Merge pull request 'next' (#50) from next into main

Reviewed-on: #50

.dockerignore

@@ -1,9 +1,4 @@
-# .git is sent without its config. Without a VERSION build argument the
+.git
-# stage that compiles runs `git describe --tags --always` on .git, which
-# does not need .git/config; that file can hold a credential, such as a
-# password in a remote URL or the token the CI checkout step stores there.
-.git/config
-
 .claude
 .DS_Store
 sfdupes

.gitea/workflows/check.yml

@@ -6,6 +6,4 @@ jobs:
         steps:
             # actions/checkout v4.2.2, 2026-02-22
             - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683
-              with:
-                  fetch-depth: 0
             - run: script/cibuild

Dockerfile

@@ -108,19 +108,7 @@ ARG CHECK_EPOCH
 RUN echo "gate test, epoch ${CHECK_EPOCH}" && make test
 RUN echo "gate fmt-check, epoch ${CHECK_EPOCH}" && make fmt-check
 
-# The version stamped into the binary: the VERSION build argument when
+RUN make build
-# one is given, otherwise `git describe --tags --always` of the .git in
-# the build context (git is installed by script/bootstrap above). A
-# context that carries .git and still yields no version fails the build;
-# with neither, as from a source tarball, it is "dev".
-ARG VERSION
-RUN version="${VERSION:-$(git describe --tags --always || echo dev)}"; \
-    if [ -e .git ] && { [ -z "$version" ] || [ "$version" = dev ] || \
-        [ "$version" = unknown ]; }; then \
-        echo "no version could be derived although the build context carries .git" >&2; \
-        exit 1; \
-    fi; \
-    make build VERSION="$version"
 
 # Runtime stage
 # alpine:3.22, 2026-07-23

README.md

@@ -113,10 +113,8 @@ Goals, in order:
     `sfdupes`.
 -   Dependencies: standard library, `github.com/spf13/cobra` for the
     CLI, **one progress-bar library**
-    (`github.com/schollz/progressbar/v3`), `golang.org/x/term` to tell
+    (`github.com/schollz/progressbar/v3`), and **one SQLite driver**
-    whether stderr is a terminal, **one SQLite driver**
+    (`modernc.org/sqlite`, pure Go, so builds keep cgo disabled).
-    (`modernc.org/sqlite`, pure Go, so builds keep cgo disabled), and
-    `golang.org/x/sys` for `flock(2)` (the scan lock, see "Database").
     `github.com/spf13/viper` is permitted if configuration-file support
     is ever needed, but is not currently used. No other third-party
     deps.
@@ -154,42 +152,16 @@ All three subcommands operate on a single SQLite database file:
     use. `report` and `trees` require an existing database; a missing
     database file is a fatal error (exit 1) telling the user to run
     `scan` first.
--   Only one `scan` runs against a database at a time. For its whole
+-   The database uses WAL journal mode and a busy timeout, so running a
-    run, `scan` holds an exclusive `flock(2)` lock on a lock file
+    report while a cron `scan` is in progress is safe. The filesystem
-    beside the database, named by appending `.lock` to the database
+    is authoritative; the database is an eventually-consistent
-    path (`/var/lib/sfdupes/db.sqlite.lock` by default), taken before
+    reflection of it. Hashed records are committed in batched
-    it walks the filesystem or opens the database. A second `scan`
+    transactions while the scan is still running (keeping the WAL
-    against the same database does not wait: it fails at once with a
+    small and letting concurrent reports observe progress), so a
-    one-line error naming the lock file and exits 1, without walking
+    report may see a scan's changes partially applied, and a scan
-    anything or opening the database, and the running scan carries on.
+    that dies partway leaves a valid database holding everything
-    The lock file is created on first use, open to its owner only, and
+    hashed so far; the next scan skips those records and converges
-    left in place: a leftover file blocks nothing, because the lock
+    toward the filesystem.
-    ends with the process holding it however it ends, a fatal error or
-    an interrupt included, and deleting the file while a scan runs
-    would let a second scan start. `report` and `trees` never take the
-    lock, so they run during a scan.
--   While `scan` runs, the database is in WAL journal mode with a busy
-    timeout, so running a report while a cron `scan` is in progress is
-    safe. The filesystem is authoritative; the database is an
-    eventually-consistent reflection of it. Hashed records are
-    committed in batched transactions while the scan is still running
-    (keeping the WAL small and letting concurrent reports observe
-    progress), so a report may see a scan's changes partially applied,
-    and a scan that dies partway leaves a valid database holding
-    everything hashed so far; the next scan skips those records and
-    converges toward the filesystem.
--   `scan` switches the database back to rollback-journal mode when it
-    closes it, so between scans the database file alone holds the whole
-    database. Each switch needs the database to itself: a `scan` that
-    starts while a report is still reading waits for it up to the
-    10-second busy timeout, then fails; a `scan` that ends while a
-    report has the database open warns and leaves the database in WAL
-    mode until the next scan.
--   `report` and `trees` open the database read-only and need only read
-    access to the database file, and no write access to its directory.
-    While the database is in WAL mode they also read the `-wal` and
-    `-shm` files beside it, which SQLite creates with the database
-    file's permissions.
 -   Schema (`PRAGMA user_version` is the schema version, currently 1; a
     database with any other version is a fatal error):
 
@@ -456,15 +428,6 @@ first	dupe	size
 /srv/a/big.iso	/srv/c/big-copy2.iso	4294967296
 ```
 
-Paths are raw bytes and may hold any byte except NUL, so the path
-columns (`first` and `dupe`) are escaped to keep every row one line of
-tab-separated fields: a backslash is written as `\\`, a tab as `\t`, a
-newline as `\n`, and a carriage return as `\r`. Every other byte is
-written unchanged, including bytes that are not valid UTF-8. Undoing
-those four escapes gives back the stored path. Grouping and ordering
-use the stored path, not the escaped one. The warnings `scan` prints on
-stderr are escaped the same way, so each warning is one line.
-
 Summary to stderr: records read, number of duplicate groups, number of
 dupe files, and total reclaimable bytes (sum of `size` over all dupe
 rows) in human units.
@@ -536,9 +499,6 @@ first	dupe	files	size
 /srv/a/project	/srv/backup/project	3417	104857600
 ```
 
-The `first` and `dupe` paths are escaped as described under "Report
-output format". The root directory's path is `/`.
-
 Summary to stderr: records read, number of duplicate-tree groups,
 number of dupe trees, and total reclaimable bytes (sum of `size` over
 all dupe rows) in human units.
@@ -573,41 +533,22 @@ hash: [12345/98765] 12% |████      | 92 files/s elapsed 2:32 eta 17:54
 
 Additional requirements:
 
--   When stderr is not a terminal (a pipe, a file, `/dev/null`), do not
+-   When stderr is not a TTY, do not emit ANSI redraws: print a plain
-    emit ANSI redraws: print a plain one-line progress update the moment
+    one-line progress update no more often than every 5 seconds instead.
-    each phase starts, then no more often than every 5 seconds.
 -   Progress updates are driven from the main goroutine and must be
-    non-blocking with respect to the worker pool. On a terminal the
+    non-blocking with respect to the worker pool.
-    spinner-style displays also redraw on their own several times a
-    second, so their count and elapsed time stay current while a phase
-    waits for its next item.
--   A warning printed during a phase always lands on a line of its own,
-    never inside the progress display.
 -   `report` and `trees` modes need no progress display, only their
     stderr summaries.
 
 ### Error handling and exit codes
 
 -   `0`: success, even if individual files were skipped with warnings.
--   `1`: fatal error (e.g., a `PATH` operand does not exist, another
+-   `1`: fatal error (e.g., a `PATH` operand does not exist, the
-    `scan` is already running against the same database, the database
+    database cannot be created/opened/read/written, a missing database
-    cannot be created/opened/read/written, a missing database for
+    for `report`/`trees`, stdout write failure).
-    `report`/`trees`, stdout write failure).
 -   `2`: usage error (including `scan` with no `PATH` operand and
     `report`/`trees` with any positional argument).
 
-A stdout write failure, such as a full disk, is reported in one line on
-stderr and exits 1. Two cases never reach sfdupes as a failed write:
-
--   When the reader of a stdout pipe exits early, as in
-    `sfdupes report | head`, the next write ends sfdupes with `SIGPIPE`,
-    quietly and without a summary, the way `cat` or `sort` end. The
-    shell reports the signal (status 141 in most shells), not exit 1.
--   When stdout is closed outright (`sfdupes report >&-`), the Go
-    runtime opens `/dev/null` in its place before sfdupes starts, so
-    the output is discarded and the run succeeds, as with
-    `> /dev/null`.
-
 ## Entrypoints
 
 This repository adheres to the
@@ -745,7 +686,7 @@ All of the following, run in this directory, must pass:
 
     ```sh
     d=$(mktemp -d)
-    export SFDUPES_DATABASE="$(mktemp -d)/db.sqlite"
+    export SFDUPES_DATABASE="$d/db.sqlite"
     mkdir -p "$d/a" "$d/b"
     head -c 2000 /dev/urandom > "$d/a/one.bin"
     cp "$d/a/one.bin" "$d/b/copy.bin"
@@ -773,9 +714,9 @@ All of the following, run in this directory, must pass:
     ./sfdupes report
     ```
 
-    (The database lives in a temp directory of its own: inside `$d`,
+    (The scan database lives inside `$d` here purely for test hygiene;
-    the scan would record it, and its empty lock file would join the
+    scanning `$d` therefore also records the SQLite file itself, which
-    `empty1`/`empty2` group.)
+    is harmless.)
 
     Expected from the first `report`: `one.bin`/`copy.bin`/`copy2.bin`
     form one group (two dupe rows, `first` is the lexicographically

TODO.md

@@ -29,37 +29,6 @@
 
 # Completed Steps
 
-- progress prints at once on a non-terminal, uses a real terminal test,
-  and prints warnings through a spinner instead of racing its redraw
-  (2026-10-03, https://git.eeqj.de/sneak/sfdupes/issues/13)
-
-- `scan` holds a lock on a lock file beside the database for its whole run,
-  so a second `scan` fails at once with exit 1 (2026-10-03,
-  https://git.eeqj.de/sneak/sfdupes/issues/53)
-
-- test stdout write failures in `report` and `trees`; README states that
-  `| head` ends sfdupes by `SIGPIPE` and `>&-` writes to `/dev/null`
-  (2026-10-03, https://git.eeqj.de/sneak/sfdupes/issues/30)
-
-- `report` and `trees` open the database read-only, and `scan` leaves it
-  out of WAL mode, so reading needs only read access (2026-10-03, closes
-  https://git.eeqj.de/sneak/sfdupes/issues/8)
-
-- escape tabs, newlines, carriage returns and backslashes in report,
-  trees and warning paths; the root directory's path is `/`
-  (2026-10-03, https://git.eeqj.de/sneak/sfdupes/issues/7)
-
-- stamp the git tag or short commit in a plain `docker build .`
-  instead of `dev` (2026-10-02, branch `next`, closes
-  https://git.eeqj.de/sneak/sfdupes/issues/67): `.dockerignore` now
-  sends `.git`, without `.git/config`, and the `Dockerfile` build
-  stage takes the `VERSION` build argument when one is given,
-  otherwise `git describe --tags --always` of that `.git`. The build
-  fails if the context carries `.git` and the version still comes out
-  empty, `dev` or `unknown`. The CI checkout step fetches the full
-  history (`fetch-depth: 0`) so CI sees the tag and stamps the same
-  value as `make build`.
-
 - replace the 1 KiB end-window sampling with the head/tail plus
   content-hash ladder (2026-09-22, branch `next`, closes
   https://git.eeqj.de/sneak/sfdupes/issues/61): a file under 10 MiB is

db.go

@@ -11,7 +11,6 @@ import (
 	"slices"
 	"strconv"
 
-	"golang.org/x/sys/unix"
 	// The pure-Go SQLite driver, registered as "sqlite"; keeps cgo
 	// disabled.
 	_ "modernc.org/sqlite"
@@ -33,11 +32,6 @@ const schemaVersion = 1
 // scan.
 const dbDirPerm = 0o755
 
-// lockFilePerm is the mode for the scan lock file. Anyone who can open
-// the file can hold the lock and keep every scan from running, so it
-// is open to its owner only.
-const lockFilePerm = 0o600
-
 // createTableSQL is the schema applied to a fresh database. Paths are
 // BLOBs because Unix paths are raw bytes, not guaranteed UTF-8.
 const createTableSQL = `
@@ -70,10 +64,6 @@ var errNoDatabase = errors.New(
 // does not understand.
 var errSchemaVersion = errors.New("unsupported database schema version")
 
-// errScanRunning reports that another scan holds the lock on the
-// database.
-var errScanRunning = errors.New("another scan is running")
-
 // databasePath resolves the database location: SFDUPES_DATABASE when
 // set and non-empty, the compiled-in default otherwise.
 func databasePath() string {
@@ -84,24 +74,16 @@ func databasePath() string {
 	return defaultDatabasePath
 }
 
-// scanParams are the connection parameters for scan: read-write, with
+// openDB opens the SQLite database at path with WAL journaling and a
-// WAL journaling and a busy timeout, so a report can run while a cron
+// busy timeout, so a report can run while a cron scan is in progress.
-// scan is in progress. closeScanDatabase leaves WAL mode again.
+// It does not create or verify the schema.
-const scanParams = "_pragma=busy_timeout(10000)" +
+func openDB(path string) (*sql.DB, error) {
-	"&_pragma=journal_mode(WAL)" +
+	dsn := "file:" + path +
-	"&_pragma=synchronous(NORMAL)"
+		"?_pragma=busy_timeout(10000)" +
+		"&_pragma=journal_mode(WAL)" +
+		"&_pragma=synchronous(NORMAL)"
 
-// reportParams are the connection parameters for report and trees:
+	db, err := sql.Open("sqlite", dsn)
-// read-only, with the same busy timeout. They set no journal mode,
-// because setting one is a write.
-const reportParams = "mode=ro" +
-	"&_pragma=busy_timeout(10000)" +
-	"&_pragma=query_only(1)"
-
-// openDB opens the SQLite database at path with the connection
-// parameters params. It does not create or verify the schema.
-func openDB(path, params string) (*sql.DB, error) {
-	db, err := sql.Open("sqlite", "file:"+path+"?"+params)
 	if err != nil {
 		return nil, fmt.Errorf("open database %s: %w", path, err)
 	}
@@ -114,43 +96,6 @@ func openDB(path, params string) (*sql.DB, error) {
 	return db, nil
 }
 
-// lockScanDatabase takes the lock that keeps a second scan off the
-// database at path: an exclusive flock(2) on the file beside it named
-// path with ".lock" appended, created along with the database's parent
-// directory if missing. A lock held by another scan fails at once
-// instead of waiting. The lock lasts until the returned file is closed
-// or the process ends. The file is never deleted: a scan that deleted
-// it would let the next scan lock a new file while another still holds
-// the old one.
-func lockScanDatabase(path string) (*os.File, error) {
-	err := os.MkdirAll(filepath.Dir(path), dbDirPerm)
-	if err != nil {
-		return nil, fmt.Errorf("create database directory: %w", err)
-	}
-
-	lockPath := path + ".lock"
-
-	//nolint:gosec // the operator chooses the database path
-	f, err := os.OpenFile(lockPath, os.O_RDWR|os.O_CREATE, lockFilePerm)
-	if err != nil {
-		return nil, err
-	}
-
-	err = unix.Flock(int(f.Fd()), unix.LOCK_EX|unix.LOCK_NB)
-	if err != nil {
-		_ = f.Close()
-
-		if errors.Is(err, unix.EWOULDBLOCK) {
-			return nil, fmt.Errorf("%w (lock held on %s)",
-				errScanRunning, lockPath)
-		}
-
-		return nil, fmt.Errorf("lock %s: %w", lockPath, err)
-	}
-
-	return f, nil
-}
-
 // openScanDatabase opens the database for the scan subcommand, creating
 // the file, its parent directory, and the schema as needed.
 func openScanDatabase(ctx context.Context, path string) (*sql.DB, error) {
@@ -159,7 +104,7 @@ func openScanDatabase(ctx context.Context, path string) (*sql.DB, error) {
 		return nil, fmt.Errorf("create database directory: %w", err)
 	}
 
-	db, err := openDB(path, scanParams)
+	db, err := openDB(path)
 	if err != nil {
 		return nil, err
 	}
@@ -174,24 +119,6 @@ func openScanDatabase(ctx context.Context, path string) (*sql.DB, error) {
 	return db, nil
 }
 
-// closeScanDatabase switches the database at path from WAL back to
-// rollback-journal mode and closes it. Out of WAL mode the database
-// file alone holds the whole database, so a reader needs no -wal or
-// -shm file beside it, nor write access to create them. The switch
-// fails while a report has the database open; the database then stays
-// in WAL mode, still readable, until a later scan closes it.
-func closeScanDatabase(ctx context.Context, db *sql.DB, path string) {
-	// Runs on the way out of a cancelled scan too.
-	_, err := db.ExecContext(context.WithoutCancel(ctx),
-		"PRAGMA journal_mode = DELETE")
-	if err != nil {
-		fmt.Fprintf(os.Stderr, "scan: database %s left in WAL mode: %v\n",
-			path, err)
-	}
-
-	_ = db.Close()
-}
-
 // openReportDatabase opens an existing database for the report and
 // trees subcommands. A missing database file is an error directing the
 // user to run scan first; the schema version must match exactly.
@@ -207,7 +134,7 @@ func openReportDatabase(ctx context.Context,
 		return nil, fmt.Errorf("database: %w", err)
 	}
 
-	db, err := openDB(path, reportParams)
+	db, err := openDB(path)
 	if err != nil {
 		return nil, err
 	}

db_test.go

@@ -5,7 +5,6 @@ import (
 	"database/sql"
 	"errors"
 	"fmt"
-	"os"
 	"path/filepath"
 	"slices"
 	"strings"
@@ -131,49 +130,6 @@ func TestOpenReportDatabaseOK(t *testing.T) {
 	_ = db.Close()
 }
 
-func TestCloseScanDatabaseWhileReportOpen(t *testing.T) {
-	t.Parallel()
-
-	// A report holding the database open stops scan from taking it out
-	// of WAL mode. The -wal and -shm files must then stay beside it, so
-	// that a later report still needs only read access.
-	path := testDBPath(t)
-
-	scanDB, err := openScanDatabase(t.Context(), path)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	reportDB, err := openReportDatabase(t.Context(), path)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	closeScanDatabase(t.Context(), scanDB, path)
-
-	_ = reportDB.Close()
-
-	_, err = os.Stat(path + "-wal")
-	if err != nil {
-		t.Fatalf("no -wal left: the switch out of WAL mode was not "+
-			"stopped: %v", err)
-	}
-
-	makeReadOnly(t, path)
-
-	reportDB, err = openReportDatabase(t.Context(), path)
-	if err != nil {
-		t.Fatalf("openReportDatabase: %v", err)
-	}
-
-	defer func() { _ = reportDB.Close() }()
-
-	_, err = loadFileRows(t.Context(), reportDB)
-	if err != nil {
-		t.Fatalf("loadFileRows: %v", err)
-	}
-}
-
 func TestApplyChangesRoundTrip(t *testing.T) {
 	t.Parallel()
 

go.mod

@@ -5,8 +5,6 @@ go 1.25.7
 require (
 	github.com/schollz/progressbar/v3 v3.19.1
 	github.com/spf13/cobra v1.10.2
-	golang.org/x/sys v0.46.0
-	golang.org/x/term v0.44.0
 	modernc.org/sqlite v1.54.0
 )
 
@@ -20,6 +18,8 @@ require (
 	github.com/remyoudompheng/bigfft v0.0.0-20230129092748-24d4a6f8daec // indirect
 	github.com/rivo/uniseg v0.4.7 // indirect
 	github.com/spf13/pflag v1.0.9 // indirect
+	golang.org/x/sys v0.46.0 // indirect
+	golang.org/x/term v0.44.0 // indirect
 	modernc.org/libc v1.74.1 // indirect
 	modernc.org/mathutil v1.7.1 // indirect
 	modernc.org/memory v1.11.0 // indirect

main.go

@@ -57,27 +57,22 @@ var errNoSubcommand = errors.New("no subcommand")
 var Version = "dev"
 
 func main() {
-	// Once the reader of a stdout pipe has gone, as in "sfdupes report |
+	os.Exit(run(os.Args[1:], os.Stderr))
-	// head", the Go runtime ends the process with SIGPIPE on the next
-	// write instead of returning an error (README "Error handling").
-	// Registering for SIGPIPE with os/signal would change that.
-	os.Exit(run(os.Args[1:], os.Stdout, os.Stderr))
 }
 
 // run executes args against the command tree and returns the process
 // exit code. It is the program's single exit point: the subcommands
 // return their errors instead of exiting, so every deferred cleanup —
 // above all closing the database, which checkpoints the SQLite WAL —
-// runs before the process ends. The report and trees subcommands write
+// runs before the process ends.
-// their data to stdout.
+func run(args []string, stderr io.Writer) int {
-func run(args []string, stdout, stderr io.Writer) int {
 	// A nil slice makes cobra fall back to os.Args, which would let a
 	// test binary's own flags reach the command tree.
 	if args == nil {
 		args = []string{}
 	}
 
-	root := newRootCommand(stdout, stderr)
+	root := newRootCommand(stderr)
 	root.SetArgs(args)
 
 	err := root.Execute()
@@ -103,7 +98,7 @@ func run(args []string, stdout, stderr io.Writer) int {
 // newRootCommand builds the command tree. Everything on stdout is
 // machine-readable data; all human-facing output (help, usage, errors)
 // goes to stderr.
-func newRootCommand(stdout, stderr io.Writer) *cobra.Command {
+func newRootCommand(stderr io.Writer) *cobra.Command {
 	root := &cobra.Command{
 		Use:     "sfdupes",
 		Short:   "Find candidate duplicate files by size and head/tail/content SHA-256",
@@ -145,7 +140,7 @@ func newRootCommand(stdout, stderr io.Writer) *cobra.Command {
 		Short: "Read the scan database and print the file-level duplicates report",
 		Args:  cobra.NoArgs,
 		RunE: runE(func(ctx context.Context, _ []string) error {
-			return runReport(ctx, stdout)
+			return runReport(ctx)
 		}),
 	}
 
@@ -154,7 +149,7 @@ func newRootCommand(stdout, stderr io.Writer) *cobra.Command {
 		Short: "Read the scan database and print the duplicate-tree report",
 		Args:  cobra.NoArgs,
 		RunE: runE(func(ctx context.Context, _ []string) error {
-			return runTrees(ctx, stdout)
+			return runTrees(ctx)
 		}),
 	}
 

main_test.go

@@ -44,54 +44,60 @@ func assertNoSidecars(t *testing.T, path string) {
 	}
 }
 
-// makeReadOnly takes write permission away from the database at path,
+// captureStdout redirects os.Stdout to a file for the rest of the test
-// from any WAL sidecar beside it, and from their directory, as for a
+// and returns a function reading back everything written to it. Only
-// user reading a database that a root cron scan keeps. Root ignores
+// machine-readable data belongs on stdout (README design goal 4), so
-// file permissions, so it skips the test when run as root.
+// the tests assert on it directly.
-func makeReadOnly(t *testing.T, path string) {
+func captureStdout(t *testing.T) func() string {
 	t.Helper()
 
-	if os.Geteuid() == 0 {
+	f, err := os.Create(filepath.Join(t.TempDir(), "stdout"))
-		t.Skip("root ignores file permissions")
-	}
-
-	err := os.Chmod(path, 0o400)
 	if err != nil {
 		t.Fatal(err)
 	}
 
-	for _, suffix := range walSuffixes {
+	saved := os.Stdout
-		err = os.Chmod(path+suffix, 0o400)
+	os.Stdout = f
-		if err != nil && !errors.Is(err, fs.ErrNotExist) {
+
+	t.Cleanup(func() {
+		os.Stdout = saved
+
+		_ = f.Close()
+	})
+
+	return func() string {
+		// Read what has been written without disturbing the write
+		// offset, so the capture can be inspected more than once.
+		size, err := f.Seek(0, io.SeekCurrent)
+		if err != nil {
 			t.Fatal(err)
 		}
+
+		if size == 0 {
+			return ""
+		}
+
+		b := make([]byte, size)
+
+		_, err = f.ReadAt(b, 0)
+		if err != nil {
+			t.Fatal(err)
+		}
+
+		return string(b)
 	}
-
-	dir := filepath.Dir(path)
-
-	//nolint:gosec // reaching the database needs the search bit
-	err = os.Chmod(dir, 0o500)
-	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 directory needs its search bit back
-		_ = os.Chmod(dir, 0o700)
-	})
 }
 
 // brokenDatabase writes a database that opens cleanly and passes the
 // schema-version check but has no files table, so the first query
 // fails with the database already open: a fatal error on a path that
-// owns an open database. It closes the database the way scan does.
+// owns an open database.
 func brokenDatabase(t *testing.T) string {
 	t.Helper()
 
 	path := testDBPath(t)
 
-	db, err := openDB(path, scanParams)
+	db, err := openDB(path)
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -102,7 +108,10 @@ func brokenDatabase(t *testing.T) string {
 		t.Fatal(err)
 	}
 
-	closeScanDatabase(t.Context(), db, path)
+	err = db.Close()
+	if err != nil {
+		t.Fatal(err)
+	}
 
 	return path
 }
@@ -135,10 +144,7 @@ func TestOpenDatabaseKeepsWALWhileOpen(t *testing.T) {
 
 func TestRunFatalAfterOpenClosesDatabase(t *testing.T) {
 	// Every subcommand that owns an open database must close it when
-	// it fails: no os.Exit between the open and the return. The
+	// it fails: no os.Exit between the open and the return.
-	// sidecar check is evidence of the close only for scan: report and
-	// trees only read a database that is out of WAL mode, which leaves
-	// nothing on disk whether they close it or not.
 	cases := map[string][]string{
 		cmdScan:   {cmdScan},
 		cmdReport: {cmdReport},
@@ -154,15 +160,17 @@ func TestRunFatalAfterOpenClosesDatabase(t *testing.T) {
 				args = append(args, t.TempDir())
 			}
 
-			var stdout, stderr bytes.Buffer
+			var stderr bytes.Buffer
 
-			code := run(args, &stdout, &stderr)
+			stdout := captureStdout(t)
+
+			code := run(args, &stderr)
 			if code != exitFatal {
 				t.Errorf("run(%v) = %d, want %d", args, code, exitFatal)
 			}
 
 			assertNoSidecars(t, path)
-			assertFatalOutput(t, stderr.String(), stdout.String())
+			assertFatalOutput(t, stderr.String(), stdout())
 
 			// Proof that the failure happened after the open: only a
 			// query against the opened database can report this.
@@ -180,16 +188,18 @@ func TestRunMissingOperandIsFatalNotUsage(t *testing.T) {
 	// must not dump the usage text.
 	t.Setenv(databaseEnv, testDBPath(t))
 
-	var stdout, stderr bytes.Buffer
+	var stderr bytes.Buffer
+
+	stdout := captureStdout(t)
 
 	missing := filepath.Join(t.TempDir(), "nope")
 
-	code := run([]string{cmdScan, missing}, &stdout, &stderr)
+	code := run([]string{cmdScan, missing}, &stderr)
 	if code != exitFatal {
 		t.Errorf("run(scan %s) = %d, want %d", missing, code, exitFatal)
 	}
 
-	assertFatalOutput(t, stderr.String(), stdout.String())
+	assertFatalOutput(t, stderr.String(), stdout())
 }
 
 // assertFatalOutput checks that a fatal error was reported the way
@@ -233,9 +243,11 @@ func TestRunUsageErrors(t *testing.T) {
 			// path that does not exist.
 			t.Setenv(databaseEnv, testDBPath(t))
 
-			var stdout, stderr bytes.Buffer
+			var stderr bytes.Buffer
 
-			code := run(tc.args, &stdout, &stderr)
+			stdout := captureStdout(t)
+
+			code := run(tc.args, &stderr)
 			if code != exitUsage {
 				t.Errorf("run(%v) = %d, want %d", tc.args, code, exitUsage)
 			}
@@ -244,7 +256,7 @@ func TestRunUsageErrors(t *testing.T) {
 				t.Errorf("stderr = %q, want %q", stderr.String(), tc.want)
 			}
 
-			if got := stdout.String(); got != "" {
+			if got := stdout(); got != "" {
 				t.Errorf("stdout = %q, want nothing (data only)", got)
 			}
 		})
@@ -253,9 +265,9 @@ func TestRunUsageErrors(t *testing.T) {
 
 // TestRunHelpAndVersionSucceed checks that the two informational flags
 // exit 0 and keep their human-facing output on stderr.
+//
+//nolint:paralleltest // captureStdout replaces the process-wide os.Stdout
 func TestRunHelpAndVersionSucceed(t *testing.T) {
-	t.Parallel()
-
 	assertHumanOutput(t, "--help")
 	assertHumanOutput(t, "--version")
 }
@@ -266,9 +278,11 @@ func TestRunHelpAndVersionSucceed(t *testing.T) {
 func assertHumanOutput(t *testing.T, arg string) {
 	t.Helper()
 
-	var stdout, stderr bytes.Buffer
+	var stderr bytes.Buffer
 
-	code := run([]string{arg}, &stdout, &stderr)
+	stdout := captureStdout(t)
+
+	code := run([]string{arg}, &stderr)
 	if code != exitOK {
 		t.Errorf("run(%s) = %d, want %d", arg, code, exitOK)
 	}
@@ -277,7 +291,7 @@ func assertHumanOutput(t *testing.T, arg string) {
 		t.Errorf("run(%s) wrote nothing to stderr", arg)
 	}
 
-	if got := stdout.String(); got != "" {
+	if got := stdout(); got != "" {
 		t.Errorf("stdout = %q, want nothing (data only)", got)
 	}
 }
@@ -306,15 +320,17 @@ func scanFixture(t *testing.T) []string {
 		t.Fatal(err)
 	}
 
-	var stdout, stderr bytes.Buffer
+	var stderr bytes.Buffer
 
-	code := run([]string{cmdScan, dir}, &stdout, &stderr)
+	stdout := captureStdout(t)
+
+	code := run([]string{cmdScan, dir}, &stderr)
 	if code != exitOK {
 		t.Fatalf("run(scan) = %d, want %d; stderr: %s",
 			code, exitOK, stderr.String())
 	}
 
-	if got := stdout.String(); got != "" {
+	if got := stdout(); got != "" {
 		t.Errorf("scan stdout = %q, want nothing (data only)", got)
 	}
 
@@ -335,16 +351,18 @@ func TestRunReportSucceeds(t *testing.T) {
 
 	dupes := scanFixture(t)
 
-	var stdout, stderr bytes.Buffer
+	var stderr bytes.Buffer
 
-	code := run([]string{cmdReport}, &stdout, &stderr)
+	stdout := captureStdout(t)
+
+	code := run([]string{cmdReport}, &stderr)
 	if code != exitOK {
 		t.Fatalf("run(report) = %d, want %d; stderr: %s",
 			code, exitOK, stderr.String())
 	}
 
 	want := "first\tdupe\tsize\n" + dupes[0] + "\t" + dupes[1] + "\t300\n"
-	if got := stdout.String(); got != want {
+	if got := stdout(); got != want {
 		t.Errorf("stdout = %q, want %q", got, want)
 	}
 
@@ -357,9 +375,11 @@ func TestRunTreesSucceeds(t *testing.T) {
 
 	dupes := scanFixture(t)
 
-	var stdout, stderr bytes.Buffer
+	var stderr bytes.Buffer
 
-	code := run([]string{cmdTrees}, &stdout, &stderr)
+	stdout := captureStdout(t)
+
+	code := run([]string{cmdTrees}, &stderr)
 	if code != exitOK {
 		t.Fatalf("run(trees) = %d, want %d; stderr: %s",
 			code, exitOK, stderr.String())
@@ -369,197 +389,9 @@ func TestRunTreesSucceeds(t *testing.T) {
 	// trees of each other.
 	want := "first\tdupe\tfiles\tsize\n" +
 		filepath.Dir(dupes[0]) + "\t" + filepath.Dir(dupes[1]) + "\t1\t300\n"
-	if got := stdout.String(); got != want {
+	if got := stdout(); got != want {
 		t.Errorf("stdout = %q, want %q", got, want)
 	}
 
 	assertNoSidecars(t, path)
 }
-
-func TestRunReportsNeedOnlyReadAccess(t *testing.T) {
-	// README §Database: report and trees need only read access to the
-	// database file. With its directory read-only as well, SQLite
-	// cannot create any file beside it.
-	path := testDBPath(t)
-	t.Setenv(databaseEnv, path)
-
-	dupes := scanFixture(t)
-	assertNoSidecars(t, path)
-	makeReadOnly(t, path)
-
-	cases := map[string]string{
-		cmdReport: "first\tdupe\tsize\n" +
-			dupes[0] + "\t" + dupes[1] + "\t300\n",
-		cmdTrees: "first\tdupe\tfiles\tsize\n" +
-			filepath.Dir(dupes[0]) + "\t" + filepath.Dir(dupes[1]) +
-			"\t1\t300\n",
-	}
-
-	for name, want := range cases {
-		var stdout, stderr bytes.Buffer
-
-		code := run([]string{name}, &stdout, &stderr)
-		if code != exitOK {
-			t.Errorf("run(%s) = %d, want %d; stderr: %s",
-				name, code, exitOK, stderr.String())
-
-			continue
-		}
-
-		if got := stdout.String(); got != want {
-			t.Errorf("%s stdout = %q, want %q", name, got, want)
-		}
-	}
-}
-
-// holdScanLock takes the lock on the database at path, as a running
-// scan does, and holds it until the test ends. It fails the test when
-// the lock is already held.
-func holdScanLock(t *testing.T, path string) {
-	t.Helper()
-
-	lock, err := lockScanDatabase(path)
-	if err != nil {
-		t.Fatalf("lock %s: %v", path, err)
-	}
-
-	t.Cleanup(func() { _ = lock.Close() })
-}
-
-func TestRunSecondScanFails(t *testing.T) {
-	// README §Database: while one scan holds the lock, a second scan
-	// fails at once, naming the lock file, without creating the
-	// database.
-	path := testDBPath(t)
-	t.Setenv(databaseEnv, path)
-
-	holdScanLock(t, path)
-
-	var stdout, stderr bytes.Buffer
-
-	code := run([]string{cmdScan, t.TempDir()}, &stdout, &stderr)
-	if code != exitFatal {
-		t.Errorf("run(scan) = %d, want %d", code, exitFatal)
-	}
-
-	want := "sfdupes: another scan is running (lock held on " +
-		path + ".lock)\n"
-	if got := stderr.String(); got != want {
-		t.Errorf("stderr = %q, want %q", got, want)
-	}
-
-	if got := stdout.String(); got != "" {
-		t.Errorf("stdout = %q, want nothing (data only)", got)
-	}
-
-	_, err := os.Stat(path)
-	if !errors.Is(err, fs.ErrNotExist) {
-		t.Errorf("stat %s = %v, want the database not created", path, err)
-	}
-}
-
-func TestRunScanReleasesLock(t *testing.T) {
-	// README §Database: a scan releases the lock however it ends.
-	t.Run("success", func(t *testing.T) {
-		path := testDBPath(t)
-		t.Setenv(databaseEnv, path)
-
-		scanFixture(t)
-		holdScanLock(t, path)
-	})
-
-	t.Run("fatal error", func(t *testing.T) {
-		path := brokenDatabase(t)
-		t.Setenv(databaseEnv, path)
-
-		code := run([]string{cmdScan, t.TempDir()}, io.Discard, io.Discard)
-		if code != exitFatal {
-			t.Fatalf("run(scan) = %d, want %d", code, exitFatal)
-		}
-
-		holdScanLock(t, path)
-	})
-}
-
-func TestRunReportsDuringScan(t *testing.T) {
-	// README §Database: report and trees never take the lock, so they
-	// run while a scan holds it.
-	path := testDBPath(t)
-	t.Setenv(databaseEnv, path)
-
-	scanFixture(t)
-	holdScanLock(t, path)
-
-	for _, name := range []string{cmdReport, cmdTrees} {
-		var stderr bytes.Buffer
-
-		code := run([]string{name}, io.Discard, &stderr)
-		if code != exitOK {
-			t.Errorf("run(%s) = %d, want %d; stderr: %s",
-				name, code, exitOK, stderr.String())
-		}
-	}
-}
-
-func TestRunStdoutClosedIsFatal(t *testing.T) {
-	// README §Error handling: a stdout write failure exits 1, reported
-	// in one line on stderr.
-	for _, name := range []string{cmdReport, cmdTrees} {
-		t.Run(name, func(t *testing.T) {
-			t.Setenv(databaseEnv, testDBPath(t))
-
-			scanFixture(t)
-
-			stdout, err := os.Create(filepath.Join(t.TempDir(), "stdout"))
-			if err != nil {
-				t.Fatal(err)
-			}
-
-			err = stdout.Close()
-			if err != nil {
-				t.Fatal(err)
-			}
-
-			var stderr bytes.Buffer
-
-			code := run([]string{name}, stdout, &stderr)
-			if code != exitFatal {
-				t.Errorf("run(%s) = %d, want %d", name, code, exitFatal)
-			}
-
-			got := stderr.String()
-			if !strings.HasPrefix(got, "sfdupes: write stdout: ") ||
-				!strings.Contains(got, os.ErrClosed.Error()) ||
-				strings.Count(got, "\n") != 1 {
-				t.Errorf("stderr = %q, want one line reporting the "+
-					"failed stdout write", got)
-			}
-		})
-	}
-}
-
-// errWriteFailed is the error failingWriter returns.
-var errWriteFailed = errors.New("write failed")
-
-// failingWriter is a stdout that fails every write.
-type failingWriter struct{}
-
-func (failingWriter) Write([]byte) (int, error) { return 0, errWriteFailed }
-
-func TestStdoutWriteErrorPropagates(t *testing.T) {
-	t.Setenv(databaseEnv, testDBPath(t))
-
-	scanFixture(t)
-
-	cases := map[string]func(context.Context, io.Writer) error{
-		cmdReport: runReport,
-		cmdTrees:  runTrees,
-	}
-
-	for name, fn := range cases {
-		err := fn(t.Context(), failingWriter{})
-		if !errors.Is(err, errWriteFailed) {
-			t.Errorf("%s: error = %v, want %v", name, err, errWriteFailed)
-		}
-	}
-}

progress.go

@@ -6,7 +6,6 @@ import (
 	"time"
 
 	"github.com/schollz/progressbar/v3"
-	"golang.org/x/term"
 )
 
 // plainInterval is the minimum time between progress lines when stderr
@@ -25,23 +24,24 @@ const percentScale = 100
 
 // stderrIsTTY reports whether stderr is attached to a terminal.
 func stderrIsTTY() bool {
-	return term.IsTerminal(int(os.Stderr.Fd()))
+	fi, err := os.Stderr.Stat()
+	if err != nil {
+		return false
+	}
+
+	return fi.Mode()&os.ModeCharDevice != 0
 }
 
 // progress renders one scan pass's progress on stderr. On a TTY it
 // delegates to the progressbar library (spinner style when the total is
 // unknown, full bar with count/percent/rate/elapsed/ETA otherwise). When
 // stderr is not a TTY it emits no ANSI redraws: it prints a plain
-// one-line update as the pass starts, then no more often than every
+// one-line update no more often than every plainInterval.
-// plainInterval.
 //
-// All methods must be called from the main goroutine only. On a TTY
+// All methods must be called from the main goroutine only. A nil
-// the library also redraws a spinner from its own goroutine, several
+// *progress is a valid no-display receiver: every method is a no-op,
-// times a second, so its count and elapsed time stay current while a
+// so batched database flushes during the streaming pass can reuse the
-// pass waits for its next item. A nil *progress is a valid
+// update-pass helpers without rendering anything.
-// no-display receiver: every method is a no-op, so batched database
-// flushes during the streaming pass can reuse the update-pass helpers
-// without rendering anything.
 type progress struct {
 	label string
 	total int64 // -1 when unknown (walk pass)
@@ -53,22 +53,10 @@ type progress struct {
 
 func newProgress(label string, total int64) *progress {
 	p := &progress{label: label, total: total, start: time.Now()}
-	if stderrIsTTY() {
+	if !stderrIsTTY() {
-		p.bar = newBar(label, total)
-
 		return p
 	}
 
-	// Print the zero state at once: the first item may take minutes,
-	// and a pass must never look hung.
-	p.last = p.start
-	fmt.Fprintln(os.Stderr, p.plainLine())
-
-	return p
-}
-
-// newBar builds the TTY display for newProgress.
-func newBar(label string, total int64) *progressbar.ProgressBar {
 	opts := []progressbar.Option{
 		progressbar.OptionSetWriter(os.Stderr),
 		progressbar.OptionSetDescription(label),
@@ -93,7 +81,9 @@ func newBar(label string, total int64) *progressbar.ProgressBar {
 		)
 	}
 
-	return progressbar.NewOptions64(total, opts...)
+	p.bar = progressbar.NewOptions64(total, opts...)
+
+	return p
 }
 
 // increment records one completed item and refreshes the display.
@@ -116,29 +106,16 @@ func (p *progress) increment() {
 }
 
 // warnf prints a one-line warning to stderr without corrupting the bar.
-// The whole message is escaped like a report's path columns, so a path
-// holding a newline cannot split the warning.
 func (p *progress) warnf(format string, args ...any) {
 	if p == nil {
 		return
 	}
 
-	msg := escapePath(fmt.Sprintf(format, args...))
-
-	if p.bar != nil && p.total < 0 {
-		// The library also redraws a spinner from its own goroutine, so
-		// a direct write could land inside a redraw. The bar prints the
-		// warning itself, just before its next redraw.
-		_, _ = progressbar.Bprintln(p.bar, msg)
-
-		return
-	}
-
 	if p.bar != nil {
 		_ = p.bar.Clear()
 	}
 
-	fmt.Fprintln(os.Stderr, msg)
+	fmt.Fprintf(os.Stderr, format+"\n", args...)
 }
 
 // finish terminates the pass's display.

progress_test.go

@@ -1,192 +0,0 @@
-package main
-
-import (
-	"os"
-	"path/filepath"
-	"strings"
-	"testing"
-	"time"
-)
-
-// spinnerIdle comfortably outlasts the 100ms interval at which the
-// progressbar library redraws a spinner from its own goroutine.
-const spinnerIdle = 500 * time.Millisecond
-
-// captureStderr points os.Stderr at a file for the rest of the test and
-// returns a function reading back everything written to it.
-func captureStderr(t *testing.T) func() string {
-	t.Helper()
-
-	path := filepath.Join(t.TempDir(), "stderr")
-
-	f, err := os.Create(path) //nolint:gosec // test-controlled path
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	saved := os.Stderr
-	os.Stderr = f
-
-	t.Cleanup(func() {
-		os.Stderr = saved
-
-		_ = f.Close()
-	})
-
-	return func() string {
-		b, err := os.ReadFile(path) //nolint:gosec // test-controlled path
-		if err != nil {
-			t.Fatal(err)
-		}
-
-		return string(b)
-	}
-}
-
-//nolint:paralleltest // replaces the process-wide os.Stderr
-func TestStderrIsTTYFalseForNonTerminals(t *testing.T) {
-	r, pipe, err := os.Pipe()
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	regular, err := os.Create(filepath.Join(t.TempDir(), "stderr"))
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	devNull, err := os.OpenFile(os.DevNull, os.O_WRONLY, 0)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	saved := os.Stderr
-
-	t.Cleanup(func() {
-		os.Stderr = saved
-
-		for _, f := range []*os.File{r, pipe, regular, devNull} {
-			_ = f.Close()
-		}
-	})
-
-	cases := map[string]*os.File{
-		"a pipe":         pipe,
-		"a regular file": regular,
-		os.DevNull:       devNull,
-	}
-
-	for name, f := range cases {
-		os.Stderr = f
-
-		if stderrIsTTY() {
-			t.Errorf("stderrIsTTY() = true with stderr on %s", name)
-		}
-	}
-}
-
-// TestNewProgressPrintsBeforeFirstItem checks that each pass shows its
-// zero state the moment it starts when stderr is not a terminal, and
-// that the next line still waits for plainInterval.
-//
-//nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
-func TestNewProgressPrintsBeforeFirstItem(t *testing.T) {
-	stderr := captureStderr(t)
-
-	newProgress("walk", -1).increment()
-	newProgress("hash", 10).increment()
-
-	want := "walk: 0 files, elapsed 0s\n" +
-		"hash: [0/10] 0% 0 files/s elapsed 0s eta ?\n"
-	if got := stderr(); got != want {
-		t.Errorf("stderr = %q, want %q", got, want)
-	}
-}
-
-// newWalkSpinner returns the walk pass's terminal display, writing to
-// os.Stderr whether or not it is a terminal, and stops the library's
-// redraws when the test ends.
-func newWalkSpinner(t *testing.T) *progress {
-	t.Helper()
-
-	p := &progress{
-		label: "walk", total: -1, start: time.Now(),
-		bar: newBar("walk", -1),
-	}
-	t.Cleanup(p.finish)
-
-	return p
-}
-
-// TestProgressWarningsOnOwnLines drives the terminal display of the walk
-// pass through a run of warnings with no items between them, as when the
-// walk meets many unreadable paths, for several of the spinner's
-// 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) {
-	stderr := captureStderr(t)
-	p := newWalkSpinner(t)
-
-	// No pause between warnings: one written straight to stderr is
-	// garbled only if a redraw lands while it is being written.
-	issued := 0
-	for start := time.Now(); time.Since(start) < spinnerIdle; issued++ {
-		p.warnf("warning")
-	}
-
-	// The spinner prints the warnings at its next redraw.
-	time.Sleep(spinnerIdle)
-
-	// A terminal shows each line as the text after its last carriage
-	// return.
-	shown := 0
-
-	for line := range strings.SplitSeq(stderr(), "\n") {
-		if !strings.Contains(line, "warning") {
-			continue
-		}
-
-		shown++
-
-		if text := line[strings.LastIndex(line, "\r")+1:]; text != "warning" {
-			t.Errorf("terminal shows %q, want %q", text, "warning")
-		}
-	}
-
-	if shown != issued {
-		t.Errorf("%d warning lines, want %d", shown, issued)
-	}
-}
-
-// TestSpinnerShowsCountAfterBurst checks that once a burst of items
-// faster than the redraw limit is over, the walk display shows every
-// item completed while it waits for the next one.
-//
-//nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
-func TestSpinnerShowsCountAfterBurst(t *testing.T) {
-	stderr := captureStderr(t)
-	p := newWalkSpinner(t)
-
-	for range 50 {
-		p.increment()
-	}
-
-	time.Sleep(spinnerIdle)
-
-	// A terminal shows the last frame drawn. The library starts each
-	// frame with a carriage return and erases the previous one with
-	// spaces first.
-	var shown string
-
-	for frame := range strings.SplitSeq(stderr(), "\r") {
-		if strings.TrimSpace(frame) != "" {
-			shown = frame
-		}
-	}
-
-	if !strings.Contains(shown, "(50/-,") {
-		t.Errorf("terminal shows %q, want a count of 50", shown)
-	}
-}

report.go

@@ -4,7 +4,6 @@ import (
 	"bufio"
 	"context"
 	"fmt"
-	"io"
 	"os"
 	"slices"
 	"strings"
@@ -32,9 +31,9 @@ type scanRec struct {
 // loadRecords opens the database and reads every file record for the
 // report and trees subcommands. Any database problem — including a
 // missing database — is fatal. The error is returned rather than
-// exiting, so that the deferred close always runs; the database is
+// exiting, so that the deferred close — which checkpoints the SQLite
-// closed before the caller formats its output, so it stays closed even
+// WAL — always runs; the database is closed before the caller formats
-// if that output fails.
+// its output, so it stays closed even if that output fails.
 func loadRecords(ctx context.Context) ([]scanRec, error) {
 	dbPath := databasePath()
 
@@ -66,7 +65,7 @@ type dupeGroup struct {
 // from the database and prints the file-level duplicates report as TSV
 // on stdout. It never touches the scanned filesystem; its only I/O is
 // the database, stdout, and stderr.
-func runReport(ctx context.Context, stdout io.Writer) error {
+func runReport(ctx context.Context) error {
 	recs, err := loadRecords(ctx)
 	if err != nil {
 		return err
@@ -74,7 +73,7 @@ func runReport(ctx context.Context, stdout io.Writer) error {
 
 	dupes := collectDupeGroups(recs)
 
-	out := bufio.NewWriterSize(stdout, ioBufSize)
+	out := bufio.NewWriterSize(os.Stdout, ioBufSize)
 
 	_, err = fmt.Fprintln(out, "first\tdupe\tsize")
 	if err != nil {
@@ -88,7 +87,7 @@ func runReport(ctx context.Context, stdout io.Writer) error {
 	for _, g := range dupes {
 		for _, p := range g.paths[1:] {
 			_, err = fmt.Fprintf(out, "%s\t%s\t%d\n",
-				escapePath(g.paths[0]), escapePath(p), g.size)
+				g.paths[0], p, g.size)
 			if err != nil {
 				return fmt.Errorf("write stdout: %w", err)
 			}
@@ -157,21 +156,6 @@ func collectDupeGroups(recs []scanRec) []dupeGroup {
 	return dupes
 }
 
-// escapePath returns a path as it is written in a report column (README
-// "Report output format"): a backslash, tab, newline or carriage return
-// becomes \\, \t, \n or \r, and every other byte is kept as it is.
-// Grouping and sorting use the raw path, never this form.
-func escapePath(p string) string {
-	// Most paths need no escaping; skip building a replacer for them.
-	if !strings.ContainsAny(p, "\\\t\n\r") {
-		return p
-	}
-
-	return strings.NewReplacer(
-		`\`, `\\`, "\t", `\t`, "\n", `\n`, "\r", `\r`,
-	).Replace(p)
-}
-
 // humanBytes formats a byte count in human units (binary prefixes).
 func humanBytes(n int64) string {
 	const unit = 1024

report_test.go

@@ -1,126 +1,10 @@
 package main
 
 import (
-	"bytes"
-	"io"
-	"os"
-	"path/filepath"
 	"slices"
 	"testing"
 )
 
-// awkwardDir is a directory name holding every byte the reports escape.
-const awkwardDir = "/d/\tone\ntwo\rthree\\four"
-
-// awkwardPairRecs is a duplicate pair in sibling directories /d/A and
-// awkwardDir. A raw tab sorts before "A" but its escaped form `\t`
-// sorts after it, so awkwardDir coming first shows that sorting uses
-// the raw path.
-func awkwardPairRecs() []scanRec {
-	return []scanRec{
-		{size: 5, head: "h", tail: "t", content: "c", path: "/d/A/f"},
-		{size: 5, head: "h", tail: "t", content: "c", path: awkwardDir + "/f"},
-	}
-}
-
-// seedDatabase writes recs into a fresh database and returns its path.
-func seedDatabase(t *testing.T, recs []scanRec) string {
-	t.Helper()
-
-	path := testDBPath(t)
-
-	db, err := openScanDatabase(t.Context(), path)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	err = applyChanges(t.Context(), db, recs, nil, nil)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	err = db.Close()
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	return path
-}
-
-func TestRunReportEscapesPaths(t *testing.T) {
-	t.Setenv(databaseEnv, seedDatabase(t, awkwardPairRecs()))
-
-	var stdout, stderr bytes.Buffer
-
-	code := run([]string{cmdReport}, &stdout, &stderr)
-	if code != exitOK {
-		t.Fatalf("run(report) = %d, want %d; stderr: %s",
-			code, exitOK, stderr.String())
-	}
-
-	want := "first\tdupe\tsize\n" +
-		`/d/\tone\ntwo\rthree\\four/f` + "\t/d/A/f\t5\n"
-	if got := stdout.String(); got != want {
-		t.Errorf("stdout = %q, want %q", got, want)
-	}
-}
-
-func TestEscapePath(t *testing.T) {
-	t.Parallel()
-
-	cases := map[string]string{
-		"/srv/plain":    "/srv/plain",
-		"/a\tb":         `/a\tb`,
-		"/a\nb":         `/a\nb`,
-		"/a\rb":         `/a\rb`,
-		`/a\b`:          `/a\\b`,
-		`/a\tb`:         `/a\\tb`,
-		"/not-utf8\xff": "/not-utf8\xff",
-	}
-	for in, want := range cases {
-		if got := escapePath(in); got != want {
-			t.Errorf("escapePath(%q) = %q, want %q", in, got, want)
-		}
-	}
-}
-
-// TestWarnfEscapes checks that a warning naming a path that holds a
-// newline is still one line.
-//
-//nolint:paralleltest // replaces the process-wide os.Stderr
-func TestWarnfEscapes(t *testing.T) {
-	f, err := os.Create(filepath.Join(t.TempDir(), "stderr"))
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	saved := os.Stderr
-	os.Stderr = f
-
-	t.Cleanup(func() {
-		os.Stderr = saved
-
-		_ = f.Close()
-	})
-
-	(&progress{}).warnf("stat %s: %s", "/d/a\nb", "gone")
-
-	_, err = f.Seek(0, io.SeekStart)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	got, err := io.ReadAll(f)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	want := `stat /d/a\nb: gone` + "\n"
-	if string(got) != want {
-		t.Errorf("warning = %q, want %q", got, want)
-	}
-}
-
 func TestCollectDupeGroups(t *testing.T) {
 	t.Parallel()
 

scan.go

@@ -85,13 +85,10 @@ type fileMeta struct {
 // least one other file shares are ever hashed: a size-unique file
 // cannot be a duplicate. A file of headTailMin or more gets its content
 // hash only when its size, head, and tail match another file's. Flag
-// parsing and the at-least-one-operand check are done by cobra. The
+// parsing and the at-least-one-operand check are done by cobra. Errors
-// scan holds the lock on the database for its whole run, so a second
+// are returned rather than exiting, so that the deferred close — which
-// scan fails before it walks the filesystem or opens the database.
+// checkpoints the SQLite WAL — always runs. Cancelling ctx unwinds the
-// Errors are returned rather than exiting, so that the deferred close —
+// worker pools and aborts the scan with the context's error.
-// which takes the database out of WAL mode — always runs, and the lock
-// is released after it. Cancelling ctx unwinds the worker pools and
-// aborts the scan with the context's error.
 func runScan(ctx context.Context, roots []string, workers int,
 	oneFS bool,
 ) error {
@@ -106,19 +103,12 @@ func runScan(ctx context.Context, roots []string, workers int,
 
 	dbPath := databasePath()
 
-	lock, err := lockScanDatabase(dbPath)
-	if err != nil {
-		return err
-	}
-
-	defer func() { _ = lock.Close() }()
-
 	db, err := openScanDatabase(ctx, dbPath)
 	if err != nil {
 		return err
 	}
 
-	defer closeScanDatabase(ctx, db, dbPath)
+	defer func() { _ = db.Close() }()
 
 	st, err := syncScan(ctx, db, roots, workers, oneFS)
 	if err != nil {

scan_test.go

@@ -7,7 +7,6 @@ import (
 	"database/sql"
 	"encoding/hex"
 	"fmt"
-	"io"
 	"os"
 	"path/filepath"
 	"runtime"
@@ -1549,7 +1548,7 @@ func TestScanHashWriteFailureUnwindsPool(t *testing.T) {
 
 	code := run([]string{
 		cmdScan, "--workers", strconv.Itoa(hashLeakWorkers), dir,
-	}, io.Discard, &stderr)
+	}, &stderr)
 	if code != exitFatal {
 		t.Fatalf("run(scan) = %d, want %d; stderr: %s",
 			code, exitFatal, stderr.String())

script/cibuild

@@ -16,10 +16,10 @@
 # implies the repo is green.
 #
 # That implication holds only because of CHECK_EPOCH. A COPY layer is
-# invalidated only by changed content, and a rebuild of an unchanged
+# invalidated by changed content, and a merge commit's tree is
-# checkout sends the same content, so without a fresh value here Docker
+# byte-identical to the branch head it merges, so without a fresh value
-# serves the gate layers from cache and the build reports a green it
+# here Docker serves the gate layers from cache and the build reports a
-# never earned. Passing the current epoch invalidates the gate
+# green it never earned. Passing the current epoch invalidates the gate
 # layers on every run while leaving the pinned base images and
 # go mod download cached; see the Dockerfile for the placement.
 set -eu

trees.go

@@ -5,7 +5,6 @@ import (
 	"context"
 	"crypto/sha256"
 	"fmt"
-	"io"
 	"os"
 	"slices"
 	"strconv"
@@ -37,7 +36,7 @@ type treeNode struct {
 // maximal duplicate-tree groups as TSV on stdout. It never touches the
 // scanned filesystem; its only I/O is the database, stdout, and
 // stderr.
-func runTrees(ctx context.Context, stdout io.Writer) error {
+func runTrees(ctx context.Context) error {
 	recs, err := loadRecords(ctx)
 	if err != nil {
 		return err
@@ -48,7 +47,7 @@ func runTrees(ctx context.Context, stdout io.Writer) error {
 
 	dupes := collectTreeGroups(allDirs, super)
 
-	out := bufio.NewWriterSize(stdout, ioBufSize)
+	out := bufio.NewWriterSize(os.Stdout, ioBufSize)
 
 	_, err = fmt.Fprintln(out, "first\tdupe\tfiles\tsize")
 	if err != nil {
@@ -63,8 +62,7 @@ func runTrees(ctx context.Context, stdout io.Writer) error {
 		first := g[0]
 		for _, n := range g[1:] {
 			_, err = fmt.Fprintf(out, "%s\t%s\t%d\t%d\n",
-				escapePath(first.path), escapePath(n.path),
+				first.path, n.path, first.fileCount, first.totalSize)
-				first.fileCount, first.totalSize)
 			if err != nil {
 				return fmt.Errorf("write stdout: %w", err)
 			}
@@ -89,8 +87,8 @@ func runTrees(ctx context.Context, stdout io.Writer) error {
 
 // buildHierarchy reconstructs the directory hierarchy from the record
 // paths under a synthetic super-root. Paths are split on "/"; for
-// absolute paths the first component is empty, which becomes the
+// absolute paths the first component is empty, which simply becomes a
-// top-level node with path "/". It returns the super-root and every
+// top-level node representing "/". It returns the super-root and every
 // directory node created.
 func buildHierarchy(recs []scanRec) (*treeNode, []*treeNode) {
 	super := &treeNode{}
@@ -104,17 +102,9 @@ func buildHierarchy(recs []scanRec) (*treeNode, []*treeNode) {
 		for _, c := range comps[:len(comps)-1] {
 			child := node.dirs[c]
 			if child == nil {
-				childPath := node.path + "/" + c
+				childPath := c
-
+				if node != super {
-				// The root directory's path is "/", not empty, and its
+					childPath = node.path + "/" + c
-				// children's paths start with one slash, not two.
-				switch {
-				case node == super && c == "":
-					childPath = "/"
-				case node == super:
-					childPath = c
-				case node.path == "/":
-					childPath = "/" + c
 				}
 
 				child = &treeNode{path: childPath, parent: node}

trees_test.go

@@ -1,7 +1,6 @@
 package main
 
 import (
-	"bytes"
 	"slices"
 	"testing"
 )
@@ -85,44 +84,6 @@ func TestBuildHierarchyCounts(t *testing.T) {
 	}
 }
 
-func TestBuildHierarchyRootPath(t *testing.T) {
-	t.Parallel()
-
-	// The root directory's path is "/", never empty, and its
-	// children's paths start with a single slash.
-	_, dirs := buildHierarchy([]scanRec{{path: "/f"}, {path: "/srv/g"}})
-
-	got := make([]string, 0, len(dirs))
-	for _, d := range dirs {
-		got = append(got, d.path)
-	}
-
-	slices.Sort(got)
-
-	want := []string{"/", "/srv"}
-	if !slices.Equal(got, want) {
-		t.Fatalf("directory paths = %q, want %q", got, want)
-	}
-}
-
-func TestRunTreesEscapesPaths(t *testing.T) {
-	t.Setenv(databaseEnv, seedDatabase(t, awkwardPairRecs()))
-
-	var stdout, stderr bytes.Buffer
-
-	code := run([]string{cmdTrees}, &stdout, &stderr)
-	if code != exitOK {
-		t.Fatalf("run(trees) = %d, want %d; stderr: %s",
-			code, exitOK, stderr.String())
-	}
-
-	want := "first\tdupe\tfiles\tsize\n" +
-		`/d/\tone\ntwo\rthree\\four` + "\t/d/A\t1\t5\n"
-	if got := stdout.String(); got != want {
-		t.Errorf("stdout = %q, want %q", got, want)
-	}
-}
-
 func TestTreeDigests(t *testing.T) {
 	t.Parallel()