1 Commits
Author SHA1 Message Date
sneak 1a847037ef Test both hashWorker cancellation checks on their own (closes #83)
check / check (push) Failing after 1s
TestHashWorkerDropsQueuedRuns now passes hashWorker a hash function
that records being called, so a worker that hashes a run after the
scan is cancelled fails the test every time instead of only when it
then chose to send its result.

TestHashWorkerAbandonsBlockedSend cancels the scan from inside the
hash function and leaves the result channel unread, so the worker can
only return through the cancellation case beside its send. The scan
tests could not show this, because stop drains results and frees a
parked worker anyway.

Model: opus-5-5
2026-10-04 12:39:39 +00:00
4 changed files with 2 additions and 88 deletions
+1 -3
View File
@@ -283,9 +283,7 @@ 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
-3
View File
@@ -32,9 +32,6 @@
- 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)
+1 -14
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)
}
-68
View File
@@ -8,7 +8,6 @@ import (
"io/fs"
"os"
"path/filepath"
"slices"
"strconv"
"strings"
"testing"
@@ -640,73 +639,6 @@ 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.