Print progress at once off a terminal, keep warnings out of redraws (closes #13)

When stderr is not a terminal, each phase prints its zero-state line
as it starts instead of after its first item. stderrIsTTY uses
term.IsTerminal from golang.org/x/term, now a direct dependency, so
/dev/null is no longer taken for a terminal.

A spinner keeps the library's background redraw, so its count and
elapsed time stay current while a phase waits for its next item. A
warning printed during a spinner phase goes through the bar
(progressbar.Bprintln), which prints it before its next redraw instead
of racing it. Bars with a total have no background redraw and still
print warnings directly.

Model: opus-5-5

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

@@ -51,122 +51,6 @@ daily `sfdupes scan` cron job, with the reporting commands run
 interactively whenever needed; their results are as fresh as the last
 completed scan.
 
-### Install
-
-With Go installed, this builds and installs the current `main` branch:
-
-```sh
-go install sneak.berlin/go/sfdupes@main
-```
-
-The binary goes to `$(go env GOPATH)/bin`, or to `$GOBIN` when that is
-set. A binary installed this way reports its version as `dev`; one
-built from a clone or into the Docker image carries the git tag or
-commit it was built from.
-
-From a clone, `make build` writes the binary to `./sfdupes`:
-
-```sh
-git clone https://git.eeqj.de/sneak/sfdupes.git
-cd sfdupes
-make build
-```
-
-Copy the binary to `/usr/local/bin` for the cron job below.
-
-`make docker` builds the Docker image, tagged `sfdupes`, after running
-the tests and the linter (see "Build"). The image runs `sfdupes` as
-root with the database at its default path, so a bind mount of
-`/var/lib/sfdupes` keeps the database between runs. Mount the scanned
-tree at the same path inside the container as on the host; read-only
-is enough. The database records paths as the container sees them, so
-the reports then name the host's paths.
-
-```sh
-make docker
-docker run --rm -v /srv:/srv:ro -v /var/lib/sfdupes:/var/lib/sfdupes \
-    sfdupes scan /srv
-docker run --rm -v /var/lib/sfdupes:/var/lib/sfdupes sfdupes report > dupes.tsv
-```
-
-### Daily scan from cron
-
-Run `scan` as root, so that it can read every file: a path it cannot
-read is skipped with a warning and loses its database record (see
-"Rules for the walk"). As a file `/etc/cron.d/sfdupes`:
-
-```
-30 3 * * * root /usr/local/bin/sfdupes scan /srv 2>>/var/log/sfdupes.log || tail -n 3 /var/log/sfdupes.log
-```
-
--   The database is `/var/lib/sfdupes/db.sqlite`, created with its
-    directory by the first scan. To keep it elsewhere, set
-    `SFDUPES_DATABASE=/path/to/db.sqlite` before the command on the same
-    line.
--   `scan` writes nothing to stdout. Its stderr, appended here to
-    `/var/log/sfdupes.log`, holds a plain progress line as each phase
-    starts and then at most every 5 seconds, a warning for each path it
-    skips, and the summary line (see "Progress" and "`scan` mode"). The
-    log grows with every scan; rotate it like any other.
--   Skipped paths do not fail a scan: it still exits 0, and cron sends
-    nothing. A scan that fails, or is stopped by `SIGINT` or `SIGTERM`,
-    exits 1 with the reason among the last lines of the log; `tail`
-    prints them, and cron mails them to root if the host can send mail.
--   A scan still running when the next one starts carries on. The new
-    one fails at once, and the lines cron mails include
-    `sfdupes: another scan is running (lock held on /var/lib/sfdupes/db.sqlite.lock)`.
--   `report` and `trees` need only read access to the database (see
-    "Database"). Under the usual umask of `022` the first scan creates
-    it readable by every user, so an unprivileged user can run them
-    against root's database.
-
-### Reading the reports
-
-Each row of `report` names two copies of one file, and each row of
-`trees` two copies of one directory tree (see "Report output format"
-and "Trees output format"). In a group of copies, the path that sorts
-first byte by byte is `first` and every other path is a `dupe` of it.
-`first` says nothing about which copy is the original or the oldest;
-which copy to keep is your choice.
-
-A row is a candidate, not proof:
-
--   The reports read only the database, so they show the files as of
-    the last scan; a file may have changed or gone since.
--   A file of 50 MiB or more is compared only on samples of its content
-    (see "Duplicate detection").
--   Paths that are hard links to one file are listed as duplicates, but
-    they share their data, so removing one frees nothing.
-
-Compare a pair byte for byte before removing either copy. For the row
-`/srv/a/big.iso`, `/srv/b/big-copy.iso`, `4294967296`:
-
-```sh
-cmp /srv/a/big.iso /srv/b/big-copy.iso && echo identical
-[ /srv/a/big.iso -ef /srv/b/big-copy.iso ] && echo "hard links"
-```
-
-`cmp` prints nothing and exits 0 only when every byte matches, and
-otherwise reports where the files differ. The second line prints
-`hard links` when the two paths are the same file, so removing either
-frees nothing.
-
-A path holding a backslash, tab, newline or carriage return is escaped
-in the reports (see "Report output format"). Undo the escapes before
-using it. `printf '%b'` does exactly that, because every backslash in
-an escaped path starts one of the four escapes. Command substitution
-drops trailing newlines, so print an `x` after the path and remove it
-afterwards, or a path that ends in a newline names a different file:
-
-```sh
-p="$(printf '%bx' '/srv/a/tab\tname.txt')"; p="${p%x}"
-cmp "$p" /srv/b/tab-copy.txt
-```
-
-Check a `trees` row with `diff -r`, which compares the two trees file
-by file and also names anything present in only one of them, such as
-an empty directory or a symlink, which `trees` does not see.
-
 ## Rationale
 
 Duplicate finders that hash entire files do not scale to the target
@@ -210,15 +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
@@ -228,8 +104,8 @@ Goals, in order:
     again. `scan` is designed to be cronned; the reports run at any
     time against the last completed scan.
 4.  **Clean stream separation.** Everything on stdout is machine-readable
-    data. All progress, warnings, summaries, and help and usage text go
-    to stderr. Never mix them.
+    data. All progress, warnings, and summaries go to stderr. Never mix
+    them.
 
 ### Constraints
 
@@ -265,18 +141,8 @@ Three subcommands, all implemented:
 sfdupes scan [--workers N] [-x] PATH...
 sfdupes report > dupes.tsv
 sfdupes trees > dupetrees.tsv
-sfdupes --version
-sfdupes [command] --help
 ```
 
-`--workers N` sets the size of each `scan` worker pool (default: the
-number of CPUs), and `-x` (`--one-file-system`) keeps the walk of each
-operand on that operand's filesystem; both are described under
-"`scan` mode". `sfdupes --version` (or `-v`) prints one line,
-`sfdupes VERSION`, to stdout and exits 0, writing nothing to stderr.
-`-h` or `--help`, alone or after a subcommand, prints the help text to
-stderr and exits 0, writing nothing to stdout.
-
 ### Database
 
 All three subcommands operate on a single SQLite database file:
@@ -310,31 +176,22 @@ All three subcommands operate on a single SQLite database file:
     (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
-    every batch committed so far (an interrupted scan also commits the
-    batch in progress, see "Error handling and exit codes"); the next
-    scan skips those records and converges toward the filesystem.
+    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.
+    mode until the next scan.
 -   `report` and `trees` open the database read-only and need only read
     access to the database file, and no write access to its directory.
     While the database is in WAL mode they also read the `-wal` and
     `-shm` files beside it, which SQLite creates with the database
     file's permissions.
 -   Schema (`PRAGMA user_version` is the schema version, currently 1; a
-    database with any other version is a fatal error. `scan` creates
-    the schema and sets the version in one transaction, so a first scan
-    stopped while doing so leaves an empty database the next scan sets
-    up. A database at version 0 that already has a `files` table was
-    therefore not made by sfdupes; every subcommand refuses it with an
-    error telling the user to remove the file and rescan):
+    database with any other version is a fatal error):
 
     ```sql
     CREATE TABLE files (
@@ -345,7 +202,6 @@ 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
@@ -360,8 +216,7 @@ 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
 
@@ -566,9 +421,7 @@ Rules for the walk:
 Concurrency: the walk phase (which also stats files), the hash phase,
 and the content phase each use a worker pool of `--workers` workers
 (default `runtime.NumCPU()`); the walk parallelizes across
-directories, hashing across files. `--workers` must be at least 1: a
-smaller value is a usage error, reported in one line on stderr with
-exit 2 before anything is scanned. All three phases are seek-bound on
+directories, hashing across files. All three phases are seek-bound on
 spinning disks, so raising `--workers` well past the core count can
 help on pools with many spindles. The main goroutine owns
 partitioning, database writes, and progress rendering; progress
@@ -591,12 +444,9 @@ 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:
 
@@ -750,8 +600,6 @@ Additional requirements:
     waits for its next item.
 -   A warning printed during a phase always lands on a line of its own,
     never inside the progress display.
--   A bar whose phase stops short of its total, as an interrupted one
-    does, is left as last drawn rather than filled up.
 -   `report` and `trees` modes need no progress display, only their
     stderr summaries.
 
@@ -761,11 +609,9 @@ Additional requirements:
 -   `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), or a `scan` stopped by
-    `SIGINT` or `SIGTERM` (see below).
--   `2`: usage error (including `scan` with no `PATH` operand, `scan`
-    with `--workers` below 1, and `report`/`trees` with any positional
-    argument).
+    `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:
@@ -779,24 +625,6 @@ stderr and exits 1. Two cases never reach sfdupes as a failed write:
     the output is discarded and the run succeeds, as with
     `> /dev/null`.
 
-`scan` stops cleanly on `SIGINT` (Ctrl-C) or `SIGTERM`. Its workers
-stop taking work, each finishing at most the directory listing or file
-it is reading; the progress display is finished; and the records it has
-hashed but not yet committed are committed, so the next scan does not
-hash them again. Apart from that commit it starts no further writes or
-deletions: records are deleted only after a complete walk, so those
-under paths an interrupted walk never reached are kept. The database is
-closed and the lock released as on any other exit, the line
-`scan: interrupted after N files` goes to stderr, N being the number of
-files the walk reached, and the exit code is 1. The next scan skips the
-records already written and converges as usual.
-
-After the first signal `scan` stops catching them, so a second one ends
-it at once, as an uncaught signal does: the records not yet committed
-are lost, and the database is left valid, as when any scan dies (see
-"Database"). A `SIGINT` that `scan` inherits as ignored, as a script's
-background job does, stays ignored.
-
 ## Entrypoints
 
 This repository adheres to the

TODO.md

@@ -29,46 +29,6 @@
 
 # Completed Steps
 
-- `scan` rejects `--workers` below 1 as a usage error instead of
-  running single-threaded (2026-10-04,
-  https://git.eeqj.de/sneak/sfdupes/issues/10)
-
-- a test fails when either walk cancellation check in `scan.go` is
-  removed (2026-10-04, https://git.eeqj.de/sneak/sfdupes/issues/81)
-
-- test that `scan` refuses a database with another schema version
-  (2026-10-04, https://git.eeqj.de/sneak/sfdupes/issues/64)
-
-- correct four inaccurate comments in `cancel_test.go` and rename
-  `walkCancelInFlightDirs` to `walkCancelInFlightFiles` (2026-10-04,
-  https://git.eeqj.de/sneak/sfdupes/issues/33)
-
-- test the `-x` filesystem-boundary rules in `subdirJob` (2026-10-04,
-  https://git.eeqj.de/sneak/sfdupes/issues/17)
-
-- `scan` creates the schema in one transaction; a version-0 database with a
-  `files` table is refused with a clear schema-version error (2026-10-04,
-  https://git.eeqj.de/sneak/sfdupes/issues/11)
-
-- README documents install, Docker, a daily cron scan and how to read
-  and check the reports (2026-10-04,
-  https://git.eeqj.de/sneak/sfdupes/issues/54)
-
-- 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)
-
-- `--version` prints `sfdupes VERSION` to stdout; README documents it and
-  `--help` (2026-10-04, https://git.eeqj.de/sneak/sfdupes/issues/15)
-
-- `scan` stops cleanly on `SIGINT` or `SIGTERM`: commits what it has
-  hashed, deletes nothing more, exits 1 (2026-10-04,
-  https://git.eeqj.de/sneak/sfdupes/issues/5)
-
-- `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)

cancel_test.go

@@ -4,35 +4,20 @@ import (
 	"context"
 	"database/sql"
 	"errors"
-	"fmt"
 	"os"
-	"os/signal"
 	"path/filepath"
-	"slices"
 	"strconv"
-	"strings"
 	"sync"
 	"sync/atomic"
-	"syscall"
 	"testing"
 	"time"
 )
 
-// This file gathers the tests for scan cancellation and worker-pool
-// unwinding. Everything it exercises lives in scan.go, so by the repo's
-// convention of one test file per source file it would belong in
-// scan_test.go. It is kept separate on purpose: cancellation behaviour
-// cuts across both the walk pool and the hash pool as a single concern,
-// and scan_test.go is already over 1,600 lines. That is the deliberate
-// exception the convention otherwise expects to be stated.
-
-// poolUnwind bounds how long a test waits for a cancellation to take
-// effect: for a goroutine to return or a channel to close once its
-// context is cancelled, or for a signal to cancel the scan's context.
-// Only a failing run waits this long, and the bound is what makes that
-// failure an assertion instead of a hang. A call made without it, as
-// most of this file's scans are, has no bound: a regression that parks
-// it is caught only as the test binary's own timeout.
+// poolUnwind bounds how long a goroutine is given to leave a pool
+// after its context is cancelled. Only a failing run ever waits this
+// long: a pool that ignored its cancellation parks forever, and this
+// is what turns that into a failed assertion instead of a suite that
+// hangs until the test binary's own timeout.
 const poolUnwind = 2 * time.Second
 
 // walkClock is a context whose cancellation is driven by the scan's
@@ -43,14 +28,9 @@ const poolUnwind = 2 * time.Second
 //
 // The accounting behind the n chosen by each test: every blocking
 // channel operation in the walk selects on Done, so the walk spends
-// one consultation per file event plus a couple per directory. The
-// index load that runs ahead of it also consults Done, but a bounded
-// number of times that does not grow with the record count. The tests
-// depend on that property, not on the bound's exact value: each test
-// sets n from the consultations of the walk, plus those of the hash
-// phase when it cancels mid-hash, far from both ends of the phase it
-// interrupts, so the cancellation lands inside that phase whatever the
-// record count.
+// one consultation per file event plus a couple per directory, while
+// the index load that runs ahead of it spends a small fixed number
+// (three) whatever the record count.
 type walkClock struct {
 	n    int64
 	seen atomic.Int64
@@ -106,14 +86,11 @@ func (c *walkClock) Value(_ any) any {
 // directory still queued and only the handful already in flight can
 // emit anything more.
 const (
-	walkCancelDirs        = 100
-	walkCancelFilesPerDir = 20
-	walkCancelFiles       = walkCancelDirs * walkCancelFilesPerDir
-	walkCancelWorkers     = 4
-	// The most files the walkCancelWorkers directories already in
-	// flight when the scan is cancelled can still emit, at
-	// walkCancelFilesPerDir each. A file count, not a directory count.
-	walkCancelInFlightFiles = walkCancelWorkers * walkCancelFilesPerDir
+	walkCancelDirs         = 100
+	walkCancelFilesPerDir  = 20
+	walkCancelFiles        = walkCancelDirs * walkCancelFilesPerDir
+	walkCancelWorkers      = 4
+	walkCancelInFlightDirs = walkCancelWorkers * walkCancelFilesPerDir
 )
 
 // walkCancelAtDone is the consultation on which the fixture's context
@@ -173,13 +150,9 @@ func assertRecordsIntact(t *testing.T, db *sql.DB, before []string) {
 // Every one of those records would look vanished to the update phase.
 // The guard is what stops the scan there, and this test is what
 // notices if it stops doing so: deleting the guard, or making it
-// unreachable, makes the scan carry its truncated view into the update
-// phase, which counts every record the walk never reached for removal.
-//
-// The syncScan call here is not bounded by poolUnwind: a regression
-// that left a worker pool parked would hang it, and that regression is
-// caught only by the test binary's own timeout, not by a quick
-// assertion.
+// unreachable, makes the scan carry its truncated view into a later
+// phase and fail there instead, with a wrapped error rather than the
+// bare cancellation.
 //
 //nolint:paralleltest // counts goroutines: must not run beside others
 func TestSyncScanCancelledMidWalkKeepsRecords(t *testing.T) {
@@ -209,10 +182,10 @@ func TestSyncScanCancelledMidWalkKeepsRecords(t *testing.T) {
 
 // assertWalkGuardAborted checks that the scan stopped at the post-walk
 // guard: with a census that is neither empty (the walk really ran)
-// nor complete (it really was cut short), and with no record counted
-// for removal. A removal count means the partial census was carried
-// past the guard into the update phase, which is the failure this test
-// exists to catch.
+// nor complete (it really was cut short), and with the guard's own
+// bare cancellation as the error. A wrapped error means the partial
+// census was carried past the guard into the hash or update phase,
+// which is the failure this test exists to catch.
 func assertWalkGuardAborted(t *testing.T, st scanStats, err error) {
 	t.Helper()
 
@@ -221,6 +194,12 @@ func assertWalkGuardAborted(t *testing.T, st scanStats, err error) {
 			err, context.Canceled)
 	}
 
+	if errors.Unwrap(err) != nil {
+		t.Errorf("syncScan reported %q, want the guard's bare "+
+			"cancellation: a wrapped error means the truncated census "+
+			"reached a later phase", err)
+	}
+
 	if st.unchanged == 0 {
 		t.Fatalf("stats = %+v: the census is empty, so the walk never "+
 			"ran and the guard was reached for the wrong reason", st)
@@ -232,11 +211,10 @@ func assertWalkGuardAborted(t *testing.T, st scanStats, err error) {
 	}
 
 	// The workers drop every directory still queued once the scan is
-	// cancelled, so only the files in the directories already in flight
-	// can add to the census after the fact. A census beyond that bound
-	// would mean the cancellation was not observed where it should have
-	// been.
-	limit := walkCancelAtDone + walkCancelInFlightFiles
+	// cancelled, so only the directories already in flight can add to
+	// the census after the fact. A census beyond that bound would mean
+	// the cancellation was not observed where it should have been.
+	limit := walkCancelAtDone + walkCancelInFlightDirs
 	if st.unchanged > limit {
 		t.Errorf("census covers %d files, want at most %d: the walk kept "+
 			"taking directories off the queue after cancellation",
@@ -282,242 +260,6 @@ func TestSyncScanCancelledBeforeLoadIndex(t *testing.T) {
 	assertRecordsIntact(t, db, before)
 }
 
-// hashCancelAtDone is the consultation on which the mid-hash test's
-// context cancels itself. The walk of buildWalkCancelTree spends about
-// one per file and three per directory, and the hash phase then one per
-// file hashed, so this lands about half way through the hash phase.
-const hashCancelAtDone = walkCancelFiles + 3*walkCancelDirs +
-	walkCancelFiles/2
-
-// TestSyncScanCancelledMidHashKeepsHashedRecords cancels a first scan
-// part-way through its hash phase. The fixture holds fewer files than a
-// batch, so every file hashed is still waiting to be committed: the scan
-// must commit them all before it returns, and the next scan must hash
-// only the rest.
-func TestSyncScanCancelledMidHashKeepsHashedRecords(t *testing.T) {
-	t.Parallel()
-
-	dir := buildWalkCancelTree(t)
-	db := openTestDB(t)
-
-	st, err := syncScan(newWalkClock(hashCancelAtDone), db,
-		[]string{dir}, walkCancelWorkers, false)
-	if !errors.Is(err, context.Canceled) {
-		t.Fatalf("syncScan cancelled mid-hash = %v, want %v",
-			err, context.Canceled)
-	}
-
-	if st.walked != walkCancelFiles || st.added == 0 ||
-		st.added >= walkCancelFiles {
-		t.Fatalf("stats = %+v: want the walk complete and the hash phase "+
-			"cut short", st)
-	}
-
-	if got := len(dbRecords(t, db)); got != st.added {
-		t.Errorf("%d records after the cancelled scan, want the %d it hashed",
-			got, st.added)
-	}
-
-	hashed := st.added
-
-	st = syncTree(t, db, dir)
-	if st.added != walkCancelFiles-hashed || st.unchanged != hashed {
-		t.Errorf("next scan stats = %+v, want %d added %d unchanged",
-			st, walkCancelFiles-hashed, hashed)
-	}
-}
-
-// storedPaths opens the database at path as report does, which fails
-// unless it is a valid database, and returns its records' paths.
-func storedPaths(t *testing.T, path string) []string {
-	t.Helper()
-
-	db, err := openReportDatabase(t.Context(), path)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	defer func() { _ = db.Close() }()
-
-	return recordPaths(dbRecords(t, db))
-}
-
-// TestRunScanInterrupted calls the scan entrypoint with a context that
-// is already cancelled, as when a signal arrives at once. It must return
-// errInterrupted promptly with its one line on stderr, leave the
-// database valid and as it was, and leave nothing in the way of the
-// next scan, which must bring the database up to date.
-func TestRunScanInterrupted(t *testing.T) {
-	path := testDBPath(t)
-	t.Setenv(databaseEnv, path)
-
-	stderr := captureStderr(t)
-	dir := buildSmokeTree(t)
-
-	err := runScan(t.Context(), []string{dir}, walkCancelWorkers, false)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	before := storedPaths(t, path)
-
-	// A vanished file and a new one: the interrupted scan records
-	// neither.
-	gone := filepath.Join(dir, "a", "unique.bin")
-
-	err = os.Remove(gone)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	added := writeFile(t, dir, "a/new.bin", pattern(50, 10))
-	shown := len(stderr())
-	done := make(chan struct{})
-
-	go func() {
-		defer close(done)
-
-		err = runScan(cancelledContext(t), []string{dir}, walkCancelWorkers,
-			false)
-	}()
-
-	awaitReturn(t, done, "runScan")
-
-	if !errors.Is(err, errInterrupted) {
-		t.Fatalf("runScan on a cancelled context = %v, want %v",
-			err, errInterrupted)
-	}
-
-	want := "scan: interrupted after 0 files\n"
-	if got := stderr()[shown:]; got != want {
-		t.Errorf("stderr = %q, want %q", got, want)
-	}
-
-	assertNoSidecars(t, path)
-
-	if got := storedPaths(t, path); !slices.Equal(got, before) {
-		t.Errorf("records = %q after the interrupted scan, want %q",
-			got, before)
-	}
-
-	err = runScan(t.Context(), []string{dir}, walkCancelWorkers, false)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	got := storedPaths(t, path)
-	if slices.Contains(got, gone) || !slices.Contains(got, added) {
-		t.Errorf("records = %q after the next scan, want %q gone and %q "+
-			"added", got, gone, added)
-	}
-}
-
-// TestRunScanInterruptedMidHash interrupts the scan entrypoint part-way
-// through its hash phase, after the database is open. It must return
-// errInterrupted, release the lock, end stderr with its line counting
-// every file the walk reached, close the database out of WAL mode, and
-// keep the records it hashed.
-func TestRunScanInterruptedMidHash(t *testing.T) {
-	path := testDBPath(t)
-	t.Setenv(databaseEnv, path)
-
-	stderr := captureStderr(t)
-	dir := buildWalkCancelTree(t)
-
-	err := runScan(newWalkClock(hashCancelAtDone), []string{dir},
-		walkCancelWorkers, false)
-	if !errors.Is(err, errInterrupted) {
-		t.Fatalf("runScan interrupted mid-hash = %v, want %v",
-			err, errInterrupted)
-	}
-
-	holdScanLock(t, path)
-
-	want := fmt.Sprintf("scan: interrupted after %d files\n", walkCancelFiles)
-	if got := stderr(); !strings.HasSuffix(got, want) {
-		t.Errorf("stderr = %q, want it to end with %q", got, want)
-	}
-
-	assertNoSidecars(t, path)
-
-	db, err := openReportDatabase(t.Context(), path)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	defer func() { _ = db.Close() }()
-
-	// A plain close also removes the sidecars, but leaves WAL mode on.
-	var mode string
-
-	err = db.QueryRowContext(t.Context(), "PRAGMA journal_mode").Scan(&mode)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	if mode != "delete" {
-		t.Errorf("journal mode = %q after the interrupted scan, want %q",
-			mode, "delete")
-	}
-
-	kept := len(dbRecords(t, db))
-	if kept == 0 || kept >= walkCancelFiles {
-		t.Errorf("%d records after the interrupted scan, want those it "+
-			"hashed: some but not all of the %d files", kept, walkCancelFiles)
-	}
-}
-
-// TestInterruptContextCatchesSIGTERM sends SIGTERM to the test process
-// while the scan's handler is installed, and checks that it cancels the
-// scan's context.
-//
-//nolint:paralleltest // signals the whole process: must not run beside a scan
-func TestInterruptContextCatchesSIGTERM(t *testing.T) {
-	// Caught here as well, so that a handler that misses SIGTERM fails
-	// this test instead of ending the test process.
-	caught := make(chan os.Signal, 1)
-	signal.Notify(caught, syscall.SIGTERM)
-
-	defer signal.Stop(caught)
-
-	ctx, stop := interruptContext(t.Context())
-	defer stop()
-
-	err := syscall.Kill(os.Getpid(), syscall.SIGTERM)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	select {
-	case <-ctx.Done():
-	case <-time.After(poolUnwind):
-		t.Fatal("SIGTERM did not cancel the scan's context")
-	}
-}
-
-// TestCommitFullBatchKeepsFailedBatch checks that a full batch whose
-// commit fails, as it does once the scan is interrupted, stays in the
-// batch, so that syncScan's final commit saves it.
-func TestCommitFullBatchKeepsFailedBatch(t *testing.T) {
-	t.Parallel()
-
-	s := &scanState{db: openTestDB(t)}
-	for i := range updateBatchSize {
-		s.batch = append(s.batch, scanRec{path: "/f" + strconv.Itoa(i)})
-	}
-
-	err := s.commitFullBatch(cancelledContext(t))
-	if !errors.Is(err, context.Canceled) {
-		t.Fatalf("commitFullBatch on a cancelled context = %v, want %v",
-			err, context.Canceled)
-	}
-
-	if len(s.batch) != updateBatchSize {
-		t.Errorf("batch holds %d records after the failed commit, want %d",
-			len(s.batch), updateBatchSize)
-	}
-}
-
 // drainClosed counts the values received from ch until it closes,
 // failing the test if it does not close within poolUnwind. A pool that
 // ignored its cancellation leaves its channel open with its goroutines
@@ -586,49 +328,20 @@ func TestSendEventAbandonsBlockedSend(t *testing.T) {
 	awaitReturn(t, done, "sendEvent")
 }
 
-// TestWalkOneDirStopsWhenCancelled checks that a cancelled scan stops
-// reading a directory instead of going through the rest of its
-// entries. A walk that kept going would return the subdirectory below
-// to descend into. Unlike a file event, that return is not a send the
-// cancellation can abandon, so the test catches the regression every
-// time.
-func TestWalkOneDirStopsWhenCancelled(t *testing.T) {
-	t.Parallel()
-
-	dir := t.TempDir()
-
-	err := os.Mkdir(filepath.Join(dir, "sub"), 0o750)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	// Unbuffered and unread: on a cancelled scan every send gives up.
-	events := make(chan walkEvent)
-
-	subs := walkOneDir(cancelledContext(t), dirJob{path: dir}, false, events)
-	if len(subs) != 0 {
-		t.Errorf("cancelled walkOneDir returned %+v to descend into, "+
-			"want none", subs)
-	}
-}
-
 // TestWalkWorkersDropQueuedDirs checks that cancelled walk workers keep
 // reading jobs and drop the directories rather than stopping their
 // read: the range over jobs has to run out for the pool to tear down
-// and close its event stream. The queued directory does not exist, so
-// a worker that walked it anyway would send a warning before
-// walkOneDir's own cancellation check could stop it. On a cancelled
-// scan that send delivers or gives up at random, so with 64 jobs
-// queued the regression has a one in 2^64 chance of passing.
+// and close its event stream.
 func TestWalkWorkersDropQueuedDirs(t *testing.T) {
 	t.Parallel()
 
-	missing := filepath.Join(t.TempDir(), "missing")
+	dir := t.TempDir()
+	writeEmptyFiles(t, dir, walkCancelFilesPerDir)
 
 	jobs, _, events := startWalkWorkers(cancelledContext(t), 2, false)
 
-	for range 64 {
-		jobs <- dirJob{path: missing}
+	for range 4 {
+		jobs <- dirJob{path: dir}
 	}
 
 	close(jobs)
@@ -699,11 +412,7 @@ func TestDispatchDirsClosesJobsWhenCancelled(t *testing.T) {
 
 // TestFeedHashJobsClosesJobsWhenCancelled checks that the hash feeder
 // abandons the runs it has not queued yet and still closes the job
-// channel, which is what lets the workers' range terminate. The
-// receive on jobs below is not bounded: a feeder that returned without
-// closing jobs would leave that receive with no sender and no close, so
-// this regression is caught by the test binary's timeout rather than by
-// a bounded assertion.
+// channel, which is what lets the workers' range terminate.
 func TestFeedHashJobsClosesJobsWhenCancelled(t *testing.T) {
 	t.Parallel()
 
@@ -731,16 +440,6 @@ func TestFeedHashJobsClosesJobsWhenCancelled(t *testing.T) {
 // nobody wants the hashes of — while still letting the range run out
 // so the pool tears down. The queued run names a file that does not
 // exist, so a worker that hashed it anyway would produce a result.
-//
-// hashWorker's other cancellation exit, abandoning the send of a
-// result, is reachable from the scan: stop cancels the pool before it
-// drains results, so a worker waiting on that send can leave through
-// it. The tests that stop a scan mid-hash, among them
-// TestScanHashWriteFailureUnwindsPool, reach it in some runs only,
-// depending on timing, and no test fails without it, since stop's
-// drain frees a waiting worker anyway. This test, for its part, catches
-// a removed drop check in some runs only: a worker that hashes the run
-// anyway then picks at random between sending the result and leaving.
 func TestHashWorkerDropsQueuedRuns(t *testing.T) {
 	t.Parallel()
 
@@ -773,10 +472,7 @@ func TestHashWorkerDropsQueuedRuns(t *testing.T) {
 // TestHashPhaseCancelledReturnsContextError checks the result loop's
 // own exit: with the pool cancelled, no result will ever arrive, and
 // the loop must leave through the cancellation rather than wait for a
-// receive that cannot happen. This call is not bounded by poolUnwind: a
-// loop that dropped its cancellation case would block on that receive,
-// so the regression surfaces as the test binary's timeout rather than
-// as a bounded assertion.
+// receive that cannot happen.
 func TestHashPhaseCancelledReturnsContextError(t *testing.T) {
 	t.Parallel()
 

db.go

@@ -51,12 +51,6 @@ 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 = `
@@ -219,12 +213,6 @@ func openReportDatabase(ctx context.Context,
 	}
 
 	v, err := userVersion(ctx, db)
-	if err == nil && v == 0 {
-		// An empty database passes this check and fails the version
-		// check below.
-		err = checkUnversioned(ctx, db)
-	}
-
 	if err != nil {
 		_ = db.Close()
 
@@ -251,11 +239,6 @@ func initSchema(ctx context.Context, db *sql.DB) error {
 
 	switch v {
 	case 0:
-		err = checkUnversioned(ctx, db)
-		if err != nil {
-			return err
-		}
-
 		return createSchema(ctx, db)
 	case schemaVersion:
 		return nil
@@ -265,65 +248,20 @@ func initSchema(ctx context.Context, db *sql.DB) error {
 	}
 }
 
-// checkUnversioned checks a database at user_version 0 before it is
-// taken for an empty one. createSchema creates the files table and
-// sets the version together, so a files table at version 0 was made by
-// something else. Adopting it could corrupt unrelated data, so that is
-// a schema-version error telling the operator to remove the file and
-// rescan.
-func checkUnversioned(ctx context.Context, db *sql.DB) error {
-	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):
-		return nil
-	default:
-		return fmt.Errorf("check for files table: %w", err)
-	}
-}
-
 // createSchema applies the schema to a fresh database and stamps the
-// schema version in one transaction, so a creation stopped partway, by
-// an interrupt or an error, leaves an empty database the next scan
-// sets up, never a files table at version 0, which checkUnversioned
-// refuses.
+// schema version.
 func createSchema(ctx context.Context, db *sql.DB) error {
-	tx, err := db.BeginTx(ctx, nil)
+	_, err := db.ExecContext(ctx, createTableSQL)
 	if err != nil {
 		return fmt.Errorf("create schema: %w", err)
 	}
 
-	defer func() { _ = tx.Rollback() }()
-
-	_, err = tx.ExecContext(ctx, createTableSQL)
-	if err != nil {
-		return fmt.Errorf("create schema: %w", err)
-	}
-
-	_, err = tx.ExecContext(ctx, createIndexSQL)
-	if err != nil {
-		return fmt.Errorf("create schema: %w", err)
-	}
-
-	_, err = tx.ExecContext(ctx,
+	_, err = db.ExecContext(ctx,
 		"PRAGMA user_version = "+strconv.Itoa(schemaVersion))
 	if err != nil {
 		return fmt.Errorf("set schema version: %w", err)
 	}
 
-	err = tx.Commit()
-	if err != nil {
-		return fmt.Errorf("create schema: %w", err)
-	}
-
 	return nil
 }
 
@@ -339,18 +277,18 @@ 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
@@ -360,92 +298,19 @@ 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

@@ -73,78 +73,9 @@ func TestOpenScanDatabaseCreates(t *testing.T) {
 
 	defer func() { _ = db.Close() }()
 
-	if recs := dbRecords(t, db); len(recs) != 0 {
-		t.Fatalf("records = %v, want none", recs)
-	}
-}
-
-func TestOpenDatabaseUnversionedForeign(t *testing.T) {
-	t.Parallel()
-
-	// A database that has a files table but user_version 0, written by
-	// some other tool. report, trees and scan must refuse it with the
-	// schema-version error, not adopt it and not emit a raw SQLite
-	// "table files already exists".
-	path := testDBPath(t)
-
-	db, err := sql.Open("sqlite", 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 = openReportDatabase(t.Context(), path)
-	if !errors.Is(err, errSchemaVersion) ||
-		!strings.Contains(err.Error(), "remove the file and rescan") {
-		t.Fatalf("report: err = %v, want errSchemaVersion telling the "+
-			"operator to remove the file and rescan", err)
-	}
-
-	_, err = openScanDatabase(t.Context(), path)
-	if !errors.Is(err, errSchemaVersion) ||
-		!strings.Contains(err.Error(), "remove the file and rescan") {
-		t.Fatalf("scan: err = %v, want errSchemaVersion telling the "+
-			"operator to remove the file and rescan", err)
-	}
-}
-
-func TestSchemaCreationStoppedPartway(t *testing.T) {
-	t.Parallel()
-
-	// A first scan stopped while creating the schema must leave a
-	// database the next scan accepts. max_page_count(2) leaves room for
-	// the files table but not its index, so schema creation fails right
-	// after CREATE TABLE, a point an interrupt could also stop it at.
-	path := testDBPath(t)
-
-	db, err := openDB(path, scanParams+"&_pragma=max_page_count(2)")
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	err = initSchema(t.Context(), db)
-	_ = db.Close()
-
-	if err == nil {
-		t.Fatal("initSchema with no room for the index succeeded")
-	}
-
-	db, err = openScanDatabase(t.Context(), path)
-	if err != nil {
-		t.Fatalf("next scan: %v", err)
-	}
-
-	defer func() { _ = db.Close() }()
-
-	v, err := userVersion(t.Context(), db)
-	if err != nil || v != schemaVersion {
-		t.Fatalf("userVersion = %d, %v; want %d, nil", v, err, schemaVersion)
+	recs, err := loadFileRows(t.Context(), db)
+	if err != nil || len(recs) != 0 {
+		t.Fatalf("loadFileRows = %v, %v; want empty, nil", recs, err)
 	}
 }
 
@@ -157,11 +88,9 @@ func TestOpenReportDatabaseMissing(t *testing.T) {
 	}
 }
 
-func TestOpenDatabaseVersionMismatch(t *testing.T) {
+func TestOpenReportDatabaseVersionMismatch(t *testing.T) {
 	t.Parallel()
 
-	// A database stamped with a schema version other than 0 and
-	// schemaVersion. report, trees and scan must all refuse it.
 	path := testDBPath(t)
 
 	db, err := openScanDatabase(t.Context(), path)
@@ -178,12 +107,7 @@ func TestOpenDatabaseVersionMismatch(t *testing.T) {
 
 	_, err = openReportDatabase(t.Context(), path)
 	if !errors.Is(err, errSchemaVersion) {
-		t.Fatalf("report: err = %v, want errSchemaVersion", err)
-	}
-
-	_, err = openScanDatabase(t.Context(), path)
-	if !errors.Is(err, errSchemaVersion) {
-		t.Fatalf("scan: err = %v, want errSchemaVersion", err)
+		t.Fatalf("err = %v, want errSchemaVersion", err)
 	}
 }
 
@@ -244,7 +168,7 @@ func TestCloseScanDatabaseWhileReportOpen(t *testing.T) {
 
 	defer func() { _ = reportDB.Close() }()
 
-	err = loadFileRows(t.Context(), reportDB, func(scanRec) {})
+	_, err = loadFileRows(t.Context(), reportDB)
 	if err != nil {
 		t.Fatalf("loadFileRows: %v", err)
 	}
@@ -272,8 +196,15 @@ 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)
 	}
@@ -290,7 +221,11 @@ 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)
 	}
@@ -319,8 +254,9 @@ 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)
@@ -334,7 +270,8 @@ 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)
 	}
 }

main.go

@@ -15,7 +15,6 @@
 //	sfdupes scan [--workers N] [-x] PATH...
 //	sfdupes report > dupes.tsv
 //	sfdupes trees > dupetrees.tsv
-//	sfdupes --version
 //
 // See README.md for the complete specification.
 package main
@@ -51,10 +50,6 @@ const (
 // cobra prints for it is the whole message.
 var errNoSubcommand = errors.New("no subcommand")
 
-// errWorkersBelowOne is the usage error for a scan --workers value
-// below 1.
-var errWorkersBelowOne = errors.New("--workers must be at least 1")
-
 // Version is the build version, injected at link time via -ldflags
 // (see the Makefile); "dev" for a plain go build.
 //
@@ -92,9 +87,6 @@ func run(args []string, stdout, stderr io.Writer) int {
 	switch {
 	case err == nil:
 		return exitOK
-	case errors.Is(err, errInterrupted):
-		// The interrupted scan has printed its own line.
-		return exitFatal
 	case errors.As(err, &fatal):
 		// The command ran and failed: a runtime error, reported
 		// without the usage text that a usage error gets.
@@ -102,35 +94,22 @@ func run(args []string, stdout, stderr io.Writer) int {
 
 		return exitFatal
 	default:
-		// A usage error, which cobra has already reported on stderr.
+		// A usage error: cobra has already printed the message and
+		// the usage text.
 		return exitUsage
 	}
 }
 
 // newRootCommand builds the command tree. Everything on stdout is
-// machine-readable data, the version line included; all human-facing
-// output (help, usage, errors) goes to stderr.
+// machine-readable data; all human-facing output (help, usage, errors)
+// goes to stderr.
 func newRootCommand(stdout, stderr io.Writer) *cobra.Command {
-	var showVersion bool
-
-	printVersion := runE(func(context.Context, []string) error {
-		_, err := fmt.Fprintf(stdout, "sfdupes %s\n", Version)
-		if err != nil {
-			return fmt.Errorf("write stdout: %w", err)
-		}
-
-		return nil
-	})
-
 	root := &cobra.Command{
-		Use:   "sfdupes",
-		Short: "Find candidate duplicate files by size and head/tail/content SHA-256",
-		Args:  cobra.NoArgs,
-		RunE: func(cmd *cobra.Command, args []string) error {
-			if showVersion {
-				return printVersion(cmd, args)
-			}
-
+		Use:     "sfdupes",
+		Short:   "Find candidate duplicate files by size and head/tail/content SHA-256",
+		Version: Version,
+		Args:    cobra.NoArgs,
+		RunE: func(cmd *cobra.Command, _ []string) error {
 			// A missing subcommand prints usage and exits 2: cobra
 			// prints the usage text for the returned error, and run
 			// maps everything that is not a fatal error to exit 2.
@@ -143,11 +122,6 @@ func newRootCommand(stdout, stderr io.Writer) *cobra.Command {
 	root.SetErr(stderr)
 	root.CompletionOptions.DisableDefaultCmd = true
 
-	// Cobra's built-in version flag prints through the help writer,
-	// stderr; this one prints to stdout.
-	root.Flags().BoolVarP(&showVersion, "version", "v", false,
-		"print the version to stdout")
-
 	var (
 		scanWorkers int
 		scanOneFS   bool
@@ -157,13 +131,7 @@ func newRootCommand(stdout, stderr io.Writer) *cobra.Command {
 		Use:   cmdScan + " [--workers N] [-x] PATH...",
 		Short: "Walk trees and synchronize the scan database",
 		Args:  cobra.MinimumNArgs(1),
-		PreRunE: func(cmd *cobra.Command, _ []string) error {
-			return checkScanWorkers(cmd, scanWorkers)
-		},
 		RunE: runE(func(ctx context.Context, args []string) error {
-			ctx, stop := interruptContext(ctx)
-			defer stop()
-
 			return runScan(ctx, args, scanWorkers, scanOneFS)
 		}),
 	}
@@ -195,26 +163,13 @@ func newRootCommand(stdout, stderr io.Writer) *cobra.Command {
 	return root
 }
 
-// checkScanWorkers rejects a scan --workers value below 1. That is a
-// usage error reported in one line: cobra prints the returned message
-// without the usage text, and run exits 2.
-func checkScanWorkers(cmd *cobra.Command, workers int) error {
-	if workers >= 1 {
-		return nil
-	}
-
-	cmd.SilenceUsage = true
-
-	return fmt.Errorf("%w, got %d", errWorkersBelowOne, workers)
-}
-
-// runE adapts a subcommand implementation, or the version print, to
-// cobra's RunE. Cobra prints the error and the command's usage text for
-// every error RunE returns, but a subcommand that ran and failed has no
-// usage problem to report: both are silenced here, and the error is
-// marked fatal so that run reports it on stderr and exits 1 rather than
-// 2. The command's context is handed to the implementation: cancelling
-// it unwinds the scan's worker pools.
+// runE adapts a subcommand implementation to cobra's RunE. Cobra
+// prints the error and the command's usage text for every error RunE
+// returns, but a subcommand that ran and failed has no usage problem
+// to report: both are silenced here, and the error is marked fatal so
+// that run reports it on stderr and exits 1 rather than 2. The command's
+// context is handed to the implementation: cancelling it unwinds the
+// scan's worker pools.
 func runE(
 	fn func(ctx context.Context, args []string) error,
 ) func(*cobra.Command, []string) error {

main_test.go

@@ -295,108 +295,34 @@ func TestRunUsageErrors(t *testing.T) {
 	}
 }
 
-func TestRunScanRejectsWorkersBelowOne(t *testing.T) {
-	// README §scan mode: --workers below 1 is a usage error reported in
-	// one line on stderr, before the scan opens the database.
-	for _, workers := range []string{"0", "-1"} {
-		t.Run(workers, func(t *testing.T) {
-			dbPath := testDBPath(t)
-			t.Setenv(databaseEnv, dbPath)
-
-			var stdout, stderr bytes.Buffer
-
-			args := []string{cmdScan, "--workers", workers, t.TempDir()}
-
-			code := run(args, &stdout, &stderr)
-			if code != exitUsage {
-				t.Errorf("run(%v) = %d, want %d", args, code, exitUsage)
-			}
-
-			want := "Error: --workers must be at least 1, got " + workers +
-				"\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(dbPath)
-			if !errors.Is(err, fs.ErrNotExist) {
-				t.Errorf("stat %s: %v, want the database never created",
-					dbPath, err)
-			}
-		})
-	}
-}
-
-func TestRunHelp(t *testing.T) {
+// TestRunHelpAndVersionSucceed checks that the two informational flags
+// exit 0 and keep their human-facing output on stderr.
+func TestRunHelpAndVersionSucceed(t *testing.T) {
 	t.Parallel()
 
-	// README §Subcommands: help goes to stderr, exits 0, and leaves
-	// stdout empty.
-	cases := [][]string{{"--help"}, {"-h"}, {cmdScan, "--help"}}
-
-	for _, args := range cases {
-		var stdout, stderr bytes.Buffer
-
-		code := run(args, &stdout, &stderr)
-		if code != exitOK {
-			t.Errorf("run(%v) = %d, want %d", args, code, exitOK)
-		}
-
-		if !strings.Contains(stderr.String(), usageMarker) {
-			t.Errorf("run(%v) stderr = %q, want the help text",
-				args, stderr.String())
-		}
-
-		if got := stdout.String(); got != "" {
-			t.Errorf("run(%v) stdout = %q, want nothing (data only)",
-				args, got)
-		}
-	}
+	assertHumanOutput(t, "--help")
+	assertHumanOutput(t, "--version")
 }
 
-func TestRunVersion(t *testing.T) {
-	t.Parallel()
+// assertHumanOutput runs sfdupes with one informational flag and checks
+// that it succeeds with its output on stderr and stdout untouched
+// (README design goal 4).
+func assertHumanOutput(t *testing.T, arg string) {
+	t.Helper()
 
-	// README §Subcommands: the version is one line on stdout, with
-	// nothing on stderr, and exits 0.
-	for _, arg := range []string{"--version", "-v"} {
-		var stdout, stderr bytes.Buffer
+	var stdout, stderr bytes.Buffer
 
-		code := run([]string{arg}, &stdout, &stderr)
-		if code != exitOK {
-			t.Errorf("run(%s) = %d, want %d", arg, code, exitOK)
-		}
-
-		want := "sfdupes " + Version + "\n"
-		if got := stdout.String(); got != want {
-			t.Errorf("run(%s) stdout = %q, want %q", arg, got, want)
-		}
-
-		if got := stderr.String(); got != "" {
-			t.Errorf("run(%s) stderr = %q, want nothing", arg, got)
-		}
-	}
-}
-
-func TestRunVersionWriteFailureIsFatal(t *testing.T) {
-	t.Parallel()
-
-	// README §Error handling: a stdout write failure exits 1, reported
-	// in one line on stderr.
-	var stderr bytes.Buffer
-
-	code := run([]string{"--version"}, failingWriter{}, &stderr)
-	if code != exitFatal {
-		t.Errorf("run(--version) = %d, want %d", code, exitFatal)
+	code := run([]string{arg}, &stdout, &stderr)
+	if code != exitOK {
+		t.Errorf("run(%s) = %d, want %d", arg, code, exitOK)
 	}
 
-	want := "sfdupes: write stdout: " + errWriteFailed.Error() + "\n"
-	if got := stderr.String(); got != want {
-		t.Errorf("stderr = %q, want %q", got, want)
+	if stderr.Len() == 0 {
+		t.Errorf("run(%s) wrote nothing to stderr", arg)
+	}
+
+	if got := stdout.String(); got != "" {
+		t.Errorf("stdout = %q, want nothing (data only)", got)
 	}
 }
 

progress.go

@@ -141,20 +141,14 @@ func (p *progress) warnf(format string, args ...any) {
 	fmt.Fprintln(os.Stderr, msg)
 }
 
-// finish terminates the pass's display. A bar whose pass stopped short
-// of its total, as an interrupted one does, is left as last drawn; the
-// library's Finish would fill it up.
+// finish terminates the pass's display.
 func (p *progress) finish() {
 	if p == nil {
 		return
 	}
 
 	if p.bar != nil {
-		if p.total >= 0 && p.count < p.total {
-			_ = p.bar.Exit()
-		} else {
-			_ = p.bar.Finish()
-		}
+		_ = p.bar.Finish()
 
 		fmt.Fprintln(os.Stderr)
 

progress_test.go

@@ -144,46 +144,18 @@ func TestSpinnerShowsCountAfterBurst(t *testing.T) {
 
 	time.Sleep(spinnerIdle)
 
-	if shown := lastFrame(stderr()); !strings.Contains(shown, "(50/-,") {
-		t.Errorf("terminal shows %q, want a count of 50", shown)
-	}
-}
-
-// lastFrame returns what a terminal shows of the frames a bar drew: the
-// last one. The library starts each frame with a carriage return and
-// erases the previous one with spaces first.
-func lastFrame(out string) string {
+	// 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(out, "\r") {
+	for frame := range strings.SplitSeq(stderr(), "\r") {
 		if strings.TrimSpace(frame) != "" {
 			shown = frame
 		}
 	}
 
-	return shown
-}
-
-// TestBarStoppedShortKeepsCount checks that the terminal display of a
-// pass that stops before its total, as an interrupted one does, is left
-// as last drawn instead of being filled up.
-//
-//nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
-func TestBarStoppedShortKeepsCount(t *testing.T) {
-	stderr := captureStderr(t)
-	p := &progress{
-		label: "hash", total: 10, start: time.Now(),
-		bar: newBar("hash", 10),
-	}
-
-	p.increment()
-
-	// Past the redraw limit, so the bar draws the next count.
-	time.Sleep(2 * barThrottle)
-	p.increment()
-	p.finish()
-
-	if shown := lastFrame(stderr()); !strings.Contains(shown, "(2/10,") {
-		t.Errorf("terminal shows %q, want a count of 2 of 10", shown)
+	if !strings.Contains(shown, "(50/-,") {
+		t.Errorf("terminal shows %q, want a count of 50", shown)
 	}
 }

report.go

@@ -6,6 +6,7 @@ import (
 	"fmt"
 	"io"
 	"os"
+	"slices"
 	"strings"
 )
 
@@ -28,22 +29,51 @@ 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 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() }()
 
+	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, stdout io.Writer) error {
+	recs, err := loadRecords(ctx)
+	if err != nil {
+		return err
+	}
+
+	dupes := collectDupeGroups(recs)
+
 	out := bufio.NewWriterSize(stdout, ioBufSize)
 
 	_, err = fmt.Fprintln(out, "first\tdupe\tsize")
@@ -51,36 +81,21 @@ func runReport(ctx context.Context, stdout io.Writer) error {
 		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 +106,57 @@ 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"
 )
 
@@ -51,53 +47,6 @@ 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()))
 
@@ -116,82 +65,6 @@ func TestRunReportEscapesPaths(t *testing.T) {
 	}
 }
 
-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 +121,7 @@ func TestWarnfEscapes(t *testing.T) {
 	}
 }
 
-func TestDupeGroups(t *testing.T) {
+func TestCollectDupeGroups(t *testing.T) {
 	t.Parallel()
 
 	recs := []scanRec{
@@ -263,7 +136,7 @@ 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 +154,7 @@ 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 +169,7 @@ 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 +180,7 @@ 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 +190,23 @@ 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 +218,7 @@ func TestDupeGroupsTieBreak(t *testing.T) {
 	}
 }
 
-func TestDupeGroupsDeterministic(t *testing.T) {
+func TestCollectDupeGroupsDeterministic(t *testing.T) {
 	t.Parallel()
 
 	recs := []scanRec{
@@ -357,12 +228,12 @@ 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

@@ -11,7 +11,6 @@ import (
 	"io"
 	"io/fs"
 	"os"
-	"os/signal"
 	"path/filepath"
 	"slices"
 	"strings"
@@ -58,10 +57,6 @@ const sampleWindow = 1024 * 1024
 // and hash worker pools.
 const workQueueDepth = 1024
 
-// errInterrupted reports a scan stopped by SIGINT or SIGTERM. runScan
-// has already printed its line, so run prints nothing more.
-var errInterrupted = errors.New("scan interrupted")
-
 // fileRec carries one statted file between the scan phases. dev and
 // ino identify the underlying inode so hard-linked paths can share
 // one read; both are zero when the platform exposes no inode.
@@ -95,14 +90,15 @@ type fileMeta struct {
 // 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. When ctx is cancelled, as by the SIGINT or
-// SIGTERM that interruptContext catches, the scan keeps what it has
-// hashed (see syncScan), prints how many files its walk reached, and
-// returns errInterrupted. workers must be at least 1; the scan command
-// rejects anything less.
+// is released after it. Cancelling ctx unwinds the worker pools and
+// aborts the scan with the context's error.
 func runScan(ctx context.Context, roots []string, workers int,
 	oneFS bool,
 ) error {
+	if workers < 1 {
+		workers = 1
+	}
+
 	roots, err := resolveRoots(roots)
 	if err != nil {
 		return err
@@ -118,12 +114,6 @@ func runScan(ctx context.Context, roots []string, workers int,
 	defer func() { _ = lock.Close() }()
 
 	db, err := openScanDatabase(ctx, dbPath)
-	if err != nil && ctx.Err() != nil {
-		// Interrupted while opening; SQLite may report that with an
-		// error of its own rather than the context's.
-		return interrupted(0)
-	}
-
 	if err != nil {
 		return err
 	}
@@ -131,10 +121,6 @@ func runScan(ctx context.Context, roots []string, workers int,
 	defer closeScanDatabase(ctx, db, dbPath)
 
 	st, err := syncScan(ctx, db, roots, workers, oneFS)
-	if errors.Is(err, context.Canceled) {
-		return interrupted(st.walked)
-	}
-
 	if err != nil {
 		return fmt.Errorf("update database %s: %w", dbPath, err)
 	}
@@ -148,34 +134,6 @@ func runScan(ctx context.Context, roots []string, workers int,
 	return nil
 }
 
-// interruptContext returns a copy of ctx that the first SIGINT or
-// SIGTERM cancels; the scan command runs the scan under it. stop
-// releases the signals.
-func interruptContext(ctx context.Context) (context.Context, func()) {
-	// A SIGINT ignored from the start, as by a script's background job,
-	// stays ignored.
-	signals := []os.Signal{syscall.SIGTERM}
-	if !signal.Ignored(syscall.SIGINT) {
-		signals = append(signals, syscall.SIGINT)
-	}
-
-	ctx, stop := signal.NotifyContext(ctx, signals...)
-
-	// Stopping restores the default handling, so a second signal ends
-	// the process at once.
-	context.AfterFunc(ctx, stop)
-
-	return ctx, stop
-}
-
-// interrupted prints the line for a scan stopped by a signal after its
-// walk reached walked files, and returns errInterrupted.
-func interrupted(walked int) error {
-	fmt.Fprintf(os.Stderr, "scan: interrupted after %d files\n", walked)
-
-	return errInterrupted
-}
-
 // resolveRoots converts each PATH operand to an absolute, lexically
 // cleaned path (symlinks are not resolved) and verifies that it
 // exists. Database records are keyed by absolute path, so scan results
@@ -229,9 +187,8 @@ func pruneRoots(roots []string) []string {
 }
 
 // scanStats summarizes one scan's database synchronization for the
-// final stderr summary, or for the line an interrupted scan prints.
+// final stderr summary.
 type scanStats struct {
-	walked    int // files the walk reached
 	added     int
 	updated   int
 	removed   int
@@ -253,30 +210,7 @@ type scanState struct {
 	st        scanStats
 }
 
-// syncScan synchronizes the database with the filesystem under roots;
-// see runPhases. When ctx is cancelled, as by an interrupt, it commits
-// the hashed records still waiting in the batch, starts no other write
-// or deletion, and returns the cancellation.
-func syncScan(ctx context.Context, db *sql.DB, roots []string,
-	workers int, oneFS bool,
-) (scanStats, error) {
-	s := &scanState{db: db}
-
-	err := s.runPhases(ctx, roots, workers, oneFS)
-	if err == nil || ctx.Err() == nil {
-		return s.st, err
-	}
-
-	// The one write made after the cancellation, so it cannot use ctx.
-	err = applyChanges(context.WithoutCancel(ctx), db, s.batch, nil, nil)
-	if err != nil {
-		return s.st, err
-	}
-
-	return s.st, ctx.Err()
-}
-
-// runPhases synchronizes the database with the filesystem under roots
+// syncScan synchronizes the database with the filesystem under roots
 // in four sequential phases: walk (enumerate and stat every file,
 // building a complete size census), hash (read only the new or
 // changed — or previously unhashed — files whose size at least one
@@ -289,41 +223,48 @@ func syncScan(ctx context.Context, db *sql.DB, roots []string,
 // 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.
-func (s *scanState) runPhases(ctx context.Context, roots []string,
+func syncScan(ctx context.Context, db *sql.DB, roots []string,
 	workers int, oneFS bool,
-) error {
+) (scanStats, error) {
+	s := &scanState{db: db}
+
 	// 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))
 
 	err := s.loadIndex(ctx, roots)
 	if err != nil {
-		return err
+		return s.st, err
 	}
 
 	changed, unhashed := s.walkPhase(startWalk(ctx, roots, oneFS, workers))
 
 	// A cancelled walk stops early, so its size census covers only part
-	// of the roots, and every file it never reached would look vanished
-	// to the update phase. Stop before anything is written or deleted.
+	// of the roots, and every file it never reached looks vanished to
+	// the update phase. Defence in depth rather than the only barrier:
+	// that phase would today fail on its first BeginTx with the same
+	// cancelled context before deleting anything. But it is the barrier
+	// that survives a later decision to let an interrupted scan commit
+	// what it has, and it turns a confusing failure deep in the update
+	// phase into a clean abort at the phase boundary.
 	err = ctx.Err()
 	if err != nil {
-		return err
+		return s.st, err
 	}
 
 	s.partition(changed, unhashed)
 
 	err = s.hashPhase(ctx, workers)
 	if err != nil {
-		return err
+		return s.st, err
 	}
 
 	err = s.updatePhase(ctx)
 	if err != nil {
-		return err
+		return s.st, err
 	}
 
-	return s.contentPhase(ctx, workers)
+	return s.st, s.contentPhase(ctx, workers)
 }
 
 // walkableRoots returns the operands the walk can start from: regular
@@ -408,7 +349,6 @@ func (s *scanState) walkPhase(
 		}
 
 		s.sizes = append(s.sizes, ev.rec.size)
-		s.st.walked++
 
 		prog.increment()
 
@@ -612,22 +552,16 @@ func (s *scanState) recordRun(ctx context.Context, r hashResult) error {
 }
 
 // commitFullBatch commits the running batch once it holds
-// updateBatchSize records. A batch that fails to commit is kept: the
-// commit fails when the scan is interrupted, and syncScan then commits
-// the batch itself.
+// updateBatchSize records.
 func (s *scanState) commitFullBatch(ctx context.Context) error {
 	if len(s.batch) < updateBatchSize {
 		return nil
 	}
 
 	err := applyBatch(ctx, s.db, s.batch, nil, nil)
-	if err != nil {
-		return err
-	}
-
 	s.batch = s.batch[:0]
 
-	return nil
+	return err
 }
 
 // updatePhase writes the scan's tail under one progress display: the
@@ -1070,12 +1004,6 @@ func walkOneDir(ctx context.Context, job dirJob, oneFS bool,
 	var subs []dirJob
 
 	for _, e := range entries {
-		// A cancelled scan wants nothing more from this directory: stop
-		// rather than lstat the rest of a large one.
-		if ctx.Err() != nil {
-			return nil
-		}
-
 		p := filepath.Join(job.path, e.Name())
 
 		if e.IsDir() {

scan_test.go

@@ -6,18 +6,14 @@ import (
 	"crypto/sha256"
 	"database/sql"
 	"encoding/hex"
-	"errors"
 	"fmt"
 	"io"
-	"io/fs"
 	"os"
-	"os/signal"
 	"path/filepath"
 	"runtime"
 	"slices"
 	"strconv"
 	"strings"
-	"syscall"
 	"testing"
 	"time"
 )
@@ -404,7 +400,7 @@ 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)
@@ -439,7 +435,7 @@ 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)
 	}
@@ -460,13 +456,13 @@ func TestScanContentWithinOperand(t *testing.T) {
 	added := sparseFile(t, dir, "d2", headTailMin)
 
 	st := syncTree(t, db, dir)
-	if st != (scanStats{walked: 3, added: 1, unchanged: 2}) {
+	if st != (scanStats{added: 1, unchanged: 2}) {
 		t.Fatalf("rescan stats = %+v, want 1 added 2 unchanged", st)
 	}
 
 	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)
 	}
@@ -506,7 +502,7 @@ func TestScanContentStalePartners(t *testing.T) {
 	sparseFile(t, dirB, "changed-copy", headTailMin+1)
 
 	st := syncTree(t, db, dirB)
-	if st != (scanStats{walked: 2, added: 2}) {
+	if st != (scanStats{added: 2}) {
 		t.Errorf("stats = %+v, want 2 added and nothing skipped", st)
 	}
 
@@ -524,7 +520,7 @@ 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)
 	}
 }
@@ -563,7 +559,7 @@ func TestScanContentHashedStalePartners(t *testing.T) {
 	b := sparseFile(t, t.TempDir(), "copy", headTailMin)
 
 	st := syncTree(t, db, filepath.Dir(b))
-	if st != (scanStats{walked: 1, added: 1}) {
+	if st != (scanStats{added: 1}) {
 		t.Errorf("stats = %+v, want 1 added and nothing skipped", st)
 	}
 
@@ -575,7 +571,7 @@ 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)
 	}
@@ -603,7 +599,7 @@ func TestScanContentReadFailure(t *testing.T) {
 	b := sparseFile(t, dirB, "b", headTailMin)
 
 	st := syncTree(t, db, dirB)
-	if st != (scanStats{walked: 1, added: 1, skipped: 1}) {
+	if st != (scanStats{added: 1, skipped: 1}) {
 		t.Fatalf("stats = %+v, want 1 added 1 skipped", st)
 	}
 
@@ -617,14 +613,14 @@ func TestScanContentReadFailure(t *testing.T) {
 	}
 
 	st = syncTree(t, db, dirB)
-	if st != (scanStats{walked: 1, unchanged: 1}) {
+	if st != (scanStats{unchanged: 1}) {
 		t.Fatalf("rescan stats = %+v, want 1 unchanged", st)
 	}
 
 	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)
@@ -663,7 +659,7 @@ func TestScanContentCheckError(t *testing.T) {
 	b := sparseFile(t, t.TempDir(), "b", headTailMin)
 
 	st := syncTree(t, db, filepath.Dir(b))
-	if st != (scanStats{walked: 1, added: 1, skipped: 1}) {
+	if st != (scanStats{added: 1, skipped: 1}) {
 		t.Fatalf("stats = %+v, want 1 added 1 skipped", st)
 	}
 
@@ -691,7 +687,7 @@ func TestScanContentHardlinks(t *testing.T) {
 	c := sparseFile(t, dir, "copy", headTailMin)
 
 	st := syncTree(t, db, dir)
-	if st != (scanStats{walked: 3, added: 3}) {
+	if st != (scanStats{added: 3}) {
 		t.Fatalf("stats = %+v, want 3 added", st)
 	}
 
@@ -914,159 +910,6 @@ func TestDeviceOfInfo(t *testing.T) {
 	}
 }
 
-// dirEntryFor returns the fs.DirEntry for name within dir, obtained via
-// the same os.ReadDir the walk uses, so it carries a real Info().
-func dirEntryFor(t *testing.T, dir, name string) fs.DirEntry {
-	t.Helper()
-
-	entries, err := os.ReadDir(dir)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	for _, e := range entries {
-		if e.Name() == name {
-			return e
-		}
-	}
-
-	t.Fatalf("entry %q not found in %q", name, dir)
-
-	return nil
-}
-
-// callSubdirJob runs subdirJob against e under parent, collecting any
-// warning events it emits (subdirJob emits at most one).
-func callSubdirJob(t *testing.T, p string, e fs.DirEntry,
-	parent dirJob, oneFS bool,
-) (dirJob, bool, []walkEvent) {
-	t.Helper()
-
-	events := make(chan walkEvent, 1)
-	job, ok := subdirJob(t.Context(), p, e, parent, oneFS, events)
-	close(events)
-
-	var evs []walkEvent
-	for ev := range events {
-		evs = append(evs, ev)
-	}
-
-	return job, ok, evs
-}
-
-// TestSubdirJobOneFilesystem exercises the -x boundary check in
-// subdirJob directly, so no second real filesystem is needed. The
-// subdirectory's real device is compared against a fabricated operand
-// device.
-func TestSubdirJobOneFilesystem(t *testing.T) {
-	t.Parallel()
-
-	dir := t.TempDir()
-
-	sub := filepath.Join(dir, "sub")
-
-	err := os.Mkdir(sub, 0o750)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	info, err := os.Lstat(sub)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	dev, ok := deviceOfInfo(info)
-	if !ok {
-		t.Skip("platform exposes no device id")
-	}
-
-	// A device the subdirectory is not on, standing in for an operand
-	// rooted on a different filesystem.
-	otherDev := dev + 1
-	e := dirEntryFor(t, dir, "sub")
-
-	cases := []struct {
-		name   string
-		oneFS  bool
-		parent dirJob
-		wantOK bool
-	}{
-		// -x on, subdirectory on a different device than its operand:
-		// descent is refused.
-		{"reject across boundary", true,
-			dirJob{rootDev: otherDev, rootDevOK: true}, false},
-		// -x on but the operand's own device is unknown: the boundary
-		// check is bypassed and descent proceeds.
-		{"bypass when root device unknown", true,
-			dirJob{rootDev: otherDev, rootDevOK: false}, true},
-		// Default (no -x): boundaries are crossed even onto a different
-		// device.
-		{"cross by default", false,
-			dirJob{rootDev: otherDev, rootDevOK: true}, true},
-	}
-
-	for _, tc := range cases {
-		t.Run(tc.name, func(t *testing.T) {
-			t.Parallel()
-
-			job, ok, evs := callSubdirJob(t, sub, e, tc.parent, tc.oneFS)
-			if ok != tc.wantOK {
-				t.Fatalf("accepted = %v, want %v", ok, tc.wantOK)
-			}
-
-			if len(evs) != 0 {
-				t.Fatalf("unexpected events: %+v", evs)
-			}
-
-			// The accepted job must carry the operand's device down, or -x
-			// stops checking below the first level.
-			want := dirJob{
-				path:      sub,
-				rootDev:   tc.parent.rootDev,
-				rootDevOK: tc.parent.rootDevOK,
-			}
-			if ok && job != want {
-				t.Fatalf("job = %+v, want %+v", job, want)
-			}
-		})
-	}
-}
-
-// errInfoUnavailable is returned by errDirEntry.Info().
-var errInfoUnavailable = errors.New("info unavailable")
-
-// errDirEntry is a directory entry whose Info() always fails, driving
-// subdirJob's stat-error branch deterministically.
-type errDirEntry struct{ name string }
-
-func (e errDirEntry) Name() string { return e.name }
-func (errDirEntry) IsDir() bool    { return true }
-func (errDirEntry) Type() fs.FileMode {
-	return fs.ModeDir
-}
-
-func (errDirEntry) Info() (fs.FileInfo, error) {
-	return nil, errInfoUnavailable
-}
-
-// TestSubdirJobStatError asserts that when a subdirectory's Info()
-// fails under -x, subdirJob warns and refuses descent.
-func TestSubdirJobStatError(t *testing.T) {
-	t.Parallel()
-
-	p := "/does/not/matter/sub"
-
-	_, ok, evs := callSubdirJob(t, p, errDirEntry{name: "sub"},
-		dirJob{rootDev: 1, rootDevOK: true}, true)
-	if ok {
-		t.Fatal("descent accepted after stat error, want refused")
-	}
-
-	if len(evs) != 1 || !evs[0].fail || !strings.Contains(evs[0].warn, p) {
-		t.Fatalf("want one warning naming the path, got %+v", evs)
-	}
-}
-
 // buildSmokeTree recreates the README smoke-test filesystem layout
 // with deterministic content and returns the tree root.
 func buildSmokeTree(t *testing.T) string {
@@ -1113,16 +956,11 @@ 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)
 	}
@@ -1159,10 +997,10 @@ 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))
 	}
@@ -1187,10 +1025,11 @@ 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 {
@@ -1215,7 +1054,7 @@ func TestScanPipeline(t *testing.T) {
 	db := openTestDB(t)
 
 	st := syncTree(t, db, dir)
-	if st != (scanStats{walked: smokeTreeFiles, added: smokeTreeFiles}) {
+	if st != (scanStats{added: smokeTreeFiles}) {
 		t.Fatalf("stats = %+v, want %d added only", st, smokeTreeFiles)
 	}
 
@@ -1224,8 +1063,8 @@ 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) {
@@ -1238,7 +1077,7 @@ func TestSyncScanUnchangedReuse(t *testing.T) {
 	writeFile(t, dir, "b.bin", pattern(2, 600))
 
 	st := syncTree(t, db, dir)
-	if st != (scanStats{walked: 2, added: 2}) {
+	if st != (scanStats{added: 2}) {
 		t.Fatalf("first scan stats = %+v, want 2 added", st)
 	}
 
@@ -1252,7 +1091,7 @@ func TestSyncScanUnchangedReuse(t *testing.T) {
 	}
 
 	st = syncTree(t, db, dir)
-	if st != (scanStats{walked: 2, unchanged: 2}) {
+	if st != (scanStats{unchanged: 2}) {
 		t.Fatalf("rescan stats = %+v, want 2 unchanged", st)
 	}
 
@@ -1281,7 +1120,7 @@ func TestSyncScanMtimeBump(t *testing.T) {
 	}
 
 	st := syncTree(t, db, dir)
-	if st != (scanStats{walked: 1, updated: 1}) {
+	if st != (scanStats{updated: 1}) {
 		t.Fatalf("mtime-bump stats = %+v, want 1 updated", st)
 	}
 
@@ -1309,7 +1148,7 @@ func TestSyncScanAddRemove(t *testing.T) {
 	}
 
 	st := syncTree(t, db, dir)
-	if st != (scanStats{walked: 2, added: 1, removed: 1, unchanged: 1}) {
+	if st != (scanStats{added: 1, removed: 1, unchanged: 1}) {
 		t.Fatalf("add/remove stats = %+v, want 1 added 1 removed 1 unchanged",
 			st)
 	}
@@ -1426,7 +1265,7 @@ func TestSyncScanOverlappingRoots(t *testing.T) {
 	// A file reachable via two overlapping operands is deduplicated
 	// by path in the shared walk and processed once.
 	st := syncTree(t, db, dir, filepath.Join(dir, "sub"))
-	if st != (scanStats{walked: 1, added: 1}) {
+	if st != (scanStats{added: 1}) {
 		t.Fatalf("stats = %+v, want 1 added", st)
 	}
 
@@ -1447,7 +1286,7 @@ func TestScanSkipsUniqueSizes(t *testing.T) {
 	// Neither size is shared, so neither file is read: both records
 	// are written without hashes and no duplicates are reported.
 	st := syncTree(t, db, dir)
-	if st != (scanStats{walked: 2, added: 2}) {
+	if st != (scanStats{added: 2}) {
 		t.Fatalf("stats = %+v, want 2 added", st)
 	}
 
@@ -1459,7 +1298,7 @@ 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)
 	}
 
@@ -1469,12 +1308,12 @@ func TestScanSkipsUniqueSizes(t *testing.T) {
 	c := writeFile(t, dir, "c.bin", pattern(1, 500))
 
 	st = syncTree(t, db, dir)
-	if st != (scanStats{walked: 3, added: 1, updated: 1, unchanged: 1}) {
+	if st != (scanStats{added: 1, updated: 1, unchanged: 1}) {
 		t.Fatalf("rescan stats = %+v, want 1 added 1 updated 1 unchanged",
 			st)
 	}
 
-	groups := dupeGroups(t, db)
+	groups := collectDupeGroups(dbRecords(t, db))
 	if len(groups) != 1 {
 		t.Fatalf("groups = %+v, want the a/c pair", groups)
 	}
@@ -1510,7 +1349,8 @@ 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)",
@@ -1533,7 +1373,7 @@ func TestScanHardlinksReadOnce(t *testing.T) {
 	}
 
 	st := syncTree(t, db, dir)
-	if st != (scanStats{walked: 2, added: 2}) {
+	if st != (scanStats{added: 2}) {
 		t.Fatalf("stats = %+v, want 2 added", st)
 	}
 
@@ -1547,7 +1387,7 @@ 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)
 	}
 }
@@ -1655,13 +1495,6 @@ func injectWriteFailure(t *testing.T, path string) {
 func baselineGoroutines(t *testing.T) int {
 	t.Helper()
 
-	// The first scan command in a process starts os/signal's goroutine,
-	// which never exits. Start it now, so the baseline counts it
-	// instead of the scan seeming to leave it behind.
-	ch := make(chan os.Signal, 1)
-	signal.Notify(ch, syscall.SIGINT)
-	signal.Stop(ch)
-
 	deadline := time.Now().Add(goroutineSettle)
 	last := runtime.NumGoroutine()
 
@@ -1795,8 +1628,10 @@ 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

@@ -12,48 +12,39 @@ import (
 	"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.
+// 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, stdout io.Writer) error {
-	dbPath := databasePath()
-
-	db, err := openReportDatabase(ctx, dbPath)
+	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)
 
@@ -91,128 +82,73 @@ 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 +190,38 @@ 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 {
@@ -135,56 +105,6 @@ 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()))
 
@@ -206,7 +126,8 @@ 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 +160,8 @@ 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 +174,8 @@ 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 +199,16 @@ 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 +227,8 @@ 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 +250,8 @@ 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))