Add the entries that landed on next to TODO.md

Catches `TODO.md` up with `next`. The `README.md` entry takes the text
that landed, word for word. The entry of this rewrite takes the date
2026-11-02. The entries of #146
and #147 are added in their
place, newest first, in short sentences, with every fact, date and link
kept. Nothing else changes.

Model: fable-5-1

Makefile

@@ -4,7 +4,7 @@ export CGO_ENABLED = 0
 
 BINARY := sfdupes
 VERSION := $(shell git describe --tags --always --dirty 2>/dev/null || echo dev)
-LDFLAGS := -X sneak.berlin/go/sfdupes/internal/sfdupes.Version=$(VERSION)
+LDFLAGS := -X main.Version=$(VERSION)
 
 .PHONY: sfdupes build bootstrap setup test lint fmt fmt-check check docker hooks clean
 
@@ -14,7 +14,7 @@ LDFLAGS := -X sneak.berlin/go/sfdupes/internal/sfdupes.Version=$(VERSION)
 # Default target: build the binary. Phony so go build (which has its
 # own build cache) always decides what to recompile.
 sfdupes:
-	go build -ldflags "$(LDFLAGS)" -o $(BINARY) ./cmd/sfdupes
+	go build -ldflags "$(LDFLAGS)" -o $(BINARY)
 
 build: sfdupes
 

README.md

@@ -17,13 +17,12 @@ gigabyte. A large file is never read in full. A match between two large files is
 a strong candidate, not proof.
 
 `sfdupes` is meant for multi-terabyte servers, where reading every byte of every
-file takes too long. It has five subcommands. `scan` walks the filesystem and
+file takes too long. It has four subcommands. `scan` walks the filesystem and
 records the files it finds in an SQLite database. SQLite keeps a whole database
 in one file. The database is kept between runs. A rescan reads only new and
 changed files. That makes `scan` cheap enough to run every day from `cron`, the
-system's job scheduler. `report`, `trees` and `info` work from the database and
+system's job scheduler. `report`, `trees` and `info` read the database alone and
-can run at any time. `dwim` scans `/` and then prints the `trees` report, for a
+can run at any time.
-first look at a new machine with one command.
 
 ## Getting Started
 
@@ -43,9 +42,7 @@ as opposed to a directory, a symlink or a device node. A symlink is a file that
 holds the path of another file and stands in for it. A device node is a file
 that stands for a piece of hardware, such as a disk or a terminal. `report`
 prints the file-level duplicates. `trees` prints the duplicate directory trees.
-Both cover the whole database, or only the paths given after them, as in
+`info` prints the database's path, size and record count.
-`sfdupes report /srv/photos`. `info` prints the database's path, size and record
-count.
 
 The database is `/var/lib/sfdupes/db.sqlite` unless `SFDUPES_DATABASE` names
 another file. The first `scan` creates it.
@@ -59,25 +56,25 @@ shell shows both on the terminal, and `>` redirects stdout alone.
 With Go installed, this builds and installs the newest tagged release:
 
 ```sh
-go install sneak.berlin/go/sfdupes/cmd/sfdupes@latest
+go install sneak.berlin/go/sfdupes@latest
 ```
 
 `@main` installs the tip of the `main` branch instead:
 
 ```sh
-go install sneak.berlin/go/sfdupes/cmd/sfdupes@main
+go install sneak.berlin/go/sfdupes@main
 ```
 
 The binary goes to `$(go env GOPATH)/bin`, or to `$GOBIN` when that is set.
 
 `sfdupes --version` prints `sfdupes VERSION` and exits. For a binary from
 `go install`, `VERSION` is the version Go recorded in it. For `@latest` that is
-a release tag. For `@main` it is the commit's tag when it has one. Otherwise it
+a release tag such as `v0.0.3`. For `@main` it is the commit's tag when it has
-is a pseudo-version, Go's version string for an untagged commit. That string
+one. Otherwise it is a pseudo-version, Go's version string for an untagged
-ends in the commit's hash. A binary built from a clone carries the output of
+commit. That string ends in the commit's hash. A binary built from a clone
-`git describe --tags --always --dirty` in that clone, such as `v0.0.3` on a
+carries the output of `git describe --tags --always --dirty` in that clone, such
-tagged commit. `VERSION` is `dev` when no version is known. To see everything Go
+as `v0.0.3` on a tagged commit. `VERSION` is `dev` when no version is known. To
-recorded in an installed binary:
+see everything Go recorded in an installed binary:
 
 ```sh
 go version -m "$(command -v sfdupes)"
@@ -100,15 +97,13 @@ Each `-v` flag below makes a bind mount, which shows a host directory at a path
 inside the container. Bind-mount `/var/lib/sfdupes` to keep the database between
 runs. Mount the tree to scan at the same path inside the container as on the
 host. Read-only access is enough. The database then records the host's paths,
-and so do the reports. `report` and `trees` need that mount too. Without it,
+and so do the reports.
-every recorded path counts as gone, and each report holds only its header line.
 
 ```sh
 make docker
 docker run --rm -v /srv:/srv:ro -v /var/lib/sfdupes:/var/lib/sfdupes \
     sfdupes scan /srv
-docker run --rm -v /srv:/srv:ro -v /var/lib/sfdupes:/var/lib/sfdupes \
+docker run --rm -v /var/lib/sfdupes:/var/lib/sfdupes sfdupes report > dupes.tsv
-    sfdupes report > dupes.tsv
 ```
 
 ### Daily scan from `cron`
@@ -163,10 +158,8 @@ to keep is your choice.
 
 A row is a candidate, not proof:
 
-- The reports show each file as it was when a scan last recorded it. They check
+- The reports show each file as it was when a scan last recorded it. A file may
-  only that each copy still exists: the file, or the directory at the top of a
+  have changed or gone since.
-  tree. A file may have changed since, and a file inside a tree may be gone. Run
-  `scan` again to bring the reports up to date.
 - A file of 100 MiB or more is compared only on samples of its content (see
   "Duplicate detection").
 - Two paths that are hard links, two names for one file, are listed as
@@ -214,9 +207,8 @@ makes the comparison exact. Reading samples cuts a 150 GiB file to about 150 MiB
 of reads, at the price of a comparison that is not exact.
 
 The hashes live in a database that is kept between runs. A rescan reads only new
-files, and files whose size or modification time (mtime) differs from their
+files, and files whose size changed or whose modification time (mtime) is newer
-record. All analysis then works from the database. The reports only check that
+than recorded. All analysis then works from the database alone.
-each copy they name still exists.
 
 The goal is whole duplicated trees, not only single files. A download extracted
 twice, or a project copied once too often, is such a tree. It can be removed as
@@ -242,10 +234,9 @@ In order:
    the files of the directories it is reading.
 3. **Rescan cheaply, analyze from the database.** The scan keeps its database
    between runs, and an unchanged file is never read again. `report`, `trees`
-   and `info` work from the database and never read a scanned file. `report` and
+   and `info` work from the database alone and never touch the scanned
-   `trees` check only that each copy they name still exists, and leave out a
+   filesystem. `scan` is built to run from `cron`. The reports run at any time,
-   copy that is gone. `scan` is built to run from `cron`. The reports run at any
+   against what the database holds.
-   time, against what the database holds.
 4. **Keep the streams apart.** Everything on stdout is machine-readable data.
    Everything for a human reader, such as progress and warnings, goes to stderr.
 
@@ -256,14 +247,12 @@ In order:
 - `report` prints the file-level duplicate report from the database.
 - `trees` prints the duplicate-tree report from the database.
 - `info` prints the database's details.
-- `dwim` scans `/`, then prints the duplicate-tree report.
 
 ```
-sfdupes scan [--workers N] [-x] [--no-default-excludes] [--exclude PATH]... PATH...
+sfdupes scan [--workers N] [-x] [--no-default-excludes] PATH...
-sfdupes report [PATH...] > dupes.tsv
+sfdupes report > dupes.tsv
-sfdupes trees [PATH...] > dupetrees.tsv
+sfdupes trees > dupetrees.tsv
 sfdupes info
-sfdupes dwim [--workers N] [-x] [--no-default-excludes] [--exclude PATH]...
 sfdupes --version
 sfdupes [command] --help
 ```
@@ -293,34 +282,22 @@ The reference below is also the program's specification.
   database is `/var/lib/sfdupes/db.sqlite`. There is no command-line flag for
   it. The path names the file exactly, whatever characters it holds. A relative
   path is relative to the working directory.
-- `--workers N` (`scan`, `dwim`) sets how many directories `scan` reads at once
+- `--workers N` (`scan`) sets how many directories `scan` reads at once while it
-  while it lists the trees. It also sets how many files `scan` reads at once
+  lists the trees. It also sets how many files `scan` reads at once while it
-  while it hashes them. The default is the number of CPUs. `N` must be at
+  hashes them. The default is the number of CPUs. `N` must be at least 1. A
-  least 1. A smaller value is a usage error, reported in one line on stderr with
+  smaller value is a usage error, reported in one line on stderr with exit 2
-  exit 2 before anything is scanned.
+  before anything is scanned.
-- `-x`, `--one-file-system` (`scan`, `dwim`) keeps the walk of each operand out
+- `-x`, `--one-file-system` (`scan`) keeps the walk of each operand out of
-  of directories on other filesystems, as the same flag does for `du` and
+  directories on other filesystems, as the same flag does for `du` and `rsync`.
-  `rsync`. By default the walk also enters directories on other filesystems.
+  By default the walk also enters directories on other filesystems.
-- `--no-default-excludes` (`scan`, `dwim`) lets the walk enter the default
+- `--no-default-excludes` (`scan`) lets the walk enter the default excludes.
-  excludes. Those are the system and temporary directories the walk otherwise
+  Those are the system and temporary directories the walk otherwise leaves out,
-  leaves out, such as `/var/tmp` on Linux (see "Rules for the walk").
+  such as `/var/tmp` on Linux (see "Rules for the walk").
-- `--exclude PATH` (`scan`, `dwim`) keeps the walk out of `PATH` and everything
-  below it. `PATH` may be a directory or a file. The flag may be given more than
-  once. The walk knows `PATH` by its device ID and inode number, as it knows the
-  database files (see "Rules for the walk"). So the walk leaves `PATH` out
-  whatever path leads to it. That includes a hard link to a file given as
-  `PATH`. A symlink given as `PATH` excludes its target. An empty `PATH`, as in
-  `--exclude ""`, is a usage error, reported in one line on stderr with exit 2
-  before anything is scanned. A `PATH` that does not exist, or whose real path
-  `scan` cannot find, is a fatal error. So is an operand at or below one (see
-  "Operands").
 - `--version`, `-v` prints `sfdupes VERSION` (see "Install") to stdout and
   exits 0. It writes nothing to stderr.
 - `--help`, `-h`, alone or after a subcommand, prints the help text to stderr
-  and exits 0. It writes nothing to stdout. The help of `sfdupes` and of `scan`
+  and exits 0. It writes nothing to stdout. `sfdupes scan --help` also lists the
-  names the database. The help of `report`, `trees`, `info` and `dwim` says what
+  default excludes of the system it runs on, and the filesystem types the walk
-  each prints. `sfdupes scan --help` and `sfdupes dwim --help` also list the
-  default excludes of the system they run on, and the filesystem types the walk
   never records anything on.
 
 ### Duplicate detection
@@ -371,30 +348,17 @@ default. An operand may be a directory or a regular file.
 
 - `scan` with no operand is a usage error. The usage text goes to stderr, and
   the exit code is 2.
-- An operand that does not exist is a fatal error, and so is a symlink whose
+- An operand that does not exist is a fatal error. `scan` then stops before it
-  target does not exist. `scan` then stops before it walks anything, and exits
+  walks anything, and exits 1.
-  with code 1.
+- Each operand is made absolute before the walk. A relative operand is joined to
-- An operand at or below an `--exclude` path is a fatal error too. The message
+  the working directory as `pwd` prints it, with its symlinks kept. A `.` or
-  names the operand and the `--exclude` path. `scan` compares the operand and
+  `..` in it is resolved as text, and symlinks are not followed. Each record is
-  each directory above it with the `--exclude` paths by device ID and inode
+  stored under that absolute path.
-  number, not by name.
-- Each operand is resolved to its real path before the walk, as `realpath`
-  prints it. A relative operand is joined to the working directory as `pwd -P`
-  prints it. Every symlink in the path is then followed. A `..` after a symlink
-  counts from the directory the symlink leads to. From then on the operand is
-  that real path. Its files are recorded under it, and warnings name it.
-- An operand that is a symlink is scanned at its target's real path. After a
-  `cd` through a symlink, `scan .` records its files under the real path of the
-  working directory.
 - All operands belong to one scan, and one walk covers them all at once (see
   "Concurrency").
-- An operand that repeats another is dropped before the walk. Two operands
+- An operand that repeats another is dropped before the walk.
-  repeat each other when their real paths are the same.
 - An operand under another operand is dropped the same way, unless one of the
-  cases below applies. No path is then walked twice. Whether one operand is
+  cases below applies. No path is then walked twice.
-  under another is judged on their real paths. With `/srv/link` a symlink to a
-  directory outside `/srv`, `scan /srv /srv/link/sub` walks `sub` on its own,
-  because the real path of `sub` is not under `/srv`.
 - An operand under another is kept, and walked on its own, when the inner
   operand or a directory between the two is one of these:
     - a default exclude (see "Rules for the walk");
@@ -405,19 +369,25 @@ default. An operand may be a directory or a regular file.
     memory (see "Rules for the walk"). The outer operand's walk does not enter
     such a directory, so the inner operand is walked on its own.
 
-- No other case keeps an operand under another.
+- No other case keeps an operand under another. An operand reached through a
-- An operand that is neither a regular file nor a directory is not scanned. Such
+  symlinked directory below the outer operand is dropped too. The outer
-  an operand is, for example, a symlink to a device node. `scan` prints a
+  operand's walk does not follow the symlink, so no file under the inner operand
-  warning naming the real path and what it is. It counts the operand as skipped
+  is scanned. The records that an earlier scan left under it are deleted. The
-  and drops it. The scan keeps the records beneath a dropped operand, unless
+  `-x` case above also covers an operand reached that way.
-  another operand covers them.
+- An operand that is neither a regular file nor a directory is not scanned.
+  `scan` prints a warning naming the path and what it is. It counts the operand
+  as skipped and drops it. An operand beneath a symlink operand is scanned all
+  the same. The scan keeps the records beneath a dropped operand, unless another
+  operand covers them. After a `cd` through a symlink, `scan .` names the
+  symlink and is skipped as a symlink operand. `scan sub` in that directory
+  records its files under the symlink's path. `report` can then list each as a
+  duplicate of the same file recorded under its real path.
 - An operand at or inside a directory named `.zfs` is never scanned, whether
-  given alone or under another operand. The check looks at the real path, so a
+  given alone or under another operand. The check looks at the path as given and
-  symlink into a `.zfs` directory is not scanned either. `scan` prints a warning
+  at the path with its symlinks resolved. `scan` prints a warning naming the
-  naming the real path, counts the operand as skipped and drops it. The records
+  path, counts the operand as skipped and drops it. The records beneath it are
-  beneath it are kept, unless it lies under another operand. Then they are
+  kept, unless it lies under another operand. Then they are deleted, because
-  deleted, because that operand's walk never enters `.zfs` (see "Rules for the
+  that operand's walk never enters `.zfs` (see "Rules for the walk").
-  walk").
 - An operand on a filesystem that is not persistent is dropped too. `scan`
   prints a line naming it and its filesystem type, and does not count it as
   skipped.
@@ -433,16 +403,17 @@ operands:
 
 - A file not yet in the database is hashed and inserted.
 - A file already in the database is not read again when its size and mtime match
-  its record. This is what makes a daily rescan cheap.
+  its record. The mtime matches when it is not newer than the recorded one. This
+  is what makes a daily rescan cheap.
 - When such a file's size on disk differs from its recorded `disk_size`, `scan`
   updates `disk_size` alone. It still does not read the file, and counts it as
-  unchanged. ZFS, for example, counts a new file's blocks up to seconds after
+  unchanged. ZFS, for example, counts a new file's blocks only seconds after the
-  the write. A block is the unit in which a filesystem allocates disk space. A
+  write. A block is the unit in which a filesystem allocates disk space. A file
-  file scanned within those seconds gets its real `disk_size` at the next scan.
+  scanned within those seconds gets its real `disk_size` at the next scan.
-- `scan` hashes a file again when its size or its mtime differs from its record.
+- `scan` hashes a file again when its size differs or its mtime is newer. The
-  An older mtime counts as much as a newer one. A file put back by `cp -p`,
+  mtime is compared to the nanosecond, as finely as the filesystem records it. A
-  `rsync -a` or a restore from backup often has an older mtime. The mtime is
+  same-size rewrite counts as a change whenever the filesystem gives it a later
-  compared to the nanosecond, as finely as the filesystem records it.
+  mtime, even within the same second.
 - The scan deletes each record under a scanned operand whose file it could not
   verify. That covers deleted files, and paths the scan could not stat or read
   this run. To stat a file is to read its details, such as its size, without
@@ -453,16 +424,15 @@ operands:
   scanned on different schedules into one database.
 - The scan keeps every record at or below a path that the walk leaves out for
   one of these reasons:
-    - it is an `--exclude` path;
     - it is a default exclude;
     - it is not on a persistent filesystem;
     - with `-x`, it is a directory on another filesystem than its operand.
 
     Such records count as outside the scanned operands. So with `-x`, a
     filesystem mounted under an operand can be scanned on its own schedule into
-    the same database. An operand may itself lie at or inside such a path, other
+    the same database. An operand may itself lie at or inside such a path, as
-    than an `--exclude` path (see "Operands"). Its walk verifies the records
+    "Operands" describes. Its walk verifies the records below it, so they are
-    below it, so they are deleted when their files are gone.
+    deleted when their files are gone.
 
 #### Phases
 
@@ -514,12 +484,12 @@ walk practical on large or busy storage pools.
     The walk knows them by device ID and inode number. The device ID is the
     number by which the kernel tells filesystems apart. The inode number tells
     the files of one filesystem apart. So the walk passes over them whatever
-    path leads to them. The walk follows no symlink it finds. It opens each
+    path leads to them. The walk follows no symlink it finds. It does open each
-    operand at its real path, not the path given. An operand given through a
+    operand at the path given, even when that path runs through a symlinked
-    symlink can lead to the database files, and the walk passes over them there
+    directory. Such an operand can lead to the database files, and the walk
-    as well. The walk prints no line for the database files and does not count
+    passes over them there as well. The walk prints no line for the database
-    them as skipped. A record that an earlier scan left for one of them is
+    files and does not count them as skipped. A record that an earlier scan left
-    deleted.
+    for one of them is deleted.
 
 - By default the walk enters directories on other filesystems than its
   operand's. With `-x`, it never enters a directory on a different filesystem
@@ -561,17 +531,6 @@ walk practical on large or busy storage pools.
     The path is not counted as skipped. The records below it are kept, as
     described under "What a scan does to the database".
 
-- The walk never enters or records an `--exclude` path, nor anything below it.
-  For each one it reaches, `scan` prints a line on stderr naming it:
-
-    ```
-    scan: skipped /srv/cache (--exclude)
-    ```
-
-    The path is not counted as skipped. The scan keeps the records at and below
-    it, as described under "What a scan does to the database".
-    `--no-default-excludes` does not change this rule.
-
 - Below an operand, the walk does not enter a default exclude. On Linux, the
   default excludes hold temporary files and the kernel's view of the running
   system. They depend on the system, and `sfdupes scan --help` lists those of
@@ -646,8 +605,7 @@ from a thread of its own and never blocks the workers.
   it repeats another or lies under another;
 - the progress display of each phase (see "Progress"). `scan` prints each
   warning for a skipped path as it happens. It prints a line the same way for
-  each path left out as an `--exclude` path, as a default exclude or as not on a
+  each path left out as a default exclude or as not on a persistent filesystem;
-  persistent filesystem;
 - the summary line;
 - a warning when a report still has the database open as the scan ends (see
   "Concurrent reads").
@@ -688,32 +646,22 @@ and `scan` leaves it ignored.
 
 ### `report` mode
 
-`report` reads every record from the database. It takes optional `PATH`
+`report` reads every record from the database. It takes no positional arguments.
-operands. With none, it uses every record. With one or more, it uses only the
+A positional argument is anything on the command line that is not a flag, such
-records at or below them (see "Operands of `report` and `trees`"). `report`
+as the paths `scan` takes. `report` never touches the scanned filesystem. It
-never opens a scanned file. It checks that each path in a group still exists,
+neither stats nor opens any path in the records. It reads the database and
-and looks at no other path. It never looks up an operand. The check is `lstat`,
+writes to stdout and stderr, and nothing else. Its output is the same whether or
-the system call that looks up a path without following a symlink:
+not the scanned filesystem is still mounted.
-
-- A path is gone when `lstat` finds that it, or a directory above it, does not
-  exist.
-- Any other error, such as a permission error, counts as present. So a user who
-  may not look inside a directory still sees its copies.
-
-The check does not notice a file that changed after the scan. Run `scan` again
-to bring the report up to date.
 
 Processing:
 
 - Records are grouped by signature, the four values
   `(size, head, tail, content)`.
-- In a group with two or more paths, a path that is gone is left out. A group
+- Every group with two or more paths is a duplicate group.
-  that still has two or more paths is a duplicate group.
-- Empty files form no group, because removing one frees nothing.
 - Within a group, paths are sorted in byte order. The first is `first`, and
   every other path is a `dupe`.
 - Groups are ordered by size, largest first, then by `first` path. The output is
-  the same for the same database contents and the same paths on disk.
+  the same for the same database contents.
 
 `report` has two phases, each with its own progress display on stderr (see
 "Progress"). `open` opens the database. `read` gets the number of records from
@@ -725,27 +673,6 @@ with one signature come together, and so do the records of one size. So `report`
 holds only the duplicate groups of the size it is reading. Once it reaches a
 smaller size, it writes them, ordered by `first` path.
 
-#### Operands of `report` and `trees`
-
-`report` and `trees` take the same `PATH` operands:
-
-- A record is used when its path is an operand or lies below one. `/srv/photos`
-  covers `/srv/photos/x` but not `/srv/photos2/x`.
-- The records used are grouped, ordered and totalled as they are without
-  operands. A copy outside the operands is not reported. With copies `/a/f`,
-  `/srv/photos/x` and `/srv/photos/y`, `sfdupes report /srv/photos` prints one
-  row, `/srv/photos/x` and `/srv/photos/y`.
-- A relative operand is joined to the working directory as `pwd -P` prints it.
-- Each operand is then cleaned as text, as `realpath -ms` prints it. Its `.`
-  elements and repeated or trailing slashes are dropped. Each `..` drops the
-  element before it.
-- No operand is looked up on the filesystem. A symlink in an operand is not
-  followed, and an operand need not exist. The records hold real paths (see
-  "Operands" under "`scan` mode"), so an operand that passes through a symlink
-  matches no record.
-- An operand that matches no record is not an error; it adds nothing to the
-  report.
-
 #### Report output format
 
 The report is TSV (tab-separated values) on stdout. It holds a header line, then
@@ -773,25 +700,22 @@ Grouping and ordering use the stored path. The warnings about skipped paths that
 
 The summary line on stderr gives:
 
-- the records read, which are all the records in the database, with or without
+- the records read;
-  operands;
 - the duplicate groups;
 - the dupe files, which is the number of rows;
 - the reclaimable bytes, the sum of `size` over all rows.
 
 ```
-report: 14 records read, 4 duplicate groups, 7 dupe files, 10.0 KiB reclaimable
+report: 14 records read, 5 duplicate groups, 8 dupe files, 10.0 KiB reclaimable
 ```
 
 ### `trees` mode
 
-`trees` reads the same database as `report` and takes the same `PATH` operands
+`trees` reads the same database as `report` and takes no positional arguments.
-(see "Operands of `report` and `trees`"). It reports whole duplicate directory
+It reports whole duplicate directory trees. Two directories are duplicate trees
-trees. Two directories are duplicate trees when they hold the same relative
+when they hold the same relative paths, and each path holds a file with the same
-paths, and each path holds a file with the same signature in both. It rebuilds
+signature in both. Like `report`, it never touches the scanned filesystem. It
-the directory tree from the paths in the records, split on `/`. Like `report`,
+rebuilds the directory tree from the paths in the records, split on `/`.
-it never opens a scanned file and never looks up an operand. It checks only that
-the directory at the top of each copy still exists, as `report` checks a path.
 
 Definitions:
 
@@ -810,26 +734,15 @@ Processing:
 - `trees` builds the directory tree and computes every directory's digest. It
   then groups the directories by digest. Every group with two or more
   directories is a duplicate-tree group.
-- `trees` leaves out a group whose trees hold 0 bytes, because removing one
-  frees nothing. An empty file still counts toward the digest of a tree that
-  holds other files.
 - `trees` leaves out a group that a group of its members' parents already
   implies. A group is left out when its members' parents are distinct
   directories that all have the same digest. The parents' group, or an
   ancestor's, already implies it. A group is always reported when it holds
   sibling directories, or when its members' parents have different digests.
-- With operands, `trees` builds the tree from the records it uses. It reports
-  only directories at or below an operand. Any other directory lies above an
-  operand and can hold files that are not used, so its digest does not describe
-  it. Such a directory is never reported and never implies a group of its
-  children.
-- A directory that is gone is dropped from its group. A group left with fewer
-  than two directories is not reported.
 - Within a group, paths are sorted in byte order. The first is `first`, and
   every other path is a `dupe`.
 - Groups are ordered by total tree size, largest first, then by `first` path.
-  The output is the same for the same database contents and the same paths on
+  The output is the same for the same database contents.
-  disk.
 
 Two limitations are accepted:
 
@@ -843,9 +756,8 @@ Two limitations are accepted:
 `trees` has four phases, each with its own progress display on stderr (see
 "Progress"). `open` opens the database. `read` gets the number of records from
 the `totals` table, then reads them in path order. It builds the directory tree
-and computes the digests as it goes. `group` groups the directories by digest,
+and computes the digests as it goes. `group` groups the directories by digest
-picks the groups to report and checks that their directories still exist.
+and picks the groups to report. `write` writes them to stdout.
-`write` writes the groups to stdout.
 
 #### Trees output format
 
@@ -876,8 +788,7 @@ directory's path is `/`.
 
 The summary line on stderr gives:
 
-- the records read, which are all the records in the database, with or without
+- the records read;
-  operands;
 - the duplicate-tree groups;
 - the dupe trees, which is the number of rows;
 - the reclaimable bytes, the sum of `size` over all rows.
@@ -886,46 +797,6 @@ The summary line on stderr gives:
 trees: 14 records read, 1 duplicate tree groups, 1 dupe trees, 3.0 KiB reclaimable
 ```
 
-### `dwim` mode
-
-`dwim`, short for "do what I mean", scans a new machine and reports its
-duplicate trees in one command. It takes no positional arguments. A positional
-argument is anything on the command line that is not a flag, such as the paths
-`scan` takes. Like `scan`, it should run as root, so that it can read every
-file.
-
-`dwim` takes these flags of `scan`, with the same meaning (see "Settings"):
-
-- `--workers N`;
-- `-x`, `--one-file-system`;
-- `--no-default-excludes`;
-- `--exclude PATH`, which may be given more than once.
-
-`dwim` runs what `sfdupes scan /` runs with the same flags. With no flags, the
-walk skips the default excludes and crosses into other filesystems. The
-database, its creation and the scan lock are those of `scan`. Then `dwim` runs
-what `sfdupes trees` runs. The largest trees come first.
-
-```
-sfdupes dwim -x --exclude /srv/cache
-```
-
-The report goes to stdout, exactly as `trees` prints it. On stderr comes what
-`scan` prints, then what `trees` prints, then one last line:
-
-```
-dwim: run "sfdupes trees" to print this report again
-```
-
-The database keeps the scan, so `sfdupes trees` prints the report again later,
-even after the terminal is gone. It then leaves out a copy deleted in between.
-
-`SIGINT` or `SIGTERM` stops the scan as it stops `scan` (see "Stopping a scan").
-`dwim` then prints no report and exits 1. A fatal scan error also ends it before
-the report, with the same message and exit code as `scan`. Warnings for skipped
-files do not stop it. `dwim` stops catching signals when the scan ends, so a
-signal during the report ends it at once, as it ends `trees`.
-
 ### `info` mode
 
 `info` takes no positional arguments and prints the database's details on
@@ -966,7 +837,7 @@ scan is writing. `info` writes its lines after the `count` display has ended.
 
 ### Database
 
-All five subcommands work on one SQLite database file.
+All four subcommands work on one SQLite database file.
 
 #### Location
 
@@ -982,8 +853,6 @@ scan: new database /var/lib/sfdupes/db.sqlite (default)
 trees: database /srv/tmp/sfdupes/db.db (from SFDUPES_DATABASE)
 ```
 
-`dwim` prints the `scan` line first, and the `trees` line after the scan.
-
 A relative path is printed with the working directory in front of it. The
 working directory is printed as `pwd -P` prints it, with its symlinks resolved.
 The rest of the path is printed as set, so a `..` in it stays. The line names
@@ -1210,10 +1079,9 @@ in, and a phase that may wait in two places names both, as `disk/db`:
 - `hash` says `disk/db`, because it reads files and writes their records to the
   database between them.
 - `load`, `update` and the `read` phase of `trees` say `db`.
-- The `read` phase of `report` says `db/disk/out`. It checks that the paths of
+- The `read` phase of `report` says `db/out`, because it writes the report to
-  each group still exist, and writes the report to stdout, while it reads.
+  stdout while it reads.
-- `group` of `trees` says `cpu/disk`, for work in memory and the check that each
+- `group` of `trees` says `cpu`, for work in memory, and its `write` says `out`.
-  copy still exists. Its `write` says `out`.
 - A phase still waiting for its total says what it waits for, and nothing more.
 
 On a terminal:
@@ -1268,12 +1136,9 @@ showing the count it stopped at.
 ### Error handling and exit codes
 
 - `0`: success, even when files were skipped with warnings.
-- `1`: a fatal error, a `scan` stopped by `SIGINT` or `SIGTERM`, or a `dwim`
+- `1`: a fatal error, or a `scan` stopped by `SIGINT` or `SIGTERM`. A fatal
-  stopped by either during its scan. A fatal error is one of these:
+  error is one of these:
-    - an operand that does not exist, or whose real path `scan` cannot find;
+    - an operand that does not exist, or whose details `scan` cannot read;
-    - an `--exclude` path that does not exist, or whose real path `scan` cannot
-      find;
-    - an operand at or below an `--exclude` path;
     - a list of mounted filesystems that `scan` cannot read;
     - another `scan` holding the lock (see "The scan lock");
     - a database, its directory or its lock file that cannot be created or
@@ -1293,9 +1158,7 @@ showing the count it stopped at.
       `--workers abc`;
     - `scan` with no operand;
     - `--workers` below 1;
-    - an empty `--exclude` value, as in `--exclude ""`;
+    - `report`, `trees` or `info` with a positional argument.
-    - an empty `PATH` for `report` or `trees`, as in `sfdupes report ""`;
-    - `info` or `dwim` with a positional argument.
 
 A fatal error is reported on stderr, starting with `sfdupes:`. A failed write to
 stdout, such as a full disk, is reported the same way. Two cases never reach
@@ -1458,8 +1321,8 @@ commands of their own:
   not a goal. `modernc.org/sqlite` is pure Go too, so the binary builds without
   cgo. The `Makefile` exports `CGO_ENABLED=0`. The test build is the one
   exception, because the race detector needs cgo (see `script/test`).
-- `report` and `trees` give the same output for the same database contents and
+- `report` and `trees` give the same output for the same database contents,
-  the same paths on disk, whatever order the records were inserted in.
+  whatever order the records were inserted in.
 
 ### Definition of done
 
@@ -1483,7 +1346,7 @@ All of the following, run in this directory, must pass:
     head -c 2000 /dev/urandom > "$d/a/unique.bin"     # same size, different content
     printf 'x' > "$d/tiny1"; printf 'x' > "$d/tiny2"  # 1-byte duplicates
     printf 'y' > "$d/tiny3"                           # 1-byte non-duplicate
-    : > "$d/empty1"; : > "$d/empty2"                  # empty files
+    : > "$d/empty1"; : > "$d/empty2"                  # empty duplicates
     # duplicate trees: t1 and t2 are identical; t3 differs by one filename
     mkdir -p "$d/t1/sub" "$d/t2/sub" "$d/t3/sub"
     head -c 3000 /dev/urandom > "$d/t1/f1"
@@ -1508,8 +1371,8 @@ All of the following, run in this directory, must pass:
       is the path that sorts first.
     - `t1/f1`, `t2/f1` and `t3/f1` form one group.
     - `t1/sub/f2`, `t2/sub/f2` and `t3/sub/f2renamed` form one group.
-    - `tiny1` and `tiny2` form a pair.
+    - `tiny1` and `tiny2` form a pair, and so do `empty1` and `empty2`.
-    - `unique.bin`, `tiny3`, `empty1` and `empty2` appear nowhere.
+    - `unique.bin` and `tiny3` appear nowhere.
     - The groups come in order of size, largest first.
 
     `trees` prints exactly one row, `$d/t1` as `first` and `$d/t2` as `dupe`.
@@ -1522,9 +1385,8 @@ All of the following, run in this directory, must pass:
     because its content changed. `copy.bin` and `copy2.bin` remain as one pair.
     `unique.bin` is gone from the database.
 
-    The test suite automates this scenario (see
+    The test suite automates this scenario (see `scan_test.go`). It also checks
-    `internal/sfdupes/scan_test.go`). It also checks that `report` and `trees`
+    that `report` and `trees` never touch the scanned filesystem.
-    leave out a copy removed after the scan.
 
 ## TODO
 

TODO.md

@@ -4,7 +4,7 @@
   the tracker yet is filed as an issue first.
 - Branch from `next`.
 - Do the work, with tests, in small focused commits.
-- Delete Next Step from `TODO.md`, in the same commit as the work.
+- Record the step at the top of Completed Steps, in the same commit as the work.
 - Push the branch and open a PR against `next`. Its title ends with
   ` (closes #N)`.
 - An independent review gates each merge to `next`. Every finding is addressed
@@ -15,7 +15,8 @@
 
 - Pre-1.0.
 - The tracker is authoritative for the pre-1.0 backlog. The open issues under
-  the `1.0.0` milestone are what remains before the tag.
+  the `1.0.0` milestone are what remains before the tag. This file records
+  history and process, not the queue.
 
 # Next Step
 
@@ -23,6 +24,709 @@
   https://git.eeqj.de/sneak/sfdupes/milestone/17. The issues are not restated
   here, because a copy drifts as soon as the tracker moves.
 
+# Completed Steps
+
+Newest first. An entry ends with its date and its issue or branch, where those
+are known.
+
+- `TODO.md` rewritten from scratch by the same rules as `README.md`, sentence by
+  sentence. Every completed step is kept, with its date and its issue or branch.
+  The policy-compliance checklist of 2026-07-22 is folded into its step
+  (2026-11-02, https://git.eeqj.de/sneak/sfdupes/issues/135)
+
+- `README.md` rewritten from scratch, sentence by sentence, as a newcomer reads
+  it. It leads with what the program is and how to use it. A reference section
+  covers every setting and every subcommand. Development and testing come last.
+  Every statement was checked against the code on `next`. Five comments in
+  `main_test.go` cite "Settings", where their rules now live. One comment each
+  in `scan_test.go`, `trees_test.go` and `exclude_test.go` cites what the README
+  now says (2026-11-02, https://git.eeqj.de/sneak/sfdupes/issues/135)
+
+- Each record holds `disk_size`, the bytes the file takes on disk. That is its
+  allocated blocks, `st_blocks` × 512, from the `lstat` call the walk already
+  makes. `trees` prints a `disk_size` column after `size`. It is the sum over
+  the `dupe` copy's files. On a compressed or sparse file `disk_size` 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. Three triggers on `files` keep that row current.
+  `info` reads that row. 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. That 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.
+  The bar 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. That is 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 three hashes to every file that the walk records. `head`
+  and `tail` are the SHA-256 of its first and last 64 KiB. `content` is the
+  SHA-256 of the whole file under 100 MiB, and of 1 MiB at each gigabyte from
+  100 MiB up. Gone are:
+    - the 10 MiB and 50 MiB thresholds;
+    - the size census, which counted the sizes of every walked file and of every
+      record outside the operands. A file was hashed only when the census showed
+      another file of its size;
+    - the records without hashes;
+    - the content phase.
+
+    A scan has four phases, and a rescan reads only new and changed files.
+    `info` no longer counts the records with `head` and `tail` hashes, nor those
+    with a content hash, since every record has all three (2026-10-25,
+    https://git.eeqj.de/sneak/sfdupes/issues/132)
+
+- `REPO_POLICIES.md` and the four scripts that pass `CACHEBUST` were copied
+  again from `sneak/prompts` `next` at `0653579`. Two steps now come before
+  `ARG CACHEBUST`:
+    - the module download in the `lint`, `test` and `builder` stages of the
+      `Dockerfile`;
+    - the package install in `builder`.
+
+    Docker keeps them until one of these changes:
+    - the base image;
+    - the install line;
+    - `go.mod` or `go.sum`.
+
+    Every step that checks or compiles the code still comes after
+    `ARG CACHEBUST`. `golangci-lint run` also keeps the linter's own cache.
+    README says the same (2026-10-18,
+    https://git.eeqj.de/sneak/sfdupes/issues/109)
+
+- The release rule was set. Until 1.0, each tip of `main` that passes the build
+  gets the next `v0.0.N` tag. `go install sneak.berlin/go/sfdupes@latest` then
+  installs it. `go.mod` retracts `v0.0.1`, the early build without a database.
+  When the linker set no version, `sfdupes --version` prints the version Go
+  recorded in the binary. That is the tag, or the pseudo-version of a
+  `go install` build. It prints `dev` only when neither is known. README
+  "Install" documented:
+    - the rule;
+    - what `@main` and `v0.0.1` give;
+    - how to check an installed binary.
+
+    (2026-10-17, https://git.eeqj.de/sneak/sfdupes/issues/116)
+
+- `scan` creates the database's directory where the database path leads. The
+  directory is the path with its last element cut off as text, so a `..` in it
+  stays. A `..` after a symlinked directory therefore goes through the symlink,
+  as it does when the file is opened. With
+  `SFDUPES_DATABASE=/srv/link/../new/db.sqlite` and `/srv/link` a symlink to
+  `/data/x`, it now creates `/data/new` and the database in it. It used to
+  create `/srv/new` and then fail (2026-10-17,
+  https://git.eeqj.de/sneak/sfdupes/issues/119)
+
+- `scan` never records its own database. Once the database and its `.lock` file
+  are open, it notes the device and inode of each of these:
+    - the database file;
+    - its `-wal` and `-shm` files;
+    - the `.lock` file.
+
+    The walk passes over any file with the device and inode of one of them,
+    however it reaches the file. It prints no line for such a file and counts
+    nothing. A record an earlier scan left for one of them is deleted
+    (2026-10-17, https://git.eeqj.de/sneak/sfdupes/issues/115)
+
+- `scan` never records or reads anything on a filesystem that is not persistent,
+  such as `tmpfs` or `proc`. Such a filesystem is one the kernel makes up or
+  keeps in memory. `scan` matches them by device ID, however the walk or the
+  content phase reaches a path. As the scan starts, it lists the mounted
+  filesystems of those types, from `/proc/self/mountinfo` on Linux and from the
+  mount list on macOS. No flag turns that off. Below an operand, the walk does
+  not enter the default excludes either. So `sfdupes scan /` skips the kernel's
+  view of the running system and the temporary directories. On Linux those are:
+
+    ```
+    /proc, /sys, /dev, /run, /tmp, /var/tmp
+    ```
+
+    On macOS they are:
+
+    ```
+    /dev, /private/tmp, /private/var/tmp, /private/var/vm
+    /System/Volumes/VM, /System/Volumes/Data
+    ```
+
+    A Windows list exists in the code but is not used. An operand at or inside a
+    default exclude is still walked. The scan prints a line for each path it
+    leaves out, without counting it as skipped. The records there count as
+    outside the scanned operands, as for `-x`. `--no-default-excludes` turns off
+    the default excludes only, and `scan --help` lists them (2026-10-17,
+    https://git.eeqj.de/sneak/sfdupes/issues/124)
+
+- A progress display's rate covers the items completed over the last 5 seconds.
+  When stderr is not a terminal, it covers the items since the line before. It
+  falls to 0 while nothing completes. A burst after a wait no longer reads as a
+  steady rate of over 1,000 files a second. The time remaining still comes from
+  the phase's average. Once no item has completed for 10 seconds, the line shows
+  `stalled` and where the phase waits in place of the rate, as
+  `stalled disk/db`. The places are:
+    - `disk`;
+    - `db`;
+    - `out`, for stdout;
+    - `cpu`.
+
+    A phase that may wait in two places names both. Each phase's word is set in
+    the code that defines the phase. A line too wide for the terminal loses its
+    bar first, then its rate or those words. Four parts stay whole:
+    - the phase;
+    - the progress;
+    - the elapsed time;
+    - the ETA, the time remaining.
+
+    The content phase had one display for its checks and one for its reads. Both
+    lost those words on an 80-column terminal, at counts like those of README's
+    example. That happened for most elapsed times and ETAs in minutes. Every
+    other phase kept them whenever the elapsed time and the ETA were both in
+    minutes. The content phase writes its last partial batch, the records not
+    yet written, under a display of its own (2026-10-16,
+    https://git.eeqj.de/sneak/sfdupes/issues/125)
+
+- New subcommand `info` prints the database's details on stdout, one per line as
+  a name, a tab and the value:
+    - the path and where it came from;
+    - the sizes of the database file and of its `-wal` file, when there is one;
+    - when the database file was last changed;
+    - the schema version;
+    - the number of records;
+    - how many records have `head` and `tail` hashes;
+    - how many records have a content hash;
+    - the sizes of all records added up.
+
+    It opens the database as `report` does and shows two phases on stderr,
+    `[1/2] open` and `[2/2] count`. The schema version and the counts come from
+    one read-only transaction, a read of the database at one moment. The counts
+    come from one query (2026-10-16,
+    https://git.eeqj.de/sneak/sfdupes/issues/117)
+
+- `report` shows its work on stderr in two phases, `[1/2] open` and
+  `[2/2] read`, with the progress display `scan` and `trees` use. The display
+  runs from the moment `report` starts until the summary line. `open` says it is
+  opening the database, also while it waits on a busy one. `read` counts the
+  records, then reads them against that count in signature order. SQLite takes
+  that order from the `files_signature` index without sorting, so the first
+  record comes at once. `report` forms the duplicate groups itself and holds
+  only those of the size it is reading. It writes them ordered by first path
+  before it reads the next size. stdout and the summary line are unchanged, and
+  SQLite no longer needs a temporary file to sort in (2026-10-16,
+  https://git.eeqj.de/sneak/sfdupes/issues/114)
+
+- `trees` shows its work on stderr in four phases, from `[1/4] open` to
+  `[4/4] write`, each with the progress display `scan` uses. The display runs
+  from the moment `trees` starts until the summary line. `open` says it is
+  opening the database, also while it waits on a busy one. `read` counts the
+  records, then reads them against that count. `group` counts the directories it
+  groups, and `write` the groups it writes. A display's rate names what its
+  phase counts:
+    - files;
+    - records;
+    - directories;
+    - groups.
+
+    stdout and the summary line are unchanged. When stdout and stderr are the
+    same file, as one terminal is, no line of stdout shares a line with the
+    display. When they are not, the display keeps being drawn while stdout waits
+    on a slow reader (2026-10-16, https://git.eeqj.de/sneak/sfdupes/issues/113)
+
+- Each `scan` phase's progress display names the phase and its place among the
+  five, as `[2/5] walk`. It runs from the moment that the phase starts. It
+  shows:
+    - the progress;
+    - the elapsed time;
+    - the ETA, the time remaining.
+
+    `load` counts the records first. The walk's total is estimated from the
+    records under the operands. The content phase takes its total from SQLite's
+    grouping alone. Until the first record is returned, it says it is searching
+    the database. On a terminal a phase with an exact total draws its line
+    followed by the bar of the progress-bar library. Any other phase draws a
+    spinner followed by the line. Every display is drawn again several times a
+    second. No line reaches the terminal's last column, however narrow the
+    terminal is, even after it is made narrower during a phase. A line too wide
+    leaves out its rate, then its bar. The rest stays whole. The line is cut
+    short only when the rest alone does not fit, as below about 70 columns late
+    in a large scan. When stderr is not a terminal, the line is printed every 5
+    seconds whether or not an item completed (2026-10-16,
+    https://git.eeqj.de/sneak/sfdupes/issues/112)
+
+- `scan`, `report` and `trees` first print a line on stderr naming the database
+  they use, as an absolute path. The line says whether that path is the default
+  or comes from `SFDUPES_DATABASE`. `scan` says when the database is new. README
+  "Database" says when `scan` writes each file (2026-10-16,
+  https://git.eeqj.de/sneak/sfdupes/issues/111)
+
+- The canonical files and model scripts were copied again from `sneak/prompts`
+  `next` at `e3f79c4`:
+    - `golangci-lint` v2.14.0;
+    - lint and test are phases of the `Dockerfile` that write no image, and
+      `make test` runs the suite under the race detector. Gone are
+      `Dockerfile.lint`, `script/verify-lint-image-pin` and `make test-race`;
+    - every `docker build` in `script/` passes a new `CACHEBUST` value. Every
+      stage of the `Dockerfile` declares it first, so every `RUN` step runs on
+      every build. The steps that compile keep Go's build cache, and the tests
+      run with `-count=1`;
+    - `prettier` runs on the host, from the `node` and `yarn` that
+      `script/bootstrap` installs. The `prettier` and `markdown` stages are
+      gone, 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;
+    - a coding agent's settings file is deleted.
+
+    Since https://git.eeqj.de/sneak/sfdupes/issues/109 two steps come before
+    `ARG CACHEBUST`:
+    - the module download in `lint`, `test` and the build stage;
+    - the install of `git` and `make` in the build stage.
+
+    Docker keeps them between builds. Every step that checks or compiles the
+    code still runs on every build (2026-10-15,
+    https://git.eeqj.de/sneak/sfdupes/issues/95)
+
+- With `-x`, an operand under another operand is no longer dropped when a
+  directory between the two, the inner one included, is on a different
+  filesystem than the outer one. The inner operand is then walked on its own.
+  For a regular-file operand the check starts at its directory. The records of
+  files gone from below it are deleted (2026-10-14,
+  https://git.eeqj.de/sneak/sfdupes/issues/106)
+
+- With `-x`, `scan` keeps the records below a directory on another filesystem
+  under its operand, instead of deleting them. It counts their sizes in the size
+  census (2026-10-14, https://git.eeqj.de/sneak/sfdupes/issues/99)
+
+- The hash and content phases open each file without blocking and check that it
+  is still a regular file. A file that is now a FIFO or device node is warned
+  about and skipped instead of hanging the scan (2026-10-14,
+  https://git.eeqj.de/sneak/sfdupes/issues/100)
+
+- The scan lock file is named from the database's path with symlinks resolved,
+  after `scan` creates the database file if it is missing. A scan through a
+  symlink to the database therefore fails while another scan holds the lock
+  (2026-10-14, https://git.eeqj.de/sneak/sfdupes/issues/101)
+
+- On a terminal, a warning for the last file of a phase no longer erases the
+  phase's finished bar. The bar is drawn again below the warning (2026-10-14,
+  https://git.eeqj.de/sneak/sfdupes/issues/102)
+
+- `scan` records the mtime to the nanosecond, as whole seconds in `mtime` plus
+  `mtime_nsec`, and compares it at that resolution. A same-size rewrite within
+  the same second is hashed again (2026-10-07,
+  https://git.eeqj.de/sneak/sfdupes/issues/12)
+
+- The narration was cut from `TODO.md` Completed Steps and from the comments in
+  `script/`, `Dockerfile` and `Dockerfile.lint` (gone since
+  https://git.eeqj.de/sneak/sfdupes/issues/95). The Workflow section now
+  branches from and merges to `next` (2026-10-04,
+  https://git.eeqj.de/sneak/sfdupes/issues/49)
+
+- `make test-race` ran the test suite under the race detector in a cgo-enabled
+  container, outside `make check`. Since
+  https://git.eeqj.de/sneak/sfdupes/issues/95 `make test` itself runs the suite
+  under the race detector, in the `Dockerfile`'s Debian-based `test` phase.
+  `make test-race` is gone (2026-10-04,
+  https://git.eeqj.de/sneak/sfdupes/issues/18)
+
+- A bare `docker build .` failed, naming `script/cibuild` and `script/docker`,
+  rather than serve the gates, the lint and test steps, from cache. Since
+  https://git.eeqj.de/sneak/sfdupes/issues/95 a bare build succeeds, as
+  `REPO_POLICIES.md` requires, and may serve the gates from cache. The builds in
+  `script/` pass a new `CACHEBUST` value, so theirs always run (2026-10-04,
+  https://git.eeqj.de/sneak/sfdupes/issues/39)
+
+- `make fmt` and `make fmt-check` run `prettier` over all Markdown, and the
+  Gitea workflow checks it. All Markdown was reformatted (2026-10-04,
+  https://git.eeqj.de/sneak/sfdupes/issues/19)
+
+- `script/lint` writes no image, so a run no longer leaves an untagged one
+  behind (2026-10-04, https://git.eeqj.de/sneak/sfdupes/issues/48)
+
+- Tests cover:
+    - a missing database;
+    - `scan` keeping stdout empty;
+    - its skip warning;
+    - the `report` and `trees` summary lines;
+    - every subcommand going through `runE`.
+
+    (2026-10-04, https://git.eeqj.de/sneak/sfdupes/issues/16)
+
+- `.golangci.yml` was replaced with the current canonical copy, which uses
+  `gomodguard_v2`, so lint no longer prints a deprecation warning (2026-10-04,
+  https://git.eeqj.de/sneak/sfdupes/issues/26)
+
+- A test fails when either `hashWorker` cancellation check in `scan.go` is
+  removed (2026-10-04, https://git.eeqj.de/sneak/sfdupes/issues/83)
+
+- A database path holding `?`, `#` or `%` opens exactly the file it names
+  (2026-10-04, https://git.eeqj.de/sneak/sfdupes/issues/55)
+
+- `scan` rejects `--workers` below 1 as a usage error instead of running
+  single-threaded (2026-10-04, https://git.eeqj.de/sneak/sfdupes/issues/10)
+
+- A test fails when either walk cancellation check in `scan.go` is removed
+  (2026-10-04, https://git.eeqj.de/sneak/sfdupes/issues/81)
+
+- A test checks that `scan` refuses a database with another schema version
+  (2026-10-04, https://git.eeqj.de/sneak/sfdupes/issues/64)
+
+- Four inaccurate comments in `cancel_test.go` were corrected, and
+  `walkCancelInFlightDirs` was renamed to `walkCancelInFlightFiles` (2026-10-04,
+  https://git.eeqj.de/sneak/sfdupes/issues/33)
+
+- The `-x` filesystem-boundary rules in `subdirJob` are tested (2026-10-04,
+  https://git.eeqj.de/sneak/sfdupes/issues/17)
+
+- `scan` creates the schema in one transaction. A version-0 database with a
+  `files` table is refused with a clear schema-version error (2026-10-04,
+  https://git.eeqj.de/sneak/sfdupes/issues/11)
+
+- README documents install, Docker, a daily `cron` scan and how to read and
+  check the reports (2026-10-04, https://git.eeqj.de/sneak/sfdupes/issues/54)
+
+- The `Dockerfile` build stage kept the Go module cache out of `builder`'s home
+  and copied the sources with `--chown`, so no `chown -R` walked them. Since
+  https://git.eeqj.de/sneak/sfdupes/issues/95 there is no `builder` user and
+  nothing changes owner. The build stage only compiles, as root, and the tests
+  run as `nobody` in the `test` phase (2026-10-04,
+  https://git.eeqj.de/sneak/sfdupes/issues/43)
+
+- `--version` prints `sfdupes VERSION` to stdout. README documents it and
+  `--help` (2026-10-04, https://git.eeqj.de/sneak/sfdupes/issues/15)
+
+- `scan` stops cleanly on `SIGINT` or `SIGTERM`: it commits what it has hashed,
+  deletes nothing more, and exits 1 (2026-10-04,
+  https://git.eeqj.de/sneak/sfdupes/issues/5)
+
+- `report` and `trees` stream the records instead of holding them all in memory.
+  The schema gains the `files_signature` index (2026-10-04,
+  https://git.eeqj.de/sneak/sfdupes/issues/14)
+
+- Progress prints at once on a non-terminal and uses a real terminal test.
+  Warnings print through a spinner instead of racing its redraw (2026-10-03,
+  https://git.eeqj.de/sneak/sfdupes/issues/13)
+
+- These operands are warned about and skipped, and the records beneath them are
+  kept:
+    - symlinks;
+    - sockets;
+    - FIFOs;
+    - device nodes;
+    - `.zfs` directories.
+
+    (2026-10-03, https://git.eeqj.de/sneak/sfdupes/issues/9)
+
+- `scan` holds a lock on a lock file beside the database for its whole run, so a
+  second `scan` fails at once with exit 1 (2026-10-03,
+  https://git.eeqj.de/sneak/sfdupes/issues/53)
+
+- Tests cover stdout write failures in `report` and `trees`. README states that
+  `| head` ends `sfdupes` by `SIGPIPE` and that `>&-` writes to `/dev/null`
+  (2026-10-03, https://git.eeqj.de/sneak/sfdupes/issues/30)
+
+- `report` and `trees` open the database read-only, and `scan` leaves it out of
+  WAL mode, so reading needs only read access (2026-10-03,
+  https://git.eeqj.de/sneak/sfdupes/issues/8)
+
+- Four characters are escaped in `report`, `trees` and warning paths:
+    - tab;
+    - newline;
+    - carriage return;
+    - backslash.
+
+    The root directory's path is `/` (2026-10-03,
+    https://git.eeqj.de/sneak/sfdupes/issues/7)
+
+- A plain `docker build .` stamps the `git` tag or short commit instead of
+  `dev`. `.dockerignore` sends `.git` without `.git/config`. The build stage
+  stamps the `VERSION` build argument, else `git describe --tags --always`. It
+  fails if the context carries `.git` and the version is still empty, `dev` or
+  `unknown`. The Gitea workflow checks out the full history (`fetch-depth: 0`),
+  so it stamps the same value as `make build` (2026-10-02, branch `next`,
+  https://git.eeqj.de/sneak/sfdupes/issues/67)
+
+- The 1 KiB end-window sampling was replaced with the hashes chosen by file
+  size, and README "Duplicate detection" documented every size threshold. A file
+  under 10 MiB was hashed in full, and its `head`, `tail` and `content` all held
+  that hash. A larger file got only its 64 KiB `head` and `tail` in the hash
+  phase. The content phase ran after the update phase. It read a file for
+  `content` only when its size, `head` and `tail` matched another record's, from
+  this scan or an earlier one. `content` was the whole file below 50 MiB, and
+  gigabyte-spaced 1 MiB samples at or above. It never read a file gone or
+  changed since its record was written. `report` and `trees` left out any record
+  without a `content` hash. The `content` column is part of the version 1
+  schema. Superseded by https://git.eeqj.de/sneak/sfdupes/issues/132
+  (2026-09-22, branch `next`, https://git.eeqj.de/sneak/sfdupes/issues/61)
+
+- The dead `files.dat` references were removed from `Makefile`, `.gitignore` and
+  `.dockerignore` (2026-09-21, branch `next`,
+  https://git.eeqj.de/sneak/sfdupes/issues/22)
+
+- The lint-image pin comments and `FROM` form in `Dockerfile` and
+  `Dockerfile.lint` were fixed. Both pins became the policy
+  `# image:vX.Y.Z, YYYY-MM-DD` comment over a bare `FROM image@sha256:...`,
+  without the false `(Debian-based)` note or the tag. Since
+  https://git.eeqj.de/sneak/sfdupes/issues/95 the `Dockerfile`'s `lint` phase
+  holds the only `golangci-lint` pin, in that form. `Dockerfile.lint` is gone,
+  and so is `script/verify-lint-image-pin`, which compared the two pins
+  (2026-08-10, branch `next`, https://git.eeqj.de/sneak/sfdupes/issues/25)
+
+- All linting ran in Docker, via `Dockerfile.lint` and `script/lint`. Per the
+  owner ruling the linter is never installed on a host, and
+  `golangci-lint config verify` runs before `golangci-lint run`.
+  `script/bootstrap` stopped installing or pinning the linter, and
+  `script/verify-linter-pin` was retired. Since
+  https://git.eeqj.de/sneak/sfdupes/issues/95 both commands run in the
+  `Dockerfile`'s `lint` phase. `script/lint` builds that phase alone, and the
+  build stage depends on it through `COPY --from=lint /src/go.sum /dev/null`.
+  `Dockerfile.lint` and `script/verify-lint-image-pin` are gone. Nothing inside
+  an image build may run `docker`, so the phase calls `golangci-lint` directly
+  (2026-08-10, branch `next`, https://git.eeqj.de/sneak/sfdupes/issues/46)
+
+- The Docker build stage's prerequisites were installed by running
+  `script/bootstrap` instead of `apk add --no-cache make` inline.
+  `script/verify-linter-pin` failed the build unless the linter copied from the
+  lint stage was the version that `script/bootstrap` pinned. Builds then took up
+  to 5m14s from an empty cache, mostly in a `chown -R` of the module cache,
+  filed as https://git.eeqj.de/sneak/sfdupes/issues/43. Since
+  https://git.eeqj.de/sneak/sfdupes/issues/95 the build stage installs `git` and
+  `make` with `apk add --no-cache` and only compiles. The `lint` and `test`
+  phases are the gates (2026-08-09, branch `dockerfile-bootstrap`,
+  https://git.eeqj.de/sneak/sfdupes/issues/42)
+
+- The Docker layer cache is defeated for the gate steps, so `script/cibuild` and
+  `script/docker` cannot report a pass they did not earn. The `Dockerfile`
+  copies the tree before its gates. On an unchanged tree Docker served them from
+  cache, and the build exited 0 without running them. The fix was 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. Every stage of the `Dockerfile`
+  declares it before every step that checks or compiles the code. Run as root,
+  the tests fail `TestScanHardlinkRunFailsTogether`, because root reads through
+  the `chmod(0)` the test relies on. So the `test` phase runs them as `nobody`
+  (2026-08-09, branch `cibuild-cache-bust`,
+  https://git.eeqj.de/sneak/sfdupes/issues/32)
+
+- `script/bootstrap` checked the installed `golangci-lint` version instead of
+  only its presence. The version lived only in `GOLANGCI_LINT_VERSION`, with the
+  `go install` module reference derived from it. Any installed version that was
+  not the pin was reinstalled, whether:
+    - older;
+    - newer;
+    - absent;
+    - unparseable.
+
+    `go install` writes into `GOBIN`, or `GOPATH/bin`, while `make lint` ran the
+    first `golangci-lint` on `PATH`. So bootstrap re-read the effective version
+    after installing. On a mismatch it printed both paths and both versions and
+    exited non-zero. It did not reorder `PATH` or delete anyone's binary. The
+    `--version` call kept its stderr and was bounded by `timeout(1)` where that
+    exists. `git`, `make` and `go` kept presence-only checks. The version check
+    was verified by bootstrapping this host from v2.10.1 to v2.12.2, and again
+    to a no-op. Stub runs of the script under `dash` covered:
+    - a thirteen-input version-parse matrix;
+    - a shadowed install, which must exit non-zero;
+    - an install destination not on `PATH`;
+    - `GOBIN` set;
+    - a wedged binary, which must hit the timeout.
+
+    `make check` and `make lint` were clean at v2.12.2, so v2.10.1 had not been
+    hiding findings on `main`. Superseded by
+    https://git.eeqj.de/sneak/sfdupes/issues/46, since the linter is no longer
+    installed on a host (2026-08-09, branch `bootstrap-version-check`,
+    https://git.eeqj.de/sneak/sfdupes/issues/24)
+
+- The hash worker pool unwinds on the error path. The pool is an owned,
+  context-aware `hashPool`. Every blocking send in the feeder and the workers
+  selects on `ctx.Done()`, and `jobs` is closed on every path out. `hashPhase`
+  defers `pool.stop()`, which cancels and then drains `results` until the last
+  goroutine has exited. Draining is what frees a worker parked on a send. `ctx`
+  is passed from `cmd.Context()` as the first parameter, through:
+    - `runScan`;
+    - `syncScan`;
+    - both worker pools;
+    - the whole database layer.
+
+    The walk pool gets the same treatment, plus a `ctx.Err()` guard after the
+    walk. A cancelled walk yields a partial size census, and every file that it
+    never reached looks vanished to the update phase. That phase's own `BeginTx`
+    also fails on the cancelled context before deleting anything. The guard is
+    still the barrier once an interrupted scan may commit what it has. Tests
+    drive `run(scan)` against a database whose insert trigger aborts. They
+    assert that the scan fails instead of hanging, and that the goroutine count
+    returns to its pre-scan baseline. Other tests cancel a scan part-way through
+    the walk, deterministically, by counting the scan's own checks of
+    `ctx.Done()`. They assert that it stops at the guard with every record
+    intact. It then holds a partial size census and a still-populated record
+    index. Direct tests cover the remaining cancellation branches of both pools.
+    They test:
+    - `sendEvent`;
+    - the walk workers;
+    - `dispatchDirs`;
+    - `feedHashJobs`;
+    - `hashWorker`;
+    - `hashPhase`.
+
+    (2026-08-09, branch `hash-pool-cleanup`,
+    https://git.eeqj.de/sneak/sfdupes/issues/6)
+
+- The database is closed on every fatal exit path. `fatalf` and its `os.Exit(1)`
+  are gone. So the deferred `db.Close()` runs when a subcommand fails, and with
+  it the SQLite WAL checkpoint. These return errors instead:
+    - `runScan`;
+    - `runReport`;
+    - `runTrees`;
+    - `loadRecords`;
+    - `resolveRoots`.
+
+    The single exit point is `run` in `main.go`. It maps a `fatalError`,
+    anything a subcommand returned, to exit 1, and cobra's own argument and flag
+    errors to exit 2. So a runtime failure is never reported as a usage error,
+    nor printed with the usage text. `main_test.go` drives the CLI in-process
+    and asserts the exit codes from README "Error handling" and the
+    stdout/stderr split. It also checks that a fatal error after the database is
+    open leaves no `-wal` or `-shm` file behind, for `scan`, `report` or `trees`
+    (2026-08-09, branch `db-close-on-fatal`,
+    https://git.eeqj.de/sneak/sfdupes/issues/4)
+
+- `golangci-lint` was updated to v2.12.2 with the canonical config, merged as
+  `38a01bd`. The pinned linter in the `Dockerfile` lint stage and
+  `script/bootstrap` went from v2.12.1 to v2.12.2, and `.golangci.yml` was
+  replaced with the canonical file. Four thresholds now live under
+  `linters.settings`, as the v2 schema requires, so they are applied:
+    - `lll`;
+    - `funlen`;
+    - `cyclop`;
+    - `dupl`.
+
+    No new lint findings surfaced (2026-08-09, branch `golangci-v2.12.2`,
+    https://git.eeqj.de/sneak/sfdupes/issues/3)
+
+- `Makefile` targets were converted to scripts-to-rule-them-all `script/`
+  entrypoints, like the other managed repos. All 12 entrypoints exist:
+    - `bootstrap`, `setup` and `projectname`;
+    - `test`, `lint`, `fmt`, `fmt-check` and `check`;
+    - `docker`, `cibuild`, `precommit` and `install-precommit`.
+
+    Every `Makefile` target does nothing but call its script (2026-07-26, commit
+    `3abeacf`, https://git.eeqj.de/sneak/sfdupes/issues/1)
+
+- The binary is the default `make` target. Plain `make` builds `sfdupes`, where
+  it used to run `check` plus `build`. `make build` remains as an alias
+  (2026-07-24, branch `make-default-target`)
+
+- The phases became scan-wide, with concurrent operands and batched updates. All
+  operands seed the shared walk pool, and every pass runs once over the whole
+  scan. So the totals and ETAs cover the whole scan. The per-operand walk, hash
+  and update cycles and their stderr announcements are gone. The update pass
+  writes in batches, each in its own transaction. The filesystem is
+  authoritative and the database follows it, so one scan's changes need not land
+  all at once (2026-07-24, branch `scan-wide-phases`)
+
+- The stat pass was split back out of the walk. Phases are strictly sequential
+  again, per operand, with parallelism only inside each phase:
+    - walk;
+    - stat;
+    - hash;
+    - update.
+
+    The walk enumerates paths with per-directory workers, and the stat pass
+    lstats them with per-file workers. That restores the exact total and ETA of
+    the stat bar (2026-07-24, branch `parallel-phases`)
+
+- Each operand is announced on stderr before its passes. With per-operand walk,
+  hash and update cycles, a multi-operand run such as `scan /srv/*` showed pass
+  totals that looked like the whole run's (2026-07-24, branch
+  `scan-operand-progress`)
+
+- The walk became parallel. The walk pass was a single goroutine and took hours
+  at about 20 million files on a busy pool. One ZFS server took 4 hours for 22
+  million files. It is now a walk by a pool of per-directory workers that
+  records size and mtime as it goes. That folds away the separate stat pass and
+  halves the metadata reads. Each `PATH` operand commits in its own transaction,
+  so an interrupted scan keeps completed operands (2026-07-24, branch
+  `parallel-walk`)
+
+- `scan` gained a persistent database. It maintains an SQLite database that
+  survives between runs, with the absolute path as each record's key. The driver
+  is `modernc.org/sqlite`, pure Go, so cgo stays disabled. A rescan hashes only
+  new or changed files, by mtime and size. It deletes the records of files
+  vanished from under the scanned operands and leaves records outside them
+  untouched. So `scan` can run daily from `cron`. `report` and `trees` read the
+  database, with no positional arguments, instead of a scan stream. The database
+  is at `/var/lib/sfdupes/db.sqlite`, and `SFDUPES_DATABASE` overrides that. WAL
+  journaling plus a single-transaction update keep a report run during a scan
+  safe (2026-07-24, branch `persistent-database`)
+
+- The `origin` remote, `git@git.eeqj.de:sneak/sfdupes.git`, was added. `v0.0.1`
+  was tagged, and `main` and the tags were pushed (2026-07-23)
+
+- The `scan` command line was reworked. Required `PATH...` operands, parsed by
+  cobra, replace the `/srv` `-root` default. The new `-x`, `--one-file-system`
+  flag follows the GNU convention and stops at filesystem boundaries, which the
+  walk crosses by default (2026-07-23, branch `scan-required-paths`)
+
+- The repo was brought into compliance with `REPO_POLICIES.md` (the version of
+  2026-07-06), the existing repo checklist and the Go styleguide. The audit of
+  2026-07-22 found these gaps, and the branch closed them:
+    - `.gitignore`, with the standard patterns for secrets and for OS, editor
+      and Go files. The compiled `sfdupes` binary and `files.dat` had been
+      sitting untracked in the tree;
+    - `.editorconfig`;
+    - `LICENSE` and the README License section. MIT was assumed from house
+      convention, for the owner to confirm;
+    - `REPO_POLICIES.md` in the repo root;
+    - the canonical `.golangci.yml`, with its 150 findings fixed, so that
+      `make lint` is clean;
+    - the `Makefile` targets the policy requires:
+        - `test` and `lint`;
+        - `fmt` and `fmt-check`;
+        - `docker` and `hooks`.
+
+        `check` depended on `build`, which wrote the binary. `make check` must
+        not modify files, so `check` no longer depends on `build`;
+
+    - a test suite, which the policy required with a 30-second timeout and the
+      conditional `-v` rerun. At 64% coverage, it covers:
+        - parsing and grouping;
+        - digests and suppression;
+        - hashing and the scan pipeline;
+    - a multistage `Dockerfile` and `.dockerignore`. The `Dockerfile` had:
+        - hash-pinned images;
+        - a lint stage that failed fast;
+        - a build stage that ran `make check`;
+    - `.gitea/workflows/check.yml`, running `docker build .` on push with the
+      checkout action pinned by commit SHA;
+    - the README sections the policy requires. The first is a Description whose
+      first line names the project, its purpose and category, its license and
+      its author. Then come Getting Started and Rationale, and at the end TODO,
+      License and Author;
+    - the stale README non-goal "no git repository setup and no CI" removed;
+    - the pre-commit hook, installed with `make hooks` once that target existed.
+
+    The code was already `gofmt`-clean, so no standalone formatting commit was
+    needed (2026-07-23, branch `repo-policy-compliance`)
+
+- `git init` was run, with a README-only first commit. The code baseline was
+  committed on `main` (2026-07-22)
+
+- The `scan`, `report` and `trees` subcommands were implemented (pre-git
+  history)
+
 # Future Steps
 
 - Possible later features, out of scope per README, are a byte-for-byte check of
@@ -30,4 +734,6 @@
 
 # Accepted Divergences
 
-None.
+- Flat single-package layout, with the `.go` files in the repo root. That is
+  fine for a small single-binary tool per the Go styleguide, and the tracker
+  audit agrees.

cancel_test.go

@@ -1,4 +1,4 @@
-package sfdupes //nolint:testpackage // cancels the unexported runScan and hashWorker
+package main
 
 import (
 	"context"
@@ -358,9 +358,8 @@ func TestRunScanInterrupted(t *testing.T) {
 	stderr := captureStderr(t)
 	dir := buildSmokeTree(t)
 
-	opts := scanOptions{workers: walkCancelWorkers}
+	err := runScan(t.Context(), []string{dir}, walkCancelWorkers, false,
-
+		false)
-	err := runScan(t.Context(), []string{dir}, opts)
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -383,7 +382,8 @@ func TestRunScanInterrupted(t *testing.T) {
 	go func() {
 		defer close(done)
 
-		err = runScan(cancelledContext(t), []string{dir}, opts)
+		err = runScan(cancelledContext(t), []string{dir}, walkCancelWorkers,
+			false, false)
 	}()
 
 	awaitReturn(t, done, "runScan")
@@ -410,7 +410,8 @@ func TestRunScanInterrupted(t *testing.T) {
 			got, before)
 	}
 
-	err = runScan(t.Context(), []string{dir}, opts)
+	err = runScan(t.Context(), []string{dir}, walkCancelWorkers, false,
+		false)
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -436,7 +437,7 @@ func TestRunScanInterruptedMidHash(t *testing.T) {
 	dir := buildWalkCancelTree(t)
 
 	err := runScan(newWalkClock(hashCancelAtDone), []string{dir},
-		scanOptions{workers: walkCancelWorkers})
+		walkCancelWorkers, false, false)
 	if !errors.Is(err, errInterrupted) {
 		t.Fatalf("runScan interrupted mid-hash = %v, want %v",
 			err, errInterrupted)

cmd/sfdupes/main.go

@@ -1,29 +0,0 @@
-// 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 three SHA-256 hashes: of the first 64 KiB, of the last 64
-// KiB, and of the content. The content hash covers the whole file under
-// 100 MiB, and 1 MiB at each gigabyte at 100 MiB or more, so a large
-// file is never read in full. scan maintains a persistent SQLite
-// database of file signatures (SFDUPES_DATABASE, default
-// /var/lib/sfdupes/db.sqlite) that the other subcommands read.
-//
-// Usage:
-//
-//	sfdupes scan [--workers N] [-x] [--no-default-excludes] PATH...
-//	sfdupes report > dupes.tsv
-//	sfdupes trees > dupetrees.tsv
-//	sfdupes info
-//	sfdupes dwim
-//	sfdupes --version
-//
-// See README.md for the complete specification.
-package main
-
-import (
-	"os"
-
-	"sneak.berlin/go/sfdupes/internal/sfdupes"
-)
-
-func main() { os.Exit(sfdupes.Main()) }

db.go

@@ -1,4 +1,4 @@
-package sfdupes
+package main
 
 import (
 	"context"
@@ -146,44 +146,33 @@ 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, made absolute by absolutePath, and where the path came from,
+// path, with the working directory, its symlinks resolved, put in front
-// "default" or "from SFDUPES_DATABASE", for the line each subcommand
+// of it when it is relative, and where the path came from, "default" or
-// prints first on stderr.
+// "from SFDUPES_DATABASE", for the line each subcommand prints first on
+// stderr.
 func databasePath() (string, string, error) {
 	path, source := defaultDatabasePath, "default"
 	if p := os.Getenv(databaseEnv); p != "" {
 		path, source = p, "from "+databaseEnv
 	}
 
-	abs, err := absolutePath(path)
+	if filepath.IsAbs(path) {
+		return path, source, nil
+	}
+
+	// The working directory as the kernel reports it, with no symlink
+	// in it, as README "Database" says. os.Getwd may return PWD
+	// instead, which can name it through a symlink.
+	wd, err := unix.Getwd()
 	if err != nil {
 		return "", "", fmt.Errorf("resolve database path %s: %w", path, err)
 	}
 
-	return abs, source, nil
+	// Not filepath.Abs or filepath.Join: they clean the path, which
-}
+	// drops each ".." together with the directory name before it. When
-
+	// that directory is a symlink, the cleaned path names another file.
-// absolutePath returns path unchanged when it is absolute, and
-// otherwise the working directory, a "/" and path. The working
-// directory is the one the kernel reports, with no symlink in it;
-// os.Getwd may return PWD instead, which can name it through a symlink.
-// The result is not cleaned, as filepath.Abs and filepath.Join would
-// clean it. Cleaning drops each ".." together with the directory name
-// before it. When that name is a symlink, the cleaned path names
-// another file than the one the system reaches by following the symlink
-// first.
-func absolutePath(path string) (string, error) {
-	if filepath.IsAbs(path) {
-		return path, nil
-	}
-
-	wd, err := unix.Getwd()
-	if err != nil {
-		return "", err
-	}
-
 	// The working directory ends in "/" only when it is the root.
-	return strings.TrimSuffix(wd, "/") + "/" + path, nil
+	return strings.TrimSuffix(wd, "/") + "/" + path, source, nil
 }
 
 // createDatabaseDirectory creates the directory the database at path

db_test.go

@@ -1,4 +1,4 @@
-package sfdupes //nolint:testpackage // calls the unexported database openers
+package main
 
 import (
 	"context"

exclude.go

@@ -1,9 +1,8 @@
-package sfdupes
+package main
 
-// This file holds three rules for the walk (README "Rules for the
+// This file holds two rules for the walk (README "Rules for the walk"):
-// walk"): the paths given with --exclude, which the scan never enters;
 // the default excludes, the paths a scan's walk does not enter below an
-// operand unless scan is given --no-default-excludes; and the
+// operand unless scan is given --no-default-excludes, and the
 // filesystems that are not persistent, on which the scan never records
 // or reads anything.
 
@@ -13,7 +12,6 @@ import (
 	"fmt"
 	"io"
 	"io/fs"
-	"os"
 	"path/filepath"
 	"slices"
 	"strings"
@@ -45,23 +43,15 @@ const typesPerHelpLine = 6
 // readMountInfo reads.
 var errMountInfoLine = errors.New("unexpected line")
 
-// errExcludedOperand reports an operand at or below a path given with
-// --exclude.
-var errExcludedOperand = errors.New("operand excluded by --exclude")
-
 // walkRules holds the rules for the walk that a scan sets up as it
-// starts. excludePaths are the paths given with --exclude, each with
+// starts. excludes are the default excludes, or none with
-// the device ID and inode number of the file it names (see
+// --no-default-excludes. nonPersistent maps the device ID of every
-// excludePathInodes), which the walk neither enters nor records,
+// mounted filesystem that is not persistent to its type; the scan
-// whatever path leads to them. defaultExcludes are the default
+// records and reads nothing on one of those, whatever the flags.
-// excludes, or none with --no-default-excludes. nonPersistent maps the
+// databaseFiles are the scan's own database files, which the walk
-// device ID of every mounted filesystem that is not persistent to its
+// passes over (see databaseFiles in db.go).
-// type; the scan records and reads nothing on one of those, whatever
-// the flags. databaseFiles are the scan's own database files, which the
-// walk passes over (see databaseFiles in db.go).
 type walkRules struct {
-	excludePaths    []fileRec
+	excludes      []string
-	defaultExcludes []string
 	nonPersistent map[uint64]string
 	databaseFiles []fileRec
 }
@@ -107,88 +97,6 @@ func isDefaultExclude(path string, excludes []string) bool {
 	return false
 }
 
-// excludePathInodes returns each of paths, the --exclude values, as its
-// real path (see realPaths) with the device ID and inode number of the
-// file there. The walk compares what it reaches with those, as it does
-// with the database files, so it also leaves out an --exclude path
-// spelled another way, such as in another letter case on macOS.
-func excludePathInodes(paths []string) ([]fileRec, error) {
-	resolved, err := realPaths(paths)
-	if err != nil {
-		return nil, err
-	}
-
-	files := make([]fileRec, 0, len(resolved))
-
-	for _, path := range resolved {
-		fi, err := os.Lstat(path)
-		if err != nil {
-			return nil, err
-		}
-
-		dev, ino := inodeOfInfo(fi)
-		files = append(files, fileRec{path: path, dev: dev, ino: ino})
-	}
-
-	return files, nil
-}
-
-// matchingExcludePath returns the path of the one of excludePaths with
-// the device ID and inode number of fi, an lstat result, or "" when
-// there is none.
-func matchingExcludePath(fi fs.FileInfo, excludePaths []fileRec) string {
-	dev, ino := inodeOfInfo(fi)
-	f := fileRec{dev: dev, ino: ino}
-
-	for _, exclude := range excludePaths {
-		if sameInode(exclude, f) {
-			return exclude.path
-		}
-	}
-
-	return ""
-}
-
-// checkOperandsNotExcluded returns an error when one of roots, the
-// operands, or a directory above it is one of excludePaths, the
-// --exclude paths, by device ID and inode number. The error names the
-// operand and the --exclude path. The roots are absolute, so the
-// directories above each one end at /. A path here that lstat cannot
-// read is an error too.
-func checkOperandsNotExcluded(roots []string, excludePaths []fileRec) error {
-	for _, root := range roots {
-		for path := root; ; path = filepath.Dir(path) {
-			fi, err := os.Lstat(path)
-			if err != nil {
-				return fmt.Errorf("scan %s: %w", root, err)
-			}
-
-			exclude := matchingExcludePath(fi, excludePaths)
-			if exclude != "" {
-				return fmt.Errorf("scan %s: %w %s", root, errExcludedOperand,
-					exclude)
-			}
-
-			if path == "/" {
-				break
-			}
-		}
-	}
-
-	return nil
-}
-
-// excludePathLine returns the line the scan prints for path when fi,
-// its lstat, makes it one of rules.excludePaths, and "" when it does
-// not.
-func (rules walkRules) excludePathLine(path string, fi fs.FileInfo) string {
-	if matchingExcludePath(fi, rules.excludePaths) == "" {
-		return ""
-	}
-
-	return fmt.Sprintf("scan: skipped %s (--exclude)", path)
-}
-
 // nonPersistentFilesystemTypes returns the filesystem types that are
 // not persistent: filesystems that the kernel makes up or that are kept
 // in memory. devfs is the macOS filesystem of /dev; the others are
@@ -254,7 +162,7 @@ func readMountInfo(mountinfo io.Reader) (map[uint64]string, error) {
 	return devices, lines.Err()
 }
 
-// defaultExcludesHelp describes, for the scan and dwim help, the
+// defaultExcludesHelp describes, for the scan command's help, the
 // default excludes of the system goos names and, where the scan lists
 // the mounted filesystems, the types it never records anything on.
 func defaultExcludesHelp(goos string) string {

exclude_darwin.go

@@ -1,6 +1,6 @@
 //go:build darwin
 
-package sfdupes
+package main
 
 import (
 	"slices"

exclude_other.go

@@ -1,6 +1,6 @@
 //go:build !darwin
 
-package sfdupes
+package main
 
 import (
 	"fmt"

exclude_test.go

@@ -1,4 +1,4 @@
-package sfdupes //nolint:testpackage // checks the unexported defaultExcludes
+package main
 
 import (
 	"bytes"
@@ -14,9 +14,6 @@ import (
 	"golang.org/x/sys/unix"
 )
 
-// excludeFlag is the scan flag that names a path the walk never enters.
-const excludeFlag = "--exclude"
-
 func TestDefaultExcludes(t *testing.T) {
 	t.Parallel()
 
@@ -191,7 +188,7 @@ func TestScanDoesNotEnterDefaultExclude(t *testing.T) {
 	unseen := writeFile(t, excluded, "new", pattern(2, 10))
 
 	st, err := syncScan(t.Context(), db, []string{dir}, 1, false,
-		walkRules{defaultExcludes: []string{excluded}})
+		walkRules{excludes: []string{excluded}})
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -237,7 +234,7 @@ func TestScanWalksOperandInDefaultExclude(t *testing.T) {
 			db := openTestDB(t)
 
 			st, err := syncScan(t.Context(), db, roots, 1, false,
-				walkRules{defaultExcludes: []string{excluded}})
+				walkRules{excludes: []string{excluded}})
 			if err != nil {
 				t.Fatal(err)
 			}
@@ -265,7 +262,7 @@ func TestScanNamesNoDefaultExcludeThatIsAnOperand(t *testing.T) {
 	f := writeFile(t, excluded, "f", pattern(1, 10))
 
 	st, err := syncScan(t.Context(), db, []string{dir, excluded}, 1, false,
-		walkRules{defaultExcludes: []string{excluded}})
+		walkRules{excludes: []string{excluded}})
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -289,7 +286,7 @@ func TestRunScanTempDirOperand(t *testing.T) {
 	path := testDBPath(t)
 	t.Setenv(databaseEnv, path)
 
-	dir := realTempDir(t)
+	dir := t.TempDir()
 	if !underAnyRoot(dir, defaultExcludes(runtime.GOOS)) {
 		t.Skip(dir + " is not inside a default exclude")
 	}
@@ -359,217 +356,6 @@ func TestRunScanNoDefaultExcludes(t *testing.T) {
 	assertRecorded(t, path, f, true)
 }
 
-// TestRunScanExcludeNested scans a tree through the command with an
-// --exclude path two levels below the operand. The walk records nothing
-// at or below it and says so. The record an earlier scan left there is
-// kept although its file is gone.
-func TestRunScanExcludeNested(t *testing.T) {
-	path := testDBPath(t)
-	t.Setenv(databaseEnv, path)
-
-	dir := realTempDir(t)
-	excluded := filepath.Join(dir, "a", "b")
-	kept := writeFile(t, dir, "a/f", pattern(1, 10))
-	gone := writeFile(t, excluded, "gone", pattern(2, 10))
-
-	scanOK(t, dir)
-
-	err := os.Remove(gone)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	unseen := writeFile(t, excluded, "c/new", pattern(3, 10))
-
-	stderr := scanOK(t, excludeFlag, excluded, dir)
-
-	line := "scan: skipped " + excluded + " (--exclude)\n"
-	if !strings.Contains(stderr, line) {
-		t.Errorf("stderr = %q, want %q", stderr, line)
-	}
-
-	assertRecorded(t, path, kept, true)
-	assertRecorded(t, path, gone, true)
-	assertRecorded(t, path, unseen, false)
-}
-
-// TestRunScanExcludeRepeated gives --exclude twice, once for a
-// directory and once for a file, the file through a symlink to it. The
-// walk records neither, and records the file beside them.
-func TestRunScanExcludeRepeated(t *testing.T) {
-	path := testDBPath(t)
-	t.Setenv(databaseEnv, path)
-
-	dir := realTempDir(t)
-	inDir := writeFile(t, dir, "skip/f", pattern(1, 10))
-	file := writeFile(t, dir, "skip-file", pattern(2, 10))
-	kept := writeFile(t, dir, "keep", pattern(3, 10))
-
-	link := filepath.Join(t.TempDir(), "link")
-	symlink(t, file, link)
-
-	scanOK(t, excludeFlag, filepath.Dir(inDir), excludeFlag, link, dir)
-
-	assertRecorded(t, path, inDir, false)
-	assertRecorded(t, path, file, false)
-	assertRecorded(t, path, kept, true)
-}
-
-// TestRunScanExcludeReachedByAnotherPath gives --exclude a directory
-// through a symlink and a file through "..", so the walk reaches
-// neither by the path given. The walk also reaches the file through a
-// hard link. It records none of these, prints a line naming each, and
-// records the file beside them.
-func TestRunScanExcludeReachedByAnotherPath(t *testing.T) {
-	path := testDBPath(t)
-	t.Setenv(databaseEnv, path)
-
-	dir := realTempDir(t)
-	inDir := writeFile(t, dir, "a/cache/f", pattern(1, 10))
-	file := writeFile(t, dir, "a/big", pattern(2, 10))
-	kept := writeFile(t, dir, "keep", pattern(3, 10))
-
-	hardLink := filepath.Join(dir, "big-link")
-
-	err := os.Link(file, hardLink)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	link := filepath.Join(t.TempDir(), "link")
-	symlink(t, filepath.Join(dir, "a"), link)
-
-	// Joined as text, since filepath.Join would drop the "..".
-	dotDot := dir + "/a/cache/../big"
-
-	stderr := scanOK(t, excludeFlag, filepath.Join(link, "cache"),
-		excludeFlag, dotDot, dir)
-
-	for _, skipped := range []string{filepath.Dir(inDir), file, hardLink} {
-		line := "scan: skipped " + skipped + " (--exclude)\n"
-		if !strings.Contains(stderr, line) {
-			t.Errorf("stderr = %q, want %q", stderr, line)
-		}
-	}
-
-	assertRecorded(t, path, inDir, false)
-	assertRecorded(t, path, file, false)
-	assertRecorded(t, path, hardLink, false)
-	assertRecorded(t, path, kept, true)
-}
-
-// TestRunScanExcludedOperand checks that an operand at or below an
-// --exclude path is a fatal error that names both, and so is an
-// --exclude path that does not exist. An operand that is a hard link to
-// an --exclude file is at it. Neither scan writes a database.
-func TestRunScanExcludedOperand(t *testing.T) {
-	dir := realTempDir(t)
-	sub := filepath.Join(dir, "sub")
-	f := writeFile(t, sub, "f", pattern(1, 10))
-
-	hardLink := filepath.Join(dir, "f-link")
-
-	err := os.Link(f, hardLink)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	cases := map[string]struct {
-		args []string
-		want string
-	}{
-		"at it": {
-			[]string{excludeFlag, sub, sub},
-			"scan " + sub + ": operand excluded by --exclude " + sub + "\n",
-		},
-		"below it": {
-			[]string{excludeFlag, dir, sub},
-			"scan " + sub + ": operand excluded by --exclude " + dir + "\n",
-		},
-		"after an operand it does not exclude": {
-			[]string{dir, excludeFlag, sub, sub},
-			"scan " + sub + ": operand excluded by --exclude " + sub + "\n",
-		},
-		"a hard link to it": {
-			[]string{excludeFlag, f, hardLink},
-			"scan " + hardLink + ": operand excluded by --exclude " + f + "\n",
-		},
-		"exclude missing": {
-			[]string{excludeFlag, filepath.Join(dir, "nope"), dir},
-			"--exclude: resolve " + filepath.Join(dir, "nope") + ": ",
-		},
-	}
-
-	for name, tc := range cases {
-		t.Run(name, func(t *testing.T) {
-			path := testDBPath(t)
-			t.Setenv(databaseEnv, path)
-
-			stdout := captureStdout(t)
-			stderr := captureStderr(t)
-
-			code := run(append([]string{cmdScan}, tc.args...), os.Stdout,
-				os.Stderr)
-			if code != exitFatal {
-				t.Errorf("run(scan %q) = %d, want %d", tc.args, code,
-					exitFatal)
-			}
-
-			assertFatalOutput(t, stderr(), stdout())
-
-			if !strings.Contains(stderr(), "sfdupes: "+tc.want) {
-				t.Errorf("stderr = %q, want %q", stderr(), tc.want)
-			}
-
-			_, err := os.Lstat(path)
-			if !errors.Is(err, os.ErrNotExist) {
-				t.Errorf("lstat %s: %v, want no database", path, err)
-			}
-		})
-	}
-}
-
-// TestRunScanRejectsEmptyExclude checks that an empty --exclude value,
-// given as its own argument, after "=" or after another --exclude, is
-// a usage error reported in one line before anything is scanned
-// (README "Settings").
-func TestRunScanRejectsEmptyExclude(t *testing.T) {
-	dir := t.TempDir()
-
-	cases := map[string][]string{
-		"separate":     {excludeFlag, "", dir},
-		"joined by =":  {excludeFlag + "=", dir},
-		"after a path": {excludeFlag, t.TempDir(), excludeFlag, "", dir},
-	}
-
-	for name, args := range cases {
-		t.Run(name, func(t *testing.T) {
-			path := testDBPath(t)
-			t.Setenv(databaseEnv, path)
-
-			var stdout, stderr bytes.Buffer
-
-			code := run(append([]string{cmdScan}, args...), &stdout,
-				&stderr)
-			if code != exitUsage {
-				t.Errorf("run(scan %q) = %d, want %d", args, code,
-					exitUsage)
-			}
-
-			want := "Error: --exclude must not be empty\n"
-			if stdout.String() != "" || stderr.String() != want {
-				t.Errorf("stdout, stderr = %q, %q, want \"\", %q",
-					stdout.String(), stderr.String(), want)
-			}
-
-			_, err := os.Lstat(path)
-			if !errors.Is(err, os.ErrNotExist) {
-				t.Errorf("lstat %s: %v, want no database", path, err)
-			}
-		})
-	}
-}
-
 // TestRunScanSkipsNonPersistentOperand scans, through the command, a
 // directory on a filesystem that is not persistent, with and without
 // --no-default-excludes: either way it is skipped, with a line saying

info.go

@@ -1,4 +1,4 @@
-package sfdupes
+package main
 
 import (
 	"context"

info_test.go

@@ -1,4 +1,4 @@
-package sfdupes //nolint:testpackage // seeds the database with unexported scanRec
+package main
 
 import (
 	"fmt"

internal/sfdupes/cli.go

@@ -1,447 +0,0 @@
-// Package sfdupes implements the sfdupes command and the database its
-// subcommands share.
-package sfdupes
-
-import (
-	"context"
-	"errors"
-	"fmt"
-	"io"
-	"os"
-	"runtime"
-	"runtime/debug"
-	"slices"
-
-	"github.com/spf13/cobra"
-)
-
-// Exit codes: exitOK is success (even with per-file warnings),
-// exitFatal is a fatal error, exitUsage is a usage error.
-const (
-	exitOK    = 0
-	exitFatal = 1
-	exitUsage = 2
-)
-
-// The subcommand names, as typed on the command line.
-const (
-	cmdScan   = "scan"
-	cmdReport = "report"
-	cmdTrees  = "trees"
-	cmdInfo   = "info"
-	cmdDwim   = "dwim"
-)
-
-// databaseHelp is the paragraph of the root and scan help that names
-// the database (README "Location").
-const databaseHelp = "scan and dwim store what they find in a database " +
-	"file. report, trees\nand info read it. The file is $" + databaseEnv +
-	" when that is set and\nnot empty, and otherwise " +
-	defaultDatabasePath + ", where creating it\nneeds root.\n"
-
-// escapesHelp is the paragraph of the report and trees help on how
-// paths are escaped (README "Report output format").
-const escapesHelp = `Four characters in a path are escaped, so each row stays one line:
-
-  \\  a backslash
-  \t  a tab
-  \n  a newline
-  \r  a carriage return
-`
-
-// operandsHelp is the paragraph of the report and trees help on their
-// PATH operands (README "Operands of `report` and `trees`").
-const operandsHelp = `With PATH operands, only the records at or below them are used. A
-relative PATH is joined to the working directory. No PATH is looked up
-on the filesystem, so a symlink in one is not followed.
-`
-
-// reportHelp, treesHelp, infoHelp and dwimHelp follow the one-line
-// summary in the help of their subcommands.
-const (
-	reportHelp = `The report is tab-separated text on stdout: a header line, then one
-row per duplicate file. The columns are:
-
-  first   the path that sorts first, byte by byte, in its group of copies
-  dupe    another copy of that file
-  size    the file's size in bytes
-
-Rows are ordered by size, largest first, then by path.
-
-` + escapesHelp + "\n" + operandsHelp
-
-	treesHelp = `The report is tab-separated text on stdout: a header line, then one
-row per duplicate directory tree. The columns are:
-
-  first      the path that sorts first, byte by byte, in its group of copies
-  dupe       another copy of that tree
-  files      the number of regular files in one copy
-  size       their total size in bytes
-  disk_size  the bytes the dupe copy takes on disk
-
-Rows are ordered by size, largest first, then by path.
-
-` + escapesHelp + "\n" + operandsHelp
-
-	infoHelp = `The details go to stdout, one per line. Each line holds a name and its
-value, separated by a tab:
-
-  database                the path, and where it came from
-  database file size      in bytes, then rounded, as 2147483648 (2.0 GiB)
-  -wal file size          in bytes, then rounded; only if a -wal file exists
-  modified                when the database file last changed, in UTC
-  schema version          the version of the database's layout
-  records                 the number of records
-  size of recorded files  their total size, in bytes, then rounded
-`
-
-	dwimHelp = `dwim runs what "sfdupes scan /" runs with the same flags, then what
-"sfdupes trees" runs. Run it as root, so that the scan can read every
-file. The scan is stored in the database, as scan stores it, so
-"sfdupes trees" prints the report again later.
-`
-)
-
-// errNoSubcommand is returned by the root command when it is invoked
-// without a subcommand. That is a usage error, and the usage text
-// cobra prints for it is the whole message.
-var errNoSubcommand = errors.New("no subcommand")
-
-// errWorkersBelowOne is the usage error for a --workers value below 1.
-var errWorkersBelowOne = errors.New("--workers must be at least 1")
-
-// errEmptyExcludeValue is the usage error for an empty --exclude value,
-// as from --exclude "$DIR" with DIR unset. Taken as a path, it
-// would name the working directory.
-var errEmptyExcludeValue = errors.New("--exclude must not be empty")
-
-// errEmptyOperand is the usage error for an empty PATH operand of
-// report or trees, as from "$DIR" with DIR unset. Taken as a path, it
-// would name the working directory.
-var errEmptyOperand = errors.New("PATH must not be empty")
-
-// Version is the build version, injected at link time via -ldflags
-// (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 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
-}
-
-// Main runs the command line in os.Args and returns the process exit
-// code.
-func Main() int {
-	// Once the reader of a stdout pipe has gone, as in "sfdupes report |
-	// head", the Go runtime ends the process with SIGPIPE on the next
-	// write instead of returning an error (README "Error handling").
-	// Registering for SIGPIPE with os/signal would change that.
-	return run(os.Args[1:], os.Stdout, os.Stderr)
-}
-
-// run executes args against the command tree and returns the process
-// exit code. It is the program's single exit point: the subcommands
-// return their errors instead of exiting, so every deferred cleanup —
-// above all closing the database, which checkpoints the SQLite WAL —
-// runs before the process ends. The report, trees, info and dwim
-// subcommands write their data to stdout.
-func run(args []string, stdout, stderr io.Writer) int {
-	// A nil slice makes cobra fall back to os.Args, which would let a
-	// test binary's own flags reach the command tree.
-	if args == nil {
-		args = []string{}
-	}
-
-	root := newRootCommand(stdout, stderr)
-	root.SetArgs(args)
-
-	err := root.Execute()
-
-	var fatal fatalError
-
-	switch {
-	case err == nil:
-		return exitOK
-	case errors.Is(err, errInterrupted):
-		// The interrupted scan has printed its own line.
-		return exitFatal
-	case errors.As(err, &fatal):
-		// The command ran and failed: a runtime error, reported
-		// without the usage text that a usage error gets.
-		_, _ = fmt.Fprintf(stderr, "sfdupes: %v\n", err)
-
-		return exitFatal
-	default:
-		// A usage error, which cobra has already reported on stderr.
-		return exitUsage
-	}
-}
-
-// newRootCommand builds the command tree. Everything on stdout is
-// machine-readable data, the version line included; all human-facing
-// output (help, usage, errors) goes to stderr.
-func newRootCommand(stdout, stderr io.Writer) *cobra.Command {
-	var showVersion bool
-
-	printVersion := runE(func(context.Context, []string) error {
-		info, _ := debug.ReadBuildInfo()
-
-		_, err := fmt.Fprintf(stdout, "sfdupes %s\n",
-			buildVersion(Version, info))
-		if err != nil {
-			return fmt.Errorf("write stdout: %w", err)
-		}
-
-		return nil
-	})
-
-	root := &cobra.Command{
-		Use:   "sfdupes",
-		Short: "Find candidate duplicate files by size and head/tail/content SHA-256",
-		Args:  cobra.NoArgs,
-		RunE: func(cmd *cobra.Command, args []string) error {
-			if showVersion {
-				return printVersion(cmd, args)
-			}
-
-			// A missing subcommand prints usage and exits 2: cobra
-			// prints the usage text for the returned error, and run
-			// maps everything that is not a fatal error to exit 2.
-			cmd.SilenceErrors = true
-
-			return errNoSubcommand
-		},
-	}
-	root.SetOut(stderr)
-	root.SetErr(stderr)
-	root.CompletionOptions.DisableDefaultCmd = true
-
-	// Cobra's built-in version flag prints through the help writer,
-	// stderr; this one prints to stdout.
-	root.Flags().BoolVarP(&showVersion, "version", "v", false,
-		"print the version to stdout")
-
-	reportCmd := &cobra.Command{
-		Use:   cmdReport + " [PATH...]",
-		Short: "Read the scan database and print the file-level duplicates report",
-		Args:  rejectEmptyOperand,
-		RunE: runE(func(ctx context.Context, args []string) error {
-			return runReport(ctx, args, stdout)
-		}),
-	}
-
-	treesCmd := &cobra.Command{
-		Use:   cmdTrees + " [PATH...]",
-		Short: "Read the scan database and print the duplicate-tree report",
-		Args:  rejectEmptyOperand,
-		RunE: runE(func(ctx context.Context, args []string) error {
-			return runTrees(ctx, args, stdout)
-		}),
-	}
-
-	infoCmd := &cobra.Command{
-		Use:   cmdInfo,
-		Short: "Read the scan database and print its details",
-		Args:  cobra.NoArgs,
-		RunE: runE(func(ctx context.Context, _ []string) error {
-			return runInfo(ctx, stdout)
-		}),
-	}
-
-	root.Long = root.Short + ".\n\n" + databaseHelp
-	reportCmd.Long = reportCmd.Short + ".\n\n" + reportHelp
-	treesCmd.Long = treesCmd.Short + ".\n\n" + treesHelp
-	infoCmd.Long = infoCmd.Short + ".\n\n" + infoHelp
-
-	root.AddCommand(newScanCommand(), reportCmd, treesCmd, infoCmd,
-		newDwimCommand(stdout))
-
-	return root
-}
-
-// scanOptions holds the values of the flags that scan and dwim share:
-// --workers, -x, --no-default-excludes and --exclude.
-type scanOptions struct {
-	workers           int
-	oneFS             bool
-	noDefaultExcludes bool
-	excludePaths      []string
-}
-
-// scanFlagsUsage names the flags that scan and dwim share, for their
-// usage lines.
-const scanFlagsUsage = "[--workers N] [-x] [--no-default-excludes] " +
-	"[--exclude PATH]..."
-
-// addScanFlags adds the flags that scan and dwim share to cmd, which
-// stores their values in opts.
-func addScanFlags(cmd *cobra.Command, opts *scanOptions) {
-	cmd.Flags().IntVar(&opts.workers, "workers", runtime.NumCPU(),
-		"concurrent workers for the walk and hash phases")
-	cmd.Flags().BoolVarP(&opts.oneFS, "one-file-system", "x", false,
-		"do not cross filesystem boundaries")
-	cmd.Flags().BoolVar(&opts.noDefaultExcludes, "no-default-excludes",
-		false, "enter the default excludes, the paths listed above")
-	// A string array, not a slice, so a comma in a path is not a
-	// separator.
-	cmd.Flags().StringArrayVar(&opts.excludePaths, "exclude", nil,
-		"never enter or record `PATH` or anything below it; repeatable")
-}
-
-// check rejects the flag values that are usage errors, before the
-// command runs. It is the PreRunE of scan and dwim.
-func (o *scanOptions) check(cmd *cobra.Command, _ []string) error {
-	err := checkScanWorkers(cmd, o.workers)
-	if err != nil {
-		return err
-	}
-
-	return rejectEmptyExcludeValue(cmd, o.excludePaths)
-}
-
-// newScanCommand builds the scan subcommand. Its help names the
-// database, and lists the default excludes of the system it runs on and
-// the filesystem types it never records anything on.
-func newScanCommand() *cobra.Command {
-	var opts scanOptions
-
-	short := "Walk trees and synchronize the scan database"
-
-	scanCmd := &cobra.Command{
-		Use: cmdScan + " " + scanFlagsUsage + " PATH...",
-		// The Use line already names every flag, so cobra must not
-		// append its generic "[flags]" to it.
-		DisableFlagsInUseLine: true,
-		Short:                 short,
-		Long: short + ".\n\n" + databaseHelp + "\n" +
-			defaultExcludesHelp(runtime.GOOS),
-		Args:    cobra.MinimumNArgs(1),
-		PreRunE: opts.check,
-		RunE: runE(func(ctx context.Context, args []string) error {
-			ctx, stop := interruptContext(ctx)
-			defer stop()
-
-			return runScan(ctx, args, opts)
-		}),
-	}
-	addScanFlags(scanCmd, &opts)
-
-	return scanCmd
-}
-
-// newDwimCommand builds the dwim subcommand, which takes the scan flags
-// with the meaning they have for scan. Its help says what dwim runs,
-// then lists the default excludes and the filesystem types the scan
-// never records anything on.
-func newDwimCommand(stdout io.Writer) *cobra.Command {
-	var opts scanOptions
-
-	short := "Scan /, then print the duplicate-tree report"
-
-	dwimCmd := &cobra.Command{
-		Use:                   cmdDwim + " " + scanFlagsUsage,
-		DisableFlagsInUseLine: true,
-		Short:                 short,
-		Long: short + ".\n\n" + dwimHelp + "\n" +
-			defaultExcludesHelp(runtime.GOOS),
-		Args:    cobra.NoArgs,
-		PreRunE: opts.check,
-		RunE: runE(func(ctx context.Context, _ []string) error {
-			return runDwim(ctx, "/", opts, stdout)
-		}),
-	}
-	addScanFlags(dwimCmd, &opts)
-
-	return dwimCmd
-}
-
-// checkScanWorkers rejects a --workers value below 1. That is a usage
-// error reported in one line: cobra prints the returned message without
-// the usage text, and run exits 2.
-func checkScanWorkers(cmd *cobra.Command, workers int) error {
-	if workers >= 1 {
-		return nil
-	}
-
-	cmd.SilenceUsage = true
-
-	return fmt.Errorf("%w, got %d", errWorkersBelowOne, workers)
-}
-
-// rejectEmptyExcludeValue rejects an empty --exclude value. That
-// is a usage error reported in one line, as for --workers below 1.
-func rejectEmptyExcludeValue(cmd *cobra.Command, excludePaths []string) error {
-	if !slices.Contains(excludePaths, "") {
-		return nil
-	}
-
-	cmd.SilenceUsage = true
-
-	return errEmptyExcludeValue
-}
-
-// rejectEmptyOperand rejects an empty PATH operand of report or trees.
-// That is a usage error reported in one line, as for --workers below 1.
-func rejectEmptyOperand(cmd *cobra.Command, args []string) error {
-	if !slices.Contains(args, "") {
-		return nil
-	}
-
-	cmd.SilenceUsage = true
-
-	return errEmptyOperand
-}
-
-// runE adapts a subcommand implementation, or the version print, to
-// cobra's RunE. Cobra prints the error and the command's usage text for
-// every error RunE returns, but a subcommand that ran and failed has no
-// usage problem to report: both are silenced here, and the error is
-// marked fatal so that run reports it on stderr and exits 1 rather than
-// 2. The command's context is handed to the implementation: cancelling
-// it unwinds the scan's worker pools.
-func runE(
-	fn func(ctx context.Context, args []string) error,
-) func(*cobra.Command, []string) error {
-	return func(cmd *cobra.Command, args []string) error {
-		cmd.SilenceUsage = true
-		cmd.SilenceErrors = true
-
-		err := fn(cmd.Context(), args)
-		if err != nil {
-			return fatalError{err: err}
-		}
-
-		return nil
-	}
-}
-
-// fatalError marks a runtime failure, as opposed to the usage errors
-// cobra itself produces while parsing arguments and flags. Both come
-// out of Execute as plain errors, so the wrapper is what tells run to
-// report this one as "sfdupes: ..." and exit 1.
-type fatalError struct {
-	err error
-}
-
-func (e fatalError) Error() string { return e.err.Error() }
-
-func (e fatalError) Unwrap() error { return e.err }

internal/sfdupes/dwim.go

@@ -1,38 +0,0 @@
-package sfdupes
-
-import (
-	"context"
-	"fmt"
-	"io"
-	"os"
-)
-
-// runDwim implements the dwim subcommand: it runs what "sfdupes scan
-// root" runs with the scan flags in opts, then what "sfdupes trees"
-// runs, and ends with a line on stderr saying how to print the report
-// again. The dwim command passes "/" as root. It catches SIGINT and
-// SIGTERM as scan does, but only during the scan. An error from the
-// scan, an interrupt included, ends it before the report. During the
-// report, a signal ends it at once, as it ends trees.
-func runDwim(
-	ctx context.Context, root string, opts scanOptions, stdout io.Writer,
-) error {
-	scanCtx, stop := interruptContext(ctx)
-	err := runScan(scanCtx, []string{root}, opts)
-
-	stop()
-
-	if err != nil {
-		return err
-	}
-
-	err = runTrees(ctx, nil, stdout)
-	if err != nil {
-		return err
-	}
-
-	fmt.Fprintln(os.Stderr,
-		`dwim: run "sfdupes trees" to print this report again`)
-
-	return nil
-}

internal/sfdupes/dwim_test.go

@@ -1,210 +0,0 @@
-package sfdupes //nolint:testpackage // calls the unexported runDwim
-
-import (
-	"bytes"
-	"errors"
-	"os"
-	"path/filepath"
-	"runtime"
-	"strings"
-	"testing"
-)
-
-func TestRunDwimPrintsLargestTreesFirst(t *testing.T) {
-	// dwim scans its root, then prints the trees report, the larger of
-	// two duplicate-tree pairs first, and ends by saying how to print
-	// the report again.
-	t.Setenv(databaseEnv, testDBPath(t))
-
-	root := realTempDir(t)
-
-	small := []string{
-		filepath.Dir(writeFile(t, root, "a1/f.bin", pattern(1, 300))),
-		filepath.Dir(writeFile(t, root, "a2/f.bin", pattern(1, 300))),
-	}
-	large := []string{
-		filepath.Dir(writeFile(t, root, "b1/f.bin", pattern(2, 5000))),
-		filepath.Dir(writeFile(t, root, "b2/f.bin", pattern(2, 5000))),
-	}
-
-	var stdout bytes.Buffer
-
-	stderr := captureStderr(t)
-
-	err := runDwim(t.Context(), root, scanOptions{workers: 1}, &stdout)
-	if err != nil {
-		t.Fatalf("runDwim: %v; stderr: %s", err, stderr())
-	}
-
-	lines := strings.Split(strings.TrimSuffix(stdout.String(), "\n"), "\n")
-	if len(lines) != 3 {
-		t.Fatalf("stdout = %q, want a header and two groups",
-			stdout.String())
-	}
-
-	wantFirst := large[0] + "\t" + large[1] + "\t1\t5000\t"
-	if !strings.HasPrefix(lines[1], wantFirst) {
-		t.Errorf("first group = %q, want it to start %q", lines[1], wantFirst)
-	}
-
-	wantSecond := small[0] + "\t" + small[1] + "\t1\t300\t"
-	if !strings.HasPrefix(lines[2], wantSecond) {
-		t.Errorf("second group = %q, want it to start %q",
-			lines[2], wantSecond)
-	}
-
-	last := "\ndwim: run \"sfdupes trees\" to print this report again\n"
-	if got := stderr(); !strings.HasSuffix(got, last) {
-		t.Errorf("stderr = %q, want it to end %q", got, last)
-	}
-}
-
-func TestRunDwimScanErrorPrintsNoReport(t *testing.T) {
-	// A fatal scan error ends dwim before the report: a root that does
-	// not exist fails the scan as it fails scan itself.
-	t.Setenv(databaseEnv, testDBPath(t))
-
-	missing := filepath.Join(realTempDir(t), "missing")
-
-	var stdout bytes.Buffer
-
-	stderr := captureStderr(t)
-
-	err := runDwim(t.Context(), missing, scanOptions{workers: 1}, &stdout)
-	if err == nil {
-		t.Fatal("runDwim on a missing root: error = nil, want it fatal")
-	}
-
-	if got := stdout.String(); got != "" {
-		t.Errorf("stdout = %q, want no report", got)
-	}
-
-	if got := stderr(); strings.Contains(got, "trees:") ||
-		strings.Contains(got, "dwim:") {
-		t.Errorf("stderr = %q, want nothing from trees or dwim", got)
-	}
-}
-
-func TestRunDwimExcludeLeavesTreeOut(t *testing.T) {
-	// dwim passes its --exclude paths to the scan: an excluded copy is
-	// not recorded, so its pair is not reported.
-	t.Setenv(databaseEnv, testDBPath(t))
-
-	root := realTempDir(t)
-
-	kept := []string{
-		filepath.Dir(writeFile(t, root, "a1/f.bin", pattern(1, 300))),
-		filepath.Dir(writeFile(t, root, "a2/f.bin", pattern(1, 300))),
-	}
-	writeFile(t, root, "b1/f.bin", pattern(2, 5000))
-	excluded := filepath.Dir(writeFile(t, root, "b2/f.bin", pattern(2, 5000)))
-
-	var stdout bytes.Buffer
-
-	stderr := captureStderr(t)
-
-	opts := scanOptions{workers: 1, excludePaths: []string{excluded}}
-
-	err := runDwim(t.Context(), root, opts, &stdout)
-	if err != nil {
-		t.Fatalf("runDwim: %v; stderr: %s", err, stderr())
-	}
-
-	lines := strings.Split(strings.TrimSuffix(stdout.String(), "\n"), "\n")
-	if len(lines) != 2 {
-		t.Fatalf("stdout = %q, want a header and one group",
-			stdout.String())
-	}
-
-	want := kept[0] + "\t" + kept[1] + "\t1\t300\t"
-	if !strings.HasPrefix(lines[1], want) {
-		t.Errorf("group = %q, want it to start %q", lines[1], want)
-	}
-
-	skipped := "scan: skipped " + excluded + " (--exclude)\n"
-	if got := stderr(); !strings.Contains(got, skipped) {
-		t.Errorf("stderr = %q, want it to contain %q", got, skipped)
-	}
-}
-
-func TestRunDwimTakesScanFlags(t *testing.T) {
-	// The dwim command parses and checks the scan flags as scan does.
-	// Each case stops before the walk of / begins, and before the
-	// database is created. "dwim --exclude /" excludes its own operand.
-	cases := map[string]struct {
-		args []string
-		code int
-		want string
-	}{
-		"--exclude /": {
-			[]string{cmdDwim, excludeFlag, "/"},
-			exitFatal,
-			"sfdupes: scan /: operand excluded by --exclude /\n",
-		},
-		"--exclude empty": {
-			[]string{cmdDwim, excludeFlag, ""},
-			exitUsage,
-			"Error: --exclude must not be empty\n",
-		},
-		"--workers 0": {
-			[]string{cmdDwim, workersFlag, "0", "-x", "--no-default-excludes"},
-			exitUsage,
-			"Error: --workers must be at least 1, got 0\n",
-		},
-	}
-
-	for name, tc := range cases {
-		t.Run(name, func(t *testing.T) {
-			path := testDBPath(t)
-			t.Setenv(databaseEnv, path)
-
-			stdout := captureStdout(t)
-			stderr := captureStderr(t)
-
-			code := run(tc.args, os.Stdout, os.Stderr)
-			if code != tc.code {
-				t.Errorf("run(%q) = %d, want %d", tc.args, code, tc.code)
-			}
-
-			if !strings.HasSuffix(stderr(), tc.want) || stdout() != "" {
-				t.Errorf("stdout, stderr = %q, %q, want \"\" and stderr "+
-					"ending %q", stdout(), stderr(), tc.want)
-			}
-
-			_, err := os.Lstat(path)
-			if !errors.Is(err, os.ErrNotExist) {
-				t.Errorf("lstat %s: %v, want no database", path, err)
-			}
-		})
-	}
-}
-
-func TestRunDwimHelpListsScanFlags(t *testing.T) {
-	t.Parallel()
-
-	// README "Subcommands" shows this usage line for dwim.
-	const want = "\n  sfdupes dwim [--workers N] [-x] [--no-default-excludes] " +
-		"[--exclude PATH]...\n"
-
-	var stdout, stderr bytes.Buffer
-
-	run([]string{cmdDwim, "-h"}, &stdout, &stderr)
-
-	if !strings.Contains(stderr.String(), want) {
-		t.Errorf("dwim -h stderr = %q, want the usage line %q",
-			stderr.String(), want)
-	}
-
-	if !strings.Contains(stderr.String(), excludeFlag+" PATH") {
-		t.Errorf("dwim -h stderr = %q, want %s PATH", stderr.String(),
-			excludeFlag)
-	}
-
-	// README "Settings": the help lists the default excludes and the
-	// filesystem types the walk never records anything on.
-	help := strings.TrimSpace(defaultExcludesHelp(runtime.GOOS))
-	if !strings.Contains(stderr.String(), help) {
-		t.Errorf("dwim -h stderr = %q, want it to hold %q", stderr.String(),
-			help)
-	}
-}

main.go

@@ -0,0 +1,294 @@
+// 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 three SHA-256 hashes: of the first 64 KiB, of the last 64
+// KiB, and of the content. The content hash covers the whole file under
+// 100 MiB, and 1 MiB at each gigabyte at 100 MiB or more, so a large
+// file is never read in full. scan maintains a persistent SQLite
+// database of file signatures (SFDUPES_DATABASE, default
+// /var/lib/sfdupes/db.sqlite) that the other subcommands read.
+//
+// Usage:
+//
+//	sfdupes scan [--workers N] [-x] [--no-default-excludes] PATH...
+//	sfdupes report > dupes.tsv
+//	sfdupes trees > dupetrees.tsv
+//	sfdupes info
+//	sfdupes --version
+//
+// See README.md for the complete specification.
+package main
+
+import (
+	"context"
+	"errors"
+	"fmt"
+	"io"
+	"os"
+	"runtime"
+	"runtime/debug"
+
+	"github.com/spf13/cobra"
+)
+
+// Exit codes: exitOK is success (even with per-file warnings),
+// exitFatal is a fatal error, exitUsage is a usage error.
+const (
+	exitOK    = 0
+	exitFatal = 1
+	exitUsage = 2
+)
+
+// The subcommand names, as typed on the command line.
+const (
+	cmdScan   = "scan"
+	cmdReport = "report"
+	cmdTrees  = "trees"
+	cmdInfo   = "info"
+)
+
+// errNoSubcommand is returned by the root command when it is invoked
+// without a subcommand. That is a usage error, and the usage text
+// cobra prints for it is the whole message.
+var errNoSubcommand = errors.New("no subcommand")
+
+// errWorkersBelowOne is the usage error for a scan --workers value
+// below 1.
+var errWorkersBelowOne = errors.New("--workers must be at least 1")
+
+// Version is the build version, injected at link time via -ldflags
+// (see the Makefile); 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 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 |
+	// head", the Go runtime ends the process with SIGPIPE on the next
+	// write instead of returning an error (README "Error handling").
+	// Registering for SIGPIPE with os/signal would change that.
+	os.Exit(run(os.Args[1:], os.Stdout, os.Stderr))
+}
+
+// run executes args against the command tree and returns the process
+// exit code. It is the program's single exit point: the subcommands
+// return their errors instead of exiting, so every deferred cleanup —
+// above all closing the database, which checkpoints the SQLite WAL —
+// runs before the process ends. The report, trees and info subcommands
+// write their data to stdout.
+func run(args []string, stdout, stderr io.Writer) int {
+	// A nil slice makes cobra fall back to os.Args, which would let a
+	// test binary's own flags reach the command tree.
+	if args == nil {
+		args = []string{}
+	}
+
+	root := newRootCommand(stdout, stderr)
+	root.SetArgs(args)
+
+	err := root.Execute()
+
+	var fatal fatalError
+
+	switch {
+	case err == nil:
+		return exitOK
+	case errors.Is(err, errInterrupted):
+		// The interrupted scan has printed its own line.
+		return exitFatal
+	case errors.As(err, &fatal):
+		// The command ran and failed: a runtime error, reported
+		// without the usage text that a usage error gets.
+		_, _ = fmt.Fprintf(stderr, "sfdupes: %v\n", err)
+
+		return exitFatal
+	default:
+		// A usage error, which cobra has already reported on stderr.
+		return exitUsage
+	}
+}
+
+// newRootCommand builds the command tree. Everything on stdout is
+// machine-readable data, the version line included; all human-facing
+// output (help, usage, errors) goes to stderr.
+func newRootCommand(stdout, stderr io.Writer) *cobra.Command {
+	var showVersion bool
+
+	printVersion := runE(func(context.Context, []string) error {
+		info, _ := debug.ReadBuildInfo()
+
+		_, err := fmt.Fprintf(stdout, "sfdupes %s\n",
+			buildVersion(Version, info))
+		if err != nil {
+			return fmt.Errorf("write stdout: %w", err)
+		}
+
+		return nil
+	})
+
+	root := &cobra.Command{
+		Use:   "sfdupes",
+		Short: "Find candidate duplicate files by size and head/tail/content SHA-256",
+		Args:  cobra.NoArgs,
+		RunE: func(cmd *cobra.Command, args []string) error {
+			if showVersion {
+				return printVersion(cmd, args)
+			}
+
+			// A missing subcommand prints usage and exits 2: cobra
+			// prints the usage text for the returned error, and run
+			// maps everything that is not a fatal error to exit 2.
+			cmd.SilenceErrors = true
+
+			return errNoSubcommand
+		},
+	}
+	root.SetOut(stderr)
+	root.SetErr(stderr)
+	root.CompletionOptions.DisableDefaultCmd = true
+
+	// Cobra's built-in version flag prints through the help writer,
+	// stderr; this one prints to stdout.
+	root.Flags().BoolVarP(&showVersion, "version", "v", false,
+		"print the version to stdout")
+
+	reportCmd := &cobra.Command{
+		Use:   cmdReport,
+		Short: "Read the scan database and print the file-level duplicates report",
+		Args:  cobra.NoArgs,
+		RunE: runE(func(ctx context.Context, _ []string) error {
+			return runReport(ctx, stdout)
+		}),
+	}
+
+	treesCmd := &cobra.Command{
+		Use:   cmdTrees,
+		Short: "Read the scan database and print the duplicate-tree report",
+		Args:  cobra.NoArgs,
+		RunE: runE(func(ctx context.Context, _ []string) error {
+			return runTrees(ctx, stdout)
+		}),
+	}
+
+	infoCmd := &cobra.Command{
+		Use:   cmdInfo,
+		Short: "Read the scan database and print its details",
+		Args:  cobra.NoArgs,
+		RunE: runE(func(ctx context.Context, _ []string) error {
+			return runInfo(ctx, stdout)
+		}),
+	}
+
+	root.AddCommand(newScanCommand(), reportCmd, treesCmd, infoCmd)
+
+	return root
+}
+
+// newScanCommand builds the scan subcommand, with its --workers, -x and
+// --no-default-excludes flags. Its help lists the default excludes of
+// the system it runs on, and the filesystem types it never records
+// anything on.
+func newScanCommand() *cobra.Command {
+	var (
+		scanWorkers           int
+		scanOneFS             bool
+		scanNoDefaultExcludes bool
+	)
+
+	short := "Walk trees and synchronize the scan database"
+
+	scanCmd := &cobra.Command{
+		Use:   cmdScan + " [--workers N] [-x] [--no-default-excludes] PATH...",
+		Short: short,
+		Long:  short + ".\n\n" + defaultExcludesHelp(runtime.GOOS),
+		Args:  cobra.MinimumNArgs(1),
+		PreRunE: func(cmd *cobra.Command, _ []string) error {
+			return checkScanWorkers(cmd, scanWorkers)
+		},
+		RunE: runE(func(ctx context.Context, args []string) error {
+			ctx, stop := interruptContext(ctx)
+			defer stop()
+
+			return runScan(ctx, args, scanWorkers, scanOneFS,
+				scanNoDefaultExcludes)
+		}),
+	}
+	scanCmd.Flags().IntVar(&scanWorkers, "workers", runtime.NumCPU(),
+		"concurrent workers for the walk and hash phases")
+	scanCmd.Flags().BoolVarP(&scanOneFS, "one-file-system", "x", false,
+		"do not cross filesystem boundaries")
+	scanCmd.Flags().BoolVar(&scanNoDefaultExcludes, "no-default-excludes",
+		false, "enter the default excludes, the paths listed above")
+
+	return scanCmd
+}
+
+// checkScanWorkers rejects a scan --workers value below 1. That is a
+// usage error reported in one line: cobra prints the returned message
+// without the usage text, and run exits 2.
+func checkScanWorkers(cmd *cobra.Command, workers int) error {
+	if workers >= 1 {
+		return nil
+	}
+
+	cmd.SilenceUsage = true
+
+	return fmt.Errorf("%w, got %d", errWorkersBelowOne, workers)
+}
+
+// runE adapts a subcommand implementation, or the version print, to
+// cobra's RunE. Cobra prints the error and the command's usage text for
+// every error RunE returns, but a subcommand that ran and failed has no
+// usage problem to report: both are silenced here, and the error is
+// marked fatal so that run reports it on stderr and exits 1 rather than
+// 2. The command's context is handed to the implementation: cancelling
+// it unwinds the scan's worker pools.
+func runE(
+	fn func(ctx context.Context, args []string) error,
+) func(*cobra.Command, []string) error {
+	return func(cmd *cobra.Command, args []string) error {
+		cmd.SilenceUsage = true
+		cmd.SilenceErrors = true
+
+		err := fn(cmd.Context(), args)
+		if err != nil {
+			return fatalError{err: err}
+		}
+
+		return nil
+	}
+}
+
+// fatalError marks a runtime failure, as opposed to the usage errors
+// cobra itself produces while parsing arguments and flags. Both come
+// out of Execute as plain errors, so the wrapper is what tells run to
+// report this one as "sfdupes: ..." and exit 1.
+type fatalError struct {
+	err error
+}
+
+func (e fatalError) Error() string { return e.err.Error() }
+
+func (e fatalError) Unwrap() error { return e.err }

main_test.go

@@ -1,4 +1,4 @@
-package sfdupes //nolint:testpackage // drives the unexported run
+package main
 
 import (
 	"bytes"
@@ -14,20 +14,12 @@ import (
 	"strconv"
 	"strings"
 	"testing"
-
-	"golang.org/x/sys/unix"
 )
 
 // usageMarker is the first line of cobra's usage text, which a usage
 // error prints and a runtime failure must not.
 const usageMarker = "Usage:"
 
-// helpFlag asks for the help text.
-const helpFlag = "--help"
-
-// workersFlag is the scan and dwim flag that sets the worker count.
-const workersFlag = "--workers"
-
 // TestMain stops the tests at once, saying why, when their temporary
 // directory is not on a persistent filesystem: scan records nothing
 // there (README "Rules for the walk"), so most scan tests would fail
@@ -576,21 +568,20 @@ func TestRunNamesDefaultDatabase(t *testing.T) {
 	}{
 		cmdScan: {
 			run: func() error {
-				return runScan(t.Context(), []string{missing},
+				return runScan(t.Context(), []string{missing}, 1, false, false)
-					scanOptions{workers: 1})
 			},
 			want: scanWant,
 		},
 		cmdReport: {
 			run: func() error {
-				return runReport(cancelledContext(t), nil, io.Discard)
+				return runReport(cancelledContext(t), io.Discard)
 			},
 			want: "report: database " + defaultDatabasePath + " (default)\n" +
 				reportOpenLine + "\n" + reportOpenLine + "\n",
 		},
 		cmdTrees: {
 			run: func() error {
-				return runTrees(cancelledContext(t), nil, io.Discard)
+				return runTrees(cancelledContext(t), io.Discard)
 			},
 			want: "trees: database " + defaultDatabasePath + " (default)\n" +
 				treesOpenLine + "\n" + treesOpenLine + "\n",
@@ -626,8 +617,9 @@ func TestRunUsageErrors(t *testing.T) {
 	}{
 		"no subcommand":      {[]string{}, usageMarker},
 		"scan without paths": {[]string{cmdScan}, usageMarker},
+		"report with args":   {[]string{cmdReport, "x"}, usageMarker},
+		"trees with args":    {[]string{cmdTrees, "x"}, usageMarker},
 		"info with args":     {[]string{cmdInfo, "x"}, usageMarker},
-		"dwim with args":     {[]string{cmdDwim, "x"}, usageMarker},
 		"unknown flag":       {[]string{cmdScan, "--nope", "/"}, usageMarker},
 		"unknown subcommand": {[]string{"nope"}, "unknown command"},
 	}
@@ -666,7 +658,7 @@ func TestRunScanRejectsWorkersBelowOne(t *testing.T) {
 
 			var stdout, stderr bytes.Buffer
 
-			args := []string{cmdScan, workersFlag, workers, t.TempDir()}
+			args := []string{cmdScan, "--workers", workers, t.TempDir()}
 
 			code := run(args, &stdout, &stderr)
 			if code != exitUsage {
@@ -697,7 +689,7 @@ func TestRunHelp(t *testing.T) {
 
 	// README §Settings: help goes to stderr, exits 0, and leaves stdout
 	// empty.
-	cases := [][]string{{helpFlag}, {"-h"}, {cmdScan, helpFlag}}
+	cases := [][]string{{"--help"}, {"-h"}, {cmdScan, "--help"}}
 
 	for _, args := range cases {
 		var stdout, stderr bytes.Buffer
@@ -717,117 +709,6 @@ func TestRunHelp(t *testing.T) {
 				args, got)
 		}
 	}
-
-	// The scan help lists --exclude with its argument.
-	var stdout, stderr bytes.Buffer
-
-	run([]string{cmdScan, "-h"}, &stdout, &stderr)
-
-	if !strings.Contains(stderr.String(), excludeFlag+" PATH") {
-		t.Errorf("scan -h stderr = %q, want %s PATH", stderr.String(),
-			excludeFlag)
-	}
-}
-
-func TestRunScanUsageLine(t *testing.T) {
-	t.Parallel()
-
-	// README §Subcommands shows this usage line for scan, and the help
-	// and the usage error both print it.
-	const want = "\n  sfdupes scan [--workers N] [-x] [--no-default-excludes] " +
-		"[--exclude PATH]... PATH...\n"
-
-	cases := map[string][]string{
-		"help":          {cmdScan, "-h"},
-		"missing paths": {cmdScan},
-	}
-
-	for name, args := range cases {
-		t.Run(name, func(t *testing.T) {
-			t.Parallel()
-
-			var stdout, stderr bytes.Buffer
-
-			run(args, &stdout, &stderr)
-
-			if !strings.Contains(stderr.String(), want) {
-				t.Errorf("run(%v) stderr = %q, want the usage line %q",
-					args, stderr.String(), want)
-			}
-		})
-	}
-}
-
-func TestRunHelpDescribesDatabaseAndOutput(t *testing.T) {
-	t.Parallel()
-
-	// README §Settings: the help names the database, and says what
-	// report, trees, info and dwim print. The help of report and trees
-	// also explains their PATH operands.
-	database := []string{
-		"scan and dwim store", databaseEnv, defaultDatabasePath, "needs root",
-	}
-	escapes := []string{`\\`, `\t`, `\n`, `\r`}
-	operands := []string{
-		"With PATH operands", "at or below them", "working directory",
-		"No PATH is looked up", "not followed",
-	}
-
-	// The subcommand whose help is printed; none for the root.
-	cases := []struct {
-		subcommand []string
-		want       []string
-	}{
-		{nil, database},
-		{[]string{cmdScan}, database},
-		{
-			[]string{cmdReport},
-			slices.Concat([]string{
-				"tab-separated", "\n  first ", "\n  dupe ", "\n  size ",
-				"largest first",
-			}, escapes, operands),
-		},
-		{
-			[]string{cmdTrees},
-			slices.Concat([]string{
-				"tab-separated", "\n  first ", "\n  dupe ", "\n  files ",
-				"\n  size ", "\n  disk_size ", "largest first",
-			}, escapes, operands),
-		},
-		{
-			[]string{cmdInfo},
-			[]string{
-				"\n  database ", "\n  database file size ",
-				"\n  -wal file size ", "\n  modified ",
-				"\n  schema version ", "\n  records ",
-				"\n  size of recorded files ",
-			},
-		},
-		{
-			[]string{cmdDwim},
-			[]string{
-				"sfdupes scan /", "as root", "sfdupes trees", "database",
-			},
-		},
-	}
-
-	for _, tc := range cases {
-		var stdout, stderr bytes.Buffer
-
-		args := slices.Concat(tc.subcommand, []string{helpFlag})
-
-		code := run(args, &stdout, &stderr)
-		if code != exitOK {
-			t.Fatalf("run(%v) = %d, want %d", args, code, exitOK)
-		}
-
-		for _, want := range tc.want {
-			if !strings.Contains(stderr.String(), want) {
-				t.Errorf("run(%v) help lacks %q:\n%s",
-					args, want, stderr.String())
-			}
-		}
-	}
 }
 
 func TestRunVersion(t *testing.T) {
@@ -916,7 +797,7 @@ func TestRunVersionWriteFailureIsFatal(t *testing.T) {
 func scanFixture(t *testing.T) []string {
 	t.Helper()
 
-	dir := realTempDir(t)
+	dir := t.TempDir()
 
 	dupes := []string{
 		writeFile(t, dir, "one/a.bin", pattern(1, 300)),
@@ -986,7 +867,7 @@ func TestRunScanSucceedsDespiteWarnings(t *testing.T) {
 	path := testDBPath(t)
 	t.Setenv(databaseEnv, path)
 
-	dir := realTempDir(t)
+	dir := t.TempDir()
 	writeFile(t, dir, "a.bin", pattern(1, 300))
 
 	// Same size as a.bin, so the scan reads it, and the read fails.
@@ -1014,278 +895,58 @@ func TestRunScanSucceedsDespiteWarnings(t *testing.T) {
 	assertNoSidecars(t, path)
 }
 
-// realTempDir returns a new temporary directory by its real path, so
+func TestRunScanSkipsSymlinkOperand(t *testing.T) {
-// tests hold where the temporary directory is reached through a
-// symlink.
-func realTempDir(t *testing.T) string {
-	t.Helper()
-
-	dir, err := filepath.EvalSymlinks(t.TempDir())
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	return dir
-}
-
-// symlink creates link pointing at target.
-func symlink(t *testing.T, target, link string) {
-	t.Helper()
-
-	err := os.Symlink(target, link)
-	if err != nil {
-		t.Fatal(err)
-	}
-}
-
-// TestRunScanFollowsSymlinkOperand scans link, a symlink to target.
-// The operand is scanned at its real path, and its file is recorded
-// there.
-func TestRunScanFollowsSymlinkOperand(t *testing.T) {
 	path := testDBPath(t)
 	t.Setenv(databaseEnv, path)
 
-	dir := realTempDir(t)
+	dir := t.TempDir()
-	f := writeFile(t, dir, "target/sub/f", pattern(1, 10))
+	writeFile(t, dir, "target/sub/f", pattern(1, 10))
 
 	link := filepath.Join(dir, "link")
-	symlink(t, filepath.Join(dir, "target"), link)
 
-	stderr := scanOK(t, link)
+	err := os.Symlink(filepath.Join(dir, "target"), link)
-
+	if err != nil {
-	summary := "scan: 1 files seen (1 added, 0 updated, 0 removed, " +
+		t.Fatal(err)
-		"0 unchanged), 0 skipped\n"
-	if !strings.Contains(stderr, summary) {
-		t.Errorf("stderr = %q, want %q", stderr, summary)
 	}
 
-	if got := storedPaths(t, path); !slices.Equal(got, []string{f}) {
+	// Scanning a directory through the symlink stores a record beneath
-		t.Errorf("records = %q, want %q", got, []string{f})
+	// the symlink's own path for a file beneath its target.
-	}
+	scanOK(t, filepath.Join(link, "sub"))
+
+	assertOperandSkipped(t, path, link, "symlink",
+		filepath.Join(link, "sub", "f"))
 }
 
-// TestRunScanWalksOperandUnderSymlinkOperand scans link and link/sub,
-// with link a symlink to target. Both resolve under target, so
-// target/sub is walked once, as part of target.
 func TestRunScanWalksOperandUnderSymlinkOperand(t *testing.T) {
 	path := testDBPath(t)
 	t.Setenv(databaseEnv, path)
 
-	dir := realTempDir(t)
+	dir := t.TempDir()
-	f := writeFile(t, dir, "target/sub/f", pattern(1, 10))
+	writeFile(t, dir, "target/sub/f", pattern(1, 10))
 
 	link := filepath.Join(dir, "link")
-	symlink(t, filepath.Join(dir, "target"), link)
 
-	stderr := scanOK(t, link, filepath.Join(link, "sub"))
+	err := os.Symlink(filepath.Join(dir, "target"), link)
-
-	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)
-	}
-
-	if got := storedPaths(t, path); !slices.Equal(got, []string{f}) {
-		t.Errorf("records = %q, want %q", got, []string{f})
-	}
-}
-
-// TestRunScanWalksSymlinkedOperandBelowOperand is the case of
-// https://git.eeqj.de/sneak/sfdupes/issues/144: scan dir dir/link/sub,
-// with dir/link a symlink to a directory outside dir. The walk of dir
-// does not follow link, so dir/link/sub is walked on its own at its
-// real path, and the record an earlier scan stored there survives.
-func TestRunScanWalksSymlinkedOperandBelowOperand(t *testing.T) {
-	path := testDBPath(t)
-	t.Setenv(databaseEnv, path)
-
-	dir := realTempDir(t)
-	a := writeFile(t, dir, "a", pattern(1, 10))
-
-	outside := realTempDir(t)
-	f := writeFile(t, outside, "sub/f", pattern(2, 10))
-
-	symlink(t, outside, filepath.Join(dir, "link"))
-
-	scanOK(t, filepath.Join(outside, "sub"))
-
-	stderr := scanOK(t, dir, filepath.Join(dir, "link", "sub"))
-
-	summary := "scan: 2 files seen (1 added, 0 updated, 0 removed, " +
-		"1 unchanged), 0 skipped\n"
-	if !strings.Contains(stderr, summary) {
-		t.Errorf("stderr = %q, want %q", stderr, summary)
-	}
-
-	want := []string{a, f}
-	slices.Sort(want)
-
-	if got := storedPaths(t, path); !slices.Equal(got, want) {
-		t.Errorf("records = %q, want %q", got, want)
-	}
-}
-
-// TestRunScanDropsSymlinkOperandInsideOperand scans dir and link, with
-// link, outside dir, a symlink to dir/real. link resolves inside dir,
-// so it is dropped as covered by dir, and its file is recorded once.
-func TestRunScanDropsSymlinkOperandInsideOperand(t *testing.T) {
-	path := testDBPath(t)
-	t.Setenv(databaseEnv, path)
-
-	dir := realTempDir(t)
-	f := writeFile(t, dir, "real/f", pattern(1, 10))
-
-	link := filepath.Join(realTempDir(t), "link")
-	symlink(t, filepath.Join(dir, "real"), link)
-
-	stderr := scanOK(t, dir, link)
-
-	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)
-	}
-
-	if got := storedPaths(t, path); !slices.Equal(got, []string{f}) {
-		t.Errorf("records = %q, want %q", got, []string{f})
-	}
-}
-
-// TestRunScanDanglingSymlinkOperandIsFatal scans a valid directory and
-// a symlink whose target does not exist. The scan fails with exit 1 and
-// an error naming the symlink as given, before it walks anything, so no
-// database is created.
-func TestRunScanDanglingSymlinkOperandIsFatal(t *testing.T) {
-	path := testDBPath(t)
-	t.Setenv(databaseEnv, path)
-
-	dir := realTempDir(t)
-	writeFile(t, dir, "f", pattern(1, 10))
-
-	dangling := filepath.Join(realTempDir(t), "dangling")
-	symlink(t, filepath.Join(dir, "missing"), dangling)
-
-	stdout := captureStdout(t)
-
-	var stderr bytes.Buffer
-
-	code := run([]string{cmdScan, dir, dangling}, os.Stdout, &stderr)
-	if code != exitFatal {
-		t.Errorf("run(scan %s %s) = %d, want %d", dir, dangling, code,
-			exitFatal)
-	}
-
-	assertFatalOutput(t, stderr.String(), stdout())
-
-	want := "sfdupes: resolve " + dangling + ": "
-	if !strings.Contains(stderr.String(), want) {
-		t.Errorf("stderr = %q, want %q", stderr.String(), want)
-	}
-
-	_, err := os.Stat(path)
-	if !errors.Is(err, fs.ErrNotExist) {
-		t.Errorf("database: stat error %v, want it missing", err)
-	}
-}
-
-// TestRunScanFromSymlinkedWorkingDirectoryRecordsRealPath runs scan .
-// after a cd through home/proj, a symlink to data/proj. The file is
-// recorded under data/proj, its real path.
-func TestRunScanFromSymlinkedWorkingDirectoryRecordsRealPath(t *testing.T) {
-	path := testDBPath(t)
-	t.Setenv(databaseEnv, path)
-
-	dir := realTempDir(t)
-	f := writeFile(t, dir, "data/proj/f", pattern(1, 10))
-
-	err := os.Mkdir(filepath.Join(dir, "home"), 0o750)
 	if err != nil {
 		t.Fatal(err)
 	}
 
-	symlink(t, filepath.Join(dir, "data", "proj"),
+	// link is dropped as a symlink, but link/sub must still be scanned,
-		filepath.Join(dir, "home", "proj"))
+	// not dropped as lying under link.
+	scanOK(t, link, filepath.Join(link, "sub"))
 
-	// t.Chdir also sets PWD to the path through the symlink, as a
+	db, err := openDB(path, reportParams)
-	// shell does after cd.
-	t.Chdir(filepath.Join(dir, "home", "proj"))
-
-	scanOK(t, ".")
-
-	if got := storedPaths(t, path); !slices.Equal(got, []string{f}) {
-		t.Errorf("records = %q, want %q", got, []string{f})
-	}
-}
-
-// TestRunScanFollowsSymlinkBeforeDotDot scans a path with a ".." after
-// home/proj, a symlink to data/proj: home/proj/.. from dir, and .. after
-// a cd through home/proj. As with realpath, the ".." counts from
-// data/proj, so data is scanned and home is not.
-func TestRunScanFollowsSymlinkBeforeDotDot(t *testing.T) {
-	for _, tc := range []struct{ wd, operand string }{
-		{"", "home/proj/.."},
-		{"home/proj", ".."},
-	} {
-		t.Run(tc.operand, func(t *testing.T) {
-			path := testDBPath(t)
-			t.Setenv(databaseEnv, path)
-
-			dir := realTempDir(t)
-			f := writeFile(t, dir, "data/proj/f", pattern(1, 10))
-			g := writeFile(t, dir, "data/g", pattern(2, 10))
-			writeFile(t, dir, "home/h", pattern(3, 10))
-			symlink(t, filepath.Join(dir, "data", "proj"),
-				filepath.Join(dir, "home", "proj"))
-
-			// t.Chdir also sets PWD to the path given, as a shell does
-			// after cd.
-			t.Chdir(filepath.Join(dir, tc.wd))
-
-			scanOK(t, tc.operand)
-
-			want := []string{f, g}
-			slices.Sort(want)
-
-			if got := storedPaths(t, path); !slices.Equal(got, want) {
-				t.Errorf("records = %q, want %q", got, want)
-			}
-		})
-	}
-}
-
-// TestRunScanSkipsSymlinkToFIFOOperand scans link, a symlink to a FIFO.
-// The scan warns about the FIFO by its real path, counts it as skipped,
-// and exits 0.
-func TestRunScanSkipsSymlinkToFIFOOperand(t *testing.T) {
-	t.Setenv(databaseEnv, testDBPath(t))
-
-	dir := realTempDir(t)
-	fifo := filepath.Join(dir, "fifo")
-
-	err := unix.Mkfifo(fifo, 0o600)
 	if err != nil {
 		t.Fatal(err)
 	}
 
-	link := filepath.Join(dir, "link")
+	t.Cleanup(func() { _ = db.Close() })
-	symlink(t, fifo, link)
 
-	stderr := scanOK(t, link)
+	recordByPath(t, dbRecords(t, db), filepath.Join(link, "sub", "f"))
-
-	warning := "walk " + fifo + ": skipping FIFO operand\n"
-	if !strings.Contains(stderr, warning) {
-		t.Errorf("stderr = %q, want %q", stderr, warning)
-	}
-
-	summary := "scan: 0 files seen (0 added, 0 updated, 0 removed, " +
-		"0 unchanged), 1 skipped\n"
-	if !strings.Contains(stderr, summary) {
-		t.Errorf("stderr = %q, want %q", stderr, summary)
-	}
 }
 
 func TestRunScanSkipsZFSOperand(t *testing.T) {
-	zfs := filepath.Join(realTempDir(t), ".zfs")
+	zfs := filepath.Join(t.TempDir(), ".zfs")
 	f := writeFile(t, zfs, "snapshot/hourly/f", pattern(1, 10))
 
 	// No scan records a file inside a .zfs directory, so the record
@@ -1336,7 +997,7 @@ func TestRunScanSkipsOperandInsideZFS(t *testing.T) {
 	path := testDBPath(t)
 	t.Setenv(databaseEnv, path)
 
-	dir := realTempDir(t)
+	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))
@@ -1380,19 +1041,23 @@ func TestRunScanSkipsOperandInsideZFS(t *testing.T) {
 
 // TestRunScanSkipsOperandThroughSymlinkIntoZFS scans snaps/daily, where
 // snaps is a symlink to pool/.zfs/snapshot. The operand is warned about
-// by its real path, counted as skipped, and not walked.
+// by the path given, counted as skipped, and not walked.
 func TestRunScanSkipsOperandThroughSymlinkIntoZFS(t *testing.T) {
 	t.Setenv(databaseEnv, testDBPath(t))
 
-	dir := realTempDir(t)
+	dir := t.TempDir()
 	writeFile(t, dir, "pool/.zfs/snapshot/daily/f", pattern(1, 10))
 
 	snaps := filepath.Join(dir, "snaps")
-	symlink(t, filepath.Join(dir, "pool", ".zfs", "snapshot"), snaps)
 
-	stderr := scanOK(t, filepath.Join(snaps, "daily"))
+	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)
 
-	daily := filepath.Join(dir, "pool", ".zfs", "snapshot", "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"
@@ -1404,19 +1069,24 @@ func TestRunScanSkipsOperandThroughSymlinkIntoZFS(t *testing.T) {
 }
 
 // TestRunScanWalksOperandThroughSymlink scans data/daily, where data is
-// a symlink to pool/data. The operand is scanned as usual, and its file
+// a symlink to a directory outside any .zfs directory. The operand is
-// is recorded by its real path.
+// 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 := realTempDir(t)
+	dir := t.TempDir()
-	f := writeFile(t, dir, "pool/data/daily/f", pattern(1, 10))
+	writeFile(t, dir, "pool/data/daily/f", pattern(1, 10))
 
 	data := filepath.Join(dir, "data")
-	symlink(t, filepath.Join(dir, "pool", "data"), data)
 
-	stderr := scanOK(t, filepath.Join(data, "daily"))
+	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"
@@ -1424,9 +1094,14 @@ func TestRunScanWalksOperandThroughSymlink(t *testing.T) {
 		t.Errorf("stderr = %q, want %q", stderr, summary)
 	}
 
-	if got := storedPaths(t, path); !slices.Equal(got, []string{f}) {
+	db, err := openDB(path, reportParams)
-		t.Errorf("records = %q, want %q", got, []string{f})
+	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) {
@@ -1842,12 +1517,8 @@ func TestStdoutWriteErrorPropagates(t *testing.T) {
 	scanFixture(t)
 
 	cases := map[string]func(context.Context, io.Writer) error{
-		cmdReport: func(ctx context.Context, w io.Writer) error {
+		cmdReport: runReport,
-			return runReport(ctx, nil, w)
+		cmdTrees:  runTrees,
-		},
-		cmdTrees: func(ctx context.Context, w io.Writer) error {
-			return runTrees(ctx, nil, w)
-		},
 		cmdInfo:   runInfo,
 	}
 

progress.go

@@ -1,4 +1,4 @@
-package sfdupes
+package main
 
 import (
 	"fmt"

progress_test.go

@@ -1,4 +1,4 @@
-package sfdupes //nolint:testpackage // drives the unexported startProgress
+package main
 
 import (
 	"fmt"
@@ -642,9 +642,9 @@ func TestTerminalStalledLines(t *testing.T) {
 		{label: scanPhase("hash"), stalledOn: hashStalledOn},
 		{label: scanPhase("update"), stalledOn: "db"},
 		{label: treesPhase("read"), stalledOn: "db"},
-		{label: treesPhase("group"), stalledOn: "cpu/disk"},
+		{label: treesPhase("group"), stalledOn: "cpu"},
 		{label: treesPhase("write"), stalledOn: "out"},
-		{label: reportPhase("read"), stalledOn: "db/disk/out"},
+		{label: reportPhase("read"), stalledOn: "db/out"},
 	}
 
 	for _, params := range phases {

report.go

@@ -1,18 +1,14 @@
-package sfdupes
+package main
 
 import (
 	"context"
 	"crypto/sha256"
 	"database/sql"
-	"errors"
 	"fmt"
 	"io"
-	"io/fs"
 	"os"
-	"path/filepath"
 	"slices"
 	"strings"
-	"syscall"
 	"time"
 )
 
@@ -45,10 +41,8 @@ func reportPhase(name string) string {
 }
 
 // runReport implements the report subcommand: it prints the file-level
-// duplicates report as TSV on stdout, from the records at or below the
+// duplicates report as TSV on stdout. It never touches the scanned
-// operands in args, or from every record when args is empty. Of the
+// filesystem; its only I/O is the database, stdout, and stderr. It
-// scanned filesystem it only checks, with pathExists, that each path in
-// a duplicate group is still there; it never looks up an operand. It
 // names the database on stderr before it opens it. Any database
 // problem, including a missing database, is fatal.
 //
@@ -58,12 +52,7 @@ func reportPhase(name string) string {
 // order, writing each size's duplicate groups to stdout once that size
 // is read; see readReport). Each display ends before the next phase
 // starts, and before an error is returned to be printed.
-func runReport(ctx context.Context, args []string, stdout io.Writer) error {
+func runReport(ctx context.Context, stdout io.Writer) error {
-	operands, err := cleanOperands(args)
-	if err != nil {
-		return err
-	}
-
 	dbPath, source, err := databasePath()
 	if err != nil {
 		return err
@@ -88,15 +77,13 @@ func runReport(ctx context.Context, args []string, stdout io.Writer) error {
 
 	defer func() { _ = db.Close() }()
 
-	// The read phase checks the paths of each duplicate group on disk
+	// The read phase writes the report to stdout while it reads the
-	// and writes the report to stdout while it reads the records, so it
+	// records, so it may wait on either.
-	// may wait on any of the three.
 	prog = newProgress(progressParams{
 		label: reportPhase("read"), unit: "records", total: -1,
-		waitingFor: countingRecords, stalledOn: "db/disk/out",
+		waitingFor: countingRecords, stalledOn: "db/out",
 	})
-	report, err := readReport(ctx, db, dbPath, operands, stdout, pathExists,
+	report, err := readReport(ctx, db, dbPath, stdout, prog)
-		prog)
 
 	prog.finish()
 
@@ -117,17 +104,14 @@ func runReport(ctx context.Context, args []string, stdout io.Writer) error {
 // dbPath, as its total, then reads every record in signature order,
 // counting each on prog, and writes the report to stdout: the header
 // line, then the rows of each size's duplicate groups once that size is
-// read. Only the records that underOperand finds under operands join a
+// read. stdout may be the terminal prog is drawn on, so the lines go
-// group, and a path for which exists returns false is left out of its
-// group. stdout may be the terminal prog is drawn on, so the lines go
 // through prog's writer. It returns what it wrote, with the totals for
 // the summary line.
 func readReport(ctx context.Context, db *sql.DB, dbPath string,
-	operands []string, stdout io.Writer, exists func(path string) bool,
+	stdout io.Writer, prog *progress,
-	prog *progress,
 ) (*reportWriter, error) {
 	out := prog.writer(stdout)
-	report := &reportWriter{out: out, exists: exists}
+	report := &reportWriter{out: out}
 
 	_, err := fmt.Fprintln(out, "first\tdupe\tsize")
 	if err != nil {
@@ -139,12 +123,6 @@ func readReport(ctx context.Context, db *sql.DB, dbPath string,
 	err = loadSignatureRows(ctx, db, prog.setTotal, func(r scanRec) error {
 		prog.increment()
 
-		report.records++
-
-		if !underOperand(r.path, operands) {
-			return nil
-		}
-
 		writeErr = report.add(r)
 
 		return writeErr
@@ -176,14 +154,10 @@ func readReport(ctx context.Context, db *sql.DB, dbPath string,
 // records of one size, so it holds only the duplicate groups of the
 // size being read, and writes them, ordered by first path, once a
 // record of a smaller size comes. It counts what the summary line
-// reports; readReport counts the records read.
+// reports.
 type reportWriter struct {
 	out io.Writer
 
-	// exists reports whether a path is still on disk. A path that is
-	// gone is left out of its group.
-	exists func(path string) bool
-
 	sig    scanRec    // the signature being read; its path is not used
 	paths  []string   // the paths read so far with sig
 	groups [][]string // the duplicate groups of sig.size, each sorted
@@ -196,6 +170,8 @@ type reportWriter struct {
 // its paths; any other ends them, and one of a smaller size first
 // writes the groups of the size before.
 func (w *reportWriter) add(r scanRec) error {
+	w.records++
+
 	if r.size == w.sig.size && r.head == w.sig.head &&
 		r.tail == w.sig.tail && r.content == w.sig.content {
 		w.paths = append(w.paths, r.path)
@@ -218,20 +194,11 @@ func (w *reportWriter) add(r scanRec) error {
 	return nil
 }
 
-// endGroup ends the paths read with w.sig: two or more that are still
+// endGroup ends the paths read with w.sig: two or more are a duplicate
-// on disk are a duplicate group, held with its paths sorted until
+// group, held with its paths sorted until writeGroups writes it.
-// writeGroups writes it. Empty files form no group, since removing one
-// frees nothing. Only the paths of a possible group are checked, never
-// a path with no duplicate or an empty file.
 func (w *reportWriter) endGroup() {
-	if len(w.paths) >= minGroupSize && w.sig.size > 0 {
+	if len(w.paths) < minGroupSize {
-		w.paths = slices.DeleteFunc(w.paths, func(p string) bool {
+		// A path with no duplicate is dropped, and its slice reused.
-			return !w.exists(p)
-		})
-	}
-
-	if len(w.paths) < minGroupSize || w.sig.size == 0 {
-		// The paths are dropped, and their slice reused.
 		w.paths = w.paths[:0]
 
 		return
@@ -278,57 +245,6 @@ func (w *reportWriter) finish() error {
 	return w.writeGroups()
 }
 
-// pathExists reports whether path is still on disk, for report and
-// trees. It is false only when lstat finds that the path, or a
-// directory above it, is gone. Any other error counts as present, so
-// a user who may not look inside a directory still sees its copies.
-func pathExists(path string) bool {
-	_, err := os.Lstat(path)
-
-	return !errors.Is(err, fs.ErrNotExist) && !errors.Is(err, syscall.ENOTDIR)
-}
-
-// cleanOperands returns the operands of report or trees, each made
-// absolute by absolutePath and then cleaned. The records hold real
-// paths, with no "." or ".." element and no repeated or trailing
-// slash, so an operand is cleaned to match them. No operand is looked
-// up on the filesystem. None is empty: rejectEmptyOperand refuses an
-// empty operand on the command line.
-func cleanOperands(args []string) ([]string, error) {
-	operands := make([]string, 0, len(args))
-
-	for _, a := range args {
-		abs, err := absolutePath(a)
-		if err != nil {
-			return nil, fmt.Errorf("resolve path %s: %w", escapePath(a), err)
-		}
-
-		operands = append(operands, filepath.Clean(abs))
-	}
-
-	return operands, nil
-}
-
-// underOperand reports whether path is one of operands or lies below
-// one of them. Each operand is clean and absolute, as cleanOperands
-// returns it. With no operands, a report covers the whole database, so
-// underOperand is true for every path.
-func underOperand(path string, operands []string) bool {
-	if len(operands) == 0 {
-		return true
-	}
-
-	for _, o := range operands {
-		// Only the root directory's clean path ends in "/".
-		dir := strings.TrimSuffix(o, "/") + "/"
-		if path == o || strings.HasPrefix(path, dir) {
-			return true
-		}
-	}
-
-	return false
-}
-
 // escapePath returns a path as it is written in a report column (README
 // "Report output format"): a backslash, tab, newline or carriage return
 // becomes \\, \t, \n or \r, and every other byte is kept as it is.

report_test.go

@@ -1,4 +1,4 @@
-package sfdupes //nolint:testpackage // checks the unexported dupeGroup results
+package main
 
 import (
 	"bytes"
@@ -72,38 +72,15 @@ type dupeGroup struct {
 	paths []string
 }
 
-// everyPathExists stands in for pathExists where a test's records name
-// made-up paths that are not on disk.
-func everyPathExists(string) bool { return true }
-
-// recsOnDisk returns a new directory and recs with each path moved
-// under it, after creating an empty file at each moved path: report and
-// trees then find every path still on disk.
-func recsOnDisk(t *testing.T, recs []scanRec) (string, []scanRec) {
-	t.Helper()
-
-	dir := realTempDir(t)
-	moved := make([]scanRec, len(recs))
-
-	for i, r := range recs {
-		r.path = writeFile(t, dir, r.path, nil)
-		moved[i] = r
-	}
-
-	return dir, moved
-}
-
 // dupeGroups returns the duplicate groups report reads from db, in
 // report order, from the rows it writes: a group's rows come together,
-// each naming the group's first path. Every path counts as still on
+// each naming the group's first path.
-// disk.
 func dupeGroups(t *testing.T, db *sql.DB) []dupeGroup {
 	t.Helper()
 
 	var out bytes.Buffer
 
-	_, err := readReport(t.Context(), db, "", nil, &out, everyPathExists,
+	_, err := readReport(t.Context(), db, "", &out, nil)
-		nil)
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -149,139 +126,8 @@ func dupeGroupsOf(t *testing.T, recs []scanRec) []dupeGroup {
 	return dupeGroups(t, db)
 }
 
-// TestRunReportOperands runs report with operands on three copies of
-// one file, two of them under srv/photos, and a fourth copy in
-// srv/photos2, all in a new directory. Only the records at or below the
-// operands form the groups and the totals, however each operand is
-// written.
-//
-//nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
-func TestRunReportOperands(t *testing.T) {
-	h := testHash("h")
-
-	recs := make([]scanRec, 0, 4)
-	for _, p := range []string{
-		"/a/copy", "/srv/photos/x", "/srv/photos/y", "/srv/photos2/z",
-	} {
-		recs = append(recs,
-			scanRec{size: 7, head: h, tail: h, content: h, path: p})
-	}
-
-	dir, recs := recsOnDisk(t, recs)
-	a, x, y, z := recs[0].path, recs[1].path, recs[2].path, recs[3].path
-
-	t.Setenv(databaseEnv, seedDatabase(t, recs))
-
-	header := "first\tdupe\tsize\n"
-	row := func(first, dupe string) string {
-		return first + "\t" + dupe + "\t7\n"
-	}
-	photos := header + row(x, y)
-
-	cases := map[string]struct {
-		operands []string
-		want     string
-		summary  string
-	}{
-		"directory": {[]string{dir + "/srv/photos"}, photos,
-			"1 duplicate groups, 1 dupe files, 7 B reclaimable"},
-		"trailing slash":  {[]string{dir + "/srv/photos/"}, photos, ""},
-		"dot and dot-dot": {[]string{dir + "/srv/./a/../photos"}, photos, ""},
-		"files":           {[]string{a, z}, header + row(a, z), ""},
-		"overlapping": {[]string{dir + "/srv", dir + "/srv/photos"},
-			header + row(x, y) + row(x, z), ""},
-		"root": {[]string{"/"},
-			header + row(a, x) + row(a, y) + row(a, z), ""},
-		"no record": {[]string{dir + "/srv/photo"}, header,
-			"0 duplicate groups, 0 dupe files, 0 B reclaimable"},
-	}
-
-	for name, tc := range cases {
-		t.Run(name, func(t *testing.T) {
-			var stdout bytes.Buffer
-
-			stderr := captureStderr(t)
-
-			code := run(append([]string{cmdReport}, tc.operands...),
-				&stdout, os.Stderr)
-			if code != exitOK {
-				t.Fatalf("run(report %q) = %d, want %d; stderr: %s",
-					tc.operands, code, exitOK, stderr())
-			}
-
-			if got := stdout.String(); got != tc.want {
-				t.Errorf("stdout = %q, want %q", got, tc.want)
-			}
-
-			// The records read are all four, whatever the operands.
-			summary := "report: 4 records read, " + tc.summary + "\n"
-			if got := stderr(); tc.summary != "" &&
-				!strings.HasSuffix(got, summary) {
-				t.Errorf("stderr = %q, want it to end %q", got, summary)
-			}
-		})
-	}
-}
-
-//nolint:paralleltest // t.Chdir changes the process-wide working directory
-func TestCleanOperandsMakesRelativePathsAbsolute(t *testing.T) {
-	dir := t.TempDir()
-	t.Chdir(dir)
-
-	wd, err := absolutePath(".")
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	got, err := cleanOperands([]string{"photos/", "a/../b", "/c//d"})
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	want := []string{
-		filepath.Join(wd, "photos"), filepath.Join(wd, "b"), "/c/d",
-	}
-	if !slices.Equal(got, want) {
-		t.Errorf("cleanOperands = %q, want %q", got, want)
-	}
-}
-
-// TestRunReportsRejectEmptyOperand checks that an empty PATH operand of
-// report or trees, alone or after another operand, is a usage error
-// reported in one line before the database is opened (README "Error
-// handling and exit codes").
-func TestRunReportsRejectEmptyOperand(t *testing.T) {
-	cases := map[string][]string{
-		"report":           {cmdReport, ""},
-		"trees":            {cmdTrees, ""},
-		"after an operand": {cmdTrees, t.TempDir(), ""},
-	}
-
-	for name, args := range cases {
-		t.Run(name, func(t *testing.T) {
-			// No database exists there, so opening one would be a fatal
-			// error, exit 1.
-			t.Setenv(databaseEnv, testDBPath(t))
-
-			var stdout, stderr bytes.Buffer
-
-			code := run(args, &stdout, &stderr)
-			if code != exitUsage {
-				t.Errorf("run(%q) = %d, want %d", args, code, exitUsage)
-			}
-
-			want := "Error: PATH must not be empty\n"
-			if stdout.String() != "" || stderr.String() != want {
-				t.Errorf("stdout, stderr = %q, %q, want \"\", %q",
-					stdout.String(), stderr.String(), want)
-			}
-		})
-	}
-}
-
 func TestRunReportEscapesPaths(t *testing.T) {
-	dir, recs := recsOnDisk(t, awkwardPairRecs())
+	t.Setenv(databaseEnv, seedDatabase(t, awkwardPairRecs()))
-	t.Setenv(databaseEnv, seedDatabase(t, recs))
 
 	var stdout, stderr bytes.Buffer
 
@@ -292,7 +138,7 @@ func TestRunReportEscapesPaths(t *testing.T) {
 	}
 
 	want := "first\tdupe\tsize\n" +
-		dir + `/d/\tone\ntwo\rthree\\four/f` + "\t" + dir + "/d/A/f\t5\n"
+		`/d/\tone\ntwo\rthree\\four/f` + "\t/d/A/f\t5\n"
 	if got := stdout.String(); got != want {
 		t.Errorf("stdout = %q, want %q", got, want)
 	}
@@ -326,8 +172,7 @@ func TestReportStdoutFailsWhileReading(t *testing.T) {
 	// Counts the records read, and draws nothing.
 	prog := &progress{now: time.Now}
 
-	_, err = readReport(t.Context(), db, "", nil, failingWriter{},
+	_, err = readReport(t.Context(), db, "", failingWriter{}, prog)
-		everyPathExists, prog)
 	if !errors.Is(err, errWriteFailed) ||
 		!strings.HasPrefix(err.Error(), "write stdout: ") {
 		t.Errorf("error = %v, want write stdout: %v", err, errWriteFailed)
@@ -358,8 +203,7 @@ const smokeReport = "first\tdupe\tsize\n" +
 // it ends; read counts the 6 records before it reads them. The summary
 // comes last, and stdout holds the report alone.
 func TestRunReportProgressNamesEachPhase(t *testing.T) {
-	dir, recs := recsOnDisk(t, smokeTreeRecs())
+	path := seedDatabase(t, smokeTreeRecs())
-	path := seedDatabase(t, recs)
 	t.Setenv(databaseEnv, path)
 
 	stderr := captureStderr(t)
@@ -372,9 +216,8 @@ func TestRunReportProgressNamesEachPhase(t *testing.T) {
 			code, exitOK, stderr())
 	}
 
-	report := strings.ReplaceAll(smokeReport, "/d/", dir+"/d/")
+	if got := stdout.String(); got != smokeReport {
-	if got := stdout.String(); got != report {
+		t.Errorf("stdout = %q, want %q", got, smokeReport)
-		t.Errorf("stdout = %q, want %q", got, report)
 	}
 
 	// How each line starts; the rate at the end of a phase varies.
@@ -423,8 +266,7 @@ func TestReadReportOnTerminal(t *testing.T) {
 		waitingFor: countingRecords,
 	}, terminalWidth, time.Hour, time.Now)
 
-	_, err = readReport(t.Context(), db, "", nil, os.Stderr,
+	_, err = readReport(t.Context(), db, "", os.Stderr, p)
-		everyPathExists, p)
 
 	p.finish()
 
@@ -459,8 +301,6 @@ func TestRunReportsIgnoreInsertionOrder(t *testing.T) {
 		scanRec{size: 50, head: a, tail: a, content: a, path: "/x/1"},
 	)
 
-	_, recs = recsOnDisk(t, recs)
-
 	reversed := slices.Clone(recs)
 	slices.Reverse(reversed)
 
@@ -594,141 +434,6 @@ func TestDupeGroups(t *testing.T) {
 	}
 }
 
-// TestDupeGroupsLeavesOutEmptyFiles checks that empty files form no
-// duplicate group, while 1-byte files still do.
-func TestDupeGroupsLeavesOutEmptyFiles(t *testing.T) {
-	t.Parallel()
-
-	e, x := sha256.Sum256(nil), testHash("x")
-	recs := []scanRec{
-		{size: 0, head: e, tail: e, content: e, path: "/a/.gitkeep"},
-		{size: 0, head: e, tail: e, content: e, path: "/b/.gitkeep"},
-		{size: 0, head: e, tail: e, content: e, path: "/c/__init__.py"},
-		{size: 1, head: x, tail: x, content: x, path: "/tiny1"},
-		{size: 1, head: x, tail: x, content: x, path: "/tiny2"},
-	}
-
-	groups := dupeGroupsOf(t, recs)
-	if len(groups) != 1 || groups[0].size != 1 ||
-		!slices.Equal(groups[0].paths, []string{"/tiny1", "/tiny2"}) {
-		t.Fatalf("groups = %+v, want only /tiny1 /tiny2 of size 1", groups)
-	}
-}
-
-// TestReadReportChecksOnlyPossibleDuplicates checks that report asks
-// whether a path is on disk only when its signature has two or more
-// records, and never for an empty file.
-func TestReadReportChecksOnlyPossibleDuplicates(t *testing.T) {
-	t.Parallel()
-
-	a, u, e := testHash("a"), testHash("u"), sha256.Sum256(nil)
-	recs := []scanRec{
-		{size: 9, head: a, tail: a, content: a, path: "/copy/1"},
-		{size: 9, head: a, tail: a, content: a, path: "/copy/2"},
-		{size: 9, head: a, tail: a, content: a, path: "/copy/3"},
-		{size: 9, head: u, tail: u, content: u, path: "/lonely"},
-		{size: 0, head: e, tail: e, content: e, path: "/empty1"},
-		{size: 0, head: e, tail: e, content: e, path: "/empty2"},
-	}
-
-	db := openTestDB(t)
-
-	err := applyChanges(t.Context(), db, recs, nil, nil)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	var checked []string
-
-	exists := func(path string) bool {
-		checked = append(checked, path)
-
-		return true
-	}
-
-	_, err = readReport(t.Context(), db, "", nil, io.Discard, exists, nil)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	slices.Sort(checked)
-
-	want := []string{"/copy/1", "/copy/2", "/copy/3"}
-	if !slices.Equal(checked, want) {
-		t.Errorf("paths checked on disk = %q, want %q", checked, want)
-	}
-}
-
-// TestReadReportDropsGroupLeftWithOnePath checks that a group of two
-// paths, one of them gone, is no duplicate group. If kept, it would
-// write no row, but the summary line would count it.
-func TestReadReportDropsGroupLeftWithOnePath(t *testing.T) {
-	t.Parallel()
-
-	a := testHash("a")
-	recs := []scanRec{
-		{size: 9, head: a, tail: a, content: a, path: "/a/kept"},
-		{size: 9, head: a, tail: a, content: a, path: "/a/gone"},
-	}
-
-	db := openTestDB(t)
-
-	err := applyChanges(t.Context(), db, recs, nil, nil)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	exists := func(path string) bool { return path != "/a/gone" }
-
-	report, err := readReport(t.Context(), db, "", nil, io.Discard, exists,
-		nil)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	if report.dupeGroups != 0 {
-		t.Errorf("duplicate groups = %d, want 0", report.dupeGroups)
-	}
-}
-
-// TestReadReportKeepsGroupLeftWithTwoPaths checks that a group of three
-// paths, one of them gone, is a duplicate group of the other two.
-func TestReadReportKeepsGroupLeftWithTwoPaths(t *testing.T) {
-	t.Parallel()
-
-	a := testHash("a")
-	recs := []scanRec{
-		{size: 9, head: a, tail: a, content: a, path: "/b/kept1"},
-		{size: 9, head: a, tail: a, content: a, path: "/b/gone"},
-		{size: 9, head: a, tail: a, content: a, path: "/b/kept2"},
-	}
-
-	db := openTestDB(t)
-
-	err := applyChanges(t.Context(), db, recs, nil, nil)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	exists := func(path string) bool { return path != "/b/gone" }
-
-	var out bytes.Buffer
-
-	report, err := readReport(t.Context(), db, "", nil, &out, exists, nil)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	if report.dupeGroups != 1 {
-		t.Errorf("duplicate groups = %d, want 1", report.dupeGroups)
-	}
-
-	want := "first\tdupe\tsize\n/b/kept1\t/b/kept2\t9\n"
-	if got := out.String(); got != want {
-		t.Errorf("stdout = %q, want %q", got, want)
-	}
-}
-
 func TestDupeGroupsContentSeparates(t *testing.T) {
 	t.Parallel()
 

scan.go

@@ -1,4 +1,4 @@
-package sfdupes
+package main
 
 import (
 	"cmp"
@@ -98,47 +98,44 @@ func scanPhase(name string) string {
 // runs, and the lock is released after it. When ctx is cancelled, as by
 // the SIGINT or SIGTERM that interruptContext catches, the scan keeps
 // what it has hashed (see syncScan), prints how many files its walk
-// reached, and returns errInterrupted. opts.workers must be at least 1;
+// reached, and returns errInterrupted. workers must be at least 1; the
-// the scan and dwim commands reject anything less. Before the lock is
+// scan command rejects anything less. Before the lock is taken, the
-// taken, the scan lists the filesystems that are not persistent, on
+// scan lists the filesystems that are not persistent, on which the walk
-// which the walk records nothing; unless opts.noDefaultExcludes is set,
+// records nothing; unless noDefaultExcludes is set, the walk does not
-// the walk does not enter the default excludes either. The walk neither
+// enter the default excludes either. Once the database is open, the
-// enters nor records the paths in opts.excludePaths, the --exclude
+// scan notes its files, which the walk passes over.
-// values; an operand at or below one is a fatal error. Once the
+func runScan(ctx context.Context, roots []string, workers int,
-// database is open, the scan notes its files, which the walk passes
+	oneFS, noDefaultExcludes bool,
-// over.
+) error {
-func runScan(ctx context.Context, roots []string, opts scanOptions) error {
 	dbPath, source, err := databasePath()
 	if err != nil {
 		return err
 	}
 
-	printDatabasePath(dbPath, source)
+	// A database file missing now is created by lockScanDatabase below.
+	what := "database"
 
-	roots, err = realPaths(roots)
+	_, err = os.Stat(dbPath)
+	if errors.Is(err, fs.ErrNotExist) {
+		what = "new database"
+	}
+
+	fmt.Fprintf(os.Stderr, "scan: %s %s (%s)\n", what, escapePath(dbPath),
+		source)
+
+	roots, err = resolveRoots(roots)
 	if err != nil {
 		return err
 	}
 
-	var rules walkRules
+	nonPersistent, err := nonPersistentFilesystems()
-
-	rules.excludePaths, err = excludePathInodes(opts.excludePaths)
-	if err != nil {
-		return fmt.Errorf("--exclude: %w", err)
-	}
-
-	err = checkOperandsNotExcluded(roots, rules.excludePaths)
-	if err != nil {
-		return err
-	}
-
-	rules.nonPersistent, err = nonPersistentFilesystems()
 	if err != nil {
 		return fmt.Errorf("list the mounted filesystems: %w", err)
 	}
 
-	if !opts.noDefaultExcludes {
+	rules := walkRules{nonPersistent: nonPersistent}
-		rules.defaultExcludes = defaultExcludes(runtime.GOOS)
+	if !noDefaultExcludes {
+		rules.excludes = defaultExcludes(runtime.GOOS)
 	}
 
 	lock, err := lockScanDatabase(dbPath)
@@ -166,7 +163,7 @@ func runScan(ctx context.Context, roots []string, opts scanOptions) error {
 		return err
 	}
 
-	st, err := syncScan(ctx, db, roots, opts.workers, opts.oneFS, rules)
+	st, err := syncScan(ctx, db, roots, workers, oneFS, rules)
 	if errors.Is(err, context.Canceled) {
 		return interrupted(st.walked)
 	}
@@ -184,21 +181,6 @@ func runScan(ctx context.Context, roots []string, opts scanOptions) error {
 	return nil
 }
 
-// printDatabasePath prints on stderr the line that names the database
-// at dbPath, with source, saying whether it is new. A database file
-// missing now is new: lockScanDatabase creates it.
-func printDatabasePath(dbPath, source string) {
-	what := "database"
-
-	_, err := os.Stat(dbPath)
-	if errors.Is(err, fs.ErrNotExist) {
-		what = "new database"
-	}
-
-	fmt.Fprintf(os.Stderr, "scan: %s %s (%s)\n", what, escapePath(dbPath),
-		source)
-}
-
 // interruptContext returns a copy of ctx that the first SIGINT or
 // SIGTERM cancels; the scan command runs the scan under it. stop
 // releases the signals.
@@ -227,31 +209,29 @@ func interrupted(walked int) error {
 	return errInterrupted
 }
 
-// realPaths returns the real path of each of paths, the PATH operands
+// resolveRoots converts each PATH operand to an absolute, lexically
-// or the --exclude values: absolute, with every symlink in it followed.
+// cleaned path (symlinks are not resolved) and verifies that it
-// Database records are keyed by that path, so scan results depend
+// exists. Database records are keyed by absolute path, so scan results
-// neither on the working directory nor on the symlinks an operand was
+// must not depend on the working directory.
-// given through. A path that cannot be resolved, because it or a
+func resolveRoots(roots []string) ([]string, error) {
-// symlink's target does not exist or cannot be read, is a fatal error
+	abs := make([]string, 0, len(roots))
-// before any scanning.
-func realPaths(paths []string) ([]string, error) {
-	resolved := make([]string, 0, len(paths))
 
-	for _, path := range paths {
+	for _, root := range roots {
-		a, err := absolutePath(path)
+		a, err := filepath.Abs(root)
 		if err != nil {
-			return nil, fmt.Errorf("resolve %s: %w", path, err)
+			return nil, fmt.Errorf("resolve %s: %w", root, err)
 		}
 
-		r, err := filepath.EvalSymlinks(a)
+		// A nonexistent operand is a fatal error before any scanning.
+		_, err = os.Lstat(a)
 		if err != nil {
-			return nil, fmt.Errorf("resolve %s: %w", path, err)
+			return nil, err
 		}
 
-		resolved = append(resolved, r)
+		abs = append(abs, a)
 	}
 
-	return resolved, nil
+	return abs, nil
 }
 
 // pruneRoots drops operands already covered by another operand:
@@ -314,7 +294,7 @@ func walkReaches(above, r string, oneFS bool, rules walkRules,
 	}
 
 	for ; dir != above; dir = filepath.Dir(dir) {
-		if isDefaultExclude(dir, rules.defaultExcludes) {
+		if isDefaultExclude(dir, rules.excludes) {
 			return false
 		}
 
@@ -437,16 +417,14 @@ func (s *scanState) runPhases(ctx context.Context, roots []string,
 
 // walkableRoots returns the operands the walk can start from: regular
 // files, and directories not named .zfs, none of them inside a
-// directory named .zfs. The operands are real paths from realPaths,
+// directory named .zfs. Every other operand is warned about, counted as
-// so these checks apply to what a symlink operand points at. Every
+// skipped, and dropped. A dropped operand is no longer a root, so the
-// other operand is warned about, counted as skipped, and dropped. A
+// records stored beneath it are treated as if it had not been given:
-// dropped operand is no longer a root, so the records stored beneath it
+// those under no other root count as outside the roots and are not
-// are treated as if it had not been given: those under no other root
+// deleted as unverified. An operand on a filesystem in rules that is not
-// count as outside the roots and are not deleted as unverified. An
+// persistent is dropped the same way, with a line saying so that is not
-// operand on a filesystem in rules that is not persistent is dropped
+// a warning, and is not counted as skipped. An operand that fails lstat
-// the same way, with a line saying so that is not a warning, and is not
+// here is kept, and the walk warns about it unless it no longer exists.
-// counted as skipped. An operand that fails lstat here is kept, and the
-// walk warns about it unless it no longer exists.
 func (s *scanState) walkableRoots(roots []string, rules walkRules) []string {
 	kept := make([]string, 0, len(roots))
 
@@ -512,11 +490,10 @@ func (s *scanState) loadIndex(ctx context.Context, roots []string) error {
 // as verified. When its disk_size differs from the record's, it is
 // queued for the update phase, which writes the new disk_size. A record
 // at or below a path the walk left out, because -x stopped at it, it is
-// an --exclude path or a default exclude, or it is not on a persistent
+// a default exclude, or it is not on a persistent filesystem, counts as
-// filesystem, counts as outside the roots: it is not deleted. That does
+// outside the roots: it is not deleted. That does not hold below a root
-// not hold below a root at or inside that path, since that root's own
+// at or inside that path, since that root's own walk verifies the
-// walk verifies the records below it; nor is a line printed for such a
+// records below it; nor is a line printed for such a root.
-// root.
 func (s *scanState) walkPhase(events <-chan walkEvent, roots []string) {
 	// The records the last scan left under the roots estimate how many
 	// files the walk will find. A first scan has none, and no estimate.
@@ -565,7 +542,7 @@ func (s *scanState) walkPhase(events <-chan walkEvent, roots []string) {
 		prog.increment()
 
 		old, ok := s.existing[ev.rec.path]
-		if !ok || old.size != ev.rec.size || !ev.rec.mtime.Equal(old.mtime) {
+		if !ok || old.size != ev.rec.size || mtimeAfter(ev.rec.mtime, old.mtime) {
 			s.toHash = append(s.toHash, ev.rec)
 
 			continue
@@ -577,7 +554,7 @@ func (s *scanState) walkPhase(events <-chan walkEvent, roots []string) {
 
 		// The space a file takes on disk can change while its size and
 		// mtime stay the same. ZFS, for one, counts a new file's blocks
-		// up to seconds after the write.
+		// only seconds after the write.
 		if old.diskSize != ev.rec.diskSize {
 			s.diskSizes = append(s.diskSizes, ev.rec)
 		}
@@ -800,6 +777,16 @@ func (s *scanState) updatePhase(ctx context.Context) error {
 	return applyChanges(ctx, s.db, nil, deletes, prog)
 }
 
+// mtimeAfter reports whether mtime a is later than mtime b.
+// Not a.After(b): time.Time wraps an mtime past year 292 billion; Unix() undoes it.
+func mtimeAfter(a, b time.Time) bool {
+	if a.Unix() != b.Unix() {
+		return a.Unix() > b.Unix()
+	}
+
+	return a.Nanosecond() > b.Nanosecond()
+}
+
 // underAnyRoot reports whether path is any of the roots or lies under
 // one of them.
 func underAnyRoot(path string, roots []string) bool {
@@ -854,9 +841,9 @@ type dirJob struct {
 // file's statted record, a warning when fail is set, or a path the walk
 // left out: when otherFSDir is set, a directory -x did not enter
 // because it is on another filesystem than its operand, and when
-// leftOut is set, an --exclude path, a default exclude or a directory or
+// leftOut is set, a default exclude or a directory or file on a
-// file on a filesystem that is not persistent, with warn holding the
+// filesystem that is not persistent, with warn holding the line that
-// line that says so.
+// says so.
 type walkEvent struct {
 	rec        fileRec
 	warn       string
@@ -907,13 +894,19 @@ func sendEvent(ctx context.Context, events chan<- walkEvent,
 // operandWarning returns the one-line warning for an operand the walk
 // does not start from, naming the path and what it is, or "" for one it
 // does: a regular file, or a directory not named .zfs, that is not
-// inside a directory named .zfs. realPaths has already followed the
+// inside a directory named .zfs, neither as given nor with its symlinks
-// operand's symlinks, so a symlink here is an operand replaced by one
+// resolved. Symlinks are never followed, including as operands.
-// after it was resolved, and is not followed.
 func operandWarning(root string, fi fs.FileInfo) string {
 	// The walk never enters a .zfs directory, so it starts from nothing
-	// inside one either.
+	// inside one either, not even through a symlink. An operand whose
-	if slices.Contains(strings.Split(filepath.Dir(root), "/"), ".zfs") {
+	// symlinks cannot be resolved is checked as given.
+	resolved, err := filepath.EvalSymlinks(root)
+	if err != nil {
+		resolved = root
+	}
+
+	if slices.Contains(strings.Split(filepath.Dir(root), "/"), ".zfs") ||
+		slices.Contains(strings.Split(filepath.Dir(resolved), "/"), ".zfs") {
 		return fmt.Sprintf("walk %s: skipping operand inside a .zfs directory",
 			root)
 	}
@@ -1138,9 +1131,8 @@ func walkOneDir(ctx context.Context, job dirJob, oneFS bool,
 // no longer exists, and one that has stopped being a regular file is
 // skipped. A file on a filesystem in rules that is not persistent, as
 // through a bind mount of one file, is not recorded: it gets an event
-// naming it instead, and so does a file given with --exclude, reached
+// naming it instead. One of the scan's own database files in rules gets
-// by any path, a hard link to it included. One of the scan's own
+// no event at all.
-// database files in rules gets no event at all.
 func emitFile(ctx context.Context, p string, e fs.DirEntry,
 	rules walkRules, events chan<- walkEvent,
 ) {
@@ -1164,10 +1156,6 @@ func emitFile(ctx context.Context, p string, e fs.DirEntry,
 	}
 
 	line := rules.nonPersistentLine(p, info)
-	if line == "" {
-		line = rules.excludePathLine(p, info)
-	}
-
 	if line != "" {
 		sendEvent(ctx, events, walkEvent{leftOut: p, warn: line})
 
@@ -1192,11 +1180,11 @@ func emitFile(ctx context.Context, p string, e fs.DirEntry,
 // subdirJob applies the descent rules to directory p: never enter
 // .zfs (ZFS snapshot pseudo-dirs would list every file once per
 // snapshot), never enter a directory on a filesystem in rules that is
-// not persistent, nor an --exclude path or a default exclude in rules,
+// not persistent, nor a default exclude in rules, and with -x never
-// and with -x never enter a directory on a different filesystem than
+// enter a directory on a different filesystem than its operand. For the
-// its operand. For all but .zfs it sends an event that names the
+// last three it sends an event that names the directory, so the scan
-// directory, so the scan keeps the records below it, except those below
+// keeps the records below it, except those below an operand at or
-// an operand at or inside it.
+// inside it.
 func subdirJob(ctx context.Context, p string, e fs.DirEntry,
 	parent dirJob, oneFS bool, rules walkRules,
 	events chan<- walkEvent,
@@ -1221,17 +1209,13 @@ func subdirJob(ctx context.Context, p string, e fs.DirEntry,
 	}
 
 	line := rules.nonPersistentLine(p, info)
-	if line == "" {
-		line = rules.excludePathLine(p, info)
-	}
-
 	if line != "" {
 		sendEvent(ctx, events, walkEvent{leftOut: p, warn: line})
 
 		return dirJob{}, false
 	}
 
-	if isDefaultExclude(p, rules.defaultExcludes) {
+	if isDefaultExclude(p, rules.excludes) {
 		sendEvent(ctx, events, walkEvent{
 			leftOut: p,
 			warn:    fmt.Sprintf("scan: skipped %s (default exclude)", p),

scan_dev_darwin.go

@@ -1,6 +1,6 @@
 //go:build darwin
 
-package sfdupes
+package main
 
 import "syscall"
 

scan_dev_other.go

@@ -1,6 +1,6 @@
 //go:build !darwin
 
-package sfdupes
+package main
 
 import "syscall"
 

scan_test.go

@@ -1,4 +1,4 @@
-package sfdupes //nolint:testpackage // drives the unexported syncTree
+package main
 
 import (
 	"bytes"
@@ -43,16 +43,10 @@ func writeFile(t *testing.T, dir, name string, data []byte) string {
 }
 
 // diskSizeOf returns the bytes the file at path takes on disk, from its
-// own lstat: st_blocks counts 512-byte units. ZFS counts a write's
+// own lstat: st_blocks counts 512-byte units. ZFS counts a new file's
-// blocks only when it commits the write, up to seconds later, and one
+// blocks only seconds after the write, and fsync does not hasten that.
-// commit can take the file through several growing sizes. So this value
+// A test therefore calls unix.Sync, which waits for it, before the scan
-// can change at any moment. Neither fsync nor unix.Sync hastens that,
+// whose disk_size it compares with this.
-// but a unix.Sync call often takes long enough that the blocks are
-// counted when it returns. A test that needs the value to change waits
-// for the change. A test that compares it with a scan's disk_size reads
-// it before and after the scan. The rewrite test rescans until the two
-// reads match, then compares exactly. The other two tests fail only on
-// a disk_size outside the two reads.
 func diskSizeOf(t *testing.T, path string) int64 {
 	t.Helper()
 
@@ -1094,7 +1088,7 @@ func TestScanOneFilesystemWalksNestedFileOperand(t *testing.T) {
 func buildSmokeTree(t *testing.T) string {
 	t.Helper()
 
-	dir := realTempDir(t)
+	dir := t.TempDir()
 	one := pattern(10, 2000)
 	f1 := pattern(30, 3000)
 	f2 := pattern(40, 100)
@@ -1185,12 +1179,11 @@ func assertSmokeDupeGroups(t *testing.T, dir string, db *sql.DB) {
 	t.Helper()
 
 	groups := dupeGroups(t, db)
-	if len(groups) != 4 {
+	if len(groups) != 5 {
-		t.Fatalf("len(groups) = %d, want 4", len(groups))
+		t.Fatalf("len(groups) = %d, want 5", len(groups))
 	}
 
-	// The empty files empty1 and empty2 form no group.
+	wantSizes := []int64{3000, 2000, 100, 1, 0}
-	wantSizes := []int64{3000, 2000, 100, 1}
 	for i, g := range groups {
 		if g.size != wantSizes[i] {
 			t.Errorf("groups[%d].size = %d, want %d",
@@ -1215,7 +1208,7 @@ func assertSmokeTreeGroups(t *testing.T, dir string, db *sql.DB) {
 
 	super, dirs := dbTree(t, db)
 
-	tg := collectTreeGroups(dirs, super, everyPathExists, nil)
+	tg := collectTreeGroups(dirs, super, nil)
 	if len(tg) != 1 {
 		t.Fatalf("len(tree groups) = %d, want 1", len(tg))
 	}
@@ -1384,47 +1377,6 @@ func TestSyncScanMtimeBump(t *testing.T) {
 	}
 }
 
-// TestSyncScanMtimeMovedBack replaces a file with other content of the
-// same size and an older mtime, as cp -p or a restore from backup does.
-// The next scan must hash the file again.
-func TestSyncScanMtimeMovedBack(t *testing.T) {
-	t.Parallel()
-
-	dir := t.TempDir()
-	db := openTestDB(t)
-	a := writeFile(t, dir, "a.bin", pattern(1, 500))
-
-	recorded := time.Date(2026, 1, 2, 3, 4, 5, 0, time.UTC)
-
-	err := os.Chtimes(a, recorded, recorded)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	syncTree(t, db, dir)
-
-	replaced := pattern(3, 500)
-	writeFile(t, dir, "a.bin", replaced)
-
-	older := recorded.Add(-time.Hour)
-
-	err = os.Chtimes(a, older, older)
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	st := syncTree(t, db, dir)
-	if st != (scanStats{walked: 1, updated: 1}) {
-		t.Fatalf("rescan stats = %+v, want 1 updated", st)
-	}
-
-	assertWholeFileHashed(t, db, a, replaced)
-
-	if r := recordByPath(t, dbRecords(t, db), a); !r.mtime.Equal(older) {
-		t.Fatalf("mtime = %v, want %v", r.mtime, older)
-	}
-}
-
 // assertWholeFileHashed fails unless the record for path holds the
 // whole-file hash of data as its head, tail, and content.
 func assertWholeFileHashed(t *testing.T, db *sql.DB, path string,
@@ -1496,26 +1448,20 @@ func TestScanStoresDiskSize(t *testing.T) {
 
 	unix.Sync() // see diskSizeOf
 
-	size := diskSizeOf(t, p)
+	want := diskSizeOf(t, p)
-	if size == 0 || size >= length {
+	if want == 0 || want >= length {
 		t.Fatalf("the file takes %d bytes on disk, want more than none "+
-			"and fewer than its length %d", size, length)
+			"and fewer than its length %d", want, length)
 	}
 
 	for _, operand := range []string{filepath.Dir(p), p} {
 		db := openTestDB(t)
-
-		// ZFS may count the blocks during the scan; see diskSizeOf.
-		before := diskSizeOf(t, p)
-
 		syncTree(t, db, operand)
 
-		after := diskSizeOf(t, p)
-
 		got := recordByPath(t, dbRecords(t, db), p).diskSize
-		if got < before || got > after {
+		if got != want {
-			t.Errorf("scan of %s: disk_size = %d, want %d to %d",
+			t.Errorf("scan of %s: disk_size = %d, want %d",
-				operand, got, before, after)
+				operand, got, want)
 		}
 	}
 }
@@ -1533,7 +1479,7 @@ func TestSyncScanRewriteUpdatesDiskSize(t *testing.T) {
 
 	syncTree(t, db, dir)
 
-	recorded := recordByPath(t, dbRecords(t, db), p).diskSize
+	before := recordByPath(t, dbRecords(t, db), p).diskSize
 
 	pokeAt(t, p, 512*1024, pattern(7, 64*1024))
 
@@ -1546,53 +1492,22 @@ func TestSyncScanRewriteUpdatesDiskSize(t *testing.T) {
 		t.Fatal(err)
 	}
 
-	// Wait for ZFS to count the write; see diskSizeOf.
+	unix.Sync() // see diskSizeOf
-	deadline := time.Now().Add(30 * time.Second)
-	for diskSizeOf(t, p) == recorded {
-		if time.Now().After(deadline) {
-			t.Fatalf("the file still takes %d bytes on disk 30 seconds "+
-				"after the write into its hole", recorded)
-		}
 
-		unix.Sync()
+	want := diskSizeOf(t, p)
+	if want == before {
+		t.Fatalf("the file still takes %d bytes on disk after the write "+
+			"into its hole", want)
 	}
 
-	// ZFS may still be counting, so the size may change during a rescan.
-	// Only a rescan with the same size on both sides of it can be compared
-	// exactly. A rescan that keeps the old size still fails, because the
-	// wait made before differ from it.
-	for {
-		before := diskSizeOf(t, p)
-
 	st := syncTree(t, db, dir)
-
-		after := diskSizeOf(t, p)
-
 	if st != (scanStats{walked: 1, updated: 1}) {
 		t.Fatalf("rescan stats = %+v, want 1 updated", st)
 	}
 
-		if before == after {
 	got := recordByPath(t, dbRecords(t, db), p).diskSize
-			if got != after {
+	if got != want {
-				t.Errorf("disk_size = %d, want %d", got, after)
+		t.Errorf("disk_size = %d, want %d", got, want)
-			}
-
-			return
-		}
-
-		if time.Now().After(deadline) {
-			t.Fatalf("the size on disk was still changing 30 seconds after "+
-				"the write into its hole: %d, then %d", before, after)
-		}
-
-		// A later mtime makes the next rescan read the file again.
-		later = later.Add(time.Second)
-
-		err = os.Chtimes(p, later, later)
-		if err != nil {
-			t.Fatal(err)
-		}
 	}
 }
 
@@ -1618,21 +1533,15 @@ func TestSyncScanUnchangedUpdatesDiskSize(t *testing.T) {
 
 	unix.Sync() // see diskSizeOf
 
-	// ZFS may count the blocks during the rescan; see diskSizeOf.
-	before := diskSizeOf(t, p)
-
 	// A file read again would count as updated.
 	st := syncTree(t, db, dir)
-
-	after := diskSizeOf(t, p)
-
 	if st != (scanStats{walked: 1, unchanged: 1}) {
 		t.Fatalf("rescan stats = %+v, want 1 unchanged", st)
 	}
 
 	got := recordByPath(t, dbRecords(t, db), p).diskSize
-	if got < before || got > after {
+	if want := diskSizeOf(t, p); got != want {
-		t.Errorf("disk_size = %d, want %d to %d", got, before, after)
+		t.Errorf("disk_size = %d, want %d", got, want)
 	}
 }
 
@@ -2196,7 +2105,7 @@ func TestScanHashWriteFailureUnwindsPool(t *testing.T) {
 	var stderr bytes.Buffer
 
 	code := run([]string{
-		cmdScan, workersFlag, strconv.Itoa(hashLeakWorkers), dir,
+		cmdScan, "--workers", strconv.Itoa(hashLeakWorkers), dir,
 	}, io.Discard, &stderr)
 	if code != exitFatal {
 		t.Fatalf("run(scan) = %d, want %d; stderr: %s",
@@ -2289,7 +2198,7 @@ func TestPruneRoots(t *testing.T) {
 
 	// The walk of /p does not enter /p/q when it is a default exclude, so
 	// /p/q is kept, without -x too; /p/q/r lies under it and is dropped.
-	got = pruneRoots(nested, false, walkRules{defaultExcludes: []string{pqRoot}},
+	got = pruneRoots(nested, false, walkRules{excludes: []string{pqRoot}},
 		device)
 	if !slices.Equal(got, want) {
 		t.Fatalf("pruneRoots excluding %s = %q, want %q", pqRoot, got, want)
@@ -2307,86 +2216,23 @@ func TestPruneRoots(t *testing.T) {
 	}
 }
 
-// TestRunReportsLeaveOutRemovedCopies scans the smoke tree, then
+func TestReportsNeverTouchFilesystem(t *testing.T) {
-// removes copies the reports name. report leaves out each removed file,
-// and a group left with one path. trees checks only the root of each
-// duplicate tree: with a file under t2 removed it still names t2, and
-// with t2 removed it names nothing.
-func TestRunReportsLeaveOutRemovedCopies(t *testing.T) {
-	t.Setenv(databaseEnv, testDBPath(t))
-
-	dir := buildSmokeTree(t)
-	p := func(name string) string { return filepath.Join(dir, name) }
-
-	scanOK(t, dir)
-
-	for _, name := range []string{"b/copy2.bin", "tiny2", "t2/sub/f2"} {
-		err := os.Remove(p(name))
-		if err != nil {
-			t.Fatal(err)
-		}
-	}
-
-	want := "first\tdupe\tsize\n" +
-		p("t1/f1") + "\t" + p("t2/f1") + "\t3000\n" +
-		p("t1/f1") + "\t" + p("t3/f1") + "\t3000\n" +
-		p("a/one.bin") + "\t" + p("b/copy.bin") + "\t2000\n" +
-		p("t1/sub/f2") + "\t" + p("t3/sub/f2renamed") + "\t100\n"
-	if got := runStdout(t, cmdReport); got != want {
-		t.Errorf("report stdout = %q, want %q", got, want)
-	}
-
-	// disk_size, the last column, depends on the filesystem.
-	header := "first\tdupe\tfiles\tsize\tdisk_size\n"
-
-	want = header + p("t1") + "\t" + p("t2") + "\t2\t3100\t"
-	if got := runStdout(t, cmdTrees); !strings.HasPrefix(got, want) ||
-		strings.Count(got, "\n") != 2 {
-		t.Errorf("trees stdout = %q, want one row starting %q", got, want)
-	}
-
-	err := os.RemoveAll(p("t2"))
-	if err != nil {
-		t.Fatal(err)
-	}
-
-	if got := runStdout(t, cmdTrees); got != header {
-		t.Errorf("trees stdout after removing t2 = %q, want %q", got, header)
-	}
-}
-
-func TestPathExists(t *testing.T) {
 	t.Parallel()
 
-	dir := t.TempDir()
+	dir := buildSmokeTree(t)
-	file := writeFile(t, dir, "file", nil)
+	db := openTestDB(t)
-	locked := writeFile(t, dir, "locked/file", nil)
 
-	// Without search permission on its directory, a file cannot be
+	syncTree(t, db, dir)
-	// looked at by anyone but root.
+
-	err := os.Chmod(filepath.Dir(locked), 0)
+	// Remove the scanned tree entirely; the analysis must be
+	// unaffected because it reads the database alone.
+	err := os.RemoveAll(dir)
 	if err != nil {
 		t.Fatal(err)
 	}
 
-	// Runs before t.TempDir's own cleanup, which must delete the files.
+	assertSmokeDupeGroups(t, dir, db)
-	t.Cleanup(func() {
+	assertSmokeTreeGroups(t, dir, db)
-		//nolint:gosec // removing the directory needs its search bit back
-		_ = os.Chmod(filepath.Dir(locked), 0o700)
-	})
-
-	cases := map[string]bool{
-		dir:                                 true,
-		file:                                true,
-		locked:                              true,
-		filepath.Join(dir, "gone"):          false,
-		filepath.Join(file, "under-a-file"): false,
-	}
-	for path, want := range cases {
-		if got := pathExists(path); got != want {
-			t.Errorf("pathExists(%q) = %v, want %v", path, got, want)
-		}
-	}
 }
 
 func TestUnderRoot(t *testing.T) {
@@ -2415,24 +2261,33 @@ func TestUnderRoot(t *testing.T) {
 }
 
 // TestRunScanPassesOverDatabase scans a tree that holds the scan's own
-// database, and in one case also a hard link to the database file. The
+// database, reached directly and through a symlinked directory. The
-// walk knows the database's files by device ID and inode number, so it
+// walk passes over the database file, its -wal and -shm files and its
-// passes over the database file, its -wal and -shm files, its .lock
+// .lock file with no line and no count, and the record an earlier scan
-// file and the hard link with no line and no count. The record an
+// left for the .lock file is deleted. A rescan of the unchanged tree
-// earlier scan left for the .lock file is deleted. A rescan of the
+// updates nothing, and report lists none of the database's files.
-// unchanged tree updates nothing, and report lists none of the
-// database's files.
 func TestRunScanPassesOverDatabase(t *testing.T) {
-	for _, viaHardLink := range []bool{false, true} {
+	for _, viaSymlink := range []bool{false, true} {
-		t.Run(fmt.Sprintf("via hard link %v", viaHardLink), func(t *testing.T) {
+		t.Run(fmt.Sprintf("via symlink %v", viaSymlink), func(t *testing.T) {
-			tree := realTempDir(t)
+			base := t.TempDir()
-			hardLink := filepath.Join(tree, "hardlink")
+			tree := filepath.Join(base, "real", "tree")
+			operand := tree
 
 			writeFile(t, tree, "a", pattern(1, 100))
 			writeFile(t, tree, "b", pattern(1, 100))
 			writeFile(t, tree, "empty1", nil)
 			writeFile(t, tree, "empty2", nil)
 
+			if viaSymlink {
+				err := os.Symlink(filepath.Join(base, "real"),
+					filepath.Join(base, "link"))
+				if err != nil {
+					t.Fatal(err)
+				}
+
+				operand = filepath.Join(base, "link", "tree")
+			}
+
 			dbPath := filepath.Join(tree, "db.sqlite")
 			t.Setenv(databaseEnv, dbPath)
 
@@ -2442,7 +2297,7 @@ func TestRunScanPassesOverDatabase(t *testing.T) {
 			}
 
 			err = applyChanges(t.Context(), db, []scanRec{
-				{path: filepath.Join(tree, "db.sqlite.lock")},
+				{path: filepath.Join(operand, "db.sqlite.lock")},
 			}, nil, nil)
 			if err != nil {
 				t.Fatal(err)
@@ -2450,30 +2305,17 @@ func TestRunScanPassesOverDatabase(t *testing.T) {
 
 			closeScanDatabase(t.Context(), db, dbPath)
 
-			if viaHardLink {
+			assertScanSummary(t,
-				err = os.Link(dbPath, hardLink)
-				if err != nil {
-					t.Fatal(err)
-				}
-			}
-
-			stderr := assertScanSummary(t,
 				"4 files seen (4 added, 0 updated, 1 removed, 0 unchanged)",
-				tree)
+				operand)
-			stderr += assertScanSummary(t,
+			assertScanSummary(t,
 				"4 files seen (0 added, 0 updated, 0 removed, 4 unchanged)",
-				tree)
+				operand)
-
-			if strings.Contains(stderr, hardLink) {
-				t.Errorf("scan stderr = %q, want no line naming %s",
-					stderr, hardLink)
-			}
 
 			report := runStdout(t, cmdReport)
 			if strings.Contains(report, "db.sqlite") ||
-				strings.Contains(report, hardLink) ||
+				!strings.Contains(report, filepath.Join(operand, "empty2")) {
-				!strings.Contains(report, filepath.Join(tree, "b")) {
+				t.Errorf("report = %q, want the empty files and none of "+
-				t.Errorf("report = %q, want a and b and none of "+
 					"the database's files", report)
 			}
 		})
@@ -2497,9 +2339,8 @@ func TestRunScanPassesOverDatabaseOperands(t *testing.T) {
 
 // assertScanSummary scans operands and fails the test unless the
 // summary line gives counts with nothing skipped, and the line naming
-// the database is the only one that names one of its files. It returns
+// the database is the only one that names one of its files.
-// everything the scan printed to stderr.
+func assertScanSummary(t *testing.T, counts string, operands ...string) {
-func assertScanSummary(t *testing.T, counts string, operands ...string) string {
 	t.Helper()
 
 	stderr := scanOK(t, operands...)
@@ -2513,6 +2354,4 @@ func assertScanSummary(t *testing.T, counts string, operands ...string) string {
 		t.Errorf("scan %q: stderr = %q, want only the line naming the "+
 			"database to name one of its files", operands, stderr)
 	}
-
-	return stderr
 }

trees.go

@@ -1,4 +1,4 @@
-package sfdupes
+package main
 
 import (
 	"context"
@@ -37,14 +37,11 @@ func treesPhase(name string) string {
 
 // runTrees implements the trees subcommand: it reads every record from
 // the database in path order, reconstructs the directory hierarchy from
-// the paths of the records at or below the operands in args (of every
+// the record paths, computes a Merkle-style digest per directory, and
-// record when args is empty), computes a Merkle-style digest per
+// prints maximal duplicate-tree groups as TSV on stdout. It never
-// directory, and prints maximal duplicate-tree groups as TSV on stdout.
+// touches the scanned filesystem; its only I/O is the database, stdout,
-// Of the scanned filesystem it only checks, with pathExists, that the
+// and stderr. It names the database on stderr before it opens it. Any
-// root of each duplicate tree is still there, never the files below it;
+// database problem, including a missing database, is fatal.
-// it never looks up an operand. It names the database on stderr before
-// it opens it. Any database problem, including a missing database, is
-// fatal.
 //
 // The work runs in four phases, each under a progress display of its
 // own on stderr: open (open the database), read (read the number of
@@ -52,12 +49,7 @@ func treesPhase(name string) string {
 // hierarchy), group (group the directories by digest) and write (write
 // the groups to stdout). Each display ends before the next phase
 // starts, and before an error is returned to be printed.
-func runTrees(ctx context.Context, args []string, stdout io.Writer) error {
+func runTrees(ctx context.Context, stdout io.Writer) error {
-	operands, err := cleanOperands(args)
-	if err != nil {
-		return err
-	}
-
 	dbPath, source, err := databasePath()
 	if err != nil {
 		return err
@@ -86,7 +78,7 @@ func runTrees(ctx context.Context, args []string, stdout io.Writer) error {
 		label: treesPhase("read"), unit: "records", total: -1,
 		waitingFor: countingRecords, stalledOn: "db",
 	})
-	records, super, allDirs, err := readTree(ctx, db, operands, prog)
+	records, super, allDirs, err := readTree(ctx, db, prog)
 
 	prog.finish()
 
@@ -94,13 +86,13 @@ func runTrees(ctx context.Context, args []string, stdout io.Writer) error {
 		return fmt.Errorf("database %s: %w", dbPath, err)
 	}
 
-	// Grouping works in memory, then checks the root of each duplicate
+	// Grouping works in memory, so it waits on nothing but the
-	// tree on disk, so it waits on the processor or the disk.
+	// processor.
 	prog = newProgress(progressParams{
 		label: treesPhase("group"), unit: "directories",
-		total: int64(len(allDirs)), stalledOn: "cpu/disk",
+		total: int64(len(allDirs)), stalledOn: "cpu",
 	})
-	dupes := collectTreeGroups(allDirs, super, pathExists, prog)
+	dupes := collectTreeGroups(allDirs, super, prog)
 
 	prog.finish()
 
@@ -125,17 +117,10 @@ func runTrees(ctx context.Context, args []string, stdout io.Writer) error {
 }
 
 // readTree gives prog the number of records in db as its total, then
-// reads every record in path order, counting each on prog. It adds the
+// reads every record in path order into the directory hierarchy,
-// records that underOperand finds under operands to the directory
+// counting each on prog. It returns the number of records read, the
-// hierarchy. It returns the number of records read, the super-root and
+// super-root and every directory.
-// every directory at or below one of operands.
+func readTree(ctx context.Context, db *sql.DB,
-//
-// Any other directory lies above an operand and can hold files that are
-// not used, so its digest does not describe it. It is left out of the
-// directories returned. A directory whose parent is left out gets the
-// super-root as its parent, so suppressed never judges its group by
-// that parent's digest.
-func readTree(ctx context.Context, db *sql.DB, operands []string,
 	prog *progress,
 ) (int, *treeNode, []*treeNode, error) {
 	records := 0
@@ -145,10 +130,7 @@ func readTree(ctx context.Context, db *sql.DB, operands []string,
 		records++
 
 		prog.increment()
-
-		if underOperand(r.path, operands) {
 		tree.add(r)
-		}
 	})
 	if err != nil {
 		return 0, nil, nil, err
@@ -156,21 +138,7 @@ func readTree(ctx context.Context, db *sql.DB, operands []string,
 
 	super, allDirs := tree.finish()
 
-	dirs := allDirs[:0]
+	return records, super, allDirs, nil
-
-	for _, d := range allDirs {
-		if !underOperand(d.path, operands) {
-			continue
-		}
-
-		if !underOperand(d.parent.path, operands) {
-			d.parent = super
-		}
-
-		dirs = append(dirs, d)
-	}
-
-	return records, super, dirs, nil
 }
 
 // writeTreeGroups writes dupes to stdout as TSV, a header line and then
@@ -332,14 +300,10 @@ func fileEntry(name string, r scanRec) string {
 
 // collectTreeGroups groups directories by digest, counting each one on
 // prog as it is grouped, and returns every maximal group with two or
-// more members for which exists returns true, each group's members
+// more members, each group's members sorted by path, groups ordered by
-// sorted by path, groups ordered by tree size descending then by first
+// tree size descending then by first path ascending.
-// path ascending. A group whose trees hold 0 bytes is left out, since
-// removing one frees nothing. The groups it implies hold 0 bytes too,
-// so leaving it out hides nothing. exists is called only on the members
-// of maximal groups.
 func collectTreeGroups(allDirs []*treeNode, super *treeNode,
-	exists func(path string) bool, prog *progress,
+	prog *progress,
 ) [][]*treeNode {
 	groups := make(map[[sha256.Size]byte][]*treeNode)
 	for _, d := range allDirs {
@@ -351,19 +315,7 @@ func collectTreeGroups(allDirs []*treeNode, super *treeNode,
 	var dupes [][]*treeNode
 
 	for _, g := range groups {
-		// The members share a digest, so they share a total size.
+		if len(g) < minGroupSize || suppressed(g, super) {
-		if len(g) < minGroupSize || g[0].totalSize == 0 ||
-			suppressed(g, super) {
-			continue
-		}
-
-		// A member that is gone leaves the group. A suppressed group is
-		// still implied: its members still on disk have parents still
-		// on disk, and those parents' group is checked the same way.
-		g = slices.DeleteFunc(g, func(n *treeNode) bool {
-			return !exists(n.path)
-		})
-		if len(g) < minGroupSize {
 			continue
 		}
 

trees_test.go

@@ -1,12 +1,10 @@
-package sfdupes //nolint:testpackage // checks the unexported treeNode results
+package main
 
 import (
 	"bytes"
-	"crypto/sha256"
 	"database/sql"
 	"os"
 	"slices"
-	"strconv"
 	"strings"
 	"testing"
 	"time"
@@ -180,7 +178,7 @@ func TestTreeNamesSortingBeforeSlash(t *testing.T) {
 		t.Fatalf("directory paths = %q, want %q", got, want)
 	}
 
-	groups := collectTreeGroups(dirs, super, everyPathExists, nil)
+	groups := collectTreeGroups(dirs, super, nil)
 
 	gotGroups := groupPaths(groups)
 	wantGroups := [][]string{{"/a", "/c"}}
@@ -196,8 +194,7 @@ func TestTreeNamesSortingBeforeSlash(t *testing.T) {
 }
 
 func TestRunTreesEscapesPaths(t *testing.T) {
-	dir, recs := recsOnDisk(t, awkwardPairRecs())
+	t.Setenv(databaseEnv, seedDatabase(t, awkwardPairRecs()))
-	t.Setenv(databaseEnv, seedDatabase(t, recs))
 
 	var stdout, stderr bytes.Buffer
 
@@ -208,63 +205,12 @@ func TestRunTreesEscapesPaths(t *testing.T) {
 	}
 
 	want := "first\tdupe\tfiles\tsize\tdisk_size\n" +
-		dir + `/d/\tone\ntwo\rthree\\four` + "\t" + dir + "/d/A\t1\t5\t4096\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)
 	}
 }
 
-// TestRunTreesOperands runs trees with operands on records in a new
-// directory. x/a and y/a are copies, and so are y/a and srv/b. x and y
-// also hold files that differ. Given x/a and y/a, trees reads x and y
-// as holding one copy each of a, yet neither is reported: only the
-// directories at or below an operand are.
-func TestRunTreesOperands(t *testing.T) {
-	f, g, k := testHash("f"), testHash("g"), testHash("k")
-	dir, recs := recsOnDisk(t, []scanRec{
-		{size: 10, head: f, tail: f, content: f, path: "/srv/b/f"},
-		{size: 10, head: f, tail: f, content: f, path: "/x/a/f"},
-		{size: 20, head: g, tail: g, content: g, path: "/x/g"},
-		{size: 10, head: f, tail: f, content: f, path: "/y/a/f"},
-		{size: 30, head: k, tail: k, content: k, path: "/y/k"},
-	})
-	b, xa, ya := dir+"/srv/b", dir+"/x/a", dir+"/y/a"
-
-	header := "first\tdupe\tfiles\tsize\tdisk_size\n"
-	row := func(first, dupe string) string {
-		return first + "\t" + dupe + "\t1\t10\t0\n"
-	}
-
-	cases := map[string]struct {
-		operands []string
-		want     string
-	}{
-		"none":       {nil, header + row(b, xa) + row(b, ya)},
-		"two copies": {[]string{xa, ya}, header + row(xa, ya)},
-		"parents":    {[]string{dir + "/x", dir + "/y"}, header + row(xa, ya)},
-		"one copy":   {[]string{b}, header},
-	}
-
-	for name, tc := range cases {
-		t.Run(name, func(t *testing.T) {
-			t.Setenv(databaseEnv, seedDatabase(t, recs))
-
-			var stdout, stderr bytes.Buffer
-
-			code := run(append([]string{cmdTrees}, tc.operands...),
-				&stdout, &stderr)
-			if code != exitOK {
-				t.Fatalf("run(trees %q) = %d, want %d; stderr: %s",
-					tc.operands, code, exitOK, stderr.String())
-			}
-
-			if got := stdout.String(); got != tc.want {
-				t.Errorf("stdout = %q, want %q", got, tc.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.
@@ -277,11 +223,9 @@ func TestRunTreesDiskSize(t *testing.T) {
 		{size: 20, diskSize: 1024, head: g, tail: g, content: g, path: "/b/sub/g"},
 	}
 
-	dir, recs := recsOnDisk(t, recs)
 	t.Setenv(databaseEnv, seedDatabase(t, recs))
 
-	want := "first\tdupe\tfiles\tsize\tdisk_size\n" +
+	want := "first\tdupe\tfiles\tsize\tdisk_size\n/a\t/b\t2\t30\t1536\n"
-		dir + "/a\t" + dir + "/b\t2\t30\t1536\n"
 	if got := runStdout(t, cmdTrees); got != want {
 		t.Errorf("stdout = %q, want %q", got, want)
 	}
@@ -292,11 +236,10 @@ func TestRunTreesDiskSize(t *testing.T) {
 // there. After the line naming the database, each phase prints a line
 // naming it with its place among the four as it starts and another as
 // it ends. read counts the 6 records before it reads them, group counts
-// the directories, and write the 1 group. The summary comes last, and
+// the 8 directories, and write the 1 group. The summary comes last, and
 // stdout holds the report alone.
 func TestRunTreesProgressNamesEachPhase(t *testing.T) {
-	dir, recs := recsOnDisk(t, smokeTreeRecs())
+	path := seedDatabase(t, smokeTreeRecs())
-	path := seedDatabase(t, recs)
 	t.Setenv(databaseEnv, path)
 
 	stderr := captureStderr(t)
@@ -310,15 +253,11 @@ func TestRunTreesProgressNamesEachPhase(t *testing.T) {
 	}
 
 	report := "first\tdupe\tfiles\tsize\tdisk_size\n" +
-		dir + "/d/t1\t" + dir + "/d/t2\t2\t3100\t8192\n"
+		"/d/t1\t/d/t2\t2\t3100\t8192\n"
 	if got := stdout.String(); got != report {
 		t.Errorf("stdout = %q, want %q", got, report)
 	}
 
-	// The smoke-test records name 8 directories, / included. Moved under
-	// dir, they name one more for each slash in dir.
-	dirs := strconv.Itoa(8 + strings.Count(dir, "/"))
-
 	// How each line starts; the rate at the end of a phase varies.
 	want := []string{
 		"trees: database " + path + " (from " + databaseEnv + ")",
@@ -326,9 +265,8 @@ func TestRunTreesProgressNamesEachPhase(t *testing.T) {
 		treesOpenLine,
 		"[2/4] read: counting the records, elapsed 0s, remain unknown",
 		"[2/4] read: [6/6] 100%, ",
-		"[3/4] group: [0/" + dirs + "] 0%, 0 directories/s, elapsed 0s, " +
+		"[3/4] group: [0/8] 0%, 0 directories/s, elapsed 0s, remain unknown",
-			"remain unknown",
+		"[3/4] group: [8/8] 100%, ",
-		"[3/4] group: [" + dirs + "/" + dirs + "] 100%, ",
 		"[4/4] write: [0/1] 0%, 0 groups/s, elapsed 0s, remain unknown",
 		"[4/4] write: [1/1] 100%, ",
 		"trees: 6 records read, 1 duplicate tree groups, 1 dupe trees, ",
@@ -357,7 +295,7 @@ func TestRunTreesProgressNamesEachPhase(t *testing.T) {
 func TestWriteTreeGroupsOnTerminal(t *testing.T) {
 	stderr := captureStderr(t)
 	super, dirs := treeOf(t, smokeTreeRecs())
-	dupes := collectTreeGroups(dirs, super, everyPathExists, nil)
+	dupes := collectTreeGroups(dirs, super, nil)
 
 	// No timed draws: the display is drawn as it starts and as it ends.
 	p := startProgress(progressParams{
@@ -438,7 +376,7 @@ func TestCollectTreeGroupsMaximal(t *testing.T) {
 
 	super, dirs := treeOf(t, smokeTreeRecs())
 
-	groups := collectTreeGroups(dirs, super, everyPathExists, nil)
+	groups := collectTreeGroups(dirs, super, nil)
 
 	want := [][]string{{"/d/t1", "/d/t2"}}
 	if got := groupPaths(groups); !slices.EqualFunc(got, want,
@@ -462,16 +400,14 @@ func TestCollectTreeGroupsDeterministic(t *testing.T) {
 
 	super, dirs := treeOf(t, recs)
 
-	forward := groupPaths(collectTreeGroups(dirs, super, everyPathExists,
+	forward := groupPaths(collectTreeGroups(dirs, super, nil))
-		nil))
 
 	reversed := slices.Clone(recs)
 	slices.Reverse(reversed)
 
 	superR, dirsR := treeOf(t, reversed)
 
-	backward := groupPaths(collectTreeGroups(dirsR, superR, everyPathExists,
+	backward := groupPaths(collectTreeGroups(dirsR, superR, nil))
-		nil))
 	if !slices.EqualFunc(forward, backward, slices.Equal) {
 		t.Fatalf("output depends on record order: %v vs %v",
 			forward, backward)
@@ -491,36 +427,7 @@ func TestCollectTreeGroupsSiblings(t *testing.T) {
 
 	super, dirs := treeOf(t, recs)
 
-	got := groupPaths(collectTreeGroups(dirs, super, everyPathExists, nil))
+	got := groupPaths(collectTreeGroups(dirs, super, nil))
-
-	want := [][]string{{"/p/x1", "/p/x2"}}
-	if !slices.EqualFunc(got, want, slices.Equal) {
-		t.Fatalf("groups = %v, want %v", got, want)
-	}
-}
-
-// TestCollectTreeGroupsLeavesOutEmptyTrees checks that directories
-// holding only empty files form no group, and that an empty file still
-// counts toward the digest of a tree that holds other files.
-func TestCollectTreeGroupsLeavesOutEmptyTrees(t *testing.T) {
-	t.Parallel()
-
-	h, tl, c, e := testHash("h"), testHash("t"), testHash("c"),
-		sha256.Sum256(nil)
-	recs := []scanRec{
-		{size: 0, head: e, tail: e, content: e, path: "/e/a/.gitkeep"},
-		{size: 0, head: e, tail: e, content: e, path: "/e/b/.gitkeep"},
-		{size: 10, head: h, tail: tl, content: c, path: "/p/x1/f"},
-		{size: 0, head: e, tail: e, content: e, path: "/p/x1/.gitkeep"},
-		{size: 10, head: h, tail: tl, content: c, path: "/p/x2/f"},
-		{size: 0, head: e, tail: e, content: e, path: "/p/x2/.gitkeep"},
-		// Without the empty file, /p/x3 is no copy of /p/x1.
-		{size: 10, head: h, tail: tl, content: c, path: "/p/x3/f"},
-	}
-
-	super, dirs := treeOf(t, recs)
-
-	got := groupPaths(collectTreeGroups(dirs, super, everyPathExists, nil))
 
 	want := [][]string{{"/p/x1", "/p/x2"}}
 	if !slices.EqualFunc(got, want, slices.Equal) {
@@ -543,98 +450,10 @@ func TestCollectTreeGroupsDifferingParents(t *testing.T) {
 
 	super, dirs := treeOf(t, recs)
 
-	got := groupPaths(collectTreeGroups(dirs, super, everyPathExists, nil))
+	got := groupPaths(collectTreeGroups(dirs, super, nil))
 
 	want := [][]string{{"/p/a/x", "/q/b/x"}}
 	if !slices.EqualFunc(got, want, slices.Equal) {
 		t.Fatalf("groups = %v, want %v", got, want)
 	}
 }
-
-// TestCollectTreeGroupsChecksOnlyReportedCopies checks that trees asks
-// whether a directory is on disk only for the members of the groups it
-// returns. It never asks about /a/proj/sub, which lies inside a copy
-// and whose group the group of /a/proj implies.
-func TestCollectTreeGroupsChecksOnlyReportedCopies(t *testing.T) {
-	t.Parallel()
-
-	f, g, u := testHash("f"), testHash("g"), testHash("u")
-	recs := []scanRec{
-		{size: 10, head: f, tail: f, content: f, path: "/a/proj/f"},
-		{size: 20, head: g, tail: g, content: g, path: "/a/proj/sub/g"},
-		{size: 10, head: f, tail: f, content: f, path: "/b/proj/f"},
-		{size: 20, head: g, tail: g, content: g, path: "/b/proj/sub/g"},
-		// /a lacks this file, so /a and /b are no copies of each other.
-		{size: 30, head: u, tail: u, content: u, path: "/b/lonely"},
-	}
-
-	super, dirs := treeOf(t, recs)
-
-	var checked []string
-
-	exists := func(path string) bool {
-		checked = append(checked, path)
-
-		return true
-	}
-
-	got := groupPaths(collectTreeGroups(dirs, super, exists, nil))
-
-	want := [][]string{{"/a/proj", "/b/proj"}}
-	if !slices.EqualFunc(got, want, slices.Equal) {
-		t.Fatalf("groups = %v, want %v", got, want)
-	}
-
-	slices.Sort(checked)
-
-	if !slices.Equal(checked, want[0]) {
-		t.Errorf("directories checked on disk = %q, want %q",
-			checked, want[0])
-	}
-}
-
-// TestCollectTreeGroupsDropsGroupLeftWithOneCopy checks that a group of
-// two copies, one of them gone, is not returned. If kept, it would
-// write no row, but the summary line would count it.
-func TestCollectTreeGroupsDropsGroupLeftWithOneCopy(t *testing.T) {
-	t.Parallel()
-
-	f := testHash("f")
-	recs := []scanRec{
-		{size: 10, head: f, tail: f, content: f, path: "/c/kept/f"},
-		{size: 10, head: f, tail: f, content: f, path: "/c/gone/f"},
-	}
-
-	super, dirs := treeOf(t, recs)
-
-	exists := func(path string) bool { return path != "/c/gone" }
-
-	got := groupPaths(collectTreeGroups(dirs, super, exists, nil))
-	if len(got) != 0 {
-		t.Errorf("groups = %v, want none", got)
-	}
-}
-
-// TestCollectTreeGroupsKeepsGroupLeftWithTwoCopies checks that a group
-// of three copies, one of them gone, is returned with the other two.
-func TestCollectTreeGroupsKeepsGroupLeftWithTwoCopies(t *testing.T) {
-	t.Parallel()
-
-	f := testHash("f")
-	recs := []scanRec{
-		{size: 10, head: f, tail: f, content: f, path: "/d/kept1/f"},
-		{size: 10, head: f, tail: f, content: f, path: "/d/gone/f"},
-		{size: 10, head: f, tail: f, content: f, path: "/d/kept2/f"},
-	}
-
-	super, dirs := treeOf(t, recs)
-
-	exists := func(path string) bool { return path != "/d/gone" }
-
-	got := groupPaths(collectTreeGroups(dirs, super, exists, nil))
-
-	want := [][]string{{"/d/kept1", "/d/kept2"}}
-	if !slices.EqualFunc(got, want, slices.Equal) {
-		t.Errorf("groups = %v, want %v", got, want)
-	}
-}