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 +29,70 @@
 
 # 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
@@ -144,7 +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
@@ -345,9 +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
@@ -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)
 	}
 }
 
@@ -762,7 +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)
@@ -802,7 +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"
@@ -46,18 +47,20 @@ 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
 `
 
@@ -67,14 +70,59 @@ 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
 `
@@ -92,6 +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
@@ -144,9 +196,14 @@ func createDatabaseDirectory(path string) error {
 // 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, trees and
 // info: read-only, with the same busy timeout. They set no journal
@@ -420,14 +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,
@@ -474,7 +531,7 @@ func loadFileRows(ctx context.Context, db *sql.DB, total func(n int64),
 
 	var n int64
 
-	err = tx.QueryRowContext(ctx, "SELECT COUNT(*) FROM files").Scan(&n)
+	err = tx.QueryRowContext(ctx, recordCountSQL).Scan(&n)
 	if err != nil {
 		return fmt.Errorf("count records: %w", err)
 	}
@@ -482,8 +539,8 @@ func loadFileRows(ctx context.Context, db *sql.DB, total func(n int64),
 	total(n)
 
 	rows, err := tx.QueryContext(ctx,
-		"SELECT path, size, mtime, mtime_nsec, head, tail, content "+
+		"SELECT path, size, disk_size, mtime, mtime_nsec, head, tail, "+
-			"FROM files ORDER BY path")
+			"content FROM files ORDER BY path")
 	if err != nil {
 		return fmt.Errorf("read records: %w", err)
 	}
@@ -492,19 +549,25 @@ func loadFileRows(ctx context.Context, db *sql.DB, total func(n int64),
 
 	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)
 	}
 
@@ -527,10 +590,11 @@ ORDER BY size DESC, head DESC, tail DESC, content DESC
 `
 
 // loadSignatureRows gives total the number of records, then streams
-// every record's signature and path to fn, without its mtime, in the
+// every record's signature and path to fn, without its mtime or its
-// order of signatureRowsSQL. The count and the records are read in one
+// disk_size, in the order of signatureRowsSQL. The count and the
-// transaction, so they agree while a scan is committing. An error from
+// records are read in one transaction, so they agree while a scan is
-// fn stops the reading and is returned as it is.
+// committing. An error from fn stops the reading and is returned as it
+// is.
 func loadSignatureRows(ctx context.Context, db *sql.DB,
 	total func(n int64), fn func(r scanRec) error,
 ) error {
@@ -545,7 +609,7 @@ func loadSignatureRows(ctx context.Context, db *sql.DB,
 
 	var n int64
 
-	err = tx.QueryRowContext(ctx, "SELECT COUNT(*) FROM files").Scan(&n)
+	err = tx.QueryRowContext(ctx, recordCountSQL).Scan(&n)
 	if err != nil {
 		return fmt.Errorf("count records: %w", err)
 	}
@@ -561,17 +625,22 @@ func loadSignatureRows(ctx context.Context, db *sql.DB,
 
 	for rows.Next() {
 		var (
-			path []byte
+			path, head, tail, content []byte
-			r    scanRec
+			r                         scanRec
 		)
 
-		err = rows.Scan(&r.size, &r.head, &r.tail, &r.content, &path)
+		err = rows.Scan(&r.size, &head, &tail, &content, &path)
 		if err != nil {
 			return fmt.Errorf("read record: %w", err)
 		}
 
 		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
@@ -586,11 +655,27 @@ func loadSignatureRows(ctx context.Context, db *sql.DB,
 	return nil
 }
 
+// setHashes sets r's head, tail and content to the values read from
+// those columns. Each must be the raw 32 bytes of a SHA-256.
+func (r *scanRec) setHashes(head, tail, content []byte) error {
+	for _, b := range [][]byte{head, tail, content} {
+		if len(b) != sha256.Size {
+			return fmt.Errorf("%w: found %d bytes", errHashSize, len(b))
+		}
+	}
+
+	r.head = [sha256.Size]byte(head)
+	r.tail = [sha256.Size]byte(tail)
+	r.content = [sha256.Size]byte(content)
+
+	return nil
+}
+
 // countRecords returns the number of records in the database.
 func countRecords(ctx context.Context, db *sql.DB) (int64, error) {
 	var n int64
 
-	err := db.QueryRowContext(ctx, "SELECT COUNT(*) FROM files").Scan(&n)
+	err := db.QueryRowContext(ctx, recordCountSQL).Scan(&n)
 	if err != nil {
 		return 0, fmt.Errorf("count records: %w", err)
 	}
@@ -598,16 +683,10 @@ func countRecords(ctx context.Context, db *sql.DB) (int64, error) {
 	return n, nil
 }
 
-// databaseCountsSQL counts the records, those with head and tail
+// databaseCountsSQL reads the number of records and the sizes of all
-// hashes and those with a content hash, and adds up their sizes, in one
+// records added up from totals.
-// pass over the table. A SUM over no rows is NULL, so on an empty table
-// each SUM falls back to 0.
 const databaseCountsSQL = `
-SELECT COUNT(*),
+SELECT records, size FROM totals
-       COALESCE(SUM(head <> '' AND tail <> ''), 0),
-       COALESCE(SUM(content <> ''), 0),
-       COALESCE(SUM(size), 0)
-FROM files
 `
 
 // databaseCounts is what info reads from the database: its schema
@@ -615,8 +694,6 @@ FROM files
 type databaseCounts struct {
 	schemaVersion int
 	records       int64 // every record
-	headTail      int64 // records with head and tail hashes
-	content       int64 // records with a content hash
 	size          int64 // the sizes of all records added up
 }
 
@@ -644,7 +721,7 @@ func readDatabaseCounts(ctx context.Context,
 	}
 
 	err = tx.QueryRowContext(ctx, databaseCountsSQL).
-		Scan(&c.records, &c.headTail, &c.content, &c.size)
+		Scan(&c.records, &c.size)
 	if err != nil {
 		return c, fmt.Errorf("count records: %w", err)
 	}
@@ -652,90 +729,15 @@ func readDatabaseCounts(ctx context.Context,
 	return c, nil
 }
 
-// loadFileMeta streams every record's path, size, mtime, and whether
+// loadFileMeta streams every record's path, size, disk_size and mtime
-// it carries hashes to fn. Scan change detection needs no hash
+// to fn. Scan change detection needs no hash values, and skipping the
-// values, and skipping the hash columns keeps the scan's in-memory
+// hash columns keeps the scan's in-memory index small on
-// index small on multi-million-file databases.
+// multi-million-file databases.
 func loadFileMeta(ctx context.Context, db *sql.DB,
-	fn func(path string, size int64, mtime time.Time, hashed bool),
+	fn func(path string, m fileMeta),
 ) error {
 	rows, err := db.QueryContext(ctx,
-		"SELECT path, size, mtime, mtime_nsec, head <> '' FROM files")
+		"SELECT path, size, disk_size, mtime, mtime_nsec FROM files")
-	if err != nil {
-		return fmt.Errorf("read records: %w", err)
-	}
-
-	defer func() { _ = rows.Close() }()
-
-	for rows.Next() {
-		var (
-			path            []byte
-			size, sec, nsec int64
-			hashed          int64
-		)
-
-		err = rows.Scan(&path, &size, &sec, &nsec, &hashed)
-		if err != nil {
-			return fmt.Errorf("read record: %w", err)
-		}
-
-		fn(string(path), size, time.Unix(sec, nsec), hashed != 0)
-	}
-
-	err = rows.Err()
-	if err != nil {
-		return fmt.Errorf("read records: %w", err)
-	}
-
-	return nil
-}
-
-// contentGroupsSQL selects each group (the records sharing a size,
-// head, and tail) of records of at least headTailMin bytes that has more
-// than one record and at least one record without a content hash, with
-// the number of its records.
-const contentGroupsSQL = `
-SELECT size, head, tail, COUNT(*) AS records
-FROM files
-WHERE size >= ? AND head <> ''
-GROUP BY size, head, tail
-HAVING COUNT(*) > 1 AND SUM(content = '') > 0
-`
-
-// contentCandidatesSQL selects every record of the groups
-// contentGroupsSQL selects, with whether each record has a content
-// hash. SQLite does the grouping, so no other record's hashes are
-// loaded into memory; the rows come ordered by size, head, and tail, so
-// each 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
-JOIN (` + contentGroupsSQL + `) AS g USING (size, head, tail)
-ORDER BY size, head, tail
-`
-
-// countContentCandidates returns the number of rows of
-// contentCandidatesSQL, adding up the records of the groups
-// contentGroupsSQL selects, so it neither joins nor sorts.
-func countContentCandidates(ctx context.Context, db *sql.DB) (int64, error) {
-	var n int64
-
-	err := db.QueryRowContext(ctx,
-		"SELECT COALESCE(SUM(records), 0) FROM ("+contentGroupsSQL+")",
-		headTailMin).Scan(&n)
-	if err != nil {
-		return 0, fmt.Errorf("count content candidates: %w", err)
-	}
-
-	return n, nil
-}
-
-// loadContentCandidates streams the rows of contentCandidatesSQL to fn:
-// each record, without its content hash, and whether it has one.
-func loadContentCandidates(ctx context.Context, db *sql.DB,
-	fn func(r scanRec, hashed bool),
-) error {
-	rows, err := db.QueryContext(ctx, contentCandidatesSQL, headTailMin)
 	if err != nil {
 		return fmt.Errorf("read records: %w", err)
 	}
@@ -745,20 +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()
@@ -776,21 +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
 		}
@@ -799,10 +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 {
@@ -816,6 +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
@@ -841,8 +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)
 		}
@@ -853,6 +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

@@ -2,6 +2,7 @@ package main
 
 import (
 	"context"
+	"crypto/sha256"
 	"database/sql"
 	"errors"
 	"fmt"
@@ -473,17 +474,73 @@ func TestLoadRowsCountAgreeDuringScan(t *testing.T) {
 	}
 }
 
-// TestSignatureRowsNeedNoSort checks that SQLite reads signatureRowsSQL
+// TestLoadRowsRefuseWrongSizeHash stores a record whose head, tail or
-// from the files_signature index alone, with nothing to sort: the
+// content is not the 32 bytes of a SHA-256: either one byte, or the 64
-// first record comes at once, so report's read phase counts each
+// bytes of a SHA-256 written as hex text. loadFileRows and
-// record as it comes rather than waiting on SQLite for all of them.
+// loadSignatureRows must each fail on it with an error naming its path.
-func TestSignatureRowsNeedNoSort(t *testing.T) {
+func TestLoadRowsRefuseWrongSizeHash(t *testing.T) {
 	t.Parallel()
 
-	db := openTestDB(t)
+	hexText := strings.Repeat("ab", sha256.Size)
 
-	rows, err := db.QueryContext(t.Context(),
+	cases := []struct {
-		"EXPLAIN QUERY PLAN "+signatureRowsSQL)
+		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)
 	}
@@ -511,12 +568,164 @@ func TestSignatureRowsNeedNoSort(t *testing.T) {
 		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()
 
@@ -527,12 +736,13 @@ 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",
 		},
 	}
 
@@ -553,8 +763,8 @@ 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},
@@ -581,8 +791,8 @@ 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),
 		})
 	}
 
@@ -612,62 +822,3 @@ func TestApplyChangesBatching(t *testing.T) {
 		t.Fatalf("records = %d, want 0", len(got))
 	}
 }
-
-// TestCountContentCandidates checks that countContentCandidates counts
-// the records the content phase's search returns: those of each group
-// of two or more records of headTailMin or more with a head, where at
-// least one has no content hash.
-func TestCountContentCandidates(t *testing.T) {
-	t.Parallel()
-
-	db := openTestDB(t)
-
-	// Each group's records: size, head, and content, one per record.
-	groups := []struct {
-		size     int64
-		head     string
-		contents []string
-	}{
-		{headTailMin, "h", []string{"", "c", "c"}}, // returned
-		{headTailMin + 1, "h", []string{"", ""}},   // returned
-		{headTailMin + 2, "h", []string{"c", "c"}}, // all hashed
-		{headTailMin + 3, "h", []string{""}},       // one record
-		{headTailMin - 1, "h", []string{"", ""}},   // too small
-		{headTailMin + 4, "", []string{"", ""}},    // no head
-	}
-
-	var recs []scanRec
-
-	for _, g := range groups {
-		for _, content := range g.contents {
-			recs = append(recs, scanRec{
-				size: g.size, mtime: time.Unix(1, 0), head: g.head,
-				tail: "t", content: content,
-				path: fmt.Sprintf("/r/%d", len(recs)),
-			})
-		}
-	}
-
-	err := applyChanges(t.Context(), db, recs, nil, nil)
-	if err != nil {
-		t.Fatalf("applyChanges: %v", err)
-	}
-
-	got, err := countContentCandidates(t.Context(), db)
-	if err != nil {
-		t.Fatalf("countContentCandidates: %v", err)
-	}
-
-	var returned int64
-
-	err = loadContentCandidates(t.Context(), db,
-		func(scanRec, bool) { returned++ })
-	if err != nil {
-		t.Fatalf("loadContentCandidates: %v", err)
-	}
-
-	if got != 5 || returned != 5 {
-		t.Errorf("count = %d, records returned = %d, want 5 and 5",
-			got, returned)
-	}
-}

exclude_test.go

@@ -164,9 +164,8 @@ func TestDefaultExcludesHelp(t *testing.T) {
 // 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, and
+// outside the operands: the record of a file gone from it is kept,
-// its size joins the size census, while a file added to it is not
+// while a file added to it is not recorded.
-// recorded.
 //
 //nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
 func TestScanDoesNotEnterDefaultExclude(t *testing.T) {
@@ -186,10 +185,6 @@ func TestScanDoesNotEnterDefaultExclude(t *testing.T) {
 
 	unseen := writeFile(t, excluded, "new", pattern(2, 10))
 
-	// The same size as gone, so it is hashed only if the census holds the
-	// size of gone's record.
-	added := writeFile(t, dir, "added", pattern(3, 100))
-
 	st, err := syncScan(t.Context(), db, []string{dir}, 1, false,
 		walkRules{excludes: []string{excluded}})
 	if err != nil {
@@ -203,11 +198,6 @@ func TestScanDoesNotEnterDefaultExclude(t *testing.T) {
 	recs := dbRecords(t, db)
 	recordByPath(t, recs, gone)
 
-	if recordByPath(t, recs, added).head == "" {
-		t.Errorf("%s not hashed: the census lacks the size of %s",
-			added, gone)
-	}
-
 	if slices.Contains(recordPaths(recs), unseen) {
 		t.Errorf("%s recorded: the walk entered %s", unseen, excluded)
 	}
@@ -391,9 +381,8 @@ func TestRunScanSkipsNonPersistentOperand(t *testing.T) {
 // 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, and its size joins the size
+// the record of a file gone from it is kept, while a file added to it
-// census, while a file added to it is not recorded, and its size does
+// is not recorded.
-// not join the census.
 //
 //nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
 func TestScanKeepsRecordsOnNonPersistent(t *testing.T) {
@@ -413,11 +402,6 @@ func TestScanKeepsRecordsOnNonPersistent(t *testing.T) {
 
 	unseen := writeFile(t, shm, "new", pattern(2, 10))
 
-	// added has the size of gone, and lonely that of unseen: each is
-	// hashed only if the census holds that size.
-	added := writeFile(t, dir, "added", pattern(3, 100))
-	lonely := writeFile(t, dir, "lonely", pattern(4, 10))
-
 	st, err := syncScan(t.Context(), db, []string{shm, dir}, 1, false, rules)
 	if err != nil {
 		t.Fatal(err)
@@ -430,15 +414,6 @@ func TestScanKeepsRecordsOnNonPersistent(t *testing.T) {
 	recs := dbRecords(t, db)
 	recordByPath(t, recs, gone)
 
-	if recordByPath(t, recs, added).head == "" {
-		t.Errorf("%s not hashed: the census lacks the size of %s",
-			added, gone)
-	}
-
-	if recordByPath(t, recs, lonely).head != "" {
-		t.Errorf("%s hashed: the census holds the size of %s", lonely, unseen)
-	}
-
 	if slices.Contains(recordPaths(recs), unseen) {
 		t.Errorf("%s recorded", unseen)
 	}
@@ -450,51 +425,6 @@ func TestScanKeepsRecordsOnNonPersistent(t *testing.T) {
 	}
 }
 
-// TestScanContentSkipsNonPersistent checks that the content phase does
-// not read a file on a filesystem that is not persistent, though an
-// earlier scan left a record for it: it is treated as a changed file,
-// so its record is left as it is and its identical copy in another
-// tree, having no other match, is not read either.
-func TestScanContentSkipsNonPersistent(t *testing.T) {
-	t.Parallel()
-
-	shm, _, rules := shmTempDir(t)
-	db := openTestDB(t)
-
-	// A scan that, without the list of filesystems, records a with a
-	// head and tail but no content hash.
-	a := sparseFileWithoutMatch(t, shm, "a", headTailMin)
-
-	syncTree(t, db, shm)
-
-	before := recordByPath(t, dbRecords(t, db), a)
-	if before.head == "" || before.content != "" {
-		t.Fatalf("after scanning %s: %+v, want head and tail only", shm, before)
-	}
-
-	b := sparseFile(t, t.TempDir(), "b", headTailMin)
-
-	st, err := syncScan(t.Context(), db, []string{filepath.Dir(b)}, 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)
-	if r := recordByPath(t, recs, a); r != before {
-		t.Errorf("record = %+v, want it left as %+v", r, before)
-	}
-
-	if r := recordByPath(t, recs, b); r.content != "" {
-		t.Errorf("%s: content = %q, want none: its only match is on %s",
-			b, r.content, shm)
-	}
-}
-
 // 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

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

@@ -26,11 +26,11 @@ func infoPhase(name string) string {
 // 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 (count the records,
+// own on stderr: open (open the database) and count (read the number of
-// with one query). Each display ends before the next phase starts, and
+// records and their total size from the totals table). Each display
-// before an error is returned to be printed. The details are written
+// ends before the next phase starts, and before an error is returned
-// once the last display has ended, so no display is drawn while they
+// to be printed. The details are written once the last display has
-// are written.
+// 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 {
@@ -56,7 +56,7 @@ func runInfo(ctx context.Context, stdout io.Writer) error {
 
 	defer func() { _ = db.Close() }()
 
-	// One query counts everything, so the phase never has a total.
+	// One row holds both counts, so the phase never has a total.
 	prog = newProgress(progressParams{
 		label: infoPhase("count"), total: -1,
 		waitingFor: countingRecords,
@@ -113,9 +113,6 @@ func writeInfo(stdout io.Writer, dbPath, source string,
 		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, "records with head and tail hashes\t%d\n",
-		counts.headTail)
-	fmt.Fprintf(&b, "records with content hash\t%d\n", counts.content)
 	fmt.Fprintf(&b, "size of recorded files\t%d (%s)\n",
 		counts.size, humanBytes(counts.size))
 

info_test.go

@@ -12,23 +12,25 @@ import (
 // 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, " +
-	"eta unknown"
+	"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, " +
-	"eta unknown"
+	"remain unknown"
 
-// infoRecs are four records: a duplicate pair with every hash, a file
+// infoRecs are four records: a duplicate pair, a file of 20 MiB and
-// of 20 MiB with head and tail hashes but no content hash yet, and a
+// another small file.
-// file never hashed.
 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: "t", content: "c", path: "/d/a"},
+		{size: 5, head: h, tail: tl, content: c, path: "/d/a"},
-		{size: 5, head: "h", tail: "t", content: "c", path: "/d/b"},
+		{size: 5, head: h, tail: tl, content: c, path: "/d/b"},
-		{size: 20 << 20, head: "bh", tail: "bt", path: "/d/big"},
+		{size: 20 << 20, head: bigH, tail: bigT, content: bigC, path: "/d/big"},
-		{size: 7, path: "/d/unique"},
+		{size: 7, head: u, tail: u, content: u, path: "/d/unique"},
 	}
 }
 
@@ -45,16 +47,12 @@ func TestRunInfo(t *testing.T) {
 		"empty": {
 			want: "schema version\t1\n" +
 				"records\t0\n" +
-				"records with head and tail hashes\t0\n" +
-				"records with content hash\t0\n" +
 				"size of recorded files\t0 (0 B)\n",
 		},
 		"filled": {
 			recs: infoRecs(),
 			want: "schema version\t1\n" +
 				"records\t4\n" +
-				"records with head and tail hashes\t3\n" +
-				"records with content hash\t2\n" +
 				"size of recorded files\t20971537 (20.0 MiB)\n",
 		},
 	}

main.go

@@ -1,14 +1,12 @@
 // 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 other subcommands read.
 //
 // Usage:
 //
@@ -28,6 +26,7 @@ import (
 	"io"
 	"os"
 	"runtime"
+	"runtime/debug"
 
 	"github.com/spf13/cobra"
 )
@@ -58,10 +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 |
@@ -116,7 +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)
 		}
@@ -212,7 +236,7 @@ func newScanCommand() *cobra.Command {
 		}),
 	}
 	scanCmd.Flags().IntVar(&scanWorkers, "workers", runtime.NumCPU(),
-		"concurrent workers for the walk, hash, and content phases")
+		"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",

main_test.go

@@ -9,6 +9,7 @@ import (
 	"io/fs"
 	"os"
 	"path/filepath"
+	"runtime/debug"
 	"slices"
 	"strconv"
 	"strings"
@@ -179,9 +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()
 
@@ -264,8 +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())
 			}
@@ -714,6 +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
 
@@ -722,7 +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)
 		}
@@ -733,6 +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()
 
@@ -780,6 +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 {
@@ -891,24 +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,
 ) {
@@ -937,6 +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)
@@ -991,8 +1158,9 @@ 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)
 	}
@@ -1026,9 +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 {
@@ -1063,8 +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)
 	}

progress.go

@@ -9,6 +9,7 @@ import (
 	"strings"
 	"sync"
 	"time"
+	"unicode/utf8"
 
 	"github.com/schollz/progressbar/v3"
 	"golang.org/x/term"
@@ -34,10 +35,17 @@ const stallTime = 10 * time.Second
 // spinnerType selects the progressbar library's spinner style.
 const spinnerType = 14
 
-// barWidth is the width of the progressbar library's bar between its
+// barWidth is the width of a phase's bar between its two ends, as in
-// two ends, as in the example line in README "Progress".
+// 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
 
@@ -45,19 +53,14 @@ const percentScale = 100
 // read, as the progressbar library takes it.
 const fallbackWidth = 80
 
-// spinnerMargin is the columns of a spinner's line besides its text:
+// spinnerMargin is the columns of a line besides its text: the spinner
-// the spinner and the three spaces the library draws around the text,
+// and the three spaces the library draws around the text, and the
-// and the terminal's last column, which every line stays clear of so
+// terminal's last column, which every line stays clear of so that no
-// that no terminal wraps it.
+// terminal wraps it.
 const spinnerMargin = 5
 
-// barMargin is the columns of a bar's line besides its text: the
-// percent and the bar the library draws after the text, the spaces
-// around them, and the terminal's last column.
-const barMargin = barWidth + 11
-
 // countingRecords is what the display of a phase that reads the records
-// says while it counts them, before it has its total.
+// 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
@@ -85,7 +88,7 @@ func terminalWidth() int {
 	return width
 }
 
-// phaseLabel names phase with its place among phases, as "[2/5] walk".
+// 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)
@@ -109,13 +112,13 @@ type drawnCount struct {
 }
 
 // progress renders one phase's progress on stderr. On a TTY the
-// progressbar library draws line, fitted to the terminal's width: after
+// progressbar library draws its spinner and then line, fitted to the
-// the library's spinner, or, for a phase with an exact total, before the
+// terminal's width. A phase with an exact total ends the line with its
-// library's bar when the terminal has room for the bar beside it. It is
+// percent and bar, at the terminal's right edge, when the terminal has
-// drawn again every redrawInterval, so its elapsed time keeps moving
+// room for them. It is drawn again every redrawInterval, so its elapsed
-// while the phase waits for its next item. When stderr is not a TTY it
+// time keeps moving while the phase waits for its next item. When
-// emits no ANSI redraws: it prints line as the phase starts, every
+// stderr is not a TTY it emits no ANSI redraws: it prints line as the
-// plainInterval while it runs, and as it ends.
+// 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
@@ -131,7 +134,6 @@ type progress struct {
 
 	mu         sync.Mutex
 	bar        *progressbar.ProgressBar // what the library draws; nil until then
-	withBar    bool                     // bar is the library's bar, not its spinner
 	widest     int                      // the widest line bar has drawn, in columns
 	label      string
 	unit       string
@@ -141,7 +143,7 @@ type progress struct {
 	stalledOn  string
 	count      int64
 	start      time.Time // when the phase started, for the elapsed time
-	rateStart  time.Time // when the count started, for the ETA
+	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
@@ -215,55 +217,34 @@ func (p *progress) draw() {
 	}
 
 	if p.width == nil {
-		fmt.Fprintln(os.Stderr, p.line(now, math.MaxInt, true))
+		fmt.Fprintln(os.Stderr, p.line(now, math.MaxInt, false))
 
 		return
 	}
 
 	width := p.width()
+	text := p.line(now, width-spinnerMargin, true)
 
-	// A phase with an exact total gets the library's bar when its whole
+	// Before each draw the library erases its line with as many spaces as
-	// line, without the percent the bar shows, fits beside the bar: the
+	// the widest line it has drawn. A display gets a new one when the
-	// bar gives way before any part of the line. A total of 0 leaves the
+	// terminal has been made too narrow for that erase, which would wrap
-	// bar nothing to fill.
+	// and leave a line behind at every draw.
-	text, withBar := "", false
+	if p.bar == nil || p.widest >= width {
-	if p.total > 0 && !p.estimate {
+		p.newBar(width)
-		text = p.line(now, math.MaxInt, false)
-		withBar = len(text) <= width-barMargin
-	}
-
-	margin := barMargin
-	if !withBar {
-		margin = spinnerMargin
-		text = p.line(now, width-margin, true)
-	}
-
-	// The library makes a bar or a spinner, and before each draw erases
-	// its line with as many spaces as the widest line it has drawn. A
-	// display gets a new one when it turns from one to the other, as its
-	// line grows or the terminal is resized, and 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.withBar != withBar || p.widest >= width {
-		p.newBar(withBar, width)
-	}
-
-	if withBar {
-		_ = p.bar.Set64(p.count)
 	}
 
 	p.bar.Describe(text)
 
-	// The library drew the text and its margin, less the terminal's last
+	// The library drew the spinner, the text and the spaces around it,
-	// column, which the margin keeps clear.
+	// less the terminal's last column, which spinnerMargin keeps clear. A
-	p.widest = max(p.widest, len(text)+margin-1)
+	// bar's cells take one column each but more than one byte.
+	p.widest = max(p.widest, utf8.RuneCountInString(text)+spinnerMargin-1)
 }
 
-// newBar has the library make what draw draws: a bar for the phase's
+// newBar has the library make what draw draws: its spinner, followed by
-// total when withBar is set, and a spinner when not. Either shows the
+// the text draw gives it and nothing of the library's own. p.mu must be
-// text draw gives it, and nothing of its own besides the spinner, or
+// held.
-// the bar and its percent. p.mu must be held.
+func (p *progress) newBar(width int) {
-func (p *progress) newBar(withBar bool, 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
@@ -272,29 +253,36 @@ func (p *progress) newBar(withBar bool, width int) {
 		fmt.Fprint(os.Stderr, "\r"+blank+"\r")
 	}
 
-	total := int64(-1) // the library's spinner
+	// A total of -1 gives the library's spinner.
-	if withBar {
+	p.bar = progressbar.NewOptions64(-1,
-		total = p.total
-	}
-
-	p.bar = progressbar.NewOptions64(total,
 		progressbar.OptionSetWriter(os.Stderr),
-		progressbar.OptionSetWidth(barWidth),
 		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 ETA.
+		// The text carries the elapsed time and the time remaining.
 		progressbar.OptionSetElapsedTime(false),
 		progressbar.OptionSetPredictTime(false),
 	)
-	p.withBar, p.widest = withBar, 0
+	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 ETA and the time with no item completed
+// it is known. The rate, the time remaining and the time with no item
-// count from then on: the time spent waiting for the total says nothing
+// completed count from then on: the time spent waiting for the total
-// about how fast items go.
+// says nothing about how fast items go.
 func (p *progress) setTotal(total int64) {
 	if p == nil {
 		return
@@ -438,22 +426,26 @@ func (p *progress) finish() {
 // line formats the phase's progress as of now in at most room columns,
 // as
 //
-//	[3/5] hash: [1234/5000] 25%, 300 files/s, elapsed 4s, eta 13s
+//	[3/4] hash: [1234/5000] 25%, 300 files/s, elapsed 4s, remain 13s
 //
-// where "files" is the phase's unit, without the percent when percent
+// where "files" is the phase's unit. A phase with no total shows the
-// is false, as before the library's bar, which shows its own. A phase
+// items done instead, or what it waits for. The rate is that since the
-// with no total shows the items done instead, or what it waits for. The
+// first draw in drawn, and the time remaining comes from the rate since
-// rate is that since the first draw in drawn, and the ETA comes from
+// the count started. Once no item has been completed for stallTime, the
-// the rate since the count started. Once no item has been completed for
+// rate, which would read 0, gives way to the word "stalled" and where
-// stallTime, the rate, which would read 0, gives way to the word
+// the phase waits, as "stalled disk/db".
-// "stalled" and where the phase waits, as "stalled disk/db".
 //
-// The phase and its place, the progress, the elapsed time and the ETA
+// When bar is true, as on a terminal, a phase with an exact total ends
-// are kept whole. A line wider than room leaves out the rate, the words
+// the line with its percent and bar, in place of the percent after its
-// of a stalled phase, or what the phase waits for; only if it is still
+// count. A total of 0 leaves the bar nothing to fill.
-// wider is it cut at room. Every part is ASCII, so its length is its
+//
-// width in columns. p.mu must be held.
+// The phase and its place, the progress, the elapsed time and the time
-func (p *progress) line(now time.Time, room int, percent bool) string {
+// 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
@@ -462,21 +454,41 @@ func (p *progress) line(now time.Time, room int, percent bool) string {
 
 	if p.total < 0 && p.waitingFor != "" {
 		head, extra = p.label+": ", p.waitingFor+", "
-		tail = fmt.Sprintf("elapsed %s, eta unknown", elapsed)
+		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(percent) + ", "
+		head = p.label + ": " + p.itemsDone(true) + ", "
 		extra = fmt.Sprintf("%.0f %s/s, ", rate, p.unit)
-		tail = fmt.Sprintf("elapsed %s, eta %s", elapsed, p.eta(average))
+		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 {
@@ -526,10 +538,10 @@ func (p *progress) itemsDone(percent bool) string {
 	return fmt.Sprintf("%s %.0f%%", done, pct)
 }
 
-// eta returns the time the phase has left at rate items a second, or
+// 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) eta(rate float64) string {
+func (p *progress) remain(rate float64) string {
 	switch {
 	case p.total < 0, p.estimate && p.count > p.total:
 		return "unknown"
@@ -539,8 +551,8 @@ func (p *progress) eta(rate float64) string {
 		return "unknown"
 	}
 
-	remaining := time.Duration(
+	left := time.Duration(
 		float64(p.total-p.count) / rate * float64(time.Second))
 
-	return remaining.Round(time.Second).String()
+	return left.Round(time.Second).String()
 }

progress_test.go

@@ -23,7 +23,7 @@ const testRedraw = time.Millisecond
 const testDeadline = 5 * time.Second
 
 // hashStalledOn is where the hash phase says it waits once it has
-// stalled, as readRuns gives it.
+// stalled, as hashPhase gives it.
 const hashStalledOn = "disk/db"
 
 // testClock is a clock a test moves by hand, for a display that reads
@@ -117,38 +117,38 @@ func TestProgressLine(t *testing.T) {
 			label: scanPhase("load"), total: -1,
 			waitingFor: countingRecords,
 		},
-		want: "[1/5] load: counting the records, elapsed 10s, eta unknown",
+		want: "[1/4] load: counting the records, elapsed 10s, remain unknown",
 	}, {
 		p: &progress{
 			label: scanPhase("hash"), unit: scanUnit, total: 100, count: 20,
 		},
-		want: "[3/5] hash: [20/100] 20%, 2 files/s, elapsed 10s, eta 40s",
+		want: "[3/4] hash: [20/100] 20%, 2 files/s, elapsed 10s, remain 40s",
 	}, {
 		p:    &progress{label: scanPhase("hash"), unit: scanUnit, total: 100},
-		want: "[3/5] hash: [0/100] 0%, 0 files/s, elapsed 10s, eta unknown",
+		want: "[3/4] hash: [0/100] 0%, 0 files/s, elapsed 10s, remain unknown",
 	}, {
 		p:    &progress{label: scanPhase("update"), unit: scanUnit, total: 0},
-		want: "[4/5] update: [0/0] 100%, 0 files/s, elapsed 10s, eta 0s",
+		want: "[4/4] update: [0/0] 100%, 0 files/s, elapsed 10s, remain 0s",
 	}, {
 		p: &progress{
 			label: scanPhase("walk"), unit: scanUnit, total: 100,
 			estimate: true, count: 20,
 		},
-		want: "[2/5] walk: [20/~100] 20%, 2 files/s, elapsed 10s, eta 40s",
+		want: "[2/4] walk: [20/~100] 20%, 2 files/s, elapsed 10s, remain 40s",
 	}, {
 		// Past the estimate the walk cannot tell how long it has left.
 		p: &progress{
 			label: scanPhase("walk"), unit: scanUnit, total: 100,
 			estimate: true, count: 120,
 		},
-		want: "[2/5] walk: [120/~100] 120%, 12 files/s, elapsed 10s, " +
+		want: "[2/4] walk: [120/~100] 120%, 12 files/s, elapsed 10s, " +
-			"eta unknown",
+			"remain unknown",
 	}, {
 		// A first scan's walk has no estimate.
 		p: &progress{
 			label: scanPhase("walk"), unit: scanUnit, total: -1, count: 20,
 		},
-		want: "[2/5] walk: 20 files, 2 files/s, elapsed 10s, eta unknown",
+		want: "[2/4] walk: 20 files, 2 files/s, elapsed 10s, remain unknown",
 	}, {
 		// The rate is in what the phase counts.
 		p: &progress{
@@ -156,14 +156,14 @@ func TestProgressLine(t *testing.T) {
 			count: 20,
 		},
 		want: "[3/4] group: [20/100] 20%, 2 directories/s, elapsed 10s, " +
-			"eta 40s",
+			"remain 40s",
 	}}
 
 	for _, tc := range cases {
 		tc.p.start, tc.p.rateStart, tc.p.lastItem = ago, ago, now
 		tc.p.drawn = []drawnCount{{at: ago}}
 
-		if got := tc.p.line(now, math.MaxInt, true); got != tc.want {
+		if got := tc.p.line(now, math.MaxInt, false); got != tc.want {
 			t.Errorf("line = %q, want %q", got, tc.want)
 		}
 	}
@@ -184,9 +184,9 @@ func TestLineFitsRoom(t *testing.T) {
 		start: ago, rateStart: ago, lastItem: now,
 		drawn: []drawnCount{{at: ago}},
 	}
-	content := &progress{
+	load := &progress{
-		label: scanPhase("content"), total: -1,
+		label: scanPhase("load"), total: -1,
-		waitingFor: "searching the database", start: ago, rateStart: ago,
+		waitingFor: countingRecords, start: ago, rateStart: ago,
 	}
 
 	started := now.Add(-50 * time.Second)
@@ -198,48 +198,49 @@ func TestLineFitsRoom(t *testing.T) {
 	}
 
 	cases := []struct {
-		p       *progress
+		p    *progress
-		room    int
+		room int
-		percent bool
+		bar  bool
-		want    string
+		want string
 	}{{
-		p: hash, room: 57, percent: true,
+		p: hash, room: 60,
-		want: "[3/5] hash: [20/100] 20%, 2 files/s, elapsed 10s, eta 40s",
+		want: "[3/4] hash: [20/100] 20%, 2 files/s, elapsed 10s, remain 40s",
 	}, {
-		p: hash, room: 56, percent: true,
+		p: hash, room: 59,
-		want: "[3/5] hash: [20/100] 20%, elapsed 10s, eta 40s",
+		want: "[3/4] hash: [20/100] 20%, elapsed 10s, remain 40s",
 	}, {
-		p: hash, room: 45, percent: true,
+		p: hash, room: 48,
-		want: "[3/5] hash: [20/100] 20%, elapsed 10s, eta 40",
+		want: "[3/4] hash: [20/100] 20%, elapsed 10s, remain 40",
 	}, {
-		// Before the library's bar, which shows the percent.
+		// The bar shows the percent.
-		p: hash, room: 57, percent: false,
+		p: hash, room: 74, bar: true,
-		want: "[3/5] hash: [20/100], 2 files/s, elapsed 10s, eta 40s",
+		want: "[3/4] hash: [20/100], 2 files/s, elapsed 10s, remain 40s" +
+			"  20% |██        |",
 	}, {
-		p: content, room: 40, percent: true,
+		p: load, room: 43,
-		want: "[5/5] content: elapsed 10s, eta unknown",
+		want: "[1/4] load: elapsed 10s, remain unknown",
 	}, {
-		p: stalled, room: 65, percent: true,
+		p: stalled, room: 68,
-		want: "[3/5] hash: [20/100] 20%, stalled disk/db, elapsed 50s, " +
+		want: "[3/4] hash: [20/100] 20%, stalled disk/db, elapsed 50s, " +
-			"eta 3m20s",
+			"remain 3m20s",
 	}, {
-		p: stalled, room: 64, percent: true,
+		p: stalled, room: 67,
-		want: "[3/5] hash: [20/100] 20%, elapsed 50s, eta 3m20s",
+		want: "[3/4] hash: [20/100] 20%, elapsed 50s, remain 3m20s",
 	}}
 
 	for _, tc := range cases {
-		if got := tc.p.line(now, tc.room, tc.percent); got != tc.want {
+		if got := tc.p.line(now, tc.room, tc.bar); got != tc.want {
-			t.Errorf("line(%d, %t) = %q, want %q",
+			t.Errorf("line(%d, %t) = %q, want %q", tc.room, tc.bar, got,
-				tc.room, tc.percent, got, tc.want)
+				tc.want)
 		}
 	}
 }
 
 // TestSetTotalStartsRate checks that setTotal starts a phase's rate,
-// its ETA and its time with no record read from when the total becomes
+// its time remaining and its time with no record read from when the
-// known, not from when the phase started waiting for it: after 20
+// total becomes known, not from when the phase started waiting for it:
-// seconds of waiting for the total, the phase has not stalled 5 seconds
+// after 20 seconds of waiting for the total, the phase has not stalled 5
-// after it, and has 10 seconds after it with no record read.
+// seconds after it, and has 10 seconds after it with no record read.
 func TestSetTotalStartsRate(t *testing.T) {
 	t.Parallel()
 
@@ -255,15 +256,15 @@ func TestSetTotalStartsRate(t *testing.T) {
 
 	clock.Add(5 * time.Second)
 
-	want := "[1/5] load: [0/100] 0%, 0 files/s, elapsed 25s, eta unknown"
+	want := "[1/4] load: [0/100] 0%, 0 files/s, elapsed 25s, remain unknown"
-	if got := p.line(clock.Now(), math.MaxInt, true); got != want {
+	if got := p.line(clock.Now(), math.MaxInt, false); got != want {
 		t.Errorf("line = %q, want %q", got, want)
 	}
 
 	clock.Add(5 * time.Second)
 
-	want = "[1/5] load: [0/100] 0%, stalled db, elapsed 30s, eta unknown"
+	want = "[1/4] load: [0/100] 0%, stalled db, elapsed 30s, remain unknown"
-	if got := p.line(clock.Now(), math.MaxInt, true); got != want {
+	if got := p.line(clock.Now(), math.MaxInt, false); got != want {
 		t.Errorf("line = %q, want %q", got, want)
 	}
 
@@ -272,8 +273,8 @@ func TestSetTotalStartsRate(t *testing.T) {
 		p.increment()
 	}
 
-	want = "[1/5] load: [20/100] 20%, 2 files/s, elapsed 30s, eta 40s"
+	want = "[1/4] load: [20/100] 20%, 2 files/s, elapsed 30s, remain 40s"
-	if got := p.line(clock.Now(), math.MaxInt, true); got != want {
+	if got := p.line(clock.Now(), math.MaxInt, false); got != want {
 		t.Errorf("line = %q, want %q", got, want)
 	}
 }
@@ -316,9 +317,9 @@ func TestPlainProgressPrintsAtStartAndEnd(t *testing.T) {
 
 	lines := strings.Split(strings.TrimSuffix(stderr(), "\n"), "\n")
 
-	want := "[3/5] hash: [0/1000] 0%, 0 files/s, elapsed 0s, eta unknown"
+	want := "[3/4] hash: [0/1000] 0%, 0 files/s, elapsed 0s, remain unknown"
 	if len(lines) != 2 || lines[0] != want ||
-		!strings.HasPrefix(lines[1], "[3/5] hash: [1000/1000] 100%, ") {
+		!strings.HasPrefix(lines[1], "[3/4] hash: [1000/1000] 100%, ") {
 		t.Errorf("stderr lines = %q, want %q, then the line at 1000",
 			lines, want)
 	}
@@ -336,7 +337,7 @@ func TestPlainProgressPrintsWhileWaiting(t *testing.T) {
 	}, nil, testRedraw, time.Now)
 
 	awaitOutput(t, stderr,
-		"[1/5] load: counting the records, elapsed 0s, eta unknown\n", 3)
+		"[1/4] load: counting the records, elapsed 0s, remain unknown\n", 3)
 	p.finish()
 }
 
@@ -366,23 +367,23 @@ func TestPlainProgressStalledProducer(t *testing.T) {
 
 	clock.Add(5 * time.Second)
 	awaitOutput(t, stderr,
-		"[3/5] hash: [20/100] 20%, 4 files/s, elapsed 5s, eta 20s\n", 3)
+		"[3/4] hash: [20/100] 20%, 4 files/s, elapsed 5s, remain 20s\n", 3)
 
 	clock.Add(time.Second)
 	awaitOutput(t, stderr,
-		"[3/5] hash: [20/100] 20%, 0 files/s, elapsed 6s, eta 24s\n", 3)
+		"[3/4] hash: [20/100] 20%, 0 files/s, elapsed 6s, remain 24s\n", 3)
 
 	clock.Add(4 * time.Second)
 	awaitOutput(t, stderr,
-		"[3/5] hash: [20/100] 20%, stalled disk/db, elapsed 10s, eta 40s\n",
+		"[3/4] hash: [20/100] 20%, stalled disk/db, elapsed 10s, remain 40s\n",
 		3)
 }
 
 // TestPlainProgressRateAfterStall draws a phase's plain line by hand, a
 // little over plainInterval after the line before, as a late tick
 // does, through a stall and a burst of files after it: the rate covers
-// the files read since the line before, while the ETA comes from the
+// the files read since the line before, while the time remaining comes
-// phase's average.
+// from the phase's average.
 //
 //nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
 func TestPlainProgressRateAfterStall(t *testing.T) {
@@ -410,10 +411,10 @@ func TestPlainProgressRateAfterStall(t *testing.T) {
 	p.finish()
 
 	want := []string{
-		"[3/5] hash: [0/1000] 0%, 0 files/s, elapsed 0s, eta unknown",
+		"[3/4] hash: [0/1000] 0%, 0 files/s, elapsed 0s, remain unknown",
-		"[3/5] hash: [0/1000] 0%, 0 files/s, elapsed 5s, eta unknown",
+		"[3/4] hash: [0/1000] 0%, 0 files/s, elapsed 5s, remain unknown",
-		"[3/5] hash: [0/1000] 0%, stalled disk/db, elapsed 10s, eta unknown",
+		"[3/4] hash: [0/1000] 0%, stalled disk/db, elapsed 10s, remain unknown",
-		"[3/5] hash: [100/1000] 10%, 20 files/s, elapsed 15s, eta 2m15s",
+		"[3/4] hash: [100/1000] 10%, 20 files/s, elapsed 15s, remain 2m15s",
 	}
 
 	lines := strings.Split(strings.TrimSuffix(stderr(), "\n"), "\n")
@@ -426,8 +427,8 @@ func TestPlainProgressRateAfterStall(t *testing.T) {
 // redrawInterval, as a terminal does, through a stall of stallTime and
 // a burst of files after it: the rate covers the files read over the
 // last rateWindow, and falls to 0 once the burst is older than that,
-// while the ETA comes from the phase's average. Plain lines show each
+// while the time remaining comes from the phase's average. Plain lines
-// draw.
+// show each draw.
 //
 //nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
 func TestProgressRateAfterStallRedrawn(t *testing.T) {
@@ -457,8 +458,8 @@ func TestProgressRateAfterStallRedrawn(t *testing.T) {
 	redraw(rateWindow + redrawInterval)
 	p.finish()
 
-	want := "[3/5] hash: [50/1000] 5%, 10 files/s, elapsed 15s, eta 4m45s\n" +
+	want := "[3/4] hash: [50/1000] 5%, 10 files/s, elapsed 15s, remain 4m45s\n" +
-		"[3/5] hash: [50/1000] 5%, 0 files/s, elapsed 15s, eta 4m47s\n"
+		"[3/4] hash: [50/1000] 5%, 0 files/s, elapsed 15s, remain 4m47s\n"
 	if !strings.Contains(stderr(), want) {
 		t.Errorf("stderr = %q, want the lines %q", stderr(), want)
 	}
@@ -480,10 +481,10 @@ func lastFrame(out string) string {
 }
 
 // TestTerminalRedrawsWhileWaiting checks that the terminal display of a
-// phase, spinner or bar, keeps being drawn while the phase waits for its
+// phase, with a bar or without, keeps being drawn while the phase waits
-// next item, with the elapsed time as of now, and shows every item
+// for its next item, with the elapsed time as of now, and shows every
-// completed before the wait. stderr is not a terminal here, so the
+// item completed before the wait. The terminal is 120 columns wide, so
-// displays take it to be fallbackWidth wide.
+// the hash phase's display has room for its bar.
 //
 //nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
 func TestTerminalRedrawsWhileWaiting(t *testing.T) {
@@ -506,7 +507,8 @@ func TestTerminalRedrawsWhileWaiting(t *testing.T) {
 	for _, tc := range cases {
 		before := len(stderr())
 		since := func() string { return stderr()[before:] }
-		p := startProgress(tc.params, terminalWidth, testRedraw, time.Now)
+		p := startProgress(tc.params, func() int { return 120 }, testRedraw,
+			time.Now)
 
 		for range 50 {
 			p.increment()
@@ -552,13 +554,13 @@ func drawLate(stderr func() string, params progressParams, width int,
 	return stderr()[before:]
 }
 
-// TestTerminalLinesKeepETA checks the line each display shows on an
+// TestTerminalLinesKeepTimeRemaining checks the line each display shows
-// 80-column terminal at a large scan's counts and times, and the line
+// on an 80-column terminal at a large scan's counts and times, and the
-// of trees' read phase at the same counts: the rate is left out, so
+// line of trees' read phase at the same counts: the rate is left out,
-// that the elapsed time and the ETA stay whole.
+// so that the elapsed time and the time remaining stay whole.
 //
 //nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
-func TestTerminalLinesKeepETA(t *testing.T) {
+func TestTerminalLinesKeepTimeRemaining(t *testing.T) {
 	stderr := captureStderr(t)
 
 	cases := []struct {
@@ -570,26 +572,20 @@ func TestTerminalLinesKeepETA(t *testing.T) {
 			label: scanPhase("walk"), unit: scanUnit, total: 1200000,
 			estimate: true,
 		},
-		want: "[2/5] walk: [1234567/~1200000] 103%, elapsed 2h30m0s, " +
+		want: "[2/4] walk: [1234567/~1200000] 103%, elapsed 2h30m0s, " +
-			"eta unknown",
+			"remain unknown",
 	}, {
 		params: progressParams{
 			label: scanPhase("hash"), unit: scanUnit, total: 9876543,
 		},
-		want: "[3/5] hash: [1234567/9876543] 12%, elapsed 2h30m0s, " +
+		want: "[3/4] hash: [1234567/9876543] 12%, elapsed 2h30m0s, " +
-			"eta 17h30m0s",
+			"remain 17h30m0s",
-	}, {
-		params: progressParams{
-			label: scanPhase("content"), unit: scanUnit, total: 9876543,
-		},
-		want: "[5/5] content: [1234567/9876543] 12%, elapsed 2h30m0s, " +
-			"eta 17h30m0s",
 	}, {
 		params: progressParams{
 			label: treesPhase("read"), unit: "records", total: 9876543,
 		},
 		want: "[2/4] read: [1234567/9876543] 12%, elapsed 2h30m0s, " +
-			"eta 17h30m0s",
+			"remain 17h30m0s",
 	}}
 
 	for _, tc := range cases {
@@ -600,30 +596,32 @@ func TestTerminalLinesKeepETA(t *testing.T) {
 	}
 }
 
-// TestTerminalStalledLines draws every phase's line on an 80-column
+// TestTerminalStalledLines draws every phase's line once the phase has
-// terminal once the phase has stalled, its last item done 42 seconds
+// stalled, its last item done 42 seconds before. At an ordinary scan's
-// before. At an ordinary scan's counts and times, 12345 of 45678 items
+// counts and times, 12345 of 45678 items done four and a half minutes
-// done four and a half minutes in, the line shows where the phase waits
+// in, on a terminal 100 columns wide, the line shows where the phase
-// whole, beside the phase, progress, elapsed time and ETA. At a large
+// waits whole, beside the phase, progress, elapsed time and time
-// scan's, 1234567 of 9876543 two and a half hours in, those four still
+// remaining. At a large scan's, 1234567 of 9876543 two and a half hours
-// show whole, as the words give way first where they do not fit.
+// in, on an 80-column terminal, those four still show whole, as the
+// words give way first where they do not fit.
 //
 //nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
 func TestTerminalStalledLines(t *testing.T) {
 	stderr := captureStderr(t)
 
-	// drawStalled draws the display params describes as it starts and
+	// drawStalled draws the display params describes on a terminal width
-	// once more as it ends, with count of total items done elapsed into
+	// columns wide as it starts and once more as it ends, with count of
-	// the phase, and returns what the terminal shows.
+	// total items done elapsed into the phase, and returns what the
-	drawStalled := func(params progressParams, total, count int64,
+	// terminal shows.
-		elapsed time.Duration,
+	drawStalled := func(params progressParams, width int, total,
+		count int64, elapsed time.Duration,
 	) string {
 		before := len(stderr())
 		clock := &testClock{now: time.Now()}
 		params.total = total
 
 		// No timed draws come between the two.
-		p := startProgress(params, func() int { return 80 }, time.Hour,
+		p := startProgress(params, func() int { return width }, time.Hour,
 			clock.Now)
 
 		clock.Add(elapsed - 42*time.Second)
@@ -643,9 +641,6 @@ func TestTerminalStalledLines(t *testing.T) {
 		{label: scanPhase("walk"), estimate: true, stalledOn: "disk"},
 		{label: scanPhase("hash"), stalledOn: hashStalledOn},
 		{label: scanPhase("update"), stalledOn: "db"},
-		// The content phase's checks and reads, then its last write.
-		{label: scanPhase("content"), stalledOn: "disk/db"},
-		{label: scanPhase("content"), stalledOn: "db"},
 		{label: treesPhase("read"), stalledOn: "db"},
 		{label: treesPhase("group"), stalledOn: "cpu"},
 		{label: treesPhase("write"), stalledOn: "out"},
@@ -658,19 +653,22 @@ func TestTerminalStalledLines(t *testing.T) {
 			approx = "~"
 		}
 
-		shown := drawStalled(params, 45678, 12345,
+		// The percent is in the line, or beside the bar.
+		shown := drawStalled(params, 100, 45678, 12345,
 			4*time.Minute+30*time.Second)
-		want := params.label + ": [12345/" + approx + "45678] 27%, stalled " +
+		for _, want := range []string{
-			params.stalledOn + ", elapsed 4m30s, eta 12m9s"
+			params.label + ": [12345/" + approx + "45678]",
-
+			", stalled " + params.stalledOn + ", elapsed 4m30s, remain 12m9s",
-		if !strings.Contains(shown, want) {
+		} {
-			t.Errorf("terminal shows %q, want %q", shown, want)
+			if !strings.Contains(shown, want) {
+				t.Errorf("terminal shows %q, want %q", shown, want)
+			}
 		}
 
-		shown = drawStalled(params, 9876543, 1234567, 150*time.Minute)
+		shown = drawStalled(params, 80, 9876543, 1234567, 150*time.Minute)
 		for _, want := range []string{
 			params.label + ": [1234567/" + approx + "9876543] 12%, ",
-			", elapsed 2h30m0s, eta 17h30m0s",
+			", elapsed 2h30m0s, remain 17h30m0s",
 		} {
 			if !strings.Contains(shown, want) {
 				t.Errorf("terminal shows %q, want %q", shown, want)
@@ -693,7 +691,7 @@ func TestTerminalLinesFitWidth(t *testing.T) {
 	for _, width := range []int{120, 100, 80, 72, 60, 50, 40} {
 		for _, total := range []int64{9876543, 20000} {
 			params := progressParams{
-				label: scanPhase("content"), unit: scanUnit, total: total,
+				label: scanPhase("update"), unit: scanUnit, total: total,
 			}
 			out := drawLate(stderr, params, width, total/8)
 
@@ -715,13 +713,164 @@ func TestTerminalLinesFitWidth(t *testing.T) {
 	}
 }
 
+// TestTerminalLinesStartWithSpinner draws a display with no total and
+// one with a bar, two and a half hours into the phase, on a terminal 120
+// columns wide. Each line must start with the library's spinner in the
+// first column, then a space and the phase's label.
+//
+//nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
+func TestTerminalLinesStartWithSpinner(t *testing.T) {
+	stderr := captureStderr(t)
+
+	for _, params := range []progressParams{
+		{label: scanPhase("walk"), unit: scanUnit, total: -1},
+		{label: scanPhase("hash"), unit: scanUnit, total: 9876543},
+	} {
+		shown := lastFrame(drawLate(stderr, params, 120, 1234567))
+		spinner, rest, _ := strings.Cut(shown, " ")
+
+		if utf8.RuneCountInString(spinner) != 1 ||
+			!strings.HasPrefix(rest, params.label+": ") {
+			t.Errorf("terminal shows %q, want the spinner, a space and %q",
+				shown, params.label)
+		}
+
+		if params.total > 0 && !strings.Contains(shown, "% |") {
+			t.Errorf("terminal shows %q, want a bar", shown)
+		}
+	}
+}
+
+// TestTerminalBarStaysAtRightEdge draws the hash phase's display two
+// and a half hours in, at two counts whose lines differ in length, on
+// terminals 110 and 120 columns wide. The bar is partly filled at the
+// first count and full at the second. It must start the same number of
+// columns from the terminal's right edge each time, and end the same
+// number of columns from it: a line that grows or shrinks, as its time
+// remaining does, never moves the bar, and nor do the bar's filled
+// cells.
+//
+//nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
+func TestTerminalBarStaysAtRightEdge(t *testing.T) {
+	stderr := captureStderr(t)
+	params := progressParams{
+		label: scanPhase("hash"), unit: scanUnit, total: 9876543,
+	}
+
+	widths := []int{110, 120}
+	counts := []int64{1234567, 9876543}
+	startFromEdge := make([]int, 0, len(widths)*len(counts))
+	endFromEdge := make([]int, 0, len(widths)*len(counts))
+
+	for _, width := range widths {
+		for _, count := range counts {
+			shown := lastFrame(drawLate(stderr, params, width, count))
+
+			beforeBar, _, found := strings.Cut(shown, "% |")
+			if !found {
+				t.Fatalf("terminal %d wide shows %q, want a bar", width, shown)
+			}
+
+			// The bar ends with the last "|".
+			throughBar := shown[:strings.LastIndex(shown, "|")+1]
+
+			startFromEdge = append(startFromEdge,
+				width-utf8.RuneCountInString(beforeBar))
+			endFromEdge = append(endFromEdge,
+				width-utf8.RuneCountInString(throughBar))
+		}
+	}
+
+	if slices.Min(startFromEdge) != slices.Max(startFromEdge) {
+		t.Errorf("bar starts %v columns from the right edge, want the same "+
+			"every time", startFromEdge)
+	}
+
+	if slices.Min(endFromEdge) != slices.Max(endFromEdge) {
+		t.Errorf("bar ends %v columns from the right edge, want the same "+
+			"every time", endFromEdge)
+	}
+}
+
+// TestTerminalRateGivesWayBeforeBar draws the hash phase's display two
+// and a half hours in. On a terminal 90 columns wide the line fits
+// beside the bar without its rate, but not with it: the bar is drawn
+// and the rate is not. On a terminal 85 columns wide the line does not
+// fit beside the bar even without its rate: neither is drawn, though
+// the rate would fit where the bar was.
+//
+//nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
+func TestTerminalRateGivesWayBeforeBar(t *testing.T) {
+	stderr := captureStderr(t)
+	params := progressParams{
+		label: scanPhase("hash"), unit: scanUnit, total: 9876543,
+	}
+
+	shown := lastFrame(drawLate(stderr, params, 90, 1234567))
+	if !strings.Contains(shown, "% |") || strings.Contains(shown, "files/s") {
+		t.Errorf("terminal 90 wide shows %q, want the bar and no rate", shown)
+	}
+
+	shown = lastFrame(drawLate(stderr, params, 85, 1234567))
+	if strings.Contains(shown, "% |") || strings.Contains(shown, "files/s") {
+		t.Errorf("terminal 85 wide shows %q, want neither bar nor rate", shown)
+	}
+}
+
+// TestTerminalSpinnerTurnsBesideBar draws the hash phase's display, its
+// bar partly filled, several times on a terminal 120 columns wide. The
+// spinner must turn at every draw. A filled cell of the bar takes one
+// column but three bytes. A line measured in bytes would seem too wide
+// for the terminal, and every draw would start the display over, its
+// spinner included.
+//
+//nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
+func TestTerminalSpinnerTurnsBesideBar(t *testing.T) {
+	stderr := captureStderr(t)
+	params := progressParams{
+		label: scanPhase("hash"), unit: scanUnit, total: 9876543,
+	}
+
+	// No timed draws: the test draws.
+	p := startProgress(params, func() int { return 120 }, time.Hour,
+		time.Now)
+
+	p.mu.Lock()
+	p.count = 1234567
+	p.mu.Unlock()
+
+	const draws = 4
+
+	spinners := make([]string, 0, draws)
+
+	for range draws {
+		before := len(stderr())
+
+		p.draw()
+
+		spinner, _, _ := strings.Cut(lastFrame(stderr()[before:]), " ")
+		spinners = append(spinners, spinner)
+	}
+
+	p.finish()
+
+	for i := 1; i < len(spinners); i++ {
+		if spinners[i] == spinners[i-1] {
+			t.Errorf("spinners at successive draws are %q, want each to "+
+				"differ from the one before", spinners)
+
+			break
+		}
+	}
+}
+
 // TestTerminalNarrowedRedrawsInPlace draws a large scan's display, two
 // and a half hours into the phase, on a terminal 120 columns wide, then
 // makes the terminal narrower than that line and draws it again a few
 // times. Nothing written after that, the erase before each redraw
 // included, may reach the narrower terminal's last column: it would
-// wrap, and every redraw would leave a line behind. At these widths the
+// wrap, and every redraw would leave a line behind. At the narrower
-// spinner stays a spinner and the bar gives way to the spinner.
+// width the hash phase's bar gives way.
 //
 //nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
 func TestTerminalNarrowedRedrawsInPlace(t *testing.T) {
@@ -739,7 +888,7 @@ func TestTerminalNarrowedRedrawsInPlace(t *testing.T) {
 			progressParams{
 				label: scanPhase("hash"), unit: scanUnit, total: 9876543,
 			},
-			90,
+			80,
 		},
 	}
 
@@ -779,10 +928,10 @@ func TestTerminalNarrowedRedrawsInPlace(t *testing.T) {
 	}
 }
 
-// TestProgressWarningsOnOwnLines drives the terminal displays, spinner
+// TestProgressWarningsOnOwnLines drives the terminal displays, with a
-// and bar, through a run of warnings with no items between them, as when
+// bar and without, through a run of warnings with no items between
-// the walk meets many unreadable paths, for many redraws: every warning
+// them, as when the walk meets many unreadable paths, for many redraws:
-// must land on a line of its own, never inside a redraw.
+// every warning must land on a line of its own, never inside a redraw.
 //
 //nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
 func TestProgressWarningsOnOwnLines(t *testing.T) {
@@ -828,11 +977,12 @@ func TestProgressWarningsOnOwnLines(t *testing.T) {
 	}
 }
 
-// TestProgressWriterRowsOnOwnLines drives the terminal displays,
+// TestProgressWriterRowsOnOwnLines drives the terminal displays, with a
-// spinner and bar, through a run of rows written through the display's
+// bar and without, through a run of rows written through the display's
 // writer to the same terminal, as stdout is in a plain "sfdupes trees",
 // each written out at once, for many redraws: the terminal must show
-// every row whole, in order, on a line of its own.
+// every row whole, in order, on a line of its own. The terminal is 120
+// columns wide, so the write phase's display has room for its bar.
 //
 //nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
 func TestProgressWriterRowsOnOwnLines(t *testing.T) {
@@ -849,7 +999,8 @@ func TestProgressWriterRowsOnOwnLines(t *testing.T) {
 	var want []string
 
 	for _, params := range cases {
-		p := startProgress(params, terminalWidth, testRedraw, time.Now)
+		p := startProgress(params, func() int { return 120 }, testRedraw,
+			time.Now)
 		out := p.writer(os.Stderr)
 
 		// No pause between rows: one is garbled only if a redraw lands

report.go

@@ -2,6 +2,7 @@ package main
 
 import (
 	"context"
+	"crypto/sha256"
 	"database/sql"
 	"fmt"
 	"io"
@@ -20,14 +21,16 @@ 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
@@ -44,11 +47,11 @@ func reportPhase(name string) string {
 // 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 (count the records,
+// own on stderr: open (open the database) and read (read the number of
-// then read them in signature order, writing each size's duplicate
+// records from the totals table, then read the records in signature
-// groups to stdout once that size is read; see readReport). Each
+// order, writing each size's duplicate groups to stdout once that size
-// display ends before the next phase starts, and before an error is
+// is read; see readReport). Each display ends before the next phase
-// returned to be printed.
+// 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 {
@@ -169,12 +172,6 @@ type reportWriter struct {
 func (w *reportWriter) add(r scanRec) error {
 	w.records++
 
-	// A record without a content hash has unknown content (README
-	// "Database"), so it is never a duplicate.
-	if r.content == "" {
-		return nil
-	}
-
 	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)

report_test.go

@@ -2,6 +2,7 @@ package main
 
 import (
 	"bytes"
+	"crypto/sha256"
 	"database/sql"
 	"errors"
 	"fmt"
@@ -18,14 +19,27 @@ 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"},
 	}
 }
 
@@ -143,8 +157,8 @@ func TestReportStdoutFailsWhileReading(t *testing.T) {
 	recs := make([]scanRec, 2*ioBufSize/len(dir))
 	for i := range recs {
 		recs[i] = scanRec{
-			size: int64(i/2) + 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),
 		}
 	}
 
@@ -173,7 +187,7 @@ func TestReportStdoutFailsWhileReading(t *testing.T) {
 // 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, " +
-	"eta unknown"
+	"remain unknown"
 
 // smokeReport is report's stdout for the smoke-test records.
 const smokeReport = "first\tdupe\tsize\n" +
@@ -211,7 +225,7 @@ func TestRunReportProgressNamesEachPhase(t *testing.T) {
 		"report: database " + path + " (from " + databaseEnv + ")",
 		reportOpenLine,
 		reportOpenLine,
-		"[2/2] read: counting the records, elapsed 0s, eta unknown",
+		"[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",
@@ -277,13 +291,14 @@ func TestReadReportOnTerminal(t *testing.T) {
 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)
@@ -386,16 +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)
@@ -419,16 +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)
@@ -447,14 +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",
 		},
 	}
 
@@ -469,11 +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)
@@ -495,15 +512,16 @@ func TestDupeGroupsOrderedByFirstPath(t *testing.T) {
 	// /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/2"},
-		{size: 50, head: "a", tail: "a", content: "a", path: "/k/1"},
+		{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/1"},
-		{size: 50, head: "b", tail: "b", content: "b", path: "/z/2"},
+		{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/2"},
-		{size: 50, head: "c", tail: "c", content: "c", path: "/a/1"},
+		{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: "/0/2"},
-		{size: 7, head: "d", tail: "d", content: "d", path: "/0/1"},
+		{size: 7, head: d, tail: d, content: d, path: "/0/1"},
 	}
 
 	groups := dupeGroupsOf(t, recs)
@@ -522,11 +540,12 @@ func TestDupeGroupsOrderedByFirstPath(t *testing.T) {
 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

@@ -22,6 +22,10 @@ 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,
@@ -40,11 +44,11 @@ func treesPhase(name string) string {
 // 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 (count the records,
+// own on stderr: open (open the database), read (read the number of
-// then read them into the hierarchy), group (group the directories by
+// records from the totals table, then read the records into the
-// digest) and write (write the groups to stdout). Each display ends
+// hierarchy), group (group the directories by digest) and write (write
-// before the next phase starts, and before an error is returned to be
+// the groups to stdout). Each display ends before the next phase
-// printed.
+// 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 {
@@ -139,15 +143,16 @@ func readTree(ctx context.Context, db *sql.DB,
 
 // 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. stdout may be the terminal
+// group on prog once its rows are written. The disk_size column is the
-// prog is drawn on, so the lines go through prog's writer. It returns
+// dupe's own. stdout may be the terminal prog is drawn on, so the lines
-// the number of rows (dupe trees) and the bytes they could reclaim.
+// 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 0, 0, fmt.Errorf("write stdout: %w", err)
 	}
@@ -159,9 +164,9 @@ func writeTreeGroups(stdout io.Writer, dupes [][]*treeNode,
 	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 0, 0, fmt.Errorf("write stdout: %w", err)
 			}
@@ -232,6 +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
@@ -270,6 +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)
 	}
 }
@@ -286,18 +293,9 @@ 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, counting each one on
@@ -347,7 +345,8 @@ func collectTreeGroups(allDirs []*treeNode, super *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

@@ -10,32 +10,31 @@ import (
 	"time"
 )
 
-// Signature hashes shared by the smoke-test records.
-const (
-	f1Head    = "f1h"
-	f1Tail    = "f1t"
-	f1Content = "f1c"
-	f2Head    = "f2h"
-	f2Tail    = "f2t"
-	f2Content = "f2c"
-)
-
 // treesOpenLine is the plain line of trees' open phase when it opens
 // the database at once; it prints it as the phase starts and as it ends.
 const treesOpenLine = "[1/4] open: opening the database, elapsed 0s, " +
-	"eta unknown"
+	"remain unknown"
 
 // 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"},
 	}
 }
 
@@ -153,13 +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,
 			})
 		}
 	}
@@ -204,13 +204,33 @@ 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
@@ -232,7 +252,8 @@ func TestRunTreesProgressNamesEachPhase(t *testing.T) {
 			code, exitOK, stderr())
 	}
 
-	report := "first\tdupe\tfiles\tsize\n/d/t1\t/d/t2\t2\t3100\n"
+	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)
 	}
@@ -242,11 +263,11 @@ func TestRunTreesProgressNamesEachPhase(t *testing.T) {
 		"trees: database " + path + " (from " + databaseEnv + ")",
 		treesOpenLine,
 		treesOpenLine,
-		"[2/4] read: counting the records, elapsed 0s, eta unknown",
+		"[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, eta unknown",
+		"[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, eta unknown",
+		"[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, ",
 	}
@@ -297,7 +318,9 @@ func TestWriteTreeGroupsOnTerminal(t *testing.T) {
 		shown = append(shown, line[strings.LastIndex(line, "\r")+1:])
 	}
 
-	want := []string{"first\tdupe\tfiles\tsize", "/d/t1\t/d/t2\t2\t3100"}
+	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)
 	}
@@ -332,11 +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)
@@ -397,9 +419,10 @@ 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)
@@ -418,10 +441,11 @@ 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)