Record each file's size on disk and print it in trees (closes #147)

The files table gets a disk_size column: the file's allocated blocks,
st_blocks × 512, from the lstat the walk already does. scan writes it
with every record it writes. When a rescan finds a file with its size
and mtime unchanged but a different disk_size, it updates disk_size
alone, without reading the file. trees adds disk_size up per directory
and prints it as a column after size. On a compressed or sparse file it
is less than size, so two copies of one tree can differ.

Judgement calls: each row's disk_size is the dupe copy's, not the
first's. A file whose record gets only a new disk_size counts as
unchanged.

Model: opus-5-5

Dockerfile

@@ -1,16 +1,23 @@
-# Every stage declares ARG CACHEBUST first: script/ passes a new value
+# In every stage ARG CACHEBUST comes right after the steps that install
-# on every build, which reruns every RUN step after it. The steps that
+# system packages and download Go's modules, or right after FROM in a
-# compile mount Go's build cache, which survives from build to build.
+# stage with neither, and every step that lints, tests or compiles
+# comes after it. script/ passes a new value on every build, which
+# reruns every RUN step after it. Docker keeps the layers above it
+# until the base image, their own lines or go.mod and go.sum change.
+# The steps that compile mount Go's build cache, and golangci-lint run
+# also mounts golangci-lint's; both survive from build to build. The
+# test phase runs as nobody and so mounts Go's build cache at
+# /tmp/.cache/go-build; its own comment says why.
 
 # Lint phase, built alone by script/lint. The tools are invoked directly
 # rather than through `make lint`, which runs docker itself and so cannot
 # run inside a build step.
 # golangci/golangci-lint:v2.14.0, 2026-10-07
 FROM golangci/golangci-lint@sha256:ad862ba6b3798cbe0fd9fd7408d498fd74fbd2623a92406b2fd3898faf0bf98f AS lint
-ARG CACHEBUST
 WORKDIR /src
 COPY go.mod go.sum ./
 RUN go mod download
+ARG CACHEBUST
 COPY . .
 
 # The gofmt half of `make fmt-check`. gofmt's output is assigned to a
@@ -24,6 +31,7 @@ RUN files="$(gofmt -s -l .)" && \
 # Validates .golangci.yml against the schema the pinned binary embeds.
 RUN golangci-lint config verify --config .golangci.yml
 RUN --mount=type=cache,target=/root/.cache/go-build \
+    --mount=type=cache,target=/root/.cache/golangci-lint \
     golangci-lint run --config .golangci.yml ./...
 
 # Test phase, built alone by script/test. -race needs cgo and so a C
@@ -38,12 +46,12 @@ RUN --mount=type=cache,target=/root/.cache/go-build \
 # nobody (65534) so the tests can write to it.
 # golang:1.25-trixie, 2026-10-04
 FROM golang@sha256:2c4c60ef415fbfa5e90300722293bef36c5e63fae17570ce18f580af933dbd73 AS test
-ARG CACHEBUST
 USER nobody
 ENV HOME=/tmp
 WORKDIR /src
 COPY go.mod go.sum ./
 RUN go mod download
+ARG CACHEBUST
 COPY . .
 RUN --mount=type=cache,target=/tmp/.cache/go-build,uid=65534,gid=65534 \
     go test -count=1 -timeout 90s -race -cover ./... || \
@@ -51,19 +59,19 @@ RUN --mount=type=cache,target=/tmp/.cache/go-build,uid=65534,gid=65534 \
       go test -count=1 -timeout 90s -race -v ./...; exit 1; }
 
 # Build stage. Nothing is wanted from either phase above; the copies are
-# what make BuildKit build them first, so this stage cannot run unless
+# what make BuildKit build them first, so nothing after them can run
-# lint and test passed.
+# unless lint and test passed.
 # golang:1.25-alpine, 2026-07-23
 FROM golang@sha256:56961d79ea8129efddcc0b8643fd8a5416b4e6228cfd477e3fd61deb2672c587 AS builder
-ARG CACHEBUST
-COPY --from=lint /src/go.sum /dev/null
-COPY --from=test /src/go.sum /dev/null
 RUN apk add --no-cache git make
-# A tar-stream context keeps the sender's file owners, which git refuses.
-RUN git config --system --add safe.directory /src
 WORKDIR /src
 COPY go.mod go.sum ./
 RUN go mod download
+ARG CACHEBUST
+COPY --from=lint /src/go.sum /dev/null
+COPY --from=test /src/go.sum /dev/null
+# A tar-stream context keeps the sender's file owners, which git refuses.
+RUN git config --system --add safe.directory /src
 COPY . .
 
 # The version stamped into the binary: the VERSION build argument when

REPO_POLICIES.md

@@ -1,6 +1,6 @@
 ---
 title: Repository Policies
-last_modified: 2026-10-15
+last_modified: 2026-10-18
 ---
 
 This document covers repository structure, tooling, and workflow standards. Code
@@ -159,8 +159,11 @@ style conventions are in separate documents:
     one's findings, and a host-global lock in `$TMPDIR` makes concurrent runs
     exit non-zero with `parallel golangci-lint is running` — a status a caller
     cannot tell from real findings. Both have produced wrong verdicts in this
-    org, in both directions. A container has its own golangci-lint cache, its
+    org, in both directions. A container has its own `TMPDIR`, so the lock is
-    own `TMPDIR` and a digest-pinned binary, so neither is reachable.
+    out of reach. The lint phase does keep golangci-lint's cache between check
+    builds (below), but it lints every checkout at `/src`, and a finding is
+    taken from that cache only for the same files, settings and golangci-lint
+    version.
 
 - **Any build that runs checks is given a new `CACHEBUST` value.** Docker
   invalidates a `COPY` layer only when the copied content changes, so on an
@@ -170,15 +173,21 @@ style conventions are in separate documents:
   id, so no two builds share a value, not even the three in one
   `script/cibuild`. `script/lint`, `script/test`, `script/cibuild` and
   `script/docker` are the four, and there is no fifth — `script/check` runs the
-  two gate phases and `script/fmt-check`, and builds no image of its own. Every
+  two gate phases and `script/fmt-check`, and builds no image of its own. In
-  stage of the `Dockerfile` declares `ARG CACHEBUST` as its first line after
+  every stage of the `Dockerfile`, `ARG CACHEBUST` comes right after the steps
-  `FROM`, and a new value reruns every `RUN` step after that line; `COPY` steps
+  that install system packages and download Go's modules, or right after `FROM`
-  are compared by content and need nothing. A stage without the `ARG` line is
+  in a stage with neither, and every step that lints, tests or compiles comes
-  served from cache on an unchanged tree, so a repository re-vendors the scripts
+  after it. A step that installs anything else as well, such as a
-  and adds the `ARG` lines in one commit. The scripts do not pass `--no-cache`:
+  `script/bootstrap` that also installs node packages, comes after it too. A new
-  it reruns every step too, but it also empties every cache mount, and Go's
+  value reruns every `RUN` step after that line; `COPY` steps are compared by
-  build cache, which the canonical Go `Dockerfile` below mounts so that compiled
+  content and need nothing. Docker keeps the layers above the line until the
-  packages survive between check builds, would start empty every time. A bare
+  base image, their own lines or the files they copy change. A stage without the
+  `ARG` line is served from cache on an unchanged tree, so a repository
+  re-vendors the scripts and adds the `ARG` lines in one commit. The scripts do
+  not pass `--no-cache`: it reruns every step too, but it also builds the layers
+  above the line again and empties every cache mount, so Go's build cache and
+  golangci-lint's, which the canonical Go `Dockerfile` below mounts so that they
+  survive between check builds, would start empty every time. A bare
   `docker build .` is not evidence that anything ran: a sub-second build
   reporting success is a cache hit, not a result. Never invalidate by pruning —
   `docker builder prune` and friends destroy a build cache shared with every
@@ -194,19 +203,25 @@ style conventions are in separate documents:
   `Dockerfile`:
 
     ```dockerfile
-    # Every stage declares ARG CACHEBUST first: script/ passes a new value
+    # In every stage ARG CACHEBUST comes right after the steps that install
-    # on every build, which reruns every RUN step after it. The steps that
+    # system packages and download Go's modules, or right after FROM in a
-    # compile mount Go's build cache, which survives from build to build.
+    # stage with neither, and every step that lints, tests or compiles
+    # comes after it. script/ passes a new value on every build, which
+    # reruns every RUN step after it. Docker keeps the layers above it
+    # until the base image, their own lines or go.mod and go.sum change.
+    # The steps that compile mount Go's build cache, and golangci-lint run
+    # also mounts golangci-lint's; both survive from build to build.
 
     # Lint phase
     # golangci/golangci-lint:v2.x.x, YYYY-MM-DD
     FROM golangci/golangci-lint@sha256:... AS lint
-    ARG CACHEBUST
     WORKDIR /src
     COPY go.mod go.sum ./
     RUN go mod download
+    ARG CACHEBUST
     COPY . .
     RUN --mount=type=cache,target=/root/.cache/go-build \
+        --mount=type=cache,target=/root/.cache/golangci-lint \
         golangci-lint run --config .golangci.yml ./...
 
     # Test phase. -race needs cgo and so a C compiler, which the Debian Go
@@ -214,10 +229,10 @@ style conventions are in separate documents:
     # cache also holds test results, which go test would otherwise replay.
     # golang:1.x, YYYY-MM-DD
     FROM golang@sha256:... AS test
-    ARG CACHEBUST
     WORKDIR /src
     COPY go.mod go.sum ./
     RUN go mod download
+    ARG CACHEBUST
     COPY . .
     RUN --mount=type=cache,target=/root/.cache/go-build \
         go test -count=1 -timeout 90s -race -cover ./... || \
@@ -225,19 +240,19 @@ style conventions are in separate documents:
           go test -count=1 -timeout 90s -race -v ./...; exit 1; }
 
     # Build stage. Nothing is wanted from either phase above; the copies
-    # are what make BuildKit build them first, so this stage cannot run
+    # are what make BuildKit build them first, so nothing after them can
-    # unless lint and test passed.
+    # run unless lint and test passed.
     # golang:1.x-alpine, YYYY-MM-DD
     FROM golang@sha256:... AS builder
-    ARG CACHEBUST
-    COPY --from=lint /src/go.sum /dev/null
-    COPY --from=test /src/go.sum /dev/null
     RUN apk add --no-cache git
-    # A tar-stream context keeps the sender's file owners, which git refuses.
-    RUN git config --system --add safe.directory /src
     WORKDIR /src
     COPY go.mod go.sum ./
     RUN go mod download
+    ARG CACHEBUST
+    COPY --from=lint /src/go.sum /dev/null
+    COPY --from=test /src/go.sum /dev/null
+    # A tar-stream context keeps the sender's file owners, which git refuses.
+    RUN git config --system --add safe.directory /src
     COPY . .
 
     # The VERSION build arg when one is given, otherwise
@@ -274,16 +289,26 @@ style conventions are in separate documents:
     - Keep the runtime stage last, and if you add a stage after it, give it the
       same two copies. A plain `docker build .` builds the last stage's chain
       and nothing else.
-    - Only Go's build cache is mounted (`/root/.cache/go-build`, where Go keeps
+    - Check builds keep these, and none of them can hand back a stale result:
-      it for root), and only on the steps that compile: `golangci-lint run`,
+        - The layers above `ARG CACHEBUST`: the system packages and Go's
-      both `go test` runs and `go build`. It keeps compiled packages between
+          modules. Docker installs the packages again when the base image or the
-      check builds, and Go reuses one only when all its inputs are unchanged, so
+          install line changes, and downloads the modules again when `go.mod` or
-      it saves the compile without skipping a check. Nothing else is kept:
+          `go.sum` changes. Go checks every module against `go.sum` as it
-      golangci-lint's own cache would replay stored findings in place of a lint
+          downloads it, and no later build can change a kept layer. The modules
-      run, and Go builds from whatever files a kept module cache holds without
+          are kept in a layer rather than a cache mount because a cache mount is
-      checking them again (only `go mod verify` does), so a file changed there
+          shared by every build on the host, and Go builds from whatever files
-      would go unnoticed. Go's build cache also holds test results, which is why
+          it holds without checking them again (only `go mod verify` does), so a
-      both `go test` runs carry `-count=1`.
+          file changed there would go unnoticed.
+        - Go's build cache (`/root/.cache/go-build`, where Go keeps it for
+          root), mounted on the steps that compile: `golangci-lint run`, both
+          `go test` runs and `go build`. Go reuses a compiled package only when
+          all its inputs are unchanged. The cache also holds test results, which
+          is why both `go test` runs carry `-count=1`.
+        - golangci-lint's cache (`/root/.cache/golangci-lint`, where the pinned
+          image keeps it), mounted on `golangci-lint run`. golangci-lint reuses
+          a package's findings only when the package's files and those of every
+          package it imports, `go.mod`, the linters and their settings in
+          `.golangci.yml`, and the golangci-lint version are all unchanged.
     - If the project uses `//go:embed` directives that reference build artifacts
       (e.g. a web frontend compiled in a separate stage), the lint phase must
       create placeholder files so the embed directives resolve. Example:
@@ -292,12 +317,20 @@ style conventions are in separate documents:
       in the lint phase. The `golangci/golangci-lint` image is Debian-based and
       has no `apk`, so install with `apt-get` under the Debian package name
       (`libvips-dev`, where alpine says `vips-dev`), and delete the package
-      lists in the same `RUN`, so the layer does not keep them:
+      lists in the same `RUN`, so the layer does not keep them. The test phase,
+      on the Debian Go image, installs the libraries its tests need the same
+      way. Either install goes right after `FROM`, above `ARG CACHEBUST`, so
+      Docker keeps it until the base image or the install line changes:
 
         ```dockerfile
+        FROM golangci/golangci-lint@sha256:... AS lint
         RUN apt-get update \
             && apt-get install -y --no-install-recommends libvips-dev \
             && rm -rf /var/lib/apt/lists/*
+        WORKDIR /src
+        COPY go.mod go.sum ./
+        RUN go mod download
+        ARG CACHEBUST
         ```
 
     - `.dockerignore` lets `.git` into the build context. It keeps out every git

TODO.md

@@ -29,6 +29,167 @@
 
 # Completed Steps
 
+- each record holds `disk_size`, the bytes the file takes on disk: its allocated
+  blocks, `st_blocks` × 512, from the lstat the walk already does. `trees`
+  prints a `disk_size` column after `size`, the sum over the `dupe` copy's
+  files; on a compressed or sparse file it differs from `size`. A rescan updates
+  the `disk_size` of an unchanged file whose size on disk changed, without
+  reading the file (2026-10-27, https://git.eeqj.de/sneak/sfdupes/issues/147)
+
+- the database keeps the number of records and the sum of their sizes in the one
+  row of a `totals` table, which three triggers on `files` keep current. `info`
+  reads that row, and so do `scan`'s `load` phase and the `read` phases of
+  `report` and `trees` for their totals; no count reads every record any more.
+  The triggers make each write to `files` slower. `scan` keeps SQLite's
+  temporary data in memory, which wins back part of that time (2026-10-27,
+  https://git.eeqj.de/sneak/sfdupes/issues/146)
+
+- an operand at or inside a directory named `.zfs` is never scanned, whether
+  given alone or under another operand. `scan` warns about it, counts it as
+  skipped and does not walk it (2026-10-26,
+  https://git.eeqj.de/sneak/sfdupes/issues/142)
+
+- a file or directory removed while the scan runs is not an error, in the walk
+  or in the hash phase. The scan prints no line for it and does not count it as
+  skipped. When the first of several hard links to a file is gone, the hash
+  phase reads the next one instead. On a terminal every progress display starts
+  with the spinner, the hash phase's included. A phase with an exact total ends
+  its line with its percent and a 10-column bar at the terminal's right edge,
+  which no longer moves as the line's length changes. A line too wide for the
+  terminal now loses its rate before its bar. The time remaining is labelled
+  `remain`, not `eta` (2026-10-26, https://git.eeqj.de/sneak/sfdupes/issues/133)
+
+- the `head`, `tail` and `content` columns are BLOBs, each holding the raw 32
+  bytes of a SHA-256, half the size of the hex text they held. The hashes stay
+  raw from the hash phase through the database to `report` and `trees`. Reading
+  a record whose hash is not 32 bytes is an error (2026-10-26,
+  https://git.eeqj.de/sneak/sfdupes/issues/134)
+
+- the hash phase gives every file the walk records three hashes: `head` and
+  `tail`, the SHA-256 of its first and last 64 KiB, and `content`, the SHA-256
+  of the whole file under 100 MiB and of 1 MiB at each gigabyte from 100 MiB up.
+  The 10 MiB and 50 MiB thresholds, the size census, the records stored without
+  hashes and the content phase are gone, so a scan has four phases and a rescan
+  reads only new and changed files. `info` no longer counts the records with
+  hashes, since every record has them (2026-10-25,
+  https://git.eeqj.de/sneak/sfdupes/issues/132)
+
+- re-vendor `REPO_POLICIES.md` and the four scripts that pass `CACHEBUST` from
+  `sneak/prompts` `next` at `0653579`: in the `lint`, `test` and `builder`
+  stages of the `Dockerfile` the module download, and in `builder` the
+  system-package install, now come before `ARG CACHEBUST`, so Docker keeps them
+  until the base image, the install line, `go.mod` or `go.sum` changes, and
+  every step that lints, tests or compiles still comes after it;
+  `golangci-lint run` also keeps golangci-lint's cache. README says the same
+  (2026-10-18, https://git.eeqj.de/sneak/sfdupes/issues/109)
+
+- releases until 1.0 are `v0.0.N` tags on `main`'s tip, so
+  `go install sneak.berlin/go/sfdupes@latest` installs `main`'s tip once it has
+  passed the build; README "Install" says so, says what `@main` and `v0.0.1`
+  give, and how to check an installed binary. `go.mod` retracts `v0.0.1`, the
+  early build without a database. When the linker set no version,
+  `sfdupes --version` prints the main module's version that Go recorded in the
+  binary, the tag or the pseudo-version of a `go install` build, and `dev` only
+  when neither is known (2026-10-17,
+  https://git.eeqj.de/sneak/sfdupes/issues/116)
+
+- `scan` creates the database's directory where the database path leads: the
+  path with its last element cut off as text, never cleaned, so a `..` after a
+  symlinked directory is followed through the symlink, as when the file is
+  opened. With `SFDUPES_DATABASE=/srv/link/../new/db.sqlite` and `/srv/link` a
+  symlink to `/data/x`, it creates `/data/new` and the database in it, where it
+  used to create `/srv/new` and then fail (2026-10-17,
+  https://git.eeqj.de/sneak/sfdupes/issues/119)
+
+- `scan` never records its own database: once the database and its `.lock` file
+  are open, it notes the device and inode of the database file, its `-wal` and
+  `-shm` files and its `.lock` file, and the walk passes over a file with one of
+  them wherever the operands reach it, through a symlinked directory included,
+  printing no line and counting nothing. A record an earlier scan left for one
+  of them is deleted (2026-10-17, https://git.eeqj.de/sneak/sfdupes/issues/115)
+
+- `scan` never records or reads anything that is not on a persistent filesystem
+  (`tmpfs`, `proc`, `sysfs` and the other kernel or memory-backed types),
+  matched by the device ID of each such filesystem, listed as the scan starts
+  from `/proc/self/mountinfo` on Linux and the mounted-filesystem list on macOS,
+  however the walk or the content phase reaches it; no flag turns that off.
+  Below an operand, its walk does not enter the default excludes either, so
+  `sfdupes scan /` skips the kernel's view of the running system and the
+  temporary directories: on Linux `/proc`, `/sys`, `/dev`, `/run`, `/tmp` and
+  `/var/tmp`, on macOS `/dev`, `/private/tmp`, `/private/var/tmp`,
+  `/private/var/vm`, `/System/Volumes/VM` and `/System/Volumes/Data`, and a
+  Windows list, not used yet. An operand at or inside a default exclude is still
+  walked. The scan prints a line for each path it leaves out, without counting
+  it as skipped, and the records there count as outside the scanned operands, as
+  for `-x`. `--no-default-excludes` turns off the default excludes only, and
+  `scan --help` lists them (2026-10-17,
+  https://git.eeqj.de/sneak/sfdupes/issues/124)
+
+- the rate a progress display shows covers the items completed over the last 5
+  seconds, or since the line before when stderr is not a terminal, so it falls
+  to 0 while nothing completes, and a burst after a wait no longer reads as a
+  steady rate of over 1,000 files a second; the ETA still comes from the phase's
+  average. Once no item has completed for 10 seconds, the word `stalled` and
+  where the phase waits take the rate's place, as `stalled disk/db`: `disk`,
+  `db`, `out` for stdout or `cpu`, or two of them for a phase that may wait on
+  either, each phase giving its word where it is defined. A line too wide for
+  the terminal loses its bar first, then its rate or those words, so the phase,
+  progress, elapsed time and ETA stay whole. On an 80-column terminal, at counts
+  like those of README's example, the content phase's checks and reads lose
+  those words at most times in minutes, and every other phase keeps them
+  whenever the elapsed time and the ETA are both in minutes. The content phase's
+  last partial batch is now written under a display of its own (2026-10-16,
+  https://git.eeqj.de/sneak/sfdupes/issues/125)
+
+- new subcommand `info` prints the database's details on stdout, one per line as
+  a name, a tab and the value: its path and where it came from, the sizes of the
+  database file and of its `-wal` file when there is one, when the database file
+  was last changed, the schema version, the number of records, how many have
+  head and tail hashes and how many a content hash, and the sizes of all records
+  added up. It opens the database as `report` does, and shows two phases on
+  stderr, `[1/2] open` and `[2/2] count`; the schema version and the counts come
+  from one read-only transaction, the counts from one query (2026-10-16,
+  https://git.eeqj.de/sneak/sfdupes/issues/117)
+
+- `report` shows its work on stderr in two phases, `[1/2] open` and
+  `[2/2] read`, with the progress display `scan` and `trees` use, from the
+  moment it starts until the summary line: `open` says it is opening the
+  database, also while it waits on a busy one; `read` counts the records, then
+  reads them against that count in signature order, which SQLite takes from the
+  `files_signature` index without sorting, so the first record comes at once.
+  `report` forms the duplicate groups itself, holding only those of the size it
+  is reading, and writes them ordered by first path before it reads the next
+  size. stdout and the summary line are unchanged, and SQLite no longer needs a
+  temporary file to sort in (2026-10-16,
+  https://git.eeqj.de/sneak/sfdupes/issues/114)
+
+- `trees` shows its work on stderr in four phases, `[1/4] open`, `[2/4] read`,
+  `[3/4] group` and `[4/4] write`, each with the progress display `scan` uses,
+  from the moment it starts until the summary line: `open` says it is opening
+  the database, also while it waits on a busy one; `read` counts the records,
+  then reads them against that count; `group` counts the directories it groups,
+  and `write` the groups it writes. A display's rate names what its phase
+  counts: files, records, directories or groups. stdout and the summary line are
+  unchanged. When stdout and stderr are the same file, as one terminal is, none
+  of stdout's lines shares a line with the display; when they are not, the
+  display keeps being drawn while stdout waits on a slow reader (2026-10-16,
+  https://git.eeqj.de/sneak/sfdupes/issues/113)
+
+- each `scan` phase's progress display names the phase and its place among the
+  five, as `[2/5] walk`, from the moment it starts, with its progress, elapsed
+  time and ETA: `load` counts the records first, the walk's total is estimated
+  from the records under the operands, and the content phase counts the records
+  it checks from SQLite's grouping alone, then says it is searching the database
+  until the first one is returned. On a terminal a phase with an exact total
+  draws its line followed by the library's bar, and any other a spinner followed
+  by the line; every display is drawn again several times a second. No line
+  reaches the terminal's last column, however narrow, also after the terminal is
+  made narrower during a phase: a line too wide leaves out its rate, then its
+  bar, keeping the phase, progress, elapsed time and ETA whole, and is cut short
+  only when those alone do not fit, as below about 70 columns late in a large
+  scan. In plain mode the line is printed every 5 seconds whether or not an item
+  completed (2026-10-16, https://git.eeqj.de/sneak/sfdupes/issues/112)
+
 - `scan`, `report` and `trees` first print a line on stderr naming the database
   they use, as an absolute path, and whether that path is the default or comes
   from `SFDUPES_DATABASE`; `scan` says when the database is new. README
@@ -47,7 +208,11 @@
   and the build stage installs `git` and `make` itself; a new push cancels the
   workflow's older run on the same branch, and a run stops after 20 minutes;
   `.claude/settings.json` is deleted (2026-10-15,
-  https://git.eeqj.de/sneak/sfdupes/issues/95)
+  https://git.eeqj.de/sneak/sfdupes/issues/95). Since
+  https://git.eeqj.de/sneak/sfdupes/issues/109 the module download in `lint`,
+  `test` and the build stage, and the install of `git` and `make` in the build
+  stage, come before `ARG CACHEBUST`, and Docker keeps them between builds;
+  every step that lints, tests or compiles still runs on every build
 
 - with `-x`, an operand under another operand is walked on its own instead of
   being dropped when a directory from it (from its directory, for a regular
@@ -248,9 +413,9 @@
   a `CHECK_EPOCH` build argument; since
   https://git.eeqj.de/sneak/sfdupes/issues/95 every `docker build` in `script/`
   passes a new `CACHEBUST` value instead, which every stage of the `Dockerfile`
-  declares first. Run as root, the tests fail
+  declares before every step that lints, tests or compiles. Run as root, the
-  `TestScanHardlinkRunFailsTogether`, because root reads through the `chmod(0)`
+  tests fail `TestScanHardlinkRunFailsTogether`, because root reads through the
-  the test relies on, so the `test` phase runs them as `nobody`
+  `chmod(0)` the test relies on, so the `test` phase runs them as `nobody`
 - 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

cancel_test.go

@@ -2,6 +2,7 @@ package main
 
 import (
 	"context"
+	"crypto/sha256"
 	"database/sql"
 	"errors"
 	"fmt"
@@ -168,8 +169,8 @@ func assertRecordsIntact(t *testing.T, db *sql.DB, before []string) {
 
 // TestSyncScanCancelledMidWalkKeepsRecords is the regression net under
 // the post-walk guard. The scan is cancelled part-way through the
-// walk, so it reaches the guard holding a genuinely partial size
+// walk, so it reaches the guard having walked a genuinely partial tree
-// census and a still-populated index of records the walk never got to.
+// and holding a still-populated index of records the walk never got to.
 // 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
@@ -196,7 +197,7 @@ func TestSyncScanCancelledMidWalkKeepsRecords(t *testing.T) {
 	base := baselineGoroutines(t)
 
 	st, err := syncScan(newWalkClock(walkCancelAtDone), db,
-		[]string{dir}, walkCancelWorkers, false)
+		[]string{dir}, walkCancelWorkers, false, walkRules{})
 
 	assertWalkGuardAborted(t, st, err)
 	assertRecordsIntact(t, db, before)
@@ -208,10 +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)
+// guard: with a walk that reached some files (it really ran) but not
-// nor complete (it really was cut short), and with no record counted
+// all of them (it really was cut short), and with no record counted for
-// for removal. A removal count means the partial census was carried
+// removal. A removal count means the partial walk was carried past
-// past the guard into the update phase, which is the failure this test
+// 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()
@@ -222,30 +223,30 @@ func assertWalkGuardAborted(t *testing.T, st scanStats, err error) {
 	}
 
 	if st.unchanged == 0 {
-		t.Fatalf("stats = %+v: the census is empty, so the walk never "+
+		t.Fatalf("stats = %+v: the walk reached no file, so it never "+
 			"ran and the guard was reached for the wrong reason", st)
 	}
 
 	if st.unchanged >= walkCancelFiles {
-		t.Fatalf("stats = %+v: the census covers the whole tree, so the "+
+		t.Fatalf("stats = %+v: the walk reached the whole tree, so it "+
-			"walk was not cut short", st)
+			"was not cut short", st)
 	}
 
 	// The workers drop every directory still queued once the scan is
 	// cancelled, so only the files in the directories already in flight
-	// can add to the census after the fact. A census beyond that bound
+	// can still be reached after the fact. A walk 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 "+
+		t.Errorf("the walk reached %d files, want at most %d: it kept "+
 			"taking directories off the queue after cancellation",
 			st.unchanged, limit)
 	}
 
 	if st.removed != 0 {
 		t.Errorf("stats = %+v: the scan counted records for removal from "+
-			"a partial census", st)
+			"a partial walk", st)
 	}
 }
 
@@ -268,7 +269,8 @@ func TestSyncScanCancelledBeforeLoadIndex(t *testing.T) {
 	ctx, cancel := context.WithCancel(t.Context())
 	cancel()
 
-	st, err := syncScan(ctx, db, []string{dir}, walkCancelWorkers, false)
+	st, err := syncScan(ctx, db, []string{dir}, walkCancelWorkers, false,
+		walkRules{})
 	if !errors.Is(err, context.Canceled) {
 		t.Fatalf("syncScan on a cancelled context = %v, want %v",
 			err, context.Canceled)
@@ -301,7 +303,7 @@ func TestSyncScanCancelledMidHashKeepsHashedRecords(t *testing.T) {
 	db := openTestDB(t)
 
 	st, err := syncScan(newWalkClock(hashCancelAtDone), db,
-		[]string{dir}, walkCancelWorkers, false)
+		[]string{dir}, walkCancelWorkers, false, walkRules{})
 	if !errors.Is(err, context.Canceled) {
 		t.Fatalf("syncScan cancelled mid-hash = %v, want %v",
 			err, context.Canceled)
@@ -356,7 +358,8 @@ func TestRunScanInterrupted(t *testing.T) {
 	stderr := captureStderr(t)
 	dir := buildSmokeTree(t)
 
-	err := runScan(t.Context(), []string{dir}, walkCancelWorkers, false)
+	err := runScan(t.Context(), []string{dir}, walkCancelWorkers, false,
+		false)
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -380,7 +383,7 @@ func TestRunScanInterrupted(t *testing.T) {
 		defer close(done)
 
 		err = runScan(cancelledContext(t), []string{dir}, walkCancelWorkers,
-			false)
+			false, false)
 	}()
 
 	awaitReturn(t, done, "runScan")
@@ -407,7 +410,8 @@ func TestRunScanInterrupted(t *testing.T) {
 			got, before)
 	}
 
-	err = runScan(t.Context(), []string{dir}, walkCancelWorkers, false)
+	err = runScan(t.Context(), []string{dir}, walkCancelWorkers, false,
+		false)
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -433,7 +437,7 @@ func TestRunScanInterruptedMidHash(t *testing.T) {
 	dir := buildWalkCancelTree(t)
 
 	err := runScan(newWalkClock(hashCancelAtDone), []string{dir},
-		walkCancelWorkers, false)
+		walkCancelWorkers, false, false)
 	if !errors.Is(err, errInterrupted) {
 		t.Fatalf("runScan interrupted mid-hash = %v, want %v",
 			err, errInterrupted)
@@ -617,7 +621,8 @@ func TestWalkOneDirStopsWhenCancelled(t *testing.T) {
 	// Unbuffered and unread: on a cancelled scan every send gives up.
 	events := make(chan walkEvent)
 
-	subs := walkOneDir(cancelledContext(t), dirJob{path: dir}, false, events)
+	subs := walkOneDir(cancelledContext(t), dirJob{path: dir}, false,
+		walkRules{}, events)
 	if len(subs) != 0 {
 		t.Errorf("cancelled walkOneDir returned %+v to descend into, "+
 			"want none", subs)
@@ -637,7 +642,8 @@ func TestWalkWorkersDropQueuedDirs(t *testing.T) {
 
 	missing := filepath.Join(t.TempDir(), "missing")
 
-	jobs, _, events := startWalkWorkers(cancelledContext(t), 2, false)
+	jobs, _, events := startWalkWorkers(cancelledContext(t), 2, false,
+		walkRules{})
 
 	for range 64 {
 		jobs <- dirJob{path: missing}
@@ -668,7 +674,7 @@ func TestWalkWorkerAbandonsSubdirHandoff(t *testing.T) {
 	ctx, cancel := context.WithCancel(t.Context())
 	defer cancel()
 
-	jobs, subdirs, events := startWalkWorkers(ctx, 1, false)
+	jobs, subdirs, events := startWalkWorkers(ctx, 1, false, walkRules{})
 
 	// Fill the hand-back channel to its capacity — one slot per worker
 	// — so the worker's own hand-back is certain to block.
@@ -757,7 +763,9 @@ func TestHashWorkerDropsQueuedRuns(t *testing.T) {
 
 	var hashed atomic.Bool
 
-	hash := func(path string, size int64) (string, string, string, error) {
+	hash := func(path string, size int64) (
+		[sha256.Size]byte, [sha256.Size]byte, [sha256.Size]byte, error,
+	) {
 		hashed.Store(true)
 
 		return hashSignature(path, size)
@@ -797,7 +805,9 @@ func TestHashWorkerAbandonsBlockedSend(t *testing.T) {
 
 	// 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) {
+	hash := func(path string, size int64) (
+		[sha256.Size]byte, [sha256.Size]byte, [sha256.Size]byte, error,
+	) {
 		cancel()
 
 		return hashSignature(path, size)

db.go

@@ -2,6 +2,7 @@ package main
 
 import (
 	"context"
+	"crypto/sha256"
 	"database/sql"
 	"errors"
 	"fmt"
@@ -46,40 +47,88 @@ const dbFilePerm = 0o644
 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. mtime
+// BLOBs because Unix paths are raw bytes, not guaranteed UTF-8.
-// holds whole Unix seconds and mtime_nsec the nanoseconds within that
+// disk_size holds the bytes the file takes on disk. mtime holds whole
-// second.
+// Unix seconds and mtime_nsec the nanoseconds within that second. head,
+// tail and content each hold the raw 32 bytes of a SHA-256.
 const createTableSQL = `
 CREATE TABLE files (
     path       BLOB PRIMARY KEY,
     size       INTEGER NOT NULL,
+    disk_size  INTEGER NOT NULL,
     mtime      INTEGER NOT NULL,
     mtime_nsec INTEGER NOT NULL,
-    head       TEXT NOT NULL,
+    head       BLOB NOT NULL,
-    tail       TEXT NOT NULL,
+    tail       BLOB NOT NULL,
-    content    TEXT NOT NULL
+    content    BLOB NOT NULL
 ) WITHOUT ROWID
 `
 
-// createIndexSQL indexes the records by signature, so report can have
+// createIndexSQL indexes the records by signature, so report can read
-// SQLite group them without sorting the whole table.
+// them in signature order without sorting the table.
 const createIndexSQL = `
 CREATE INDEX files_signature ON files (size, head, tail, content)
 `
 
+// createTotalsSQL creates the totals table, which holds one row: the
+// number of records and the sizes of all records added up. Counting
+// them over files would read every record. The three triggers below
+// keep the row current, in the transaction of each change to files.
+const createTotalsSQL = `
+CREATE TABLE totals (
+    records INTEGER NOT NULL,
+    size    INTEGER NOT NULL
+)
+`
+
+// insertTotalsSQL adds the one row of totals, for an empty files table.
+const insertTotalsSQL = `
+INSERT INTO totals (records, size) VALUES (0, 0)
+`
+
+// totalsAfterInsertSQL counts each inserted record into totals.
+const totalsAfterInsertSQL = `
+CREATE TRIGGER totals_after_insert AFTER INSERT ON files BEGIN
+    UPDATE totals SET records = records + 1, size = size + NEW.size;
+END
+`
+
+// totalsAfterDeleteSQL takes each deleted record out of totals.
+const totalsAfterDeleteSQL = `
+CREATE TRIGGER totals_after_delete AFTER DELETE ON files BEGIN
+    UPDATE totals SET records = records - 1, size = size - OLD.size;
+END
+`
+
+// totalsAfterUpdateSQL replaces a record's old size in totals with its
+// new one. scan's upsert of an existing record is such an update.
+const totalsAfterUpdateSQL = `
+CREATE TRIGGER totals_after_update AFTER UPDATE OF size ON files BEGIN
+    UPDATE totals SET size = size + NEW.size - OLD.size;
+END
+`
+
+// recordCountSQL reads the number of records from totals.
+const recordCountSQL = `
+SELECT records FROM totals
+`
+
 // upsertSQL inserts one file record, replacing any existing record for
 // the same path.
 const upsertSQL = `
-INSERT INTO files (path, size, mtime, mtime_nsec, head, tail, content)
+INSERT INTO files (
-VALUES (?, ?, ?, ?, ?, ?, ?)
+    path, size, disk_size, mtime, mtime_nsec, head, tail, content
+)
+VALUES (?, ?, ?, ?, ?, ?, ?, ?)
 ON CONFLICT (path) DO UPDATE SET
-    size = excluded.size, mtime = excluded.mtime,
+    size = excluded.size, disk_size = excluded.disk_size,
-    mtime_nsec = excluded.mtime_nsec,
+    mtime = excluded.mtime, mtime_nsec = excluded.mtime_nsec,
     head = excluded.head, tail = excluded.tail,
     content = excluded.content
 `
 
-// errNoDatabase reports a missing database file for report/trees.
+// errNoDatabase reports a missing database file for report, trees and
+// info.
 var errNoDatabase = errors.New(
 	"no database (run \"sfdupes scan\" first, or set " + databaseEnv + ")")
 
@@ -91,6 +140,10 @@ var errSchemaVersion = errors.New("unsupported database schema version")
 // database.
 var errScanRunning = errors.New("another scan is running")
 
+// errHashSize reports a record whose head, tail or content is not the
+// 32 bytes of a SHA-256.
+var errHashSize = errors.New("hash is not 32 bytes")
+
 // databasePath resolves the database location: SFDUPES_DATABASE when
 // set and non-empty, the compiled-in default otherwise. It returns the
 // path, with the working directory, its symlinks resolved, put in front
@@ -108,10 +161,8 @@ func databasePath() (string, string, error) {
 	}
 
 	// The working directory as the kernel reports it, with no symlink
-	// in it. os.Getwd may return PWD instead, which can name it through
+	// in it, as README "Database" says. os.Getwd may return PWD
-	// a symlink; a ".." after that symlink then leads somewhere else
+	// instead, which can name it through a symlink.
-	// once the path is cleaned, as scan cleans it to create the
-	// database's directory.
 	wd, err := unix.Getwd()
 	if err != nil {
 		return "", "", fmt.Errorf("resolve database path %s: %w", path, err)
@@ -124,16 +175,39 @@ func databasePath() (string, string, error) {
 	return strings.TrimSuffix(wd, "/") + "/" + path, source, nil
 }
 
+// createDatabaseDirectory creates the directory the database at path
+// goes in, and any directory above it, if missing. path is absolute, as
+// databasePath returns it. The directory is path with its last element
+// cut off as text, by filepath.Split. filepath.Dir would clean it,
+// dropping each ".." together with the directory name before it; when
+// that name is a symlink, the cleaned path names another directory than
+// the one the system reaches when it opens path.
+func createDatabaseDirectory(path string) error {
+	dir, _ := filepath.Split(path)
+
+	err := os.MkdirAll(dir, dbDirPerm)
+	if err != nil {
+		return fmt.Errorf("create database directory: %w", err)
+	}
+
+	return nil
+}
+
 // 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.
+//
+// Each write to files fires a trigger, so SQLite keeps a statement
+// journal for it. temp_store(MEMORY) keeps that journal in memory,
+// which costs far less than a temporary file.
 const scanParams = "_pragma=busy_timeout(10000)" +
 	"&_pragma=journal_mode(WAL)" +
-	"&_pragma=synchronous(NORMAL)"
+	"&_pragma=synchronous(NORMAL)" +
+	"&_pragma=temp_store(MEMORY)"
 
-// reportParams are the connection parameters for report and trees:
+// reportParams are the connection parameters for report, trees and
-// read-only, with the same busy timeout. They set no journal mode,
+// info: read-only, with the same busy timeout. They set no journal
-// because setting one is a write.
+// mode, because setting one is a write.
 const reportParams = "mode=ro" +
 	"&_pragma=busy_timeout(10000)" +
 	"&_pragma=query_only(1)"
@@ -178,9 +252,9 @@ func openDB(path, params string) (*sql.DB, error) {
 // 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)
+	err := createDatabaseDirectory(path)
 	if err != nil {
-		return nil, fmt.Errorf("create database directory: %w", err)
+		return nil, err
 	}
 
 	// Like SQLite, this follows a symlink at path and creates its
@@ -224,9 +298,9 @@ func lockScanDatabase(path string) (*os.File, error) {
 // 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) {
-	err := os.MkdirAll(filepath.Dir(path), dbDirPerm)
+	err := createDatabaseDirectory(path)
 	if err != nil {
-		return nil, fmt.Errorf("create database directory: %w", err)
+		return nil, err
 	}
 
 	db, err := openDB(path, scanParams)
@@ -244,6 +318,42 @@ func openScanDatabase(ctx context.Context, path string) (*sql.DB, error) {
 	return db, nil
 }
 
+// databaseFiles returns, by device and inode, the files of the database
+// at path that the scan keeps open: the database file, its -wal and
+// -shm files and its .lock file, each named from the database's path
+// with symlinks resolved, as SQLite and lockScanDatabase name them. The
+// scan calls it once the database and the lock file are open, so that
+// its walk passes over them however it reaches them, through a
+// symlinked directory included. A file that does not exist then is left
+// out, since no walk can reach it. There is no -journal file while the
+// database is in WAL mode.
+func databaseFiles(path string) ([]fileRec, error) {
+	resolved, err := filepath.EvalSymlinks(path)
+	if err != nil {
+		return nil, fmt.Errorf("resolve database path: %w", err)
+	}
+
+	var files []fileRec
+
+	for _, p := range []string{
+		resolved, resolved + "-wal", resolved + "-shm", resolved + ".lock",
+	} {
+		fi, err := os.Lstat(p)
+		if errors.Is(err, fs.ErrNotExist) {
+			continue
+		}
+
+		if err != nil {
+			return nil, fmt.Errorf("database: %w", err)
+		}
+
+		dev, ino := inodeOfInfo(fi)
+		files = append(files, fileRec{path: p, dev: dev, ino: ino})
+	}
+
+	return files, 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
@@ -262,9 +372,9 @@ func closeScanDatabase(ctx context.Context, db *sql.DB, path string) {
 	_ = db.Close()
 }
 
-// openReportDatabase opens an existing database for the report and
+// openReportDatabase opens an existing database for the report, trees
-// trees subcommands. A missing database file is an error directing the
+// and info subcommands. A missing database file is an error directing
-// user to run scan first; the schema version must match exactly.
+// the user to run scan first; the schema version must match exactly.
 func openReportDatabase(ctx context.Context,
 	path string,
 ) (*sql.DB, error) {
@@ -367,14 +477,14 @@ func createSchema(ctx context.Context, db *sql.DB) error {
 
 	defer func() { _ = tx.Rollback() }()
 
-	_, err = tx.ExecContext(ctx, createTableSQL)
+	for _, stmt := range []string{
-	if err != nil {
+		createTableSQL, createIndexSQL, createTotalsSQL, insertTotalsSQL,
-		return fmt.Errorf("create schema: %w", err)
+		totalsAfterInsertSQL, totalsAfterDeleteSQL, totalsAfterUpdateSQL,
-	}
+	} {
-
+		_, err = tx.ExecContext(ctx, stmt)
-	_, err = tx.ExecContext(ctx, createIndexSQL)
+		if err != nil {
-	if err != nil {
+			return fmt.Errorf("create schema: %w", err)
-		return fmt.Errorf("create schema: %w", err)
+		}
 	}
 
 	_, err = tx.ExecContext(ctx,
@@ -403,12 +513,34 @@ func userVersion(ctx context.Context, db *sql.DB) (int, error) {
 	return v, nil
 }
 
-// loadFileRows streams every record to fn in path order: byte order,
+// loadFileRows gives total the number of records, then streams every
-// which is the order of the primary key, so SQLite does not sort.
+// record to fn in path order: byte order, which is the order of the
-func loadFileRows(ctx context.Context, db *sql.DB, fn func(r scanRec)) error {
+// primary key, so SQLite does not sort. The count and the records are
-	rows, err := db.QueryContext(ctx,
+// read in one transaction, so they agree while a scan is committing.
-		"SELECT path, size, mtime, mtime_nsec, head, tail, content "+
+func loadFileRows(ctx context.Context, db *sql.DB, total func(n int64),
-			"FROM files ORDER BY path")
+	fn func(r scanRec),
+) error {
+	// Everything goes through tx: db has one connection, so a query on
+	// db would wait for tx forever.
+	tx, err := db.BeginTx(ctx, &sql.TxOptions{ReadOnly: true})
+	if err != nil {
+		return fmt.Errorf("read records: %w", err)
+	}
+
+	defer func() { _ = tx.Rollback() }()
+
+	var n int64
+
+	err = tx.QueryRowContext(ctx, recordCountSQL).Scan(&n)
+	if err != nil {
+		return fmt.Errorf("count records: %w", err)
+	}
+
+	total(n)
+
+	rows, err := tx.QueryContext(ctx,
+		"SELECT path, size, disk_size, mtime, mtime_nsec, head, tail, "+
+			"content FROM files ORDER BY path")
 	if err != nil {
 		return fmt.Errorf("read records: %w", err)
 	}
@@ -417,19 +549,25 @@ func loadFileRows(ctx context.Context, db *sql.DB, fn func(r scanRec)) error {
 
 	for rows.Next() {
 		var (
-			path      []byte
+			path, head, tail, content []byte
-			sec, nsec int64
+			sec, nsec                 int64
-			r         scanRec
+			r                         scanRec
 		)
 
-		err = rows.Scan(&path, &r.size, &sec, &nsec, &r.head, &r.tail,
+		err = rows.Scan(&path, &r.size, &r.diskSize, &sec, &nsec,
-			&r.content)
+			&head, &tail, &content)
 		if err != nil {
 			return fmt.Errorf("read record: %w", err)
 		}
 
 		r.path = string(path)
 		r.mtime = time.Unix(sec, nsec)
+
+		err = r.setHashes(head, tail, content)
+		if err != nil {
+			return fmt.Errorf("read record %s: %w", escapePath(r.path), err)
+		}
+
 		fn(r)
 	}
 
@@ -441,88 +579,44 @@ func loadFileRows(ctx context.Context, db *sql.DB, fn func(r scanRec)) error {
 	return nil
 }
 
-// dupeRowsSQL selects every record in a duplicate group, with the
+// signatureRowsSQL selects every record's signature and path in
-// group's first path. A group is the records with a content hash that
+// signature order, largest size first. That is the order of the
-// share a size, head, tail, and content, when there are two or more of
+// files_signature index read backwards, so SQLite reads the index alone
-// them. The rows come in report order: groups by size descending, then
+// and returns the first row at once, with nothing to sort.
-// by first path, and each group's paths ascending.
+const signatureRowsSQL = `
-const dupeRowsSQL = `
+SELECT size, head, tail, content, path
-SELECT g.first, f.path, f.size
+FROM files
-FROM files AS f
+ORDER BY size DESC, head DESC, tail DESC, content DESC
-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
+// loadSignatureRows gives total the number of records, then streams
-// number of records in the database. The count and the rows are read
+// every record's signature and path to fn, without its mtime or its
-// in one transaction, so they agree while a scan is committing. An
+// disk_size, in the order of signatureRowsSQL. The count and the
-// error from fn stops the reading and is returned as it is.
+// records are read in one transaction, so they agree while a scan is
-func loadDupeRows(ctx context.Context, db *sql.DB,
+// committing. An error from fn stops the reading and is returned as it
-	fn func(first, path string, size int64) error,
+// is.
-) (int, error) {
+func loadSignatureRows(ctx context.Context, db *sql.DB,
+	total func(n int64), fn func(r scanRec) error,
+) 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)
+		return fmt.Errorf("read records: %w", err)
 	}
 
 	defer func() { _ = tx.Rollback() }()
 
-	var records int
+	var n int64
 
-	err = tx.QueryRowContext(ctx, "SELECT COUNT(*) FROM files").Scan(&records)
+	err = tx.QueryRowContext(ctx, recordCountSQL).Scan(&n)
 	if err != nil {
-		return 0, fmt.Errorf("read records: %w", err)
+		return fmt.Errorf("count records: %w", err)
 	}
 
-	rows, err := tx.QueryContext(ctx, dupeRowsSQL)
+	total(n)
-	if err != nil {
-		return 0, fmt.Errorf("read records: %w", err)
-	}
 
-	defer func() { _ = rows.Close() }()
+	rows, err := tx.QueryContext(ctx, signatureRowsSQL)
-
-	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
-// it carries hashes to fn. Scan change detection needs no hash
-// values, and skipping the hash columns keeps the scan's in-memory
-// index small on multi-million-file databases.
-func loadFileMeta(ctx context.Context, db *sql.DB,
-	fn func(path string, size int64, mtime time.Time, hashed bool),
-) error {
-	rows, err := db.QueryContext(ctx,
-		"SELECT path, size, mtime, mtime_nsec, head <> '' FROM files")
 	if err != nil {
 		return fmt.Errorf("read records: %w", err)
 	}
@@ -531,17 +625,26 @@ func loadFileMeta(ctx context.Context, db *sql.DB,
 
 	for rows.Next() {
 		var (
-			path            []byte
+			path, head, tail, content []byte
-			size, sec, nsec int64
+			r                         scanRec
-			hashed          int64
 		)
 
-		err = rows.Scan(&path, &size, &sec, &nsec, &hashed)
+		err = rows.Scan(&r.size, &head, &tail, &content, &path)
 		if err != nil {
 			return fmt.Errorf("read record: %w", err)
 		}
 
-		fn(string(path), size, time.Unix(sec, nsec), hashed != 0)
+		r.path = string(path)
+
+		err = r.setHashes(head, tail, content)
+		if err != nil {
+			return fmt.Errorf("read record %s: %w", escapePath(r.path), err)
+		}
+
+		err = fn(r)
+		if err != nil {
+			return err
+		}
 	}
 
 	err = rows.Err()
@@ -552,32 +655,89 @@ func loadFileMeta(ctx context.Context, db *sql.DB,
 	return nil
 }
 
-// contentCandidatesSQL selects every record of at least headTailMin
+// setHashes sets r's head, tail and content to the values read from
-// bytes whose size, head, and tail equal another record's, in each
+// those columns. Each must be the raw 32 bytes of a SHA-256.
-// group (the records sharing a size, head, and tail) where at least one
+func (r *scanRec) setHashes(head, tail, content []byte) error {
-// record has no content hash, with whether each record has one. SQLite
+	for _, b := range [][]byte{head, tail, content} {
-// does the grouping, so no other record's hashes are loaded into
+		if len(b) != sha256.Size {
-// memory; the rows come ordered by size, head, and tail, so each
+			return fmt.Errorf("%w: found %d bytes", errHashSize, len(b))
-// group's rows arrive together.
+		}
-const contentCandidatesSQL = `
+	}
-SELECT f.path, f.size, f.mtime, f.mtime_nsec, f.head, f.tail, f.content <> ''
+
-FROM files AS f
+	r.head = [sha256.Size]byte(head)
-JOIN (
+	r.tail = [sha256.Size]byte(tail)
-    SELECT size, head, tail
+	r.content = [sha256.Size]byte(content)
-    FROM files
+
-    WHERE size >= ? AND head <> ''
+	return nil
-    GROUP BY size, head, tail
+}
-    HAVING COUNT(*) > 1 AND SUM(content = '') > 0
+
-) AS g USING (size, head, tail)
+// countRecords returns the number of records in the database.
-ORDER BY size, head, tail
+func countRecords(ctx context.Context, db *sql.DB) (int64, error) {
+	var n int64
+
+	err := db.QueryRowContext(ctx, recordCountSQL).Scan(&n)
+	if err != nil {
+		return 0, fmt.Errorf("count records: %w", err)
+	}
+
+	return n, nil
+}
+
+// databaseCountsSQL reads the number of records and the sizes of all
+// records added up from totals.
+const databaseCountsSQL = `
+SELECT records, size FROM totals
 `
 
-// loadContentCandidates streams the rows of contentCandidatesSQL to fn:
+// databaseCounts is what info reads from the database: its schema
-// each record, without its content hash, and whether it has one.
+// version and the counts of databaseCountsSQL.
-func loadContentCandidates(ctx context.Context, db *sql.DB,
+type databaseCounts struct {
-	fn func(r scanRec, hashed bool),
+	schemaVersion int
+	records       int64 // every record
+	size          int64 // the sizes of all records added up
+}
+
+// readDatabaseCounts reads the schema version, then the counts of
+// databaseCountsSQL, in one read-only transaction, so both describe the
+// database at one moment while a scan is committing.
+func readDatabaseCounts(ctx context.Context,
+	db *sql.DB,
+) (databaseCounts, error) {
+	var c databaseCounts
+
+	// 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 c, fmt.Errorf("count records: %w", err)
+	}
+
+	defer func() { _ = tx.Rollback() }()
+
+	err = tx.QueryRowContext(ctx, "PRAGMA user_version").
+		Scan(&c.schemaVersion)
+	if err != nil {
+		return c, fmt.Errorf("read schema version: %w", err)
+	}
+
+	err = tx.QueryRowContext(ctx, databaseCountsSQL).
+		Scan(&c.records, &c.size)
+	if err != nil {
+		return c, fmt.Errorf("count records: %w", err)
+	}
+
+	return c, nil
+}
+
+// loadFileMeta streams every record's path, size, disk_size and mtime
+// to fn. Scan change detection needs no hash values, and skipping the
+// hash columns keeps the scan's in-memory index small on
+// multi-million-file databases.
+func loadFileMeta(ctx context.Context, db *sql.DB,
+	fn func(path string, m fileMeta),
 ) error {
-	rows, err := db.QueryContext(ctx, contentCandidatesSQL, headTailMin)
+	rows, err := db.QueryContext(ctx,
+		"SELECT path, size, disk_size, mtime, mtime_nsec FROM files")
 	if err != nil {
 		return fmt.Errorf("read records: %w", err)
 	}
@@ -587,20 +747,18 @@ func loadContentCandidates(ctx context.Context, db *sql.DB,
 	for rows.Next() {
 		var (
 			path      []byte
+			m         fileMeta
 			sec, nsec int64
-			r         scanRec
-			hashed    int64
 		)
 
-		err = rows.Scan(&path, &r.size, &sec, &nsec, &r.head, &r.tail,
+		err = rows.Scan(&path, &m.size, &m.diskSize, &sec, &nsec)
-			&hashed)
 		if err != nil {
 			return fmt.Errorf("read record: %w", err)
 		}
 
-		r.path = string(path)
+		m.mtime = time.Unix(sec, nsec)
-		r.mtime = time.Unix(sec, nsec)
+
-		fn(r, hashed != 0)
+		fn(string(path), m)
 	}
 
 	err = rows.Err()
@@ -618,21 +776,21 @@ func loadContentCandidates(ctx context.Context, db *sql.DB,
 // WAL small and let concurrent reports observe progress.
 const updateBatchSize = 10000
 
-// applyChanges writes one scan's database changes — upserts for new and
+// applyChanges writes upserts for new and changed files and deletes for
-// changed files, deletes for vanished ones — in batched transactions.
+// vanished ones, in batched transactions. Progress is rendered on prog
-// Progress is rendered on prog (one increment per change).
+// (one increment per change).
 func applyChanges(ctx context.Context, db *sql.DB, upserts []scanRec,
 	deletes []string, prog *progress,
 ) error {
 	for batch := range slices.Chunk(upserts, updateBatchSize) {
-		err := applyBatch(ctx, db, batch, nil, prog)
+		err := applyBatch(ctx, db, batch, nil, nil, prog)
 		if err != nil {
 			return err
 		}
 	}
 
 	for batch := range slices.Chunk(deletes, updateBatchSize) {
-		err := applyBatch(ctx, db, nil, batch, prog)
+		err := applyBatch(ctx, db, nil, nil, batch, prog)
 		if err != nil {
 			return err
 		}
@@ -641,10 +799,26 @@ func applyChanges(ctx context.Context, db *sql.DB, upserts []scanRec,
 	return nil
 }
 
-// applyBatch commits one batch of upserts and deletes in a single
+// applyDiskSizes writes the disk_size of each of recs into its record,
-// transaction.
+// in batched transactions, and leaves the rest of the record alone.
+// Progress is rendered on prog (one increment per record).
+func applyDiskSizes(ctx context.Context, db *sql.DB, recs []fileRec,
+	prog *progress,
+) error {
+	for batch := range slices.Chunk(recs, updateBatchSize) {
+		err := applyBatch(ctx, db, nil, batch, nil, prog)
+		if err != nil {
+			return err
+		}
+	}
+
+	return nil
+}
+
+// applyBatch commits one batch of upserts, disk_size updates and
+// deletes in a single transaction.
 func applyBatch(ctx context.Context, db *sql.DB, upserts []scanRec,
-	deletes []string, prog *progress,
+	diskSizes []fileRec, deletes []string, prog *progress,
 ) error {
 	tx, err := db.BeginTx(ctx, nil)
 	if err != nil {
@@ -658,6 +832,11 @@ func applyBatch(ctx context.Context, db *sql.DB, upserts []scanRec,
 		return err
 	}
 
+	err = execDiskSizes(ctx, tx, diskSizes, prog)
+	if err != nil {
+		return err
+	}
+
 	err = execDeletes(ctx, tx, deletes, prog)
 	if err != nil {
 		return err
@@ -683,8 +862,9 @@ func execUpserts(ctx context.Context, tx *sql.Tx, upserts []scanRec,
 	defer func() { _ = st.Close() }()
 
 	for _, r := range upserts {
-		_, err = st.ExecContext(ctx, []byte(r.path), r.size,
+		_, err = st.ExecContext(ctx, []byte(r.path), r.size, r.diskSize,
-			r.mtime.Unix(), r.mtime.Nanosecond(), r.head, r.tail, r.content)
+			r.mtime.Unix(), r.mtime.Nanosecond(),
+			r.head[:], r.tail[:], r.content[:])
 		if err != nil {
 			return fmt.Errorf("upsert %s: %w", r.path, err)
 		}
@@ -695,6 +875,31 @@ func execUpserts(ctx context.Context, tx *sql.Tx, upserts []scanRec,
 	return nil
 }
 
+// execDiskSizes sets the disk_size of the record of each of recs. It
+// does not touch size, so the totals triggers do not fire.
+func execDiskSizes(ctx context.Context, tx *sql.Tx, recs []fileRec,
+	prog *progress,
+) error {
+	st, err := tx.PrepareContext(ctx,
+		"UPDATE files SET disk_size = ? WHERE path = ?")
+	if err != nil {
+		return fmt.Errorf("prepare disk_size update: %w", err)
+	}
+
+	defer func() { _ = st.Close() }()
+
+	for _, r := range recs {
+		_, err = st.ExecContext(ctx, r.diskSize, []byte(r.path))
+		if err != nil {
+			return fmt.Errorf("update disk_size of %s: %w", r.path, err)
+		}
+
+		prog.increment()
+	}
+
+	return nil
+}
+
 // execDeletes removes the records for paths no longer present.
 func execDeletes(ctx context.Context, tx *sql.Tx, deletes []string,
 	prog *progress,

db_test.go

@@ -2,9 +2,11 @@ package main
 
 import (
 	"context"
+	"crypto/sha256"
 	"database/sql"
 	"errors"
 	"fmt"
+	"io/fs"
 	"os"
 	"path/filepath"
 	"slices"
@@ -118,6 +120,116 @@ func TestOpenScanDatabaseCreates(t *testing.T) {
 	}
 }
 
+// TestScanCreatesDatabaseDirectoryAfterSymlink has a database path go
+// through a symlink to a directory, then "..", to a missing directory.
+// With srv/link a symlink to data/x, srv/link/../new/db.sqlite leads to
+// data/new/db.sqlite. lockScanDatabase and openScanDatabase, the two
+// places scan creates the database's directory, must each create the
+// database there, and nothing at srv/new, where the path leads once
+// cleaned as text.
+func TestScanCreatesDatabaseDirectoryAfterSymlink(t *testing.T) {
+	t.Parallel()
+
+	creates := map[string]func(ctx context.Context, path string) error{
+		"lockScanDatabase": func(_ context.Context, path string) error {
+			lock, err := lockScanDatabase(path)
+			if err == nil {
+				_ = lock.Close()
+			}
+
+			return err
+		},
+		"openScanDatabase": func(ctx context.Context, path string) error {
+			db, err := openScanDatabase(ctx, path)
+			if err == nil {
+				_ = db.Close()
+			}
+
+			return err
+		},
+	}
+
+	for name, create := range creates {
+		t.Run(name, func(t *testing.T) {
+			t.Parallel()
+
+			dir, err := filepath.EvalSymlinks(t.TempDir())
+			if err != nil {
+				t.Fatal(err)
+			}
+
+			err = os.MkdirAll(filepath.Join(dir, "data", "x"), 0o750)
+			if err != nil {
+				t.Fatal(err)
+			}
+
+			err = os.Mkdir(filepath.Join(dir, "srv"), 0o750)
+			if err != nil {
+				t.Fatal(err)
+			}
+
+			err = os.Symlink(filepath.Join(dir, "data", "x"),
+				filepath.Join(dir, "srv", "link"))
+			if err != nil {
+				t.Fatal(err)
+			}
+
+			err = create(t.Context(), dir+"/srv/link/../new/db.sqlite")
+			if err != nil {
+				t.Fatalf("%s: %v", name, err)
+			}
+
+			_, err = os.Stat(filepath.Join(dir, "data", "new", "db.sqlite"))
+			if err != nil {
+				t.Errorf("database the path leads to: %v", err)
+			}
+
+			_, err = os.Lstat(filepath.Join(dir, "srv", "new"))
+			if !errors.Is(err, fs.ErrNotExist) {
+				t.Errorf("srv/new: stat error %v, want it missing", err)
+			}
+		})
+	}
+}
+
+// TestDatabaseFiles opens a database through a symlink to its file:
+// databaseFiles finds the database file and its -wal and -shm files
+// beside the symlink's target, where SQLite keeps them, and leaves out
+// the .lock file, which only a scan creates.
+func TestDatabaseFiles(t *testing.T) {
+	t.Parallel()
+
+	path := testDBPath(t)
+	link := filepath.Join(t.TempDir(), "link.sqlite")
+
+	err := os.Symlink(path, link)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	db, err := openScanDatabase(t.Context(), link)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	defer func() { _ = db.Close() }()
+
+	files, err := databaseFiles(link)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	got := make([]string, 0, len(files))
+	for _, f := range files {
+		got = append(got, f.path)
+	}
+
+	want := []string{path, path + "-wal", path + "-shm"}
+	if !slices.Equal(got, want) {
+		t.Errorf("databaseFiles(%s) = %q, want %q", link, got, want)
+	}
+}
+
 func TestOpenDatabaseUnversionedForeign(t *testing.T) {
 	t.Parallel()
 
@@ -284,12 +396,336 @@ func TestCloseScanDatabaseWhileReportOpen(t *testing.T) {
 
 	defer func() { _ = reportDB.Close() }()
 
-	err = loadFileRows(t.Context(), reportDB, func(scanRec) {})
+	err = loadFileRows(t.Context(), reportDB, func(int64) {},
+		func(scanRec) {})
 	if err != nil {
 		t.Fatalf("loadFileRows: %v", err)
 	}
 }
 
+// TestLoadRowsCountAgreeDuringScan has a scan commit records after
+// loadFileRows, as trees calls it, or loadSignatureRows, as report
+// calls it, has counted the records and before it reads them, as when
+// trees or report runs during a scan: each must read exactly as many
+// records as it counted.
+func TestLoadRowsCountAgreeDuringScan(t *testing.T) {
+	t.Parallel()
+
+	loads := map[string]func(context.Context, *sql.DB, func(int64),
+		func(scanRec)) error{
+		"loadFileRows": loadFileRows,
+		"loadSignatureRows": func(ctx context.Context, db *sql.DB,
+			total func(int64), fn func(scanRec),
+		) error {
+			return loadSignatureRows(ctx, db, total, func(r scanRec) error {
+				fn(r)
+
+				return nil
+			})
+		},
+	}
+
+	for name, load := range loads {
+		t.Run(name, func(t *testing.T) {
+			t.Parallel()
+
+			path := testDBPath(t)
+
+			scanDB, err := openScanDatabase(t.Context(), path)
+			if err != nil {
+				t.Fatal(err)
+			}
+
+			defer func() { _ = scanDB.Close() }()
+
+			recs := smokeTreeRecs()
+
+			err = applyChanges(t.Context(), scanDB, recs[:3], nil, nil)
+			if err != nil {
+				t.Fatal(err)
+			}
+
+			reportDB, err := openReportDatabase(t.Context(), path)
+			if err != nil {
+				t.Fatal(err)
+			}
+
+			defer func() { _ = reportDB.Close() }()
+
+			var counted, read int64
+
+			err = load(t.Context(), reportDB, func(n int64) {
+				counted = n
+
+				err := applyChanges(t.Context(), scanDB, recs[3:], nil, nil)
+				if err != nil {
+					t.Error(err)
+				}
+			}, func(scanRec) { read++ })
+			if err != nil {
+				t.Fatal(err)
+			}
+
+			if counted != 3 || read != counted {
+				t.Errorf("counted %d records and read %d, want 3 and 3",
+					counted, read)
+			}
+		})
+	}
+}
+
+// TestLoadRowsRefuseWrongSizeHash stores a record whose head, tail or
+// content is not the 32 bytes of a SHA-256: either one byte, or the 64
+// bytes of a SHA-256 written as hex text. loadFileRows and
+// loadSignatureRows must each fail on it with an error naming its path.
+func TestLoadRowsRefuseWrongSizeHash(t *testing.T) {
+	t.Parallel()
+
+	hexText := strings.Repeat("ab", sha256.Size)
+
+	cases := []struct {
+		name   string
+		update string
+		value  any
+	}{
+		{"one-byte head", "UPDATE files SET head = ?", []byte{0}},
+		{"hex-text head", "UPDATE files SET head = ?", hexText},
+		{"one-byte tail", "UPDATE files SET tail = ?", []byte{0}},
+		{"hex-text tail", "UPDATE files SET tail = ?", hexText},
+		{"one-byte content", "UPDATE files SET content = ?", []byte{0}},
+		{"hex-text content", "UPDATE files SET content = ?", hexText},
+	}
+	for _, c := range cases {
+		t.Run(c.name, func(t *testing.T) {
+			t.Parallel()
+
+			db := openTestDB(t)
+
+			err := applyChanges(t.Context(), db,
+				[]scanRec{{path: "/a/f"}}, nil, nil)
+			if err != nil {
+				t.Fatal(err)
+			}
+
+			_, err = db.ExecContext(t.Context(), c.update, c.value)
+			if err != nil {
+				t.Fatal(err)
+			}
+
+			loads := map[string]func() error{
+				"loadFileRows": func() error {
+					return loadFileRows(t.Context(), db, func(int64) {},
+						func(scanRec) {})
+				},
+				"loadSignatureRows": func() error {
+					return loadSignatureRows(t.Context(), db, func(int64) {},
+						func(scanRec) error { return nil })
+				},
+			}
+
+			for name, load := range loads {
+				err := load()
+				if !errors.Is(err, errHashSize) ||
+					!strings.Contains(err.Error(), "/a/f") {
+					t.Errorf("%s: err = %v, want %v naming /a/f",
+						name, err, errHashSize)
+				}
+			}
+		})
+	}
+}
+
+// queryPlan returns the detail of each line of SQLite's EXPLAIN QUERY
+// PLAN for query.
+func queryPlan(t *testing.T, db *sql.DB, query string) []string {
+	t.Helper()
+
+	rows, err := db.QueryContext(t.Context(), "EXPLAIN QUERY PLAN "+query)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	defer func() { _ = rows.Close() }()
+
+	var plan []string
+
+	for rows.Next() {
+		var (
+			id, parent, unused int
+			detail             string
+		)
+
+		err = rows.Scan(&id, &parent, &unused, &detail)
+		if err != nil {
+			t.Fatal(err)
+		}
+
+		plan = append(plan, detail)
+	}
+
+	err = rows.Err()
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	return plan
+}
+
+// TestSignatureRowsNeedNoSort checks that SQLite reads signatureRowsSQL
+// from the files_signature index alone, with nothing to sort: the
+// first record comes at once, so report's read phase counts each
+// record as it comes rather than waiting on SQLite for all of them.
+func TestSignatureRowsNeedNoSort(t *testing.T) {
+	t.Parallel()
+
+	db := openTestDB(t)
+
+	plan := queryPlan(t, db, signatureRowsSQL)
+
+	want := []string{"SCAN files USING COVERING INDEX files_signature"}
+	if !slices.Equal(plan, want) {
+		t.Errorf("query plan = %q, want %q", plan, want)
+	}
+}
+
+// TestCountsReadOnlyTotals checks that SQLite answers the queries for
+// the number of records and their total size from the one row of
+// totals. A plan that reads files or its index reads every record.
+func TestCountsReadOnlyTotals(t *testing.T) {
+	t.Parallel()
+
+	db := openTestDB(t)
+
+	for _, query := range []string{recordCountSQL, databaseCountsSQL} {
+		plan := queryPlan(t, db, query)
+
+		want := []string{"SCAN totals"}
+		if !slices.Equal(plan, want) {
+			t.Errorf("query plan of %q = %q, want %q", query, plan, want)
+		}
+	}
+}
+
+// TestCountsComeFromTotals sets the row of totals to numbers that files
+// does not hold, then checks that scan's load phase, the read phases of
+// trees and report, and info each report the numbers from totals.
+func TestCountsComeFromTotals(t *testing.T) {
+	t.Parallel()
+
+	// files is empty, so a count over files gives 0 records of 0 bytes.
+	const records, size = 7, 9000
+
+	db := openTestDB(t)
+
+	_, err := db.ExecContext(t.Context(),
+		"UPDATE totals SET records = ?, size = ?", records, size)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	scanTotal, err := countRecords(t.Context(), db)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	var treesTotal, reportTotal int64
+
+	err = loadFileRows(t.Context(), db,
+		func(n int64) { treesTotal = n }, func(scanRec) {})
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	err = loadSignatureRows(t.Context(), db,
+		func(n int64) { reportTotal = n },
+		func(scanRec) error { return nil })
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	info, err := readDatabaseCounts(t.Context(), db)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	for name, got := range map[string]int64{
+		"scan's load":   scanTotal,
+		"trees' read":   treesTotal,
+		"report's read": reportTotal,
+		"info":          info.records,
+	} {
+		if got != records {
+			t.Errorf("%s: %d records, want %d from totals",
+				name, got, records)
+		}
+	}
+
+	if info.size != size {
+		t.Errorf("info: size %d, want %d from totals", info.size, size)
+	}
+}
+
+// assertTotalsMatchFiles fails unless the row of totals holds the
+// number of records and the sizes of all records added up, as counted
+// over files.
+func assertTotalsMatchFiles(t *testing.T, db *sql.DB) {
+	t.Helper()
+
+	got, err := readDatabaseCounts(t.Context(), db)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	var records, size int64
+
+	err = db.QueryRowContext(t.Context(),
+		"SELECT COUNT(*), COALESCE(SUM(size), 0) FROM files").
+		Scan(&records, &size)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	if got.records != records || got.size != size {
+		t.Errorf("totals = %d records of %d bytes, files holds %d of %d",
+			got.records, got.size, records, size)
+	}
+}
+
+// TestTotalsMatchFiles scans the smoke tree, rescans it after two files
+// change size, and rescans it after two files are removed. After each
+// scan the row of totals must agree with files.
+func TestTotalsMatchFiles(t *testing.T) {
+	t.Parallel()
+
+	dir := buildSmokeTree(t)
+	db := openTestDB(t)
+
+	syncTree(t, db, dir)
+	assertTotalsMatchFiles(t, db)
+
+	writeFile(t, dir, "a/one.bin", pattern(10, 2500))
+	writeFile(t, dir, "t1/f1", pattern(30, 1000))
+
+	if st := syncTree(t, db, dir); st.updated != 2 {
+		t.Fatalf("rescan stats = %+v, want 2 updated", st)
+	}
+
+	assertTotalsMatchFiles(t, db)
+
+	for _, name := range []string{"a/unique.bin", "t2/sub/f2"} {
+		err := os.Remove(filepath.Join(dir, name))
+		if err != nil {
+			t.Fatal(err)
+		}
+	}
+
+	if st := syncTree(t, db, dir); st.removed != 2 {
+		t.Fatalf("rescan stats = %+v, want 2 removed", st)
+	}
+
+	assertTotalsMatchFiles(t, db)
+}
+
 func TestApplyChangesRoundTrip(t *testing.T) {
 	t.Parallel()
 
@@ -300,17 +736,20 @@ func TestApplyChangesRoundTrip(t *testing.T) {
 	// written.
 	recs := []scanRec{
 		{
-			size: 2, mtime: time.Unix(20, 999_999_999), head: "h2", tail: "t2",
+			size: 2, mtime: time.Unix(20, 999_999_999), head: testHash("h2"),
-			content: "c2", path: "/a/tab\tnew\nline",
+			tail: testHash("t2"), content: testHash("c2"),
+			path: "/a/tab\tnew\nline",
 		},
 		{
-			size: 1, mtime: time.Unix(10, 0), head: "h1", tail: "t1",
+			size: 1, mtime: time.Unix(10, 0), head: testHash("h1"),
-			content: "c1", path: "/a/x",
+			tail: testHash("t1"), content: testHash("c1"), path: "/a/x",
 		},
 	}
 
-	err := applyChanges(t.Context(), db, recs, nil,
+	prog := newProgress(progressParams{label: "update", total: 4})
-		newProgress("update", 2))
+	defer prog.finish()
+
+	err := applyChanges(t.Context(), db, recs, nil, prog)
 	if err != nil {
 		t.Fatalf("applyChanges: %v", err)
 	}
@@ -324,12 +763,12 @@ func TestApplyChangesRoundTrip(t *testing.T) {
 	// An upsert for an existing path updates in place; a delete
 	// removes exactly its path.
 	upd := scanRec{
-		size: 3, mtime: time.Unix(30, 0), head: "h3", tail: "t3", content: "c3",
+		size: 3, mtime: time.Unix(30, 0), head: testHash("h3"),
-		path: "/a/x",
+		tail: testHash("t3"), content: testHash("c3"), path: "/a/x",
 	}
 
 	err = applyChanges(t.Context(), db, []scanRec{upd},
-		[]string{"/a/tab\tnew\nline"}, newProgress("update", 2))
+		[]string{"/a/tab\tnew\nline"}, prog)
 	if err != nil {
 		t.Fatalf("applyChanges: %v", err)
 	}
@@ -352,13 +791,15 @@ func TestApplyChangesBatching(t *testing.T) {
 	recs := make([]scanRec, 0, n)
 	for i := range n {
 		recs = append(recs, scanRec{
-			size: int64(i), mtime: time.Unix(1, 0), head: "h", tail: "t",
+			size: int64(i), mtime: time.Unix(1, 0), head: testHash("h"),
-			path: fmt.Sprintf("/batch/%07d", i),
+			tail: testHash("t"), path: fmt.Sprintf("/batch/%07d", i),
 		})
 	}
 
-	err := applyChanges(t.Context(), db, recs, nil,
+	prog := newProgress(progressParams{label: "update", total: int64(2 * n)})
-		newProgress("update", int64(n)))
+	defer prog.finish()
+
+	err := applyChanges(t.Context(), db, recs, nil, prog)
 	if err != nil {
 		t.Fatalf("applyChanges: %v", err)
 	}
@@ -372,8 +813,7 @@ func TestApplyChangesBatching(t *testing.T) {
 		deletes = append(deletes, r.path)
 	}
 
-	err = applyChanges(t.Context(), db, nil, deletes,
+	err = applyChanges(t.Context(), db, nil, deletes, prog)
-		newProgress("update", int64(n)))
 	if err != nil {
 		t.Fatalf("applyChanges deletes: %v", err)
 	}

exclude.go

@@ -0,0 +1,195 @@
+package main
+
+// This file holds two rules for the walk (README "Rules for the walk"):
+// the default excludes, the paths a scan's walk does not enter below an
+// operand unless scan is given --no-default-excludes, and the
+// filesystems that are not persistent, on which the scan never records
+// or reads anything.
+
+import (
+	"bufio"
+	"errors"
+	"fmt"
+	"io"
+	"io/fs"
+	"path/filepath"
+	"slices"
+	"strings"
+
+	"golang.org/x/sys/unix"
+)
+
+// The systems that have default excludes, as runtime.GOOS names them.
+const (
+	goosLinux   = "linux"
+	goosDarwin  = "darwin"
+	goosWindows = "windows"
+)
+
+// The fields of a line of mountInfoPath that readMountInfo reads,
+// counted from 0 (see proc(5)): the device ID, as major:minor, is the
+// third field, and after the sixth come optional fields, then a field
+// holding "-", then the filesystem type.
+const (
+	deviceField         = 2
+	optionalFieldsStart = 6
+)
+
+// typesPerHelpLine is how many filesystem types the scan command's help
+// lists on each line.
+const typesPerHelpLine = 6
+
+// errMountInfoLine reports a line of mountInfoPath without the fields
+// readMountInfo reads.
+var errMountInfoLine = errors.New("unexpected line")
+
+// walkRules holds the rules for the walk that a scan sets up as it
+// starts. excludes are the default excludes, or none with
+// --no-default-excludes. nonPersistent maps the device ID of every
+// mounted filesystem that is not persistent to its type; the scan
+// records and reads nothing on one of those, whatever the flags.
+// databaseFiles are the scan's own database files, which the walk
+// passes over (see databaseFiles in db.go).
+type walkRules struct {
+	excludes      []string
+	nonPersistent map[uint64]string
+	databaseFiles []fileRec
+}
+
+// defaultExcludes returns the default excludes of the system goos
+// names, as runtime.GOOS does: a fixed list on Linux, macOS and
+// Windows, and none on any other system.
+func defaultExcludes(goos string) []string {
+	switch goos {
+	case goosLinux:
+		return []string{"/proc", "/sys", "/dev", "/run", "/tmp", "/var/tmp"}
+	case goosDarwin:
+		// A walk of / reaches everything in /System/Volumes/Data through
+		// the firmlinks, so walking it as well would record each of
+		// those files twice.
+		return []string{
+			"/dev", "/private/tmp", "/private/var/tmp", "/private/var/vm",
+			"/System/Volumes/VM", "/System/Volumes/Data",
+		}
+	case goosWindows:
+		// Relative to the root of the drive an operand lies on. The
+		// first three are the page, swap and hibernation files.
+		return []string{
+			"pagefile.sys", "swapfile.sys", "hiberfil.sys",
+			"System Volume Information", "$Recycle.Bin", `Windows\Temp`,
+			`Users\*\AppData\Local\Temp`,
+		}
+	default:
+		return nil
+	}
+}
+
+// isDefaultExclude reports whether path is one of excludes, in which a
+// * matches one path component.
+func isDefaultExclude(path string, excludes []string) bool {
+	for _, pattern := range excludes {
+		// The patterns are fixed, so none is malformed.
+		if ok, _ := filepath.Match(pattern, path); ok {
+			return true
+		}
+	}
+
+	return false
+}
+
+// nonPersistentFilesystemTypes returns the filesystem types that are
+// not persistent: filesystems that the kernel makes up or that are kept
+// in memory. devfs is the macOS filesystem of /dev; the others are
+// Linux names.
+func nonPersistentFilesystemTypes() []string {
+	return []string{
+		"proc", "sysfs", "devtmpfs", "devpts", "tmpfs", "ramfs",
+		"cgroup", "cgroup2", "debugfs", "tracefs", "securityfs", "pstore",
+		"bpf", "configfs", "fusectl", "mqueue", "hugetlbfs", "efivarfs",
+		"binfmt_misc", "autofs", "nsfs", "rpc_pipefs", "selinuxfs", "devfs",
+	}
+}
+
+// nonPersistentLine returns the line the scan prints for path when fi,
+// its lstat, puts it on a filesystem in rules.nonPersistent, and ""
+// when it is on any other.
+func (rules walkRules) nonPersistentLine(path string, fi fs.FileInfo) string {
+	dev, ok := deviceOfInfo(fi)
+	if !ok {
+		return ""
+	}
+
+	fsType, found := rules.nonPersistent[dev]
+	if !found {
+		return ""
+	}
+
+	return fmt.Sprintf("scan: skipped %s (%s, not a persistent filesystem)",
+		path, fsType)
+}
+
+// readMountInfo reads mountinfo, laid out as mountInfoPath is, and
+// returns the device ID of every mounted filesystem that is not
+// persistent, with its type. The device ID is the one each line gives,
+// not that of the file now at its mount point, so a mount that a later
+// mount hides never adds the device of another filesystem.
+func readMountInfo(mountinfo io.Reader) (map[uint64]string, error) {
+	types := nonPersistentFilesystemTypes()
+	devices := make(map[uint64]string)
+	lines := bufio.NewScanner(mountinfo)
+
+	for lines.Scan() {
+		fields := strings.Fields(lines.Text())
+
+		sep := slices.Index(fields, "-")
+		if sep < optionalFieldsStart || sep+1 >= len(fields) {
+			return nil, fmt.Errorf("%w: %q", errMountInfoLine, lines.Text())
+		}
+
+		var major, minor uint32
+
+		_, err := fmt.Sscanf(fields[deviceField], "%d:%d", &major, &minor)
+		if err != nil {
+			return nil, fmt.Errorf("%w: %q", errMountInfoLine, lines.Text())
+		}
+
+		fsType := fields[sep+1]
+		if slices.Contains(types, fsType) {
+			devices[unix.Mkdev(major, minor)] = fsType
+		}
+	}
+
+	return devices, lines.Err()
+}
+
+// defaultExcludesHelp describes, for the scan command's help, the
+// default excludes of the system goos names and, where the scan lists
+// the mounted filesystems, the types it never records anything on.
+func defaultExcludesHelp(goos string) string {
+	var help strings.Builder
+
+	dirs := defaultExcludes(goos)
+	if len(dirs) == 0 {
+		help.WriteString("This system has no default excludes.\n")
+	} else {
+		help.WriteString("Below an operand, the walk does not enter these " +
+			"default excludes, unless\n--no-default-excludes is given:\n\n")
+
+		for _, dir := range dirs {
+			fmt.Fprintf(&help, "  %s\n", dir)
+		}
+	}
+
+	if goos == goosLinux || goos == goosDarwin {
+		help.WriteString("\nWith or without --no-default-excludes, the scan " +
+			"records nothing on a\nfilesystem that is not persistent, " +
+			"one of these types:\n\n")
+
+		types := nonPersistentFilesystemTypes()
+		for line := range slices.Chunk(types, typesPerHelpLine) {
+			fmt.Fprintf(&help, "  %s\n", strings.Join(line, ", "))
+		}
+	}
+
+	return help.String()
+}

exclude_darwin.go

@@ -0,0 +1,52 @@
+//go:build darwin
+
+package main
+
+import (
+	"slices"
+
+	"golang.org/x/sys/unix"
+)
+
+// nonPersistentFilesystems returns the device ID of every mounted
+// filesystem that is not persistent, with its type, from the system's
+// list of mounted filesystems. The device ID is read with lstat on the
+// mount point. Where one filesystem is mounted over another on the same
+// mount point, the later one in the list counts. A mount point that
+// lstat cannot reach is left out.
+func nonPersistentFilesystems() (map[uint64]string, error) {
+	// The first call counts the filesystems, the second lists them.
+	n, err := unix.Getfsstat(nil, unix.MNT_NOWAIT)
+	if err != nil {
+		return nil, err
+	}
+
+	list := make([]unix.Statfs_t, n)
+
+	n, err = unix.Getfsstat(list, unix.MNT_NOWAIT)
+	if err != nil {
+		return nil, err
+	}
+
+	mounts := make(map[string]string, n)
+
+	for _, st := range list[:n] {
+		mounts[unix.ByteSliceToString(st.Mntonname[:])] =
+			unix.ByteSliceToString(st.Fstypename[:])
+	}
+
+	types := nonPersistentFilesystemTypes()
+	devices := make(map[uint64]string)
+
+	for mountPoint, fsType := range mounts {
+		if !slices.Contains(types, fsType) {
+			continue
+		}
+
+		if dev, ok := deviceOfPath(mountPoint); ok {
+			devices[dev] = fsType
+		}
+	}
+
+	return devices, nil
+}

exclude_other.go

@@ -0,0 +1,36 @@
+//go:build !darwin
+
+package main
+
+import (
+	"fmt"
+	"os"
+	"runtime"
+)
+
+// mountInfoPath is the file in which Linux lists the mounts the reading
+// process sees.
+const mountInfoPath = "/proc/self/mountinfo"
+
+// nonPersistentFilesystems returns the device ID of every mounted
+// filesystem that is not persistent, with its type: on Linux read from
+// mountInfoPath (see readMountInfo), and on any other system none.
+func nonPersistentFilesystems() (map[uint64]string, error) {
+	if runtime.GOOS != goosLinux {
+		return map[uint64]string{}, nil
+	}
+
+	f, err := os.Open(mountInfoPath)
+	if err != nil {
+		return nil, err
+	}
+
+	defer func() { _ = f.Close() }()
+
+	devices, err := readMountInfo(f)
+	if err != nil {
+		return nil, fmt.Errorf("read %s: %w", mountInfoPath, err)
+	}
+
+	return devices, nil
+}

exclude_test.go

@@ -0,0 +1,513 @@
+package main
+
+import (
+	"bytes"
+	"errors"
+	"maps"
+	"os"
+	"path/filepath"
+	"runtime"
+	"slices"
+	"strings"
+	"testing"
+
+	"golang.org/x/sys/unix"
+)
+
+func TestDefaultExcludes(t *testing.T) {
+	t.Parallel()
+
+	// README "Rules for the walk": each system's list.
+	cases := map[string][]string{
+		goosLinux: {"/proc", "/sys", "/dev", "/run", "/tmp", "/var/tmp"},
+		goosDarwin: {
+			"/dev", "/private/tmp", "/private/var/tmp", "/private/var/vm",
+			"/System/Volumes/VM", "/System/Volumes/Data",
+		},
+		goosWindows: {
+			"pagefile.sys", "swapfile.sys", "hiberfil.sys",
+			"System Volume Information", "$Recycle.Bin", `Windows\Temp`,
+			`Users\*\AppData\Local\Temp`,
+		},
+		"freebsd": nil,
+	}
+
+	for goos, want := range cases {
+		if got := defaultExcludes(goos); !slices.Equal(got, want) {
+			t.Errorf("defaultExcludes(%q) = %q, want %q", goos, got, want)
+		}
+	}
+}
+
+func TestIsDefaultExclude(t *testing.T) {
+	t.Parallel()
+
+	// A * matches one path component, no more and no fewer.
+	excludes := []string{"/scratch", "/home/*/cache"}
+
+	cases := map[string]bool{
+		"/scratch":        true,
+		"/scratch/x":      false,
+		"/home/u/cache":   true,
+		"/home/u/v/cache": false,
+		"/home/cache":     false,
+	}
+
+	for path, want := range cases {
+		if got := isDefaultExclude(path, excludes); got != want {
+			t.Errorf("isDefaultExclude(%q) = %v, want %v", path, got, want)
+		}
+	}
+}
+
+func TestReadMountInfo(t *testing.T) {
+	t.Parallel()
+
+	// The second-to-last line has no optional fields. The tmpfs on
+	// /data/a/b is hidden by the root filesystem's /srv, mounted over
+	// /data/a after it: the tmpfs still gives its own device, and the
+	// root filesystem's device is not listed.
+	mountinfo := strings.Join([]string{
+		"22 1 8:1 / / rw,relatime shared:1 - ext4 /dev/sda1 rw",
+		"23 22 0:21 / /proc rw,nosuid shared:12 - proc none rw",
+		"24 22 0:22 / /sys rw,nosuid shared:7 - sysfs none rw",
+		"25 22 0:23 / /data/a/b rw shared:2 - tmpfs none rw",
+		"26 22 8:1 /srv /data/a rw - ext4 /dev/sda1 rw",
+		"27 22 0:25 / /srv/auto rw shared:4 - autofs systemd-1 rw",
+	}, "\n")
+
+	got, err := readMountInfo(strings.NewReader(mountinfo))
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	want := map[uint64]string{
+		unix.Mkdev(0, 21): "proc", unix.Mkdev(0, 22): "sysfs",
+		unix.Mkdev(0, 23): "tmpfs", unix.Mkdev(0, 25): "autofs",
+	}
+	if !maps.Equal(got, want) {
+		t.Errorf("readMountInfo = %v, want %v", got, want)
+	}
+
+	for _, line := range []string{
+		"22 1 8:1 / / rw,relatime\n",
+		"22 1 sda / / rw,relatime shared:1 - ext4 /dev/sda1 rw\n",
+	} {
+		_, err = readMountInfo(strings.NewReader(line))
+		if !errors.Is(err, errMountInfoLine) {
+			t.Errorf("readMountInfo(%q) = %v, want %v", line, err,
+				errMountInfoLine)
+		}
+	}
+}
+
+func TestNonPersistentFilesystems(t *testing.T) {
+	t.Parallel()
+
+	if runtime.GOOS != goosLinux {
+		t.Skip("the test knows a mount only on Linux: /proc")
+	}
+
+	nonPersistent, err := nonPersistentFilesystems()
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	dev, ok := deviceOfPath("/proc")
+	if !ok {
+		t.Fatal("no device for /proc")
+	}
+
+	if got := nonPersistent[dev]; got != "proc" {
+		t.Errorf("filesystem of /proc = %q, want %q", got, "proc")
+	}
+}
+
+func TestDefaultExcludesHelp(t *testing.T) {
+	t.Parallel()
+
+	for _, goos := range []string{goosLinux, goosDarwin, goosWindows} {
+		help := defaultExcludesHelp(goos)
+
+		for _, dir := range defaultExcludes(goos) {
+			if !strings.Contains(help, "\n  "+dir+"\n") {
+				t.Errorf("help for %s does not list %s:\n%s", goos, dir, help)
+			}
+		}
+
+		// Only Linux and macOS list their mounted filesystems.
+		for _, fsType := range nonPersistentFilesystemTypes() {
+			listed := strings.Contains(help, " "+fsType+",") ||
+				strings.Contains(help, " "+fsType+"\n")
+			if listed != (goos != goosWindows) {
+				t.Errorf("help for %s lists %s: %v", goos, fsType, listed)
+			}
+		}
+	}
+
+	want := "This system has no default excludes.\n"
+	if got := defaultExcludesHelp("freebsd"); got != want {
+		t.Errorf("help for freebsd = %q, want %q", got, want)
+	}
+
+	// scan's help shows those of the system it runs on.
+	var stdout, stderr bytes.Buffer
+
+	run([]string{cmdScan, "-h"}, &stdout, &stderr)
+
+	help := strings.TrimSpace(defaultExcludesHelp(runtime.GOOS))
+	if !strings.Contains(stderr.String(), help) {
+		t.Errorf("scan --help = %q, want it to hold %q", stderr.String(), help)
+	}
+}
+
+// TestScanDoesNotEnterDefaultExclude checks that the walk does not
+// enter a default exclude below an operand. It says so on a line of its
+// own and does not count it as skipped. The records below it count as
+// outside the operands: the record of a file gone from it is kept,
+// while a file added to it is not recorded.
+//
+//nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
+func TestScanDoesNotEnterDefaultExclude(t *testing.T) {
+	stderr := captureStderr(t)
+	dir := t.TempDir()
+	db := openTestDB(t)
+	excluded := filepath.Join(dir, "tmp")
+
+	// A scan with no default excludes records the file in excluded.
+	gone := writeFile(t, excluded, "gone", pattern(1, 100))
+	syncTree(t, db, dir)
+
+	err := os.Remove(gone)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	unseen := writeFile(t, excluded, "new", pattern(2, 10))
+
+	st, err := syncScan(t.Context(), db, []string{dir}, 1, false,
+		walkRules{excludes: []string{excluded}})
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	if st.skipped != 0 {
+		t.Errorf("skipped = %d, want 0", st.skipped)
+	}
+
+	recs := dbRecords(t, db)
+	recordByPath(t, recs, gone)
+
+	if slices.Contains(recordPaths(recs), unseen) {
+		t.Errorf("%s recorded: the walk entered %s", unseen, excluded)
+	}
+
+	line := "\nscan: skipped " + excluded + " (default exclude)\n"
+	if !strings.Contains(stderr(), line) {
+		t.Errorf("stderr = %q, want %q", stderr(), line)
+	}
+}
+
+// TestScanWalksOperandInDefaultExclude checks that an operand at or
+// inside a default exclude is walked, also when it lies under another
+// operand, whose walk does not enter the default exclude.
+func TestScanWalksOperandInDefaultExclude(t *testing.T) {
+	t.Parallel()
+
+	dir := t.TempDir()
+	excluded := filepath.Join(dir, "tmp")
+	f := writeFile(t, excluded, "sub/f", pattern(1, 10))
+	sub := filepath.Dir(f)
+
+	cases := map[string][]string{
+		"at it":                      {excluded},
+		"inside it":                  {sub},
+		"inside it under an operand": {dir, sub},
+	}
+
+	for name, roots := range cases {
+		t.Run(name, func(t *testing.T) {
+			t.Parallel()
+
+			db := openTestDB(t)
+
+			st, err := syncScan(t.Context(), db, roots, 1, false,
+				walkRules{excludes: []string{excluded}})
+			if err != nil {
+				t.Fatal(err)
+			}
+
+			if st.added != 1 {
+				t.Errorf("added = %d, want %s recorded once", st.added, f)
+			}
+
+			recordByPath(t, dbRecords(t, db), f)
+		})
+	}
+}
+
+// TestScanNamesNoDefaultExcludeThatIsAnOperand checks that a default
+// exclude given as an operand under another operand, which the walk of
+// that other operand does not enter, gets no line saying it was
+// skipped: it is walked as an operand of its own.
+//
+//nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
+func TestScanNamesNoDefaultExcludeThatIsAnOperand(t *testing.T) {
+	stderr := captureStderr(t)
+	dir := t.TempDir()
+	db := openTestDB(t)
+	excluded := filepath.Join(dir, "tmp")
+	f := writeFile(t, excluded, "f", pattern(1, 10))
+
+	st, err := syncScan(t.Context(), db, []string{dir, excluded}, 1, false,
+		walkRules{excludes: []string{excluded}})
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	if st.added != 1 {
+		t.Errorf("added = %d, want %s recorded once", st.added, f)
+	}
+
+	recordByPath(t, dbRecords(t, db), f)
+
+	if strings.Contains(stderr(), "scan: skipped") {
+		t.Errorf("stderr = %q, want no line for %s", stderr(), excluded)
+	}
+}
+
+// TestRunScanTempDirOperand scans a tree in the tests' temporary
+// directory, which on Linux lies inside the default exclude /tmp unless
+// TMPDIR names another place, with the system's own default excludes:
+// the scan walks the whole tree and reports no default exclude.
+func TestRunScanTempDirOperand(t *testing.T) {
+	path := testDBPath(t)
+	t.Setenv(databaseEnv, path)
+
+	dir := t.TempDir()
+	if !underAnyRoot(dir, defaultExcludes(runtime.GOOS)) {
+		t.Skip(dir + " is not inside a default exclude")
+	}
+
+	f := writeFile(t, dir, "sub/f", pattern(1, 10))
+
+	stderr := scanOK(t, dir)
+	if strings.Contains(stderr, "scan: skipped") {
+		t.Errorf("stderr = %q, want no line saying a path was skipped",
+			stderr)
+	}
+
+	assertRecorded(t, path, f, true)
+}
+
+// TestRunScanNoDefaultExcludes scans /var through the command. Its
+// /var/tmp, on a persistent filesystem, is a default exclude on Linux:
+// without --no-default-excludes the walk does not enter it and says so,
+// and with that flag the walk records a file the test puts there.
+func TestRunScanNoDefaultExcludes(t *testing.T) {
+	if runtime.GOOS != goosLinux {
+		t.Skip("only Linux has /var/tmp among its default excludes")
+	}
+
+	nonPersistent, err := nonPersistentFilesystems()
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	rules := walkRules{nonPersistent: nonPersistent}
+
+	for _, dir := range []string{"/var", "/var/tmp"} {
+		fi, lstatErr := os.Lstat(dir)
+		if lstatErr != nil || !fi.IsDir() ||
+			rules.nonPersistentLine(dir, fi) != "" {
+			t.Skip(dir + " is not a directory on a persistent filesystem here")
+		}
+	}
+
+	//nolint:usetesting // the directory must be inside /var/tmp
+	tmp, err := os.MkdirTemp("/var/tmp", "sfdupes-test-")
+	if err != nil {
+		t.Skip("cannot write to /var/tmp here: " + err.Error())
+	}
+
+	t.Cleanup(func() { _ = os.RemoveAll(tmp) })
+
+	f := writeFile(t, tmp, "f", pattern(1, 10))
+
+	path := testDBPath(t)
+	t.Setenv(databaseEnv, path)
+
+	line := "scan: skipped /var/tmp (default exclude)\n"
+
+	if stderr := scanOK(t, "/var"); !strings.Contains(stderr, line) {
+		t.Errorf("scan /var: stderr = %q, want %q", stderr, line)
+	}
+
+	assertRecorded(t, path, f, false)
+
+	stderr := scanOK(t, "--no-default-excludes", "/var")
+	if strings.Contains(stderr, line) {
+		t.Errorf("scan --no-default-excludes /var: stderr = %q, want no %q",
+			stderr, line)
+	}
+
+	assertRecorded(t, path, f, true)
+}
+
+// TestRunScanSkipsNonPersistentOperand scans, through the command, a
+// directory on a filesystem that is not persistent, with and without
+// --no-default-excludes: either way it is skipped, with a line saying
+// so, and nothing in it is recorded.
+func TestRunScanSkipsNonPersistentOperand(t *testing.T) {
+	shm, fsType, _ := shmTempDir(t)
+	writeFile(t, shm, "f", pattern(1, 10))
+
+	t.Setenv(databaseEnv, testDBPath(t))
+
+	line := "scan: skipped " + shm + " (" + fsType +
+		", not a persistent filesystem)\n"
+	summary := "scan: 0 files seen"
+
+	for _, flags := range [][]string{nil, {"--no-default-excludes"}} {
+		stderr := scanOK(t, append(flags, shm)...)
+		if !strings.Contains(stderr, line) ||
+			!strings.Contains(stderr, summary) {
+			t.Errorf("scan %q: stderr = %q, want %q and %q", flags, stderr,
+				line, summary)
+		}
+	}
+}
+
+// TestScanKeepsRecordsOnNonPersistent scans a directory on a filesystem
+// that is not persistent beside one on the tests' temporary directory.
+// The records an earlier scan left in it count as outside the operands:
+// the record of a file gone from it is kept, while a file added to it
+// is not recorded.
+//
+//nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
+func TestScanKeepsRecordsOnNonPersistent(t *testing.T) {
+	shm, fsType, rules := shmTempDir(t)
+	stderr := captureStderr(t)
+	dir := t.TempDir()
+	db := openTestDB(t)
+
+	// A scan that, without the list of filesystems, records gone.
+	gone := writeFile(t, shm, "gone", pattern(1, 100))
+	syncTree(t, db, shm)
+
+	err := os.Remove(gone)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	unseen := writeFile(t, shm, "new", pattern(2, 10))
+
+	st, err := syncScan(t.Context(), db, []string{shm, dir}, 1, false, rules)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	if st.skipped != 0 {
+		t.Errorf("skipped = %d, want 0", st.skipped)
+	}
+
+	recs := dbRecords(t, db)
+	recordByPath(t, recs, gone)
+
+	if slices.Contains(recordPaths(recs), unseen) {
+		t.Errorf("%s recorded", unseen)
+	}
+
+	line := "scan: skipped " + shm + " (" + fsType +
+		", not a persistent filesystem)\n"
+	if !strings.Contains(stderr(), line) {
+		t.Errorf("stderr = %q, want %q", stderr(), line)
+	}
+}
+
+// TestWalkLeavesOutNonPersistent starts the walk itself in a directory
+// on a filesystem that is not persistent, which a scan never does: it
+// drops such an operand first. Below a directory on a persistent
+// filesystem, one on another takes a mount, which a test cannot make.
+// The walk enters no directory and records no file there, and names
+// each.
+func TestWalkLeavesOutNonPersistent(t *testing.T) {
+	t.Parallel()
+
+	shm, fsType, rules := shmTempDir(t)
+	f := writeFile(t, shm, "f", pattern(1, 10))
+	sub := filepath.Dir(writeFile(t, shm, "sub/g", pattern(1, 10)))
+
+	var leftOut []string
+
+	for ev := range startWalk(t.Context(), []string{shm}, false, rules, 1) {
+		if ev.rec.path != "" {
+			t.Errorf("walk recorded %s", ev.rec.path)
+		}
+
+		if ev.leftOut == "" {
+			continue
+		}
+
+		leftOut = append(leftOut, ev.leftOut)
+
+		want := "scan: skipped " + ev.leftOut + " (" + fsType +
+			", not a persistent filesystem)"
+		if ev.warn != want {
+			t.Errorf("line = %q, want %q", ev.warn, want)
+		}
+	}
+
+	slices.Sort(leftOut)
+
+	if want := []string{f, sub}; !slices.Equal(leftOut, want) {
+		t.Errorf("walk left out %q, want %q", leftOut, want)
+	}
+}
+
+// shmTempDir returns a new directory in /dev/shm, removed when the test
+// ends, the type of its filesystem, and the rules holding the real
+// filesystems that are not persistent. It skips the test where /dev/shm
+// is on a persistent filesystem, or cannot be written to.
+func shmTempDir(t *testing.T) (string, string, walkRules) {
+	t.Helper()
+
+	nonPersistent, err := nonPersistentFilesystems()
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	dev, ok := deviceOfPath("/dev/shm")
+
+	fsType, found := nonPersistent[dev]
+	if !ok || !found {
+		t.Skip("/dev/shm is not a memory-backed filesystem here")
+	}
+
+	//nolint:usetesting // the directory must be inside /dev/shm
+	dir, err := os.MkdirTemp("/dev/shm", "sfdupes-test-")
+	if err != nil {
+		t.Skip("cannot write to /dev/shm here: " + err.Error())
+	}
+
+	t.Cleanup(func() { _ = os.RemoveAll(dir) })
+
+	return dir, fsType, walkRules{nonPersistent: nonPersistent}
+}
+
+// assertRecorded checks that the database at dbPath holds a record for
+// path when want is set, and none when it is not.
+func assertRecorded(t *testing.T, dbPath, path string, want bool) {
+	t.Helper()
+
+	db, err := openDB(dbPath, reportParams)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	defer func() { _ = db.Close() }()
+
+	if got := slices.Contains(recordPaths(dbRecords(t, db)), path); got != want {
+		t.Errorf("%s recorded: %v, want %v", path, got, want)
+	}
+}

go.mod

@@ -24,3 +24,5 @@ require (
 	modernc.org/mathutil v1.7.1 // indirect
 	modernc.org/memory v1.11.0 // indirect
 )
+
+retract v0.0.1 // early build without a database; does not work as the README describes

info.go

@@ -0,0 +1,125 @@
+package main
+
+import (
+	"context"
+	"errors"
+	"fmt"
+	"io"
+	"io/fs"
+	"os"
+	"path/filepath"
+	"strings"
+	"time"
+)
+
+// infoPhase names one phase of info with its place among all of them,
+// as "[2/2] count", for the phase's progress display. The list here is
+// the one place the phases are counted.
+func infoPhase(name string) string {
+	return phaseLabel([]string{openPhase, "count"}, name)
+}
+
+// runInfo implements the info subcommand: it prints the database's
+// details on stdout (see writeInfo). It opens the database as report
+// does, read-only and without the scan lock, and never touches the
+// scanned filesystem. It names the database on stderr before it opens
+// it. Any database problem, including a missing database, is fatal.
+//
+// The work runs in two phases, each under a progress display of its
+// own on stderr: open (open the database) and count (read the number of
+// records and their total size from the totals table). Each display
+// ends before the next phase starts, and before an error is returned
+// to be printed. The details are written once the last display has
+// ended, so no display is drawn while they are written.
+func runInfo(ctx context.Context, stdout io.Writer) error {
+	dbPath, source, err := databasePath()
+	if err != nil {
+		return err
+	}
+
+	fmt.Fprintf(os.Stderr, "info: database %s (%s)\n",
+		escapePath(dbPath), source)
+
+	// Opening can wait on a busy database for as long as the busy
+	// timeout.
+	prog := newProgress(progressParams{
+		label: infoPhase(openPhase), total: -1,
+		waitingFor: openingDatabase,
+	})
+	db, err := openReportDatabase(ctx, dbPath)
+
+	prog.finish()
+
+	if err != nil {
+		return err
+	}
+
+	defer func() { _ = db.Close() }()
+
+	// One row holds both counts, so the phase never has a total.
+	prog = newProgress(progressParams{
+		label: infoPhase("count"), total: -1,
+		waitingFor: countingRecords,
+	})
+	counts, err := readDatabaseCounts(ctx, db)
+
+	prog.finish()
+
+	if err != nil {
+		return fmt.Errorf("database %s: %w", dbPath, err)
+	}
+
+	return writeInfo(stdout, dbPath, source, counts)
+}
+
+// writeInfo writes the details of the database at dbPath to stdout,
+// one per line, as a name, a tab and the value (README "`info` mode"):
+// the path and source as databasePath returns them, the sizes of the
+// database file and of its -wal file when there is one, when the
+// database file was last changed, and the schema version and record
+// counts that readDatabaseCounts read.
+func writeInfo(stdout io.Writer, dbPath, source string,
+	counts databaseCounts,
+) error {
+	// SQLite keeps the -wal file beside the database file, named from
+	// its path with symlinks resolved.
+	file, err := filepath.EvalSymlinks(dbPath)
+	if err != nil {
+		return fmt.Errorf("database: %w", err)
+	}
+
+	dbFile, err := os.Stat(file)
+	if err != nil {
+		return fmt.Errorf("database: %w", err)
+	}
+
+	walFile, err := os.Stat(file + "-wal")
+	if err != nil && !errors.Is(err, fs.ErrNotExist) {
+		return fmt.Errorf("database: %w", err)
+	}
+
+	var b strings.Builder
+
+	fmt.Fprintf(&b, "database\t%s (%s)\n", escapePath(dbPath), source)
+	fmt.Fprintf(&b, "database file size\t%d (%s)\n",
+		dbFile.Size(), humanBytes(dbFile.Size()))
+
+	if walFile != nil {
+		fmt.Fprintf(&b, "-wal file size\t%d (%s)\n",
+			walFile.Size(), humanBytes(walFile.Size()))
+	}
+
+	fmt.Fprintf(&b, "modified\t%s\n",
+		dbFile.ModTime().UTC().Format(time.RFC3339))
+	fmt.Fprintf(&b, "schema version\t%d\n", counts.schemaVersion)
+	fmt.Fprintf(&b, "records\t%d\n", counts.records)
+	fmt.Fprintf(&b, "size of recorded files\t%d (%s)\n",
+		counts.size, humanBytes(counts.size))
+
+	_, err = io.WriteString(stdout, b.String())
+	if err != nil {
+		return fmt.Errorf("write stdout: %w", err)
+	}
+
+	return nil
+}

info_test.go

@@ -0,0 +1,166 @@
+package main
+
+import (
+	"fmt"
+	"os"
+	"path/filepath"
+	"strings"
+	"testing"
+	"time"
+)
+
+// infoOpenLine is the plain line of info's open phase when it opens the
+// database at once; it prints it as the phase starts and as it ends.
+const infoOpenLine = "[1/2] open: opening the database, elapsed 0s, " +
+	"remain unknown"
+
+// infoCountLine is the plain line of info's count phase when the count
+// takes under a second; it prints it as the phase starts and as it
+// ends.
+const infoCountLine = "[2/2] count: counting the records, elapsed 0s, " +
+	"remain unknown"
+
+// infoRecs are four records: a duplicate pair, a file of 20 MiB and
+// another small file.
+func infoRecs() []scanRec {
+	h, tl, c, u := testHash("h"), testHash("t"), testHash("c"), testHash("u")
+	bigH, bigT, bigC := testHash("bh"), testHash("bt"), testHash("bc")
+
+	return []scanRec{
+		{size: 5, head: h, tail: tl, content: c, path: "/d/a"},
+		{size: 5, head: h, tail: tl, content: c, path: "/d/b"},
+		{size: 20 << 20, head: bigH, tail: bigT, content: bigC, path: "/d/big"},
+		{size: 7, head: u, tail: u, content: u, path: "/d/unique"},
+	}
+}
+
+// TestRunInfo runs info on an empty and on a filled database, with
+// stdout and stderr the same file that is not a terminal, and checks
+// everything written there: the line naming the database, each phase's
+// line as it starts and as it ends, and then the details, each on a
+// line of its own. No -wal file is beside a database scan has closed.
+func TestRunInfo(t *testing.T) {
+	cases := map[string]struct {
+		recs []scanRec
+		want string // the details after the database file's time
+	}{
+		"empty": {
+			want: "schema version\t1\n" +
+				"records\t0\n" +
+				"size of recorded files\t0 (0 B)\n",
+		},
+		"filled": {
+			recs: infoRecs(),
+			want: "schema version\t1\n" +
+				"records\t4\n" +
+				"size of recorded files\t20971537 (20.0 MiB)\n",
+		},
+	}
+
+	for name, tc := range cases {
+		t.Run(name, func(t *testing.T) {
+			path := seedDatabase(t, tc.recs)
+			t.Setenv(databaseEnv, path)
+
+			file, err := os.Stat(path)
+			if err != nil {
+				t.Fatal(err)
+			}
+
+			stderr := captureStderr(t)
+
+			code := run([]string{cmdInfo}, os.Stderr, os.Stderr)
+			if code != exitOK {
+				t.Fatalf("run(info) = %d, want %d; stderr: %s",
+					code, exitOK, stderr())
+			}
+
+			named := path + " (from " + databaseEnv + ")\n"
+			want := "info: database " + named +
+				infoOpenLine + "\n" + infoOpenLine + "\n" +
+				infoCountLine + "\n" + infoCountLine + "\n" +
+				"database\t" + named +
+				fmt.Sprintf("database file size\t%d (%s)\n",
+					file.Size(), humanBytes(file.Size())) +
+				"modified\t" + file.ModTime().UTC().Format(time.RFC3339) +
+				"\n" + tc.want
+
+			if got := stderr(); got != want {
+				t.Errorf("stdout and stderr = %q, want %q", got, want)
+			}
+		})
+	}
+}
+
+// TestRunInfoDuringScan runs info while a scan holds the lock and has
+// the database open in WAL mode, with records committed to the -wal
+// file only. info must count those records and show the -wal file's
+// size, also when the database path is a symlink: SQLite keeps the
+// -wal file beside the symlink's target.
+func TestRunInfoDuringScan(t *testing.T) {
+	path := testDBPath(t)
+	link := filepath.Join(t.TempDir(), "link.sqlite")
+
+	err := os.Symlink(path, link)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	db, err := openScanDatabase(t.Context(), path)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	t.Cleanup(func() { _ = db.Close() })
+
+	err = applyChanges(t.Context(), db, infoRecs(), nil, nil)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	holdScanLock(t, path)
+
+	wal, err := os.Stat(path + "-wal")
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	for _, named := range []string{path, link} {
+		t.Run(filepath.Base(named), func(t *testing.T) {
+			t.Setenv(databaseEnv, named)
+
+			stdout := runStdout(t, cmdInfo)
+
+			for _, want := range []string{
+				"database\t" + named + " (from " + databaseEnv + ")\n",
+				fmt.Sprintf("\n-wal file size\t%d (%s)\n",
+					wal.Size(), humanBytes(wal.Size())),
+				"\nrecords\t4\n",
+			} {
+				if !strings.Contains(stdout, want) {
+					t.Errorf("stdout = %q, want it to hold %q", stdout, want)
+				}
+			}
+		})
+	}
+}
+
+func TestRunInfoNeedsOnlyReadAccess(t *testing.T) {
+	// README "`info` mode": like report, info needs only read access to
+	// the database file and none to its directory.
+	path := testDBPath(t)
+	t.Setenv(databaseEnv, path)
+
+	scanFixture(t)
+	makeReadOnly(t, path)
+
+	stdout := runStdout(t, cmdInfo)
+
+	if want := "\nrecords\t2\n"; !strings.Contains(stdout, want) {
+		t.Errorf("stdout = %q, want it to hold %q", stdout, want)
+	}
+
+	if strings.Contains(stdout, "-wal") {
+		t.Errorf("stdout = %q, want no -wal file between scans", stdout)
+	}
+}

main.go

@@ -1,20 +1,19 @@
 // Command sfdupes quickly identifies candidate duplicate files across
 // very large filesystems without reading every byte of every file.
 // Files are considered duplicates when their sizes are equal and they
-// agree on a short ladder of SHA-256 hashes. A file under 10 MiB is
+// agree on three SHA-256 hashes: of the first 64 KiB, of the last 64
-// hashed in full. A larger file is compared on the hashes of its first
+// KiB, and of the content. The content hash covers the whole file under
-// and last 64 KiB, and only when those match another file's is its
+// 100 MiB, and 1 MiB at each gigabyte at 100 MiB or more, so a large
-// content hash computed and compared: of the whole file when it is
+// file is never read in full. scan maintains a persistent SQLite
-// under 50 MiB, or of gigabyte-spaced 1 MiB samples when it is 50 MiB
+// database of file signatures (SFDUPES_DATABASE, default
-// or larger. scan maintains a persistent SQLite database of file
+// /var/lib/sfdupes/db.sqlite) that the other subcommands read.
-// signatures (SFDUPES_DATABASE, default /var/lib/sfdupes/db.sqlite)
-// that the reporting subcommands read.
 //
 // Usage:
 //
-//	sfdupes scan [--workers N] [-x] PATH...
+//	sfdupes scan [--workers N] [-x] [--no-default-excludes] PATH...
 //	sfdupes report > dupes.tsv
 //	sfdupes trees > dupetrees.tsv
+//	sfdupes info
 //	sfdupes --version
 //
 // See README.md for the complete specification.
@@ -27,6 +26,7 @@ import (
 	"io"
 	"os"
 	"runtime"
+	"runtime/debug"
 
 	"github.com/spf13/cobra"
 )
@@ -44,6 +44,7 @@ const (
 	cmdScan   = "scan"
 	cmdReport = "report"
 	cmdTrees  = "trees"
+	cmdInfo   = "info"
 )
 
 // errNoSubcommand is returned by the root command when it is invoked
@@ -56,10 +57,32 @@ var errNoSubcommand = errors.New("no subcommand")
 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.
+// (see the Makefile); empty when the linker set none, as for a binary
+// built by go install. buildVersion turns it into what --version prints.
 //
 //nolint:gochecknoglobals // written only by the linker
-var Version = "dev"
+var Version string
+
+// buildVersion returns the version that sfdupes --version prints
+// (README "Install"): the version the linker set, when it set one;
+// otherwise the main module's version that Go recorded in the binary,
+// a tag such as v0.0.2 or the pseudo-version of an @main build; and
+// "dev" when neither is known. info is what debug.ReadBuildInfo
+// returns, nil when the binary carries none. Go records "(devel)" for
+// a build that has no version, such as one inside a copy of the source
+// without git.
+func buildVersion(linkerVersion string, info *debug.BuildInfo) string {
+	if linkerVersion != "" {
+		return linkerVersion
+	}
+
+	if info == nil || info.Main.Version == "" ||
+		info.Main.Version == "(devel)" {
+		return "dev"
+	}
+
+	return info.Main.Version
+}
 
 func main() {
 	// Once the reader of a stdout pipe has gone, as in "sfdupes report |
@@ -73,8 +96,8 @@ func main() {
 // exit code. It is the program's single exit point: the subcommands
 // return their errors instead of exiting, so every deferred cleanup —
 // above all closing the database, which checkpoints the SQLite WAL —
-// runs before the process ends. The report and trees subcommands write
+// runs before the process ends. The report, trees and info subcommands
-// their data to stdout.
+// write their data to stdout.
 func run(args []string, stdout, stderr io.Writer) int {
 	// A nil slice makes cobra fall back to os.Args, which would let a
 	// test binary's own flags reach the command tree.
@@ -114,7 +137,10 @@ 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)
+		info, _ := debug.ReadBuildInfo()
+
+		_, err := fmt.Fprintf(stdout, "sfdupes %s\n",
+			buildVersion(Version, info))
 		if err != nil {
 			return fmt.Errorf("write stdout: %w", err)
 		}
@@ -148,30 +174,6 @@ func newRootCommand(stdout, stderr io.Writer) *cobra.Command {
 	root.Flags().BoolVarP(&showVersion, "version", "v", false,
 		"print the version to stdout")
 
-	var (
-		scanWorkers int
-		scanOneFS   bool
-	)
-
-	scanCmd := &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)
-		}),
-	}
-	scanCmd.Flags().IntVar(&scanWorkers, "workers", runtime.NumCPU(),
-		"concurrent workers for the walk, hash, and content phases")
-	scanCmd.Flags().BoolVarP(&scanOneFS, "one-file-system", "x", false,
-		"do not cross filesystem boundaries")
-
 	reportCmd := &cobra.Command{
 		Use:   cmdReport,
 		Short: "Read the scan database and print the file-level duplicates report",
@@ -190,11 +192,59 @@ func newRootCommand(stdout, stderr io.Writer) *cobra.Command {
 		}),
 	}
 
-	root.AddCommand(scanCmd, reportCmd, treesCmd)
+	infoCmd := &cobra.Command{
+		Use:   cmdInfo,
+		Short: "Read the scan database and print its details",
+		Args:  cobra.NoArgs,
+		RunE: runE(func(ctx context.Context, _ []string) error {
+			return runInfo(ctx, stdout)
+		}),
+	}
+
+	root.AddCommand(newScanCommand(), reportCmd, treesCmd, infoCmd)
 
 	return root
 }
 
+// newScanCommand builds the scan subcommand, with its --workers, -x and
+// --no-default-excludes flags. Its help lists the default excludes of
+// the system it runs on, and the filesystem types it never records
+// anything on.
+func newScanCommand() *cobra.Command {
+	var (
+		scanWorkers           int
+		scanOneFS             bool
+		scanNoDefaultExcludes bool
+	)
+
+	short := "Walk trees and synchronize the scan database"
+
+	scanCmd := &cobra.Command{
+		Use:   cmdScan + " [--workers N] [-x] [--no-default-excludes] PATH...",
+		Short: short,
+		Long:  short + ".\n\n" + defaultExcludesHelp(runtime.GOOS),
+		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,
+				scanNoDefaultExcludes)
+		}),
+	}
+	scanCmd.Flags().IntVar(&scanWorkers, "workers", runtime.NumCPU(),
+		"concurrent workers for the walk and hash phases")
+	scanCmd.Flags().BoolVarP(&scanOneFS, "one-file-system", "x", false,
+		"do not cross filesystem boundaries")
+	scanCmd.Flags().BoolVar(&scanNoDefaultExcludes, "no-default-excludes",
+		false, "enter the default excludes, the paths listed above")
+
+	return scanCmd
+}
+
 // 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.

main_test.go

@@ -4,10 +4,12 @@ import (
 	"bytes"
 	"context"
 	"errors"
+	"fmt"
 	"io"
 	"io/fs"
 	"os"
 	"path/filepath"
+	"runtime/debug"
 	"slices"
 	"strconv"
 	"strings"
@@ -18,6 +20,36 @@ import (
 // error prints and a runtime failure must not.
 const usageMarker = "Usage:"
 
+// TestMain stops the tests at once, saying why, when their temporary
+// directory is not on a persistent filesystem: scan records nothing
+// there (README "Rules for the walk"), so most scan tests would fail
+// without saying why.
+func TestMain(m *testing.M) {
+	nonPersistent, err := nonPersistentFilesystems()
+	if err != nil {
+		fmt.Fprintf(os.Stderr, "list the mounted filesystems: %v\n", err)
+		os.Exit(1)
+	}
+
+	dir := os.TempDir()
+
+	fi, err := os.Stat(dir)
+	if err != nil {
+		fmt.Fprintln(os.Stderr, err)
+		os.Exit(1)
+	}
+
+	dev, ok := deviceOfInfo(fi)
+	if fsType, found := nonPersistent[dev]; ok && found {
+		fmt.Fprintf(os.Stderr, "%s is on %s, not a persistent filesystem, "+
+			"and scan records nothing there: set TMPDIR to a directory on a "+
+			"persistent filesystem\n", dir, fsType)
+		os.Exit(1)
+	}
+
+	os.Exit(m.Run())
+}
+
 // walSuffixes are the SQLite sidecar files a WAL-mode database keeps
 // while it is open. A clean close checkpoints the WAL and removes
 // both; finding either afterwards means the database was never closed.
@@ -148,9 +180,9 @@ func capture(t *testing.T, std **os.File) func() string {
 }
 
 // brokenDatabase writes a database that opens cleanly and passes the
-// schema-version check but has no files table, so the first query
+// schema-version check but has no tables, so the first query fails
-// fails with the database already open: a fatal error on a path that
+// with the database already open: a fatal error on a path that owns an
-// owns an open database. It closes the database the way scan does.
+// open database. It closes the database the way scan does.
 func brokenDatabase(t *testing.T) string {
 	t.Helper()
 
@@ -233,8 +265,9 @@ func TestRunFatalAfterOpenClosesDatabase(t *testing.T) {
 			assertFatalOutput(t, stderr.String(), stdout())
 
 			// Proof that the failure happened after the open: only a
-			// query against the opened database can report this.
+			// query against the opened database can report this. Each
-			if !strings.Contains(stderr.String(), "no such table: files") {
+			// subcommand's first query reads totals.
+			if !strings.Contains(stderr.String(), "no such table: totals") {
 				t.Errorf("stderr = %q, want the failure to come from a "+
 					"query on the open database", stderr.String())
 			}
@@ -284,10 +317,16 @@ func assertFatalOutput(t *testing.T, stderr, stdout string) {
 }
 
 func TestRunMissingDatabaseIsFatal(t *testing.T) {
-	// README §Database: report and trees need an existing database; a
+	// README §Database: report, trees and info need an existing
-	// missing one exits 1 with a message telling the user to run scan,
+	// database; a missing one exits 1 with a message telling the user to
-	// after the line naming the database.
+	// run scan, after the line naming the database.
-	for _, name := range []string{cmdReport, cmdTrees} {
+	openLines := map[string]string{
+		cmdReport: reportOpenLine,
+		cmdTrees:  treesOpenLine,
+		cmdInfo:   infoOpenLine,
+	}
+
+	for name, openLine := range openLines {
 		t.Run(name, func(t *testing.T) {
 			path := testDBPath(t)
 			t.Setenv(databaseEnv, path)
@@ -303,8 +342,10 @@ func TestRunMissingDatabaseIsFatal(t *testing.T) {
 				t.Errorf("run(%s) = %d, want %d", name, code, exitFatal)
 			}
 
+			// Each shows its open phase, as it starts and as it ends,
+			// before the error.
 			want := name + ": database " + path + " (from " + databaseEnv +
-				")\n" +
+				")\n" + openLine + "\n" + openLine + "\n" +
 				"sfdupes: " + path + ": no database (run \"sfdupes " +
 				"scan\" first, or set " + databaseEnv + ")\n"
 			if got := stderr(); got != want {
@@ -505,8 +546,9 @@ func TestRunNamesDefaultDatabase(t *testing.T) {
 	// exist at the default path on the machine running the test, so
 	// nothing here may create or read one: scan gets an operand that
 	// does not exist, which stops it before it takes the lock, and
-	// report and trees a cancelled context, which stops them before
+	// report, trees and info a cancelled context, which stops them
-	// they read anything.
+	// before they read anything. They show their open phase after the
+	// line.
 	t.Setenv(databaseEnv, "")
 
 	// Whether scan calls the database new depends on that machine too.
@@ -526,7 +568,7 @@ func TestRunNamesDefaultDatabase(t *testing.T) {
 	}{
 		cmdScan: {
 			run: func() error {
-				return runScan(t.Context(), []string{missing}, 1, false)
+				return runScan(t.Context(), []string{missing}, 1, false, false)
 			},
 			want: scanWant,
 		},
@@ -534,13 +576,22 @@ func TestRunNamesDefaultDatabase(t *testing.T) {
 			run: func() error {
 				return runReport(cancelledContext(t), io.Discard)
 			},
-			want: "report: database " + defaultDatabasePath + " (default)\n",
+			want: "report: database " + defaultDatabasePath + " (default)\n" +
+				reportOpenLine + "\n" + reportOpenLine + "\n",
 		},
 		cmdTrees: {
 			run: func() error {
 				return runTrees(cancelledContext(t), io.Discard)
 			},
-			want: "trees: database " + defaultDatabasePath + " (default)\n",
+			want: "trees: database " + defaultDatabasePath + " (default)\n" +
+				treesOpenLine + "\n" + treesOpenLine + "\n",
+		},
+		cmdInfo: {
+			run: func() error {
+				return runInfo(cancelledContext(t), io.Discard)
+			},
+			want: "info: database " + defaultDatabasePath + " (default)\n" +
+				infoOpenLine + "\n" + infoOpenLine + "\n",
 		},
 	}
 
@@ -568,6 +619,7 @@ func TestRunUsageErrors(t *testing.T) {
 		"scan without paths": {[]string{cmdScan}, usageMarker},
 		"report with args":   {[]string{cmdReport, "x"}, usageMarker},
 		"trees with args":    {[]string{cmdTrees, "x"}, usageMarker},
+		"info with args":     {[]string{cmdInfo, "x"}, usageMarker},
 		"unknown flag":       {[]string{cmdScan, "--nope", "/"}, usageMarker},
 		"unknown subcommand": {[]string{"nope"}, "unknown command"},
 	}
@@ -664,6 +716,8 @@ func TestRunVersion(t *testing.T) {
 
 	// README §Subcommands: the version is one line on stdout, with
 	// nothing on stderr, and exits 0.
+	info, _ := debug.ReadBuildInfo()
+
 	for _, arg := range []string{"--version", "-v"} {
 		var stdout, stderr bytes.Buffer
 
@@ -672,7 +726,7 @@ func TestRunVersion(t *testing.T) {
 			t.Errorf("run(%s) = %d, want %d", arg, code, exitOK)
 		}
 
-		want := "sfdupes " + Version + "\n"
+		want := "sfdupes " + buildVersion(Version, info) + "\n"
 		if got := stdout.String(); got != want {
 			t.Errorf("run(%s) stdout = %q, want %q", arg, got, want)
 		}
@@ -683,6 +737,40 @@ func TestRunVersion(t *testing.T) {
 	}
 }
 
+func TestBuildVersion(t *testing.T) {
+	t.Parallel()
+
+	// README "Install": the linker's version wins; otherwise the main
+	// module's version that Go recorded; "dev" when neither is known.
+	tagged := &debug.BuildInfo{Main: debug.Module{Version: "v0.0.2"}}
+	pseudo := &debug.BuildInfo{Main: debug.Module{
+		Version: "v1.0.0-rc2.0.20261016120000-4e4a94d0c2a1",
+	}}
+	devel := &debug.BuildInfo{Main: debug.Module{Version: "(devel)"}}
+
+	cases := []struct {
+		name   string
+		linker string
+		info   *debug.BuildInfo
+		want   string
+	}{
+		{"linker set", "v0.0.2-3-g4e4a94d", tagged, "v0.0.2-3-g4e4a94d"},
+		{"linker set, no build info", "4e4a94d", nil, "4e4a94d"},
+		{"build info with a tag", "", tagged, "v0.0.2"},
+		{"build info with a pseudo-version", "", pseudo,
+			"v1.0.0-rc2.0.20261016120000-4e4a94d0c2a1"},
+		{"(devel)", "", devel, "dev"},
+		{"no build info", "", nil, "dev"},
+	}
+
+	for _, c := range cases {
+		if got := buildVersion(c.linker, c.info); got != c.want {
+			t.Errorf("%s: buildVersion(%q, ...) = %q, want %q",
+				c.name, c.linker, got, c.want)
+		}
+	}
+}
+
 func TestRunVersionWriteFailureIsFatal(t *testing.T) {
 	t.Parallel()
 
@@ -730,6 +818,23 @@ func scanFixture(t *testing.T) []string {
 	return dupes
 }
 
+// storedDiskSize returns the disk_size of the record for path in the
+// database at dbPath. A test of a trees run compares with this rather
+// than with a new lstat, which on ZFS can differ from the scan's (see
+// diskSizeOf).
+func storedDiskSize(t *testing.T, dbPath, path string) int64 {
+	t.Helper()
+
+	db, err := openReportDatabase(t.Context(), dbPath)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	defer func() { _ = db.Close() }()
+
+	return recordByPath(t, dbRecords(t, db), path).diskSize
+}
+
 // 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 {
@@ -841,24 +946,21 @@ func TestRunScanWalksOperandUnderSymlinkOperand(t *testing.T) {
 }
 
 func TestRunScanSkipsZFSOperand(t *testing.T) {
-	path := testDBPath(t)
-	t.Setenv(databaseEnv, path)
-
 	zfs := filepath.Join(t.TempDir(), ".zfs")
-	snapshot := filepath.Join(zfs, "snapshot", "hourly")
+	f := writeFile(t, zfs, "snapshot/hourly/f", pattern(1, 10))
-	f := writeFile(t, snapshot, "f", pattern(1, 10))
 
-	// An operand beneath a .zfs directory is walked, because it is not
+	// No scan records a file inside a .zfs directory, so the record
-	// itself named .zfs.
+	// beneath the operand is written straight into the database.
-	scanOK(t, snapshot)
+	path := seedDatabase(t, []scanRec{{size: 10, path: f}})
+	t.Setenv(databaseEnv, path)
 
 	assertOperandSkipped(t, path, zfs, ".zfs directory", f)
 }
 
 // assertOperandSkipped scans operand alone and checks that it is skipped
 // as kind: a warning naming it, one skip in the summary, exit 0, and the
-// record for kept, which an earlier scan stored beneath operand, still
+// record for kept, stored beneath operand before this scan, still in the
-// in the database at dbPath.
+// database at dbPath.
 func assertOperandSkipped(t *testing.T, dbPath, operand, kind,
 	kept string,
 ) {
@@ -887,6 +989,121 @@ func assertOperandSkipped(t *testing.T, dbPath, operand, kind,
 	recordByPath(t, dbRecords(t, db), kept)
 }
 
+// TestRunScanSkipsOperandInsideZFS scans a directory inside a .zfs
+// directory, first alone and then under another operand. Each time it
+// is warned about and counted as skipped, and nothing in it is walked.
+// The other operand is scanned as usual.
+func TestRunScanSkipsOperandInsideZFS(t *testing.T) {
+	path := testDBPath(t)
+	t.Setenv(databaseEnv, path)
+
+	dir := t.TempDir()
+	hourly := filepath.Join(dir, ".zfs", "snapshot", "hourly")
+	writeFile(t, hourly, "f", pattern(1, 10))
+	f := writeFile(t, dir, "f", pattern(2, 10))
+
+	warning := "walk " + hourly + ": skipping operand inside a .zfs directory\n"
+
+	for _, tc := range []struct {
+		operands []string
+		summary  string
+	}{
+		{
+			[]string{hourly},
+			"scan: 0 files seen (0 added, 0 updated, 0 removed, " +
+				"0 unchanged), 1 skipped\n",
+		},
+		{
+			[]string{dir, hourly},
+			"scan: 1 files seen (1 added, 0 updated, 0 removed, " +
+				"0 unchanged), 1 skipped\n",
+		},
+	} {
+		stderr := scanOK(t, tc.operands...)
+		if !strings.Contains(stderr, warning) ||
+			!strings.Contains(stderr, tc.summary) {
+			t.Errorf("scan %q: stderr = %q, want %q and %q", tc.operands,
+				stderr, warning, tc.summary)
+		}
+	}
+
+	db, err := openDB(path, reportParams)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	t.Cleanup(func() { _ = db.Close() })
+
+	if got := recordPaths(dbRecords(t, db)); !slices.Equal(got, []string{f}) {
+		t.Errorf("records = %q, want %q", got, []string{f})
+	}
+}
+
+// TestRunScanSkipsOperandThroughSymlinkIntoZFS scans snaps/daily, where
+// snaps is a symlink to pool/.zfs/snapshot. The operand is warned about
+// by the path given, counted as skipped, and not walked.
+func TestRunScanSkipsOperandThroughSymlinkIntoZFS(t *testing.T) {
+	t.Setenv(databaseEnv, testDBPath(t))
+
+	dir := t.TempDir()
+	writeFile(t, dir, "pool/.zfs/snapshot/daily/f", pattern(1, 10))
+
+	snaps := filepath.Join(dir, "snaps")
+
+	err := os.Symlink(filepath.Join(dir, "pool", ".zfs", "snapshot"), snaps)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	daily := filepath.Join(snaps, "daily")
+	stderr := scanOK(t, daily)
+
+	warning := "walk " + daily + ": skipping operand inside a .zfs directory\n"
+	summary := "scan: 0 files seen (0 added, 0 updated, 0 removed, " +
+		"0 unchanged), 1 skipped\n"
+
+	if !strings.Contains(stderr, warning) ||
+		!strings.Contains(stderr, summary) {
+		t.Errorf("stderr = %q, want %q and %q", stderr, warning, summary)
+	}
+}
+
+// TestRunScanWalksOperandThroughSymlink scans data/daily, where data is
+// a symlink to a directory outside any .zfs directory. The operand is
+// scanned as usual, and its file is recorded by the path given.
+func TestRunScanWalksOperandThroughSymlink(t *testing.T) {
+	path := testDBPath(t)
+	t.Setenv(databaseEnv, path)
+
+	dir := t.TempDir()
+	writeFile(t, dir, "pool/data/daily/f", pattern(1, 10))
+
+	data := filepath.Join(dir, "data")
+
+	err := os.Symlink(filepath.Join(dir, "pool", "data"), data)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	daily := filepath.Join(data, "daily")
+	stderr := scanOK(t, daily)
+
+	summary := "scan: 1 files seen (1 added, 0 updated, 0 removed, " +
+		"0 unchanged), 0 skipped\n"
+	if !strings.Contains(stderr, summary) {
+		t.Errorf("stderr = %q, want %q", stderr, summary)
+	}
+
+	db, err := openDB(path, reportParams)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	t.Cleanup(func() { _ = db.Close() })
+
+	recordByPath(t, dbRecords(t, db), filepath.Join(daily, "f"))
+}
+
 func TestRunReportSucceeds(t *testing.T) {
 	path := testDBPath(t)
 	t.Setenv(databaseEnv, path)
@@ -908,11 +1125,16 @@ func TestRunReportSucceeds(t *testing.T) {
 		t.Errorf("stdout = %q, want %q", got, want)
 	}
 
-	want = "report: database " + path + " (from " + databaseEnv + ")\n" +
+	// Its phases come between the two lines; see
-		"report: 2 records read, 1 duplicate groups, 1 dupe files, " +
+	// TestRunReportProgressNamesEachPhase.
+	first := "report: database " + path + " (from " + databaseEnv + ")\n"
+	last := "\nreport: 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)
+	if got := stderr(); !strings.HasPrefix(got, first) ||
+		!strings.HasSuffix(got, last) {
+		t.Errorf("stderr = %q, want it to start %q and end %q",
+			got, first, last)
 	}
 
 	assertNoSidecars(t, path)
@@ -936,17 +1158,23 @@ func TestRunTreesSucceeds(t *testing.T) {
 
 	// The two directories holding the duplicate pair are duplicate
 	// trees of each other.
-	want := "first\tdupe\tfiles\tsize\n" +
+	want := "first\tdupe\tfiles\tsize\tdisk_size\n" +
-		filepath.Dir(dupes[0]) + "\t" + filepath.Dir(dupes[1]) + "\t1\t300\n"
+		filepath.Dir(dupes[0]) + "\t" + filepath.Dir(dupes[1]) + "\t1\t300\t" +
+		strconv.FormatInt(storedDiskSize(t, path, dupes[1]), 10) + "\n"
 	if got := stdout.String(); got != want {
 		t.Errorf("stdout = %q, want %q", got, want)
 	}
 
-	want = "trees: database " + path + " (from " + databaseEnv + ")\n" +
+	// Its phases come between the two lines; see
-		"trees: 2 records read, 1 duplicate tree groups, 1 dupe trees, " +
+	// TestRunTreesProgressNamesEachPhase.
-		"300 B reclaimable\n"
+	first := "trees: database " + path + " (from " + databaseEnv + ")\n"
-	if got := stderr(); got != want {
+	last := "\ntrees: 2 records read, 1 duplicate tree groups, " +
-		t.Errorf("stderr = %q, want %q", got, want)
+		"1 dupe trees, 300 B reclaimable\n"
+
+	if got := stderr(); !strings.HasPrefix(got, first) ||
+		!strings.HasSuffix(got, last) {
+		t.Errorf("stderr = %q, want it to start %q and end %q",
+			got, first, last)
 	}
 
 	assertNoSidecars(t, path)
@@ -966,9 +1194,10 @@ func TestRunReportsNeedOnlyReadAccess(t *testing.T) {
 	cases := map[string]string{
 		cmdReport: "first\tdupe\tsize\n" +
 			dupes[0] + "\t" + dupes[1] + "\t300\n",
-		cmdTrees: "first\tdupe\tfiles\tsize\n" +
+		cmdTrees: "first\tdupe\tfiles\tsize\tdisk_size\n" +
 			filepath.Dir(dupes[0]) + "\t" + filepath.Dir(dupes[1]) +
-			"\t1\t300\n",
+			"\t1\t300\t" +
+			strconv.FormatInt(storedDiskSize(t, path, dupes[1]), 10) + "\n",
 	}
 
 	for name, want := range cases {
@@ -1003,8 +1232,11 @@ func assertRunsUseDatabase(t *testing.T, dir, name string) {
 		t.Errorf("report stdout = %q, want %q", got, want)
 	}
 
-	want = "first\tdupe\tfiles\tsize\n" +
+	diskSize := storedDiskSize(t, filepath.Join(dir, name), dupes[1])
-		filepath.Dir(dupes[0]) + "\t" + filepath.Dir(dupes[1]) + "\t1\t300\n"
+
+	want = "first\tdupe\tfiles\tsize\tdisk_size\n" +
+		filepath.Dir(dupes[0]) + "\t" + filepath.Dir(dupes[1]) + "\t1\t300\t" +
+		strconv.FormatInt(diskSize, 10) + "\n"
 	if got := runStdout(t, cmdTrees); got != want {
 		t.Errorf("trees stdout = %q, want %q", got, want)
 	}
@@ -1238,7 +1470,7 @@ func TestRunReportsDuringScan(t *testing.T) {
 func TestRunStdoutClosedIsFatal(t *testing.T) {
 	// README §Error handling: a stdout write failure exits 1, reported
 	// in one line on stderr.
-	for _, name := range []string{cmdReport, cmdTrees} {
+	for _, name := range []string{cmdReport, cmdTrees, cmdInfo} {
 		t.Run(name, func(t *testing.T) {
 			t.Setenv(databaseEnv, testDBPath(t))
 
@@ -1288,6 +1520,7 @@ func TestStdoutWriteErrorPropagates(t *testing.T) {
 	cases := map[string]func(context.Context, io.Writer) error{
 		cmdReport: runReport,
 		cmdTrees:  runTrees,
+		cmdInfo:   runInfo,
 	}
 
 	for name, fn := range cases {

progress.go

@@ -2,122 +2,321 @@ package main
 
 import (
 	"fmt"
+	"io"
+	"math"
 	"os"
+	"slices"
+	"strings"
+	"sync"
 	"time"
+	"unicode/utf8"
 
 	"github.com/schollz/progressbar/v3"
 	"golang.org/x/term"
 )
 
-// plainInterval is the minimum time between progress lines when stderr
+// plainInterval is the time between progress lines while a phase runs,
-// is not a TTY.
+// when stderr is not a TTY.
 const plainInterval = 5 * time.Second
 
-// barThrottle caps how often the TTY progress bar redraws.
+// redrawInterval is the time between redraws of the progress display on
-const barThrottle = 100 * time.Millisecond
+// a TTY.
+const redrawInterval = 100 * time.Millisecond
 
-// walkSpinnerType selects the progressbar library's spinner style used
+// rateWindow is the time the rate a display shows covers: the items
-// for the walk pass, which has no known total.
+// completed over the last rateWindow, which is the time since the line
-const walkSpinnerType = 14
+// before when stderr is not a TTY.
+const rateWindow = 5 * time.Second
+
+// stallTime is how long a phase goes with no item completed before its
+// line says it has stalled, and where it waits, in place of the rate.
+const stallTime = 10 * time.Second
+
+// spinnerType selects the progressbar library's spinner style.
+const spinnerType = 14
+
+// barWidth is the width of a phase's bar between its two ends, as in
+// the example line in README "Progress".
+const barWidth = 10
+
+// barCell is one column of the filled part of a bar.
+const barCell = "█"
+
+// barColumns is the width of what percentBar returns: the percent in
+// four columns and its sign, a space, and the bar with its two ends.
+const barColumns = barWidth + 8
 
 // percentScale converts a fraction to a percentage.
 const percentScale = 100
 
+// fallbackWidth is the width taken for a terminal whose width cannot be
+// read, as the progressbar library takes it.
+const fallbackWidth = 80
+
+// spinnerMargin is the columns of a line besides its text: the spinner
+// and the three spaces the library draws around the text, and the
+// terminal's last column, which every line stays clear of so that no
+// terminal wraps it.
+const spinnerMargin = 5
+
+// countingRecords is what the display of a phase that reads the records
+// says until it has the number of records, its total.
+const countingRecords = "counting the records"
+
+// openPhase is the name of the phase in which report, trees and info
+// open the database, and openingDatabase what its display says while
+// it does.
+const (
+	openPhase       = "open"
+	openingDatabase = "opening the database"
+)
+
 // stderrIsTTY reports whether stderr is attached to a terminal.
 func stderrIsTTY() bool {
 	return term.IsTerminal(int(os.Stderr.Fd()))
 }
 
-// progress renders one scan pass's progress on stderr. On a TTY it
+// terminalWidth returns the width of the terminal on stderr, or
-// delegates to the progressbar library (spinner style when the total is
+// fallbackWidth, as the progressbar library does, when it cannot read
-// unknown, full bar with count/percent/rate/elapsed/ETA otherwise). When
+// one.
-// stderr is not a TTY it emits no ANSI redraws: it prints a plain
+func terminalWidth() int {
-// one-line update as the pass starts, then no more often than every
+	width, _, err := term.GetSize(int(os.Stderr.Fd()))
-// plainInterval.
+	if err != nil || width <= 0 {
-//
+		return fallbackWidth
-// 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)
-	bar   *progressbar.ProgressBar
-	count int64
-	start time.Time
-	last  time.Time
-}
-
-func newProgress(label string, total int64) *progress {
-	p := &progress{label: label, total: total, start: time.Now()}
-	if stderrIsTTY() {
-		p.bar = newBar(label, total)
-
-		return p
 	}
 
-	// Print the zero state at once: the first item may take minutes,
+	return width
-	// and a pass must never look hung.
+}
-	p.last = p.start
+
-	fmt.Fprintln(os.Stderr, p.plainLine())
+// phaseLabel names phase with its place among phases, as "[2/4] walk".
+func phaseLabel(phases []string, phase string) string {
+	return fmt.Sprintf("[%d/%d] %s",
+		slices.Index(phases, phase)+1, len(phases), phase)
+}
+
+// progressParams describe one phase's progress display as it starts.
+type progressParams struct {
+	label      string // the phase and its place, from phaseLabel
+	unit       string // what the phase counts, as "files"
+	total      int64  // the items the phase will complete; -1 when not known
+	estimate   bool   // total is an estimate, which the count may pass
+	waitingFor string // what the phase waits for until setTotal is called
+	stalledOn  string // where the phase waits, as "disk/db"; see stallTime
+}
+
+// drawnCount is the count of items completed as of one draw, and when
+// that draw was.
+type drawnCount struct {
+	at    time.Time
+	count int64
+}
+
+// progress renders one phase's progress on stderr. On a TTY the
+// progressbar library draws its spinner and then line, fitted to the
+// terminal's width. A phase with an exact total ends the line with its
+// percent and bar, at the terminal's right edge, when the terminal has
+// room for them. It is drawn again every redrawInterval, so its elapsed
+// time keeps moving while the phase waits for its next item. When
+// stderr is not a TTY it emits no ANSI redraws: it prints line as the
+// phase starts, every plainInterval while it runs, and as it ends.
+//
+// The draws come from a goroutine of their own, so mu guards the fields
+// below it. Every method must be called from the main goroutine. A nil
+// *progress is a valid no-display receiver: every method is a no-op, so
+// batched database flushes during the hash phase can reuse the update
+// phase's helpers without rendering anything, and its writer writes
+// with no display to clear.
+type progress struct {
+	now   func() time.Time // reads the time
+	width func() int       // reads the terminal's width; nil when not a TTY
+	stop  chan struct{}    // closed by finish to end the draws
+	done  chan struct{}    // closed once the draws have ended
+
+	mu         sync.Mutex
+	bar        *progressbar.ProgressBar // what the library draws; nil until then
+	widest     int                      // the widest line bar has drawn, in columns
+	label      string
+	unit       string
+	total      int64
+	estimate   bool
+	waitingFor string
+	stalledOn  string
+	count      int64
+	start      time.Time // when the phase started, for the elapsed time
+	rateStart  time.Time // when the count started, for the time remaining
+	lastItem   time.Time // when the last item was completed, or the count started
+	// drawn holds the count at each draw over the last rateWindow, oldest
+	// first; the rate counts from the first. It keeps the draw before the
+	// latest even when that is older, as the line before is when lines
+	// are plainInterval apart and a tick comes late.
+	drawn []drawnCount
+}
+
+// newProgress starts the display of one phase on stderr.
+func newProgress(params progressParams) *progress {
+	if stderrIsTTY() {
+		return startProgress(params, terminalWidth, redrawInterval, time.Now)
+	}
+
+	return startProgress(params, nil, plainInterval, time.Now)
+}
+
+// startProgress shows the phase params describes at once, and again
+// every interval until finish: with the progressbar library on a
+// terminal, whose width each draw reads by calling width, or as a plain
+// line when width is nil. The display reads the time by calling now.
+func startProgress(params progressParams, width func() int,
+	interval time.Duration, now func() time.Time,
+) *progress {
+	start := now()
+	p := &progress{
+		now: now, width: width,
+		stop: make(chan struct{}), done: make(chan struct{}),
+		label: params.label, unit: params.unit, total: params.total,
+		estimate: params.estimate, waitingFor: params.waitingFor,
+		stalledOn: params.stalledOn, start: start, rateStart: start,
+		lastItem: start, drawn: []drawnCount{{at: start}},
+	}
+
+	// Show the zero state at once: the first item may take minutes,
+	// and a phase must never look hung.
+	p.draw()
+
+	go func() {
+		defer close(p.done)
+
+		ticker := time.NewTicker(interval)
+		defer ticker.Stop()
+
+		for {
+			select {
+			case <-p.stop:
+				return
+			case <-ticker.C:
+				p.draw()
+			}
+		}
+	}()
 
 	return p
 }
 
-// newBar builds the TTY display for newProgress.
+// draw shows the phase's progress: on a TTY in place of the line
-func newBar(label string, total int64) *progressbar.ProgressBar {
+// before, and otherwise as a plain line. It first adds the count to
-	opts := []progressbar.Option{
+// drawn, then drops from drawn the draws older than rateWindow, except
-		progressbar.OptionSetWriter(os.Stderr),
+// the one before this draw.
-		progressbar.OptionSetDescription(label),
+func (p *progress) draw() {
-		progressbar.OptionShowCount(),
+	p.mu.Lock()
-		progressbar.OptionShowIts(),
+	defer p.mu.Unlock()
-		progressbar.OptionSetItsString("files"),
+
-		progressbar.OptionSetElapsedTime(true),
+	now := p.now()
-		progressbar.OptionThrottle(barThrottle),
+
-		// Render at zero immediately: a phase must be visible the
+	p.drawn = append(p.drawn, drawnCount{at: now, count: p.count})
-		// moment it starts, even before its first item completes.
+	for len(p.drawn) > 2 && now.Sub(p.drawn[0].at) > rateWindow {
-		progressbar.OptionSetRenderBlankState(true),
+		p.drawn = p.drawn[1:]
-	}
-	if total >= 0 {
-		opts = append(opts,
-			progressbar.OptionSetPredictTime(true),
-			progressbar.OptionShowElapsedTimeOnFinish(),
-		)
-	} else {
-		opts = append(opts,
-			progressbar.OptionSetPredictTime(false),
-			progressbar.OptionSpinnerType(walkSpinnerType),
-		)
 	}
 
-	return progressbar.NewOptions64(total, opts...)
+	if p.width == nil {
+		fmt.Fprintln(os.Stderr, p.line(now, math.MaxInt, false))
+
+		return
+	}
+
+	width := p.width()
+	text := p.line(now, width-spinnerMargin, true)
+
+	// Before each draw the library erases its line with as many spaces as
+	// the widest line it has drawn. A display gets a new one when the
+	// terminal has been made too narrow for that erase, which would wrap
+	// and leave a line behind at every draw.
+	if p.bar == nil || p.widest >= width {
+		p.newBar(width)
+	}
+
+	p.bar.Describe(text)
+
+	// The library drew the spinner, the text and the spaces around it,
+	// less the terminal's last column, which spinnerMargin keeps clear. A
+	// bar's cells take one column each but more than one byte.
+	p.widest = max(p.widest, utf8.RuneCountInString(text)+spinnerMargin-1)
 }
 
-// increment records one completed item and refreshes the display.
+// newBar has the library make what draw draws: its spinner, followed by
+// the text draw gives it and nothing of the library's own. p.mu must be
+// held.
+func (p *progress) newBar(width int) {
+	if p.bar != nil {
+		// Erase what was drawn before, short of the last column of a
+		// terminal that may have been made narrower since: the library's
+		// own erase is as wide as the widest line it drew.
+		blank := strings.Repeat(" ", min(p.widest, width-1))
+		fmt.Fprint(os.Stderr, "\r"+blank+"\r")
+	}
+
+	// A total of -1 gives the library's spinner.
+	p.bar = progressbar.NewOptions64(-1,
+		progressbar.OptionSetWriter(os.Stderr),
+		progressbar.OptionSpinnerType(spinnerType),
+		// The spinner turns at each draw, not on a timer of the
+		// library's own.
+		progressbar.OptionSetSpinnerChangeInterval(0),
+		// The text carries the elapsed time and the time remaining.
+		progressbar.OptionSetElapsedTime(false),
+		progressbar.OptionSetPredictTime(false),
+	)
+	p.widest = 0
+}
+
+// percentBar returns the percent and the bar that end the text of a
+// phase with an exact total, as "  25% |██        |": the bar's
+// barWidth columns fill in proportion to the items done. A count past
+// the total, as when a scan adds records while trees reads them, shows
+// as 100%. p.mu must be held.
+func (p *progress) percentBar() string {
+	done := min(float64(p.count)/float64(p.total), 1)
+	filled := strings.Repeat(barCell, int(done*barWidth))
+
+	return fmt.Sprintf("%4.0f%% |%-*s|", done*percentScale, barWidth, filled)
+}
+
+// setTotal gives a phase that started without a total its total, once
+// it is known. The rate, the time remaining and the time with no item
+// completed count from then on: the time spent waiting for the total
+// says nothing about how fast items go.
+func (p *progress) setTotal(total int64) {
+	if p == nil {
+		return
+	}
+
+	now := p.now()
+
+	p.mu.Lock()
+	defer p.mu.Unlock()
+
+	p.total = total
+	p.rateStart, p.lastItem = now, now
+	p.drawn = []drawnCount{{at: now, count: p.count}}
+}
+
+// increment records one completed item, which the display shows at its
+// next draw.
 func (p *progress) increment() {
 	if p == nil {
 		return
 	}
 
+	now := p.now()
+
+	p.mu.Lock()
+	defer p.mu.Unlock()
+
 	p.count++
-	if p.bar != nil {
+	p.lastItem = now
-		_ = p.bar.Add(1)
-
-		return
-	}
-
-	if time.Since(p.last) >= plainInterval {
-		p.last = time.Now()
-		fmt.Fprintln(os.Stderr, p.plainLine())
-	}
 }
 
-// warnf prints a one-line warning to stderr without corrupting the bar.
+// warnf prints a one-line warning to stderr without corrupting the
-// The whole message is escaped like a report's path columns, so a path
+// display. The whole message is escaped like a report's path columns,
-// holding a newline cannot split the warning.
+// so a path holding a newline cannot split the warning.
 func (p *progress) warnf(format string, args ...any) {
 	if p == nil {
 		return
@@ -125,58 +324,210 @@ func (p *progress) warnf(format string, args ...any) {
 
 	msg := escapePath(fmt.Sprintf(format, args...))
 
-	if p.bar != nil && p.total < 0 {
+	p.mu.Lock()
-		// The library also redraws a spinner from its own goroutine, so
+	defer p.mu.Unlock()
-		// 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 {
+		// The warning takes the display's line; the next draw shows
+		// the display again, on the line below.
 		_ = p.bar.Clear()
 	}
 
 	fmt.Fprintln(os.Stderr, msg)
-
-	// The library never draws a finished bar again, so the warning for
-	// a pass's last item would erase it for good: draw its last frame
-	// again below the warning.
-	if p.bar != nil && p.bar.IsFinished() {
-		fmt.Fprint(os.Stderr, p.bar.String())
-	}
 }
 
-// finish terminates the pass's display. A bar whose pass stopped short
+// progressWriter writes a phase's output to out, which may be the file
-// of its total, as an interrupted one does, is left as last drawn; the
+// the phase's display is drawn on, as stdout is in a plain "sfdupes
-// library's Finish would fill it up.
+// trees" on a terminal. It holds what is written to it and writes that
+// to out in pieces of about ioBufSize bytes. When out is the file
+// stderr is, each piece is written under the display's lock with the
+// display cleared first, as warnf does for a warning: no draw lands in
+// the middle of a piece, and the next draw shows the display again, on
+// the line below. Every write to it must end with a newline, as a row
+// written with one fmt.Fprintf does, so that each piece ends a line.
+// Flush writes what it holds once the last row is written.
+type progressWriter struct {
+	// p is the display to clear, nil unless out is the file stderr is.
+	p   *progress
+	out io.Writer
+	buf []byte
+}
+
+// writer returns a progressWriter writing to out around p's display.
+// It clears the display and takes its lock only when out is the file
+// stderr is: the same device and inode, as os.SameFile compares them,
+// which is one terminal, or one pipe or file that both are sent to.
+// Otherwise it writes to out without the lock, so the display keeps
+// being drawn while a write to out waits for a slow reader.
+func (p *progress) writer(out io.Writer) *progressWriter {
+	w := &progressWriter{out: out}
+
+	if f, ok := out.(*os.File); ok {
+		outInfo, outErr := f.Stat()
+		errInfo, errErr := os.Stderr.Stat()
+
+		if outErr == nil && errErr == nil && os.SameFile(outInfo, errInfo) {
+			w.p = p
+		}
+	}
+
+	return w
+}
+
+// Write holds b, and writes what it holds to out once that comes to
+// ioBufSize bytes.
+func (w *progressWriter) Write(b []byte) (int, error) {
+	w.buf = append(w.buf, b...)
+	if len(w.buf) < ioBufSize {
+		return len(b), nil
+	}
+
+	return len(b), w.Flush()
+}
+
+// Flush writes what w holds to out. When out is the file stderr is, the
+// display is cleared first and not drawn again until it is written.
+func (w *progressWriter) Flush() error {
+	if w.p != nil {
+		w.p.mu.Lock()
+		defer w.p.mu.Unlock()
+
+		if w.p.bar != nil {
+			_ = w.p.bar.Clear()
+		}
+	}
+
+	_, err := w.out.Write(w.buf)
+	w.buf = w.buf[:0]
+
+	return err
+}
+
+// finish ends the phase's display, drawn once more as the phase ends.
+// A phase stopped short of its total, as an interrupted one is, shows
+// the count it stopped at rather than a full bar.
 func (p *progress) finish() {
 	if p == nil {
 		return
 	}
 
-	if p.bar != nil {
+	close(p.stop)
-		if p.total >= 0 && p.count < p.total {
+	<-p.done
-			_ = p.bar.Exit()
-		} else {
-			_ = p.bar.Finish()
-		}
 
+	p.draw()
+
+	if p.width != nil {
+		// The display stays on the TTY as drawn; what follows starts
+		// on a line of its own.
 		fmt.Fprintln(os.Stderr)
-
-		return
 	}
-
-	fmt.Fprintln(os.Stderr, p.plainLine())
 }
 
-// plainLine formats a non-TTY progress line.
+// line formats the phase's progress as of now in at most room columns,
-func (p *progress) plainLine() string {
+// as
-	elapsed := time.Since(p.start)
+//
+//	[3/4] hash: [1234/5000] 25%, 300 files/s, elapsed 4s, remain 13s
+//
+// where "files" is the phase's unit. A phase with no total shows the
+// items done instead, or what it waits for. The rate is that since the
+// first draw in drawn, and the time remaining comes from the rate since
+// the count started. Once no item has been completed for stallTime, the
+// rate, which would read 0, gives way to the word "stalled" and where
+// the phase waits, as "stalled disk/db".
+//
+// When bar is true, as on a terminal, a phase with an exact total ends
+// the line with its percent and bar, in place of the percent after its
+// count. A total of 0 leaves the bar nothing to fill.
+//
+// The phase and its place, the progress, the elapsed time and the time
+// remaining are kept whole. A line wider than room first leaves out the
+// rate, the words of a stalled phase, or what the phase waits for. Next
+// it leaves out the bar. Only if it is still wider is it cut at room.
+// Every part but the bar is ASCII, so its length is its width in
+// columns. p.mu must be held.
+func (p *progress) line(now time.Time, room int, bar bool) string {
+	elapsed := now.Sub(p.start).Round(time.Second)
+
+	// head and tail hold the parts kept whole; extra, between them, is
+	// the part left out.
+	var head, extra, tail string
+
+	if p.total < 0 && p.waitingFor != "" {
+		head, extra = p.label+": ", p.waitingFor+", "
+		tail = fmt.Sprintf("elapsed %s, remain unknown", elapsed)
+	} else {
+		since := p.drawn[0]
+		rate := perSecond(p.count-since.count, now.Sub(since.at))
+		average := perSecond(p.count, now.Sub(p.rateStart))
+
+		head = p.label + ": " + p.itemsDone(true) + ", "
+		extra = fmt.Sprintf("%.0f %s/s, ", rate, p.unit)
+		tail = fmt.Sprintf("elapsed %s, remain %s", elapsed, p.remain(average))
+
+		if now.Sub(p.lastItem) >= stallTime {
+			extra = "stalled " + p.stalledOn + ", "
+		}
+	}
+
+	if bar && p.total > 0 && !p.estimate {
+		// Beside the bar, which shows the percent, the count shows none.
+		// The line is padded to the room the bar leaves it, so the bar
+		// stays at room's right edge however long the line is.
+		beside := room - barColumns
+		barHead := p.label + ": " + p.itemsDone(false) + ", "
+
+		switch {
+		case len(barHead+extra+tail) <= beside:
+			return fmt.Sprintf("%-*s%s", beside, barHead+extra+tail,
+				p.percentBar())
+		case len(barHead+tail) <= beside:
+			return fmt.Sprintf("%-*s%s", beside, barHead+tail, p.percentBar())
+		}
+
+		// The bar gives way. The rate, or the words of a stalled phase,
+		// gave way before it and stay out.
+		extra = ""
+	}
+
+	full, kept := head+extra+tail, head+tail
+
+	switch {
+	case len(full) <= room:
+		return full
+	case len(kept) <= room:
+		return kept
+	}
+
+	return kept[:max(room, 0)]
+}
+
+// perSecond returns count items over d as items a second, or 0 when no
+// time has passed.
+func perSecond(count int64, d time.Duration) float64 {
+	if d <= 0 {
+		return 0
+	}
+
+	return float64(count) / d.Seconds()
+}
+
+// itemsDone formats the items done, as "[1234/5000] 25%", with "~"
+// before a total that is an estimate and without the percent when
+// percent is false, or as "1234 files", in the phase's unit, when the
+// phase has no total. p.mu must be held.
+func (p *progress) itemsDone(percent bool) string {
 	if p.total < 0 {
-		return fmt.Sprintf("%s: %d files, elapsed %s",
+		return fmt.Sprintf("%d %s", p.count, p.unit)
-			p.label, p.count, elapsed.Round(time.Second))
+	}
+
+	approx := ""
+	if p.estimate {
+		approx = "~"
+	}
+
+	done := fmt.Sprintf("[%d/%s%d]", p.count, approx, p.total)
+	if !percent {
+		return done
 	}
 
 	pct := float64(percentScale)
@@ -184,19 +535,24 @@ func (p *progress) plainLine() string {
 		pct = percentScale * float64(p.count) / float64(p.total)
 	}
 
-	rate := 0.0
+	return fmt.Sprintf("%s %.0f%%", done, pct)
-	if s := elapsed.Seconds(); s > 0 {
+}
-		rate = float64(p.count) / s
+
+// remain returns the time the phase has left at rate items a second, or
+// "unknown": with no total, before the first item, and once the count
+// passes an estimate. p.mu must be held.
+func (p *progress) remain(rate float64) string {
+	switch {
+	case p.total < 0, p.estimate && p.count > p.total:
+		return "unknown"
+	case p.count >= p.total:
+		return "0s"
+	case rate <= 0:
+		return "unknown"
 	}
-
-	eta := "?"
 
-	if rate > 0 && p.count <= p.total {
+	left := time.Duration(
-		remaining := time.Duration(float64(p.total-p.count) / rate * float64(time.Second))
+		float64(p.total-p.count) / rate * float64(time.Second))
-		eta = remaining.Round(time.Second).String()
-	}
 
-	return fmt.Sprintf("%s: [%d/%d] %.0f%% %.0f files/s elapsed %s eta %s",
+	return left.Round(time.Second).String()
-		p.label, p.count, p.total, pct, rate,
-		elapsed.Round(time.Second), eta)
 }

report.go

@@ -1,11 +1,13 @@
 package main
 
 import (
-	"bufio"
 	"context"
+	"crypto/sha256"
+	"database/sql"
 	"fmt"
 	"io"
 	"os"
+	"slices"
 	"strings"
 	"time"
 )
@@ -19,23 +21,37 @@ const minGroupSize = 2
 
 // scanRec is one file record from the database. The signature (size,
 // head, tail, content) is the duplicate key; mtime is informational
-// only and used by scan for change detection.
+// only and used by scan for change detection. diskSize is the bytes the
+// file takes on disk, which trees adds up.
 type scanRec struct {
-	size    int64
+	size     int64
-	mtime   time.Time
+	diskSize int64
-	head    string
+	mtime    time.Time
-	tail    string
+	head     [sha256.Size]byte
-	content string
+	tail     [sha256.Size]byte
-	path    string
+	content  [sha256.Size]byte
+	path     string
+}
+
+// reportPhase names one phase of report with its place among all of
+// them, as "[2/2] read", for the phase's progress display. The list
+// here is the one place the phases are counted.
+func reportPhase(name string) string {
+	return phaseLabel([]string{openPhase, "read"}, name)
 }
 
 // runReport implements the report subcommand: it prints the file-level
-// duplicates report as TSV on stdout. SQLite groups and orders the
+// duplicates report as TSV on stdout. It never touches the scanned
-// records, and each row is written as it is read, so no group is held
+// filesystem; its only I/O is the database, stdout, and stderr. It
-// in memory. It never touches the scanned filesystem; its only I/O is
+// names the database on stderr before it opens it. Any database
-// the database (with SQLite's temporary sort file), stdout, and stderr.
-// It names the database on stderr before it opens it. Any database
 // problem, including a missing database, is fatal.
+//
+// The work runs in two phases, each under a progress display of its
+// own on stderr: open (open the database) and read (read the number of
+// records from the totals table, then read the records in signature
+// order, writing each size's duplicate groups to stdout once that size
+// is read; see readReport). Each display ends before the next phase
+// starts, and before an error is returned to be printed.
 func runReport(ctx context.Context, stdout io.Writer) error {
 	dbPath, source, err := databasePath()
 	if err != nil {
@@ -45,65 +61,190 @@ func runReport(ctx context.Context, stdout io.Writer) error {
 	fmt.Fprintf(os.Stderr, "report: database %s (%s)\n",
 		escapePath(dbPath), source)
 
+	// Opening can wait on a busy database for as long as the busy
+	// timeout.
+	prog := newProgress(progressParams{
+		label: reportPhase(openPhase), total: -1,
+		waitingFor: openingDatabase,
+	})
 	db, err := openReportDatabase(ctx, dbPath)
+
+	prog.finish()
+
 	if err != nil {
 		return err
 	}
 
 	defer func() { _ = db.Close() }()
 
-	out := bufio.NewWriterSize(stdout, ioBufSize)
+	// The read phase writes the report to stdout while it reads the
+	// records, so it may wait on either.
+	prog = newProgress(progressParams{
+		label: reportPhase("read"), unit: "records", total: -1,
+		waitingFor: countingRecords, stalledOn: "db/out",
+	})
+	report, err := readReport(ctx, db, dbPath, stdout, prog)
 
-	_, err = fmt.Fprintln(out, "first\tdupe\tsize")
+	prog.finish()
-	if err != nil {
-		return fmt.Errorf("write stdout: %w", err)
-	}
-
-	var (
-		groups, dupeFiles int
-		reclaimable       int64
-		writeErr          error
-	)
-
-	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++
-
-				return nil
-			}
-
-			_, writeErr = fmt.Fprintf(out, "%s\t%s\t%d\n",
-				escapePath(first), escapePath(path), size)
-			dupeFiles++
-			reclaimable += size
-
-			return writeErr
-		})
-
-	if writeErr != nil {
-		return fmt.Errorf("write stdout: %w", writeErr)
-	}
 
 	if err != nil {
-		return fmt.Errorf("database %s: %w", dbPath, err)
+		return err
-	}
-
-	err = out.Flush()
-	if err != nil {
-		return fmt.Errorf("write stdout: %w", err)
 	}
 
 	fmt.Fprintf(os.Stderr,
 		"report: %d records read, %d duplicate groups, %d dupe files, "+
 			"%s reclaimable\n",
-		records, groups, dupeFiles, humanBytes(reclaimable))
+		report.records, report.dupeGroups, report.dupeFiles,
+		humanBytes(report.reclaimable))
 
 	return nil
 }
 
+// readReport gives prog the number of records in db, the database at
+// dbPath, as its total, then reads every record in signature order,
+// counting each on prog, and writes the report to stdout: the header
+// line, then the rows of each size's duplicate groups once that size is
+// read. stdout may be the terminal prog is drawn on, so the lines go
+// through prog's writer. It returns what it wrote, with the totals for
+// the summary line.
+func readReport(ctx context.Context, db *sql.DB, dbPath string,
+	stdout io.Writer, prog *progress,
+) (*reportWriter, error) {
+	out := prog.writer(stdout)
+	report := &reportWriter{out: out}
+
+	_, err := fmt.Fprintln(out, "first\tdupe\tsize")
+	if err != nil {
+		return nil, fmt.Errorf("write stdout: %w", err)
+	}
+
+	var writeErr error
+
+	err = loadSignatureRows(ctx, db, prog.setTotal, func(r scanRec) error {
+		prog.increment()
+
+		writeErr = report.add(r)
+
+		return writeErr
+	})
+
+	if writeErr != nil {
+		return nil, fmt.Errorf("write stdout: %w", writeErr)
+	}
+
+	if err != nil {
+		return nil, fmt.Errorf("database %s: %w", dbPath, err)
+	}
+
+	err = report.finish()
+	if err == nil {
+		err = out.Flush()
+	}
+
+	if err != nil {
+		return nil, fmt.Errorf("write stdout: %w", err)
+	}
+
+	return report, nil
+}
+
+// reportWriter writes the report's rows to out from the records, added
+// in signature order, largest size first, as loadSignatureRows reads
+// them. The records sharing a signature come together, and so do the
+// records of one size, so it holds only the duplicate groups of the
+// size being read, and writes them, ordered by first path, once a
+// record of a smaller size comes. It counts what the summary line
+// reports.
+type reportWriter struct {
+	out io.Writer
+
+	sig    scanRec    // the signature being read; its path is not used
+	paths  []string   // the paths read so far with sig
+	groups [][]string // the duplicate groups of sig.size, each sorted
+
+	records, dupeGroups, dupeFiles int
+	reclaimable                    int64
+}
+
+// add takes the next record. One with the signature being read joins
+// its paths; any other ends them, and one of a smaller size first
+// writes the groups of the size before.
+func (w *reportWriter) add(r scanRec) error {
+	w.records++
+
+	if r.size == w.sig.size && r.head == w.sig.head &&
+		r.tail == w.sig.tail && r.content == w.sig.content {
+		w.paths = append(w.paths, r.path)
+
+		return nil
+	}
+
+	w.endGroup()
+
+	if r.size != w.sig.size {
+		err := w.writeGroups()
+		if err != nil {
+			return err
+		}
+	}
+
+	w.sig = r
+	w.paths = append(w.paths, r.path)
+
+	return nil
+}
+
+// endGroup ends the paths read with w.sig: two or more are a duplicate
+// group, held with its paths sorted until writeGroups writes it.
+func (w *reportWriter) endGroup() {
+	if len(w.paths) < minGroupSize {
+		// A path with no duplicate is dropped, and its slice reused.
+		w.paths = w.paths[:0]
+
+		return
+	}
+
+	slices.Sort(w.paths)
+	w.groups = append(w.groups, w.paths)
+	w.paths = nil
+}
+
+// writeGroups writes the duplicate groups held, all of size w.sig.size,
+// ordered by first path: for each group, a row for every path but the
+// first. No two groups share a first path, since no two records share
+// a path.
+func (w *reportWriter) writeGroups() error {
+	slices.SortFunc(w.groups, func(a, b []string) int {
+		return strings.Compare(a[0], b[0])
+	})
+
+	for _, g := range w.groups {
+		for _, path := range g[1:] {
+			_, err := fmt.Fprintf(w.out, "%s\t%s\t%d\n",
+				escapePath(g[0]), escapePath(path), w.sig.size)
+			if err != nil {
+				return err
+			}
+
+			w.dupeFiles++
+			w.reclaimable += w.sig.size
+		}
+
+		w.dupeGroups++
+	}
+
+	w.groups = nil
+
+	return nil
+}
+
+// finish writes the groups of the last size read.
+func (w *reportWriter) finish() error {
+	w.endGroup()
+
+	return w.writeGroups()
+}
+
 // 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

@@ -2,6 +2,7 @@ package main
 
 import (
 	"bytes"
+	"crypto/sha256"
 	"database/sql"
 	"errors"
 	"fmt"
@@ -9,6 +10,7 @@ import (
 	"os"
 	"path/filepath"
 	"slices"
+	"strconv"
 	"strings"
 	"testing"
 	"time"
@@ -17,18 +19,32 @@ import (
 // awkwardDir is a directory name holding every byte the reports escape.
 const awkwardDir = "/d/\tone\ntwo\rthree\\four"
 
+// testHash returns a stand-in hash for a test record: the bytes of s,
+// then zeros. Stand-ins sort as their strings do, so a test can choose
+// the order in which report reads its records.
+func testHash(s string) [sha256.Size]byte {
+	var h [sha256.Size]byte
+
+	copy(h[:], s)
+
+	return h
+}
+
 // awkwardPairRecs is a duplicate pair in sibling directories /d/A and
 // awkwardDir. A raw tab sorts before "A" but its escaped form `\t`
 // sorts after it, so awkwardDir coming first shows that sorting uses
 // the raw path.
 func awkwardPairRecs() []scanRec {
+	h, tl, c := testHash("h"), testHash("t"), testHash("c")
+
 	return []scanRec{
-		{size: 5, head: "h", tail: "t", content: "c", path: "/d/A/f"},
+		{size: 5, diskSize: 4096, head: h, tail: tl, content: c, path: "/d/A/f"},
-		{size: 5, head: "h", tail: "t", content: "c", path: awkwardDir + "/f"},
+		{size: 5, diskSize: 4096, head: h, tail: tl, content: c, path: awkwardDir + "/f"},
 	}
 }
 
-// seedDatabase writes recs into a fresh database and returns its path.
+// seedDatabase writes recs into a fresh database, closes it as scan
+// does, out of WAL mode, and returns its path.
 func seedDatabase(t *testing.T, recs []scanRec) string {
 	t.Helper()
 
@@ -44,10 +60,7 @@ func seedDatabase(t *testing.T, recs []scanRec) string {
 		t.Fatal(err)
 	}
 
-	err = db.Close()
+	closeScanDatabase(t.Context(), db, path)
-	if err != nil {
-		t.Fatal(err)
-	}
 
 	return path
 }
@@ -60,27 +73,41 @@ type dupeGroup struct {
 }
 
 // dupeGroups returns the duplicate groups report reads from db, in
-// report order.
+// report order, from the rows it writes: a group's rows come together,
+// each naming the group's first path.
 func dupeGroups(t *testing.T, db *sql.DB) []dupeGroup {
 	t.Helper()
 
-	var groups []dupeGroup
+	var out bytes.Buffer
 
-	_, err := loadDupeRows(t.Context(), db,
+	_, err := readReport(t.Context(), db, "", &out, nil)
-		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)
 	}
 
+	var groups []dupeGroup
+
+	rows := strings.Split(strings.TrimSuffix(out.String(), "\n"), "\n")
+	for _, row := range rows[1:] { // after the header
+		fields := strings.Split(row, "\t")
+		if len(fields) != 3 {
+			t.Fatalf("row %q, want first, dupe and size", row)
+		}
+
+		size, err := strconv.ParseInt(fields[2], 10, 64)
+		if err != nil {
+			t.Fatal(err)
+		}
+
+		if len(groups) == 0 || groups[len(groups)-1].paths[0] != fields[0] {
+			groups = append(groups,
+				dupeGroup{size: size, paths: []string{fields[0]}})
+		}
+
+		g := &groups[len(groups)-1]
+		g.paths = append(g.paths, fields[1])
+	}
+
 	return groups
 }
 
@@ -118,38 +145,160 @@ func TestRunReportEscapesPaths(t *testing.T) {
 }
 
 func TestReportStdoutFailsWhileReading(t *testing.T) {
-	// Each row holds two paths longer than dir, so the report is more
+	t.Parallel()
-	// than twice the stdout buffer and stdout fails while rows are
+
-	// still being read, not at the final flush.
+	// Every two records are a duplicate pair of a size of their own, and
+	// a pair's row is written once a smaller size is read. Each row
+	// holds two paths longer than dir, so the rows come to more than
+	// twice the stdout buffer, and stdout fails while records are still
+	// being read, not once every record is.
 	dir := "/" + strings.Repeat("d", 4096)
 
-	recs := make([]scanRec, ioBufSize/len(dir))
+	recs := make([]scanRec, 2*ioBufSize/len(dir))
 	for i := range recs {
 		recs[i] = scanRec{
-			size: 1, head: "h", tail: "t", content: "c",
+			size: int64(i/2) + 1, head: testHash("h"), tail: testHash("t"),
-			path: fmt.Sprintf("%s/%d", dir, i),
+			content: testHash("c"), path: fmt.Sprintf("%s/%d", dir, i),
 		}
 	}
 
-	t.Setenv(databaseEnv, seedDatabase(t, recs))
+	db := openTestDB(t)
 
-	err := runReport(t.Context(), failingWriter{})
+	err := applyChanges(t.Context(), db, recs, nil, nil)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	// Counts the records read, and draws nothing.
+	prog := &progress{now: time.Now}
+
+	_, err = readReport(t.Context(), db, "", failingWriter{}, prog)
 	if !errors.Is(err, errWriteFailed) ||
 		!strings.HasPrefix(err.Error(), "write stdout: ") {
 		t.Errorf("error = %v, want write stdout: %v", err, errWriteFailed)
 	}
+
+	if prog.count >= int64(len(recs)) {
+		t.Errorf("stdout failed after all %d records were read, want it "+
+			"to stop the read", prog.count)
+	}
+}
+
+// reportOpenLine is the plain line of report's open phase when it opens
+// the database at once; it prints it as the phase starts and as it ends.
+const reportOpenLine = "[1/2] open: opening the database, elapsed 0s, " +
+	"remain unknown"
+
+// smokeReport is report's stdout for the smoke-test records.
+const smokeReport = "first\tdupe\tsize\n" +
+	"/d/t1/f1\t/d/t2/f1\t3000\n" +
+	"/d/t1/f1\t/d/t3/f1\t3000\n" +
+	"/d/t1/sub/f2\t/d/t2/sub/f2\t100\n" +
+	"/d/t1/sub/f2\t/d/t3/sub/f2renamed\t100\n"
+
+// TestRunReportProgressNamesEachPhase runs report on the smoke-test
+// records with stderr not a terminal, and checks every line it prints
+// there. After the line naming the database, each phase prints a line
+// naming it with its place among the two as it starts and another as
+// it ends; read counts the 6 records before it reads them. The summary
+// comes last, and stdout holds the report alone.
+func TestRunReportProgressNamesEachPhase(t *testing.T) {
+	path := seedDatabase(t, smokeTreeRecs())
+	t.Setenv(databaseEnv, path)
+
+	stderr := captureStderr(t)
+
+	var stdout bytes.Buffer
+
+	code := run([]string{cmdReport}, &stdout, os.Stderr)
+	if code != exitOK {
+		t.Fatalf("run(report) = %d, want %d; stderr: %s",
+			code, exitOK, stderr())
+	}
+
+	if got := stdout.String(); got != smokeReport {
+		t.Errorf("stdout = %q, want %q", got, smokeReport)
+	}
+
+	// How each line starts; the rate at the end of a phase varies.
+	want := []string{
+		"report: database " + path + " (from " + databaseEnv + ")",
+		reportOpenLine,
+		reportOpenLine,
+		"[2/2] read: counting the records, elapsed 0s, remain unknown",
+		"[2/2] read: [6/6] 100%, ",
+		"report: 6 records read, 2 duplicate groups, 4 dupe files, " +
+			"6.1 KiB reclaimable",
+	}
+
+	lines := strings.Split(strings.TrimSuffix(stderr(), "\n"), "\n")
+	if len(lines) != len(want) {
+		t.Fatalf("stderr lines = %q, want %d lines starting %q",
+			lines, len(want), want)
+	}
+
+	for i := range want {
+		if !strings.HasPrefix(lines[i], want[i]) {
+			t.Errorf("stderr line %d = %q, want it to start %q",
+				i+1, lines[i], want[i])
+		}
+	}
+}
+
+// TestReadReportOnTerminal writes the smoke-test report to the terminal
+// its read phase's display is drawn on, as a plain "sfdupes report"
+// does: the terminal must show the header and every row whole, each on
+// a line of its own.
+//
+//nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
+func TestReadReportOnTerminal(t *testing.T) {
+	stderr := captureStderr(t)
+	db := openTestDB(t)
+
+	err := applyChanges(t.Context(), db, smokeTreeRecs(), nil, nil)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	// No timed draws: the display is drawn as it starts and as it ends.
+	p := startProgress(progressParams{
+		label: reportPhase("read"), unit: "records", total: -1,
+		waitingFor: countingRecords,
+	}, terminalWidth, time.Hour, time.Now)
+
+	_, err = readReport(t.Context(), db, "", os.Stderr, p)
+
+	p.finish()
+
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	// A terminal shows each line as the text after its last carriage
+	// return.
+	var shown []string
+
+	for line := range strings.SplitSeq(stderr(), "\n") {
+		shown = append(shown, line[strings.LastIndex(line, "\r")+1:])
+	}
+
+	want := strings.Split(strings.TrimSuffix(smokeReport, "\n"), "\n")
+	if len(shown) < len(want) || !slices.Equal(shown[:len(want)], want) {
+		t.Errorf("terminal shows lines %q, want %q first", shown, want)
+	}
 }
 
 func TestRunReportsIgnoreInsertionOrder(t *testing.T) {
 	// README §Constraints: identical database contents give identical
 	// output, whatever order the records were inserted in.
+	a, b := testHash("a"), testHash("b")
+
 	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/2"},
-		scanRec{size: 50, head: "b", tail: "b", content: "b", path: "/y/1"},
+		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/2"},
-		scanRec{size: 50, head: "a", tail: "a", content: "a", path: "/x/1"},
+		scanRec{size: 50, head: a, tail: a, content: a, path: "/x/1"},
-		scanRec{size: 50, path: "/x/unhashed"},
 	)
 
 	reversed := slices.Clone(recs)
@@ -252,16 +401,19 @@ func TestWarnfEscapes(t *testing.T) {
 func TestDupeGroups(t *testing.T) {
 	t.Parallel()
 
+	h, tl, c := testHash("h"), testHash("t"), testHash("c")
+	bigH, bigT, bigC := testHash("H"), testHash("T"), testHash("C")
+	u := testHash("u")
 	recs := []scanRec{
-		{size: 100, head: "h", tail: "t", content: "c", path: "/z/b"},
+		{size: 100, head: h, tail: tl, content: c, path: "/z/b"},
-		{size: 100, head: "h", tail: "t", content: "c", path: "/z/a"},
+		{size: 100, head: h, tail: tl, content: c, path: "/z/a"},
-		{size: 100, head: "h", tail: "t", content: "c", path: "/z/c"},
+		{size: 100, head: h, tail: tl, content: c, path: "/z/c"},
-		{size: 4000, head: "H", tail: "T", content: "C", path: "/big/2"},
+		{size: 4000, head: bigH, tail: bigT, content: bigC, path: "/big/2"},
-		{size: 4000, head: "H", tail: "T", content: "C", path: "/big/1"},
+		{size: 4000, head: bigH, tail: bigT, content: bigC, path: "/big/1"},
 		// Same size as the /z group but a different head hash.
-		{size: 100, head: "other", tail: "t", content: "c", path: "/z/d"},
+		{size: 100, head: testHash("other"), tail: tl, content: c, path: "/z/d"},
 		// A singleton signature must not form a group.
-		{size: 7, head: "u", tail: "u", content: "u", path: "/lonely"},
+		{size: 7, head: u, tail: u, content: u, path: "/lonely"},
 	}
 
 	groups := dupeGroupsOf(t, recs)
@@ -285,16 +437,13 @@ func TestDupeGroups(t *testing.T) {
 func TestDupeGroupsContentSeparates(t *testing.T) {
 	t.Parallel()
 
-	// Same size, head, and tail, but different content hashes: the final
+	// Same size, head, and tail: /b differs from the others only in its
-	// rung keeps them apart, so no group forms. Matching content groups.
+	// content hash, so it joins no group, while /a and /c group.
-	// Records without a content hash never group, not even with each
+	h, tl := testHash("h"), testHash("t")
-	// other.
 	recs := []scanRec{
-		{size: 100, head: "h", tail: "t", content: "c1", path: "/a"},
+		{size: 100, head: h, tail: tl, content: testHash("c1"), path: "/a"},
-		{size: 100, head: "h", tail: "t", content: "c2", path: "/b"},
+		{size: 100, head: h, tail: tl, content: testHash("c2"), path: "/b"},
-		{size: 100, head: "h", tail: "t", content: "c1", path: "/c"},
+		{size: 100, head: h, tail: tl, content: testHash("c1"), path: "/c"},
-		{size: 100, head: "h", tail: "t", path: "/d"},
-		{size: 100, head: "h", tail: "t", path: "/e"},
 	}
 
 	groups := dupeGroupsOf(t, recs)
@@ -313,14 +462,15 @@ func TestDupeGroupsMtimeExcluded(t *testing.T) {
 
 	// mtime is informational only; records differing only in mtime
 	// still group together.
+	h, tl, c := testHash("h"), testHash("t"), testHash("c")
 	recs := []scanRec{
 		{
-			size: 9, mtime: time.Unix(100, 0), head: "h", tail: "t",
+			size: 9, mtime: time.Unix(100, 0), head: h, tail: tl,
-			content: "c", path: "/m/1",
+			content: c, path: "/m/1",
 		},
 		{
-			size: 9, mtime: time.Unix(200, 0), head: "h", tail: "t",
+			size: 9, mtime: time.Unix(200, 0), head: h, tail: tl,
-			content: "c", path: "/m/2",
+			content: c, path: "/m/2",
 		},
 	}
 
@@ -335,11 +485,12 @@ func TestDupeGroupsTieBreak(t *testing.T) {
 
 	// The hashes sort opposite to the first paths, so ordering the
 	// groups by hash instead of by first path fails this test.
+	a, b := testHash("a"), testHash("b")
 	recs := []scanRec{
-		{size: 50, head: "a", tail: "a", content: "a", path: "/beta/2"},
+		{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: 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/2"},
-		{size: 50, head: "b", tail: "b", content: "b", path: "/alpha/1"},
+		{size: 50, head: b, tail: b, content: b, path: "/alpha/1"},
 	}
 
 	groups := dupeGroupsOf(t, recs)
@@ -354,14 +505,47 @@ func TestDupeGroupsTieBreak(t *testing.T) {
 	}
 }
 
+func TestDupeGroupsOrderedByFirstPath(t *testing.T) {
+	t.Parallel()
+
+	// report reads the groups of size 50 in signature order, here /a,
+	// /z, /k, which is neither the order of their first paths nor its
+	// reverse, and must write them ordered by first path. The group of
+	// size 7 comes after them all, though its first path sorts first.
+	a, b, c, d := testHash("a"), testHash("b"), testHash("c"), testHash("d")
+	recs := []scanRec{
+		{size: 50, head: a, tail: a, content: a, path: "/k/2"},
+		{size: 50, head: a, tail: a, content: a, path: "/k/1"},
+		{size: 50, head: b, tail: b, content: b, path: "/z/1"},
+		{size: 50, head: b, tail: b, content: b, path: "/z/2"},
+		{size: 50, head: c, tail: c, content: c, path: "/a/2"},
+		{size: 50, head: c, tail: c, content: c, path: "/a/1"},
+		{size: 7, head: d, tail: d, content: d, path: "/0/2"},
+		{size: 7, head: d, tail: d, content: d, path: "/0/1"},
+	}
+
+	groups := dupeGroupsOf(t, recs)
+
+	got := make([]string, 0, len(groups))
+	for _, g := range groups {
+		got = append(got, g.paths[0])
+	}
+
+	want := []string{"/a/1", "/k/1", "/z/1", "/0/1"}
+	if !slices.Equal(got, want) {
+		t.Errorf("groups' first paths = %q, want %q", got, want)
+	}
+}
+
 func TestDupeGroupsDeterministic(t *testing.T) {
 	t.Parallel()
 
+	a, b := testHash("a"), testHash("b")
 	recs := []scanRec{
-		{size: 1, head: "a", tail: "a", content: "a", path: "/p/1"},
+		{size: 1, head: a, tail: a, content: a, path: "/p/1"},
-		{size: 1, head: "a", tail: "a", content: "a", path: "/p/2"},
+		{size: 1, head: a, tail: a, content: a, path: "/p/2"},
-		{size: 2, head: "b", tail: "b", content: "b", path: "/q/1"},
+		{size: 2, head: b, tail: b, content: b, path: "/q/1"},
-		{size: 2, head: "b", tail: "b", content: "b", path: "/q/2"},
+		{size: 2, head: b, tail: b, content: b, path: "/q/2"},
 	}
 
 	forward := dupeGroupsOf(t, recs)

script/cibuild

@@ -2,11 +2,12 @@
 # script/cibuild: run the CI build. It bootstraps first: a CI runner
 # checks out and runs this and nothing else, and script/fmt-check runs
 # the formatter on the host, which a pristine checkout cannot do.
-# A new CACHEBUST value reruns every RUN step, since a cached gate phase
+# A new CACHEBUST value reruns every RUN step after the ARG CACHEBUST
-# is a check that did not run; unlike --no-cache, it keeps Go's build cache.
+# line, since a cached gate phase is a check that did not run; unlike
+# --no-cache, it keeps the layers above that line and the cache mounts.
 # This relies on every stage of the Dockerfile declaring ARG CACHEBUST
-# first; a stage without that line is served from cache on an unchanged
+# before every step that lints, tests or compiles; a stage without that
-# tree, with no warning.
+# line is served from cache on an unchanged tree, with no warning.
 set -eu
 
 SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)"

script/docker

@@ -1,11 +1,12 @@
 #!/bin/sh
 # script/docker: build the Docker image tagged with the project name.
 # Identical in all repos; the tag comes from script/projectname.
-# A new CACHEBUST value reruns every RUN step, since a cached gate phase
+# A new CACHEBUST value reruns every RUN step after the ARG CACHEBUST
-# is a check that did not run; unlike --no-cache, it keeps Go's build cache.
+# line, since a cached gate phase is a check that did not run; unlike
+# --no-cache, it keeps the layers above that line and the cache mounts.
 # This relies on every stage of the Dockerfile declaring ARG CACHEBUST
-# first; a stage without that line is served from cache on an unchanged
+# before every step that lints, tests or compiles; a stage without that
-# tree, with no warning.
+# line is served from cache on an unchanged tree, with no warning.
 set -eu
 
 SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)"

script/lint

@@ -5,11 +5,13 @@
 # make its answer untrustworthy.
 #
 # The phase is not the last stage in the file, so it is built only when
-# --target names it. A new CACHEBUST value reruns every RUN step, since
+# --target names it. A new CACHEBUST value reruns every RUN step after
-# a cached lint layer is a lint that did not run; unlike --no-cache, it
+# the ARG CACHEBUST line, since a cached lint layer is a lint that did
-# keeps Go's build cache. This relies on every stage of the Dockerfile
+# not run; unlike --no-cache, it keeps the layers above that line and
-# declaring ARG CACHEBUST first; a stage without that line is served
+# the cache mounts. This relies on every stage of the Dockerfile
-# from cache on an unchanged tree, with no warning.
+# declaring ARG CACHEBUST before every step that lints, tests or
+# compiles; a stage without that line is served from cache on an
+# unchanged tree, with no warning.
 # --output type=cacheonly writes no image, since nothing uses one.
 set -eu
 

script/test

@@ -3,11 +3,12 @@
 # and this builds that phase alone, on the same terms as script/lint:
 # --target because a phase that is not the last stage is built only when
 # named, and a new CACHEBUST value because a cached test layer is a test
-# that did not run; unlike --no-cache, it keeps Go's build cache. This
+# that did not run; unlike --no-cache, it keeps the layers above the ARG
-# relies on every stage of the Dockerfile declaring ARG CACHEBUST first;
+# CACHEBUST line and the cache mounts. This relies on every stage of the
-# a stage without that line is served from cache on an unchanged tree,
+# Dockerfile declaring ARG CACHEBUST before every step that lints, tests
-# with no warning. --output type=cacheonly writes no image, since
+# or compiles; a stage without that line is served from cache on an
-# nothing uses one.
+# unchanged tree, with no warning. --output type=cacheonly writes no
+# image, since nothing uses one.
 set -eu
 
 SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd -P)"

trees.go

@@ -1,9 +1,9 @@
 package main
 
 import (
-	"bufio"
 	"context"
 	"crypto/sha256"
+	"database/sql"
 	"fmt"
 	"io"
 	"os"
@@ -22,6 +22,17 @@ type treeNode struct {
 	digest    [sha256.Size]byte
 	fileCount int64
 	totalSize int64
+	// diskSize is the bytes the directory's files take on disk. Two
+	// copies of one tree have the same totalSize, but their diskSize
+	// can differ.
+	diskSize int64
+}
+
+// treesPhase names one phase of trees with its place among all of them,
+// as "[2/4] read", for the phase's progress display. The list here is
+// the one place the phases are counted.
+func treesPhase(name string) string {
+	return phaseLabel([]string{openPhase, "read", "group", "write"}, name)
 }
 
 // runTrees implements the trees subcommand: it reads every record from
@@ -31,6 +42,13 @@ type treeNode struct {
 // touches the scanned filesystem; its only I/O is the database, stdout,
 // and stderr. It names the database on stderr before it opens it. Any
 // database problem, including a missing database, is fatal.
+//
+// The work runs in four phases, each under a progress display of its
+// own on stderr: open (open the database), read (read the number of
+// records from the totals table, then read the records into the
+// hierarchy), group (group the directories by digest) and write (write
+// the groups to stdout). Each display ends before the next phase
+// starts, and before an error is returned to be printed.
 func runTrees(ctx context.Context, stdout io.Writer) error {
 	dbPath, source, err := databasePath()
 	if err != nil {
@@ -40,34 +58,103 @@ func runTrees(ctx context.Context, stdout io.Writer) error {
 	fmt.Fprintf(os.Stderr, "trees: database %s (%s)\n",
 		escapePath(dbPath), source)
 
+	// Opening can wait on a busy database for as long as the busy
+	// timeout.
+	prog := newProgress(progressParams{
+		label: treesPhase(openPhase), total: -1,
+		waitingFor: openingDatabase,
+	})
 	db, err := openReportDatabase(ctx, dbPath)
+
+	prog.finish()
+
 	if err != nil {
 		return err
 	}
 
 	defer func() { _ = db.Close() }()
 
-	records := 0
+	prog = newProgress(progressParams{
-	tree := newTreeBuilder()
+		label: treesPhase("read"), unit: "records", total: -1,
-
+		waitingFor: countingRecords, stalledOn: "db",
-	err = loadFileRows(ctx, db, func(r scanRec) {
-		records++
-
-		tree.add(r)
 	})
+	records, super, allDirs, err := readTree(ctx, db, prog)
+
+	prog.finish()
+
 	if err != nil {
 		return fmt.Errorf("database %s: %w", dbPath, err)
 	}
 
+	// Grouping works in memory, so it waits on nothing but the
+	// processor.
+	prog = newProgress(progressParams{
+		label: treesPhase("group"), unit: "directories",
+		total: int64(len(allDirs)), stalledOn: "cpu",
+	})
+	dupes := collectTreeGroups(allDirs, super, prog)
+
+	prog.finish()
+
+	prog = newProgress(progressParams{
+		label: treesPhase("write"), unit: "groups", total: int64(len(dupes)),
+		stalledOn: "out",
+	})
+	dupeTrees, reclaimable, err := writeTreeGroups(stdout, dupes, prog)
+
+	prog.finish()
+
+	if err != nil {
+		return err
+	}
+
+	fmt.Fprintf(os.Stderr,
+		"trees: %d records read, %d duplicate tree groups, %d dupe trees, "+
+			"%s reclaimable\n",
+		records, len(dupes), dupeTrees, humanBytes(reclaimable))
+
+	return nil
+}
+
+// readTree gives prog the number of records in db as its total, then
+// reads every record in path order into the directory hierarchy,
+// counting each on prog. It returns the number of records read, the
+// super-root and every directory.
+func readTree(ctx context.Context, db *sql.DB,
+	prog *progress,
+) (int, *treeNode, []*treeNode, error) {
+	records := 0
+	tree := newTreeBuilder()
+
+	err := loadFileRows(ctx, db, prog.setTotal, func(r scanRec) {
+		records++
+
+		prog.increment()
+		tree.add(r)
+	})
+	if err != nil {
+		return 0, nil, nil, err
+	}
+
 	super, allDirs := tree.finish()
 
-	dupes := collectTreeGroups(allDirs, super)
+	return records, super, allDirs, nil
+}
 
-	out := bufio.NewWriterSize(stdout, ioBufSize)
+// writeTreeGroups writes dupes to stdout as TSV, a header line and then
+// a row for every member of each group but its first, counting each
+// group on prog once its rows are written. The disk_size column is the
+// dupe's own. stdout may be the terminal prog is drawn on, so the lines
+// go through prog's writer. It returns the number of rows (dupe trees)
+// and the bytes they could reclaim.
+func writeTreeGroups(stdout io.Writer, dupes [][]*treeNode,
+	prog *progress,
+) (int, int64, error) {
+	out := prog.writer(stdout)
 
-	_, err = fmt.Fprintln(out, "first\tdupe\tfiles\tsize")
+	_, err := fmt.Fprintln(out, "first\tdupe\tfiles\tsize\tdisk_size")
 	if err != nil {
-		return fmt.Errorf("write stdout: %w", err)
+		return 0, 0, fmt.Errorf("write stdout: %w", err)
 	}
 
 	dupeTrees := 0
@@ -77,29 +164,26 @@ func runTrees(ctx context.Context, stdout io.Writer) error {
 	for _, g := range dupes {
 		first := g[0]
 		for _, n := range g[1:] {
-			_, err = fmt.Fprintf(out, "%s\t%s\t%d\t%d\n",
+			_, err = fmt.Fprintf(out, "%s\t%s\t%d\t%d\t%d\n",
 				escapePath(first.path), escapePath(n.path),
-				first.fileCount, first.totalSize)
+				first.fileCount, first.totalSize, n.diskSize)
 			if err != nil {
-				return fmt.Errorf("write stdout: %w", err)
+				return 0, 0, fmt.Errorf("write stdout: %w", err)
 			}
 
 			dupeTrees++
 			reclaimable += first.totalSize
 		}
+
+		prog.increment()
 	}
 
 	err = out.Flush()
 	if err != nil {
-		return fmt.Errorf("write stdout: %w", err)
+		return 0, 0, fmt.Errorf("write stdout: %w", err)
 	}
 
-	fmt.Fprintf(os.Stderr,
+	return dupeTrees, reclaimable, nil
-		"trees: %d records read, %d duplicate tree groups, %d dupe trees, "+
-			"%s reclaimable\n",
-		records, len(dupes), dupeTrees, humanBytes(reclaimable))
-
-	return nil
 }
 
 // treeBuilder reconstructs the directory hierarchy from records added
@@ -153,6 +237,7 @@ func (b *treeBuilder) add(r scanRec) {
 	dir.entries = append(dir.entries, fileEntry(name, r))
 	dir.fileCount++
 	dir.totalSize += r.size
+	dir.diskSize += r.diskSize
 }
 
 // openDir starts the directory called name inside the innermost open
@@ -191,6 +276,7 @@ func (b *treeBuilder) closeTo(n int) {
 			"d\x00"+name+"\x00"+string(dir.digest[:]))
 		dir.parent.fileCount += dir.fileCount
 		dir.parent.totalSize += dir.totalSize
+		dir.parent.diskSize += dir.diskSize
 		b.dirs = append(b.dirs, dir)
 	}
 }
@@ -207,28 +293,23 @@ func (b *treeBuilder) finish() (*treeNode, []*treeNode) {
 // name and its signature (size, head, tail, content); mtime is
 // excluded.
 func fileEntry(name string, r scanRec) string {
-	content := r.content
-
-	// A record without a content hash has unknown content (README
-	// "Database"): give it a signature no other file can share, so
-	// trees containing it never compare equal. Real hashes are hex, so
-	// the NUL-prefixed form cannot collide.
-	if content == "" {
-		content = "unhashed\x00" + r.path
-	}
-
 	return "f\x00" + name + "\x00" + strconv.FormatInt(r.size, 10) +
-		"\x00" + r.head + "\x00" + r.tail + "\x00" + content
+		"\x00" + string(r.head[:]) + "\x00" + string(r.tail[:]) +
+		"\x00" + string(r.content[:])
 }
 
-// collectTreeGroups groups directories by digest and returns every
+// collectTreeGroups groups directories by digest, counting each one on
-// maximal group with two or more members, each group's members sorted
+// prog as it is grouped, and returns every maximal group with two or
-// by path, groups ordered by tree size descending then by first path
+// more members, each group's members sorted by path, groups ordered by
-// ascending.
+// tree size descending then by first path ascending.
-func collectTreeGroups(allDirs []*treeNode, super *treeNode) [][]*treeNode {
+func collectTreeGroups(allDirs []*treeNode, super *treeNode,
+	prog *progress,
+) [][]*treeNode {
 	groups := make(map[[sha256.Size]byte][]*treeNode)
 	for _, d := range allDirs {
 		groups[d.digest] = append(groups[d.digest], d)
+
+		prog.increment()
 	}
 
 	var dupes [][]*treeNode
@@ -264,7 +345,8 @@ func collectTreeGroups(allDirs []*treeNode, super *treeNode) [][]*treeNode {
 // 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.
+// and every hash and digest is 32 bytes, so NUL delimiters are
+// unambiguous.
 func (n *treeNode) computeDigest() {
 	slices.Sort(n.entries)
 

trees_test.go

@@ -3,31 +3,38 @@ package main
 import (
 	"bytes"
 	"database/sql"
+	"os"
 	"slices"
+	"strings"
 	"testing"
+	"time"
 )
 
-// Signature hashes shared by the smoke-test records.
+// treesOpenLine is the plain line of trees' open phase when it opens
-const (
+// the database at once; it prints it as the phase starts and as it ends.
-	f1Head    = "f1h"
+const treesOpenLine = "[1/4] open: opening the database, elapsed 0s, " +
-	f1Tail    = "f1t"
+	"remain unknown"
-	f1Content = "f1c"
-	f2Head    = "f2h"
-	f2Tail    = "f2t"
-	f2Content = "f2c"
-)
 
 // smokeTreeRecs mirrors the README smoke-test tree layout: /d/t1 and
 // /d/t2 are identical, /d/t3 differs from them only by one filename.
+// Each file takes one 4 KiB block on disk.
 func smokeTreeRecs() []scanRec {
+	f1Head, f1Tail, f1Content := testHash("f1h"), testHash("f1t"), testHash("f1c")
+	f2Head, f2Tail, f2Content := testHash("f2h"), testHash("f2t"), testHash("f2c")
+
 	return []scanRec{
-		{size: 3000, head: f1Head, tail: f1Tail, content: f1Content, path: "/d/t1/f1"},
+		{size: 3000, diskSize: 4096, head: f1Head, tail: f1Tail,
-		{size: 100, head: f2Head, tail: f2Tail, content: f2Content, path: "/d/t1/sub/f2"},
+			content: f1Content, path: "/d/t1/f1"},
-		{size: 3000, head: f1Head, tail: f1Tail, content: f1Content, path: "/d/t2/f1"},
+		{size: 100, diskSize: 4096, head: f2Head, tail: f2Tail,
-		{size: 100, head: f2Head, tail: f2Tail, content: f2Content, path: "/d/t2/sub/f2"},
+			content: f2Content, path: "/d/t1/sub/f2"},
-		{size: 3000, head: f1Head, tail: f1Tail, content: f1Content, path: "/d/t3/f1"},
+		{size: 3000, diskSize: 4096, head: f1Head, tail: f1Tail,
-		{size: 100, head: f2Head, tail: f2Tail, content: f2Content,
+			content: f1Content, path: "/d/t2/f1"},
-			path: "/d/t3/sub/f2renamed"},
+		{size: 100, diskSize: 4096, head: f2Head, tail: f2Tail,
+			content: f2Content, path: "/d/t2/sub/f2"},
+		{size: 3000, diskSize: 4096, head: f1Head, tail: f1Tail,
+			content: f1Content, path: "/d/t3/f1"},
+		{size: 100, diskSize: 4096, head: f2Head, tail: f2Tail,
+			content: f2Content, path: "/d/t3/sub/f2renamed"},
 	}
 }
 
@@ -38,7 +45,7 @@ func dbTree(t *testing.T, db *sql.DB) (*treeNode, []*treeNode) {
 
 	tree := newTreeBuilder()
 
-	err := loadFileRows(t.Context(), db, tree.add)
+	err := loadFileRows(t.Context(), db, func(int64) {}, tree.add)
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -145,13 +152,14 @@ func TestTreeNamesSortingBeforeSlash(t *testing.T) {
 
 	for _, top := range []string{"/a", "/c"} {
 		for _, p := range []string{"/b", "/b-x/f", "/b.txt", "/b/f"} {
-			content := "c"
+			content := testHash("c")
 			if p == "/b-x/f" {
-				content = "other"
+				content = testHash("other")
 			}
 
 			recs = append(recs, scanRec{
-				size: 1, head: "h", tail: "t", content: content, path: top + p,
+				size: 1, head: testHash("h"), tail: testHash("t"),
+				content: content, path: top + p,
 			})
 		}
 	}
@@ -170,7 +178,7 @@ func TestTreeNamesSortingBeforeSlash(t *testing.T) {
 		t.Fatalf("directory paths = %q, want %q", got, want)
 	}
 
-	groups := collectTreeGroups(dirs, super)
+	groups := collectTreeGroups(dirs, super, nil)
 
 	gotGroups := groupPaths(groups)
 	wantGroups := [][]string{{"/a", "/c"}}
@@ -196,13 +204,128 @@ func TestRunTreesEscapesPaths(t *testing.T) {
 			code, exitOK, stderr.String())
 	}
 
-	want := "first\tdupe\tfiles\tsize\n" +
+	want := "first\tdupe\tfiles\tsize\tdisk_size\n" +
-		`/d/\tone\ntwo\rthree\\four` + "\t/d/A\t1\t5\n"
+		`/d/\tone\ntwo\rthree\\four` + "\t/d/A\t1\t5\t4096\n"
 	if got := stdout.String(); got != want {
 		t.Errorf("stdout = %q, want %q", got, want)
 	}
 }
 
+// TestRunTreesDiskSize runs trees on two copies of a tree whose files
+// take different space on disk. The row's disk_size is the sum over the
+// dupe copy's files, those in its subdirectory included.
+func TestRunTreesDiskSize(t *testing.T) {
+	f, g := testHash("f"), testHash("g")
+	recs := []scanRec{
+		{size: 10, diskSize: 4096, head: f, tail: f, content: f, path: "/a/f"},
+		{size: 20, diskSize: 4096, head: g, tail: g, content: g, path: "/a/sub/g"},
+		{size: 10, diskSize: 512, head: f, tail: f, content: f, path: "/b/f"},
+		{size: 20, diskSize: 1024, head: g, tail: g, content: g, path: "/b/sub/g"},
+	}
+
+	t.Setenv(databaseEnv, seedDatabase(t, recs))
+
+	want := "first\tdupe\tfiles\tsize\tdisk_size\n/a\t/b\t2\t30\t1536\n"
+	if got := runStdout(t, cmdTrees); got != want {
+		t.Errorf("stdout = %q, want %q", got, want)
+	}
+}
+
+// TestRunTreesProgressNamesEachPhase runs trees on the smoke-test
+// records with stderr not a terminal, and checks every line it prints
+// there. After the line naming the database, each phase prints a line
+// naming it with its place among the four as it starts and another as
+// it ends. read counts the 6 records before it reads them, group counts
+// the 8 directories, and write the 1 group. The summary comes last, and
+// stdout holds the report alone.
+func TestRunTreesProgressNamesEachPhase(t *testing.T) {
+	path := seedDatabase(t, smokeTreeRecs())
+	t.Setenv(databaseEnv, path)
+
+	stderr := captureStderr(t)
+
+	var stdout bytes.Buffer
+
+	code := run([]string{cmdTrees}, &stdout, os.Stderr)
+	if code != exitOK {
+		t.Fatalf("run(trees) = %d, want %d; stderr: %s",
+			code, exitOK, stderr())
+	}
+
+	report := "first\tdupe\tfiles\tsize\tdisk_size\n" +
+		"/d/t1\t/d/t2\t2\t3100\t8192\n"
+	if got := stdout.String(); got != report {
+		t.Errorf("stdout = %q, want %q", got, report)
+	}
+
+	// How each line starts; the rate at the end of a phase varies.
+	want := []string{
+		"trees: database " + path + " (from " + databaseEnv + ")",
+		treesOpenLine,
+		treesOpenLine,
+		"[2/4] read: counting the records, elapsed 0s, remain unknown",
+		"[2/4] read: [6/6] 100%, ",
+		"[3/4] group: [0/8] 0%, 0 directories/s, elapsed 0s, remain unknown",
+		"[3/4] group: [8/8] 100%, ",
+		"[4/4] write: [0/1] 0%, 0 groups/s, elapsed 0s, remain unknown",
+		"[4/4] write: [1/1] 100%, ",
+		"trees: 6 records read, 1 duplicate tree groups, 1 dupe trees, ",
+	}
+
+	lines := strings.Split(strings.TrimSuffix(stderr(), "\n"), "\n")
+	if len(lines) != len(want) {
+		t.Fatalf("stderr lines = %q, want %d lines starting %q",
+			lines, len(want), want)
+	}
+
+	for i := range want {
+		if !strings.HasPrefix(lines[i], want[i]) {
+			t.Errorf("stderr line %d = %q, want it to start %q",
+				i+1, lines[i], want[i])
+		}
+	}
+}
+
+// TestWriteTreeGroupsOnTerminal writes the smoke-test report to the
+// terminal its write phase's display is drawn on, as a plain "sfdupes
+// trees" does: the terminal must show the header and the row whole,
+// each on a line of its own.
+//
+//nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
+func TestWriteTreeGroupsOnTerminal(t *testing.T) {
+	stderr := captureStderr(t)
+	super, dirs := treeOf(t, smokeTreeRecs())
+	dupes := collectTreeGroups(dirs, super, nil)
+
+	// No timed draws: the display is drawn as it starts and as it ends.
+	p := startProgress(progressParams{
+		label: treesPhase("write"), unit: "groups", total: int64(len(dupes)),
+	}, terminalWidth, time.Hour, time.Now)
+
+	_, _, err := writeTreeGroups(os.Stderr, dupes, p)
+
+	p.finish()
+
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	// A terminal shows each line as the text after its last carriage
+	// return.
+	var shown []string
+
+	for line := range strings.SplitSeq(stderr(), "\n") {
+		shown = append(shown, line[strings.LastIndex(line, "\r")+1:])
+	}
+
+	want := []string{
+		"first\tdupe\tfiles\tsize\tdisk_size", "/d/t1\t/d/t2\t2\t3100\t8192",
+	}
+	if len(shown) < len(want) || !slices.Equal(shown[:len(want)], want) {
+		t.Errorf("terminal shows lines %q, want %q first", shown, want)
+	}
+}
+
 func TestTreeDigests(t *testing.T) {
 	t.Parallel()
 
@@ -232,11 +355,10 @@ func TestTreeDigests(t *testing.T) {
 func TestTreeDigestContentSensitivity(t *testing.T) {
 	t.Parallel()
 
-	const sharedTail = "same"
+	same, c := testHash("same"), testHash("c")
-
 	recs := []scanRec{
-		{size: 10, head: sharedTail, tail: sharedTail, content: "c", path: "/r/a/f"},
+		{size: 10, head: same, tail: same, content: c, path: "/r/a/f"},
-		{size: 10, head: "DIFF", tail: sharedTail, content: "c", path: "/r/b/f"},
+		{size: 10, head: testHash("DIFF"), tail: same, content: c, path: "/r/b/f"},
 	}
 
 	_, dirs := treeOf(t, recs)
@@ -254,7 +376,7 @@ func TestCollectTreeGroupsMaximal(t *testing.T) {
 
 	super, dirs := treeOf(t, smokeTreeRecs())
 
-	groups := collectTreeGroups(dirs, super)
+	groups := collectTreeGroups(dirs, super, nil)
 
 	want := [][]string{{"/d/t1", "/d/t2"}}
 	if got := groupPaths(groups); !slices.EqualFunc(got, want,
@@ -278,14 +400,14 @@ func TestCollectTreeGroupsDeterministic(t *testing.T) {
 
 	super, dirs := treeOf(t, recs)
 
-	forward := groupPaths(collectTreeGroups(dirs, super))
+	forward := groupPaths(collectTreeGroups(dirs, super, nil))
 
 	reversed := slices.Clone(recs)
 	slices.Reverse(reversed)
 
 	superR, dirsR := treeOf(t, reversed)
 
-	backward := groupPaths(collectTreeGroups(dirsR, superR))
+	backward := groupPaths(collectTreeGroups(dirsR, superR, nil))
 	if !slices.EqualFunc(forward, backward, slices.Equal) {
 		t.Fatalf("output depends on record order: %v vs %v",
 			forward, backward)
@@ -297,14 +419,15 @@ func TestCollectTreeGroupsSiblings(t *testing.T) {
 
 	// Identical sibling dirs share a parent, so their group cannot be
 	// implied by a parent group and must be reported.
+	h, tl, c := testHash("h"), testHash("t"), testHash("c")
 	recs := []scanRec{
-		{size: 10, head: "h", tail: "t", content: "c", path: "/p/x1/f"},
+		{size: 10, head: h, tail: tl, content: c, path: "/p/x1/f"},
-		{size: 10, head: "h", tail: "t", content: "c", path: "/p/x2/f"},
+		{size: 10, head: h, tail: tl, content: c, path: "/p/x2/f"},
 	}
 
 	super, dirs := treeOf(t, recs)
 
-	got := groupPaths(collectTreeGroups(dirs, super))
+	got := groupPaths(collectTreeGroups(dirs, super, nil))
 
 	want := [][]string{{"/p/x1", "/p/x2"}}
 	if !slices.EqualFunc(got, want, slices.Equal) {
@@ -318,15 +441,16 @@ func TestCollectTreeGroupsDifferingParents(t *testing.T) {
 	// /p/a and /q/b contain identical x subtrees, but /p/a has an
 	// extra file, so the parents' digests differ and the x group must
 	// be reported.
+	h, tl, c, e := testHash("h"), testHash("t"), testHash("c"), testHash("e")
 	recs := []scanRec{
-		{size: 10, head: "h", tail: "t", content: "c", path: "/p/a/x/f"},
+		{size: 10, head: h, tail: tl, content: c, path: "/p/a/x/f"},
-		{size: 99, head: "e", tail: "e", content: "e", path: "/p/a/extra"},
+		{size: 99, head: e, tail: e, content: e, path: "/p/a/extra"},
-		{size: 10, head: "h", tail: "t", content: "c", path: "/q/b/x/f"},
+		{size: 10, head: h, tail: tl, content: c, path: "/q/b/x/f"},
 	}
 
 	super, dirs := treeOf(t, recs)
 
-	got := groupPaths(collectTreeGroups(dirs, super))
+	got := groupPaths(collectTreeGroups(dirs, super, nil))
 
 	want := [][]string{{"/p/a/x", "/q/b/x"}}
 	if !slices.EqualFunc(got, want, slices.Equal) {