prog.increment()
|
||||
|
||||
// A file removed since the walk is no error: it gets no record.
|
||||
if errors.Is(r.err, fs.ErrNotExist) {
|
||||
continue
|
||||
}
|
||||
|
||||
if r.err != nil {
|
||||
s.st.skipped += len(r.run)
|
||||
|
||||
@@ -829,10 +837,12 @@ type walkEvent struct {
|
||||
// startWalk seeds every root into the shared walk worker pool and
|
||||
// returns the event stream: one record per regular file, one warning
|
||||
// event per per-path error, and one event per path -x or rules kept the
|
||||
// walk from entering or recording. The channel is closed when the walk
|
||||
// completes, and also when ctx is cancelled — every goroutine in the
|
||||
// pool abandons its blocking send in that case, so the consumer sees a
|
||||
// truncated but properly terminated stream instead of a stalled one.
|
||||
// walk from entering or recording. A path that no longer exists when
|
||||
// the walk reaches it is no error, and gets no event. The channel is
|
||||
// closed when the walk completes, and also when ctx is cancelled —
|
||||
// every goroutine in the pool abandons its blocking send in that case,
|
||||
// so the consumer sees a truncated but properly terminated stream
|
||||
// instead of a stalled one.
|
||||
func startWalk(ctx context.Context, roots []string, oneFS bool,
|
||||
rules walkRules, workers int,
|
||||
) <-chan walkEvent {
|
||||
@@ -865,9 +875,24 @@ func sendEvent(ctx context.Context, events chan<- walkEvent,
|
||||
|
||||
// operandWarning returns the one-line warning for an operand the walk
|
||||
// does not start from, naming the path and what it is, or "" for one it
|
||||
// does: a regular file, or a directory not named .zfs. Symlinks are
|
||||
// never followed, including as operands.
|
||||
// does: a regular file, or a directory not named .zfs, that is not
|
||||
// inside a directory named .zfs, neither as given nor with its symlinks
|
||||
// resolved. Symlinks are never followed, including as operands.
|
||||
func operandWarning(root string, fi fs.FileInfo) string {
|
||||
// The walk never enters a .zfs directory, so it starts from nothing
|
||||
// inside one either, not even through a symlink. An operand whose
|
||||
// symlinks cannot be resolved is checked as given.
|
||||
resolved, err := filepath.EvalSymlinks(root)
|
||||
if err != nil {
|
||||
resolved = root
|
||||
}
|
||||
|
||||
if slices.Contains(strings.Split(filepath.Dir(root), "/"), ".zfs") ||
|
||||
slices.Contains(strings.Split(filepath.Dir(resolved), "/"), ".zfs") {
|
||||
return fmt.Sprintf("walk %s: skipping operand inside a .zfs directory",
|
||||
root)
|
||||
}
|
||||
|
||||
var kind string
|
||||
|
||||
switch mode := fi.Mode(); {
|
||||
@@ -899,13 +924,19 @@ func operandWarning(root string, fi fs.FileInfo) string {
|
||||
// one of the scan's own database files in rules, and a directory
|
||||
// operand becomes an initial job. walkableRoots has already dropped
|
||||
// every other operand. One that has changed into something else since
|
||||
// is warned about and skipped here; it is still a root, so the records
|
||||
// stored beneath it, other than those under another root, are deleted
|
||||
// as unverified.
|
||||
// is warned about and skipped here, and one removed since is skipped
|
||||
// without a warning. Either is still a root, so the records stored
|
||||
// beneath it, other than those under another root, are deleted as
|
||||
// unverified.
|
||||
func seedRoot(ctx context.Context, root string, rules walkRules,
|
||||
events chan<- walkEvent,
|
||||
) []dirJob {
|
||||
fi, err := os.Lstat(root)
|
||||
if errors.Is(err, fs.ErrNotExist) {
|
||||
// Removed since the scan started: no error, and no files.
|
||||
return nil
|
||||
}
|
||||
|
||||
if err != nil {
|
||||
sendEvent(ctx, events, walkEvent{
|
||||
warn: fmt.Sprintf("walk %s: %v", root, err),
|
||||
@@ -1023,11 +1054,17 @@ func dispatchDirs(ctx context.Context, initial []dirJob,
|
||||
|
||||
// walkOneDir reads one directory, emitting an event per regular-file
|
||||
// entry and a warning event per unreadable one, and returns the
|
||||
// subdirectories to descend into.
|
||||
// subdirectories to descend into. A directory or entry removed since
|
||||
// the walk found it gets no event.
|
||||
func walkOneDir(ctx context.Context, job dirJob, oneFS bool,
|
||||
rules walkRules, events chan<- walkEvent,
|
||||
) []dirJob {
|
||||
entries, err := os.ReadDir(job.path)
|
||||
if errors.Is(err, fs.ErrNotExist) {
|
||||
// Removed since its parent was read: no error, and no files.
|
||||
return nil
|
||||
}
|
||||
|
||||
if err != nil {
|
||||
sendEvent(ctx, events, walkEvent{
|
||||
warn: fmt.Sprintf("walk %s: %v", job.path, err),
|
||||
@@ -1070,16 +1107,22 @@ func walkOneDir(ctx context.Context, job dirJob, oneFS bool,
|
||||
|
||||
// emitFile stats one regular directory entry and emits its record.
|
||||
// The lstat happens here in the walk worker, while the directory's
|
||||
// metadata is still hot; a path that fails to stat (or stops being a
|
||||
// regular file) between the directory read and the lstat is warned
|
||||
// about and skipped. A file on a filesystem in rules that is not
|
||||
// persistent, as through a bind mount of one file, is not recorded: it
|
||||
// gets an event naming it instead. One of the scan's own database files
|
||||
// in rules gets no event at all.
|
||||
// metadata is still hot; a path that fails to stat between the
|
||||
// directory read and the lstat is warned about and skipped, unless it
|
||||
// no longer exists, and one that has stopped being a regular file is
|
||||
// skipped. A file on a filesystem in rules that is not persistent, as
|
||||
// through a bind mount of one file, is not recorded: it gets an event
|
||||
// naming it instead. One of the scan's own database files in rules gets
|
||||
// no event at all.
|
||||
func emitFile(ctx context.Context, p string, e fs.DirEntry,
|
||||
rules walkRules, events chan<- walkEvent,
|
||||
) {
|
||||
info, err := e.Info()
|
||||
if errors.Is(err, fs.ErrNotExist) {
|
||||
// Removed since its directory was read: no error.
|
||||
return
|
||||
}
|
||||
|
||||
if err != nil {
|
||||
sendEvent(ctx, events, walkEvent{
|
||||
warn: fmt.Sprintf("stat %s: %v", p, err),
|
||||
@@ -1131,6 +1174,11 @@ func subdirJob(ctx context.Context, p string, e fs.DirEntry,
|
||||
}
|
||||
|
||||
info, err := e.Info()
|
||||
if errors.Is(err, fs.ErrNotExist) {
|
||||
// Removed since its parent was read: no error, and no files.
|
||||
return dirJob{}, false
|
||||
}
|
||||
|
||||
if err != nil {
|
||||
sendEvent(ctx, events, walkEvent{
|
||||
warn: fmt.Sprintf("walk %s: %v", p, err),
|
||||
@@ -1195,7 +1243,7 @@ func inodeOfInfo(fi fs.FileInfo) (uint64, uint64) {
|
||||
|
||||
// hashResult carries the hashes computed for one inode run (or the
|
||||
// error that prevented computing them) from the pool's workers to the
|
||||
// hash phase.
|
||||
// hash phase. Its run leaves out the paths found removed.
|
||||
type hashResult struct {
|
||||
run []fileRec
|
||||
head [sha256.Size]byte
|
||||
@@ -1296,6 +1344,13 @@ func hashWorker(ctx context.Context, jobs <-chan []fileRec,
|
||||
|
||||
head, tail, content, err := hash(run[0].path, run[0].size)
|
||||
|
||||
// A path removed since the walk is dropped from its run. The
|
||||
// next path is a hard link to the same file, and is read instead.
|
||||
for errors.Is(err, fs.ErrNotExist) && len(run) > 1 {
|
||||
run = run[1:]
|
||||
head, tail, content, err = hash(run[0].path, run[0].size)
|
||||
}
|
||||
|
||||
select {
|
||||
case results <- hashResult{
|
||||
run: run, head: head, tail: tail, content: content, err: err,
|
||||
|
||||
+158
-6
@@ -683,6 +683,108 @@ func TestSubdirJobStatError(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
// TestWalkPassesOverRemovedPaths removes a file and a directory after
|
||||
// their parent was read, as when they are deleted while a scan runs.
|
||||
// The walk then reaches them, the directory also as one to read and as
|
||||
// an operand. None of that is an error: the walk sends no event.
|
||||
func TestWalkPassesOverRemovedPaths(t *testing.T) {
|
||||
t.Parallel()
|
||||
|
||||
dir := t.TempDir()
|
||||
file := writeFile(t, dir, "file", []byte("x"))
|
||||
writeFile(t, dir, "sub/f", []byte("y"))
|
||||
sub := filepath.Join(dir, "sub")
|
||||
fileEntry := dirEntryFor(t, dir, "file")
|
||||
subEntry := dirEntryFor(t, dir, "sub")
|
||||
|
||||
for _, p := range []string{file, sub} {
|
||||
err := os.RemoveAll(p)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
}
|
||||
|
||||
ctx := t.Context()
|
||||
events := make(chan walkEvent, 4)
|
||||
|
||||
emitFile(ctx, file, fileEntry, walkRules{}, events)
|
||||
|
||||
_, descend := subdirJob(ctx, sub, subEntry, dirJob{path: dir}, false,
|
||||
walkRules{}, events)
|
||||
subs := walkOneDir(ctx, dirJob{path: sub}, false, walkRules{}, events)
|
||||
jobs := seedRoot(ctx, sub, walkRules{}, events)
|
||||
|
||||
close(events)
|
||||
|
||||
for ev := range events {
|
||||
t.Errorf("event %+v for a removed path, want none", ev)
|
||||
}
|
||||
|
||||
if descend || len(subs) != 0 || len(jobs) != 0 {
|
||||
t.Errorf("descend = %t, subdirectories %+v, jobs %+v, want none",
|
||||
descend, subs, jobs)
|
||||
}
|
||||
}
|
||||
|
||||
// TestScanWarnsAboutUnreadablePaths checks that a permission error is
|
||||
// still warned about and counted as skipped, unlike a removed path. The
|
||||
// walk reaches an unreadable directory, and a file in a directory that
|
||||
// can be read but not searched. Another such file is an operand.
|
||||
//
|
||||
//nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
|
||||
func TestScanWarnsAboutUnreadablePaths(t *testing.T) {
|
||||
if os.Geteuid() == 0 {
|
||||
t.Skip("root ignores file permissions")
|
||||
}
|
||||
|
||||
stderr := captureStderr(t)
|
||||
dir := t.TempDir()
|
||||
tree := filepath.Join(dir, "tree")
|
||||
walked := writeFile(t, tree, "unsearchable/f", []byte("x"))
|
||||
operand := writeFile(t, dir, "unsearchable/f", []byte("y"))
|
||||
unreadable := filepath.Join(tree, "unreadable")
|
||||
|
||||
err := os.Mkdir(unreadable, 0o750)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
modes := map[string]fs.FileMode{
|
||||
unreadable: 0,
|
||||
filepath.Dir(walked): 0o400,
|
||||
filepath.Dir(operand): 0o400,
|
||||
}
|
||||
|
||||
for p, mode := range modes {
|
||||
err = os.Chmod(p, mode)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
// Runs before t.TempDir's own cleanup, which must delete the files.
|
||||
t.Cleanup(func() {
|
||||
//nolint:gosec // removing the files needs the search bit back
|
||||
_ = os.Chmod(p, 0o700)
|
||||
})
|
||||
}
|
||||
|
||||
st := syncTree(t, openTestDB(t), tree, operand)
|
||||
if st != (scanStats{skipped: 3}) {
|
||||
t.Errorf("stats = %+v, want 3 skipped and nothing else", st)
|
||||
}
|
||||
|
||||
got := stderr()
|
||||
for _, warning := range []string{
|
||||
"walk " + unreadable + ": open " + unreadable + ": permission denied\n",
|
||||
"stat " + walked + ": lstat " + walked + ": permission denied\n",
|
||||
"walk " + operand + ": lstat " + operand + ": permission denied\n",
|
||||
} {
|
||||
if !strings.Contains(got, warning) {
|
||||
t.Errorf("stderr = %q, want %q", got, warning)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// syncOneFilesystem scans roots into db with -x and returns the scan
|
||||
// stats. Every device pruneRoots looks up, and the device each
|
||||
// operand's walk compares its subdirectories with, comes from devices
|
||||
@@ -962,8 +1064,9 @@ func TestScanOneFilesystemWalksNestedFileOperand(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
// buildSmokeTree recreates the README smoke-test filesystem layout
|
||||
// with deterministic content and returns the tree root.
|
||||
// buildSmokeTree recreates the tree of the test under README
|
||||
// "Definition of done" with deterministic content and returns the tree
|
||||
// root.
|
||||
func buildSmokeTree(t *testing.T) string {
|
||||
t.Helper()
|
||||
|
||||
@@ -1128,7 +1231,7 @@ func TestScanPipeline(t *testing.T) {
|
||||
// database's records. Each phase's first line names it with its place
|
||||
// among the four: load counts the records before reading them, and the
|
||||
// walk estimates its total from the records under its operand, or says
|
||||
// its ETA is unknown when there are none.
|
||||
// its time remaining is unknown when there are none.
|
||||
//
|
||||
//nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
|
||||
func TestScanProgressNamesEachPhase(t *testing.T) {
|
||||
@@ -1143,14 +1246,14 @@ func TestScanProgressNamesEachPhase(t *testing.T) {
|
||||
syncTree(t, db, filepath.Join(dir, "a"))
|
||||
|
||||
rescan := stderr()[len(first):]
|
||||
load := "[1/4] load: counting the records, elapsed 0s, eta unknown"
|
||||
load := "[1/4] load: counting the records, elapsed 0s, remain unknown"
|
||||
cases := map[string][]string{
|
||||
first: {
|
||||
load, "[2/4] walk: 0 files, 0 files/s, elapsed 0s, eta unknown",
|
||||
load, "[2/4] walk: 0 files, 0 files/s, elapsed 0s, remain unknown",
|
||||
"[3/4] hash: [0/", "[4/4] update: [0/",
|
||||
},
|
||||
rescan: {
|
||||
load, "[2/4] walk: [0/~2] 0%, 0 files/s, elapsed 0s, eta unknown",
|
||||
load, "[2/4] walk: [0/~2] 0%, 0 files/s, elapsed 0s, remain unknown",
|
||||
"[3/4] hash: [0/", "[4/4] update: [0/",
|
||||
},
|
||||
}
|
||||
@@ -1685,6 +1788,55 @@ func TestHashPhaseSkipsFileReplacedByFIFO(t *testing.T) {
|
||||
}
|
||||
}
|
||||
|
||||
// TestHashPhasePassesOverRemovedFiles removes two walked files before
|
||||
// the hash phase reads them: one with no other path, and the first of
|
||||
// two hard links to one file. Neither is an error. The phase prints
|
||||
// nothing but its progress, counts nothing as skipped, and records only
|
||||
// the hard link still there.
|
||||
//
|
||||
//nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
|
||||
func TestHashPhasePassesOverRemovedFiles(t *testing.T) {
|
||||
stderr := captureStderr(t)
|
||||
dir := t.TempDir()
|
||||
alone := writeFile(t, dir, "alone.bin", pattern(1, 300))
|
||||
a := writeFile(t, dir, "a.bin", pattern(2, 300))
|
||||
b := filepath.Join(dir, "b.bin")
|
||||
|
||||
err := os.Link(a, b)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
walked, _ := collectWalk(t, []string{dir}, false, 1)
|
||||
|
||||
// a.bin sorts before b.bin, so the run of the two reads it first.
|
||||
for _, p := range []string{alone, a} {
|
||||
err = os.Remove(p)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
}
|
||||
|
||||
s := &scanState{db: openTestDB(t), toHash: walked}
|
||||
|
||||
err = s.hashPhase(t.Context(), 1)
|
||||
if err != nil {
|
||||
t.Fatalf("hashPhase = %v, want nil", err)
|
||||
}
|
||||
|
||||
if s.st.skipped != 0 || len(s.batch) != 1 || s.batch[0].path != b {
|
||||
t.Errorf("skipped = %d, records %+v, want none skipped and a "+
|
||||
"record for %s alone", s.st.skipped, s.batch, b)
|
||||
}
|
||||
|
||||
for line := range strings.Lines(stderr()) {
|
||||
if !strings.HasPrefix(line, scanPhase("hash")+": ") {
|
||||
t.Errorf("stderr holds %q, want the hash phase's progress alone",
|
||||
line)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// injectedWriteFailure is the message the injected database trigger
|
||||
// aborts with, so the test can recognize its own failure in the error
|
||||
// the scan reports.
|
||||
|
||||
+7
-6
@@ -13,10 +13,11 @@ import (
|
||||
// treesOpenLine is the plain line of trees' open phase when it opens
|
||||
// the database at once; it prints it as the phase starts and as it ends.
|
||||
const treesOpenLine = "[1/4] open: opening the database, elapsed 0s, " +
|
||||
"eta unknown"
|
||||
"remain unknown"
|
||||
|
||||
// smokeTreeRecs mirrors the README smoke-test tree layout: /d/t1 and
|
||||
// /d/t2 are identical, /d/t3 differs from them only by one filename.
|
||||
// smokeTreeRecs mirrors the tree of the test under README "Definition
|
||||
// of done": /d/t1 and /d/t2 are identical, /d/t3 differs from them only
|
||||
// by one filename.
|
||||
func smokeTreeRecs() []scanRec {
|
||||
f1Head, f1Tail, f1Content := testHash("f1h"), testHash("f1t"), testHash("f1c")
|
||||
f2Head, f2Tail, f2Content := testHash("f2h"), testHash("f2t"), testHash("f2c")
|
||||
@@ -236,11 +237,11 @@ func TestRunTreesProgressNamesEachPhase(t *testing.T) {
|
||||
"trees: database " + path + " (from " + databaseEnv + ")",
|
||||
treesOpenLine,
|
||||
treesOpenLine,
|
||||
"[2/4] read: counting the records, elapsed 0s, eta unknown",
|
||||
"[2/4] read: counting the records, elapsed 0s, remain unknown",
|
||||
"[2/4] read: [6/6] 100%, ",
|
||||
"[3/4] group: [0/8] 0%, 0 directories/s, elapsed 0s, eta unknown",
|
||||
"[3/4] group: [0/8] 0%, 0 directories/s, elapsed 0s, remain unknown",
|
||||
"[3/4] group: [8/8] 100%, ",
|
||||
"[4/4] write: [0/1] 0%, 0 groups/s, elapsed 0s, eta unknown",
|
||||
"[4/4] write: [0/1] 0%, 0 groups/s, elapsed 0s, remain unknown",
|
||||
"[4/4] write: [1/1] 100%, ",
|
||||
"trees: 6 records read, 1 duplicate tree groups, 1 dupe trees, ",
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user