Refuse an unversioned database that already has a files table (closes #11)

An unversioned database (user_version 0) that already contains a files
table was not created by this build; it is a foreign or partially
initialized file. Adopting it silently could corrupt unrelated data, so
createSchema now checks for a files table first and, when one exists,
returns the schema-version error telling the operator to remove the file
and rescan. A genuinely empty database is still created and stamped as
before.

Model: opus-4-8 (implementation); opus-5-5 (rebase)

Dockerfile

@@ -51,21 +51,14 @@ RUN echo "gate lint, epoch ${CHECK_EPOCH}" && \
 FROM golang@sha256:56961d79ea8129efddcc0b8643fd8a5416b4e6228cfd477e3fd61deb2672c587 AS builder
 
 # We never build or run as root. Create an unprivileged user and point
-# HOME and the build cache at its home so go build and go test can write
-# it when we drop to it below. $GOPATH/bin is deliberately not on PATH:
-# script/bootstrap no longer `go install`s anything (the linter runs
-# from a pinned image, never from a host install), so nothing lands
+# HOME and the Go caches at its home so go build and go test can write
+# their caches when we drop to it below. $GOPATH/bin is deliberately not
+# on PATH: script/bootstrap no longer `go install`s anything (the linter
+# runs from a pinned image, never from a host install), so nothing lands
 # there and adding it would only widen what this image resolves.
-#
-# The module cache is kept outside that home, at the base image's
-# default /go/pkg/mod, and belongs to root: script/bootstrap fills it as
-# root. Do not move it into the home and hand it over with `chown -R`:
-# that walks every file in it, which took from about 80 s to over ten
-# minutes on a shared host, depending on load.
 RUN adduser -D -u 1000 builder
 ENV HOME=/home/builder
 ENV GOPATH=/home/builder/go
-ENV GOMODCACHE=/go/pkg/mod
 ENV GOCACHE=/home/builder/.cache/go-build
 
 WORKDIR /src
@@ -90,22 +83,11 @@ COPY script/ script/
 COPY go.mod go.sum ./
 RUN script/bootstrap
 
-# Hand builder only what it writes to, without walking the module cache.
-# This layer stays cached with bootstrap.
-# - /src itself: make build writes the binary into it, and git refuses
-#   a repository whose top directory belongs to another user.
-# - the module cache's cache/download directory itself, not what is in
-#   it: Go only reads the downloaded modules, but make build saves its
-#   lookup of this module's own version from git there, in a new
-#   directory named after the module path.
-# - builder's home: the go commands bootstrap ran as root left Go's
-#   telemetry files there, a few small files.
-RUN chown builder:builder /src /go/pkg/mod/cache/download && \
-    chown -R builder:builder /home/builder
+COPY . .
 
-# The sources are handed to builder as they are copied, so no layer has
-# to walk them. Then drop root before running any checks or builds.
-COPY --chown=builder:builder . .
+# Hand the sources and caches to the unprivileged user, then drop root
+# before running any checks or builds.
+RUN chown -R builder:builder /src /home/builder
 USER builder
 
 # Fail the build unless the branch is green. Runs as non-root so the

README.md

@@ -94,15 +94,7 @@ Goals, in order:
     millions of files, ~150 TB filesystem, possibly slow or busy disks
     (ZFS pool under resilver). Holding one small record (path, size,
     mtime) per file in memory during a scan is acceptable; holding
-    every file's hashes is not (they stay in the database). The
-    reporting commands do not hold every file's hashes either: `report`
-    lets SQLite group and order the records and writes each row as it
-    reads it, so its memory does not grow with the database, and
-    `trees` reads the records in path order and keeps each directory's
-    path, digest and totals, plus the hashes of only the files in the
-    directories holding the record being read, so its memory grows with
-    the number of directories and with the size of the largest
-    directory.
+    every file's hashes is not (they stay in the database).
 3.  **Scan incrementally, analyze offline.** The expensive filesystem
     scan maintains a persistent database; an unchanged file is never
     read again on a rescan, except to compute its content hash once a
@@ -121,10 +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
-    whether stderr is a terminal, **one SQLite driver**
-    (`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/schollz/progressbar/v3`), and **one SQLite driver**
+    (`modernc.org/sqlite`, pure Go, so builds keep cgo disabled).
     `github.com/spf13/viper` is permitted if configuration-file support
     is ever needed, but is not currently used. No other third-party
     deps.
@@ -162,45 +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
-    run, `scan` holds an exclusive `flock(2)` lock on a lock file
-    beside the database, named by appending `.lock` to the database
-    path (`/var/lib/sfdupes/db.sqlite.lock` by default), taken before
-    it walks the filesystem or opens the database. A second `scan`
-    against the same database does not wait: it fails at once with a
-    one-line error naming the lock file and exits 1, without walking
-    anything or opening the database, and the running scan carries on.
-    The lock file is created on first use, open to its owner only, and
-    left in place: a leftover file blocks nothing, because the lock
-    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` writes each row as it reads it,
-    so it is still reading while its output is paused (a pager, a
-    stalled pipe), and a `scan` started then fails after the busy
-    timeout.
--   `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.
+-   The database uses WAL journal mode and 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.
 -   Schema (`PRAGMA user_version` is the schema version, currently 1; a
     database with any other version is a fatal error):
 
@@ -213,7 +174,6 @@ All three subcommands operate on a single SQLite database file:
         tail    TEXT NOT NULL,     -- lowercase-hex SHA-256; last 64 KiB, or whole file under 10 MiB
         content TEXT NOT NULL      -- lowercase-hex SHA-256, whole file or samples
     ) WITHOUT ROWID;
-    CREATE INDEX files_signature ON files (size, head, tail, content);
     ```
 
     Paths are stored as BLOBs because Unix paths are raw bytes, not
@@ -228,8 +188,7 @@ All three subcommands operate on a single SQLite database file:
     until the content phase of a scan (see "`scan` mode" below) has
     read the file. A record with an empty `content` is never part of a
     duplicate group, though it still defines the file for tree
-    reconstruction. The `files_signature` index lets SQLite group the
-    records by signature for `report` without sorting the whole table.
+    reconstruction.
 
 ### Duplicate detection
 
@@ -292,18 +251,6 @@ duplicates another or lies under another is dropped before walking,
 so every file is reached exactly once and produces one database
 record.
 
-An operand that is a symlink (never followed, not even as an operand),
-socket, FIFO, or device node, or a directory named `.zfs`, is not
-scanned. `scan` prints a one-line warning naming the path and what it
-is, counts it as skipped, and drops it from the scanned operands before
-reading the database. Another operand beneath it is still scanned. The
-records stored beneath it are not deleted: they are treated like any
-other record outside the scanned operands, including the content-phase
-exception below. If it lies under another operand, they are under that
-operand instead, and are deleted like any other record there that this
-scan did not verify. This is not an error: a scan whose every operand
-is dropped walks nothing and exits 0.
-
 `scan` synchronizes the database with the filesystem state under the
 scanned operands:
 
@@ -409,12 +356,9 @@ during the hash phase:
 Rules for the walk:
 
 -   Only regular files. Skip directories, symlinks (do not follow,
-    including symlink operands), sockets, FIFOs, and device nodes. An
-    operand that is a symlink, socket, FIFO, or device node is dropped
-    as described in "`scan` mode" above.
+    including symlink operands), sockets, FIFOs, and device nodes.
 -   Never descend into a directory named `.zfs` (ZFS snapshot pseudo-dirs;
-    walking them would list every file once per snapshot), not even
-    when it is an operand; such an operand is dropped the same way.
+    walking them would list every file once per snapshot).
 -   Filesystem boundaries are crossed by default. With `-x`
     (long form `--one-file-system`, following the GNU `du`/`rsync`
     convention), never descend into a directory on a different
@@ -425,11 +369,9 @@ Rules for the walk:
     path, and continue. Per-file errors never abort the run; the final
     summary reports how many were skipped. As specified above, a
     skipped path that has a database record from an earlier scan loses
-    that record, unless it failed only in the content phase, or is an
-    operand dropped before the database was read that lies under no
-    other operand; an unreadable directory subtree likewise loses its
-    records (accepted: the database mirrors what the latest scan could
-    actually verify).
+    that record, unless it failed only in the content phase; an
+    unreadable directory subtree likewise loses its records (accepted:
+    the database mirrors what the latest scan could actually verify).
 
 Concurrency: the walk phase (which also stats files), the hash phase,
 and the content phase each use a worker pool of `--workers` workers
@@ -457,12 +399,9 @@ arguments.
 
 **`report` must never touch the filesystem being analyzed.** It does not
 stat, open, or otherwise access any path that appears in the records; its
-only I/O is reading the database, writing stdout/stderr, and the
-temporary file SQLite sorts in when the duplicate rows do not fit in
-memory. SQLite puts that file in `$SQLITE_TMPDIR` or `$TMPDIR` when set,
-otherwise in `/var/tmp` (or `/tmp`), and deletes it as soon as it has
-opened it. `report` must produce identical output whether or not the
-scanned filesystem is still mounted.
+only I/O is reading the database and writing stdout/stderr. It must
+produce identical output whether or not the scanned filesystem is still
+mounted.
 
 Processing:
 
@@ -606,41 +545,22 @@ 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
-    emit ANSI redraws: print a plain one-line progress update the moment
-    each phase starts, then no more often than every 5 seconds.
+-   When stderr is not a TTY, do not emit ANSI redraws: print a plain
+    one-line progress update no more often than every 5 seconds instead.
 -   Progress updates are driven from the main goroutine and must be
-    non-blocking with respect to the worker pool. On a terminal the
-    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.
+    non-blocking with respect to the worker pool.
 -   `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
-    `scan` is already running against the same database, the database
-    cannot be created/opened/read/written, a missing database for
-    `report`/`trees`, stdout write failure).
+-   `1`: fatal error (e.g., a `PATH` operand does not exist, the
+    database cannot be created/opened/read/written, a missing database
+    for `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
@@ -778,7 +698,7 @@ 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"
@@ -806,9 +726,9 @@ All of the following, run in this directory, must pass:
     ./sfdupes report
     ```
 
-    (The database lives in a temp directory of its own: inside `$d`,
-    the scan would record it, and its empty lock file would join the
-    `empty1`/`empty2` group.)
+    (The scan database lives inside `$d` here purely for test hygiene;
+    scanning `$d` therefore also records the SQLite file itself, which
+    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

@@ -29,33 +29,9 @@
 
 # Completed Steps
 
-- the `Dockerfile` build stage keeps the Go module cache out of `builder`'s
-  home and copies the sources with `--chown`, so no `chown -R` walks them
-  (2026-10-04, https://git.eeqj.de/sneak/sfdupes/issues/43)
-
-- `report` and `trees` stream the records instead of holding them all in
-  memory; the schema gains the `files_signature` index (2026-10-04,
-  https://git.eeqj.de/sneak/sfdupes/issues/14)
-
-- 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)
-
-- warn about and skip symlink, socket, FIFO, device and `.zfs`
-  operands, keeping the records beneath them (2026-10-03,
-  https://git.eeqj.de/sneak/sfdupes/issues/9)
-
-- `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)
+- refuse an unversioned database that already has a `files` table with
+  a clear schema-version error (2026-10-03,
+  https://git.eeqj.de/sneak/sfdupes/issues/11)
 
 - escape tabs, newlines, carriage returns and backslashes in report,
   trees and warning paths; the root directory's path 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 = `
@@ -51,12 +45,6 @@ CREATE TABLE files (
 ) WITHOUT ROWID
 `
 
-// createIndexSQL indexes the records by signature, so report can have
-// SQLite group them without sorting the whole table.
-const createIndexSQL = `
-CREATE INDEX files_signature ON files (size, head, tail, content)
-`
-
 // upsertSQL inserts one file record, replacing any existing record for
 // the same path.
 const upsertSQL = `
@@ -76,10 +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 {
@@ -90,24 +74,16 @@ func databasePath() string {
 	return defaultDatabasePath
 }
 
-// scanParams are the connection parameters for scan: read-write, with
-// WAL journaling and a busy timeout, so a report can run while a cron
-// scan is in progress. closeScanDatabase leaves WAL mode again.
-const scanParams = "_pragma=busy_timeout(10000)" +
-	"&_pragma=journal_mode(WAL)" +
-	"&_pragma=synchronous(NORMAL)"
+// openDB opens the SQLite database at path with WAL journaling and a
+// busy timeout, so a report can run while a cron scan is in progress.
+// It does not create or verify the schema.
+func openDB(path string) (*sql.DB, error) {
+	dsn := "file:" + path +
+		"?_pragma=busy_timeout(10000)" +
+		"&_pragma=journal_mode(WAL)" +
+		"&_pragma=synchronous(NORMAL)"
 
-// reportParams are the connection parameters for report and trees:
-// 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)
+	db, err := sql.Open("sqlite", dsn)
 	if err != nil {
 		return nil, fmt.Errorf("open database %s: %w", path, err)
 	}
@@ -120,43 +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) {
@@ -165,7 +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
 	}
@@ -180,24 +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.
@@ -213,7 +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
 	}
@@ -255,14 +176,30 @@ func initSchema(ctx context.Context, db *sql.DB) error {
 }
 
 // createSchema applies the schema to a fresh database and stamps the
-// schema version.
+// schema version. A database with user_version 0 that already has a
+// files table was not created by this build — a foreign or partially
+// initialized file. Adopting it silently could corrupt unrelated data,
+// so that is a fatal schema-version error telling the operator to
+// remove the file and rescan.
 func createSchema(ctx context.Context, db *sql.DB) error {
-	_, err := db.ExecContext(ctx, createTableSQL)
-	if err != nil {
-		return fmt.Errorf("create schema: %w", err)
+	var name string
+
+	err := db.QueryRowContext(ctx,
+		"SELECT name FROM sqlite_master "+
+			"WHERE type = 'table' AND name = 'files'").Scan(&name)
+
+	switch {
+	case err == nil:
+		return fmt.Errorf(
+			"has a files table but no schema version; "+
+				"remove the file and rescan: %w", errSchemaVersion)
+	case errors.Is(err, sql.ErrNoRows):
+		// Genuinely empty: create the schema below.
+	default:
+		return fmt.Errorf("check for files table: %w", err)
 	}
 
-	_, err = db.ExecContext(ctx, createIndexSQL)
+	_, err = db.ExecContext(ctx, createTableSQL)
 	if err != nil {
 		return fmt.Errorf("create schema: %w", err)
 	}
@@ -288,18 +225,18 @@ func userVersion(ctx context.Context, db *sql.DB) (int, error) {
 	return v, nil
 }
 
-// loadFileRows streams every record to fn in path order: byte order,
-// which is the order of the primary key, so SQLite does not sort.
-func loadFileRows(ctx context.Context, db *sql.DB, fn func(r scanRec)) error {
+// loadFileRows reads every record from the files table.
+func loadFileRows(ctx context.Context, db *sql.DB) ([]scanRec, error) {
 	rows, err := db.QueryContext(ctx,
-		"SELECT path, size, mtime, head, tail, content FROM files "+
-			"ORDER BY path")
+		"SELECT path, size, mtime, head, tail, content FROM files")
 	if err != nil {
-		return fmt.Errorf("read records: %w", err)
+		return nil, fmt.Errorf("read records: %w", err)
 	}
 
 	defer func() { _ = rows.Close() }()
 
+	var recs []scanRec
+
 	for rows.Next() {
 		var (
 			path []byte
@@ -309,92 +246,19 @@ func loadFileRows(ctx context.Context, db *sql.DB, fn func(r scanRec)) error {
 		err = rows.Scan(&path, &r.size, &r.mtime, &r.head, &r.tail,
 			&r.content)
 		if err != nil {
-			return fmt.Errorf("read record: %w", err)
+			return nil, fmt.Errorf("read record: %w", err)
 		}
 
 		r.path = string(path)
-		fn(r)
+		recs = append(recs, r)
 	}
 
 	err = rows.Err()
 	if err != nil {
-		return fmt.Errorf("read records: %w", err)
+		return nil, fmt.Errorf("read records: %w", err)
 	}
 
-	return nil
-}
-
-// dupeRowsSQL selects every record in a duplicate group, with the
-// group's first path. A group is the records with a content hash that
-// share a size, head, tail, and content, when there are two or more of
-// them. The rows come in report order: groups by size descending, then
-// by first path, and each group's paths ascending.
-const dupeRowsSQL = `
-SELECT g.first, f.path, f.size
-FROM files AS f
-JOIN (
-    SELECT size, head, tail, content, MIN(path) AS first
-    FROM files
-    WHERE content <> ''
-    GROUP BY size, head, tail, content
-    HAVING COUNT(*) > 1
-) AS g USING (size, head, tail, content)
-ORDER BY f.size DESC, g.first, f.path
-`
-
-// loadDupeRows streams the rows of dupeRowsSQL to fn and returns the
-// number of records in the database. The count and the rows are read
-// in one transaction, so they agree while a scan is committing. An
-// error from fn stops the reading and is returned as it is.
-func loadDupeRows(ctx context.Context, db *sql.DB,
-	fn func(first, path string, size int64) error,
-) (int, error) {
-	// Everything goes through tx: the report connection is the only
-	// one, so a query on db would wait for tx forever.
-	tx, err := db.BeginTx(ctx, &sql.TxOptions{ReadOnly: true})
-	if err != nil {
-		return 0, fmt.Errorf("read records: %w", err)
-	}
-
-	defer func() { _ = tx.Rollback() }()
-
-	var records int
-
-	err = tx.QueryRowContext(ctx, "SELECT COUNT(*) FROM files").Scan(&records)
-	if err != nil {
-		return 0, fmt.Errorf("read records: %w", err)
-	}
-
-	rows, err := tx.QueryContext(ctx, dupeRowsSQL)
-	if err != nil {
-		return 0, fmt.Errorf("read records: %w", err)
-	}
-
-	defer func() { _ = rows.Close() }()
-
-	for rows.Next() {
-		var (
-			first, path []byte
-			size        int64
-		)
-
-		err = rows.Scan(&first, &path, &size)
-		if err != nil {
-			return 0, fmt.Errorf("read record: %w", err)
-		}
-
-		err = fn(string(first), string(path), size)
-		if err != nil {
-			return 0, err
-		}
-	}
-
-	err = rows.Err()
-	if err != nil {
-		return 0, fmt.Errorf("read records: %w", err)
-	}
-
-	return records, nil
+	return recs, nil
 }
 
 // loadFileMeta streams every record's path, size, mtime, and whether

db_test.go

@@ -5,9 +5,9 @@ import (
 	"database/sql"
 	"errors"
 	"fmt"
-	"os"
 	"path/filepath"
 	"slices"
+	"strings"
 	"testing"
 )
 
@@ -72,8 +72,41 @@ func TestOpenScanDatabaseCreates(t *testing.T) {
 
 	defer func() { _ = db.Close() }()
 
-	if recs := dbRecords(t, db); len(recs) != 0 {
-		t.Fatalf("records = %v, want none", recs)
+	recs, err := loadFileRows(t.Context(), db)
+	if err != nil || len(recs) != 0 {
+		t.Fatalf("loadFileRows = %v, %v; want empty, nil", recs, err)
+	}
+}
+
+func TestOpenScanDatabaseUnversionedForeign(t *testing.T) {
+	t.Parallel()
+
+	path := testDBPath(t)
+
+	// A database that has a files table but user_version 0 — a foreign
+	// or partially initialized file. scan must refuse it with a clear
+	// schema-version error, not adopt it and not emit a raw SQLite
+	// "table files already exists".
+	db, err := openDB(path)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	_, err = db.ExecContext(t.Context(), "CREATE TABLE files (x INTEGER)")
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	_ = db.Close()
+
+	_, err = openScanDatabase(t.Context(), path)
+	if !errors.Is(err, errSchemaVersion) {
+		t.Fatalf("err = %v, want errSchemaVersion", err)
+	}
+
+	if !strings.Contains(err.Error(), "remove the file and rescan") {
+		t.Fatalf("err = %v, want it to tell the operator to remove and rescan",
+			err)
 	}
 }
 
@@ -129,49 +162,6 @@ 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, func(scanRec) {})
-	if err != nil {
-		t.Fatalf("loadFileRows: %v", err)
-	}
-}
-
 func TestApplyChangesRoundTrip(t *testing.T) {
 	t.Parallel()
 
@@ -194,8 +184,15 @@ func TestApplyChangesRoundTrip(t *testing.T) {
 		t.Fatalf("applyChanges: %v", err)
 	}
 
-	// The records come back in path order, which is the order of recs.
-	got := dbRecords(t, db)
+	got, err := loadFileRows(t.Context(), db)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	slices.SortFunc(got, func(a, b scanRec) int {
+		return strings.Compare(a.path, b.path)
+	})
+
 	if !slices.Equal(got, recs) {
 		t.Fatalf("rows = %+v, want %+v", got, recs)
 	}
@@ -212,7 +209,11 @@ func TestApplyChangesRoundTrip(t *testing.T) {
 		t.Fatalf("applyChanges: %v", err)
 	}
 
-	got = dbRecords(t, db)
+	got, err = loadFileRows(t.Context(), db)
+	if err != nil {
+		t.Fatal(err)
+	}
+
 	if len(got) != 1 || got[0] != upd {
 		t.Fatalf("rows = %+v, want just %+v", got, upd)
 	}
@@ -241,8 +242,9 @@ func TestApplyChangesBatching(t *testing.T) {
 		t.Fatalf("applyChanges: %v", err)
 	}
 
-	if got := dbRecords(t, db); len(got) != n {
-		t.Fatalf("records = %d, want %d", len(got), n)
+	got, err := loadFileRows(t.Context(), db)
+	if err != nil || len(got) != n {
+		t.Fatalf("loadFileRows = %d rows, %v; want %d", len(got), err, n)
 	}
 
 	deletes := make([]string, 0, n)
@@ -256,7 +258,8 @@ func TestApplyChangesBatching(t *testing.T) {
 		t.Fatalf("applyChanges deletes: %v", err)
 	}
 
-	if got := dbRecords(t, db); len(got) != 0 {
-		t.Fatalf("records = %d, want 0", len(got))
+	got, err = loadFileRows(t.Context(), db)
+	if err != nil || len(got) != 0 {
+		t.Fatalf("loadFileRows = %d rows, %v; want 0", len(got), err)
 	}
 }

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 |
-	// 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))
+	os.Exit(run(os.Args[1:], 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
-// their data to stdout.
-func run(args []string, stdout, stderr io.Writer) int {
+// runs before the process ends.
+func run(args []string, 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

@@ -44,61 +44,23 @@ func assertNoSidecars(t *testing.T, path string) {
 	}
 }
 
-// makeReadOnly takes write permission away from the database at path,
-// from any WAL sidecar beside it, and from their directory, as for a
-// user reading a database that a root cron scan keeps. Root ignores
-// file permissions, so it skips the test when run as root.
-func makeReadOnly(t *testing.T, path string) {
+// captureStdout redirects os.Stdout to a file for the rest of the test
+// and returns a function reading back everything written to it. Only
+// machine-readable data belongs on stdout (README design goal 4), so
+// the tests assert on it directly.
+func captureStdout(t *testing.T) func() string {
 	t.Helper()
 
-	if os.Geteuid() == 0 {
-		t.Skip("root ignores file permissions")
-	}
-
-	err := os.Chmod(path, 0o400)
+	f, err := os.Create(filepath.Join(t.TempDir(), "stdout"))
 	if err != nil {
 		t.Fatal(err)
 	}
 
-	for _, suffix := range walSuffixes {
-		err = os.Chmod(path+suffix, 0o400)
-		if err != nil && !errors.Is(err, fs.ErrNotExist) {
-			t.Fatal(err)
-		}
-	}
-
-	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)
-	})
-}
-
-// captureStderr redirects os.Stderr to a file for the rest of the test
-// and returns a function reading back everything written to it. scan
-// writes its warnings and summary straight to os.Stderr, not to the
-// stderr writer run is given.
-func captureStderr(t *testing.T) func() string {
-	t.Helper()
-
-	f, err := os.Create(filepath.Join(t.TempDir(), "stderr"))
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	saved := os.Stderr
-	os.Stderr = f
+	saved := os.Stdout
+	os.Stdout = f
 
 	t.Cleanup(func() {
-		os.Stderr = saved
+		os.Stdout = saved
 
 		_ = f.Close()
 	})
@@ -129,13 +91,13 @@ func captureStderr(t *testing.T) func() string {
 // 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)
 	}
@@ -146,7 +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
 }
@@ -179,10 +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
-	// 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.
+	// it fails: no os.Exit between the open and the return.
 	cases := map[string][]string{
 		cmdScan:   {cmdScan},
 		cmdReport: {cmdReport},
@@ -198,15 +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.
@@ -224,16 +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
@@ -277,9 +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)
 			}
@@ -288,7 +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)
 			}
 		})
@@ -297,9 +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")
 }
@@ -310,9 +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)
 	}
@@ -321,7 +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)
 	}
 }
@@ -350,31 +320,21 @@ func scanFixture(t *testing.T) []string {
 		t.Fatal(err)
 	}
 
-	scanOK(t, dir)
+	var stderr bytes.Buffer
 
-	return dupes
-}
+	stdout := captureStdout(t)
 
-// scanOK runs scan over operands, fails the test unless it exits 0 with
-// nothing on stdout, and returns everything it printed to stderr.
-func scanOK(t *testing.T, operands ...string) string {
-	t.Helper()
-
-	var stdout bytes.Buffer
-
-	stderr := captureStderr(t)
-
-	code := run(append([]string{cmdScan}, operands...), &stdout, os.Stderr)
+	code := run([]string{cmdScan, dir}, &stderr)
 	if code != exitOK {
-		t.Fatalf("run(scan %q) = %d, want %d; stderr: %s",
-			operands, code, exitOK, stderr())
+		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)
 	}
 
-	return stderr()
+	return dupes
 }
 
 func TestRunScanSucceedsDespiteWarnings(t *testing.T) {
@@ -385,119 +345,24 @@ func TestRunScanSucceedsDespiteWarnings(t *testing.T) {
 	assertNoSidecars(t, path)
 }
 
-func TestRunScanSkipsSymlinkOperand(t *testing.T) {
-	path := testDBPath(t)
-	t.Setenv(databaseEnv, path)
-
-	dir := t.TempDir()
-	writeFile(t, dir, "target/sub/f", pattern(1, 10))
-
-	link := filepath.Join(dir, "link")
-
-	err := os.Symlink(filepath.Join(dir, "target"), link)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	// Scanning a directory through the symlink stores a record beneath
-	// the symlink's own path for a file beneath its target.
-	scanOK(t, filepath.Join(link, "sub"))
-
-	assertOperandSkipped(t, path, link, "symlink",
-		filepath.Join(link, "sub", "f"))
-}
-
-func TestRunScanWalksOperandUnderSymlinkOperand(t *testing.T) {
-	path := testDBPath(t)
-	t.Setenv(databaseEnv, path)
-
-	dir := t.TempDir()
-	writeFile(t, dir, "target/sub/f", pattern(1, 10))
-
-	link := filepath.Join(dir, "link")
-
-	err := os.Symlink(filepath.Join(dir, "target"), link)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	// link is dropped as a symlink, but link/sub must still be scanned,
-	// not dropped as lying under link.
-	scanOK(t, link, filepath.Join(link, "sub"))
-
-	db, err := openDB(path, reportParams)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	t.Cleanup(func() { _ = db.Close() })
-
-	recordByPath(t, dbRecords(t, db), filepath.Join(link, "sub", "f"))
-}
-
-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))
-
-	// An operand beneath a .zfs directory is walked, because it is not
-	// itself named .zfs.
-	scanOK(t, snapshot)
-
-	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.
-func assertOperandSkipped(t *testing.T, dbPath, operand, kind,
-	kept string,
-) {
-	t.Helper()
-
-	stderr := scanOK(t, operand)
-
-	warning := "walk " + operand + ": skipping " + kind + " operand\n"
-	if !strings.Contains(stderr, warning) {
-		t.Errorf("stderr = %q, want %q", stderr, warning)
-	}
-
-	summary := "scan: 0 files seen (0 added, 0 updated, 0 removed, " +
-		"0 unchanged), 1 skipped\n"
-	if !strings.Contains(stderr, summary) {
-		t.Errorf("stderr = %q, want %q", stderr, summary)
-	}
-
-	db, err := openDB(dbPath, reportParams)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	t.Cleanup(func() { _ = db.Close() })
-
-	recordByPath(t, dbRecords(t, db), kept)
-}
-
 func TestRunReportSucceeds(t *testing.T) {
 	path := testDBPath(t)
 	t.Setenv(databaseEnv, path)
 
 	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)
 	}
 
@@ -510,9 +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())
@@ -522,197 +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
-// plainInterval.
+// one-line update no more often than every plainInterval.
 //
-// All methods must be called from the main goroutine only. On a TTY
-// the library also redraws a spinner from its own goroutine, several
-// times a second, so its count and elapsed time stay current while a
-// pass waits for its next item. A nil *progress is a valid
-// 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.
+// All methods must be called from the main goroutine only. A nil
+// *progress is a valid 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() {
-		p.bar = newBar(label, total)
-
+	if !stderrIsTTY() {
 		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.
@@ -123,22 +113,11 @@ func (p *progress) warnf(format string, args ...any) {
 		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.Fprintln(os.Stderr, escapePath(fmt.Sprintf(format, args...)))
 }
 
 // finish terminates the pass's display.

progress_test.go

@@ -1,161 +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
-
-//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

@@ -4,8 +4,8 @@ import (
 	"bufio"
 	"context"
 	"fmt"
-	"io"
 	"os"
+	"slices"
 	"strings"
 )
 
@@ -28,59 +28,73 @@ type scanRec struct {
 	path    string
 }
 
-// runReport implements the report subcommand: it prints the file-level
-// duplicates report as TSV on stdout. SQLite groups and orders the
-// records, and each row is written as it is read, so no group is held
-// in memory. It never touches the scanned filesystem; its only I/O is
-// the database (with SQLite's temporary sort file), stdout, and stderr.
-// Any database problem, including a missing database, is fatal.
-func runReport(ctx context.Context, stdout io.Writer) error {
+// 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 — which checkpoints the SQLite
+// WAL — always runs; the database is closed before the caller formats
+// its output, so it stays closed even if that output fails.
+func loadRecords(ctx context.Context) ([]scanRec, error) {
 	dbPath := databasePath()
 
 	db, err := openReportDatabase(ctx, dbPath)
 	if err != nil {
-		return err
+		return nil, err
 	}
 
 	defer func() { _ = db.Close() }()
 
-	out := bufio.NewWriterSize(stdout, ioBufSize)
+	recs, err := loadFileRows(ctx, db)
+	if err != nil {
+		return nil, fmt.Errorf("database %s: %w", dbPath, err)
+	}
+
+	return recs, nil
+}
+
+// dupeGroup is one set of candidate-duplicate files: identical size,
+// head hash, tail hash, and content hash. paths is sorted
+// lexicographically; the first entry is the group's "first", the rest
+// are dupes.
+type dupeGroup struct {
+	size  int64
+	paths []string
+}
+
+// runReport implements the report subcommand: it reads every record
+// 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) error {
+	recs, err := loadRecords(ctx)
+	if err != nil {
+		return err
+	}
+
+	dupes := collectDupeGroups(recs)
+
+	out := bufio.NewWriterSize(os.Stdout, ioBufSize)
 
 	_, err = fmt.Fprintln(out, "first\tdupe\tsize")
 	if err != nil {
 		return fmt.Errorf("write stdout: %w", err)
 	}
 
-	var (
-		groups, dupeFiles int
-		reclaimable       int64
-		writeErr          error
-	)
+	dupeFiles := 0
 
-	records, err := loadDupeRows(ctx, db,
-		func(first, path string, size int64) error {
-			// A group's first path is its first row; every other
-			// path is a dupe.
-			if path == first {
-				groups++
+	var reclaimable int64
 
-				return nil
+	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)
+			if err != nil {
+				return fmt.Errorf("write stdout: %w", err)
 			}
 
-			_, writeErr = fmt.Fprintf(out, "%s\t%s\t%d\n",
-				escapePath(first), escapePath(path), size)
 			dupeFiles++
-			reclaimable += size
-
-			return writeErr
-		})
-
-	if writeErr != nil {
-		return fmt.Errorf("write stdout: %w", writeErr)
-	}
-
-	if err != nil {
-		return fmt.Errorf("database %s: %w", dbPath, err)
+			reclaimable += g.size
+		}
 	}
 
 	err = out.Flush()
@@ -91,11 +105,57 @@ func runReport(ctx context.Context, stdout io.Writer) error {
 	fmt.Fprintf(os.Stderr,
 		"report: %d records read, %d duplicate groups, %d dupe files, "+
 			"%s reclaimable\n",
-		records, groups, dupeFiles, humanBytes(reclaimable))
+		len(recs), len(dupes), dupeFiles, humanBytes(reclaimable))
 
 	return nil
 }
 
+// collectDupeGroups groups records by signature and returns every group
+// with two or more paths, each group's paths sorted lexicographically,
+// groups ordered by size descending then by first path ascending.
+func collectDupeGroups(recs []scanRec) []dupeGroup {
+	groups := make(map[fileSig][]string)
+
+	for _, r := range recs {
+		// A record without a content hash has unknown content and is
+		// never reported as a duplicate (README "Database").
+		if r.content == "" {
+			continue
+		}
+
+		k := fileSig{
+			size: r.size, head: r.head, tail: r.tail, content: r.content,
+		}
+		groups[k] = append(groups[k], r.path)
+	}
+
+	var dupes []dupeGroup
+
+	for k, paths := range groups {
+		if len(paths) < minGroupSize {
+			continue
+		}
+
+		slices.Sort(paths)
+		dupes = append(dupes, dupeGroup{size: k.size, paths: paths})
+	}
+
+	// Biggest reclaimable space first; ties broken by first path.
+	slices.SortFunc(dupes, func(a, b dupeGroup) int {
+		if a.size != b.size {
+			if a.size > b.size {
+				return -1
+			}
+
+			return 1
+		}
+
+		return strings.Compare(a.paths[0], b.paths[0])
+	})
+
+	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.

report_test.go

@@ -2,14 +2,10 @@ package main
 
 import (
 	"bytes"
-	"database/sql"
-	"errors"
-	"fmt"
 	"io"
 	"os"
 	"path/filepath"
 	"slices"
-	"strings"
 	"testing"
 )
 
@@ -51,59 +47,14 @@ func seedDatabase(t *testing.T, recs []scanRec) string {
 	return path
 }
 
-// dupeGroup is one duplicate group as report reads it: the size, and
-// the paths in report order, first path first.
-type dupeGroup struct {
-	size  int64
-	paths []string
-}
-
-// dupeGroups returns the duplicate groups report reads from db, in
-// report order.
-func dupeGroups(t *testing.T, db *sql.DB) []dupeGroup {
-	t.Helper()
-
-	var groups []dupeGroup
-
-	_, err := loadDupeRows(t.Context(), db,
-		func(first, path string, size int64) error {
-			if path == first {
-				groups = append(groups, dupeGroup{size: size})
-			}
-
-			g := &groups[len(groups)-1]
-			g.paths = append(g.paths, path)
-
-			return nil
-		})
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	return groups
-}
-
-// dupeGroupsOf writes recs into a fresh database and returns the
-// duplicate groups report reads from it.
-func dupeGroupsOf(t *testing.T, recs []scanRec) []dupeGroup {
-	t.Helper()
-
-	db := openTestDB(t)
-
-	err := applyChanges(t.Context(), db, recs, nil, nil)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	return dupeGroups(t, db)
-}
-
 func TestRunReportEscapesPaths(t *testing.T) {
 	t.Setenv(databaseEnv, seedDatabase(t, awkwardPairRecs()))
 
-	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())
@@ -111,87 +62,11 @@ func TestRunReportEscapesPaths(t *testing.T) {
 
 	want := "first\tdupe\tsize\n" +
 		`/d/\tone\ntwo\rthree\\four/f` + "\t/d/A/f\t5\n"
-	if got := stdout.String(); got != want {
+	if got := stdout(); got != want {
 		t.Errorf("stdout = %q, want %q", got, want)
 	}
 }
 
-func TestReportStdoutFailsWhileReading(t *testing.T) {
-	// Each row holds two paths longer than dir, so the report is more
-	// than twice the stdout buffer and stdout fails while rows are
-	// still being read, not at the final flush.
-	dir := "/" + strings.Repeat("d", 4096)
-
-	recs := make([]scanRec, ioBufSize/len(dir))
-	for i := range recs {
-		recs[i] = scanRec{
-			size: 1, head: "h", tail: "t", content: "c",
-			path: fmt.Sprintf("%s/%d", dir, i),
-		}
-	}
-
-	t.Setenv(databaseEnv, seedDatabase(t, recs))
-
-	err := runReport(t.Context(), failingWriter{})
-	if !errors.Is(err, errWriteFailed) ||
-		!strings.HasPrefix(err.Error(), "write stdout: ") {
-		t.Errorf("error = %v, want write stdout: %v", err, errWriteFailed)
-	}
-}
-
-func TestRunReportsIgnoreInsertionOrder(t *testing.T) {
-	// README §Constraints: identical database contents give identical
-	// output, whatever order the records were inserted in.
-	recs := append(smokeTreeRecs(), awkwardPairRecs()...)
-	recs = append(recs,
-		scanRec{size: 50, head: "b", tail: "b", content: "b", path: "/y/2"},
-		scanRec{size: 50, head: "b", tail: "b", content: "b", path: "/y/1"},
-		scanRec{size: 50, head: "a", tail: "a", content: "a", path: "/x/2"},
-		scanRec{size: 50, head: "a", tail: "a", content: "a", path: "/x/1"},
-		scanRec{size: 50, path: "/x/unhashed"},
-	)
-
-	reversed := slices.Clone(recs)
-	slices.Reverse(reversed)
-
-	for _, name := range []string{cmdReport, cmdTrees} {
-		t.Run(name, func(t *testing.T) {
-			t.Setenv(databaseEnv, seedDatabase(t, recs))
-
-			forward := runStdout(t, name)
-
-			t.Setenv(databaseEnv, seedDatabase(t, reversed))
-
-			backward := runStdout(t, name)
-
-			if strings.Count(forward, "\n") < 3 {
-				t.Errorf("stdout = %q, want at least two rows", forward)
-			}
-
-			if forward != backward {
-				t.Errorf("stdout depends on insertion order: %q vs %q",
-					forward, backward)
-			}
-		})
-	}
-}
-
-// runStdout runs the subcommand name and returns its stdout, failing
-// the test unless it succeeds.
-func runStdout(t *testing.T, name string) string {
-	t.Helper()
-
-	var stdout, stderr bytes.Buffer
-
-	code := run([]string{name}, &stdout, &stderr)
-	if code != exitOK {
-		t.Fatalf("run(%s) = %d, want %d; stderr: %s",
-			name, code, exitOK, stderr.String())
-	}
-
-	return stdout.String()
-}
-
 func TestEscapePath(t *testing.T) {
 	t.Parallel()
 
@@ -248,7 +123,7 @@ func TestWarnfEscapes(t *testing.T) {
 	}
 }
 
-func TestDupeGroups(t *testing.T) {
+func TestCollectDupeGroups(t *testing.T) {
 	t.Parallel()
 
 	recs := []scanRec{
@@ -263,7 +138,7 @@ func TestDupeGroups(t *testing.T) {
 		{size: 7, head: "u", tail: "u", content: "u", path: "/lonely"},
 	}
 
-	groups := dupeGroupsOf(t, recs)
+	groups := collectDupeGroups(recs)
 	if len(groups) != 2 {
 		t.Fatalf("len(groups) = %d, want 2", len(groups))
 	}
@@ -281,7 +156,7 @@ func TestDupeGroups(t *testing.T) {
 	}
 }
 
-func TestDupeGroupsContentSeparates(t *testing.T) {
+func TestCollectDupeGroupsContentSeparates(t *testing.T) {
 	t.Parallel()
 
 	// Same size, head, and tail, but different content hashes: the final
@@ -296,7 +171,7 @@ func TestDupeGroupsContentSeparates(t *testing.T) {
 		{size: 100, head: "h", tail: "t", path: "/e"},
 	}
 
-	groups := dupeGroupsOf(t, recs)
+	groups := collectDupeGroups(recs)
 	if len(groups) != 1 {
 		t.Fatalf("len(groups) = %d, want 1 (only the matching content)",
 			len(groups))
@@ -307,7 +182,7 @@ func TestDupeGroupsContentSeparates(t *testing.T) {
 	}
 }
 
-func TestDupeGroupsMtimeExcluded(t *testing.T) {
+func TestCollectDupeGroupsMtimeExcluded(t *testing.T) {
 	t.Parallel()
 
 	// mtime is informational only; records differing only in mtime
@@ -317,25 +192,23 @@ func TestDupeGroupsMtimeExcluded(t *testing.T) {
 		{size: 9, mtime: 200, head: "h", tail: "t", content: "c", path: "/m/2"},
 	}
 
-	groups := dupeGroupsOf(t, recs)
+	groups := collectDupeGroups(recs)
 	if len(groups) != 1 {
 		t.Fatalf("len(groups) = %d, want 1", len(groups))
 	}
 }
 
-func TestDupeGroupsTieBreak(t *testing.T) {
+func TestCollectDupeGroupsTieBreak(t *testing.T) {
 	t.Parallel()
 
-	// The hashes sort opposite to the first paths, so ordering the
-	// groups by hash instead of by first path fails this test.
 	recs := []scanRec{
-		{size: 50, head: "a", tail: "a", content: "a", path: "/beta/2"},
-		{size: 50, head: "a", tail: "a", content: "a", path: "/beta/1"},
-		{size: 50, head: "b", tail: "b", content: "b", path: "/alpha/2"},
-		{size: 50, head: "b", tail: "b", content: "b", path: "/alpha/1"},
+		{size: 50, head: "b", tail: "b", content: "b", path: "/beta/2"},
+		{size: 50, head: "b", tail: "b", content: "b", path: "/beta/1"},
+		{size: 50, head: "a", tail: "a", content: "a", path: "/alpha/2"},
+		{size: 50, head: "a", tail: "a", content: "a", path: "/alpha/1"},
 	}
 
-	groups := dupeGroupsOf(t, recs)
+	groups := collectDupeGroups(recs)
 	if len(groups) != 2 {
 		t.Fatalf("len(groups) = %d, want 2", len(groups))
 	}
@@ -347,7 +220,7 @@ func TestDupeGroupsTieBreak(t *testing.T) {
 	}
 }
 
-func TestDupeGroupsDeterministic(t *testing.T) {
+func TestCollectDupeGroupsDeterministic(t *testing.T) {
 	t.Parallel()
 
 	recs := []scanRec{
@@ -357,12 +230,12 @@ func TestDupeGroupsDeterministic(t *testing.T) {
 		{size: 2, head: "b", tail: "b", content: "b", path: "/q/2"},
 	}
 
-	forward := dupeGroupsOf(t, recs)
+	forward := collectDupeGroups(recs)
 
 	reversed := slices.Clone(recs)
 	slices.Reverse(reversed)
 
-	backward := dupeGroupsOf(t, reversed)
+	backward := collectDupeGroups(reversed)
 	if !slices.EqualFunc(forward, backward, func(a, b dupeGroup) bool {
 		return a.size == b.size && slices.Equal(a.paths, b.paths)
 	}) {

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
-// scan holds the lock on the database for its whole run, so a second
-// scan fails before it walks the filesystem or opens the database.
-// Errors are returned rather than exiting, so that the deferred close —
-// 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.
+// parsing and the at-least-one-operand check are done by cobra. Errors
+// are returned rather than exiting, so that the deferred close — which
+// checkpoints the SQLite WAL — always runs. 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 {
@@ -220,17 +210,13 @@ type scanState struct {
 // in the content hash of every record of headTailMin or more whose
 // size, head, and tail match another record's). Records outside the
 // roots are never touched, except that the content phase fills in
-// their content hash. Operands the walk cannot start from are dropped
-// first, so the records beneath them count as outside the roots unless
-// they lie under another root.
+// their content hash.
 func syncScan(ctx context.Context, db *sql.DB, roots []string,
 	workers int, oneFS bool,
 ) (scanStats, error) {
-	s := &scanState{db: db}
+	roots = pruneRoots(roots)
 
-	// Types are checked before pruning so that an operand under a
-	// dropped one is still scanned, not dropped as lying under it.
-	roots = pruneRoots(s.walkableRoots(roots))
+	s := &scanState{db: db}
 
 	err := s.loadIndex(ctx, roots)
 	if err != nil {
@@ -267,35 +253,6 @@ func syncScan(ctx context.Context, db *sql.DB, roots []string,
 	return s.st, s.contentPhase(ctx, workers)
 }
 
-// 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 count as outside the
-// roots and are not deleted as unverified, unless it lies under another
-// root. An operand that fails lstat here is kept, and the walk warns
-// about it.
-func (s *scanState) walkableRoots(roots []string) []string {
-	kept := make([]string, 0, len(roots))
-
-	for _, root := range roots {
-		fi, err := os.Lstat(root)
-		if err == nil {
-			warn := operandWarning(root, fi)
-			if warn != "" {
-				s.st.skipped++
-
-				fmt.Fprintln(os.Stderr, escapePath(warn))
-
-				continue
-			}
-		}
-
-		kept = append(kept, root)
-	}
-
-	return kept
-}
-
 // loadIndex indexes the database records under the scan roots for
 // change detection and collects the sizes of every record outside
 // them: out-of-scope records join the size census so a scanned file
@@ -832,43 +789,11 @@ 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.
-func operandWarning(root string, fi fs.FileInfo) string {
-	var kind string
-
-	switch mode := fi.Mode(); {
-	case mode.IsRegular():
-		return ""
-	case mode.IsDir():
-		if filepath.Base(root) != ".zfs" {
-			return ""
-		}
-
-		kind = ".zfs directory"
-	case mode&fs.ModeSymlink != 0:
-		kind = "symlink"
-	case mode&fs.ModeSocket != 0:
-		kind = "socket"
-	case mode&fs.ModeNamedPipe != 0:
-		kind = "FIFO"
-	case mode&fs.ModeDevice != 0:
-		kind = "device node"
-	default:
-		kind = "non-regular file"
-	}
-
-	return fmt.Sprintf("walk %s: skipping %s operand", root, kind)
-}
-
 // seedRoot turns one PATH operand into the walk's starting state: a
-// regular-file operand is statted and emitted directly, 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 are deleted as unverified.
+// regular-file operand is statted and emitted directly, a directory
+// operand becomes an initial job, and a symlink or other non-regular
+// operand yields nothing (symlinks are never followed, including as
+// operands).
 func seedRoot(ctx context.Context, root string,
 	events chan<- walkEvent,
 ) []dirJob {
@@ -882,30 +807,30 @@ func seedRoot(ctx context.Context, root string,
 		return nil
 	}
 
-	warn := operandWarning(root, fi)
-	if warn != "" {
-		sendEvent(ctx, events, walkEvent{warn: warn, fail: true})
+	switch {
+	case fi.IsDir():
+		if filepath.Base(root) == ".zfs" {
+			return nil
+		}
 
-		return nil
-	}
-
-	if fi.IsDir() {
 		dev, ok := deviceOfInfo(fi)
 
 		return []dirJob{{path: root, rootDev: dev, rootDevOK: ok}}
+	case fi.Mode().IsRegular():
+		dev, ino := inodeOfInfo(fi)
+
+		sendEvent(ctx, events, walkEvent{rec: fileRec{
+			path:  root,
+			size:  fi.Size(),
+			mtime: fi.ModTime().Unix(),
+			dev:   dev,
+			ino:   ino,
+		}})
+
+		return nil
+	default:
+		return nil
 	}
-
-	dev, ino := inodeOfInfo(fi)
-
-	sendEvent(ctx, events, walkEvent{rec: fileRec{
-		path:  root,
-		size:  fi.Size(),
-		mtime: fi.ModTime().Unix(),
-		dev:   dev,
-		ino:   ino,
-	}})
-
-	return nil
 }
 
 // startWalkWorkers starts the walk worker pool. Each worker processes

scan_test.go

@@ -7,7 +7,6 @@ import (
 	"database/sql"
 	"encoding/hex"
 	"fmt"
-	"io"
 	"os"
 	"path/filepath"
 	"runtime"
@@ -400,7 +399,7 @@ func TestScanContentGate(t *testing.T) {
 		}
 	}
 
-	groups := dupeGroups(t, db)
+	groups := collectDupeGroups(recs)
 	if len(groups) != 1 || !slices.Equal(groups[0].paths, same) {
 		t.Fatalf("groups = %+v, want only the identical pair %q",
 			groups, same)
@@ -435,7 +434,7 @@ func TestScanContentAcrossOperands(t *testing.T) {
 	want := []string{a, b}
 	slices.Sort(want)
 
-	groups := dupeGroups(t, db)
+	groups := collectDupeGroups(recs)
 	if len(groups) != 1 || !slices.Equal(groups[0].paths, want) {
 		t.Fatalf("groups = %+v, want the pair %q", groups, want)
 	}
@@ -462,7 +461,7 @@ func TestScanContentWithinOperand(t *testing.T) {
 
 	want := []string{stored, added}
 
-	groups := dupeGroups(t, db)
+	groups := collectDupeGroups(dbRecords(t, db))
 	if len(groups) != 1 || !slices.Equal(groups[0].paths, want) {
 		t.Fatalf("groups = %+v, want the pair %q", groups, want)
 	}
@@ -520,7 +519,7 @@ func TestScanContentStalePartners(t *testing.T) {
 		}
 	}
 
-	if groups := dupeGroups(t, db); len(groups) != 0 {
+	if groups := collectDupeGroups(recs); len(groups) != 0 {
 		t.Errorf("groups = %+v, want none", groups)
 	}
 }
@@ -571,7 +570,7 @@ func TestScanContentHashedStalePartners(t *testing.T) {
 
 	// The stored records lie outside the operand and are left as they
 	// are, so they still group with each other, but not with the copy.
-	groups := dupeGroups(t, db)
+	groups := collectDupeGroups(recs)
 	if len(groups) != 1 || !slices.Equal(groups[0].paths, stored) {
 		t.Errorf("groups = %+v, want only the stored pair %q", groups, stored)
 	}
@@ -620,7 +619,7 @@ func TestScanContentReadFailure(t *testing.T) {
 	want := []string{a, b}
 	slices.Sort(want)
 
-	groups := dupeGroups(t, db)
+	groups := collectDupeGroups(dbRecords(t, db))
 	if len(groups) != 1 || !slices.Equal(groups[0].paths, want) {
 		t.Fatalf("groups = %+v, want the pair %q after the retry",
 			groups, want)
@@ -857,11 +856,9 @@ func TestWalkFileAndSymlinkOperands(t *testing.T) {
 		t.Fatalf("file operand: recs = %+v, errs = %d", recs, errs)
 	}
 
-	// A symlink operand that reaches the walk (it became one after
-	// walkableRoots checked it) is not followed: it yields a warning and
-	// no records.
+	// A symlink operand is not followed and yields nothing.
 	recs, errs = collectWalk(t, []string{link}, false, 2)
-	if errs != 1 || len(recs) != 0 {
+	if errs != 0 || len(recs) != 0 {
 		t.Fatalf("symlink operand: recs = %+v, errs = %d", recs, errs)
 	}
 }
@@ -956,16 +953,11 @@ func syncTree(t *testing.T, db *sql.DB, roots ...string) scanStats {
 	return st
 }
 
-// dbRecords returns every record currently in the database, in path
-// order.
+// dbRecords returns every record currently in the database.
 func dbRecords(t *testing.T, db *sql.DB) []scanRec {
 	t.Helper()
 
-	var recs []scanRec
-
-	err := loadFileRows(t.Context(), db, func(r scanRec) {
-		recs = append(recs, r)
-	})
+	recs, err := loadFileRows(t.Context(), db)
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -1002,10 +994,10 @@ func recordPaths(recs []scanRec) []string {
 
 // assertSmokeDupeGroups checks the file-level duplicate groups for the
 // smoke tree rooted at dir.
-func assertSmokeDupeGroups(t *testing.T, dir string, db *sql.DB) {
+func assertSmokeDupeGroups(t *testing.T, dir string, parsed []scanRec) {
 	t.Helper()
 
-	groups := dupeGroups(t, db)
+	groups := collectDupeGroups(parsed)
 	if len(groups) != 5 {
 		t.Fatalf("len(groups) = %d, want 5", len(groups))
 	}
@@ -1030,10 +1022,11 @@ func assertSmokeDupeGroups(t *testing.T, dir string, db *sql.DB) {
 
 // assertSmokeTreeGroups checks the duplicate-tree groups for the smoke
 // tree rooted at dir.
-func assertSmokeTreeGroups(t *testing.T, dir string, db *sql.DB) {
+func assertSmokeTreeGroups(t *testing.T, dir string, parsed []scanRec) {
 	t.Helper()
 
-	super, dirs := dbTree(t, db)
+	super, dirs := buildHierarchy(parsed)
+	super.compute()
 
 	tg := collectTreeGroups(dirs, super)
 	if len(tg) != 1 {
@@ -1067,8 +1060,8 @@ func TestScanPipeline(t *testing.T) {
 		t.Fatalf("len(records) = %d, want %d", len(parsed), smokeTreeFiles)
 	}
 
-	assertSmokeDupeGroups(t, dir, db)
-	assertSmokeTreeGroups(t, dir, db)
+	assertSmokeDupeGroups(t, dir, parsed)
+	assertSmokeTreeGroups(t, dir, parsed)
 }
 
 func TestSyncScanUnchangedReuse(t *testing.T) {
@@ -1302,7 +1295,7 @@ func TestScanSkipsUniqueSizes(t *testing.T) {
 		}
 	}
 
-	if groups := dupeGroups(t, db); len(groups) != 0 {
+	if groups := collectDupeGroups(recs); len(groups) != 0 {
 		t.Fatalf("groups = %+v, want none from unhashed records", groups)
 	}
 
@@ -1317,7 +1310,7 @@ func TestScanSkipsUniqueSizes(t *testing.T) {
 			st)
 	}
 
-	groups := dupeGroups(t, db)
+	groups := collectDupeGroups(dbRecords(t, db))
 	if len(groups) != 1 {
 		t.Fatalf("groups = %+v, want the a/c pair", groups)
 	}
@@ -1353,7 +1346,8 @@ func TestTreesUnhashedNeverEqual(t *testing.T) {
 	}
 
 	for name, unknown := range cases {
-		super, dirs := treeOf(t, append(slices.Clone(shared), unknown...))
+		super, dirs := buildHierarchy(append(slices.Clone(shared), unknown...))
+		super.compute()
 
 		if tg := collectTreeGroups(dirs, super); len(tg) != 0 {
 			t.Errorf("%s: tree groups = %d, want 0 (the files may differ)",
@@ -1390,7 +1384,7 @@ func TestScanHardlinksReadOnce(t *testing.T) {
 		t.Fatalf("hardlink hashes differ: %+v vs %+v", ra, rb)
 	}
 
-	if groups := dupeGroups(t, db); len(groups) != 1 {
+	if groups := collectDupeGroups(recs); len(groups) != 1 {
 		t.Fatalf("groups = %+v, want the hardlink pair", groups)
 	}
 }
@@ -1554,7 +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())
@@ -1631,8 +1625,10 @@ func TestReportsNeverTouchFilesystem(t *testing.T) {
 		t.Fatal(err)
 	}
 
-	assertSmokeDupeGroups(t, dir, db)
-	assertSmokeTreeGroups(t, dir, db)
+	recs := dbRecords(t, db)
+
+	assertSmokeDupeGroups(t, dir, recs)
+	assertSmokeTreeGroups(t, dir, recs)
 }
 
 func TestUnderRoot(t *testing.T) {

trees.go

@@ -5,59 +5,49 @@ import (
 	"context"
 	"crypto/sha256"
 	"fmt"
-	"io"
 	"os"
 	"slices"
 	"strconv"
 	"strings"
 )
 
-// treeNode is one directory reconstructed from the record paths.
+// fileSig is a file's duplicate signature; mtime is excluded.
+type fileSig struct {
+	size    int64
+	head    string
+	tail    string
+	content string
+}
+
+// treeNode is one directory reconstructed from the scan stream.
 type treeNode struct {
-	path   string
-	parent *treeNode
-	// entries holds the serialized child entries until the digest is
-	// computed from them, and is then dropped.
-	entries   []string
+	path      string
+	parent    *treeNode
+	dirs      map[string]*treeNode
+	files     map[string]fileSig
 	digest    [sha256.Size]byte
 	fileCount int64
 	totalSize int64
 }
 
 // runTrees implements the trees subcommand: it reads every record from
-// the database in path order, reconstructs the directory hierarchy from
-// the record paths, computes a Merkle-style digest per directory, and
-// prints maximal duplicate-tree groups as TSV on stdout. It never
-// touches the scanned filesystem; its only I/O is the database, stdout,
-// and stderr. Any database problem, including a missing database, is
-// fatal.
-func runTrees(ctx context.Context, stdout io.Writer) error {
-	dbPath := databasePath()
-
-	db, err := openReportDatabase(ctx, dbPath)
+// the database, reconstructs the directory hierarchy from the record
+// paths, computes a Merkle-style digest per directory, and prints
+// 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) error {
+	recs, err := loadRecords(ctx)
 	if err != nil {
 		return err
 	}
 
-	defer func() { _ = db.Close() }()
-
-	records := 0
-	tree := newTreeBuilder()
-
-	err = loadFileRows(ctx, db, func(r scanRec) {
-		records++
-
-		tree.add(r)
-	})
-	if err != nil {
-		return fmt.Errorf("database %s: %w", dbPath, err)
-	}
-
-	super, allDirs := tree.finish()
+	super, allDirs := buildHierarchy(recs)
+	super.compute()
 
 	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 {
@@ -91,128 +81,73 @@ func runTrees(ctx context.Context, stdout io.Writer) error {
 	fmt.Fprintf(os.Stderr,
 		"trees: %d records read, %d duplicate tree groups, %d dupe trees, "+
 			"%s reclaimable\n",
-		records, len(dupes), dupeTrees, humanBytes(reclaimable))
+		len(recs), len(dupes), dupeTrees, humanBytes(reclaimable))
 
 	return nil
 }
 
-// treeBuilder reconstructs the directory hierarchy from records added
-// in path order, under a synthetic super-root. Paths are split on "/";
-// for absolute paths the first component is empty, which becomes the
-// top-level directory with path "/". In path order all the paths under
-// one directory come together, so a directory is complete once a path
-// outside it is added: its digest is computed then and its entries are
-// dropped. Only the directories holding the latest path keep entries.
-type treeBuilder struct {
-	super *treeNode
-	// open lists the directories holding the latest path, outermost
-	// first, starting with the super-root; names[i] is open[i]'s name.
-	open  []*treeNode
-	names []string
-	// dirs lists every completed directory.
-	dirs []*treeNode
-}
-
-func newTreeBuilder() *treeBuilder {
+// 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
+// top-level node with path "/". It returns the super-root and every
+// directory node created.
+func buildHierarchy(recs []scanRec) (*treeNode, []*treeNode) {
 	super := &treeNode{}
 
-	return &treeBuilder{
-		super: super,
-		open:  []*treeNode{super},
-		names: []string{""},
-	}
-}
+	var allDirs []*treeNode
 
-// add adds one record. Each record must come after the previous one in
-// path order (byte order); otherwise a completed directory would be
-// started again as a second directory with the same path.
-func (b *treeBuilder) add(r scanRec) {
-	comps := strings.Split(r.path, "/")
-	dirNames, name := comps[:len(comps)-1], comps[len(comps)-1]
+	for _, r := range recs {
+		comps := strings.Split(r.path, "/")
 
-	// Keep the open directories that hold this path; complete the rest.
-	depth := 1
-	for depth < len(b.open) && depth <= len(dirNames) &&
-		b.names[depth] == dirNames[depth-1] {
-		depth++
+		node := super
+		for _, c := range comps[:len(comps)-1] {
+			child := node.dirs[c]
+			if child == nil {
+				childPath := node.path + "/" + c
+
+				// The root directory's path is "/", not empty, and its
+				// 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}
+				if node.dirs == nil {
+					node.dirs = make(map[string]*treeNode)
+				}
+
+				node.dirs[c] = child
+				allDirs = append(allDirs, child)
+			}
+
+			node = child
+		}
+
+		if node.files == nil {
+			node.files = make(map[string]fileSig)
+		}
+
+		sig := fileSig{
+			size: r.size, head: r.head, tail: r.tail, content: r.content,
+		}
+
+		// A record without a content hash has unknown content (README
+		// "Database"): give it a signature no other file can share, so
+		// trees containing it never compare equal. Real hashes are
+		// hex, so the NUL-prefixed form cannot collide.
+		if sig.content == "" {
+			sig.content = "unhashed\x00" + r.path
+		}
+
+		node.files[comps[len(comps)-1]] = sig
 	}
 
-	b.closeTo(depth)
-
-	for _, c := range dirNames[depth-1:] {
-		b.openDir(c)
-	}
-
-	dir := b.open[len(b.open)-1]
-	dir.entries = append(dir.entries, fileEntry(name, r))
-	dir.fileCount++
-	dir.totalSize += r.size
-}
-
-// openDir starts the directory called name inside the innermost open
-// one.
-func (b *treeBuilder) openDir(name string) {
-	parent := b.open[len(b.open)-1]
-	path := parent.path + "/" + name
-
-	// The root directory's path is "/", not empty, and its children's
-	// paths start with one slash, not two.
-	switch {
-	case parent == b.super && name == "":
-		path = "/"
-	case parent == b.super:
-		path = name
-	case parent.path == "/":
-		path = "/" + name
-	}
-
-	b.open = append(b.open, &treeNode{path: path, parent: parent})
-	b.names = append(b.names, name)
-}
-
-// closeTo completes the open directories after the first n, innermost
-// first: each one's digest is computed and entered in its parent along
-// with its totals.
-func (b *treeBuilder) closeTo(n int) {
-	for len(b.open) > n {
-		last := len(b.open) - 1
-		dir, name := b.open[last], b.names[last]
-		b.open, b.names = b.open[:last], b.names[:last]
-
-		dir.computeDigest()
-
-		dir.parent.entries = append(dir.parent.entries,
-			"d\x00"+name+"\x00"+string(dir.digest[:]))
-		dir.parent.fileCount += dir.fileCount
-		dir.parent.totalSize += dir.totalSize
-		b.dirs = append(b.dirs, dir)
-	}
-}
-
-// finish completes every open directory and returns the super-root and
-// every directory.
-func (b *treeBuilder) finish() (*treeNode, []*treeNode) {
-	b.closeTo(1)
-
-	return b.super, b.dirs
-}
-
-// fileEntry serializes a file child for its directory's digest: its
-// name and its signature (size, head, tail, content); mtime is
-// excluded.
-func fileEntry(name string, r scanRec) string {
-	content := r.content
-
-	// A record without a content hash has unknown content (README
-	// "Database"): give it a signature no other file can share, so
-	// trees containing it never compare equal. Real hashes are hex, so
-	// the NUL-prefixed form cannot collide.
-	if content == "" {
-		content = "unhashed\x00" + r.path
-	}
-
-	return "f\x00" + name + "\x00" + strconv.FormatInt(r.size, 10) +
-		"\x00" + r.head + "\x00" + r.tail + "\x00" + content
+	return super, allDirs
 }
 
 // collectTreeGroups groups directories by digest and returns every
@@ -254,22 +189,38 @@ func collectTreeGroups(allDirs []*treeNode, super *treeNode) [][]*treeNode {
 	return dupes
 }
 
-// computeDigest sets n's digest and drops its entries. A directory's
-// digest is the SHA-256 of its child entries — files serialized with
-// name and signature, subdirectories with name and recursive digest —
-// sorted byte-lexicographically. Filenames cannot contain NUL or "/",
-// so NUL delimiters are unambiguous.
-func (n *treeNode) computeDigest() {
-	slices.Sort(n.entries)
+// compute fills in digest, fileCount, and totalSize for n and all of
+// its descendants. A directory's digest is the SHA-256 of its child
+// entries — files serialized with name and signature, subdirectories
+// with name and recursive digest — sorted byte-lexicographically.
+// Filenames cannot contain NUL or "/", so NUL delimiters are
+// unambiguous.
+func (n *treeNode) compute() {
+	entries := make([]string, 0, len(n.dirs)+len(n.files))
+	for name, sig := range n.files {
+		entries = append(entries,
+			"f\x00"+name+"\x00"+strconv.FormatInt(sig.size, 10)+
+				"\x00"+sig.head+"\x00"+sig.tail+"\x00"+sig.content)
+		n.fileCount++
+		n.totalSize += sig.size
+	}
+
+	for name, child := range n.dirs {
+		child.compute()
+		entries = append(entries, "d\x00"+name+"\x00"+string(child.digest[:]))
+		n.fileCount += child.fileCount
+		n.totalSize += child.totalSize
+	}
+
+	slices.Sort(entries)
 
 	h := sha256.New()
-	for _, e := range n.entries {
+	for _, e := range entries {
 		h.Write([]byte(e))
 		h.Write([]byte{0})
 	}
 
 	copy(n.digest[:], h.Sum(nil))
-	n.entries = nil
 }
 
 // suppressed reports whether a duplicate-tree group is non-maximal: its

trees_test.go

@@ -2,7 +2,6 @@ package main
 
 import (
 	"bytes"
-	"database/sql"
 	"slices"
 	"testing"
 )
@@ -31,36 +30,6 @@ func smokeTreeRecs() []scanRec {
 	}
 }
 
-// dbTree builds the directory hierarchy from the records in db the way
-// trees does, and returns the super-root and every directory.
-func dbTree(t *testing.T, db *sql.DB) (*treeNode, []*treeNode) {
-	t.Helper()
-
-	tree := newTreeBuilder()
-
-	err := loadFileRows(t.Context(), db, tree.add)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	return tree.finish()
-}
-
-// treeOf writes recs into a fresh database and builds the directory
-// hierarchy from it the way trees does.
-func treeOf(t *testing.T, recs []scanRec) (*treeNode, []*treeNode) {
-	t.Helper()
-
-	db := openTestDB(t)
-
-	err := applyChanges(t.Context(), db, recs, nil, nil)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	return dbTree(t, db)
-}
-
 // nodeByPath finds the directory node with the given path.
 func nodeByPath(t *testing.T, dirs []*treeNode, path string) *treeNode {
 	t.Helper()
@@ -91,10 +60,11 @@ func groupPaths(groups [][]*treeNode) [][]string {
 	return out
 }
 
-func TestTreeCounts(t *testing.T) {
+func TestBuildHierarchyCounts(t *testing.T) {
 	t.Parallel()
 
-	_, dirs := treeOf(t, smokeTreeRecs())
+	super, dirs := buildHierarchy(smokeTreeRecs())
+	super.compute()
 
 	d := nodeByPath(t, dirs, "/d")
 	if d.fileCount != 6 || d.totalSize != 9300 {
@@ -115,12 +85,12 @@ func TestTreeCounts(t *testing.T) {
 	}
 }
 
-func TestTreeRootPath(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 := treeOf(t, []scanRec{{path: "/f"}, {path: "/srv/g"}})
+	_, dirs := buildHierarchy([]scanRec{{path: "/f"}, {path: "/srv/g"}})
 
 	got := make([]string, 0, len(dirs))
 	for _, d := range dirs {
@@ -135,62 +105,14 @@ func TestTreeRootPath(t *testing.T) {
 	}
 }
 
-func TestTreeNamesSortingBeforeSlash(t *testing.T) {
-	t.Parallel()
-
-	// In path order "/a/b-x/f" and "/a/b.txt" come between the file
-	// "/a/b" and "/a/b/f", because "-" and "." sort before "/". Each
-	// directory must still be built once, whole, so /a matches /c.
-	recs := make([]scanRec, 0, 8)
-
-	for _, top := range []string{"/a", "/c"} {
-		for _, p := range []string{"/b", "/b-x/f", "/b.txt", "/b/f"} {
-			content := "c"
-			if p == "/b-x/f" {
-				content = "other"
-			}
-
-			recs = append(recs, scanRec{
-				size: 1, head: "h", tail: "t", content: content, path: top + p,
-			})
-		}
-	}
-
-	super, dirs := treeOf(t, recs)
-
-	got := make([]string, 0, len(dirs))
-	for _, d := range dirs {
-		got = append(got, d.path)
-	}
-
-	slices.Sort(got)
-
-	want := []string{"/", "/a", "/a/b", "/a/b-x", "/c", "/c/b", "/c/b-x"}
-	if !slices.Equal(got, want) {
-		t.Fatalf("directory paths = %q, want %q", got, want)
-	}
-
-	groups := collectTreeGroups(dirs, super)
-
-	gotGroups := groupPaths(groups)
-	wantGroups := [][]string{{"/a", "/c"}}
-
-	if !slices.EqualFunc(gotGroups, wantGroups, slices.Equal) {
-		t.Fatalf("groups = %v, want %v", gotGroups, wantGroups)
-	}
-
-	if groups[0][0].fileCount != 4 || groups[0][0].totalSize != 4 {
-		t.Errorf("group totals: %d files %d bytes, want 4 4",
-			groups[0][0].fileCount, groups[0][0].totalSize)
-	}
-}
-
 func TestRunTreesEscapesPaths(t *testing.T) {
 	t.Setenv(databaseEnv, seedDatabase(t, awkwardPairRecs()))
 
-	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())
@@ -198,7 +120,7 @@ func TestRunTreesEscapesPaths(t *testing.T) {
 
 	want := "first\tdupe\tfiles\tsize\n" +
 		`/d/\tone\ntwo\rthree\\four` + "\t/d/A\t1\t5\n"
-	if got := stdout.String(); got != want {
+	if got := stdout(); got != want {
 		t.Errorf("stdout = %q, want %q", got, want)
 	}
 }
@@ -206,7 +128,8 @@ func TestRunTreesEscapesPaths(t *testing.T) {
 func TestTreeDigests(t *testing.T) {
 	t.Parallel()
 
-	_, dirs := treeOf(t, smokeTreeRecs())
+	super, dirs := buildHierarchy(smokeTreeRecs())
+	super.compute()
 
 	t1 := nodeByPath(t, dirs, "/d/t1")
 	t2 := nodeByPath(t, dirs, "/d/t2")
@@ -239,7 +162,8 @@ func TestTreeDigestContentSensitivity(t *testing.T) {
 		{size: 10, head: "DIFF", tail: sharedTail, content: "c", path: "/r/b/f"},
 	}
 
-	_, dirs := treeOf(t, recs)
+	super, dirs := buildHierarchy(recs)
+	super.compute()
 
 	a := nodeByPath(t, dirs, "/r/a")
 	b := nodeByPath(t, dirs, "/r/b")
@@ -252,7 +176,8 @@ func TestTreeDigestContentSensitivity(t *testing.T) {
 func TestCollectTreeGroupsMaximal(t *testing.T) {
 	t.Parallel()
 
-	super, dirs := treeOf(t, smokeTreeRecs())
+	super, dirs := buildHierarchy(smokeTreeRecs())
+	super.compute()
 
 	groups := collectTreeGroups(dirs, super)
 
@@ -276,14 +201,16 @@ func TestCollectTreeGroupsDeterministic(t *testing.T) {
 
 	recs := smokeTreeRecs()
 
-	super, dirs := treeOf(t, recs)
+	super, dirs := buildHierarchy(recs)
+	super.compute()
 
 	forward := groupPaths(collectTreeGroups(dirs, super))
 
 	reversed := slices.Clone(recs)
 	slices.Reverse(reversed)
 
-	superR, dirsR := treeOf(t, reversed)
+	superR, dirsR := buildHierarchy(reversed)
+	superR.compute()
 
 	backward := groupPaths(collectTreeGroups(dirsR, superR))
 	if !slices.EqualFunc(forward, backward, slices.Equal) {
@@ -302,7 +229,8 @@ func TestCollectTreeGroupsSiblings(t *testing.T) {
 		{size: 10, head: "h", tail: "t", content: "c", path: "/p/x2/f"},
 	}
 
-	super, dirs := treeOf(t, recs)
+	super, dirs := buildHierarchy(recs)
+	super.compute()
 
 	got := groupPaths(collectTreeGroups(dirs, super))
 
@@ -324,7 +252,8 @@ func TestCollectTreeGroupsDifferingParents(t *testing.T) {
 		{size: 10, head: "h", tail: "t", content: "c", path: "/q/b/x/f"},
 	}
 
-	super, dirs := treeOf(t, recs)
+	super, dirs := buildHierarchy(recs)
+	super.compute()
 
 	got := groupPaths(collectTreeGroups(dirs, super))