Cut the narration from TODO.md and the script and Dockerfile comments (closes #49)

Completed Steps entries keep what landed, the traps, every disclosure
and every record that a check ran; the argument and history go, with
bare issue numbers turned into full links. Comment blocks in script/,
Dockerfile and Dockerfile.lint keep the trap and drop the defence of
past decisions. TODO.md Workflow now branches from next, targets next,
and leaves merging next to main to the owner. Only comments and
Markdown change.

Model: opus-5-5

.golangci.yml

@@ -10,14 +10,20 @@ run:
 
 linters:
   default: all
+  enable:
+    # Successor to the deprecated gomodguard. Named explicitly, rather than
+    # left to `default: all`, because it carries the module policy below.
+    - gomodguard_v2
   disable:
     # Genuinely incompatible with project patterns
     - exhaustruct      # Requires all struct fields
-    - depguard         # Dependency allow/block lists
     - godot            # Requires comments to end with periods
-    - wsl              # Deprecated, replaced by wsl_v5
     - wrapcheck        # Too verbose for internal packages
     - varnamelen       # Short names like db, id are idiomatic Go
+    # Deprecated: the warning is attached to the old name, so it is
+    # silenced by disabling that name, not by enabling the successor.
+    - wsl              # Deprecated, replaced by wsl_v5
+    - gomodguard       # Deprecated, replaced by gomodguard_v2
   settings:
     lll:
       line-length: 88
@@ -28,6 +34,64 @@ linters:
       max-complexity: 15
     dupl:
       threshold: 100
+    depguard:
+      # Test-support code must not be compiled into the shipped binary. A
+      # test-support package exists to hand a test privileges the program
+      # itself must never have, so a file that is not a test must not import
+      # one. Test files, and the files inside a package whose directory name
+      # ends in `test`, are where that code belongs, and are exempt.
+      #
+      # The deny list below is the one part of this file a repository is
+      # expected to extend, and the only part it may. depguard matches an
+      # import path against a list of prefixes, so it cannot be told "any path
+      # whose last segment ends in test"; a repository's own test-support
+      # packages have to be named here one at a time, by full import path,
+      # under a module path that differs from repository to repository. Add
+      # them; change nothing else.
+      rules:
+        test-support:
+          list-mode: lax
+          files:
+            - "$all"
+            - "!$test"
+            - "!**/*test/**"
+          deny:
+            - pkg: net/http/httptest
+              desc: >-
+                Test-support code belongs in test files and in packages whose
+                directory name ends in test, not in the shipped binary.
+    # Only decisions already recorded in the Go package defaults are
+    # listed here. Every entry matches the module path exactly.
+    gomodguard_v2:
+      blocked:
+        - module: github.com/rs/zerolog
+          recommendations:
+            - log/slog
+          reason: "Structured logging is stdlib log/slog."
+        # One entry per pre-fork module path, because the later releases
+        # are separate paths. A prefix match would be shorter but would
+        # also reach github.com/go-redis/redismock, the test double for
+        # the successor these entries recommend.
+        - module: github.com/go-redis/redis
+          recommendations:
+            - github.com/redis/go-redis/v9
+          reason: "Pre-fork module; use the maintained go-redis v9."
+        - module: github.com/go-redis/redis/v7
+          recommendations:
+            - github.com/redis/go-redis/v9
+          reason: "Pre-fork module; use the maintained go-redis v9."
+        - module: github.com/go-redis/redis/v8
+          recommendations:
+            - github.com/redis/go-redis/v9
+          reason: "Pre-fork module; use the maintained go-redis v9."
+        - module: github.com/sergi/go-diff
+          recommendations:
+            - github.com/aymanbagabas/go-udiff
+          reason: "No unified diff output; use go-udiff."
+        - module: github.com/hexops/gotextdiff
+          recommendations:
+            - github.com/aymanbagabas/go-udiff
+          reason: "Unmaintained fork; use go-udiff."
 
 issues:
   max-issues-per-linter: 0

.prettierignore

@@ -0,0 +1,2 @@
+node_modules/
+yarn.lock

.prettierrc

@@ -0,0 +1,4 @@
+{
+    "tabWidth": 4,
+    "proseWrap": "always"
+}

Dockerfile

@@ -6,34 +6,36 @@ COPY go.mod go.sum ./
 RUN go mod download
 COPY . .
 
-# Cache-buster for the gate layers, and only for them. Docker
-# invalidates COPY only when the copied content changes, so on an
-# unchanged tree the gates below would be served from cache and the
-# build would exit 0 having run nothing. script/cibuild and
-# script/docker pass a fresh CHECK_EPOCH on every invocation.
+# Cache-buster for the gate layers, and only for them: on an unchanged
+# tree Docker would serve the gates below from cache and the build would
+# exit 0 having run nothing. script/cibuild and script/docker pass a
+# fresh CHECK_EPOCH; a build without one, such as a bare
+# `docker build .`, fails at the check right after the ARG.
 #
-# Two properties this depends on. ARG is per-stage, so the build stage
-# below declares it again; one declaration here would leave that
-# stage's gate cacheable. And each gate RUN must reference the value,
-# because BuildKit hashes the expanded command: a declared but
-# unreferenced ARG invalidates nothing.
-#
-# It sits below the dependency layers deliberately. Everything above it
-# (the pinned base image, go mod download) keeps its cache; only the
-# gates go cold.
+# ARG is per-stage, so the markdown and build stages declare it again.
+# Each gate RUN must reference the value: BuildKit hashes the expanded
+# command, so a declared but unreferenced ARG invalidates nothing. Keep
+# it below the dependency layers so they stay cached.
 ARG CHECK_EPOCH
+RUN if [ -z "${CHECK_EPOCH}" ]; then \
+        echo "CHECK_EPOCH is unset; build via script/cibuild or script/docker" >&2; \
+        exit 1; \
+    fi
 
-# The linter is invoked directly here, not through `make lint`. That
-# target now runs `docker build -f Dockerfile.lint`, and a docker build
-# cannot run a docker build: routing the gate through make would mean
-# nesting docker inside this image. Same reason `make check` is gone
-# from the build stage below. `make fmt-check` stays as it is — it is a
-# gate, not the aggregate, and it shells out to nothing.
-RUN echo "gate fmt-check, epoch ${CHECK_EPOCH}" && make fmt-check
+# These gates call the tools directly, not through `make lint` or
+# `make fmt-check`: both run docker, which cannot run inside a docker
+# build. This step is the gofmt half of `make fmt-check`; the markdown
+# stage is its prettier half. gofmt's output is assigned to a variable
+# first so that its own exit status, as when it cannot parse a file,
+# still fails the step.
+RUN echo "gate gofmt, epoch ${CHECK_EPOCH}" && \
+    files="$(gofmt -s -l .)" && \
+    if [ -n "$files" ]; then \
+        echo "gofmt: files not formatted:" >&2; echo "$files" >&2; exit 1; \
+    fi
 
-# The FROM above and the one in Dockerfile.lint pin the same linter
-# twice, and nothing else keeps them in sync; this fails the build when
-# they disagree. See the script for why it restates neither pin.
+# Fails the build when the FROM above and the one in Dockerfile.lint pin
+# different linter images.
 RUN echo "gate lint-image-pin, epoch ${CHECK_EPOCH}" && \
     script/verify-lint-image-pin
 
@@ -46,67 +48,104 @@ RUN echo "gate config verify, epoch ${CHECK_EPOCH}" && \
 RUN echo "gate lint, epoch ${CHECK_EPOCH}" && \
     golangci-lint run --config .golangci.yml ./...
 
+# Prettier stage: the prettier that formats this repository's Markdown,
+# never installed on a host. script/fmt and script/fmt-check build this
+# stage alone and run it with the repository mounted on /src. prettier
+# is installed in /tools so that the repository, mounted or copied onto
+# /src, cannot hide it.
+# node:22-alpine, 2026-02-22
+FROM node@sha256:e4bf2a82ad0a4037d28035ae71529873c069b13eb0455466ae0bc13363826e34 AS prettier
+WORKDIR /tools
+# yarn.lock pins prettier by hash, and --frozen-lockfile fails rather
+# than install anything yarn.lock does not name.
+COPY package.json yarn.lock ./
+RUN yarn install --frozen-lockfile
+ENV PATH=/tools/node_modules/.bin:$PATH
+WORKDIR /src
+
+# Markdown stage: the Markdown half of `make fmt-check`, as a gate.
+FROM prettier AS markdown
+COPY . .
+# Second per-stage declaration of the gate cache-buster and its check;
+# see the lint stage above.
+ARG CHECK_EPOCH
+RUN if [ -z "${CHECK_EPOCH}" ]; then \
+        echo "CHECK_EPOCH is unset; build via script/cibuild or script/docker" >&2; \
+        exit 1; \
+    fi
+RUN echo "gate prettier, epoch ${CHECK_EPOCH}" && \
+    prettier --check '**/*.md' --tab-width 4 --prose-wrap always
+
 # Build stage
 # golang:1.25-alpine, 2026-07-23
 FROM golang@sha256:56961d79ea8129efddcc0b8643fd8a5416b4e6228cfd477e3fd61deb2672c587 AS builder
 
 # We never build or run as root. Create an unprivileged user and point
-# 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.
+# HOME and the build cache at its home so go build and go test can write
+# it when we drop to it below.
+#
+# The module cache stays 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
 
-# No-op file copy whose only purpose is the build-graph edge: it is what
-# makes this stage depend on the lint stage, and so what forces BuildKit
-# to finish fmt-check, the pin guard and lint before compilation and
-# tests start. Remove it and the fail-fast design dies silently — the
-# build stops gating on lint and still exits 0. It replaces a copy of
-# the linter binary itself, which is no longer wanted here: nothing in
-# this stage runs the linter, because `make lint` is now a docker build
-# and a docker build cannot run inside one.
+# No-op file copies whose only purpose is the build-graph edge: they
+# make this stage depend on the lint and markdown stages, so BuildKit
+# finishes those gates before compilation and tests start. Remove one
+# and the build silently stops gating on that stage and still exits 0.
 COPY --from=lint /src/go.sum /dev/null
+COPY --from=markdown /src/go.sum /dev/null
 
-# Install development prerequisites the same way a developer does,
-# rather than duplicating the installs inline. Only script/ and the
-# dependency manifests are copied first, nothing else, so this layer
-# stays cached until the scripts or the dependencies change — bootstrap
-# ends in `go mod download`, which is why there is no separate
-# invocation of it here.
+# Install development prerequisites the same way a developer does. Only
+# script/ and the dependency manifests are copied first, so this layer
+# stays cached until they change. Bootstrap ends in `go mod download`.
 COPY script/ script/
 COPY go.mod go.sum ./
 RUN script/bootstrap
 
-COPY . .
+# 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
 
-# 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
+# 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 . .
 USER builder
 
-# Fail the build unless the branch is green. Runs as non-root so the
-# permission-denied test paths are exercised legitimately (root would
-# bypass the chmod(0) the tests rely on).
+# Fail the build unless the branch is green. Runs as non-root: root
+# would bypass the chmod(0) the permission-denied tests rely on.
 #
-# The gates are the individual targets, not `make check`: that aggregate
-# runs `script/lint`, which is now a docker build, and nothing inside an
-# image build may shell out to docker. Lint is not skipped by this — it
-# ran in the lint stage above, which this stage's COPY --from makes a
-# prerequisite. `make`, not the scripts directly, because the Makefile's
+# The gate is `make test`, not `make check`, which runs docker; lint and
+# the format checks ran in the lint and markdown stages above. `make`,
+# not the script directly, because the Makefile's
 # `export CGO_ENABLED = 0` applies only to what it invokes.
 #
-# Second per-stage declaration of the gate cache-buster; see the lint
-# stage above for why one is not enough. It is placed after USER so the
-# drop to the unprivileged user still happens before the checks run.
+# Third per-stage declaration of the gate cache-buster and its check;
+# see the lint stage above. It is placed after USER so the drop to the
+# unprivileged user still happens before the checks run.
 ARG CHECK_EPOCH
+RUN if [ -z "${CHECK_EPOCH}" ]; then \
+        echo "CHECK_EPOCH is unset; build via script/cibuild or script/docker" >&2; \
+        exit 1; \
+    fi
 RUN echo "gate test, epoch ${CHECK_EPOCH}" && make test
-RUN echo "gate fmt-check, epoch ${CHECK_EPOCH}" && make fmt-check
 
 # The version stamped into the binary: the VERSION build argument when
 # one is given, otherwise `git describe --tags --always` of the .git in

Dockerfile.lint

@@ -1,14 +1,12 @@
-# Lint-only image: this is how the linter runs, everywhere. The repo is
-# COPYed into the pinned golangci-lint image and the linter runs as a
-# build step, so a successful build IS a clean lint. golangci-lint is
-# never installed on a host — one toolchain, pinned by digest, identical
-# on a laptop and in CI — and this works even when the docker daemon is
-# remote and bind mounts are impossible.
+# Lint-only image, built by script/lint: the repo is copied into the
+# pinned golangci-lint image and the linter runs as a build step, so a
+# successful build is a clean lint. No bind mount, so it works when the
+# docker daemon is remote.
 #
-# script/lint builds this file. It is a separate image from the lint
-# stage of the main Dockerfile because script/lint must not depend on
-# the rest of that build; the two FROM lines are kept identical by
-# script/verify-lint-image-pin, run as a gate below.
+# It is separate from the main Dockerfile's lint stage because
+# script/lint must not depend on the rest of that build; the two FROM
+# lines are kept identical by script/verify-lint-image-pin, run as a
+# gate below.
 # golangci/golangci-lint:v2.12.2, 2026-08-07
 FROM golangci/golangci-lint@sha256:5cceeef04e53efe1470638d4b4b4f5ceefd574955ab3941b2d9a68a8c9ad5240
 
@@ -20,38 +18,26 @@ RUN go mod download
 
 COPY . .
 
-# Cache-buster for the gate layers, and only for them. Caching of the
-# lint run is waived by ruling: COPY is invalidated only by changed
-# content, so on an unchanged tree the gates below would be served from
-# cache and this build would exit 0 in under a second having run no
-# linter at all. That exact false green has bitten this repo twice
-# already (#32, #39). script/lint passes a fresh value on every
+# Cache-buster for the gate layers, and only for them; caching of the
+# lint run is waived by ruling. On an unchanged tree the gates below
+# would be served from cache and this build would exit 0 in under a
+# second having run no linter. script/lint passes a fresh value on every
 # invocation.
 #
-# Each gate RUN must reference the value, because BuildKit hashes the
-# expanded command and not the ARG declaration: a declared but
-# unreferenced ARG invalidates nothing. The ARG sits below the
-# dependency layers deliberately — everything above it keeps its cache,
-# only the gates go cold.
+# Each gate RUN must reference the value: BuildKit hashes the expanded
+# command, so a declared but unreferenced ARG invalidates nothing. Keep
+# it below the dependency layers so they stay cached.
 ARG CHECK_EPOCH
 
-# The linter version is pinned in two places, here and in the main
-# Dockerfile's lint stage. Nothing else keeps them in sync, so a
-# half-applied bump is a build failure; see the script.
+# Fails the build when the FROM above and the main Dockerfile's lint
+# stage pin different linter images.
 RUN echo "gate lint-image-pin, epoch ${CHECK_EPOCH}" && \
     script/verify-lint-image-pin
 
-# Validates .golangci.yml against golangci-lint's JSON schema. The
-# concern about this step was that it fetches that schema over a live,
-# unpinned HTTPS call; measured on the pinned image, it does not. The
-# binary carries the schema for its own version, so under
-# `--network none` this both passes on a valid config and still rejects
-# an invalid one with the jsonschema error. That holds for the gate
-# steps generally — none of them makes a network call — but not for
-# this build as a whole: `go mod download` above needs the network on a
-# cold cache, and under `--network none` a first build fails there
-# before reaching any gate. That layer stays cached, so only a warm
-# cache lints offline, until go.mod or go.sum changes.
+# Validates .golangci.yml against golangci-lint's JSON schema, which the
+# pinned binary embeds: measured under `--network none`, it passes a
+# valid config and rejects an invalid one. No gate step makes a network
+# call, but `go mod download` above needs the network on a cold cache.
 RUN echo "gate config verify, epoch ${CHECK_EPOCH}" && \
     golangci-lint config verify --config .golangci.yml
 

Makefile

@@ -6,7 +6,7 @@ BINARY := sfdupes
 VERSION := $(shell git describe --tags --always --dirty 2>/dev/null || echo dev)
 LDFLAGS := -X main.Version=$(VERSION)
 
-.PHONY: sfdupes build bootstrap setup test lint fmt fmt-check check docker hooks clean
+.PHONY: sfdupes build bootstrap setup test test-race lint fmt fmt-check check docker hooks clean
 
 # Standard targets are thin shims; the implementations live in script/
 # per the scripts-to-rule-them-all pattern.
@@ -27,6 +27,9 @@ setup:
 test:
 	@script/test
 
+test-race:
+	@script/test-race
+
 lint:
 	@script/lint
 

TODO.md

@@ -1,472 +1,402 @@
 # Workflow
 
-- take an issue from the `1.0.0` milestone on the tracker; work not
-  yet on the tracker gets filed as an issue first
-- branch (from `main`)
+- take an issue from the `1.0.0` milestone on the tracker; work not yet on the
+  tracker gets filed as an issue first
+- branch from `next`
 - do the work, with tests, in small focused commits
-- record it at the top of Completed Steps (`TODO.md` changes in the
-  same commit as the work)
-- push the branch and open a PR whose title ends with
+- record it at the top of Completed Steps (`TODO.md` changes in the same commit
+  as the work)
+- push the branch and open a PR against `next` whose title ends with
   ` (closes #N)`
-- an independent review gates the merge; every finding is addressed
+- an independent review gates each merge to `next`; every finding is addressed
   or explicitly rebutted on the PR
-- merge to `main` once the review passes
+- only the owner merges `next` to `main`
 
 # Status
 
 - pre-1.0
-- the Gitea tracker is authoritative for the pre-1.0 backlog: the
-  open issues under the `1.0.0` milestone are what remains before
-  the tag, and this file records history and process, not the queue
+- the Gitea tracker is authoritative for the pre-1.0 backlog: the open issues
+  under the `1.0.0` milestone are what remains before the tag, and this file
+  records history and process, not the queue
 
 # Next Step
 
 - take the next issue from the `1.0.0` milestone on the tracker:
-  https://git.eeqj.de/sneak/sfdupes/milestone/17 — the milestone is
-  the source of truth for what is left before 1.0.0. Individual
-  issues are deliberately not restated here; a copy in this file
-  drifts out of date the moment the tracker moves
+  https://git.eeqj.de/sneak/sfdupes/milestone/17 — the milestone is the source
+  of truth for what is left before 1.0.0. Individual issues are deliberately not
+  restated here; a copy in this file drifts out of date the moment the tracker
+  moves
 
 # Completed Steps
 
+- cut the narration from `TODO.md` Completed Steps and from the comments in
+  `script/` and both Dockerfiles; §Workflow now branches from and merges to
+  `next` (2026-10-04, https://git.eeqj.de/sneak/sfdupes/issues/49)
+
+- `make test-race` runs the test suite under the race detector in a cgo-enabled
+  container, outside `make check` (2026-10-04,
+  https://git.eeqj.de/sneak/sfdupes/issues/18)
+
+- a bare `docker build .` fails with a message naming `script/cibuild` and
+  `script/docker` instead of serving the gates from cache (2026-10-04,
+  https://git.eeqj.de/sneak/sfdupes/issues/39)
+
+- `make fmt` and `make fmt-check` run prettier over all Markdown, in Docker, and
+  CI checks it; all Markdown reformatted (2026-10-04,
+  https://git.eeqj.de/sneak/sfdupes/issues/19)
+
+- `script/lint` writes no image, so a run no longer leaves an untagged one
+  behind (2026-10-04, https://git.eeqj.de/sneak/sfdupes/issues/48)
+
+- tests cover a missing database, `scan` keeping stdout empty, its skip warning,
+  the `report` and `trees` summary lines, and every subcommand going through
+  `runE` (2026-10-04, https://git.eeqj.de/sneak/sfdupes/issues/16)
+
+- `.golangci.yml` replaced with the current canonical copy, which uses
+  `gomodguard_v2`, so lint no longer prints a deprecation warning (2026-10-04,
+  https://git.eeqj.de/sneak/sfdupes/issues/26)
+
+- a test fails when either `hashWorker` cancellation check in `scan.go` is
+  removed (2026-10-04, https://git.eeqj.de/sneak/sfdupes/issues/83)
+
+- a database path holding `?`, `#` or `%` opens exactly the file it names
+  (2026-10-04, https://git.eeqj.de/sneak/sfdupes/issues/55)
+
+- `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)
+
+- warn about and skip symlink, socket, FIFO, device and `.zfs` operands, keeping
+  the records beneath them (2026-10-03,
+  https://git.eeqj.de/sneak/sfdupes/issues/9)
+
+- `scan` holds a lock on a lock file beside the database for its whole run, so a
+  second `scan` fails at once with exit 1 (2026-10-03,
+  https://git.eeqj.de/sneak/sfdupes/issues/53)
+
 - test stdout write failures in `report` and `trees`; README states that
   `| head` ends sfdupes by `SIGPIPE` and `>&-` writes to `/dev/null`
   (2026-10-03, https://git.eeqj.de/sneak/sfdupes/issues/30)
 
-- escape tabs, newlines, carriage returns and backslashes in report,
-  trees and warning paths; the root directory's path is `/`
-  (2026-10-03, https://git.eeqj.de/sneak/sfdupes/issues/7)
+- `report` and `trees` open the database read-only, and `scan` leaves it out of
+  WAL mode, so reading needs only read access (2026-10-03, closes
+  https://git.eeqj.de/sneak/sfdupes/issues/8)
 
-- stamp the git tag or short commit in a plain `docker build .`
-  instead of `dev` (2026-10-02, branch `next`, closes
-  https://git.eeqj.de/sneak/sfdupes/issues/67): `.dockerignore` now
-  sends `.git`, without `.git/config`, and the `Dockerfile` build
-  stage takes the `VERSION` build argument when one is given,
-  otherwise `git describe --tags --always` of that `.git`. The build
-  fails if the context carries `.git` and the version still comes out
-  empty, `dev` or `unknown`. The CI checkout step fetches the full
-  history (`fetch-depth: 0`) so CI sees the tag and stamps the same
-  value as `make build`.
+- escape tabs, newlines, carriage returns and backslashes in report, trees and
+  warning paths; the root directory's path is `/` (2026-10-03,
+  https://git.eeqj.de/sneak/sfdupes/issues/7)
 
-- replace the 1 KiB end-window sampling with the head/tail plus
-  content-hash ladder (2026-09-22, branch `next`, closes
-  https://git.eeqj.de/sneak/sfdupes/issues/61): a file under 10 MiB is
-  hashed in full and compared directly, with no end-window step — its
-  `head`, `tail`, and `content` all hold the whole-file hash. A file at
-  10 MiB or above gets only the 64 KiB `head` and `tail` in the hash
-  phase; a new content phase, after the update phase, reads it for its
-  `content` hash — the whole file below 50 MiB, gigabyte-spaced 1 MiB
-  samples at or above — only when its size, `head`, and `tail` match
-  another record's, from the same scan or stored by an earlier one, so
-  a stored file gains its content hash when it gains a match. A file
-  that is gone or has changed since its record was written is not
-  read. The `content` column is part of the version 1 schema. `report`
-  and `trees` group by the extended signature and leave out any record
-  without a `content` hash, so the ladder is applied across the whole
-  database. README "Duplicate detection" documents every rung including
-  the probabilistic large-file path.
+- stamp the git tag or short commit in a plain `docker build .` instead of `dev`
+  (2026-10-02, branch `next`, closes
+  https://git.eeqj.de/sneak/sfdupes/issues/67): `.dockerignore` sends `.git`
+  without `.git/config`; the build stage stamps the `VERSION` build argument,
+  else `git describe --tags --always`, and fails if the context carries `.git`
+  and the version is still empty, `dev` or `unknown`. CI checks out the full
+  history (`fetch-depth: 0`) so it stamps the same value as `make build`.
 
-- remove the dead `files.dat` references from `Makefile`, `.gitignore`
-  and `.dockerignore` (2026-09-21, branch `next`, closes
+- replace the 1 KiB end-window sampling with the head/tail plus content-hash
+  ladder (2026-09-22, branch `next`, closes
+  https://git.eeqj.de/sneak/sfdupes/issues/61); README "Duplicate detection"
+  documents every rung. A file under 10 MiB is hashed in full, and its `head`,
+  `tail` and `content` all hold that hash. A larger file gets only its 64 KiB
+  `head` and `tail` in the hash phase; the content phase, after the update
+  phase, reads it for `content` (the whole file below 50 MiB, gigabyte-spaced 1
+  MiB samples at or above) only when its size, `head` and `tail` match another
+  record's from this scan or an earlier one, and never reads a file gone or
+  changed since its record was written. `report` and `trees` leave out any
+  record without a `content` hash. The `content` column is part of the version 1
+  schema.
+
+- remove the dead `files.dat` references from `Makefile`, `.gitignore` and
+  `.dockerignore` (2026-09-21, branch `next`, closes
   https://git.eeqj.de/sneak/sfdupes/issues/22)
 
 - fix the lint-image pin comments and `FROM` form in `Dockerfile` and
   `Dockerfile.lint` (2026-08-10, branch `next`, closes
-  https://git.eeqj.de/sneak/sfdupes/issues/25): dropped the false
-  `(Debian-based)` parenthetical (v2.12.1 was Debian too) and the
-  redundant tag, so both pins are the policy `# image:vX.Y.Z,
-  YYYY-MM-DD` comment over a bare `FROM image@sha256:...`. Digest
-  unchanged. `script/verify-lint-image-pin` parses those `FROM` lines
-  and still matches the tagless form; its advice line lost the now
-  meaningless "tag and digest". With no tag in either reference, a
-  tag-only disagreement no longer exists — a one-sided tag is caught as
-  a plain mismatch.
+  https://git.eeqj.de/sneak/sfdupes/issues/25): both pins are now the policy
+  `# image:vX.Y.Z, YYYY-MM-DD` comment over a bare `FROM image@sha256:...`,
+  without the false `(Debian-based)` note or the tag; digest unchanged.
+  `script/verify-lint-image-pin` still matches the tagless form, and a tag on
+  one side only is caught as a plain mismatch.
 
-- run all linting in Docker via `Dockerfile.lint` and `script/lint`
-  (2026-08-10, branch `next`, closes
-  https://git.eeqj.de/sneak/sfdupes/issues/46): per the owner ruling, the
-  linter runs inside a container invoked through the `script/`
-  entrypoint and is never installed on a host. New root
-  `Dockerfile.lint` COPYs the repo into the digest-pinned
-  `golangci/golangci-lint:v2.12.2` image and runs
-  `golangci-lint config verify` and `golangci-lint run` as build
-  steps, so a successful build IS a clean lint; `script/lint` is
-  reduced to building it. `script/bootstrap` loses the `go install`,
-  the pin constants, the version parser and `verify_golangci_lint`
-  outright rather than hardening them — with nothing linting on the
-  host, the `$GOPATH/bin` versus `PATH` problem that motivated them has
-  no subject — and now warns rather than fails when `docker` is absent.
-  Two traps handled. A lint build on an unchanged tree returns success
-  in well under a second having run no linter, which is
-  https://git.eeqj.de/sneak/sfdupes/issues/32 and
-  https://git.eeqj.de/sneak/sfdupes/issues/39 again, so
-  `Dockerfile.lint` carries `ARG CHECK_EPOCH` referenced
-  inside every gate `RUN` (BuildKit hashes the expanded command, not
-  the declaration) and `script/lint` passes `"$(date +%s)-$$"` — the
-  PID matters because two lint runs land inside the same second easily.
-  And nothing inside an image build may shell out to docker, so the
-  main `Dockerfile`'s lint stage now invokes `golangci-lint` directly
-  instead of `make lint`, and its build stage runs `make test` and
-  `make fmt-check` instead of the `make check` aggregate (`make`, not
-  the scripts bare, because the Makefile's `export CGO_ENABLED = 0`
-  only reaches what it invokes). `COPY --from=lint`
-  `/usr/bin/golangci-lint` is replaced by
-  `COPY --from=lint /src/go.sum /dev/null`: the copied binary was the
-  only edge forcing BuildKit to finish linting before the build stage
-  starts, and dropping it without replacing the edge would have ended
-  fail-fast linting silently under a still-green build. That is
-  canonical `REPO_POLICIES.md:107`'s ordering edge, restored.
-  `ENV PATH=/home/builder/go/bin:$PATH` is gone with the `go install`
-  that justified it. `script/verify-linter-pin` is retired, deleted
-  along with its README entry, because both of its subjects ceased to
-  exist in the same change: it compared a linter binary against
-  `GOLANGCI_LINT_VERSION` in `script/bootstrap`, and there is now
-  neither a binary crossing between stages nor a version pin in
-  bootstrap. The drift it guarded has not gone away, it has moved — the
-  linter is still pinned twice, now as the `FROM` line of
-  `Dockerfile.lint` and the `FROM` line of the `Dockerfile` lint stage,
-  with nothing syncing them, which is exactly what
-  https://git.eeqj.de/sneak/sfdupes/issues/42 made a build failure. Its
-  replacement is one new `script/verify-lint-image-pin`,
-  run as a gate in both files, which compares the two references to
-  each other and deliberately restates neither: a hardcoded expected
-  digest would be a third copy and the same drift one file further out.
-  `golangci-lint config verify` is included per the ruling, and the
-  concern about its unpinned live HTTPS schema fetch was measured
-  rather than assumed — under `--network none` the pinned binary both
-  passes a valid config and rejects an invalid one with the jsonschema
-  error, so it validates from an embedded schema and makes no network
-  call of its own. The README scopes that to the gate steps rather
-  than to linting as a whole: `Dockerfile.lint` runs `go mod download`
-  above them, so a cold cache still needs the network and only a warm
-  one lints offline. Verified: `make lint` green with every `PATH`
-  directory containing a `golangci-lint` removed
-  (`/home/user/go/bin`, `/home/user/.local/bin`, `/usr/local/bin`;
-  `command -v golangci-lint` empty); two consecutive `script/lint` runs
-  on an untouched tree both executed the linter, 27.7s and 28.7s in the
-  lint step under distinct epochs with the `COPY . .` layer `CACHED`
-  above them, at 42.2s and 41.8s wall clock — the no-cache rule was not
-  weakened to shorten that. Negative control: a planted
-  `var unusedIssue46Sentinel = 1` failed `script/lint` with
-  `report.go:173:5: var unusedIssue46Sentinel is unused (unused)`, and
-  failed `make docker` at `[lint 9/9]` with the build stage stopped at
-  `[builder 3/12]` — `COPY --from=lint`, `script/bootstrap`, the test
-  gate and `make build` all zero occurrences — then reverted clean. The
-  drift guard fails on a tag-only disagreement, on a digest-only
-  disagreement, and on an unreadable reference, naming both sides.
-  `make docker` green in 5m35s with all six gates executing under one
-  epoch (lint 37.6s, test 25.2s reporting
-  `ok sneak.berlin/go/sfdupes 1.938s coverage: 88.5%`, not `(cached)`).
-  The non-root quirk still holds: in the builder image with the Go test
-  cache off, `--user 0:0` fails `TestScanHardlinkRunFailsTogether`
-  (exit 1) where the unprivileged user passes (exit 0). Noted for
-  follow-up, not fixed here: `golangci-lint` warns that the
-  `gomodguard` linter is deprecated since v2.12.0 in favour of
-  `gomodguard_v2`.
+- run all linting in Docker via `Dockerfile.lint` and `script/lint` (2026-08-10,
+  branch `next`, closes https://git.eeqj.de/sneak/sfdupes/issues/46): per the
+  owner ruling the linter is never installed on a host. `Dockerfile.lint` copies
+  the repo into the digest-pinned `golangci/golangci-lint:v2.12.2` image and
+  runs `golangci-lint config verify` and `golangci-lint run` as build steps;
+  `script/lint` builds it. `script/bootstrap` no longer installs or pins the
+  linter, and warns rather than fails when `docker` is absent;
+  `ENV PATH=/home/builder/go/bin:$PATH` went with its `go install`.
+  `script/verify-linter-pin` is retired; `script/verify-lint-image-pin`, a gate
+  in both files, compares their two `FROM` lines and restates neither pin.
+  Traps: an unchanged tree lets a lint build pass in under a second having run
+  no linter, so every gate `RUN` references `ARG CHECK_EPOCH` (BuildKit hashes
+  the expanded command) and `script/lint` passes `"$(date +%s)-$$"`, the PID
+  because two runs land in the same second easily. Nothing inside an image build
+  may shell out to docker, so the `Dockerfile` lint stage calls `golangci-lint`
+  directly and the build stage runs `make test` and `make fmt-check` instead of
+  `make check`, through `make` because the Makefile's `export CGO_ENABLED = 0`
+  only reaches what it invokes. `COPY --from=lint /src/go.sum /dev/null`
+  replaces the copied linter binary as the only edge making the build stage wait
+  for lint; dropping it would end fail-fast linting under a still-green build.
+  `golangci-lint config verify`, included per the ruling, validates from an
+  embedded schema with no network call, but `go mod download` above the gates
+  still needs the network on a cold cache. Verified: `make lint` green with no
+  `golangci-lint` on `PATH`; two back-to-back `script/lint` runs on an untouched
+  tree both ran the linter (27.7s and 28.7s in the lint step, `COPY . .`
+  `CACHED` above); a planted unused variable failed `script/lint`, and failed
+  `make docker` at `[lint 9/9]` with the build stage stopped at
+  `[builder 3/12]`; the drift guard fails on a tag-only, a digest-only and an
+  unreadable reference, naming both sides; under `--network none` config verify
+  passes a valid config and rejects an invalid one; `make docker` green in 5m35s
+  with all six gates run under one epoch (lint 37.6s, test 25.2s reporting
+  `ok sneak.berlin/go/sfdupes 1.938s coverage: 88.5%`, not `(cached)`); in the
+  builder image with the Go test cache off, `--user 0:0` still fails
+  `TestScanHardlinkRunFailsTogether` where the unprivileged user passes. Noted
+  for follow-up, not fixed here: `golangci-lint` warns that `gomodguard` is
+  deprecated since v2.12.0 in favour of `gomodguard_v2`.
 
-- install the Docker build stage's prerequisites by running
-  `script/bootstrap` instead of `apk add --no-cache make` inline
-  (2026-08-09, branch `dockerfile-bootstrap`, closes #42): canonical
-  `REPO_POLICIES.md:97` requires it, and the inline install left the
-  build stage maintaining its own notion of the toolchain — exactly
-  the divergence #24 exists to close, one layer down. The stage now
-  copies `script/` plus `go.mod`/`go.sum` and runs `script/bootstrap`,
-  which ends in `go mod download`, so the separate invocation of that
-  is gone. `COPY --from=lint /usr/bin/golangci-lint` stays, and moves
-  above the bootstrap layer. It is the only edge making this stage
-  depend on the lint stage, so deleting it as redundant would end
-  fail-fast linting silently. Letting bootstrap install its own linter
-  here would have reintroduced the second toolchain and paid for a
-  from-source build of it. What makes the two stages provably one
-  toolchain rather than two that happen to agree is a new
-  `script/verify-linter-pin`, run in the build stage on the binary
-  that arrives from the lint stage, before bootstrap: it fails the
-  build naming both versions unless that binary is the version
-  `script/bootstrap` pins. Bootstrap's own check could not serve that
-  purpose — it reinstalls its pin from source and then verifies
-  whatever `PATH` resolves, so drift self-heals silently and a lint
-  stage image bumped on its own would lint at the new version while
-  `make check` ran at the old one, green. The linter version is pinned
-  in two independent places (the lint stage image digest and
-  `GOLANGCI_LINT_VERSION`) and nothing else keeps them in sync, so a
-  half-applied bump is now a build failure. The pin is read out of
-  `script/bootstrap`, which stays the single source of truth; a pin
-  that cannot be read is a hard failure, not a skip. The check needs
-  no `CHECK_EPOCH`: its only inputs are the copied binary and
-  `script/`, so Docker invalidates the layer exactly when a cached
-  result would stop being true, and it is documented with the other
-  entrypoints in the README. `$GOPATH/bin` joins `PATH` because
-  that is where bootstrap's `go install` lands and bootstrap verifies
-  its installs against what `PATH` resolves — nothing in the image is
-  shadowed by it, the directory does not exist until bootstrap runs.
-  Everything added sits above `ARG CHECK_EPOCH`, and the `chown` and
-  `USER builder` still precede `make check`. Verified: the guard fails
-  the build with both versions named when the lint stage's linter is
-  faked to a different version, and an unmodified build still passes
-  it; bootstrap runs clean under Alpine's `sh` and its `apk` branch,
-  installing `git` and `make` and finding the copied
-  linter already at the pin; a second build served the bootstrap and
-  dependency layers `CACHED` while both gates ran with a fresh epoch;
-  a planted `unused` finding failed the build at the lint gate in
-  48.9s with the build stage's `make check` never starting; and the
-  suite run in the image as `--user 0:0` fails
-  `TestScanHardlinkRunFailsTogether`, so the drop to the unprivileged
-  user is still load-bearing. That last check needs the Go test cache
-  disabled — the first attempt reported `ok ... (cached)` as root,
-  reusing the result the build-time run had left in the shared cache,
-  which would have read as a pass. Build wall time, on a shared host
-  running many concurrent builds and so noisy: 2m13s on an unchanged
-  tree, 2m17s and 4m29s for two builds after a source change, 5m14s
-  cold. Only the cold one breaches the policy ceiling, and not because
-  of this change — `chown -R builder:builder /src /home/builder` walks
-  the module cache and re-runs on every source change, and it alone
-  varied between 77s and 210s across those four builds, which is also
-  the whole spread in the totals. The same cold measurement against
-  `main` is 5m03s with a 209s `chown`. Filed as #43
-- bust the Docker layer cache for the gate steps, so `script/cibuild`
-  and `script/docker` cannot report a green they did not earn
-  (2026-08-09, branch `cibuild-cache-bust`, closes #32): both scripts
-  were bare `docker build` invocations with no cache control, and the
-  `Dockerfile` copies the tree before running its gates, so on an
-  unchanged tree Docker served those layers from cache and the build
-  exited 0 having executed nothing. That is not hypothetical here —
-  every merge this repo has done is a non-fast-forward merge of an
-  undiverged branch, so each merge commit's tree is byte-identical to
-  the branch head's and each merge CI run was almost certainly a full
-  cache hit; and PR #31's reviewer found `make docker` returning
-  success as a 17-layer cache hit, catching it only by being
-  suspicious. The fix is `ARG CHECK_EPOCH` with the scripts passing
-  `--build-arg CHECK_EPOCH="$(date +%s)"`. Two details make or break
-  it. `ARG` is scoped per stage and this `Dockerfile` has three gates
-  across two — `make fmt-check` and `make lint` in the lint stage,
-  `make check` in the build stage — so a single declaration would have
-  left one stage silently cacheable; it is declared in both. And
-  BuildKit hashes the expanded command, not the declaration, so a
-  declared-but-unreferenced `ARG` invalidates nothing: each gate `RUN`
-  echoes the epoch, which also puts the value in the build log as
-  evidence the layer really ran. Placement is below the dependency
-  layers on purpose — a build that goes cold every time would be a
-  different bug, not a fix. Verified by running each script twice back
-  to back on an unchanged tree under `BUILDKIT_PROGRESS=plain`: all
-  three gates executed on all four runs, each with a fresh epoch in
-  the log (`script/cibuild` 78.8s then 61.1s; `script/docker` 61.1s
-  then 53.4s), and twelve steps were still served `CACHED` in the
-  steady state — both `go mod download`s, `apk add`, `adduser`, the
-  `chown`, every `go.mod`/`go.sum` and source copy, the linter copy
-  out of the lint stage, and the binary copy into the runtime stage.
-  The lint stage still gates the build stage: with a deliberate
-  `unused` finding planted in the tree, the build failed at
-  `make lint` in 36.1s and the build-stage `make check` never started.
-  The build stage also still drops to the unprivileged `builder` user
-  before `make check`, which the suite depends on rather than merely
-  prefers: forcing the same image to run the tests as root fails
-  `TestScanHardlinkRunFailsTogether`, because root reads straight
-  through the `chmod(0)` the test uses to prove hard links are read
-  once. This is the local fix only; propagating it to the canonical
-  templates is `prompts` #26
-- check the installed golangci-lint version in `script/bootstrap`
-  instead of only its presence (2026-08-09, branch
-  `bootstrap-version-check`, closes #24): `missing golangci-lint` meant
-  any linter already on `PATH` satisfied the check, so the pin was never
-  consulted and the v2.12.2 bump from #3 was inert on every host that
-  already had one — this host ran v2.10.1 against a v2.12.2 pin,
-  `make check` went green, and `make docker` then rejected the same
-  commit with findings the local gate never saw. The version now lives
-  in one place, `GOLANGCI_LINT_VERSION`, with the `go install` module
-  ref derived from it so a bump cannot half-apply; a
-  `golangci_lint_version` helper parses `golangci-lint --version`
-  (taking the field after the word `version` and tolerating an optional
-  leading `v`, which the module ref carries and the binary's output does
-  not), and any version that is not the pin — older, newer, absent or
-  unparseable — is reinstalled. The install is then verified against the
-  binary `PATH` actually resolves: `go install` writes into `GOBIN` (or
-  `GOPATH/bin`) while `make lint` runs whichever `golangci-lint` comes
-  first on `PATH`, so a wrong-version one sitting ahead of it — nix,
-  apt, brew, apk, or the `/usr/local/bin` copy the `Dockerfile` builder
-  stage makes — would swallow the install and leave the local gate
-  disagreeing with CI under an affirmative `bootstrap complete`.
-  Bootstrap now re-reads the effective version after installing and, on
-  a mismatch, prints both paths and both versions to stderr and exits
-  non-zero instead of claiming success; it does not reorder anyone's
-  `PATH` or delete their binary. The `--version` call keeps its stderr
-  connected, so a present-but-broken binary says why rather than
-  reinstalling forever in silence, and is bounded by `timeout(1)` where
-  that exists, so a wedged binary cannot hang bootstrap. `git`, `make`
-  and `go` keep their presence-only checks and now say why in a
-  comment: they are host package-manager tools the repo deliberately
-  does not pin, with `go.mod` governing the language version and the
-  digest-pinned images covering reproducible builds. Verified on this
-  host by bootstrapping from v2.10.1 to v2.12.2 and running it again to
-  a no-op, plus stub runs of the real script under `dash` covering a
-  thirteen-input parse matrix (absent, older, newer, host-style,
-  image-style, leading-`v`, stderr-only, empty, non-zero exit, impostor
-  binary, `(devel)`, trailing `version`), a shadowed install that must
-  exit non-zero, an install destination not on `PATH` at all, `GOBIN`
-  set, and a wedged binary that must hit the timeout; `make check` and
-  `make lint` are clean at v2.12.2, so v2.10.1 was not hiding any
-  findings on `main`
+- install the Docker build stage's prerequisites by running `script/bootstrap`
+  instead of `apk add --no-cache make` inline (2026-08-09, branch
+  `dockerfile-bootstrap`, closes https://git.eeqj.de/sneak/sfdupes/issues/42):
+  the stage copies `script/` plus `go.mod`/`go.sum` and runs `script/bootstrap`,
+  which ends in `go mod download`, so the separate call to it is gone.
+  `COPY --from=lint /usr/bin/golangci-lint` stays and moves above the bootstrap
+  layer: it is the only edge making this stage depend on the lint stage, so
+  deleting it would end fail-fast linting silently. A new
+  `script/verify-linter-pin`, run in the build stage before bootstrap, fails the
+  build naming both versions unless that copied binary is the version
+  `script/bootstrap` pins; a pin it cannot read is a hard failure, not a skip.
+  `$GOPATH/bin` joins `PATH`, where bootstrap's `go install` lands. Everything
+  added sits above `ARG CHECK_EPOCH`, and the `chown` and `USER builder` still
+  precede `make check`. Verified: the guard fails the build with both versions
+  named when the lint stage's linter is faked to another version, and passes an
+  unmodified build; bootstrap runs clean under Alpine's `sh` and `apk`, finding
+  the copied linter already at the pin; a second build served the bootstrap and
+  dependency layers `CACHED` while both gates ran with a fresh epoch; a planted
+  `unused` finding failed the build at the lint gate in 48.9s with the build
+  stage's `make check` never starting; and the suite run in the image as
+  `--user 0:0` fails `TestScanHardlinkRunFailsTogether`, so the drop to the
+  unprivileged user is still needed. That last check needs the Go test cache
+  off: as root it first reported `ok ... (cached)`, reusing the build-time
+  result. Build times on a noisy shared host: 2m13s on an unchanged tree, 2m17s
+  and 4m29s after a source change, 5m14s cold, which breaches the policy
+  ceiling; `chown -R builder:builder /src /home/builder` walks the module cache
+  and alone varied from 77s to 210s across those builds, and `main` measured
+  5m03s cold with a 209s `chown`. Filed as
+  https://git.eeqj.de/sneak/sfdupes/issues/43
+- bust the Docker layer cache for the gate steps, so `script/cibuild` and
+  `script/docker` cannot report a green they did not earn (2026-08-09, branch
+  `cibuild-cache-bust`, closes https://git.eeqj.de/sneak/sfdupes/issues/32): the
+  `Dockerfile` copies the tree before its gates, so on an unchanged tree Docker
+  served them from cache and the build exited 0 having run nothing. Both scripts
+  now pass `--build-arg CHECK_EPOCH="$(date +%s)"`. `ARG` is per stage and the
+  gates span two stages, so it is declared in both; BuildKit hashes the expanded
+  command, so each gate `RUN` echoes the epoch, which also logs it as evidence
+  the layer ran. It sits below the dependency layers so they stay cached.
+  Verified under `BUILDKIT_PROGRESS=plain`, each script run twice back to back
+  on an unchanged tree: all three gates ran on all four runs with a fresh epoch
+  (`script/cibuild` 78.8s then 61.1s; `script/docker` 61.1s then 53.4s), and
+  thirteen steps were still served `CACHED`. With a planted `unused` finding the
+  build failed at `make lint` in 36.1s and the build-stage `make check` never
+  started. Run as root, the same image fails `TestScanHardlinkRunFailsTogether`,
+  because root reads through the `chmod(0)` the test relies on, so the build
+  stage must drop to the unprivileged `builder` user. Local fix only;
+  propagating it to the canonical templates is
+  https://git.eeqj.de/sneak/prompts/issues/26
+- check the installed golangci-lint version in `script/bootstrap` instead of
+  only its presence (2026-08-09, branch `bootstrap-version-check`, closes
+  https://git.eeqj.de/sneak/sfdupes/issues/24): the version lives only in
+  `GOLANGCI_LINT_VERSION`, with the `go install` module ref derived from it, and
+  any installed version that is not the pin — older, newer, absent or
+  unparseable — is reinstalled. `go install` writes into `GOBIN` (or
+  `GOPATH/bin`) while `make lint` runs the first `golangci-lint` on `PATH`, so
+  bootstrap re-reads the effective version after installing and, on a mismatch,
+  prints both paths and both versions and exits non-zero; it does not reorder
+  `PATH` or delete anyone's binary. The `--version` call keeps its stderr and is
+  bounded by `timeout(1)` where that exists. `git`, `make` and `go` keep
+  presence-only checks. Verified by bootstrapping this host from v2.10.1 to
+  v2.12.2 and again to a no-op, and by stub runs of the script under `dash`
+  covering a thirteen-input version-parse matrix, a shadowed install that must
+  exit non-zero, an install destination not on `PATH`, `GOBIN` set, and a wedged
+  binary that must hit the timeout; `make check` and `make lint` are clean at
+  v2.12.2, so v2.10.1 was not hiding any findings on `main`
 - unwind the hash worker pool on the error path (2026-08-09, branch
-  `hash-pool-cleanup`, closes #6): `hashPhase` used to return the
-  moment `recordRun` failed and abandon the pool — the feeder parked
-  forever on a full `jobs` channel and every worker on a full
-  `results` channel. That only stopped being invisible when #4 landed
-  and `runScan` began unwinding instead of calling `os.Exit`. The
-  pool is now an owned, context-aware `hashPool`: every blocking send
-  in the feeder and the workers selects on `ctx.Done()`, `jobs` is
-  closed on every path out, and `hashPhase` defers `pool.stop()`,
-  which cancels and then drains `results` until the last goroutine
-  has exited — draining is what frees a worker already parked on a
-  send. `ctx` is threaded from `cmd.Context()` through `runScan`,
-  `syncScan`, both worker pools and the whole database layer (it is
-  the first parameter everywhere), so #5 can hand this path a signal
-  and needs to add nothing else. The walk pool never leaked, because
-  `walkPhase` always drains its events to close, but it has the same
-  unbounded-send shape and #5 will give it an early return, so it
-  gets the same treatment plus a `ctx.Err()` guard after the walk: a
-  cancelled walk yields a partial size census, and every file it never
-  reached looks vanished to the update phase. That phase's own
-  `BeginTx` fails on the same cancelled context before deleting
-  anything, so the guard is defence in depth rather than the only
-  barrier — but it is the one that survives #5 deciding an interrupted
-  scan may commit what it has. Tests drive `run(scan)` against a
-  database whose insert trigger aborts, and assert both that the scan
-  fails instead of hanging and that `runtime.NumGoroutine()` polls
-  back to its pre-scan baseline; a second set cancels a scan part-way
-  through the walk — deterministically, by counting the scan's own
-  consultations of `ctx.Done()` rather than racing a timer — and
-  asserts that it stops at the guard holding a partial census and a
-  still-populated record index, with every record intact. The
-  remaining cancellation branches of both pools are covered by direct
-  tests of `sendEvent`, the walk workers, `dispatchDirs`,
-  `feedHashJobs`, `hashWorker` and `hashPhase`
-- guarantee the database is closed on every fatal exit path
-  (2026-08-09, branch `db-close-on-fatal`, closes #4): `fatalf` and
-  its `os.Exit(1)` are gone, so the deferred `db.Close()` — and with
-  it the SQLite WAL checkpoint — now actually runs when a subcommand
-  fails; `runScan`, `runReport`, `runTrees`, `loadRecords` and
-  `resolveRoots` return errors instead. The single exit point is `run`
-  in `main.go`: it maps a `fatalError` (anything a subcommand
-  returned) to exit 1 and cobra's own argument and flag errors to exit
-  2, which keeps a runtime failure from being reported as a usage
-  error or printing the usage text. New `main_test.go` drives the CLI
-  in-process and asserts the exit codes from README §Error handling
-  plus the stdout/stderr split, including that a fatal error raised
-  after the database is open leaves no `-wal`/`-shm` sidecar behind
-  for `scan`, `report` or `trees`
-- update golangci-lint to v2.12.2 with the canonical config
-  (2026-08-09, branch `golangci-v2.12.2`, merged as `38a01bd`,
-  closes #3): bumped the pinned linter in the `Dockerfile` lint
-  stage and `script/bootstrap` from v2.12.1 to v2.12.2, and replaced
-  `.golangci.yml` with the canonical file — the linter settings
-  (`lll`, `funlen`, `cyclop`, `dupl` thresholds) now live under
-  `linters.settings` per the v2 schema, so they are actually
-  applied; no new lint findings surfaced
-- convert Makefile targets to scripts-to-rule-them-all `script/`
-  entrypoints like the other managed repos (2026-07-26, commit
-  `3abeacf`, closes #1): all 12 `script/` entrypoints exist
-  (`bootstrap`, `setup`, `projectname`, `test`, `lint`, `fmt`,
-  `fmt-check`, `check`, `docker`, `cibuild`, `precommit`,
-  `install-precommit`) and every Makefile target is now a thin shim
-  over them, matching the other managed repos
+  `hash-pool-cleanup`, closes https://git.eeqj.de/sneak/sfdupes/issues/6): the
+  pool is now an owned, context-aware `hashPool`: every blocking send in the
+  feeder and the workers selects on `ctx.Done()`, `jobs` is closed on every path
+  out, and `hashPhase` defers `pool.stop()`, which cancels and then drains
+  `results` until the last goroutine has exited — draining is what frees a
+  worker already parked on a send. `ctx` is threaded from `cmd.Context()`
+  through `runScan`, `syncScan`, both worker pools and the whole database layer,
+  as the first parameter everywhere. The walk pool gets the same treatment plus
+  a `ctx.Err()` guard after the walk: a cancelled walk yields a partial size
+  census, and every file it never reached looks vanished to the update phase.
+  That phase's own `BeginTx` also fails on the cancelled context before deleting
+  anything, but the guard is the barrier that still holds once an interrupted
+  scan may commit what it has. Tests drive `run(scan)` against a database whose
+  insert trigger aborts and assert that the scan fails instead of hanging and
+  that `runtime.NumGoroutine()` polls back to its pre-scan baseline; others
+  cancel a scan part-way through the walk, deterministically, by counting its
+  own consultations of `ctx.Done()`, and assert that it stops at the guard
+  holding a partial census and a still-populated record index, with every record
+  intact. Direct tests of `sendEvent`, the walk workers, `dispatchDirs`,
+  `feedHashJobs`, `hashWorker` and `hashPhase` cover the remaining cancellation
+  branches of both pools
+- guarantee the database is closed on every fatal exit path (2026-08-09, branch
+  `db-close-on-fatal`, closes https://git.eeqj.de/sneak/sfdupes/issues/4):
+  `fatalf` and its `os.Exit(1)` are gone, so the deferred `db.Close()` — and
+  with it the SQLite WAL checkpoint — now actually runs when a subcommand fails;
+  `runScan`, `runReport`, `runTrees`, `loadRecords` and `resolveRoots` return
+  errors instead. The single exit point is `run` in `main.go`: it maps a
+  `fatalError` (anything a subcommand returned) to exit 1 and cobra's own
+  argument and flag errors to exit 2, which keeps a runtime failure from being
+  reported as a usage error or printing the usage text. New `main_test.go`
+  drives the CLI in-process and asserts the exit codes from README §Error
+  handling plus the stdout/stderr split, including that a fatal error raised
+  after the database is open leaves no `-wal`/`-shm` sidecar behind for `scan`,
+  `report` or `trees`
+- update golangci-lint to v2.12.2 with the canonical config (2026-08-09, branch
+  `golangci-v2.12.2`, merged as `38a01bd`, closes
+  https://git.eeqj.de/sneak/sfdupes/issues/3): bumped the pinned linter in the
+  `Dockerfile` lint stage and `script/bootstrap` from v2.12.1 to v2.12.2, and
+  replaced `.golangci.yml` with the canonical file — the linter settings (`lll`,
+  `funlen`, `cyclop`, `dupl` thresholds) now live under `linters.settings` per
+  the v2 schema, so they are actually applied; no new lint findings surfaced
+- convert Makefile targets to scripts-to-rule-them-all `script/` entrypoints
+  like the other managed repos (2026-07-26, commit `3abeacf`, closes
+  https://git.eeqj.de/sneak/sfdupes/issues/1): all 12 `script/` entrypoints
+  exist (`bootstrap`, `setup`, `projectname`, `test`, `lint`, `fmt`,
+  `fmt-check`, `check`, `docker`, `cibuild`, `precommit`, `install-precommit`)
+  and every Makefile target is now a thin shim over them
 - make the binary the default Make target (2026-07-24, branch
-  `make-default-target`): plain `make` now builds `sfdupes`
-  (previously it ran `check` plus `build`); `make build` remains as
-  an alias
-- scan-wide phases, concurrent operands, batched updates (2026-07-24,
-  branch `scan-wide-phases`): all operands seed the shared walk pool
-  and every pass runs once over the whole scan, so totals and ETAs
-  are scan-global; the per-operand walk/hash/update cycles and their
-  stderr announcements are gone; the update pass commits in batched
-  transactions — the filesystem is authoritative and the database an
-  eventually-consistent reflection, so scan-level atomicity is not
-  required
+  `make-default-target`): plain `make` now builds `sfdupes` (previously it ran
+  `check` plus `build`); `make build` remains as an alias
+- scan-wide phases, concurrent operands, batched updates (2026-07-24, branch
+  `scan-wide-phases`): all operands seed the shared walk pool and every pass
+  runs once over the whole scan, so totals and ETAs are scan-global; the
+  per-operand walk/hash/update cycles and their stderr announcements are gone;
+  the update pass commits in batched transactions — the filesystem is
+  authoritative and the database an eventually-consistent reflection, so
+  scan-level atomicity is not required
 - split the stat pass back out of the walk (2026-07-24, branch
-  `parallel-phases`): phases are strictly sequential again — walk,
-  stat, hash, update per operand — with parallelism only inside each
-  phase; the walk enumerates paths with per-directory workers and the
-  stat pass lstats them with per-file workers, restoring the exact
-  total/ETA stat bar
-- announce each operand on stderr before its passes (2026-07-24,
-  branch `scan-operand-progress`): with per-operand walk/hash/update
-  cycles, a multi-operand run (e.g. `scan /srv/*`) showed pass totals
-  that looked like the whole run's — an operator watching operand 3 of
-  14 hash 300k files concluded 20M files were being skipped
-- parallel walk (2026-07-24, branch `parallel-walk`): the walk pass
-  was a single goroutine and took hours at ~20M files on a busy pool
-  (observed: 22M files in 4h on a ZFS server); it is now a
-  per-directory worker-pool traversal that records size/mtime during
-  the walk (folding away the separate stat pass, halving metadata
-  I/O), and each `PATH` operand commits in its own transaction so an
-  interrupted scan keeps completed operands
+  `parallel-phases`): phases are strictly sequential again — walk, stat, hash,
+  update per operand — with parallelism only inside each phase; the walk
+  enumerates paths with per-directory workers and the stat pass lstats them with
+  per-file workers, restoring the exact total/ETA stat bar
+- announce each operand on stderr before its passes (2026-07-24, branch
+  `scan-operand-progress`): with per-operand walk/hash/update cycles, a
+  multi-operand run (e.g. `scan /srv/*`) showed pass totals that looked like the
+  whole run's
+- parallel walk (2026-07-24, branch `parallel-walk`): the walk pass was a single
+  goroutine and took hours at ~20M files on a busy pool (observed: 22M files in
+  4h on a ZFS server); it is now a per-directory worker-pool traversal that
+  records size/mtime during the walk (folding away the separate stat pass,
+  halving metadata I/O), and each `PATH` operand commits in its own transaction
+  so an interrupted scan keeps completed operands
 
-- persistent scan database (2026-07-24, branch `persistent-database`):
-  `scan` now maintains a SQLite database (`modernc.org/sqlite`, pure
-  Go, cgo stays disabled) keyed by absolute path that survives between
-  runs — a rescan hashes only new or changed files (by mtime/size),
-  deletes records for files vanished from under the scanned operands,
-  and leaves records outside them untouched, so `scan` can be cronned
-  daily; `report` and `trees` read the database (no positional
-  arguments) instead of a scan stream. Database at
-  `/var/lib/sfdupes/db.sqlite`, overridable via `SFDUPES_DATABASE`;
-  WAL journaling plus a single-transaction update keep a report run
-  during a scan safe
-- add the `origin` remote (`git@git.eeqj.de:sneak/sfdupes.git`), tag
-  `v0.0.1`, and push `main` plus tags (2026-07-23)
+- persistent scan database (2026-07-24, branch `persistent-database`): `scan`
+  now maintains a SQLite database (`modernc.org/sqlite`, pure Go, cgo stays
+  disabled) keyed by absolute path that survives between runs — a rescan hashes
+  only new or changed files (by mtime/size), deletes records for files vanished
+  from under the scanned operands, and leaves records outside them untouched, so
+  `scan` can be cronned daily; `report` and `trees` read the database (no
+  positional arguments) instead of a scan stream. Database at
+  `/var/lib/sfdupes/db.sqlite`, overridable via `SFDUPES_DATABASE`; WAL
+  journaling plus a single-transaction update keep a report run during a scan
+  safe
+- add the `origin` remote (`git@git.eeqj.de:sneak/sfdupes.git`), tag `v0.0.1`,
+  and push `main` plus tags (2026-07-23)
 - `scan` CLI rework (2026-07-23, branch `scan-required-paths`): required
-  `PATH...` operands via cobra flags replacing the `/srv` `-root`
-  default; new `-x`/`--one-file-system` flag (GNU convention) to stop
-  at filesystem boundaries, which are crossed by default
+  `PATH...` operands via cobra flags replacing the `/srv` `-root` default; new
+  `-x`/`--one-file-system` flag (GNU convention) to stop at filesystem
+  boundaries, which are crossed by default
 - bring the repo into full policy compliance (2026-07-23, branch
   `repo-policy-compliance`; checklist below)
-- `git init` with README-only first commit; code baseline committed on
-  `main` (2026-07-22)
+- `git init` with README-only first commit; code baseline committed on `main`
+  (2026-07-22)
 - implement `scan`, `report`, and `trees` subcommands (pre-git history)
 
 # Future Steps
 
-- possible later features (explicitly out of scope per README):
-  full-content verification of candidates, removal-script helpers
+- possible later features (explicitly out of scope per README): full-content
+  verification of candidates, removal-script helpers
 
 # Repo Policy Compliance
 
-Audited 2026-07-22 against `REPO_POLICIES.md` (2026-07-06), the existing
-repo checklist, and the Go styleguide. Code is already gofmt-clean, so no
-standalone formatting commit is needed.
+Audited 2026-07-22 against `REPO_POLICIES.md` (2026-07-06), the existing repo
+checklist, and the Go styleguide. Code is already gofmt-clean, so no standalone
+formatting commit is needed.
 
-- [x] `.gitignore` missing — the compiled `sfdupes` binary and
-      `files.dat` sit untracked in the tree; needs OS/editor/Go
-      artifacts plus secrets patterns
+- [x] `.gitignore` missing — the compiled `sfdupes` binary and `files.dat` sit
+      untracked in the tree; needs OS/editor/Go artifacts plus secrets patterns
 - [x] `.editorconfig` missing
-- [x] `LICENSE` missing and README has no License section (MIT assumed
-      from house convention — user to confirm)
+- [x] `LICENSE` missing and README has no License section (MIT assumed from
+      house convention — user to confirm)
 - [x] `REPO_POLICIES.md` missing from repo root
-- [x] `.golangci.yml` missing (install canonical copy); code must then
-      pass `make lint` (150 findings fixed; `make lint` is clean)
-- [x] `Makefile` lacks required targets `test`, `lint`, `fmt`,
-      `fmt-check`, `docker`, `hooks`; `check` currently depends on
-      `build`, which writes the binary (`make check` must not modify
-      files)
-- [x] no tests — `go test ./...` has nothing to run; policy requires
-      real tests with a 30-second timeout and the conditional `-v`
-      rerun pattern (suite covers parsing, grouping, digests,
-      suppression, hashing, and the scan pipeline; 64% coverage)
-- [x] `Dockerfile` missing — Go multistage with hash-pinned images:
-      fail-fast lint stage, build stage running `make check`
+- [x] `.golangci.yml` missing (install canonical copy); code must then pass
+      `make lint` (150 findings fixed; `make lint` is clean)
+- [x] `Makefile` lacks required targets `test`, `lint`, `fmt`, `fmt-check`,
+      `docker`, `hooks`; `check` currently depends on `build`, which writes the
+      binary (`make check` must not modify files)
+- [x] no tests — `go test ./...` has nothing to run; policy requires real tests
+      with a 30-second timeout and the conditional `-v` rerun pattern (suite
+      covers parsing, grouping, digests, suppression, hashing, and the scan
+      pipeline; 64% coverage)
+- [x] `Dockerfile` missing — Go multistage with hash-pinned images: fail-fast
+      lint stage, build stage running `make check`
 - [x] `.dockerignore` missing
-- [x] `.gitea/workflows/check.yml` missing (`docker build .` on push,
-      checkout action pinned by commit SHA)
+- [x] `.gitea/workflows/check.yml` missing (`docker build .` on push, checkout
+      action pinned by commit SHA)
 - [x] README lacks required sections: Description first line
-      (name/purpose/category/license/author), Getting Started,
-      Rationale, TODO, License, Author
-- [x] README non-goal "no git repository setup and no CI" is stale now
-      that the repo is under git with CI
-- [x] pre-commit hook not installed (`make hooks` once the target
-      exists)
+      (name/purpose/category/license/author), Getting Started, Rationale, TODO,
+      License, Author
+- [x] README non-goal "no git repository setup and no CI" is stale now that the
+      repo is under git with CI
+- [x] pre-commit hook not installed (`make hooks` once the target exists)
 
 Accepted divergences (no action):
 
-- flat single-package layout with `.go` files in the repo root — fine
-  for a small single-binary tool per the Go styleguide; the tracker
-  audit agrees
-- `go test` runs without `-race` — the repo mandates `CGO_ENABLED=0`
-  (pure-Go builds) and the race detector requires cgo
+- flat single-package layout with `.go` files in the repo root — fine for a
+  small single-binary tool per the Go styleguide; the tracker audit agrees
+- `make test` runs without `-race` — the repo mandates `CGO_ENABLED=0` (pure-Go
+  builds) and the race detector requires cgo, so the detector runs in a separate
+  cgo-enabled container, `make test-race`, which is not part of `make check`

cancel_test.go

@@ -4,20 +4,35 @@ import (
 	"context"
 	"database/sql"
 	"errors"
+	"fmt"
 	"os"
+	"os/signal"
 	"path/filepath"
+	"slices"
 	"strconv"
+	"strings"
 	"sync"
 	"sync/atomic"
+	"syscall"
 	"testing"
 	"time"
 )
 
-// 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.
+// 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.
 const poolUnwind = 2 * time.Second
 
 // walkClock is a context whose cancellation is driven by the scan's
@@ -28,9 +43,14 @@ 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, while
-// the index load that runs ahead of it spends a small fixed number
-// (three) whatever the record count.
+// 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.
 type walkClock struct {
 	n    int64
 	seen atomic.Int64
@@ -90,7 +110,10 @@ const (
 	walkCancelFilesPerDir = 20
 	walkCancelFiles       = walkCancelDirs * walkCancelFilesPerDir
 	walkCancelWorkers     = 4
-	walkCancelInFlightDirs = walkCancelWorkers * walkCancelFilesPerDir
+	// 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
 )
 
 // walkCancelAtDone is the consultation on which the fixture's context
@@ -150,9 +173,13 @@ 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 a later
-// phase and fail there instead, with a wrapped error rather than the
-// bare cancellation.
+// 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.
 //
 //nolint:paralleltest // counts goroutines: must not run beside others
 func TestSyncScanCancelledMidWalkKeepsRecords(t *testing.T) {
@@ -182,10 +209,10 @@ 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 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.
+// 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.
 func assertWalkGuardAborted(t *testing.T, st scanStats, err error) {
 	t.Helper()
 
@@ -194,12 +221,6 @@ 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)
@@ -211,10 +232,11 @@ func assertWalkGuardAborted(t *testing.T, st scanStats, err error) {
 	}
 
 	// The workers drop every directory still queued once the scan is
-	// 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
+	// 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
 	if st.unchanged > limit {
 		t.Errorf("census covers %d files, want at most %d: the walk kept "+
 			"taking directories off the queue after cancellation",
@@ -260,6 +282,252 @@ 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 and nothing on
+// stdout, 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)
+
+	stdout := captureStdout(t)
+	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)
+	}
+
+	if got := stdout(); got != "" {
+		t.Errorf("stdout = %q, want nothing (data only)", got)
+	}
+
+	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, write nothing to stdout, 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)
+
+	stdout := captureStdout(t)
+	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)
+	}
+
+	if got := stdout(); got != "" {
+		t.Errorf("stdout = %q, want nothing (data only)", got)
+	}
+
+	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
@@ -328,20 +596,49 @@ func TestSendEventAbandonsBlockedSend(t *testing.T) {
 	awaitReturn(t, done, "sendEvent")
 }
 
-// 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.
-func TestWalkWorkersDropQueuedDirs(t *testing.T) {
+// 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()
-	writeEmptyFiles(t, dir, walkCancelFilesPerDir)
+
+	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.
+func TestWalkWorkersDropQueuedDirs(t *testing.T) {
+	t.Parallel()
+
+	missing := filepath.Join(t.TempDir(), "missing")
 
 	jobs, _, events := startWalkWorkers(cancelledContext(t), 2, false)
 
-	for range 4 {
-		jobs <- dirJob{path: dir}
+	for range 64 {
+		jobs <- dirJob{path: missing}
 	}
 
 	close(jobs)
@@ -412,7 +709,11 @@ 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.
+// 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.
 func TestFeedHashJobsClosesJobsWhenCancelled(t *testing.T) {
 	t.Parallel()
 
@@ -438,41 +739,84 @@ func TestFeedHashJobsClosesJobsWhenCancelled(t *testing.T) {
 // TestHashWorkerDropsQueuedRuns checks that a cancelled hash worker
 // keeps reading jobs and drops the runs rather than reading files
 // 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.
+// so the pool tears down. The hash function records that it was
+// called, so a worker that hashed the queued run anyway is caught
+// every time.
 func TestHashWorkerDropsQueuedRuns(t *testing.T) {
 	t.Parallel()
 
 	done := make(chan struct{})
 	jobs := make(chan []fileRec, 1)
-	results := make(chan hashResult, 1)
+	results := make(chan hashResult)
 
-	run := []fileRec{{path: filepath.Join(t.TempDir(), "missing"), size: 1}}
-
-	jobs <- run
+	jobs <- []fileRec{{path: filepath.Join(t.TempDir(), "missing"), size: 1}}
 
 	close(jobs)
 
+	var hashed atomic.Bool
+
+	hash := func(path string, size int64) (string, string, string, error) {
+		hashed.Store(true)
+
+		return hashSignature(path, size)
+	}
+
 	go func() {
 		defer close(done)
 
-		hashWorker(cancelledContext(t), jobs, results, hashSignature)
+		hashWorker(cancelledContext(t), jobs, results, hash)
 	}()
 
 	awaitReturn(t, done, "hashWorker")
 
-	select {
-	case r := <-results:
-		t.Errorf("cancelled hash worker produced %+v, want the run dropped",
-			r)
-	default:
+	if hashed.Load() {
+		t.Error("cancelled hash worker hashed the queued run, want it dropped")
 	}
 }
 
+// TestHashWorkerAbandonsBlockedSend checks that a hash worker with a
+// result to deliver and nobody to deliver it to leaves once the scan
+// is cancelled, instead of holding the pool open. The scan tests do
+// not catch this: stop drains results, which frees a parked worker
+// anyway.
+func TestHashWorkerAbandonsBlockedSend(t *testing.T) {
+	t.Parallel()
+
+	ctx, cancel := context.WithCancel(t.Context())
+	defer cancel()
+
+	done := make(chan struct{})
+	jobs := make(chan []fileRec, 1)
+	// Unbuffered and unread, with jobs left open: the worker's only way
+	// out is the cancellation case beside its send.
+	results := make(chan hashResult)
+
+	jobs <- []fileRec{{path: filepath.Join(t.TempDir(), "missing"), size: 1}}
+
+	// The scan is cancelled while the worker hashes, so the worker has
+	// already passed the check that drops queued runs.
+	hash := func(path string, size int64) (string, string, string, error) {
+		cancel()
+
+		return hashSignature(path, size)
+	}
+
+	go func() {
+		defer close(done)
+
+		hashWorker(ctx, jobs, results, hash)
+	}()
+
+	awaitReturn(t, done, "hashWorker")
+}
+
 // 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.
+// 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.
 func TestHashPhaseCancelledReturnsContextError(t *testing.T) {
 	t.Parallel()
 

db.go

@@ -6,11 +6,13 @@ import (
 	"errors"
 	"fmt"
 	"io/fs"
+	"net/url"
 	"os"
 	"path/filepath"
 	"slices"
 	"strconv"
 
+	"golang.org/x/sys/unix"
 	// The pure-Go SQLite driver, registered as "sqlite"; keeps cgo
 	// disabled.
 	_ "modernc.org/sqlite"
@@ -32,6 +34,11 @@ const schemaVersion = 1
 // scan.
 const dbDirPerm = 0o755
 
+// lockFilePerm is the mode for the scan lock file. Anyone who can open
+// the file can hold the lock and keep every scan from running, so it
+// is open to its owner only.
+const lockFilePerm = 0o600
+
 // createTableSQL is the schema applied to a fresh database. Paths are
 // BLOBs because Unix paths are raw bytes, not guaranteed UTF-8.
 const createTableSQL = `
@@ -45,6 +52,12 @@ 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 = `
@@ -64,6 +77,10 @@ var errNoDatabase = errors.New(
 // does not understand.
 var errSchemaVersion = errors.New("unsupported database schema version")
 
+// errScanRunning reports that another scan holds the lock on the
+// database.
+var errScanRunning = errors.New("another scan is running")
+
 // databasePath resolves the database location: SFDUPES_DATABASE when
 // set and non-empty, the compiled-in default otherwise.
 func databasePath() string {
@@ -74,16 +91,36 @@ func databasePath() string {
 	return defaultDatabasePath
 }
 
-// openDB opens the SQLite database at path with WAL journaling and a
-// busy timeout, so a report can run while a cron scan is in progress.
-// It does not create or verify the schema.
-func openDB(path string) (*sql.DB, error) {
-	dsn := "file:" + path +
-		"?_pragma=busy_timeout(10000)" +
+// scanParams are the connection parameters for scan: read-write, with
+// WAL journaling and a busy timeout, so a report can run while a cron
+// scan is in progress. closeScanDatabase leaves WAL mode again.
+const scanParams = "_pragma=busy_timeout(10000)" +
 	"&_pragma=journal_mode(WAL)" +
 	"&_pragma=synchronous(NORMAL)"
 
-	db, err := sql.Open("sqlite", dsn)
+// reportParams are the connection parameters for report and trees:
+// read-only, with the same busy timeout. They set no journal mode,
+// because setting one is a write.
+const reportParams = "mode=ro" +
+	"&_pragma=busy_timeout(10000)" +
+	"&_pragma=query_only(1)"
+
+// openDB opens the SQLite database at path with the connection
+// parameters params. It does not create or verify the schema.
+func openDB(path, params string) (*sql.DB, error) {
+	// The path is escaped into a file: URI, so ?, # and % in it stay
+	// part of the file name. SQLite reads what follows file:// up to
+	// the next / as a host name, so an absolute path goes after an
+	// empty host (file:///abs) and a relative path goes without one
+	// (file:rel).
+	uri := url.URL{
+		Scheme:   "file",
+		OmitHost: !filepath.IsAbs(path),
+		Path:     path,
+		RawQuery: params,
+	}
+
+	db, err := sql.Open("sqlite", uri.String())
 	if err != nil {
 		return nil, fmt.Errorf("open database %s: %w", path, err)
 	}
@@ -96,6 +133,43 @@ func openDB(path string) (*sql.DB, error) {
 	return db, nil
 }
 
+// lockScanDatabase takes the lock that keeps a second scan off the
+// database at path: an exclusive flock(2) on the file beside it named
+// path with ".lock" appended, created along with the database's parent
+// directory if missing. A lock held by another scan fails at once
+// instead of waiting. The lock lasts until the returned file is closed
+// or the process ends. The file is never deleted: a scan that deleted
+// it would let the next scan lock a new file while another still holds
+// the old one.
+func lockScanDatabase(path string) (*os.File, error) {
+	err := os.MkdirAll(filepath.Dir(path), dbDirPerm)
+	if err != nil {
+		return nil, fmt.Errorf("create database directory: %w", err)
+	}
+
+	lockPath := path + ".lock"
+
+	//nolint:gosec // the operator chooses the database path
+	f, err := os.OpenFile(lockPath, os.O_RDWR|os.O_CREATE, lockFilePerm)
+	if err != nil {
+		return nil, err
+	}
+
+	err = unix.Flock(int(f.Fd()), unix.LOCK_EX|unix.LOCK_NB)
+	if err != nil {
+		_ = f.Close()
+
+		if errors.Is(err, unix.EWOULDBLOCK) {
+			return nil, fmt.Errorf("%w (lock held on %s)",
+				errScanRunning, lockPath)
+		}
+
+		return nil, fmt.Errorf("lock %s: %w", lockPath, err)
+	}
+
+	return f, nil
+}
+
 // openScanDatabase opens the database for the scan subcommand, creating
 // the file, its parent directory, and the schema as needed.
 func openScanDatabase(ctx context.Context, path string) (*sql.DB, error) {
@@ -104,7 +178,7 @@ func openScanDatabase(ctx context.Context, path string) (*sql.DB, error) {
 		return nil, fmt.Errorf("create database directory: %w", err)
 	}
 
-	db, err := openDB(path)
+	db, err := openDB(path, scanParams)
 	if err != nil {
 		return nil, err
 	}
@@ -119,6 +193,24 @@ func openScanDatabase(ctx context.Context, path string) (*sql.DB, error) {
 	return db, nil
 }
 
+// closeScanDatabase switches the database at path from WAL back to
+// rollback-journal mode and closes it. Out of WAL mode the database
+// file alone holds the whole database, so a reader needs no -wal or
+// -shm file beside it, nor write access to create them. The switch
+// fails while a report has the database open; the database then stays
+// in WAL mode, still readable, until a later scan closes it.
+func closeScanDatabase(ctx context.Context, db *sql.DB, path string) {
+	// Runs on the way out of a cancelled scan too.
+	_, err := db.ExecContext(context.WithoutCancel(ctx),
+		"PRAGMA journal_mode = DELETE")
+	if err != nil {
+		fmt.Fprintf(os.Stderr, "scan: database %s left in WAL mode: %v\n",
+			path, err)
+	}
+
+	_ = db.Close()
+}
+
 // openReportDatabase opens an existing database for the report and
 // trees subcommands. A missing database file is an error directing the
 // user to run scan first; the schema version must match exactly.
@@ -134,12 +226,18 @@ func openReportDatabase(ctx context.Context,
 		return nil, fmt.Errorf("database: %w", err)
 	}
 
-	db, err := openDB(path)
+	db, err := openDB(path, reportParams)
 	if err != nil {
 		return nil, err
 	}
 
 	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()
 
@@ -166,6 +264,11 @@ 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
@@ -175,20 +278,65 @@ 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.
+// 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.
 func createSchema(ctx context.Context, db *sql.DB) error {
-	_, err := db.ExecContext(ctx, createTableSQL)
+	tx, err := db.BeginTx(ctx, nil)
 	if err != nil {
 		return fmt.Errorf("create schema: %w", err)
 	}
 
-	_, err = db.ExecContext(ctx,
+	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,
 		"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
 }
 
@@ -204,18 +352,18 @@ func userVersion(ctx context.Context, db *sql.DB) (int, error) {
 	return v, nil
 }
 
-// loadFileRows reads every record from the files table.
-func loadFileRows(ctx context.Context, db *sql.DB) ([]scanRec, error) {
+// 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 {
 	rows, err := db.QueryContext(ctx,
-		"SELECT path, size, mtime, head, tail, content FROM files")
+		"SELECT path, size, mtime, head, tail, content FROM files "+
+			"ORDER BY path")
 	if err != nil {
-		return nil, fmt.Errorf("read records: %w", err)
+		return fmt.Errorf("read records: %w", err)
 	}
 
 	defer func() { _ = rows.Close() }()
 
-	var recs []scanRec
-
 	for rows.Next() {
 		var (
 			path []byte
@@ -225,19 +373,92 @@ func loadFileRows(ctx context.Context, db *sql.DB) ([]scanRec, error) {
 		err = rows.Scan(&path, &r.size, &r.mtime, &r.head, &r.tail,
 			&r.content)
 		if err != nil {
-			return nil, fmt.Errorf("read record: %w", err)
+			return fmt.Errorf("read record: %w", err)
 		}
 
 		r.path = string(path)
-		recs = append(recs, r)
+		fn(r)
 	}
 
 	err = rows.Err()
 	if err != nil {
-		return nil, fmt.Errorf("read records: %w", err)
+		return fmt.Errorf("read records: %w", err)
 	}
 
-	return recs, nil
+	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
 }
 
 // loadFileMeta streams every record's path, size, mtime, and whether

db_test.go

@@ -5,6 +5,7 @@ import (
 	"database/sql"
 	"errors"
 	"fmt"
+	"os"
 	"path/filepath"
 	"slices"
 	"strings"
@@ -72,9 +73,78 @@ func TestOpenScanDatabaseCreates(t *testing.T) {
 
 	defer func() { _ = db.Close() }()
 
-	recs, err := loadFileRows(t.Context(), db)
-	if err != nil || len(recs) != 0 {
-		t.Fatalf("loadFileRows = %v, %v; want empty, nil", recs, err)
+	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)
 	}
 }
 
@@ -87,9 +157,11 @@ func TestOpenReportDatabaseMissing(t *testing.T) {
 	}
 }
 
-func TestOpenReportDatabaseVersionMismatch(t *testing.T) {
+func TestOpenDatabaseVersionMismatch(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)
@@ -106,7 +178,12 @@ func TestOpenReportDatabaseVersionMismatch(t *testing.T) {
 
 	_, err = openReportDatabase(t.Context(), path)
 	if !errors.Is(err, errSchemaVersion) {
-		t.Fatalf("err = %v, want errSchemaVersion", err)
+		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)
 	}
 }
 
@@ -130,6 +207,49 @@ func TestOpenReportDatabaseOK(t *testing.T) {
 	_ = db.Close()
 }
 
+func TestCloseScanDatabaseWhileReportOpen(t *testing.T) {
+	t.Parallel()
+
+	// A report holding the database open stops scan from taking it out
+	// of WAL mode. The -wal and -shm files must then stay beside it, so
+	// that a later report still needs only read access.
+	path := testDBPath(t)
+
+	scanDB, err := openScanDatabase(t.Context(), path)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	reportDB, err := openReportDatabase(t.Context(), path)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	closeScanDatabase(t.Context(), scanDB, path)
+
+	_ = reportDB.Close()
+
+	_, err = os.Stat(path + "-wal")
+	if err != nil {
+		t.Fatalf("no -wal left: the switch out of WAL mode was not "+
+			"stopped: %v", err)
+	}
+
+	makeReadOnly(t, path)
+
+	reportDB, err = openReportDatabase(t.Context(), path)
+	if err != nil {
+		t.Fatalf("openReportDatabase: %v", err)
+	}
+
+	defer func() { _ = reportDB.Close() }()
+
+	err = loadFileRows(t.Context(), reportDB, func(scanRec) {})
+	if err != nil {
+		t.Fatalf("loadFileRows: %v", err)
+	}
+}
+
 func TestApplyChangesRoundTrip(t *testing.T) {
 	t.Parallel()
 
@@ -152,15 +272,8 @@ func TestApplyChangesRoundTrip(t *testing.T) {
 		t.Fatalf("applyChanges: %v", err)
 	}
 
-	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)
-	})
-
+	// The records come back in path order, which is the order of recs.
+	got := dbRecords(t, db)
 	if !slices.Equal(got, recs) {
 		t.Fatalf("rows = %+v, want %+v", got, recs)
 	}
@@ -177,11 +290,7 @@ func TestApplyChangesRoundTrip(t *testing.T) {
 		t.Fatalf("applyChanges: %v", err)
 	}
 
-	got, err = loadFileRows(t.Context(), db)
-	if err != nil {
-		t.Fatal(err)
-	}
-
+	got = dbRecords(t, db)
 	if len(got) != 1 || got[0] != upd {
 		t.Fatalf("rows = %+v, want just %+v", got, upd)
 	}
@@ -210,9 +319,8 @@ func TestApplyChangesBatching(t *testing.T) {
 		t.Fatalf("applyChanges: %v", err)
 	}
 
-	got, err := loadFileRows(t.Context(), db)
-	if err != nil || len(got) != n {
-		t.Fatalf("loadFileRows = %d rows, %v; want %d", len(got), err, n)
+	if got := dbRecords(t, db); len(got) != n {
+		t.Fatalf("records = %d, want %d", len(got), n)
 	}
 
 	deletes := make([]string, 0, n)
@@ -226,8 +334,7 @@ func TestApplyChangesBatching(t *testing.T) {
 		t.Fatalf("applyChanges deletes: %v", err)
 	}
 
-	got, err = loadFileRows(t.Context(), db)
-	if err != nil || len(got) != 0 {
-		t.Fatalf("loadFileRows = %d rows, %v; want 0", len(got), err)
+	if got := dbRecords(t, db); len(got) != 0 {
+		t.Fatalf("records = %d, want 0", len(got))
 	}
 }

go.mod

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

main.go

@@ -15,6 +15,7 @@
 //	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
@@ -50,6 +51,10 @@ 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.
 //
@@ -87,6 +92,9 @@ 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.
@@ -94,22 +102,35 @@ func run(args []string, stdout, stderr io.Writer) int {
 
 		return exitFatal
 	default:
-		// A usage error: cobra has already printed the message and
-		// the usage text.
+		// A usage error, which cobra has already reported on stderr.
 		return exitUsage
 	}
 }
 
 // newRootCommand builds the command tree. Everything on stdout is
-// machine-readable data; all human-facing output (help, usage, errors)
-// goes to stderr.
+// machine-readable data, the version line included; 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",
-		Version: Version,
 		Args:  cobra.NoArgs,
-		RunE: func(cmd *cobra.Command, _ []string) error {
+		RunE: func(cmd *cobra.Command, args []string) error {
+			if showVersion {
+				return printVersion(cmd, args)
+			}
+
 			// 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.
@@ -122,6 +143,11 @@ 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
@@ -131,7 +157,13 @@ 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)
 		}),
 	}
@@ -163,13 +195,26 @@ func newRootCommand(stdout, stderr io.Writer) *cobra.Command {
 	return root
 }
 
-// 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.
+// 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.
 func runE(
 	fn func(ctx context.Context, args []string) error,
 ) func(*cobra.Command, []string) error {

main_test.go

@@ -8,6 +8,7 @@ import (
 	"io/fs"
 	"os"
 	"path/filepath"
+	"slices"
 	"strconv"
 	"strings"
 	"testing"
@@ -44,16 +45,118 @@ func assertNoSidecars(t *testing.T, path string) {
 	}
 }
 
+// makeReadOnly takes write permission away from the database at path,
+// from any WAL sidecar beside it, and from their directory, as for a
+// user reading a database that a root cron scan keeps. Root ignores
+// file permissions, so it skips the test when run as root.
+func makeReadOnly(t *testing.T, path string) {
+	t.Helper()
+
+	if os.Geteuid() == 0 {
+		t.Skip("root ignores file permissions")
+	}
+
+	err := os.Chmod(path, 0o400)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	for _, suffix := range walSuffixes {
+		err = os.Chmod(path+suffix, 0o400)
+		if err != nil && !errors.Is(err, fs.ErrNotExist) {
+			t.Fatal(err)
+		}
+	}
+
+	dir := filepath.Dir(path)
+
+	//nolint:gosec // reaching the database needs the search bit
+	err = os.Chmod(dir, 0o500)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	// Runs before t.TempDir's own cleanup, which must delete the files.
+	t.Cleanup(func() {
+		//nolint:gosec // removing the directory needs its search bit back
+		_ = os.Chmod(dir, 0o700)
+	})
+}
+
+// captureStderr redirects os.Stderr to a file for the rest of the test
+// and returns a function reading back everything written to it. scan
+// writes its warnings and summary, and report and trees their
+// summaries, straight to os.Stderr, not to the stderr writer run is
+// given.
+func captureStderr(t *testing.T) func() string {
+	t.Helper()
+
+	return capture(t, &os.Stderr)
+}
+
+// captureStdout does for os.Stdout what captureStderr does for
+// os.Stderr. scan is never given run's stdout writer, so anything it
+// printed would go straight to os.Stdout. The scan tests pass os.Stdout
+// as run's stdout too, so the one capture sees both.
+func captureStdout(t *testing.T) func() string {
+	t.Helper()
+
+	return capture(t, &os.Stdout)
+}
+
+// capture redirects *std, which is os.Stdout or os.Stderr, to a file
+// for the rest of the test and returns a function reading back
+// everything written to it.
+func capture(t *testing.T, std **os.File) func() string {
+	t.Helper()
+
+	f, err := os.Create(filepath.Join(t.TempDir(), "output"))
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	saved := *std
+	*std = f
+
+	t.Cleanup(func() {
+		*std = saved
+
+		_ = f.Close()
+	})
+
+	return func() string {
+		// Read what has been written without disturbing the write
+		// offset, so the capture can be inspected more than once.
+		size, err := f.Seek(0, io.SeekCurrent)
+		if err != nil {
+			t.Fatal(err)
+		}
+
+		if size == 0 {
+			return ""
+		}
+
+		b := make([]byte, size)
+
+		_, err = f.ReadAt(b, 0)
+		if err != nil {
+			t.Fatal(err)
+		}
+
+		return string(b)
+	}
+}
+
 // brokenDatabase writes a database that opens cleanly and passes the
 // schema-version check but has no files table, so the first query
 // fails with the database already open: a fatal error on a path that
-// owns an open database.
+// owns an open database. It closes the database the way scan does.
 func brokenDatabase(t *testing.T) string {
 	t.Helper()
 
 	path := testDBPath(t)
 
-	db, err := openDB(path)
+	db, err := openDB(path, scanParams)
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -64,10 +167,7 @@ func brokenDatabase(t *testing.T) string {
 		t.Fatal(err)
 	}
 
-	err = db.Close()
-	if err != nil {
-		t.Fatal(err)
-	}
+	closeScanDatabase(t.Context(), db, path)
 
 	return path
 }
@@ -100,31 +200,37 @@ func TestOpenDatabaseKeepsWALWhileOpen(t *testing.T) {
 
 func TestRunFatalAfterOpenClosesDatabase(t *testing.T) {
 	// Every subcommand that owns an open database must close it when
-	// it fails: no os.Exit between the open and the return.
-	cases := map[string][]string{
-		cmdScan:   {cmdScan},
-		cmdReport: {cmdReport},
-		cmdTrees:  {cmdTrees},
-	}
+	// it fails: no os.Exit between the open and the return. The
+	// sidecar check is evidence of the close only for scan: report and
+	// trees only read a database that is out of WAL mode, which leaves
+	// nothing on disk whether they close it or not.
+	//
+	// The subcommands come from the command tree, so a new one is
+	// checked too: one wired with a bare RunE instead of runE reports
+	// its failure as a usage error, exit 2 with the usage text.
+	for _, cmd := range newRootCommand(io.Discard, io.Discard).Commands() {
+		name := cmd.Name()
 
-	for name, args := range cases {
 		t.Run(name, func(t *testing.T) {
 			path := brokenDatabase(t)
 			t.Setenv(databaseEnv, path)
 
+			args := []string{name}
 			if name == cmdScan {
 				args = append(args, t.TempDir())
 			}
 
-			var stdout, stderr bytes.Buffer
+			stdout := captureStdout(t)
 
-			code := run(args, &stdout, &stderr)
+			var stderr bytes.Buffer
+
+			code := run(args, os.Stdout, &stderr)
 			if code != exitFatal {
 				t.Errorf("run(%v) = %d, want %d", args, code, exitFatal)
 			}
 
 			assertNoSidecars(t, path)
-			assertFatalOutput(t, stderr.String(), stdout.String())
+			assertFatalOutput(t, stderr.String(), stdout())
 
 			// Proof that the failure happened after the open: only a
 			// query against the opened database can report this.
@@ -136,22 +242,24 @@ func TestRunFatalAfterOpenClosesDatabase(t *testing.T) {
 	}
 }
 
-func TestRunMissingOperandIsFatalNotUsage(t *testing.T) {
+func TestRunNonexistentPathIsFatalNotUsage(t *testing.T) {
 	// README §Error handling: a PATH operand that does not exist is a
 	// fatal error (1), not a usage error (2) — and a runtime failure
 	// must not dump the usage text.
 	t.Setenv(databaseEnv, testDBPath(t))
 
-	var stdout, stderr bytes.Buffer
+	stdout := captureStdout(t)
+
+	var stderr bytes.Buffer
 
 	missing := filepath.Join(t.TempDir(), "nope")
 
-	code := run([]string{cmdScan, missing}, &stdout, &stderr)
+	code := run([]string{cmdScan, missing}, os.Stdout, &stderr)
 	if code != exitFatal {
 		t.Errorf("run(scan %s) = %d, want %d", missing, code, exitFatal)
 	}
 
-	assertFatalOutput(t, stderr.String(), stdout.String())
+	assertFatalOutput(t, stderr.String(), stdout())
 }
 
 // assertFatalOutput checks that a fatal error was reported the way
@@ -175,6 +283,34 @@ func assertFatalOutput(t *testing.T, stderr, stdout string) {
 	}
 }
 
+func TestRunMissingDatabaseIsFatal(t *testing.T) {
+	// README §Database: report and trees need an existing database; a
+	// missing one exits 1 with a message telling the user to run scan.
+	for _, name := range []string{cmdReport, cmdTrees} {
+		t.Run(name, func(t *testing.T) {
+			path := testDBPath(t)
+			t.Setenv(databaseEnv, path)
+
+			var stdout, stderr bytes.Buffer
+
+			code := run([]string{name}, &stdout, &stderr)
+			if code != exitFatal {
+				t.Errorf("run(%s) = %d, want %d", name, code, exitFatal)
+			}
+
+			want := "sfdupes: " + path + ": no database (run \"sfdupes " +
+				"scan\" first, or set " + databaseEnv + ")\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)
+			}
+		})
+	}
+}
+
 func TestRunUsageErrors(t *testing.T) {
 	// Usage errors keep exiting 2 with cobra's own report on stderr.
 	cases := map[string]struct {
@@ -213,21 +349,75 @@ func TestRunUsageErrors(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()
+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)
 
-	assertHumanOutput(t, "--help")
-	assertHumanOutput(t, "--version")
+			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)
+			}
+		})
+	}
 }
 
-// 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()
+func TestRunHelp(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)
+		}
+	}
+}
+
+func TestRunVersion(t *testing.T) {
+	t.Parallel()
+
+	// 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
 
 		code := run([]string{arg}, &stdout, &stderr)
@@ -235,12 +425,32 @@ func assertHumanOutput(t *testing.T, arg string) {
 			t.Errorf("run(%s) = %d, want %d", arg, code, exitOK)
 		}
 
-	if stderr.Len() == 0 {
-		t.Errorf("run(%s) wrote nothing to stderr", arg)
+		want := "sfdupes " + Version + "\n"
+		if got := stdout.String(); got != want {
+			t.Errorf("run(%s) stdout = %q, want %q", arg, got, want)
 		}
 
-	if got := stdout.String(); got != "" {
-		t.Errorf("stdout = %q, want nothing (data only)", got)
+		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)
+	}
+
+	want := "sfdupes: write stdout: " + errWriteFailed.Error() + "\n"
+	if got := stderr.String(); got != want {
+		t.Errorf("stderr = %q, want %q", got, want)
 	}
 }
 
@@ -268,41 +478,182 @@ func scanFixture(t *testing.T) []string {
 		t.Fatal(err)
 	}
 
-	var stdout, stderr bytes.Buffer
-
-	code := run([]string{cmdScan, dir}, &stdout, &stderr)
-	if code != exitOK {
-		t.Fatalf("run(scan) = %d, want %d; stderr: %s",
-			code, exitOK, stderr.String())
-	}
-
-	if got := stdout.String(); got != "" {
-		t.Errorf("scan stdout = %q, want nothing (data only)", got)
-	}
+	scanOK(t, dir)
 
 	return dupes
 }
 
+// scanOK runs scan over operands, fails the test unless it exits 0 with
+// nothing on stdout, and returns everything it printed to stderr.
+func scanOK(t *testing.T, operands ...string) string {
+	t.Helper()
+
+	stdout := captureStdout(t)
+	stderr := captureStderr(t)
+
+	code := run(append([]string{cmdScan}, operands...), os.Stdout, os.Stderr)
+	if code != exitOK {
+		t.Fatalf("run(scan %q) = %d, want %d; stderr: %s",
+			operands, code, exitOK, stderr())
+	}
+
+	if got := stdout(); got != "" {
+		t.Errorf("scan stdout = %q, want nothing (data only)", got)
+	}
+
+	return stderr()
+}
+
 func TestRunScanSucceedsDespiteWarnings(t *testing.T) {
+	// README §Error handling: a scan that skips a file it cannot read
+	// warns, counts the skip in its summary, and still exits 0, which
+	// scanOK checks along with the empty stdout.
+	if os.Geteuid() == 0 {
+		t.Skip("root ignores file permissions")
+	}
+
 	path := testDBPath(t)
 	t.Setenv(databaseEnv, path)
 
-	scanFixture(t)
+	dir := t.TempDir()
+	writeFile(t, dir, "a.bin", pattern(1, 300))
+
+	// Same size as a.bin, so the scan reads it, and the read fails.
+	unreadable := writeFile(t, dir, "unreadable.bin", pattern(2, 300))
+
+	err := os.Chmod(unreadable, 0)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	stderr := scanOK(t, dir)
+
+	warning := "hash " + unreadable + ": open " + unreadable +
+		": permission denied\n"
+	if !strings.Contains(stderr, warning) {
+		t.Errorf("stderr = %q, want %q", stderr, warning)
+	}
+
+	summary := "scan: 1 files seen (1 added, 0 updated, 0 removed, " +
+		"0 unchanged), 1 skipped\n"
+	if !strings.Contains(stderr, summary) {
+		t.Errorf("stderr = %q, want %q", stderr, summary)
+	}
+
 	assertNoSidecars(t, path)
 }
 
+func TestRunScanSkipsSymlinkOperand(t *testing.T) {
+	path := testDBPath(t)
+	t.Setenv(databaseEnv, path)
+
+	dir := t.TempDir()
+	writeFile(t, dir, "target/sub/f", pattern(1, 10))
+
+	link := filepath.Join(dir, "link")
+
+	err := os.Symlink(filepath.Join(dir, "target"), link)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	// Scanning a directory through the symlink stores a record beneath
+	// the symlink's own path for a file beneath its target.
+	scanOK(t, filepath.Join(link, "sub"))
+
+	assertOperandSkipped(t, path, link, "symlink",
+		filepath.Join(link, "sub", "f"))
+}
+
+func TestRunScanWalksOperandUnderSymlinkOperand(t *testing.T) {
+	path := testDBPath(t)
+	t.Setenv(databaseEnv, path)
+
+	dir := t.TempDir()
+	writeFile(t, dir, "target/sub/f", pattern(1, 10))
+
+	link := filepath.Join(dir, "link")
+
+	err := os.Symlink(filepath.Join(dir, "target"), link)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	// link is dropped as a symlink, but link/sub must still be scanned,
+	// not dropped as lying under link.
+	scanOK(t, link, filepath.Join(link, "sub"))
+
+	db, err := openDB(path, reportParams)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	t.Cleanup(func() { _ = db.Close() })
+
+	recordByPath(t, dbRecords(t, db), filepath.Join(link, "sub", "f"))
+}
+
+func TestRunScanSkipsZFSOperand(t *testing.T) {
+	path := testDBPath(t)
+	t.Setenv(databaseEnv, path)
+
+	zfs := filepath.Join(t.TempDir(), ".zfs")
+	snapshot := filepath.Join(zfs, "snapshot", "hourly")
+	f := writeFile(t, snapshot, "f", pattern(1, 10))
+
+	// An operand beneath a .zfs directory is walked, because it is not
+	// itself named .zfs.
+	scanOK(t, snapshot)
+
+	assertOperandSkipped(t, path, zfs, ".zfs directory", f)
+}
+
+// assertOperandSkipped scans operand alone and checks that it is skipped
+// as kind: a warning naming it, one skip in the summary, exit 0, and the
+// record for kept, which an earlier scan stored beneath operand, still
+// in the database at dbPath.
+func assertOperandSkipped(t *testing.T, dbPath, operand, kind,
+	kept string,
+) {
+	t.Helper()
+
+	stderr := scanOK(t, operand)
+
+	warning := "walk " + operand + ": skipping " + kind + " operand\n"
+	if !strings.Contains(stderr, warning) {
+		t.Errorf("stderr = %q, want %q", stderr, warning)
+	}
+
+	summary := "scan: 0 files seen (0 added, 0 updated, 0 removed, " +
+		"0 unchanged), 1 skipped\n"
+	if !strings.Contains(stderr, summary) {
+		t.Errorf("stderr = %q, want %q", stderr, summary)
+	}
+
+	db, err := openDB(dbPath, reportParams)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	t.Cleanup(func() { _ = db.Close() })
+
+	recordByPath(t, dbRecords(t, db), kept)
+}
+
 func TestRunReportSucceeds(t *testing.T) {
 	path := testDBPath(t)
 	t.Setenv(databaseEnv, path)
 
 	dupes := scanFixture(t)
 
-	var stdout, stderr bytes.Buffer
+	var stdout bytes.Buffer
 
-	code := run([]string{cmdReport}, &stdout, &stderr)
+	stderr := captureStderr(t)
+
+	code := run([]string{cmdReport}, &stdout, os.Stderr)
 	if code != exitOK {
 		t.Fatalf("run(report) = %d, want %d; stderr: %s",
-			code, exitOK, stderr.String())
+			code, exitOK, stderr())
 	}
 
 	want := "first\tdupe\tsize\n" + dupes[0] + "\t" + dupes[1] + "\t300\n"
@@ -310,6 +661,12 @@ func TestRunReportSucceeds(t *testing.T) {
 		t.Errorf("stdout = %q, want %q", got, want)
 	}
 
+	want = "report: 2 records read, 1 duplicate groups, 1 dupe files, " +
+		"300 B reclaimable\n"
+	if got := stderr(); got != want {
+		t.Errorf("stderr = %q, want %q", got, want)
+	}
+
 	assertNoSidecars(t, path)
 }
 
@@ -319,12 +676,14 @@ func TestRunTreesSucceeds(t *testing.T) {
 
 	dupes := scanFixture(t)
 
-	var stdout, stderr bytes.Buffer
+	var stdout bytes.Buffer
 
-	code := run([]string{cmdTrees}, &stdout, &stderr)
+	stderr := captureStderr(t)
+
+	code := run([]string{cmdTrees}, &stdout, os.Stderr)
 	if code != exitOK {
 		t.Fatalf("run(trees) = %d, want %d; stderr: %s",
-			code, exitOK, stderr.String())
+			code, exitOK, stderr())
 	}
 
 	// The two directories holding the duplicate pair are duplicate
@@ -335,9 +694,209 @@ func TestRunTreesSucceeds(t *testing.T) {
 		t.Errorf("stdout = %q, want %q", got, want)
 	}
 
+	want = "trees: 2 records read, 1 duplicate tree groups, 1 dupe trees, " +
+		"300 B reclaimable\n"
+	if got := stderr(); got != want {
+		t.Errorf("stderr = %q, want %q", got, want)
+	}
+
 	assertNoSidecars(t, path)
 }
 
+func TestRunReportsNeedOnlyReadAccess(t *testing.T) {
+	// README §Database: report and trees need only read access to the
+	// database file. With its directory read-only as well, SQLite
+	// cannot create any file beside it.
+	path := testDBPath(t)
+	t.Setenv(databaseEnv, path)
+
+	dupes := scanFixture(t)
+	assertNoSidecars(t, path)
+	makeReadOnly(t, path)
+
+	cases := map[string]string{
+		cmdReport: "first\tdupe\tsize\n" +
+			dupes[0] + "\t" + dupes[1] + "\t300\n",
+		cmdTrees: "first\tdupe\tfiles\tsize\n" +
+			filepath.Dir(dupes[0]) + "\t" + filepath.Dir(dupes[1]) +
+			"\t1\t300\n",
+	}
+
+	for name, want := range cases {
+		var stdout, stderr bytes.Buffer
+
+		code := run([]string{name}, &stdout, &stderr)
+		if code != exitOK {
+			t.Errorf("run(%s) = %d, want %d; stderr: %s",
+				name, code, exitOK, stderr.String())
+
+			continue
+		}
+
+		if got := stdout.String(); got != want {
+			t.Errorf("%s stdout = %q, want %q", name, got, want)
+		}
+	}
+}
+
+// assertRunsUseDatabase runs scan, then report and trees, against the
+// database that SFDUPES_DATABASE names, the file name in dir. It fails
+// unless the reports find the duplicate pair the scan recorded and dir
+// then holds only that file and its lock file: nothing was created
+// under a shortened name.
+func assertRunsUseDatabase(t *testing.T, dir, name string) {
+	t.Helper()
+
+	dupes := scanFixture(t)
+
+	want := "first\tdupe\tsize\n" + dupes[0] + "\t" + dupes[1] + "\t300\n"
+	if got := runStdout(t, cmdReport); got != want {
+		t.Errorf("report stdout = %q, want %q", got, want)
+	}
+
+	want = "first\tdupe\tfiles\tsize\n" +
+		filepath.Dir(dupes[0]) + "\t" + filepath.Dir(dupes[1]) + "\t1\t300\n"
+	if got := runStdout(t, cmdTrees); got != want {
+		t.Errorf("trees stdout = %q, want %q", got, want)
+	}
+
+	entries, err := os.ReadDir(dir)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	got := make([]string, 0, len(entries))
+	for _, e := range entries {
+		got = append(got, e.Name())
+	}
+
+	if wantFiles := []string{name, name + ".lock"}; !slices.Equal(got, wantFiles) {
+		t.Errorf("%s holds %q, want %q", dir, got, wantFiles)
+	}
+}
+
+func TestRunDatabasePathUsedAsGiven(t *testing.T) {
+	// README §Database: the path names the database file exactly. In
+	// SQLite's connection string an unescaped ? or # would end the file
+	// name and % would start an escape, and a path starting with //
+	// could be read as a host name. %25 is a valid escape, so unescaped
+	// this name opens a file named a without any error.
+	const name = "a?b#c%25d e.sqlite"
+
+	t.Run("absolute", func(t *testing.T) {
+		dir := t.TempDir()
+		t.Setenv(databaseEnv, filepath.Join(dir, name))
+
+		assertRunsUseDatabase(t, dir, name)
+	})
+
+	t.Run("leading double slash", func(t *testing.T) {
+		dir := t.TempDir()
+		t.Setenv(databaseEnv, "/"+filepath.Join(dir, name))
+
+		assertRunsUseDatabase(t, dir, name)
+	})
+
+	t.Run("relative", func(t *testing.T) {
+		dir := t.TempDir()
+		t.Chdir(dir)
+		t.Setenv(databaseEnv, name)
+
+		assertRunsUseDatabase(t, dir, name)
+	})
+}
+
+// holdScanLock takes the lock on the database at path, as a running
+// scan does, and holds it until the test ends. It fails the test when
+// the lock is already held.
+func holdScanLock(t *testing.T, path string) {
+	t.Helper()
+
+	lock, err := lockScanDatabase(path)
+	if err != nil {
+		t.Fatalf("lock %s: %v", path, err)
+	}
+
+	t.Cleanup(func() { _ = lock.Close() })
+}
+
+func TestRunSecondScanFails(t *testing.T) {
+	// README §Database: while one scan holds the lock, a second scan
+	// fails at once, naming the lock file, without creating the
+	// database.
+	path := testDBPath(t)
+	t.Setenv(databaseEnv, path)
+
+	holdScanLock(t, path)
+
+	stdout := captureStdout(t)
+
+	var stderr bytes.Buffer
+
+	code := run([]string{cmdScan, t.TempDir()}, os.Stdout, &stderr)
+	if code != exitFatal {
+		t.Errorf("run(scan) = %d, want %d", code, exitFatal)
+	}
+
+	want := "sfdupes: another scan is running (lock held on " +
+		path + ".lock)\n"
+	if got := stderr.String(); got != want {
+		t.Errorf("stderr = %q, want %q", got, want)
+	}
+
+	if got := stdout(); got != "" {
+		t.Errorf("stdout = %q, want nothing (data only)", got)
+	}
+
+	_, err := os.Stat(path)
+	if !errors.Is(err, fs.ErrNotExist) {
+		t.Errorf("stat %s = %v, want the database not created", path, err)
+	}
+}
+
+func TestRunScanReleasesLock(t *testing.T) {
+	// README §Database: a scan releases the lock however it ends.
+	t.Run("success", func(t *testing.T) {
+		path := testDBPath(t)
+		t.Setenv(databaseEnv, path)
+
+		scanFixture(t)
+		holdScanLock(t, path)
+	})
+
+	t.Run("fatal error", func(t *testing.T) {
+		path := brokenDatabase(t)
+		t.Setenv(databaseEnv, path)
+
+		code := run([]string{cmdScan, t.TempDir()}, io.Discard, io.Discard)
+		if code != exitFatal {
+			t.Fatalf("run(scan) = %d, want %d", code, exitFatal)
+		}
+
+		holdScanLock(t, path)
+	})
+}
+
+func TestRunReportsDuringScan(t *testing.T) {
+	// README §Database: report and trees never take the lock, so they
+	// run while a scan holds it.
+	path := testDBPath(t)
+	t.Setenv(databaseEnv, path)
+
+	scanFixture(t)
+	holdScanLock(t, path)
+
+	for _, name := range []string{cmdReport, cmdTrees} {
+		var stderr bytes.Buffer
+
+		code := run([]string{name}, io.Discard, &stderr)
+		if code != exitOK {
+			t.Errorf("run(%s) = %d, want %d; stderr: %s",
+				name, code, exitOK, stderr.String())
+		}
+	}
+}
+
 func TestRunStdoutClosedIsFatal(t *testing.T) {
 	// README §Error handling: a stdout write failure exits 1, reported
 	// in one line on stderr.

package.json

@@ -0,0 +1,5 @@
+{
+  "devDependencies": {
+    "prettier": "3.8.1"
+  }
+}

progress.go

@@ -6,6 +6,7 @@ import (
 	"time"
 
 	"github.com/schollz/progressbar/v3"
+	"golang.org/x/term"
 )
 
 // plainInterval is the minimum time between progress lines when stderr
@@ -24,24 +25,23 @@ const percentScale = 100
 
 // stderrIsTTY reports whether stderr is attached to a terminal.
 func stderrIsTTY() bool {
-	fi, err := os.Stderr.Stat()
-	if err != nil {
-		return false
-	}
-
-	return fi.Mode()&os.ModeCharDevice != 0
+	return term.IsTerminal(int(os.Stderr.Fd()))
 }
 
 // progress renders one scan pass's progress on stderr. On a TTY it
 // delegates to the progressbar library (spinner style when the total is
 // unknown, full bar with count/percent/rate/elapsed/ETA otherwise). When
 // stderr is not a TTY it emits no ANSI redraws: it prints a plain
-// one-line update no more often than every plainInterval.
+// one-line update as the pass starts, then no more often than every
+// plainInterval.
 //
-// All methods must be called from the main goroutine only. A nil
-// *progress is a valid no-display receiver: every method is a no-op,
-// so batched database flushes during the streaming pass can reuse the
-// update-pass helpers without rendering anything.
+// All methods must be called from the main goroutine only. On a TTY
+// the library also redraws a spinner from its own goroutine, several
+// times a second, so its count and elapsed time stay current while a
+// pass waits for its next item. A nil *progress is a valid
+// no-display receiver: every method is a no-op, so batched database
+// flushes during the streaming pass can reuse the update-pass helpers
+// without rendering anything.
 type progress struct {
 	label string
 	total int64 // -1 when unknown (walk pass)
@@ -53,10 +53,22 @@ type progress struct {
 
 func newProgress(label string, total int64) *progress {
 	p := &progress{label: label, total: total, start: time.Now()}
-	if !stderrIsTTY() {
+	if stderrIsTTY() {
+		p.bar = newBar(label, total)
+
 		return p
 	}
 
+	// Print the zero state at once: the first item may take minutes,
+	// and a pass must never look hung.
+	p.last = p.start
+	fmt.Fprintln(os.Stderr, p.plainLine())
+
+	return p
+}
+
+// newBar builds the TTY display for newProgress.
+func newBar(label string, total int64) *progressbar.ProgressBar {
 	opts := []progressbar.Option{
 		progressbar.OptionSetWriter(os.Stderr),
 		progressbar.OptionSetDescription(label),
@@ -81,9 +93,7 @@ func newProgress(label string, total int64) *progress {
 		)
 	}
 
-	p.bar = progressbar.NewOptions64(total, opts...)
-
-	return p
+	return progressbar.NewOptions64(total, opts...)
 }
 
 // increment records one completed item and refreshes the display.
@@ -113,21 +123,38 @@ func (p *progress) warnf(format string, args ...any) {
 		return
 	}
 
+	msg := escapePath(fmt.Sprintf(format, args...))
+
+	if p.bar != nil && p.total < 0 {
+		// The library also redraws a spinner from its own goroutine, so
+		// a direct write could land inside a redraw. The bar prints the
+		// warning itself, just before its next redraw.
+		_, _ = progressbar.Bprintln(p.bar, msg)
+
+		return
+	}
+
 	if p.bar != nil {
 		_ = p.bar.Clear()
 	}
 
-	fmt.Fprintln(os.Stderr, escapePath(fmt.Sprintf(format, args...)))
+	fmt.Fprintln(os.Stderr, msg)
 }
 
-// finish terminates the pass's display.
+// 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.
 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()
+		}
 
 		fmt.Fprintln(os.Stderr)
 

progress_test.go

@@ -0,0 +1,189 @@
+package main
+
+import (
+	"os"
+	"path/filepath"
+	"strings"
+	"testing"
+	"time"
+)
+
+// spinnerIdle comfortably outlasts the 100ms interval at which the
+// progressbar library redraws a spinner from its own goroutine.
+const spinnerIdle = 500 * time.Millisecond
+
+//nolint:paralleltest // replaces the process-wide os.Stderr
+func TestStderrIsTTYFalseForNonTerminals(t *testing.T) {
+	r, pipe, err := os.Pipe()
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	regular, err := os.Create(filepath.Join(t.TempDir(), "stderr"))
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	devNull, err := os.OpenFile(os.DevNull, os.O_WRONLY, 0)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	saved := os.Stderr
+
+	t.Cleanup(func() {
+		os.Stderr = saved
+
+		for _, f := range []*os.File{r, pipe, regular, devNull} {
+			_ = f.Close()
+		}
+	})
+
+	cases := map[string]*os.File{
+		"a pipe":         pipe,
+		"a regular file": regular,
+		os.DevNull:       devNull,
+	}
+
+	for name, f := range cases {
+		os.Stderr = f
+
+		if stderrIsTTY() {
+			t.Errorf("stderrIsTTY() = true with stderr on %s", name)
+		}
+	}
+}
+
+// TestNewProgressPrintsBeforeFirstItem checks that each pass shows its
+// zero state the moment it starts when stderr is not a terminal, and
+// that the next line still waits for plainInterval.
+//
+//nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
+func TestNewProgressPrintsBeforeFirstItem(t *testing.T) {
+	stderr := captureStderr(t)
+
+	newProgress("walk", -1).increment()
+	newProgress("hash", 10).increment()
+
+	want := "walk: 0 files, elapsed 0s\n" +
+		"hash: [0/10] 0% 0 files/s elapsed 0s eta ?\n"
+	if got := stderr(); got != want {
+		t.Errorf("stderr = %q, want %q", got, want)
+	}
+}
+
+// newWalkSpinner returns the walk pass's terminal display, writing to
+// os.Stderr whether or not it is a terminal, and stops the library's
+// redraws when the test ends.
+func newWalkSpinner(t *testing.T) *progress {
+	t.Helper()
+
+	p := &progress{
+		label: "walk", total: -1, start: time.Now(),
+		bar: newBar("walk", -1),
+	}
+	t.Cleanup(p.finish)
+
+	return p
+}
+
+// TestProgressWarningsOnOwnLines drives the terminal display of the walk
+// pass through a run of warnings with no items between them, as when the
+// walk meets many unreadable paths, for several of the spinner's
+// redraws: every warning must land on a line of its own, never inside a
+// redraw.
+//
+//nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
+func TestProgressWarningsOnOwnLines(t *testing.T) {
+	stderr := captureStderr(t)
+	p := newWalkSpinner(t)
+
+	// No pause between warnings: one written straight to stderr is
+	// garbled only if a redraw lands while it is being written.
+	issued := 0
+	for start := time.Now(); time.Since(start) < spinnerIdle; issued++ {
+		p.warnf("warning")
+	}
+
+	// The spinner prints the warnings at its next redraw.
+	time.Sleep(spinnerIdle)
+
+	// A terminal shows each line as the text after its last carriage
+	// return.
+	shown := 0
+
+	for line := range strings.SplitSeq(stderr(), "\n") {
+		if !strings.Contains(line, "warning") {
+			continue
+		}
+
+		shown++
+
+		if text := line[strings.LastIndex(line, "\r")+1:]; text != "warning" {
+			t.Errorf("terminal shows %q, want %q", text, "warning")
+		}
+	}
+
+	if shown != issued {
+		t.Errorf("%d warning lines, want %d", shown, issued)
+	}
+}
+
+// TestSpinnerShowsCountAfterBurst checks that once a burst of items
+// faster than the redraw limit is over, the walk display shows every
+// item completed while it waits for the next one.
+//
+//nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
+func TestSpinnerShowsCountAfterBurst(t *testing.T) {
+	stderr := captureStderr(t)
+	p := newWalkSpinner(t)
+
+	for range 50 {
+		p.increment()
+	}
+
+	time.Sleep(spinnerIdle)
+
+	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 {
+	var shown string
+
+	for frame := range strings.SplitSeq(out, "\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)
+	}
+}

report.go

@@ -6,7 +6,6 @@ import (
 	"fmt"
 	"io"
 	"os"
-	"slices"
 	"strings"
 )
 
@@ -29,50 +28,21 @@ type scanRec struct {
 	path    string
 }
 
-// loadRecords opens the database and reads every file record for the
-// report and trees subcommands. Any database problem — including a
-// missing database — is fatal. The error is returned rather than
-// exiting, so that the deferred close — which checkpoints the SQLite
-// WAL — always runs; the database is closed before the caller formats
-// its output, so it stays closed even if that output fails.
-func loadRecords(ctx context.Context) ([]scanRec, error) {
+// 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 {
 	dbPath := databasePath()
 
 	db, err := openReportDatabase(ctx, dbPath)
-	if err != nil {
-		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)
+	defer func() { _ = db.Close() }()
 
 	out := bufio.NewWriterSize(stdout, ioBufSize)
 
@@ -81,21 +51,36 @@ func runReport(ctx context.Context, stdout io.Writer) error {
 		return fmt.Errorf("write stdout: %w", err)
 	}
 
-	dupeFiles := 0
+	var (
+		groups, dupeFiles int
+		reclaimable       int64
+		writeErr          error
+	)
 
-	var reclaimable int64
+	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++
 
-	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)
+				return nil
 			}
 
+			_, writeErr = fmt.Fprintf(out, "%s\t%s\t%d\n",
+				escapePath(first), escapePath(path), size)
 			dupeFiles++
-			reclaimable += g.size
+			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)
 	}
 
 	err = out.Flush()
@@ -106,57 +91,11 @@ 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",
-		len(recs), len(dupes), dupeFiles, humanBytes(reclaimable))
+		records, groups, 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

@@ -2,10 +2,14 @@ package main
 
 import (
 	"bytes"
+	"database/sql"
+	"errors"
+	"fmt"
 	"io"
 	"os"
 	"path/filepath"
 	"slices"
+	"strings"
 	"testing"
 )
 
@@ -47,6 +51,53 @@ 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()))
 
@@ -65,6 +116,82 @@ 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()
 
@@ -121,7 +248,7 @@ func TestWarnfEscapes(t *testing.T) {
 	}
 }
 
-func TestCollectDupeGroups(t *testing.T) {
+func TestDupeGroups(t *testing.T) {
 	t.Parallel()
 
 	recs := []scanRec{
@@ -136,7 +263,7 @@ func TestCollectDupeGroups(t *testing.T) {
 		{size: 7, head: "u", tail: "u", content: "u", path: "/lonely"},
 	}
 
-	groups := collectDupeGroups(recs)
+	groups := dupeGroupsOf(t, recs)
 	if len(groups) != 2 {
 		t.Fatalf("len(groups) = %d, want 2", len(groups))
 	}
@@ -154,7 +281,7 @@ func TestCollectDupeGroups(t *testing.T) {
 	}
 }
 
-func TestCollectDupeGroupsContentSeparates(t *testing.T) {
+func TestDupeGroupsContentSeparates(t *testing.T) {
 	t.Parallel()
 
 	// Same size, head, and tail, but different content hashes: the final
@@ -169,7 +296,7 @@ func TestCollectDupeGroupsContentSeparates(t *testing.T) {
 		{size: 100, head: "h", tail: "t", path: "/e"},
 	}
 
-	groups := collectDupeGroups(recs)
+	groups := dupeGroupsOf(t, recs)
 	if len(groups) != 1 {
 		t.Fatalf("len(groups) = %d, want 1 (only the matching content)",
 			len(groups))
@@ -180,7 +307,7 @@ func TestCollectDupeGroupsContentSeparates(t *testing.T) {
 	}
 }
 
-func TestCollectDupeGroupsMtimeExcluded(t *testing.T) {
+func TestDupeGroupsMtimeExcluded(t *testing.T) {
 	t.Parallel()
 
 	// mtime is informational only; records differing only in mtime
@@ -190,23 +317,25 @@ func TestCollectDupeGroupsMtimeExcluded(t *testing.T) {
 		{size: 9, mtime: 200, head: "h", tail: "t", content: "c", path: "/m/2"},
 	}
 
-	groups := collectDupeGroups(recs)
+	groups := dupeGroupsOf(t, recs)
 	if len(groups) != 1 {
 		t.Fatalf("len(groups) = %d, want 1", len(groups))
 	}
 }
 
-func TestCollectDupeGroupsTieBreak(t *testing.T) {
+func TestDupeGroupsTieBreak(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: "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"},
+		{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"},
 	}
 
-	groups := collectDupeGroups(recs)
+	groups := dupeGroupsOf(t, recs)
 	if len(groups) != 2 {
 		t.Fatalf("len(groups) = %d, want 2", len(groups))
 	}
@@ -218,7 +347,7 @@ func TestCollectDupeGroupsTieBreak(t *testing.T) {
 	}
 }
 
-func TestCollectDupeGroupsDeterministic(t *testing.T) {
+func TestDupeGroupsDeterministic(t *testing.T) {
 	t.Parallel()
 
 	recs := []scanRec{
@@ -228,12 +357,12 @@ func TestCollectDupeGroupsDeterministic(t *testing.T) {
 		{size: 2, head: "b", tail: "b", content: "b", path: "/q/2"},
 	}
 
-	forward := collectDupeGroups(recs)
+	forward := dupeGroupsOf(t, recs)
 
 	reversed := slices.Clone(recs)
 	slices.Reverse(reversed)
 
-	backward := collectDupeGroups(reversed)
+	backward := dupeGroupsOf(t, reversed)
 	if !slices.EqualFunc(forward, backward, func(a, b dupeGroup) bool {
 		return a.size == b.size && slices.Equal(a.paths, b.paths)
 	}) {

scan.go

@@ -11,6 +11,7 @@ import (
 	"io"
 	"io/fs"
 	"os"
+	"os/signal"
 	"path/filepath"
 	"slices"
 	"strings"
@@ -57,6 +58,10 @@ 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.
@@ -85,17 +90,19 @@ type fileMeta struct {
 // least one other file shares are ever hashed: a size-unique file
 // cannot be a duplicate. A file of headTailMin or more gets its content
 // hash only when its size, head, and tail match another file's. Flag
-// parsing and the at-least-one-operand check are done by cobra. Errors
-// are returned rather than exiting, so that the deferred close — which
-// checkpoints the SQLite WAL — always runs. Cancelling ctx unwinds the
-// worker pools and aborts the scan with the context's error.
+// parsing and the at-least-one-operand check are done by cobra. The
+// scan holds the lock on the database for its whole run, so a second
+// scan fails before it walks the filesystem or opens the database.
+// Errors are returned rather than exiting, so that the deferred close —
+// which takes the database out of WAL mode — always runs, and the lock
+// is released after it. 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.
 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
@@ -103,14 +110,31 @@ func runScan(ctx context.Context, roots []string, workers int,
 
 	dbPath := databasePath()
 
-	db, err := openScanDatabase(ctx, dbPath)
+	lock, err := lockScanDatabase(dbPath)
 	if err != nil {
 		return err
 	}
 
-	defer func() { _ = db.Close() }()
+	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
+	}
+
+	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)
 	}
@@ -124,6 +148,34 @@ 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
@@ -177,8 +229,9 @@ func pruneRoots(roots []string) []string {
 }
 
 // scanStats summarizes one scan's database synchronization for the
-// final stderr summary.
+// final stderr summary, or for the line an interrupted scan prints.
 type scanStats struct {
+	walked    int // files the walk reached
 	added     int
 	updated   int
 	removed   int
@@ -200,7 +253,30 @@ type scanState struct {
 	st        scanStats
 }
 
-// syncScan synchronizes the database with the filesystem under roots
+// 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
 // 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
@@ -210,47 +286,73 @@ type scanState struct {
 // in the content hash of every record of headTailMin or more whose
 // size, head, and tail match another record's). Records outside the
 // roots are never touched, except that the content phase fills in
-// their content hash.
-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,
 	workers int, oneFS bool,
-) (scanStats, error) {
-	roots = pruneRoots(roots)
-
-	s := &scanState{db: db}
+) error {
+	// 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 s.st, err
+		return 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 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.
+	// of the roots, and every file it never reached would look vanished
+	// to the update phase. Stop before anything is written or deleted.
 	err = ctx.Err()
 	if err != nil {
-		return s.st, err
+		return err
 	}
 
 	s.partition(changed, unhashed)
 
 	err = s.hashPhase(ctx, workers)
 	if err != nil {
-		return s.st, err
+		return err
 	}
 
 	err = s.updatePhase(ctx)
 	if err != nil {
-		return s.st, err
+		return err
 	}
 
-	return s.st, s.contentPhase(ctx, workers)
+	return s.contentPhase(ctx, workers)
+}
+
+// walkableRoots returns the operands the walk can start from: regular
+// files, and directories not named .zfs. Every other operand is warned
+// about, counted as skipped, and dropped. A dropped operand is no
+// longer a root, so the records stored beneath it count as outside the
+// roots and are not deleted as unverified, unless it lies under another
+// root. An operand that fails lstat here is kept, and the walk warns
+// about it.
+func (s *scanState) walkableRoots(roots []string) []string {
+	kept := make([]string, 0, len(roots))
+
+	for _, root := range roots {
+		fi, err := os.Lstat(root)
+		if err == nil {
+			warn := operandWarning(root, fi)
+			if warn != "" {
+				s.st.skipped++
+
+				fmt.Fprintln(os.Stderr, escapePath(warn))
+
+				continue
+			}
+		}
+
+		kept = append(kept, root)
+	}
+
+	return kept
 }
 
 // loadIndex indexes the database records under the scan roots for
@@ -306,6 +408,7 @@ func (s *scanState) walkPhase(
 		}
 
 		s.sizes = append(s.sizes, ev.rec.size)
+		s.st.walked++
 
 		prog.increment()
 
@@ -509,16 +612,22 @@ func (s *scanState) recordRun(ctx context.Context, r hashResult) error {
 }
 
 // commitFullBatch commits the running batch once it holds
-// updateBatchSize records.
+// 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.
 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 err
+	return nil
 }
 
 // updatePhase writes the scan's tail under one progress display: the
@@ -789,11 +898,43 @@ func sendEvent(ctx context.Context, events chan<- walkEvent,
 	}
 }
 
+// operandWarning returns the one-line warning for an operand the walk
+// does not start from, naming the path and what it is, or "" for one it
+// does: a regular file, or a directory not named .zfs. Symlinks are
+// never followed, including as operands.
+func operandWarning(root string, fi fs.FileInfo) string {
+	var kind string
+
+	switch mode := fi.Mode(); {
+	case mode.IsRegular():
+		return ""
+	case mode.IsDir():
+		if filepath.Base(root) != ".zfs" {
+			return ""
+		}
+
+		kind = ".zfs directory"
+	case mode&fs.ModeSymlink != 0:
+		kind = "symlink"
+	case mode&fs.ModeSocket != 0:
+		kind = "socket"
+	case mode&fs.ModeNamedPipe != 0:
+		kind = "FIFO"
+	case mode&fs.ModeDevice != 0:
+		kind = "device node"
+	default:
+		kind = "non-regular file"
+	}
+
+	return fmt.Sprintf("walk %s: skipping %s operand", root, kind)
+}
+
 // seedRoot turns one PATH operand into the walk's starting state: a
-// regular-file operand is statted and emitted directly, a directory
-// operand becomes an initial job, and a symlink or other non-regular
-// operand yields nothing (symlinks are never followed, including as
-// operands).
+// regular-file operand is statted and emitted directly, and a directory
+// operand becomes an initial job. walkableRoots has already dropped
+// every other operand. One that has changed into something else since
+// is warned about and skipped here; it is still a root, so the records
+// stored beneath it are deleted as unverified.
 func seedRoot(ctx context.Context, root string,
 	events chan<- walkEvent,
 ) []dirJob {
@@ -807,16 +948,19 @@ func seedRoot(ctx context.Context, root string,
 		return nil
 	}
 
-	switch {
-	case fi.IsDir():
-		if filepath.Base(root) == ".zfs" {
+	warn := operandWarning(root, fi)
+	if warn != "" {
+		sendEvent(ctx, events, walkEvent{warn: warn, fail: true})
+
 		return nil
 	}
 
+	if fi.IsDir() {
 		dev, ok := deviceOfInfo(fi)
 
 		return []dirJob{{path: root, rootDev: dev, rootDevOK: ok}}
-	case fi.Mode().IsRegular():
+	}
+
 	dev, ino := inodeOfInfo(fi)
 
 	sendEvent(ctx, events, walkEvent{rec: fileRec{
@@ -828,9 +972,6 @@ func seedRoot(ctx context.Context, root string,
 	}})
 
 	return nil
-	default:
-		return nil
-	}
 }
 
 // startWalkWorkers starts the walk worker pool. Each worker processes
@@ -929,6 +1070,12 @@ 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

@@ -6,14 +6,18 @@ import (
 	"crypto/sha256"
 	"database/sql"
 	"encoding/hex"
+	"errors"
 	"fmt"
 	"io"
+	"io/fs"
 	"os"
+	"os/signal"
 	"path/filepath"
 	"runtime"
 	"slices"
 	"strconv"
 	"strings"
+	"syscall"
 	"testing"
 	"time"
 )
@@ -400,7 +404,7 @@ func TestScanContentGate(t *testing.T) {
 		}
 	}
 
-	groups := collectDupeGroups(recs)
+	groups := dupeGroups(t, db)
 	if len(groups) != 1 || !slices.Equal(groups[0].paths, same) {
 		t.Fatalf("groups = %+v, want only the identical pair %q",
 			groups, same)
@@ -435,7 +439,7 @@ func TestScanContentAcrossOperands(t *testing.T) {
 	want := []string{a, b}
 	slices.Sort(want)
 
-	groups := collectDupeGroups(recs)
+	groups := dupeGroups(t, db)
 	if len(groups) != 1 || !slices.Equal(groups[0].paths, want) {
 		t.Fatalf("groups = %+v, want the pair %q", groups, want)
 	}
@@ -456,13 +460,13 @@ func TestScanContentWithinOperand(t *testing.T) {
 	added := sparseFile(t, dir, "d2", headTailMin)
 
 	st := syncTree(t, db, dir)
-	if st != (scanStats{added: 1, unchanged: 2}) {
+	if st != (scanStats{walked: 3, added: 1, unchanged: 2}) {
 		t.Fatalf("rescan stats = %+v, want 1 added 2 unchanged", st)
 	}
 
 	want := []string{stored, added}
 
-	groups := collectDupeGroups(dbRecords(t, db))
+	groups := dupeGroups(t, db)
 	if len(groups) != 1 || !slices.Equal(groups[0].paths, want) {
 		t.Fatalf("groups = %+v, want the pair %q", groups, want)
 	}
@@ -502,7 +506,7 @@ func TestScanContentStalePartners(t *testing.T) {
 	sparseFile(t, dirB, "changed-copy", headTailMin+1)
 
 	st := syncTree(t, db, dirB)
-	if st != (scanStats{added: 2}) {
+	if st != (scanStats{walked: 2, added: 2}) {
 		t.Errorf("stats = %+v, want 2 added and nothing skipped", st)
 	}
 
@@ -520,7 +524,7 @@ func TestScanContentStalePartners(t *testing.T) {
 		}
 	}
 
-	if groups := collectDupeGroups(recs); len(groups) != 0 {
+	if groups := dupeGroups(t, db); len(groups) != 0 {
 		t.Errorf("groups = %+v, want none", groups)
 	}
 }
@@ -559,7 +563,7 @@ func TestScanContentHashedStalePartners(t *testing.T) {
 	b := sparseFile(t, t.TempDir(), "copy", headTailMin)
 
 	st := syncTree(t, db, filepath.Dir(b))
-	if st != (scanStats{added: 1}) {
+	if st != (scanStats{walked: 1, added: 1}) {
 		t.Errorf("stats = %+v, want 1 added and nothing skipped", st)
 	}
 
@@ -571,7 +575,7 @@ 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 := collectDupeGroups(recs)
+	groups := dupeGroups(t, db)
 	if len(groups) != 1 || !slices.Equal(groups[0].paths, stored) {
 		t.Errorf("groups = %+v, want only the stored pair %q", groups, stored)
 	}
@@ -599,7 +603,7 @@ func TestScanContentReadFailure(t *testing.T) {
 	b := sparseFile(t, dirB, "b", headTailMin)
 
 	st := syncTree(t, db, dirB)
-	if st != (scanStats{added: 1, skipped: 1}) {
+	if st != (scanStats{walked: 1, added: 1, skipped: 1}) {
 		t.Fatalf("stats = %+v, want 1 added 1 skipped", st)
 	}
 
@@ -613,14 +617,14 @@ func TestScanContentReadFailure(t *testing.T) {
 	}
 
 	st = syncTree(t, db, dirB)
-	if st != (scanStats{unchanged: 1}) {
+	if st != (scanStats{walked: 1, unchanged: 1}) {
 		t.Fatalf("rescan stats = %+v, want 1 unchanged", st)
 	}
 
 	want := []string{a, b}
 	slices.Sort(want)
 
-	groups := collectDupeGroups(dbRecords(t, db))
+	groups := dupeGroups(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)
@@ -659,7 +663,7 @@ func TestScanContentCheckError(t *testing.T) {
 	b := sparseFile(t, t.TempDir(), "b", headTailMin)
 
 	st := syncTree(t, db, filepath.Dir(b))
-	if st != (scanStats{added: 1, skipped: 1}) {
+	if st != (scanStats{walked: 1, added: 1, skipped: 1}) {
 		t.Fatalf("stats = %+v, want 1 added 1 skipped", st)
 	}
 
@@ -687,7 +691,7 @@ func TestScanContentHardlinks(t *testing.T) {
 	c := sparseFile(t, dir, "copy", headTailMin)
 
 	st := syncTree(t, db, dir)
-	if st != (scanStats{added: 3}) {
+	if st != (scanStats{walked: 3, added: 3}) {
 		t.Fatalf("stats = %+v, want 3 added", st)
 	}
 
@@ -857,9 +861,11 @@ func TestWalkFileAndSymlinkOperands(t *testing.T) {
 		t.Fatalf("file operand: recs = %+v, errs = %d", recs, errs)
 	}
 
-	// A symlink operand is not followed and yields nothing.
+	// A symlink operand that reaches the walk (it became one after
+	// walkableRoots checked it) is not followed: it yields a warning and
+	// no records.
 	recs, errs = collectWalk(t, []string{link}, false, 2)
-	if errs != 0 || len(recs) != 0 {
+	if errs != 1 || len(recs) != 0 {
 		t.Fatalf("symlink operand: recs = %+v, errs = %d", recs, errs)
 	}
 }
@@ -908,6 +914,159 @@ 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 {
@@ -954,11 +1113,16 @@ func syncTree(t *testing.T, db *sql.DB, roots ...string) scanStats {
 	return st
 }
 
-// dbRecords returns every record currently in the database.
+// dbRecords returns every record currently in the database, in path
+// order.
 func dbRecords(t *testing.T, db *sql.DB) []scanRec {
 	t.Helper()
 
-	recs, err := loadFileRows(t.Context(), db)
+	var recs []scanRec
+
+	err := loadFileRows(t.Context(), db, func(r scanRec) {
+		recs = append(recs, r)
+	})
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -995,10 +1159,10 @@ 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, parsed []scanRec) {
+func assertSmokeDupeGroups(t *testing.T, dir string, db *sql.DB) {
 	t.Helper()
 
-	groups := collectDupeGroups(parsed)
+	groups := dupeGroups(t, db)
 	if len(groups) != 5 {
 		t.Fatalf("len(groups) = %d, want 5", len(groups))
 	}
@@ -1023,11 +1187,10 @@ func assertSmokeDupeGroups(t *testing.T, dir string, parsed []scanRec) {
 
 // assertSmokeTreeGroups checks the duplicate-tree groups for the smoke
 // tree rooted at dir.
-func assertSmokeTreeGroups(t *testing.T, dir string, parsed []scanRec) {
+func assertSmokeTreeGroups(t *testing.T, dir string, db *sql.DB) {
 	t.Helper()
 
-	super, dirs := buildHierarchy(parsed)
-	super.compute()
+	super, dirs := dbTree(t, db)
 
 	tg := collectTreeGroups(dirs, super)
 	if len(tg) != 1 {
@@ -1052,7 +1215,7 @@ func TestScanPipeline(t *testing.T) {
 	db := openTestDB(t)
 
 	st := syncTree(t, db, dir)
-	if st != (scanStats{added: smokeTreeFiles}) {
+	if st != (scanStats{walked: smokeTreeFiles, added: smokeTreeFiles}) {
 		t.Fatalf("stats = %+v, want %d added only", st, smokeTreeFiles)
 	}
 
@@ -1061,8 +1224,8 @@ func TestScanPipeline(t *testing.T) {
 		t.Fatalf("len(records) = %d, want %d", len(parsed), smokeTreeFiles)
 	}
 
-	assertSmokeDupeGroups(t, dir, parsed)
-	assertSmokeTreeGroups(t, dir, parsed)
+	assertSmokeDupeGroups(t, dir, db)
+	assertSmokeTreeGroups(t, dir, db)
 }
 
 func TestSyncScanUnchangedReuse(t *testing.T) {
@@ -1075,7 +1238,7 @@ func TestSyncScanUnchangedReuse(t *testing.T) {
 	writeFile(t, dir, "b.bin", pattern(2, 600))
 
 	st := syncTree(t, db, dir)
-	if st != (scanStats{added: 2}) {
+	if st != (scanStats{walked: 2, added: 2}) {
 		t.Fatalf("first scan stats = %+v, want 2 added", st)
 	}
 
@@ -1089,7 +1252,7 @@ func TestSyncScanUnchangedReuse(t *testing.T) {
 	}
 
 	st = syncTree(t, db, dir)
-	if st != (scanStats{unchanged: 2}) {
+	if st != (scanStats{walked: 2, unchanged: 2}) {
 		t.Fatalf("rescan stats = %+v, want 2 unchanged", st)
 	}
 
@@ -1118,7 +1281,7 @@ func TestSyncScanMtimeBump(t *testing.T) {
 	}
 
 	st := syncTree(t, db, dir)
-	if st != (scanStats{updated: 1}) {
+	if st != (scanStats{walked: 1, updated: 1}) {
 		t.Fatalf("mtime-bump stats = %+v, want 1 updated", st)
 	}
 
@@ -1146,7 +1309,7 @@ func TestSyncScanAddRemove(t *testing.T) {
 	}
 
 	st := syncTree(t, db, dir)
-	if st != (scanStats{added: 1, removed: 1, unchanged: 1}) {
+	if st != (scanStats{walked: 2, added: 1, removed: 1, unchanged: 1}) {
 		t.Fatalf("add/remove stats = %+v, want 1 added 1 removed 1 unchanged",
 			st)
 	}
@@ -1263,7 +1426,7 @@ 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{added: 1}) {
+	if st != (scanStats{walked: 1, added: 1}) {
 		t.Fatalf("stats = %+v, want 1 added", st)
 	}
 
@@ -1284,7 +1447,7 @@ 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{added: 2}) {
+	if st != (scanStats{walked: 2, added: 2}) {
 		t.Fatalf("stats = %+v, want 2 added", st)
 	}
 
@@ -1296,7 +1459,7 @@ func TestScanSkipsUniqueSizes(t *testing.T) {
 		}
 	}
 
-	if groups := collectDupeGroups(recs); len(groups) != 0 {
+	if groups := dupeGroups(t, db); len(groups) != 0 {
 		t.Fatalf("groups = %+v, want none from unhashed records", groups)
 	}
 
@@ -1306,12 +1469,12 @@ func TestScanSkipsUniqueSizes(t *testing.T) {
 	c := writeFile(t, dir, "c.bin", pattern(1, 500))
 
 	st = syncTree(t, db, dir)
-	if st != (scanStats{added: 1, updated: 1, unchanged: 1}) {
+	if st != (scanStats{walked: 3, added: 1, updated: 1, unchanged: 1}) {
 		t.Fatalf("rescan stats = %+v, want 1 added 1 updated 1 unchanged",
 			st)
 	}
 
-	groups := collectDupeGroups(dbRecords(t, db))
+	groups := dupeGroups(t, db)
 	if len(groups) != 1 {
 		t.Fatalf("groups = %+v, want the a/c pair", groups)
 	}
@@ -1347,8 +1510,7 @@ func TestTreesUnhashedNeverEqual(t *testing.T) {
 	}
 
 	for name, unknown := range cases {
-		super, dirs := buildHierarchy(append(slices.Clone(shared), unknown...))
-		super.compute()
+		super, dirs := treeOf(t, append(slices.Clone(shared), unknown...))
 
 		if tg := collectTreeGroups(dirs, super); len(tg) != 0 {
 			t.Errorf("%s: tree groups = %d, want 0 (the files may differ)",
@@ -1371,7 +1533,7 @@ func TestScanHardlinksReadOnce(t *testing.T) {
 	}
 
 	st := syncTree(t, db, dir)
-	if st != (scanStats{added: 2}) {
+	if st != (scanStats{walked: 2, added: 2}) {
 		t.Fatalf("stats = %+v, want 2 added", st)
 	}
 
@@ -1385,7 +1547,7 @@ func TestScanHardlinksReadOnce(t *testing.T) {
 		t.Fatalf("hardlink hashes differ: %+v vs %+v", ra, rb)
 	}
 
-	if groups := collectDupeGroups(recs); len(groups) != 1 {
+	if groups := dupeGroups(t, db); len(groups) != 1 {
 		t.Fatalf("groups = %+v, want the hardlink pair", groups)
 	}
 }
@@ -1493,6 +1655,13 @@ 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()
 
@@ -1626,10 +1795,8 @@ func TestReportsNeverTouchFilesystem(t *testing.T) {
 		t.Fatal(err)
 	}
 
-	recs := dbRecords(t, db)
-
-	assertSmokeDupeGroups(t, dir, recs)
-	assertSmokeTreeGroups(t, dir, recs)
+	assertSmokeDupeGroups(t, dir, db)
+	assertSmokeTreeGroups(t, dir, db)
 }
 
 func TestUnderRoot(t *testing.T) {

script/bootstrap

@@ -1,12 +1,9 @@
 #!/bin/sh
 # script/bootstrap: install all dependencies needed to build and develop
-# this repo. Idempotent: every install is guarded by a check so already
-# installed tools are skipped. Base tooling comes from nix, apt, brew,
-# or apk (detected in that order); assumes nothing is present (not git,
-# make, or go). The linter is NOT installed: golangci-lint runs via
-# docker only (script/lint), pinned by image digest, so the only lint
-# prerequisite is a working docker — which is warned about, not
-# installed, because everything except linting works without it.
+# this repo. Idempotent; assumes nothing is present (not git, make, or
+# go). Base tooling comes from nix, apt, brew, or apk (detected in that
+# order). golangci-lint and prettier are never installed: they run via
+# docker only (script/lint, script/fmt, script/fmt-check).
 set -eu
 
 ROOT="$(cd "$(dirname "$0")/.." && pwd -P)"
@@ -61,25 +58,19 @@ missing() {
 main() {
     cd "$ROOT"
 
-    # System tooling, deliberately unpinned: these come from the host
-    # package manager and whatever version it ships is what the host
-    # gets, so a presence check is the right check. The repo pins no
-    # system toolchain versions — the Go language version is governed by
-    # go.mod, and builds that must be reproducible run in the Docker
-    # image, whose base images are pinned by digest.
+    # Deliberately unpinned, so presence is the whole check: go.mod
+    # governs the Go version, and reproducible builds run in the
+    # digest-pinned Docker images.
     if missing git; then pkg_install git git git git; fi
     if missing make; then pkg_install gnumake make make make; fi
     if missing go; then pkg_install go golang go go; fi
 
-    # Linting runs via docker only (script/lint), so docker is a lint
-    # prerequisite rather than something bootstrap installs. Warn, do
-    # not fail: everything except `make lint` — and, through it,
-    # `make check`, `make docker` and the pre-commit hook — works
-    # without it.
+    # Warn, do not fail: only the targets named below, and the
+    # pre-commit hook, need docker.
     if missing docker; then
-        echo "bootstrap: WARNING: docker not found; make lint, make check" >&2
-        echo "bootstrap: and make docker require it. Install docker to" >&2
-        echo "bootstrap: run the linter." >&2
+        echo "bootstrap: WARNING: docker not found; make lint, make fmt," >&2
+        echo "bootstrap: make fmt-check, make check, make docker and" >&2
+        echo "bootstrap: make test-race require it." >&2
     fi
 
     go mod download

script/cibuild

@@ -1,34 +1,19 @@
 #!/bin/sh
 # script/cibuild: run the CI build. The Gitea workflow runs this on
-# push.
+# push. The Dockerfile runs every gate make check runs, as build steps,
+# so a successful build means the repo is green.
 #
-# The Dockerfile runs the gates individually as build steps, not the
-# make check aggregate: the lint stage runs make fmt-check,
-# script/verify-lint-image-pin, golangci-lint config verify and
-# golangci-lint run; the build stage, dropped to an unprivileged user,
-# runs make test and make fmt-check. Neither make lint nor make check
-# appears, because both reach script/lint, which is itself a docker
-# build, and a docker build cannot run inside one. Lint is not skipped
-# by that — the linter is invoked directly in the lint stage, and the
-# build stage's COPY --from=lint makes that stage a prerequisite, so
-# BuildKit must finish it first. Between the two stages everything
-# make check would run has run, which is why a successful build here
-# implies the repo is green.
-#
-# That implication holds only because of CHECK_EPOCH. A COPY layer is
-# invalidated only by changed content, and a rebuild of an unchanged
-# checkout sends the same content, so without a fresh value here Docker
-# serves the gate layers from cache and the build reports a green it
-# never earned. Passing the current epoch invalidates the gate
-# layers on every run while leaving the pinned base images and
-# go mod download cached; see the Dockerfile for the placement.
+# Without a fresh CHECK_EPOCH, a rebuild of an unchanged checkout serves
+# the gate layers from cache and passes having run none of them. The
+# process id goes in with the epoch so two runs started in the same
+# second still differ.
 set -eu
 
 ROOT="$(cd "$(dirname "$0")/.." && pwd -P)"
 
 main() {
     cd "$ROOT"
-    docker build --build-arg CHECK_EPOCH="$(date +%s)" .
+    docker build --build-arg CHECK_EPOCH="$(date +%s)-$$" .
 }
 
 main "$@"

script/docker

@@ -1,14 +1,9 @@
 #!/bin/sh
 # script/docker: build the Docker image tagged with the project name.
-# The tag comes from script/projectname.
-#
-# CHECK_EPOCH is passed for the same reason script/cibuild passes it:
-# without it Docker serves the Dockerfile's gate layers from cache on an
-# unchanged tree and this exits 0 having run neither the lint stage's
-# gates nor the builder stage's test and fmt-check gates. This is the
-# set of gates a developer or reviewer runs by hand, so a cached pass
-# here is the most misleading result the repo can produce. Dependency
-# layers sit above the ARG and stay cached.
+# The tag comes from script/projectname. CHECK_EPOCH is passed for the
+# same reason script/cibuild passes it: without a fresh value an
+# unchanged tree is served from cache and this exits 0 having run no
+# gate.
 set -eu
 
 SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)"
@@ -17,7 +12,7 @@ ROOT="$(cd "$SCRIPT_DIR/.." && pwd -P)"
 main() {
     cd "$ROOT"
     docker build \
-        --build-arg CHECK_EPOCH="$(date +%s)" \
+        --build-arg CHECK_EPOCH="$(date +%s)-$$" \
         -t "$("$SCRIPT_DIR/projectname")" \
         .
 }

script/fmt

@@ -1,12 +1,22 @@
 #!/bin/sh
-# script/fmt: format all files (writes).
+# script/fmt: format all files (writes): the Go sources with gofmt, the
+# Markdown with prettier. prettier is never installed on the host: it
+# runs from the Dockerfile's prettier stage with the repository mounted,
+# as the calling user so the files it rewrites keep their owner. The tag
+# makes each build replace the previous image instead of leaving another
+# one behind.
 set -eu
 
-ROOT="$(cd "$(dirname "$0")/.." && pwd -P)"
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)"
+ROOT="$(cd "$SCRIPT_DIR/.." && pwd -P)"
 
 main() {
     cd "$ROOT"
     gofmt -s -w .
+    image="$("$SCRIPT_DIR/projectname")-prettier"
+    docker build -q --target prettier -t "$image" . >/dev/null
+    docker run --rm --user "$(id -u):$(id -g)" -v "$ROOT:/src" "$image" \
+        prettier --write '**/*.md' --tab-width 4 --prose-wrap always
 }
 
 main "$@"

script/fmt-check

@@ -1,18 +1,39 @@
 #!/bin/sh
 # script/fmt-check: check formatting (read-only). Same scope as
-# script/fmt, but fails instead of writing.
+# script/fmt, but fails instead of writing. gofmt and prettier both run
+# every time and each reports its own failure, so the output says which
+# one failed.
 set -eu
 
-ROOT="$(cd "$(dirname "$0")/.." && pwd -P)"
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)"
+ROOT="$(cd "$SCRIPT_DIR/.." && pwd -P)"
 
 main() {
     cd "$ROOT"
-    files="$(gofmt -s -l .)"
+    status=0
+
+    # Under set -e a bare assignment would end the script when gofmt
+    # fails (a Go file it cannot parse), and prettier would never run.
+    if ! files="$(gofmt -s -l .)"; then
+        echo "gofmt: failed; see its errors above" >&2
+        status=1
+    fi
     if [ -n "$files" ]; then
         echo "gofmt: files not formatted:" >&2
         echo "$files" >&2
-        exit 1
+        status=1
     fi
+
+    # Same image as script/fmt; see there.
+    image="$("$SCRIPT_DIR/projectname")-prettier"
+    docker build -q --target prettier -t "$image" . >/dev/null
+    if ! docker run --rm -v "$ROOT:/src:ro" "$image" \
+        prettier --check '**/*.md' --tab-width 4 --prose-wrap always; then
+        echo "prettier: Markdown not formatted; run make fmt" >&2
+        status=1
+    fi
+
+    exit "$status"
 }
 
 main "$@"

script/lint

@@ -1,19 +1,17 @@
 #!/bin/sh
 # script/lint: run the linter. golangci-lint is never installed on a
-# host: it runs via docker only, one way, everywhere — this builds
-# Dockerfile.lint, which COPYs the repo into the digest-pinned
-# golangci-lint image and lints as a build step, so a successful build
-# is a clean lint. The only prerequisite is a working docker. The gate
-# steps make no network calls of their own, but Dockerfile.lint runs
-# `go mod download` above them, so a cold cache does reach the network
-# (as does pulling the pinned image); that layer stays cached, and once
-# it is warm this runs offline until go.mod or go.sum changes.
+# host: this builds Dockerfile.lint, which copies the repo into the
+# digest-pinned golangci-lint image and lints as a build step, so a
+# successful build is a clean lint. A cold cache needs the network to
+# pull the image and for `go mod download`; once warm this runs offline
+# until go.mod or go.sum changes.
 #
-# CHECK_EPOCH is what makes the result mean anything. Without it docker
-# serves the gate layers from cache on an unchanged tree and this exits
-# 0 in well under a second having run no linter. The PID is in the value
-# as well as the epoch because two lint runs land inside the same second
-# easily, and `date +%s` alone would cache the second one.
+# Without a fresh CHECK_EPOCH docker serves the gate layers from cache
+# on an unchanged tree and this exits 0 having run no linter. The PID is
+# in the value because two lint runs land inside the same second easily.
+#
+# The image is never used, so --output=type=cacheonly writes none;
+# without it every run leaves an untagged image behind.
 set -eu
 
 ROOT="$(cd "$(dirname "$0")/.." && pwd -P)"
@@ -22,6 +20,7 @@ main() {
     cd "$ROOT"
     docker build \
         --build-arg CHECK_EPOCH="$(date +%s)-$$" \
+        --output=type=cacheonly \
         -f Dockerfile.lint \
         .
 }

script/test-race

@@ -0,0 +1,40 @@
+#!/bin/sh
+# script/test-race: run the test suite under the race detector. Not part
+# of script/check.
+#
+# The race detector needs cgo and a C compiler, which the host build
+# never uses, so the tests run in a golang image that has gcc. The
+# checkout is mounted read-only, so the docker daemon must be local. The
+# container starts with empty caches every time: each run downloads the
+# dependencies and compiles them with the detector, which needs the
+# network and takes minutes.
+#
+# The tests run as the calling user, never as root: several of them make
+# a file unreadable and expect reading it to fail, and root reads it
+# anyway. When the caller is root they run as nobody, and then the
+# checkout must be readable by other users. Neither user has a home
+# directory in the image, so HOME is /tmp, where Go puts its build cache.
+set -eu
+
+ROOT="$(cd "$(dirname "$0")/.." && pwd -P)"
+
+# golang:1.25-trixie, 2026-10-04. Debian rather than the Alpine image the
+# Dockerfile builds with, because this one includes gcc.
+IMAGE="golang@sha256:2c4c60ef415fbfa5e90300722293bef36c5e63fae17570ce18f580af933dbd73"
+
+main() {
+    user="$(id -u):$(id -g)"
+    if [ "$(id -u)" -eq 0 ]; then
+        user=65534:65534
+    fi
+    docker run --rm \
+        --user "$user" \
+        --env HOME=/tmp \
+        --env CGO_ENABLED=1 \
+        --volume "$ROOT:/src:ro" \
+        --workdir /src \
+        "$IMAGE" \
+        go test -race -timeout 60s ./...
+}
+
+main "$@"

script/verify-lint-image-pin

@@ -2,23 +2,16 @@
 # script/verify-lint-image-pin: fail unless the golangci-lint image
 # referenced by Dockerfile.lint and the one referenced by the main
 # Dockerfile's lint stage are the same image at the same digest. Our own
-# extension to scripts-to-rule-them-all, not one of its entrypoints.
+# extension to scripts-to-rule-them-all, not one of its entrypoints; run
+# as a gate in both files. Nothing else keeps the two pins in sync, and
+# a bump applied to one alone would lint the same tree against different
+# rulesets, both green.
 #
-# The linter version is pinned in two independent files. That is the
-# shape #42 turned into a build failure rather than tolerate: nothing
-# else keeps the two in sync, and a bump applied to one file alone would
-# leave `make lint` and the fail-fast lint stage of `make docker`
-# linting the same tree against different rulesets, both green. This is
-# the single guard that stops it, run as a gate in both files.
+# Do not hardcode the expected digest here: that is a third copy to keep
+# in sync.
 #
-# It deliberately restates neither pin. A hardcoded expected digest here
-# would be a third copy — one more thing to bump, and the same drift one
-# file further out. It compares the two files to each other and knows
-# nothing about which version is correct.
-#
-# A reference that cannot be read is a hard failure, not a skip: a
-# comparison of two empty strings succeeds, which would turn this guard
-# into exactly the unearned green it exists to prevent.
+# A reference that cannot be read is a hard failure, not a skip: two
+# empty strings compare equal.
 set -eu
 
 ROOT="$(cd "$(dirname "$0")/.." && pwd -P)"

trees.go

@@ -12,39 +12,48 @@ import (
 	"strings"
 )
 
-// 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.
+// treeNode is one directory reconstructed from the record paths.
 type treeNode struct {
 	path   string
 	parent *treeNode
-	dirs      map[string]*treeNode
-	files     map[string]fileSig
+	// entries holds the serialized child entries until the digest is
+	// computed from them, and is then dropped.
+	entries   []string
 	digest    [sha256.Size]byte
 	fileCount int64
 	totalSize int64
 }
 
 // runTrees implements the trees subcommand: it reads every record from
-// 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.
+// the database in path order, reconstructs the directory hierarchy from
+// the record paths, computes a Merkle-style digest per directory, and
+// prints maximal duplicate-tree groups as TSV on stdout. It never
+// touches the scanned filesystem; its only I/O is the database, stdout,
+// and stderr. Any database problem, including a missing database, is
+// fatal.
 func runTrees(ctx context.Context, stdout io.Writer) error {
-	recs, err := loadRecords(ctx)
+	dbPath := databasePath()
+
+	db, err := openReportDatabase(ctx, dbPath)
 	if err != nil {
 		return err
 	}
 
-	super, allDirs := buildHierarchy(recs)
-	super.compute()
+	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()
 
 	dupes := collectTreeGroups(allDirs, super)
 
@@ -82,73 +91,128 @@ 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",
-		len(recs), len(dupes), dupeTrees, humanBytes(reclaimable))
+		records, len(dupes), dupeTrees, humanBytes(reclaimable))
 
 	return nil
 }
 
-// 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) {
+// 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 {
 	super := &treeNode{}
 
-	var allDirs []*treeNode
+	return &treeBuilder{
+		super: super,
+		open:  []*treeNode{super},
+		names: []string{""},
+	}
+}
 
-	for _, r := range recs {
+// 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]
 
-		node := super
-		for _, c := range comps[:len(comps)-1] {
-			child := node.dirs[c]
-			if child == nil {
-				childPath := node.path + "/" + c
+	// 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++
+	}
 
-				// The root directory's path is "/", not empty, and its
-				// children's paths start with one slash, not two.
+	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 node == super && c == "":
-					childPath = "/"
-				case node == super:
-					childPath = c
-				case node.path == "/":
-					childPath = "/" + c
+	case parent == b.super && name == "":
+		path = "/"
+	case parent == b.super:
+		path = name
+	case parent.path == "/":
+		path = "/" + name
 	}
 
-				child = &treeNode{path: childPath, parent: node}
-				if node.dirs == nil {
-					node.dirs = make(map[string]*treeNode)
-				}
+	b.open = append(b.open, &treeNode{path: path, parent: parent})
+	b.names = append(b.names, name)
+}
 
-				node.dirs[c] = child
-				allDirs = append(allDirs, child)
-			}
+// 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]
 
-			node = child
-		}
+		dir.computeDigest()
 
-		if node.files == nil {
-			node.files = make(map[string]fileSig)
+		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)
 	}
+}
 
-		sig := fileSig{
-			size: r.size, head: r.head, tail: r.tail, content: r.content,
-		}
+// 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 sig.content == "" {
-			sig.content = "unhashed\x00" + r.path
+	// trees containing it never compare equal. Real hashes are hex, so
+	// the NUL-prefixed form cannot collide.
+	if content == "" {
+		content = "unhashed\x00" + r.path
 	}
 
-		node.files[comps[len(comps)-1]] = sig
-	}
-
-	return super, allDirs
+	return "f\x00" + name + "\x00" + strconv.FormatInt(r.size, 10) +
+		"\x00" + r.head + "\x00" + r.tail + "\x00" + content
 }
 
 // collectTreeGroups groups directories by digest and returns every
@@ -190,38 +254,22 @@ func collectTreeGroups(allDirs []*treeNode, super *treeNode) [][]*treeNode {
 	return dupes
 }
 
-// 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)
+// 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)
 
 	h := sha256.New()
-	for _, e := range entries {
+	for _, e := range n.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

@@ -2,6 +2,7 @@ package main
 
 import (
 	"bytes"
+	"database/sql"
 	"slices"
 	"testing"
 )
@@ -30,6 +31,36 @@ 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()
@@ -60,11 +91,10 @@ func groupPaths(groups [][]*treeNode) [][]string {
 	return out
 }
 
-func TestBuildHierarchyCounts(t *testing.T) {
+func TestTreeCounts(t *testing.T) {
 	t.Parallel()
 
-	super, dirs := buildHierarchy(smokeTreeRecs())
-	super.compute()
+	_, dirs := treeOf(t, smokeTreeRecs())
 
 	d := nodeByPath(t, dirs, "/d")
 	if d.fileCount != 6 || d.totalSize != 9300 {
@@ -85,12 +115,12 @@ func TestBuildHierarchyCounts(t *testing.T) {
 	}
 }
 
-func TestBuildHierarchyRootPath(t *testing.T) {
+func TestTreeRootPath(t *testing.T) {
 	t.Parallel()
 
 	// The root directory's path is "/", never empty, and its
 	// children's paths start with a single slash.
-	_, dirs := buildHierarchy([]scanRec{{path: "/f"}, {path: "/srv/g"}})
+	_, dirs := treeOf(t, []scanRec{{path: "/f"}, {path: "/srv/g"}})
 
 	got := make([]string, 0, len(dirs))
 	for _, d := range dirs {
@@ -105,6 +135,56 @@ func TestBuildHierarchyRootPath(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()))
 
@@ -126,8 +206,7 @@ func TestRunTreesEscapesPaths(t *testing.T) {
 func TestTreeDigests(t *testing.T) {
 	t.Parallel()
 
-	super, dirs := buildHierarchy(smokeTreeRecs())
-	super.compute()
+	_, dirs := treeOf(t, smokeTreeRecs())
 
 	t1 := nodeByPath(t, dirs, "/d/t1")
 	t2 := nodeByPath(t, dirs, "/d/t2")
@@ -160,8 +239,7 @@ func TestTreeDigestContentSensitivity(t *testing.T) {
 		{size: 10, head: "DIFF", tail: sharedTail, content: "c", path: "/r/b/f"},
 	}
 
-	super, dirs := buildHierarchy(recs)
-	super.compute()
+	_, dirs := treeOf(t, recs)
 
 	a := nodeByPath(t, dirs, "/r/a")
 	b := nodeByPath(t, dirs, "/r/b")
@@ -174,8 +252,7 @@ func TestTreeDigestContentSensitivity(t *testing.T) {
 func TestCollectTreeGroupsMaximal(t *testing.T) {
 	t.Parallel()
 
-	super, dirs := buildHierarchy(smokeTreeRecs())
-	super.compute()
+	super, dirs := treeOf(t, smokeTreeRecs())
 
 	groups := collectTreeGroups(dirs, super)
 
@@ -199,16 +276,14 @@ func TestCollectTreeGroupsDeterministic(t *testing.T) {
 
 	recs := smokeTreeRecs()
 
-	super, dirs := buildHierarchy(recs)
-	super.compute()
+	super, dirs := treeOf(t, recs)
 
 	forward := groupPaths(collectTreeGroups(dirs, super))
 
 	reversed := slices.Clone(recs)
 	slices.Reverse(reversed)
 
-	superR, dirsR := buildHierarchy(reversed)
-	superR.compute()
+	superR, dirsR := treeOf(t, reversed)
 
 	backward := groupPaths(collectTreeGroups(dirsR, superR))
 	if !slices.EqualFunc(forward, backward, slices.Equal) {
@@ -227,8 +302,7 @@ func TestCollectTreeGroupsSiblings(t *testing.T) {
 		{size: 10, head: "h", tail: "t", content: "c", path: "/p/x2/f"},
 	}
 
-	super, dirs := buildHierarchy(recs)
-	super.compute()
+	super, dirs := treeOf(t, recs)
 
 	got := groupPaths(collectTreeGroups(dirs, super))
 
@@ -250,8 +324,7 @@ func TestCollectTreeGroupsDifferingParents(t *testing.T) {
 		{size: 10, head: "h", tail: "t", content: "c", path: "/q/b/x/f"},
 	}
 
-	super, dirs := buildHierarchy(recs)
-	super.compute()
+	super, dirs := treeOf(t, recs)
 
 	got := groupPaths(collectTreeGroups(dirs, super))
 

yarn.lock

@@ -0,0 +1,8 @@
+# THIS IS AN AUTOGENERATED FILE. DO NOT EDIT THIS FILE DIRECTLY.
+# yarn lockfile v1
+
+
+prettier@3.8.1:
+  version "3.8.1"
+  resolved "https://registry.yarnpkg.com/prettier/-/prettier-3.8.1.tgz#edf48977cf991558f4fcbd8a3ba6015ba2a3a173"
+  integrity sha512-UOnG6LftzbdaHZcKoPFtOcCKztrQ57WkHDeRD9t/PTQtmT0NHSeWWepj6pS0z/N7+08BHFDQVUrfmfMRcZwbMg==