sneak/sfdupes
1
0
Fork 0
Code Issues 9 Pull Requests 2 Actions 53 Packages Projects Releases Wiki Activity

Compare commits

base: sneak/sfdupes:next
Branches Tags
sneak/sfdupes:main sneak/sfdupes:issue-48-lint-no-image sneak/sfdupes:issue-16-cli-surface-tests sneak/sfdupes:next sneak/sfdupes:issue-19-prettier-markdown sneak/sfdupes:issue-19-markdown-fmt
sneak/sfdupes:v0.0.1
..
compare: sneak/sfdupes:7cbb2d7f20620456ea4d9ae97c87d2af3f05d62a
Branches Tags
sneak/sfdupes:issue-48-lint-no-image sneak/sfdupes:issue-16-cli-surface-tests sneak/sfdupes:next sneak/sfdupes:issue-19-prettier-markdown sneak/sfdupes:main sneak/sfdupes:issue-19-markdown-fmt
sneak/sfdupes:v0.0.1
1 Commits
next .. 7cbb2d7f20
Author SHA1 Message Date
sneak 7cbb2d7f20 Stream report and trees instead of loading every record (closes #14)
check / check (push) Failing after 46s
Details 
report now has SQLite group the records and put the rows in report
order, helped by a new files_signature index on (size, head, tail,
content), and writes each row as it reads it. trees reads the records
in path order, where all the paths under a directory come together, so
it computes each directory's digest as soon as the stream leaves it and
keeps only its path, parent, digest and totals. Output is unchanged.

The tests that called the removed in-memory grouping functions now group
records stored in a database. New tests check that both commands give
the same output whatever order the records were inserted in, and that a
stdout failure partway through a long report is reported as one.

Model: opus-5-5
 2026-10-04 03:16:46 +00:00
14 changed files with 166 additions and 1385 deletions
Expand all files Collapse all files
.golangci.yml
+2 -66
View File
@@ -10,20 +10,14 @@ run:
linters:
default: all
enable:
# Successor to the deprecated gomodguard. Named explicitly, rather than
# left to `default: all`, because it carries the module policy below.
- gomodguard_v2
disable:
# Genuinely incompatible with project patterns
- exhaustruct # Requires all struct fields
- depguard # Dependency allow/block lists
- godot # Requires comments to end with periods
- wsl # Deprecated, replaced by wsl_v5
- wrapcheck # Too verbose for internal packages
- varnamelen # Short names like db, id are idiomatic Go
# Deprecated: the warning is attached to the old name, so it is
# silenced by disabling that name, not by enabling the successor.
- wsl # Deprecated, replaced by wsl_v5
- gomodguard # Deprecated, replaced by gomodguard_v2
settings:
lll:
line-length: 88
@@ -34,64 +28,6 @@ linters:
max-complexity: 15
dupl:
threshold: 100
depguard:
# Test-support code must not be compiled into the shipped binary. A
# test-support package exists to hand a test privileges the program
# itself must never have, so a file that is not a test must not import
# one. Test files, and the files inside a package whose directory name
# ends in `test`, are where that code belongs, and are exempt.
#
# The deny list below is the one part of this file a repository is
# expected to extend, and the only part it may. depguard matches an
# import path against a list of prefixes, so it cannot be told "any path
# whose last segment ends in test"; a repository's own test-support
# packages have to be named here one at a time, by full import path,
# under a module path that differs from repository to repository. Add
# them; change nothing else.
rules:
test-support:
list-mode: lax
files:
- "$all"
- "!$test"
- "!**/*test/**"
deny:
- pkg: net/http/httptest
desc: >-
Test-support code belongs in test files and in packages whose
directory name ends in test, not in the shipped binary.
# Only decisions already recorded in the Go package defaults are
# listed here. Every entry matches the module path exactly.
gomodguard_v2:
blocked:
- module: github.com/rs/zerolog
recommendations:
- log/slog
reason: "Structured logging is stdlib log/slog."
# One entry per pre-fork module path, because the later releases
# are separate paths. A prefix match would be shorter but would
# also reach github.com/go-redis/redismock, the test double for
# the successor these entries recommend.
- module: github.com/go-redis/redis
recommendations:
- github.com/redis/go-redis/v9
reason: "Pre-fork module; use the maintained go-redis v9."
- module: github.com/go-redis/redis/v7
recommendations:
- github.com/redis/go-redis/v9
reason: "Pre-fork module; use the maintained go-redis v9."
- module: github.com/go-redis/redis/v8
recommendations:
- github.com/redis/go-redis/v9
reason: "Pre-fork module; use the maintained go-redis v9."
- module: github.com/sergi/go-diff
recommendations:
- github.com/aymanbagabas/go-udiff
reason: "No unified diff output; use go-udiff."
- module: github.com/hexops/gotextdiff
recommendations:
- github.com/aymanbagabas/go-udiff
reason: "Unmaintained fork; use go-udiff."
issues:
max-issues-per-linter: 0
Dockerfile
+8 -26
View File
@@ -51,21 +51,14 @@ RUN echo "gate lint, epoch ${CHECK_EPOCH}" && \
FROM golang@sha256:56961d79ea8129efddcc0b8643fd8a5416b4e6228cfd477e3fd61deb2672c587 AS builder
# We never build or run as root. Create an unprivileged user and point
# HOME and the build cache at its home so go build and go test can write
# it when we drop to it below. $GOPATH/bin is deliberately not on PATH:
# script/bootstrap no longer `go install`s anything (the linter runs
# from a pinned image, never from a host install), so nothing lands
# HOME and the Go caches at its home so go build and go test can write
# their caches when we drop to it below. $GOPATH/bin is deliberately not
# on PATH: script/bootstrap no longer `go install`s anything (the linter
# runs from a pinned image, never from a host install), so nothing lands
# there and adding it would only widen what this image resolves.
#
# The module cache is kept outside that home, at the base image's
# default /go/pkg/mod, and belongs to root: script/bootstrap fills it as
# root. Do not move it into the home and hand it over with `chown -R`:
# that walks every file in it, which took from about 80 s to over ten
# minutes on a shared host, depending on load.
RUN adduser -D -u 1000 builder
ENV HOME=/home/builder
ENV GOPATH=/home/builder/go
ENV GOMODCACHE=/go/pkg/mod
ENV GOCACHE=/home/builder/.cache/go-build
WORKDIR /src
@@ -90,22 +83,11 @@ COPY script/ script/
COPY go.mod go.sum ./
RUN script/bootstrap
# Hand builder only what it writes to, without walking the module cache.
# This layer stays cached with bootstrap.
# - /src itself: make build writes the binary into it, and git refuses
# a repository whose top directory belongs to another user.
# - the module cache's cache/download directory itself, not what is in
# it: Go only reads the downloaded modules, but make build saves its
# lookup of this module's own version from git there, in a new
# directory named after the module path.
# - builder's home: the go commands bootstrap ran as root left Go's
# telemetry files there, a few small files.
RUN chown builder:builder /src /go/pkg/mod/cache/download && \
chown -R builder:builder /home/builder
COPY . .
# The sources are handed to builder as they are copied, so no layer has
# to walk them. Then drop root before running any checks or builds.
COPY --chown=builder:builder . .
# Hand the sources and caches to the unprivileged user, then drop root
# before running any checks or builds.
RUN chown -R builder:builder /src /home/builder
USER builder
# Fail the build unless the branch is green. Runs as non-root so the
README.md
+10 -168
View File
@@ -51,122 +51,6 @@ daily `sfdupes scan` cron job, with the reporting commands run
interactively whenever needed; their results are as fresh as the last
completed scan.
### Install
With Go installed, this builds and installs the current `main` branch:
```sh
go install sneak.berlin/go/sfdupes@main
```
The binary goes to `$(go env GOPATH)/bin`, or to `$GOBIN` when that is
set. A binary installed this way reports its version as `dev`; one
built from a clone or into the Docker image carries the git tag or
commit it was built from.
From a clone, `make build` writes the binary to `./sfdupes`:
```sh
git clone https://git.eeqj.de/sneak/sfdupes.git
cd sfdupes
make build
```
Copy the binary to `/usr/local/bin` for the cron job below.
`make docker` builds the Docker image, tagged `sfdupes`, after running
the tests and the linter (see "Build"). The image runs `sfdupes` as
root with the database at its default path, so a bind mount of
`/var/lib/sfdupes` keeps the database between runs. Mount the scanned
tree at the same path inside the container as on the host; read-only
is enough. The database records paths as the container sees them, so
the reports then name the host's paths.
```sh
make docker
docker run --rm -v /srv:/srv:ro -v /var/lib/sfdupes:/var/lib/sfdupes \
sfdupes scan /srv
docker run --rm -v /var/lib/sfdupes:/var/lib/sfdupes sfdupes report > dupes.tsv
```
### Daily scan from cron
Run `scan` as root, so that it can read every file: a path it cannot
read is skipped with a warning and loses its database record (see
"Rules for the walk"). As a file `/etc/cron.d/sfdupes`:
```
30 3 * * * root /usr/local/bin/sfdupes scan /srv 2>>/var/log/sfdupes.log || tail -n 3 /var/log/sfdupes.log
```
- The database is `/var/lib/sfdupes/db.sqlite`, created with its
directory by the first scan. To keep it elsewhere, set
`SFDUPES_DATABASE=/path/to/db.sqlite` before the command on the same
line.
- `scan` writes nothing to stdout. Its stderr, appended here to
`/var/log/sfdupes.log`, holds a plain progress line as each phase
starts and then at most every 5 seconds, a warning for each path it
skips, and the summary line (see "Progress" and "`scan` mode"). The
log grows with every scan; rotate it like any other.
- Skipped paths do not fail a scan: it still exits 0, and cron sends
nothing. A scan that fails, or is stopped by `SIGINT` or `SIGTERM`,
exits 1 with the reason among the last lines of the log; `tail`
prints them, and cron mails them to root if the host can send mail.
- A scan still running when the next one starts carries on. The new
one fails at once, and the lines cron mails include
`sfdupes: another scan is running (lock held on /var/lib/sfdupes/db.sqlite.lock)`.
- `report` and `trees` need only read access to the database (see
"Database"). Under the usual umask of `022` the first scan creates
it readable by every user, so an unprivileged user can run them
against root's database.
### Reading the reports
Each row of `report` names two copies of one file, and each row of
`trees` two copies of one directory tree (see "Report output format"
and "Trees output format"). In a group of copies, the path that sorts
first byte by byte is `first` and every other path is a `dupe` of it.
`first` says nothing about which copy is the original or the oldest;
which copy to keep is your choice.
A row is a candidate, not proof:
- The reports read only the database, so they show the files as of
the last scan; a file may have changed or gone since.
- A file of 50 MiB or more is compared only on samples of its content
(see "Duplicate detection").
- Paths that are hard links to one file are listed as duplicates, but
they share their data, so removing one frees nothing.
Compare a pair byte for byte before removing either copy. For the row
`/srv/a/big.iso`, `/srv/b/big-copy.iso`, `4294967296`:
```sh
cmp /srv/a/big.iso /srv/b/big-copy.iso && echo identical
[ /srv/a/big.iso -ef /srv/b/big-copy.iso ] && echo "hard links"
```
`cmp` prints nothing and exits 0 only when every byte matches, and
otherwise reports where the files differ. The second line prints
`hard links` when the two paths are the same file, so removing either
frees nothing.
A path holding a backslash, tab, newline or carriage return is escaped
in the reports (see "Report output format"). Undo the escapes before
using it. `printf '%b'` does exactly that, because every backslash in
an escaped path starts one of the four escapes. Command substitution
drops trailing newlines, so print an `x` after the path and remove it
afterwards, or a path that ends in a newline names a different file:
```sh
p="$(printf '%bx' '/srv/a/tab\tname.txt')"; p="${p%x}"
cmp "$p" /srv/b/tab-copy.txt
```
Check a `trees` row with `diff -r`, which compares the two trees file
by file and also names anything present in only one of them, such as
an empty directory or a symlink, which `trees` does not see.
## Rationale
Duplicate finders that hash entire files do not scale to the target
@@ -228,8 +112,8 @@ Goals, in order:
again. `scan` is designed to be cronned; the reports run at any
time against the last completed scan.
4. **Clean stream separation.** Everything on stdout is machine-readable
data. All progress, warnings, summaries, and help and usage text go
to stderr. Never mix them.
data. All progress, warnings, and summaries go to stderr. Never mix
them.
### Constraints
@@ -265,27 +149,15 @@ Three subcommands, all implemented:
sfdupes scan [--workers N] [-x] PATH...
sfdupes report > dupes.tsv
sfdupes trees > dupetrees.tsv
sfdupes --version
sfdupes [command] --help
```
`--workers N` sets the size of each `scan` worker pool (default: the
number of CPUs), and `-x` (`--one-file-system`) keeps the walk of each
operand on that operand's filesystem; both are described under
"`scan` mode". `sfdupes --version` (or `-v`) prints one line,
`sfdupes VERSION`, to stdout and exits 0, writing nothing to stderr.
`-h` or `--help`, alone or after a subcommand, prints the help text to
stderr and exits 0, writing nothing to stdout.
### Database
All three subcommands operate on a single SQLite database file:
- Location: the value of the `SFDUPES_DATABASE` environment variable
when set and non-empty, otherwise `/var/lib/sfdupes/db.sqlite`.
There is no command-line flag. The path names the file exactly,
whatever characters it holds (`?`, `#` and `%` included); a
relative path is relative to the working directory.
There is no command-line flag.
- `scan` creates the database (and its parent directory) on first
use. `report` and `trees` require an existing database; a missing
database file is a fatal error (exit 1) telling the user to run
@@ -312,9 +184,8 @@ All three subcommands operate on a single SQLite database file:
(keeping the WAL small and letting concurrent reports observe
progress), so a report may see a scan's changes partially applied,
and a scan that dies partway leaves a valid database holding
every batch committed so far (an interrupted scan also commits the
batch in progress, see "Error handling and exit codes"); the next
scan skips those records and converges toward the filesystem.
everything hashed so far; the next scan skips those records and
converges toward the filesystem.
- `scan` switches the database back to rollback-journal mode when it
closes it, so between scans the database file alone holds the whole
database. Each switch needs the database to itself: a `scan` that
@@ -331,12 +202,7 @@ All three subcommands operate on a single SQLite database file:
`-shm` files beside it, which SQLite creates with the database
file's permissions.
- Schema (`PRAGMA user_version` is the schema version, currently 1; a
database with any other version is a fatal error. `scan` creates
the schema and sets the version in one transaction, so a first scan
stopped while doing so leaves an empty database the next scan sets
up. A database at version 0 that already has a `files` table was
therefore not made by sfdupes; every subcommand refuses it with an
error telling the user to remove the file and rescan):
database with any other version is a fatal error):
```sql
CREATE TABLE files (
@@ -568,9 +434,7 @@ Rules for the walk:
Concurrency: the walk phase (which also stats files), the hash phase,
and the content phase each use a worker pool of `--workers` workers
(default `runtime.NumCPU()`); the walk parallelizes across
directories, hashing across files. `--workers` must be at least 1: a
smaller value is a usage error, reported in one line on stderr with
exit 2 before anything is scanned. All three phases are seek-bound on
directories, hashing across files. All three phases are seek-bound on
spinning disks, so raising `--workers` well past the core count can
help on pools with many spindles. The main goroutine owns
partitioning, database writes, and progress rendering; progress
@@ -752,8 +616,6 @@ Additional requirements:
waits for its next item.
- A warning printed during a phase always lands on a line of its own,
never inside the progress display.
- A bar whose phase stops short of its total, as an interrupted one
does, is left as last drawn rather than filled up.
- `report` and `trees` modes need no progress display, only their
stderr summaries.
@@ -763,11 +625,9 @@ Additional requirements:
- `1`: fatal error (e.g., a `PATH` operand does not exist, another
`scan` is already running against the same database, the database
cannot be created/opened/read/written, a missing database for
`report`/`trees`, stdout write failure), or a `scan` stopped by
`SIGINT` or `SIGTERM` (see below).
- `2`: usage error (including `scan` with no `PATH` operand, `scan`
with `--workers` below 1, and `report`/`trees` with any positional
argument).
`report`/`trees`, stdout write failure).
- `2`: usage error (including `scan` with no `PATH` operand and
`report`/`trees` with any positional argument).
A stdout write failure, such as a full disk, is reported in one line on
stderr and exits 1. Two cases never reach sfdupes as a failed write:
@@ -781,24 +641,6 @@ stderr and exits 1. Two cases never reach sfdupes as a failed write:
the output is discarded and the run succeeds, as with
`> /dev/null`.
`scan` stops cleanly on `SIGINT` (Ctrl-C) or `SIGTERM`. Its workers
stop taking work, each finishing at most the directory listing or file
it is reading; the progress display is finished; and the records it has
hashed but not yet committed are committed, so the next scan does not
hash them again. Apart from that commit it starts no further writes or
deletions: records are deleted only after a complete walk, so those
under paths an interrupted walk never reached are kept. The database is
closed and the lock released as on any other exit, the line
`scan: interrupted after N files` goes to stderr, N being the number of
files the walk reached, and the exit code is 1. The next scan skips the
records already written and converges as usual.
After the first signal `scan` stops catching them, so a second one ends
it at once, as an uncaught signal does: the records not yet committed
are lost, and the database is left valid, as when any scan dies (see
"Database"). A `SIGINT` that `scan` inherits as ignored, as a script's
background job does, stays ignored.
## Entrypoints
This repository adheres to the
TODO.md
-46
View File
@@ -29,52 +29,6 @@
# Completed Steps
- `.golangci.yml` replaced with the current canonical copy, which uses
`gomodguard_v2`, so lint no longer prints a deprecation warning
(2026-10-04, https://git.eeqj.de/sneak/sfdupes/issues/26)
- a test fails when either `hashWorker` cancellation check in `scan.go`
is removed (2026-10-04, https://git.eeqj.de/sneak/sfdupes/issues/83)
- a database path holding `?`, `#` or `%` opens exactly the file it names
(2026-10-04, https://git.eeqj.de/sneak/sfdupes/issues/55)
- `scan` rejects `--workers` below 1 as a usage error instead of
running single-threaded (2026-10-04,
https://git.eeqj.de/sneak/sfdupes/issues/10)
- a test fails when either walk cancellation check in `scan.go` is
removed (2026-10-04, https://git.eeqj.de/sneak/sfdupes/issues/81)
- test that `scan` refuses a database with another schema version
(2026-10-04, https://git.eeqj.de/sneak/sfdupes/issues/64)
- correct four inaccurate comments in `cancel_test.go` and rename
`walkCancelInFlightDirs` to `walkCancelInFlightFiles` (2026-10-04,
https://git.eeqj.de/sneak/sfdupes/issues/33)
- test the `-x` filesystem-boundary rules in `subdirJob` (2026-10-04,
https://git.eeqj.de/sneak/sfdupes/issues/17)
- `scan` creates the schema in one transaction; a version-0 database with a
`files` table is refused with a clear schema-version error (2026-10-04,
https://git.eeqj.de/sneak/sfdupes/issues/11)
- README documents install, Docker, a daily cron scan and how to read
and check the reports (2026-10-04,
https://git.eeqj.de/sneak/sfdupes/issues/54)
- the `Dockerfile` build stage keeps the Go module cache out of `builder`'s
home and copies the sources with `--chown`, so no `chown -R` walks them
(2026-10-04, https://git.eeqj.de/sneak/sfdupes/issues/43)
- `--version` prints `sfdupes VERSION` to stdout; README documents it and
`--help` (2026-10-04, https://git.eeqj.de/sneak/sfdupes/issues/15)
- `scan` stops cleanly on `SIGINT` or `SIGTERM`: commits what it has
hashed, deletes nothing more, exits 1 (2026-10-04,
https://git.eeqj.de/sneak/sfdupes/issues/5)
- `report` and `trees` stream the records instead of holding them all in
memory; the schema gains the `files_signature` index (2026-10-04,
https://git.eeqj.de/sneak/sfdupes/issues/14)
cancel_test.go
+49 -383
View File
@@ -4,35 +4,20 @@ import (
"context"
"database/sql"
"errors"
"fmt"
"os"
"os/signal"
"path/filepath"
"slices"
"strconv"
"strings"
"sync"
"sync/atomic"
"syscall"
"testing"
"time"
)
// This file gathers the tests for scan cancellation and worker-pool
// unwinding. Everything it exercises lives in scan.go, so by the repo's
// convention of one test file per source file it would belong in
// scan_test.go. It is kept separate on purpose: cancellation behaviour
// cuts across both the walk pool and the hash pool as a single concern,
// and scan_test.go is already over 1,600 lines. That is the deliberate
// exception the convention otherwise expects to be stated.
// poolUnwind bounds how long a test waits for a cancellation to take
// effect: for a goroutine to return or a channel to close once its
// context is cancelled, or for a signal to cancel the scan's context.
// Only a failing run waits this long, and the bound is what makes that
// failure an assertion instead of a hang. A call made without it, as
// most of this file's scans are, has no bound: a regression that parks
// it is caught only as the test binary's own timeout.
// poolUnwind bounds how long a goroutine is given to leave a pool
// after its context is cancelled. Only a failing run ever waits this
// long: a pool that ignored its cancellation parks forever, and this
// is what turns that into a failed assertion instead of a suite that
// hangs until the test binary's own timeout.
const poolUnwind = 2 * time.Second
// walkClock is a context whose cancellation is driven by the scan's
@@ -43,14 +28,9 @@ const poolUnwind = 2 * time.Second
//
// The accounting behind the n chosen by each test: every blocking
// channel operation in the walk selects on Done, so the walk spends
// one consultation per file event plus a couple per directory. The
// index load that runs ahead of it also consults Done, but a bounded
// number of times that does not grow with the record count. The tests
// depend on that property, not on the bound's exact value: each test
// sets n from the consultations of the walk, plus those of the hash
// phase when it cancels mid-hash, far from both ends of the phase it
// interrupts, so the cancellation lands inside that phase whatever the
// record count.
// one consultation per file event plus a couple per directory, while
// the index load that runs ahead of it spends a small fixed number
// (three) whatever the record count.
type walkClock struct {
n int64
seen atomic.Int64
@@ -106,14 +86,11 @@ func (c *walkClock) Value(_ any) any {
// directory still queued and only the handful already in flight can
// emit anything more.
const (
walkCancelDirs = 100
walkCancelFilesPerDir = 20
walkCancelFiles = walkCancelDirs * walkCancelFilesPerDir
walkCancelWorkers = 4
// The most files the walkCancelWorkers directories already in
// flight when the scan is cancelled can still emit, at
// walkCancelFilesPerDir each. A file count, not a directory count.
walkCancelInFlightFiles = walkCancelWorkers * walkCancelFilesPerDir
walkCancelDirs = 100
walkCancelFilesPerDir = 20
walkCancelFiles = walkCancelDirs * walkCancelFilesPerDir
walkCancelWorkers = 4
walkCancelInFlightDirs = walkCancelWorkers * walkCancelFilesPerDir
)
// walkCancelAtDone is the consultation on which the fixture's context
@@ -173,13 +150,9 @@ func assertRecordsIntact(t *testing.T, db *sql.DB, before []string) {
// Every one of those records would look vanished to the update phase.
// The guard is what stops the scan there, and this test is what
// notices if it stops doing so: deleting the guard, or making it
// unreachable, makes the scan carry its truncated view into the update
// phase, which counts every record the walk never reached for removal.
//
// The syncScan call here is not bounded by poolUnwind: a regression
// that left a worker pool parked would hang it, and that regression is
// caught only by the test binary's own timeout, not by a quick
// assertion.
// unreachable, makes the scan carry its truncated view into a later
// phase and fail there instead, with a wrapped error rather than the
// bare cancellation.
//
//nolint:paralleltest // counts goroutines: must not run beside others
func TestSyncScanCancelledMidWalkKeepsRecords(t *testing.T) {
@@ -209,10 +182,10 @@ func TestSyncScanCancelledMidWalkKeepsRecords(t *testing.T) {
// assertWalkGuardAborted checks that the scan stopped at the post-walk
// guard: with a census that is neither empty (the walk really ran)
// nor complete (it really was cut short), and with no record counted
// for removal. A removal count means the partial census was carried
// past the guard into the update phase, which is the failure this test
// exists to catch.
// nor complete (it really was cut short), and with the guard's own
// bare cancellation as the error. A wrapped error means the partial
// census was carried past the guard into the hash or update phase,
// which is the failure this test exists to catch.
func assertWalkGuardAborted(t *testing.T, st scanStats, err error) {
t.Helper()
@@ -221,6 +194,12 @@ func assertWalkGuardAborted(t *testing.T, st scanStats, err error) {
err, context.Canceled)
}
if errors.Unwrap(err) != nil {
t.Errorf("syncScan reported %q, want the guard's bare "+
"cancellation: a wrapped error means the truncated census "+
"reached a later phase", err)
}
if st.unchanged == 0 {
t.Fatalf("stats = %+v: the census is empty, so the walk never "+
"ran and the guard was reached for the wrong reason", st)
@@ -232,11 +211,10 @@ func assertWalkGuardAborted(t *testing.T, st scanStats, err error) {
}
// The workers drop every directory still queued once the scan is
// cancelled, so only the files in the directories already in flight
// can add to the census after the fact. A census beyond that bound
// would mean the cancellation was not observed where it should have
// been.
limit := walkCancelAtDone + walkCancelInFlightFiles
// cancelled, so only the directories already in flight can add to
// the census after the fact. A census beyond that bound would mean
// the cancellation was not observed where it should have been.
limit := walkCancelAtDone + walkCancelInFlightDirs
if st.unchanged > limit {
t.Errorf("census covers %d files, want at most %d: the walk kept "+
"taking directories off the queue after cancellation",
@@ -282,242 +260,6 @@ func TestSyncScanCancelledBeforeLoadIndex(t *testing.T) {
assertRecordsIntact(t, db, before)
}
// hashCancelAtDone is the consultation on which the mid-hash test's
// context cancels itself. The walk of buildWalkCancelTree spends about
// one per file and three per directory, and the hash phase then one per
// file hashed, so this lands about half way through the hash phase.
const hashCancelAtDone = walkCancelFiles + 3*walkCancelDirs +
walkCancelFiles/2
// TestSyncScanCancelledMidHashKeepsHashedRecords cancels a first scan
// part-way through its hash phase. The fixture holds fewer files than a
// batch, so every file hashed is still waiting to be committed: the scan
// must commit them all before it returns, and the next scan must hash
// only the rest.
func TestSyncScanCancelledMidHashKeepsHashedRecords(t *testing.T) {
t.Parallel()
dir := buildWalkCancelTree(t)
db := openTestDB(t)
st, err := syncScan(newWalkClock(hashCancelAtDone), db,
[]string{dir}, walkCancelWorkers, false)
if !errors.Is(err, context.Canceled) {
t.Fatalf("syncScan cancelled mid-hash = %v, want %v",
err, context.Canceled)
}
if st.walked != walkCancelFiles || st.added == 0 ||
st.added >= walkCancelFiles {
t.Fatalf("stats = %+v: want the walk complete and the hash phase "+
"cut short", st)
}
if got := len(dbRecords(t, db)); got != st.added {
t.Errorf("%d records after the cancelled scan, want the %d it hashed",
got, st.added)
}
hashed := st.added
st = syncTree(t, db, dir)
if st.added != walkCancelFiles-hashed || st.unchanged != hashed {
t.Errorf("next scan stats = %+v, want %d added %d unchanged",
st, walkCancelFiles-hashed, hashed)
}
}
// storedPaths opens the database at path as report does, which fails
// unless it is a valid database, and returns its records' paths.
func storedPaths(t *testing.T, path string) []string {
t.Helper()
db, err := openReportDatabase(t.Context(), path)
if err != nil {
t.Fatal(err)
}
defer func() { _ = db.Close() }()
return recordPaths(dbRecords(t, db))
}
// TestRunScanInterrupted calls the scan entrypoint with a context that
// is already cancelled, as when a signal arrives at once. It must return
// errInterrupted promptly with its one line on stderr, leave the
// database valid and as it was, and leave nothing in the way of the
// next scan, which must bring the database up to date.
func TestRunScanInterrupted(t *testing.T) {
path := testDBPath(t)
t.Setenv(databaseEnv, path)
stderr := captureStderr(t)
dir := buildSmokeTree(t)
err := runScan(t.Context(), []string{dir}, walkCancelWorkers, false)
if err != nil {
t.Fatal(err)
}
before := storedPaths(t, path)
// A vanished file and a new one: the interrupted scan records
// neither.
gone := filepath.Join(dir, "a", "unique.bin")
err = os.Remove(gone)
if err != nil {
t.Fatal(err)
}
added := writeFile(t, dir, "a/new.bin", pattern(50, 10))
shown := len(stderr())
done := make(chan struct{})
go func() {
defer close(done)
err = runScan(cancelledContext(t), []string{dir}, walkCancelWorkers,
false)
}()
awaitReturn(t, done, "runScan")
if !errors.Is(err, errInterrupted) {
t.Fatalf("runScan on a cancelled context = %v, want %v",
err, errInterrupted)
}
want := "scan: interrupted after 0 files\n"
if got := stderr()[shown:]; got != want {
t.Errorf("stderr = %q, want %q", got, want)
}
assertNoSidecars(t, path)
if got := storedPaths(t, path); !slices.Equal(got, before) {
t.Errorf("records = %q after the interrupted scan, want %q",
got, before)
}
err = runScan(t.Context(), []string{dir}, walkCancelWorkers, false)
if err != nil {
t.Fatal(err)
}
got := storedPaths(t, path)
if slices.Contains(got, gone) || !slices.Contains(got, added) {
t.Errorf("records = %q after the next scan, want %q gone and %q "+
"added", got, gone, added)
}
}
// TestRunScanInterruptedMidHash interrupts the scan entrypoint part-way
// through its hash phase, after the database is open. It must return
// errInterrupted, release the lock, end stderr with its line counting
// every file the walk reached, close the database out of WAL mode, and
// keep the records it hashed.
func TestRunScanInterruptedMidHash(t *testing.T) {
path := testDBPath(t)
t.Setenv(databaseEnv, path)
stderr := captureStderr(t)
dir := buildWalkCancelTree(t)
err := runScan(newWalkClock(hashCancelAtDone), []string{dir},
walkCancelWorkers, false)
if !errors.Is(err, errInterrupted) {
t.Fatalf("runScan interrupted mid-hash = %v, want %v",
err, errInterrupted)
}
holdScanLock(t, path)
want := fmt.Sprintf("scan: interrupted after %d files\n", walkCancelFiles)
if got := stderr(); !strings.HasSuffix(got, want) {
t.Errorf("stderr = %q, want it to end with %q", got, want)
}
assertNoSidecars(t, path)
db, err := openReportDatabase(t.Context(), path)
if err != nil {
t.Fatal(err)
}
defer func() { _ = db.Close() }()
// A plain close also removes the sidecars, but leaves WAL mode on.
var mode string
err = db.QueryRowContext(t.Context(), "PRAGMA journal_mode").Scan(&mode)
if err != nil {
t.Fatal(err)
}
if mode != "delete" {
t.Errorf("journal mode = %q after the interrupted scan, want %q",
mode, "delete")
}
kept := len(dbRecords(t, db))
if kept == 0 || kept >= walkCancelFiles {
t.Errorf("%d records after the interrupted scan, want those it "+
"hashed: some but not all of the %d files", kept, walkCancelFiles)
}
}
// TestInterruptContextCatchesSIGTERM sends SIGTERM to the test process
// while the scan's handler is installed, and checks that it cancels the
// scan's context.
//
//nolint:paralleltest // signals the whole process: must not run beside a scan
func TestInterruptContextCatchesSIGTERM(t *testing.T) {
// Caught here as well, so that a handler that misses SIGTERM fails
// this test instead of ending the test process.
caught := make(chan os.Signal, 1)
signal.Notify(caught, syscall.SIGTERM)
defer signal.Stop(caught)
ctx, stop := interruptContext(t.Context())
defer stop()
err := syscall.Kill(os.Getpid(), syscall.SIGTERM)
if err != nil {
t.Fatal(err)
}
select {
case <-ctx.Done():
case <-time.After(poolUnwind):
t.Fatal("SIGTERM did not cancel the scan's context")
}
}
// TestCommitFullBatchKeepsFailedBatch checks that a full batch whose
// commit fails, as it does once the scan is interrupted, stays in the
// batch, so that syncScan's final commit saves it.
func TestCommitFullBatchKeepsFailedBatch(t *testing.T) {
t.Parallel()
s := &scanState{db: openTestDB(t)}
for i := range updateBatchSize {
s.batch = append(s.batch, scanRec{path: "/f" + strconv.Itoa(i)})
}
err := s.commitFullBatch(cancelledContext(t))
if !errors.Is(err, context.Canceled) {
t.Fatalf("commitFullBatch on a cancelled context = %v, want %v",
err, context.Canceled)
}
if len(s.batch) != updateBatchSize {
t.Errorf("batch holds %d records after the failed commit, want %d",
len(s.batch), updateBatchSize)
}
}
// drainClosed counts the values received from ch until it closes,
// failing the test if it does not close within poolUnwind. A pool that
// ignored its cancellation leaves its channel open with its goroutines
@@ -586,49 +328,20 @@ func TestSendEventAbandonsBlockedSend(t *testing.T) {
awaitReturn(t, done, "sendEvent")
}
// TestWalkOneDirStopsWhenCancelled checks that a cancelled scan stops
// reading a directory instead of going through the rest of its
// entries. A walk that kept going would return the subdirectory below
// to descend into. Unlike a file event, that return is not a send the
// cancellation can abandon, so the test catches the regression every
// time.
func TestWalkOneDirStopsWhenCancelled(t *testing.T) {
t.Parallel()
dir := t.TempDir()
err := os.Mkdir(filepath.Join(dir, "sub"), 0o750)
if err != nil {
t.Fatal(err)
}
// Unbuffered and unread: on a cancelled scan every send gives up.
events := make(chan walkEvent)
subs := walkOneDir(cancelledContext(t), dirJob{path: dir}, false, events)
if len(subs) != 0 {
t.Errorf("cancelled walkOneDir returned %+v to descend into, "+
"want none", subs)
}
}
// TestWalkWorkersDropQueuedDirs checks that cancelled walk workers keep
// reading jobs and drop the directories rather than stopping their
// read: the range over jobs has to run out for the pool to tear down
// and close its event stream. The queued directory does not exist, so
// a worker that walked it anyway would send a warning before
// walkOneDir's own cancellation check could stop it. On a cancelled
// scan that send delivers or gives up at random, so with 64 jobs
// queued the regression has a one in 2^64 chance of passing.
// and close its event stream.
func TestWalkWorkersDropQueuedDirs(t *testing.T) {
t.Parallel()
missing := filepath.Join(t.TempDir(), "missing")
dir := t.TempDir()
writeEmptyFiles(t, dir, walkCancelFilesPerDir)
jobs, _, events := startWalkWorkers(cancelledContext(t), 2, false)
for range 64 {
jobs <- dirJob{path: missing}
for range 4 {
jobs <- dirJob{path: dir}
}
close(jobs)
@@ -699,11 +412,7 @@ func TestDispatchDirsClosesJobsWhenCancelled(t *testing.T) {
// TestFeedHashJobsClosesJobsWhenCancelled checks that the hash feeder
// abandons the runs it has not queued yet and still closes the job
// channel, which is what lets the workers' range terminate. The
// receive on jobs below is not bounded: a feeder that returned without
// closing jobs would leave that receive with no sender and no close, so
// this regression is caught by the test binary's timeout rather than by
// a bounded assertion.
// channel, which is what lets the workers' range terminate.
func TestFeedHashJobsClosesJobsWhenCancelled(t *testing.T) {
t.Parallel()
@@ -729,84 +438,41 @@ func TestFeedHashJobsClosesJobsWhenCancelled(t *testing.T) {
// TestHashWorkerDropsQueuedRuns checks that a cancelled hash worker
// keeps reading jobs and drops the runs rather than reading files
// nobody wants the hashes of — while still letting the range run out
// so the pool tears down. The hash function records that it was
// called, so a worker that hashed the queued run anyway is caught
// every time.
// so the pool tears down. The queued run names a file that does not
// exist, so a worker that hashed it anyway would produce a result.
func TestHashWorkerDropsQueuedRuns(t *testing.T) {
t.Parallel()
done := make(chan struct{})
jobs := make(chan []fileRec, 1)
results := make(chan hashResult)
results := make(chan hashResult, 1)
jobs <- []fileRec{{path: filepath.Join(t.TempDir(), "missing"), size: 1}}
run := []fileRec{{path: filepath.Join(t.TempDir(), "missing"), size: 1}}
jobs <- run
close(jobs)
var hashed atomic.Bool
hash := func(path string, size int64) (string, string, string, error) {
hashed.Store(true)
return hashSignature(path, size)
}
go func() {
defer close(done)
hashWorker(cancelledContext(t), jobs, results, hash)
hashWorker(cancelledContext(t), jobs, results, hashSignature)
}()
awaitReturn(t, done, "hashWorker")
if hashed.Load() {
t.Error("cancelled hash worker hashed the queued run, want it dropped")
select {
case r := <-results:
t.Errorf("cancelled hash worker produced %+v, want the run dropped",
r)
default:
}
}
// TestHashWorkerAbandonsBlockedSend checks that a hash worker with a
// result to deliver and nobody to deliver it to leaves once the scan
// is cancelled, instead of holding the pool open. The scan tests do
// not catch this: stop drains results, which frees a parked worker
// anyway.
func TestHashWorkerAbandonsBlockedSend(t *testing.T) {
t.Parallel()
ctx, cancel := context.WithCancel(t.Context())
defer cancel()
done := make(chan struct{})
jobs := make(chan []fileRec, 1)
// Unbuffered and unread, with jobs left open: the worker's only way
// out is the cancellation case beside its send.
results := make(chan hashResult)
jobs <- []fileRec{{path: filepath.Join(t.TempDir(), "missing"), size: 1}}
// The scan is cancelled while the worker hashes, so the worker has
// already passed the check that drops queued runs.
hash := func(path string, size int64) (string, string, string, error) {
cancel()
return hashSignature(path, size)
}
go func() {
defer close(done)
hashWorker(ctx, jobs, results, hash)
}()
awaitReturn(t, done, "hashWorker")
}
// TestHashPhaseCancelledReturnsContextError checks the result loop's
// own exit: with the pool cancelled, no result will ever arrive, and
// the loop must leave through the cancellation rather than wait for a
// receive that cannot happen. This call is not bounded by poolUnwind: a
// loop that dropped its cancellation case would block on that receive,
// so the regression surfaces as the test binary's timeout rather than
// as a bounded assertion.
// receive that cannot happen.
func TestHashPhaseCancelledReturnsContextError(t *testing.T) {
t.Parallel()
db.go
+5 -69
View File
@@ -6,7 +6,6 @@ import (
"errors"
"fmt"
"io/fs"
"net/url"
"os"
"path/filepath"
"slices"
@@ -108,19 +107,7 @@ const reportParams = "mode=ro" +
// openDB opens the SQLite database at path with the connection
// parameters params. It does not create or verify the schema.
func openDB(path, params string) (*sql.DB, error) {
// The path is escaped into a file: URI, so ?, # and % in it stay
// part of the file name. SQLite reads what follows file:// up to
// the next / as a host name, so an absolute path goes after an
// empty host (file:///abs) and a relative path goes without one
// (file:rel).
uri := url.URL{
Scheme: "file",
OmitHost: !filepath.IsAbs(path),
Path: path,
RawQuery: params,
}
db, err := sql.Open("sqlite", uri.String())
db, err := sql.Open("sqlite", "file:"+path+"?"+params)
if err != nil {
return nil, fmt.Errorf("open database %s: %w", path, err)
}
@@ -232,12 +219,6 @@ func openReportDatabase(ctx context.Context,
}
v, err := userVersion(ctx, db)
if err == nil && v == 0 {
// An empty database passes this check and fails the version
// check below.
err = checkUnversioned(ctx, db)
}
if err != nil {
_ = db.Close()
@@ -264,11 +245,6 @@ func initSchema(ctx context.Context, db *sql.DB) error {
switch v {
case 0:
err = checkUnversioned(ctx, db)
if err != nil {
return err
}
return createSchema(ctx, db)
case schemaVersion:
return nil
@@ -278,65 +254,25 @@ func initSchema(ctx context.Context, db *sql.DB) error {
}
}
// checkUnversioned checks a database at user_version 0 before it is
// taken for an empty one. createSchema creates the files table and
// sets the version together, so a files table at version 0 was made by
// something else. Adopting it could corrupt unrelated data, so that is
// a schema-version error telling the operator to remove the file and
// rescan.
func checkUnversioned(ctx context.Context, db *sql.DB) error {
var name string
err := db.QueryRowContext(ctx,
"SELECT name FROM sqlite_master "+
"WHERE type = 'table' AND name = 'files'").Scan(&name)
switch {
case err == nil:
return fmt.Errorf(
"has a files table but no schema version; "+
"remove the file and rescan: %w", errSchemaVersion)
case errors.Is(err, sql.ErrNoRows):
return nil
default:
return fmt.Errorf("check for files table: %w", err)
}
}
// createSchema applies the schema to a fresh database and stamps the
// schema version in one transaction, so a creation stopped partway, by
// an interrupt or an error, leaves an empty database the next scan
// sets up, never a files table at version 0, which checkUnversioned
// refuses.
// schema version.
func createSchema(ctx context.Context, db *sql.DB) error {
tx, err := db.BeginTx(ctx, nil)
_, err := db.ExecContext(ctx, createTableSQL)
if err != nil {
return fmt.Errorf("create schema: %w", err)
}
defer func() { _ = tx.Rollback() }()
_, err = tx.ExecContext(ctx, createTableSQL)
_, err = db.ExecContext(ctx, createIndexSQL)
if err != nil {
return fmt.Errorf("create schema: %w", err)
}
_, err = tx.ExecContext(ctx, createIndexSQL)
if err != nil {
return fmt.Errorf("create schema: %w", err)
}
_, err = tx.ExecContext(ctx,
_, err = db.ExecContext(ctx,
"PRAGMA user_version = "+strconv.Itoa(schemaVersion))
if err != nil {
return fmt.Errorf("set schema version: %w", err)
}
err = tx.Commit()
if err != nil {
return fmt.Errorf("create schema: %w", err)
}
return nil
}
db_test.go
+2 -80
View File
@@ -8,7 +8,6 @@ import (
"os"
"path/filepath"
"slices"
"strings"
"testing"
)
@@ -78,76 +77,6 @@ func TestOpenScanDatabaseCreates(t *testing.T) {
}
}
func TestOpenDatabaseUnversionedForeign(t *testing.T) {
t.Parallel()
// A database that has a files table but user_version 0, written by
// some other tool. report, trees and scan must refuse it with the
// schema-version error, not adopt it and not emit a raw SQLite
// "table files already exists".
path := testDBPath(t)
db, err := sql.Open("sqlite", path)
if err != nil {
t.Fatal(err)
}
_, err = db.ExecContext(t.Context(), "CREATE TABLE files (x INTEGER)")
if err != nil {
t.Fatal(err)
}
_ = db.Close()
_, err = openReportDatabase(t.Context(), path)
if !errors.Is(err, errSchemaVersion) ||
!strings.Contains(err.Error(), "remove the file and rescan") {
t.Fatalf("report: err = %v, want errSchemaVersion telling the "+
"operator to remove the file and rescan", err)
}
_, err = openScanDatabase(t.Context(), path)
if !errors.Is(err, errSchemaVersion) ||
!strings.Contains(err.Error(), "remove the file and rescan") {
t.Fatalf("scan: err = %v, want errSchemaVersion telling the "+
"operator to remove the file and rescan", err)
}
}
func TestSchemaCreationStoppedPartway(t *testing.T) {
t.Parallel()
// A first scan stopped while creating the schema must leave a
// database the next scan accepts. max_page_count(2) leaves room for
// the files table but not its index, so schema creation fails right
// after CREATE TABLE, a point an interrupt could also stop it at.
path := testDBPath(t)
db, err := openDB(path, scanParams+"&_pragma=max_page_count(2)")
if err != nil {
t.Fatal(err)
}
err = initSchema(t.Context(), db)
_ = db.Close()
if err == nil {
t.Fatal("initSchema with no room for the index succeeded")
}
db, err = openScanDatabase(t.Context(), path)
if err != nil {
t.Fatalf("next scan: %v", err)
}
defer func() { _ = db.Close() }()
v, err := userVersion(t.Context(), db)
if err != nil || v != schemaVersion {
t.Fatalf("userVersion = %d, %v; want %d, nil", v, err, schemaVersion)
}
}
func TestOpenReportDatabaseMissing(t *testing.T) {
t.Parallel()
@@ -157,11 +86,9 @@ func TestOpenReportDatabaseMissing(t *testing.T) {
}
}
func TestOpenDatabaseVersionMismatch(t *testing.T) {
func TestOpenReportDatabaseVersionMismatch(t *testing.T) {
t.Parallel()
// A database stamped with a schema version other than 0 and
// schemaVersion. report, trees and scan must all refuse it.
path := testDBPath(t)
db, err := openScanDatabase(t.Context(), path)
@@ -178,12 +105,7 @@ func TestOpenDatabaseVersionMismatch(t *testing.T) {
_, err = openReportDatabase(t.Context(), path)
if !errors.Is(err, errSchemaVersion) {
t.Fatalf("report: err = %v, want errSchemaVersion", err)
}
_, err = openScanDatabase(t.Context(), path)
if !errors.Is(err, errSchemaVersion) {
t.Fatalf("scan: err = %v, want errSchemaVersion", err)
t.Fatalf("err = %v, want errSchemaVersion", err)
}
}
main.go
+16 -61
View File
@@ -15,7 +15,6 @@
// sfdupes scan [--workers N] [-x] PATH...
// sfdupes report > dupes.tsv
// sfdupes trees > dupetrees.tsv
// sfdupes --version
//
// See README.md for the complete specification.
package main
@@ -51,10 +50,6 @@ const (
// cobra prints for it is the whole message.
var errNoSubcommand = errors.New("no subcommand")
// errWorkersBelowOne is the usage error for a scan --workers value
// below 1.
var errWorkersBelowOne = errors.New("--workers must be at least 1")
// Version is the build version, injected at link time via -ldflags
// (see the Makefile); "dev" for a plain go build.
//
@@ -92,9 +87,6 @@ func run(args []string, stdout, stderr io.Writer) int {
switch {
case err == nil:
return exitOK
case errors.Is(err, errInterrupted):
// The interrupted scan has printed its own line.
return exitFatal
case errors.As(err, &fatal):
// The command ran and failed: a runtime error, reported
// without the usage text that a usage error gets.
@@ -102,35 +94,22 @@ func run(args []string, stdout, stderr io.Writer) int {
return exitFatal
default:
// A usage error, which cobra has already reported on stderr.
// A usage error: cobra has already printed the message and
// the usage text.
return exitUsage
}
}
// newRootCommand builds the command tree. Everything on stdout is
// machine-readable data, the version line included; all human-facing
// output (help, usage, errors) goes to stderr.
// machine-readable data; all human-facing output (help, usage, errors)
// goes to stderr.
func newRootCommand(stdout, stderr io.Writer) *cobra.Command {
var showVersion bool
printVersion := runE(func(context.Context, []string) error {
_, err := fmt.Fprintf(stdout, "sfdupes %s\n", Version)
if err != nil {
return fmt.Errorf("write stdout: %w", err)
}
return nil
})
root := &cobra.Command{
Use: "sfdupes",
Short: "Find candidate duplicate files by size and head/tail/content SHA-256",
Args: cobra.NoArgs,
RunE: func(cmd *cobra.Command, args []string) error {
if showVersion {
return printVersion(cmd, args)
}
Use: "sfdupes",
Short: "Find candidate duplicate files by size and head/tail/content SHA-256",
Version: Version,
Args: cobra.NoArgs,
RunE: func(cmd *cobra.Command, _ []string) error {
// A missing subcommand prints usage and exits 2: cobra
// prints the usage text for the returned error, and run
// maps everything that is not a fatal error to exit 2.
@@ -143,11 +122,6 @@ func newRootCommand(stdout, stderr io.Writer) *cobra.Command {
root.SetErr(stderr)
root.CompletionOptions.DisableDefaultCmd = true
// Cobra's built-in version flag prints through the help writer,
// stderr; this one prints to stdout.
root.Flags().BoolVarP(&showVersion, "version", "v", false,
"print the version to stdout")
var (
scanWorkers int
scanOneFS bool
@@ -157,13 +131,7 @@ func newRootCommand(stdout, stderr io.Writer) *cobra.Command {
Use: cmdScan + " [--workers N] [-x] PATH...",
Short: "Walk trees and synchronize the scan database",
Args: cobra.MinimumNArgs(1),
PreRunE: func(cmd *cobra.Command, _ []string) error {
return checkScanWorkers(cmd, scanWorkers)
},
RunE: runE(func(ctx context.Context, args []string) error {
ctx, stop := interruptContext(ctx)
defer stop()
return runScan(ctx, args, scanWorkers, scanOneFS)
}),
}
@@ -195,26 +163,13 @@ func newRootCommand(stdout, stderr io.Writer) *cobra.Command {
return root
}
// checkScanWorkers rejects a scan --workers value below 1. That is a
// usage error reported in one line: cobra prints the returned message
// without the usage text, and run exits 2.
func checkScanWorkers(cmd *cobra.Command, workers int) error {
if workers >= 1 {
return nil
}
cmd.SilenceUsage = true
return fmt.Errorf("%w, got %d", errWorkersBelowOne, workers)
}
// runE adapts a subcommand implementation, or the version print, to
// cobra's RunE. Cobra prints the error and the command's usage text for
// every error RunE returns, but a subcommand that ran and failed has no
// usage problem to report: both are silenced here, and the error is
// marked fatal so that run reports it on stderr and exits 1 rather than
// 2. The command's context is handed to the implementation: cancelling
// it unwinds the scan's worker pools.
// runE adapts a subcommand implementation to cobra's RunE. Cobra
// prints the error and the command's usage text for every error RunE
// returns, but a subcommand that ran and failed has no usage problem
// to report: both are silenced here, and the error is marked fatal so
// that run reports it on stderr and exits 1 rather than 2. The command's
// context is handed to the implementation: cancelling it unwinds the
// scan's worker pools.
func runE(
fn func(ctx context.Context, args []string) error,
) func(*cobra.Command, []string) error {
main_test.go
+20 -162
View File
@@ -8,7 +8,6 @@ import (
"io/fs"
"os"
"path/filepath"
"slices"
"strconv"
"strings"
"testing"
@@ -296,108 +295,34 @@ func TestRunUsageErrors(t *testing.T) {
}
}
func TestRunScanRejectsWorkersBelowOne(t *testing.T) {
// README §scan mode: --workers below 1 is a usage error reported in
// one line on stderr, before the scan opens the database.
for _, workers := range []string{"0", "-1"} {
t.Run(workers, func(t *testing.T) {
dbPath := testDBPath(t)
t.Setenv(databaseEnv, dbPath)
var stdout, stderr bytes.Buffer
args := []string{cmdScan, "--workers", workers, t.TempDir()}
code := run(args, &stdout, &stderr)
if code != exitUsage {
t.Errorf("run(%v) = %d, want %d", args, code, exitUsage)
}
want := "Error: --workers must be at least 1, got " + workers +
"\n"
if got := stderr.String(); got != want {
t.Errorf("stderr = %q, want %q", got, want)
}
if got := stdout.String(); got != "" {
t.Errorf("stdout = %q, want nothing (data only)", got)
}
_, err := os.Stat(dbPath)
if !errors.Is(err, fs.ErrNotExist) {
t.Errorf("stat %s: %v, want the database never created",
dbPath, err)
}
})
}
}
func TestRunHelp(t *testing.T) {
// TestRunHelpAndVersionSucceed checks that the two informational flags
// exit 0 and keep their human-facing output on stderr.
func TestRunHelpAndVersionSucceed(t *testing.T) {
t.Parallel()
// README §Subcommands: help goes to stderr, exits 0, and leaves
// stdout empty.
cases := [][]string{{"--help"}, {"-h"}, {cmdScan, "--help"}}
for _, args := range cases {
var stdout, stderr bytes.Buffer
code := run(args, &stdout, &stderr)
if code != exitOK {
t.Errorf("run(%v) = %d, want %d", args, code, exitOK)
}
if !strings.Contains(stderr.String(), usageMarker) {
t.Errorf("run(%v) stderr = %q, want the help text",
args, stderr.String())
}
if got := stdout.String(); got != "" {
t.Errorf("run(%v) stdout = %q, want nothing (data only)",
args, got)
}
}
assertHumanOutput(t, "--help")
assertHumanOutput(t, "--version")
}
func TestRunVersion(t *testing.T) {
t.Parallel()
// assertHumanOutput runs sfdupes with one informational flag and checks
// that it succeeds with its output on stderr and stdout untouched
// (README design goal 4).
func assertHumanOutput(t *testing.T, arg string) {
t.Helper()
// README §Subcommands: the version is one line on stdout, with
// nothing on stderr, and exits 0.
for _, arg := range []string{"--version", "-v"} {
var stdout, stderr bytes.Buffer
var stdout, stderr bytes.Buffer
code := run([]string{arg}, &stdout, &stderr)
if code != exitOK {
t.Errorf("run(%s) = %d, want %d", arg, code, exitOK)
}
want := "sfdupes " + Version + "\n"
if got := stdout.String(); got != want {
t.Errorf("run(%s) stdout = %q, want %q", arg, got, want)
}
if got := stderr.String(); got != "" {
t.Errorf("run(%s) stderr = %q, want nothing", arg, got)
}
}
}
func TestRunVersionWriteFailureIsFatal(t *testing.T) {
t.Parallel()
// README §Error handling: a stdout write failure exits 1, reported
// in one line on stderr.
var stderr bytes.Buffer
code := run([]string{"--version"}, failingWriter{}, &stderr)
if code != exitFatal {
t.Errorf("run(--version) = %d, want %d", code, exitFatal)
code := run([]string{arg}, &stdout, &stderr)
if code != exitOK {
t.Errorf("run(%s) = %d, want %d", arg, code, exitOK)
}
want := "sfdupes: write stdout: " + errWriteFailed.Error() + "\n"
if got := stderr.String(); got != want {
t.Errorf("stderr = %q, want %q", got, want)
if stderr.Len() == 0 {
t.Errorf("run(%s) wrote nothing to stderr", arg)
}
if got := stdout.String(); got != "" {
t.Errorf("stdout = %q, want nothing (data only)", got)
}
}
@@ -640,73 +565,6 @@ func TestRunReportsNeedOnlyReadAccess(t *testing.T) {
}
}
// assertRunsUseDatabase runs scan, then report and trees, against the
// database that SFDUPES_DATABASE names, the file name in dir. It fails
// unless the reports find the duplicate pair the scan recorded and dir
// then holds only that file and its lock file: nothing was created
// under a shortened name.
func assertRunsUseDatabase(t *testing.T, dir, name string) {
t.Helper()
dupes := scanFixture(t)
want := "first\tdupe\tsize\n" + dupes[0] + "\t" + dupes[1] + "\t300\n"
if got := runStdout(t, cmdReport); got != want {
t.Errorf("report stdout = %q, want %q", got, want)
}
want = "first\tdupe\tfiles\tsize\n" +
filepath.Dir(dupes[0]) + "\t" + filepath.Dir(dupes[1]) + "\t1\t300\n"
if got := runStdout(t, cmdTrees); got != want {
t.Errorf("trees stdout = %q, want %q", got, want)
}
entries, err := os.ReadDir(dir)
if err != nil {
t.Fatal(err)
}
got := make([]string, 0, len(entries))
for _, e := range entries {
got = append(got, e.Name())
}
if wantFiles := []string{name, name + ".lock"}; !slices.Equal(got, wantFiles) {
t.Errorf("%s holds %q, want %q", dir, got, wantFiles)
}
}
func TestRunDatabasePathUsedAsGiven(t *testing.T) {
// README §Database: the path names the database file exactly. In
// SQLite's connection string an unescaped ? or # would end the file
// name and % would start an escape, and a path starting with //
// could be read as a host name. %25 is a valid escape, so unescaped
// this name opens a file named a without any error.
const name = "a?b#c%25d e.sqlite"
t.Run("absolute", func(t *testing.T) {
dir := t.TempDir()
t.Setenv(databaseEnv, filepath.Join(dir, name))
assertRunsUseDatabase(t, dir, name)
})
t.Run("leading double slash", func(t *testing.T) {
dir := t.TempDir()
t.Setenv(databaseEnv, "/"+filepath.Join(dir, name))
assertRunsUseDatabase(t, dir, name)
})
t.Run("relative", func(t *testing.T) {
dir := t.TempDir()
t.Chdir(dir)
t.Setenv(databaseEnv, name)
assertRunsUseDatabase(t, dir, name)
})
}
// holdScanLock takes the lock on the database at path, as a running
// scan does, and holds it until the test ends. It fails the test when
// the lock is already held.
progress.go
+2 -8
View File
@@ -141,20 +141,14 @@ func (p *progress) warnf(format string, args ...any) {
fmt.Fprintln(os.Stderr, msg)
}
// finish terminates the pass's display. A bar whose pass stopped short
// of its total, as an interrupted one does, is left as last drawn; the
// library's Finish would fill it up.
// finish terminates the pass's display.
func (p *progress) finish() {
if p == nil {
return
}
if p.bar != nil {
if p.total >= 0 && p.count < p.total {
_ = p.bar.Exit()
} else {
_ = p.bar.Finish()
}
_ = p.bar.Finish()
fmt.Fprintln(os.Stderr)
progress_test.go
+6 -34
View File
@@ -144,46 +144,18 @@ func TestSpinnerShowsCountAfterBurst(t *testing.T) {
time.Sleep(spinnerIdle)
if shown := lastFrame(stderr()); !strings.Contains(shown, "(50/-,") {
t.Errorf("terminal shows %q, want a count of 50", shown)
}
}
// lastFrame returns what a terminal shows of the frames a bar drew: the
// last one. The library starts each frame with a carriage return and
// erases the previous one with spaces first.
func lastFrame(out string) string {
// A terminal shows the last frame drawn. The library starts each
// frame with a carriage return and erases the previous one with
// spaces first.
var shown string
for frame := range strings.SplitSeq(out, "\r") {
for frame := range strings.SplitSeq(stderr(), "\r") {
if strings.TrimSpace(frame) != "" {
shown = frame
}
}
return shown
}
// TestBarStoppedShortKeepsCount checks that the terminal display of a
// pass that stops before its total, as an interrupted one does, is left
// as last drawn instead of being filled up.
//
//nolint:paralleltest // captureStderr replaces the process-wide os.Stderr
func TestBarStoppedShortKeepsCount(t *testing.T) {
stderr := captureStderr(t)
p := &progress{
label: "hash", total: 10, start: time.Now(),
bar: newBar("hash", 10),
}
p.increment()
// Past the redraw limit, so the bar draws the next count.
time.Sleep(2 * barThrottle)
p.increment()
p.finish()
if shown := lastFrame(stderr()); !strings.Contains(shown, "(2/10,") {
t.Errorf("terminal shows %q, want a count of 2 of 10", shown)
if !strings.Contains(shown, "(50/-,") {
t.Errorf("terminal shows %q, want a count of 50", shown)
}
}
report_test.go
+4 -4
View File
@@ -122,12 +122,12 @@ func TestReportStdoutFailsWhileReading(t *testing.T) {
// still being read, not at the final flush.
dir := "/" + strings.Repeat("d", 4096)
recs := make([]scanRec, ioBufSize/len(dir))
for i := range recs {
recs[i] = scanRec{
var recs []scanRec
for i := range ioBufSize / len(dir) {
recs = append(recs, scanRec{
size: 1, head: "h", tail: "t", content: "c",
path: fmt.Sprintf("%s/%d", dir, i),
}
})
}
t.Setenv(databaseEnv, seedDatabase(t, recs))
scan.go
+26 -98
View File
@@ -11,7 +11,6 @@ import (
"io"
"io/fs"
"os"
"os/signal"
"path/filepath"
"slices"
"strings"
@@ -58,10 +57,6 @@ const sampleWindow = 1024 * 1024
// and hash worker pools.
const workQueueDepth = 1024
// errInterrupted reports a scan stopped by SIGINT or SIGTERM. runScan
// has already printed its line, so run prints nothing more.
var errInterrupted = errors.New("scan interrupted")
// fileRec carries one statted file between the scan phases. dev and
// ino identify the underlying inode so hard-linked paths can share
// one read; both are zero when the platform exposes no inode.
@@ -95,14 +90,15 @@ type fileMeta struct {
// scan fails before it walks the filesystem or opens the database.
// Errors are returned rather than exiting, so that the deferred close —
// which takes the database out of WAL mode — always runs, and the lock
// is released after it. When ctx is cancelled, as by the SIGINT or
// SIGTERM that interruptContext catches, the scan keeps what it has
// hashed (see syncScan), prints how many files its walk reached, and
// returns errInterrupted. workers must be at least 1; the scan command
// rejects anything less.
// is released after it. Cancelling ctx unwinds the worker pools and
// aborts the scan with the context's error.
func runScan(ctx context.Context, roots []string, workers int,
oneFS bool,
) error {
if workers < 1 {
workers = 1
}
roots, err := resolveRoots(roots)
if err != nil {
return err
@@ -118,12 +114,6 @@ func runScan(ctx context.Context, roots []string, workers int,
defer func() { _ = lock.Close() }()
db, err := openScanDatabase(ctx, dbPath)
if err != nil && ctx.Err() != nil {
// Interrupted while opening; SQLite may report that with an
// error of its own rather than the context's.
return interrupted(0)
}
if err != nil {
return err
}
@@ -131,10 +121,6 @@ func runScan(ctx context.Context, roots []string, workers int,
defer closeScanDatabase(ctx, db, dbPath)
st, err := syncScan(ctx, db, roots, workers, oneFS)
if errors.Is(err, context.Canceled) {
return interrupted(st.walked)
}
if err != nil {
return fmt.Errorf("update database %s: %w", dbPath, err)
}
@@ -148,34 +134,6 @@ func runScan(ctx context.Context, roots []string, workers int,
return nil
}
// interruptContext returns a copy of ctx that the first SIGINT or
// SIGTERM cancels; the scan command runs the scan under it. stop
// releases the signals.
func interruptContext(ctx context.Context) (context.Context, func()) {
// A SIGINT ignored from the start, as by a script's background job,
// stays ignored.
signals := []os.Signal{syscall.SIGTERM}
if !signal.Ignored(syscall.SIGINT) {
signals = append(signals, syscall.SIGINT)
}
ctx, stop := signal.NotifyContext(ctx, signals...)
// Stopping restores the default handling, so a second signal ends
// the process at once.
context.AfterFunc(ctx, stop)
return ctx, stop
}
// interrupted prints the line for a scan stopped by a signal after its
// walk reached walked files, and returns errInterrupted.
func interrupted(walked int) error {
fmt.Fprintf(os.Stderr, "scan: interrupted after %d files\n", walked)
return errInterrupted
}
// resolveRoots converts each PATH operand to an absolute, lexically
// cleaned path (symlinks are not resolved) and verifies that it
// exists. Database records are keyed by absolute path, so scan results
@@ -229,9 +187,8 @@ func pruneRoots(roots []string) []string {
}
// scanStats summarizes one scan's database synchronization for the
// final stderr summary, or for the line an interrupted scan prints.
// final stderr summary.
type scanStats struct {
walked int // files the walk reached
added int
updated int
removed int
@@ -253,30 +210,7 @@ type scanState struct {
st scanStats
}
// syncScan synchronizes the database with the filesystem under roots;
// see runPhases. When ctx is cancelled, as by an interrupt, it commits
// the hashed records still waiting in the batch, starts no other write
// or deletion, and returns the cancellation.
func syncScan(ctx context.Context, db *sql.DB, roots []string,
workers int, oneFS bool,
) (scanStats, error) {
s := &scanState{db: db}
err := s.runPhases(ctx, roots, workers, oneFS)
if err == nil || ctx.Err() == nil {
return s.st, err
}
// The one write made after the cancellation, so it cannot use ctx.
err = applyChanges(context.WithoutCancel(ctx), db, s.batch, nil, nil)
if err != nil {
return s.st, err
}
return s.st, ctx.Err()
}
// runPhases synchronizes the database with the filesystem under roots
// syncScan synchronizes the database with the filesystem under roots
// in four sequential phases: walk (enumerate and stat every file,
// building a complete size census), hash (read only the new or
// changed — or previously unhashed — files whose size at least one
@@ -289,41 +223,48 @@ func syncScan(ctx context.Context, db *sql.DB, roots []string,
// their content hash. Operands the walk cannot start from are dropped
// first, so the records beneath them count as outside the roots unless
// they lie under another root.
func (s *scanState) runPhases(ctx context.Context, roots []string,
func syncScan(ctx context.Context, db *sql.DB, roots []string,
workers int, oneFS bool,
) error {
) (scanStats, error) {
s := &scanState{db: db}
// Types are checked before pruning so that an operand under a
// dropped one is still scanned, not dropped as lying under it.
roots = pruneRoots(s.walkableRoots(roots))
err := s.loadIndex(ctx, roots)
if err != nil {
return err
return s.st, err
}
changed, unhashed := s.walkPhase(startWalk(ctx, roots, oneFS, workers))
// A cancelled walk stops early, so its size census covers only part
// of the roots, and every file it never reached would look vanished
// to the update phase. Stop before anything is written or deleted.
// of the roots, and every file it never reached looks vanished to
// the update phase. Defence in depth rather than the only barrier:
// that phase would today fail on its first BeginTx with the same
// cancelled context before deleting anything. But it is the barrier
// that survives a later decision to let an interrupted scan commit
// what it has, and it turns a confusing failure deep in the update
// phase into a clean abort at the phase boundary.
err = ctx.Err()
if err != nil {
return err
return s.st, err
}
s.partition(changed, unhashed)
err = s.hashPhase(ctx, workers)
if err != nil {
return err
return s.st, err
}
err = s.updatePhase(ctx)
if err != nil {
return err
return s.st, err
}
return s.contentPhase(ctx, workers)
return s.st, s.contentPhase(ctx, workers)
}
// walkableRoots returns the operands the walk can start from: regular
@@ -408,7 +349,6 @@ func (s *scanState) walkPhase(
}
s.sizes = append(s.sizes, ev.rec.size)
s.st.walked++
prog.increment()
@@ -612,22 +552,16 @@ func (s *scanState) recordRun(ctx context.Context, r hashResult) error {
}
// commitFullBatch commits the running batch once it holds
// updateBatchSize records. A batch that fails to commit is kept: the
// commit fails when the scan is interrupted, and syncScan then commits
// the batch itself.
// updateBatchSize records.
func (s *scanState) commitFullBatch(ctx context.Context) error {
if len(s.batch) < updateBatchSize {
return nil
}
err := applyBatch(ctx, s.db, s.batch, nil, nil)
if err != nil {
return err
}
s.batch = s.batch[:0]
return nil
return err
}
// updatePhase writes the scan's tail under one progress display: the
@@ -1070,12 +1004,6 @@ func walkOneDir(ctx context.Context, job dirJob, oneFS bool,
var subs []dirJob
for _, e := range entries {
// A cancelled scan wants nothing more from this directory: stop
// rather than lstat the rest of a large one.
if ctx.Err() != nil {
return nil
}
p := filepath.Join(job.path, e.Name())
if e.IsDir() {
scan_test.go
+16 -180
View File
@@ -6,18 +6,14 @@ import (
"crypto/sha256"
"database/sql"
"encoding/hex"
"errors"
"fmt"
"io"
"io/fs"
"os"
"os/signal"
"path/filepath"
"runtime"
"slices"
"strconv"
"strings"
"syscall"
"testing"
"time"
)
@@ -460,7 +456,7 @@ func TestScanContentWithinOperand(t *testing.T) {
added := sparseFile(t, dir, "d2", headTailMin)
st := syncTree(t, db, dir)
if st != (scanStats{walked: 3, added: 1, unchanged: 2}) {
if st != (scanStats{added: 1, unchanged: 2}) {
t.Fatalf("rescan stats = %+v, want 1 added 2 unchanged", st)
}
@@ -506,7 +502,7 @@ func TestScanContentStalePartners(t *testing.T) {
sparseFile(t, dirB, "changed-copy", headTailMin+1)
st := syncTree(t, db, dirB)
if st != (scanStats{walked: 2, added: 2}) {
if st != (scanStats{added: 2}) {
t.Errorf("stats = %+v, want 2 added and nothing skipped", st)
}
@@ -563,7 +559,7 @@ func TestScanContentHashedStalePartners(t *testing.T) {
b := sparseFile(t, t.TempDir(), "copy", headTailMin)
st := syncTree(t, db, filepath.Dir(b))
if st != (scanStats{walked: 1, added: 1}) {
if st != (scanStats{added: 1}) {
t.Errorf("stats = %+v, want 1 added and nothing skipped", st)
}
@@ -603,7 +599,7 @@ func TestScanContentReadFailure(t *testing.T) {
b := sparseFile(t, dirB, "b", headTailMin)
st := syncTree(t, db, dirB)
if st != (scanStats{walked: 1, added: 1, skipped: 1}) {
if st != (scanStats{added: 1, skipped: 1}) {
t.Fatalf("stats = %+v, want 1 added 1 skipped", st)
}
@@ -617,7 +613,7 @@ func TestScanContentReadFailure(t *testing.T) {
}
st = syncTree(t, db, dirB)
if st != (scanStats{walked: 1, unchanged: 1}) {
if st != (scanStats{unchanged: 1}) {
t.Fatalf("rescan stats = %+v, want 1 unchanged", st)
}
@@ -663,7 +659,7 @@ func TestScanContentCheckError(t *testing.T) {
b := sparseFile(t, t.TempDir(), "b", headTailMin)
st := syncTree(t, db, filepath.Dir(b))
if st != (scanStats{walked: 1, added: 1, skipped: 1}) {
if st != (scanStats{added: 1, skipped: 1}) {
t.Fatalf("stats = %+v, want 1 added 1 skipped", st)
}
@@ -691,7 +687,7 @@ func TestScanContentHardlinks(t *testing.T) {
c := sparseFile(t, dir, "copy", headTailMin)
st := syncTree(t, db, dir)
if st != (scanStats{walked: 3, added: 3}) {
if st != (scanStats{added: 3}) {
t.Fatalf("stats = %+v, want 3 added", st)
}
@@ -914,159 +910,6 @@ func TestDeviceOfInfo(t *testing.T) {
}
}
// dirEntryFor returns the fs.DirEntry for name within dir, obtained via
// the same os.ReadDir the walk uses, so it carries a real Info().
func dirEntryFor(t *testing.T, dir, name string) fs.DirEntry {
t.Helper()
entries, err := os.ReadDir(dir)
if err != nil {
t.Fatal(err)
}
for _, e := range entries {
if e.Name() == name {
return e
}
}
t.Fatalf("entry %q not found in %q", name, dir)
return nil
}
// callSubdirJob runs subdirJob against e under parent, collecting any
// warning events it emits (subdirJob emits at most one).
func callSubdirJob(t *testing.T, p string, e fs.DirEntry,
parent dirJob, oneFS bool,
) (dirJob, bool, []walkEvent) {
t.Helper()
events := make(chan walkEvent, 1)
job, ok := subdirJob(t.Context(), p, e, parent, oneFS, events)
close(events)
var evs []walkEvent
for ev := range events {
evs = append(evs, ev)
}
return job, ok, evs
}
// TestSubdirJobOneFilesystem exercises the -x boundary check in
// subdirJob directly, so no second real filesystem is needed. The
// subdirectory's real device is compared against a fabricated operand
// device.
func TestSubdirJobOneFilesystem(t *testing.T) {
t.Parallel()
dir := t.TempDir()
sub := filepath.Join(dir, "sub")
err := os.Mkdir(sub, 0o750)
if err != nil {
t.Fatal(err)
}
info, err := os.Lstat(sub)
if err != nil {
t.Fatal(err)
}
dev, ok := deviceOfInfo(info)
if !ok {
t.Skip("platform exposes no device id")
}
// A device the subdirectory is not on, standing in for an operand
// rooted on a different filesystem.
otherDev := dev + 1
e := dirEntryFor(t, dir, "sub")
cases := []struct {
name string
oneFS bool
parent dirJob
wantOK bool
}{
// -x on, subdirectory on a different device than its operand:
// descent is refused.
{"reject across boundary", true,
dirJob{rootDev: otherDev, rootDevOK: true}, false},
// -x on but the operand's own device is unknown: the boundary
// check is bypassed and descent proceeds.
{"bypass when root device unknown", true,
dirJob{rootDev: otherDev, rootDevOK: false}, true},
// Default (no -x): boundaries are crossed even onto a different
// device.
{"cross by default", false,
dirJob{rootDev: otherDev, rootDevOK: true}, true},
}
for _, tc := range cases {
t.Run(tc.name, func(t *testing.T) {
t.Parallel()
job, ok, evs := callSubdirJob(t, sub, e, tc.parent, tc.oneFS)
if ok != tc.wantOK {
t.Fatalf("accepted = %v, want %v", ok, tc.wantOK)
}
if len(evs) != 0 {
t.Fatalf("unexpected events: %+v", evs)
}
// The accepted job must carry the operand's device down, or -x
// stops checking below the first level.
want := dirJob{
path: sub,
rootDev: tc.parent.rootDev,
rootDevOK: tc.parent.rootDevOK,
}
if ok && job != want {
t.Fatalf("job = %+v, want %+v", job, want)
}
})
}
}
// errInfoUnavailable is returned by errDirEntry.Info().
var errInfoUnavailable = errors.New("info unavailable")
// errDirEntry is a directory entry whose Info() always fails, driving
// subdirJob's stat-error branch deterministically.
type errDirEntry struct{ name string }
func (e errDirEntry) Name() string { return e.name }
func (errDirEntry) IsDir() bool { return true }
func (errDirEntry) Type() fs.FileMode {
return fs.ModeDir
}
func (errDirEntry) Info() (fs.FileInfo, error) {
return nil, errInfoUnavailable
}
// TestSubdirJobStatError asserts that when a subdirectory's Info()
// fails under -x, subdirJob warns and refuses descent.
func TestSubdirJobStatError(t *testing.T) {
t.Parallel()
p := "/does/not/matter/sub"
_, ok, evs := callSubdirJob(t, p, errDirEntry{name: "sub"},
dirJob{rootDev: 1, rootDevOK: true}, true)
if ok {
t.Fatal("descent accepted after stat error, want refused")
}
if len(evs) != 1 || !evs[0].fail || !strings.Contains(evs[0].warn, p) {
t.Fatalf("want one warning naming the path, got %+v", evs)
}
}
// buildSmokeTree recreates the README smoke-test filesystem layout
// with deterministic content and returns the tree root.
func buildSmokeTree(t *testing.T) string {
@@ -1215,7 +1058,7 @@ func TestScanPipeline(t *testing.T) {
db := openTestDB(t)
st := syncTree(t, db, dir)
if st != (scanStats{walked: smokeTreeFiles, added: smokeTreeFiles}) {
if st != (scanStats{added: smokeTreeFiles}) {
t.Fatalf("stats = %+v, want %d added only", st, smokeTreeFiles)
}
@@ -1238,7 +1081,7 @@ func TestSyncScanUnchangedReuse(t *testing.T) {
writeFile(t, dir, "b.bin", pattern(2, 600))
st := syncTree(t, db, dir)
if st != (scanStats{walked: 2, added: 2}) {
if st != (scanStats{added: 2}) {
t.Fatalf("first scan stats = %+v, want 2 added", st)
}
@@ -1252,7 +1095,7 @@ func TestSyncScanUnchangedReuse(t *testing.T) {
}
st = syncTree(t, db, dir)
if st != (scanStats{walked: 2, unchanged: 2}) {
if st != (scanStats{unchanged: 2}) {
t.Fatalf("rescan stats = %+v, want 2 unchanged", st)
}
@@ -1281,7 +1124,7 @@ func TestSyncScanMtimeBump(t *testing.T) {
}
st := syncTree(t, db, dir)
if st != (scanStats{walked: 1, updated: 1}) {
if st != (scanStats{updated: 1}) {
t.Fatalf("mtime-bump stats = %+v, want 1 updated", st)
}
@@ -1309,7 +1152,7 @@ func TestSyncScanAddRemove(t *testing.T) {
}
st := syncTree(t, db, dir)
if st != (scanStats{walked: 2, added: 1, removed: 1, unchanged: 1}) {
if st != (scanStats{added: 1, removed: 1, unchanged: 1}) {
t.Fatalf("add/remove stats = %+v, want 1 added 1 removed 1 unchanged",
st)
}
@@ -1426,7 +1269,7 @@ func TestSyncScanOverlappingRoots(t *testing.T) {
// A file reachable via two overlapping operands is deduplicated
// by path in the shared walk and processed once.
st := syncTree(t, db, dir, filepath.Join(dir, "sub"))
if st != (scanStats{walked: 1, added: 1}) {
if st != (scanStats{added: 1}) {
t.Fatalf("stats = %+v, want 1 added", st)
}
@@ -1447,7 +1290,7 @@ func TestScanSkipsUniqueSizes(t *testing.T) {
// Neither size is shared, so neither file is read: both records
// are written without hashes and no duplicates are reported.
st := syncTree(t, db, dir)
if st != (scanStats{walked: 2, added: 2}) {
if st != (scanStats{added: 2}) {
t.Fatalf("stats = %+v, want 2 added", st)
}
@@ -1469,7 +1312,7 @@ func TestScanSkipsUniqueSizes(t *testing.T) {
c := writeFile(t, dir, "c.bin", pattern(1, 500))
st = syncTree(t, db, dir)
if st != (scanStats{walked: 3, added: 1, updated: 1, unchanged: 1}) {
if st != (scanStats{added: 1, updated: 1, unchanged: 1}) {
t.Fatalf("rescan stats = %+v, want 1 added 1 updated 1 unchanged",
st)
}
@@ -1533,7 +1376,7 @@ func TestScanHardlinksReadOnce(t *testing.T) {
}
st := syncTree(t, db, dir)
if st != (scanStats{walked: 2, added: 2}) {
if st != (scanStats{added: 2}) {
t.Fatalf("stats = %+v, want 2 added", st)
}
@@ -1655,13 +1498,6 @@ func injectWriteFailure(t *testing.T, path string) {
func baselineGoroutines(t *testing.T) int {
t.Helper()
// The first scan command in a process starts os/signal's goroutine,
// which never exits. Start it now, so the baseline counts it
// instead of the scan seeming to leave it behind.
ch := make(chan os.Signal, 1)
signal.Notify(ch, syscall.SIGINT)
signal.Stop(ch)
deadline := time.Now().Add(goroutineSettle)
last := runtime.NumGoroutine()