Files
sfdupes/db_test.go
sneak 3ecf73c80a
All checks were successful
check / check (push) Successful in 5s
Make phases scan-wide, walk operands concurrently, batch updates
All PATH operands belong to a single scan: every operand seeds the
shared walk worker pool, and each pass (walk, stat, hash, update)
runs exactly once over the whole scan, so pass totals, percentages,
and ETAs are scan-global. The per-operand walk/hash/update cycles and
their stderr operand announcements are gone; duplicate paths from
overlapping operands are deduplicated before stat.

The update pass now commits in batched transactions (10k changes per
batch) instead of one scan-wide transaction: the filesystem is
authoritative and the database is an eventually-consistent reflection
of it, so scan-level atomicity buys nothing, while batches keep the
WAL small and let concurrent reports observe progress.
2026-07-24 10:26:52 +07:00

225 lines
4.7 KiB
Go

package main
import (
"context"
"database/sql"
"errors"
"fmt"
"path/filepath"
"slices"
"strings"
"testing"
)
// testDBPath returns a database path inside a fresh temp dir.
func testDBPath(t *testing.T) string {
t.Helper()
return filepath.Join(t.TempDir(), "db.sqlite")
}
// openTestDB creates a fresh scan database in a temp dir.
func openTestDB(t *testing.T) *sql.DB {
t.Helper()
db, err := openScanDatabase(testDBPath(t))
if err != nil {
t.Fatal(err)
}
t.Cleanup(func() { _ = db.Close() })
return db
}
func TestDatabasePath(t *testing.T) {
t.Setenv(databaseEnv, "")
if got := databasePath(); got != defaultDatabasePath {
t.Errorf("databasePath() = %q, want %q", got, defaultDatabasePath)
}
t.Setenv(databaseEnv, "/custom/place.sqlite")
if got := databasePath(); got != "/custom/place.sqlite" {
t.Errorf("databasePath() = %q, want the env override", got)
}
}
func TestOpenScanDatabaseCreates(t *testing.T) {
t.Parallel()
// The parent directory does not exist yet; scan must create it.
path := filepath.Join(t.TempDir(), "nested", "dir", "db.sqlite")
db, err := openScanDatabase(path)
if err != nil {
t.Fatalf("openScanDatabase: %v", err)
}
v, err := userVersion(db)
if err != nil || v != schemaVersion {
t.Fatalf("userVersion = %d, %v; want %d, nil", v, err, schemaVersion)
}
_ = db.Close()
// Reopening an existing database must succeed and find the schema.
db, err = openScanDatabase(path)
if err != nil {
t.Fatalf("reopen: %v", err)
}
defer func() { _ = db.Close() }()
recs, err := loadFileRows(db)
if err != nil || len(recs) != 0 {
t.Fatalf("loadFileRows = %v, %v; want empty, nil", recs, err)
}
}
func TestOpenReportDatabaseMissing(t *testing.T) {
t.Parallel()
_, err := openReportDatabase(testDBPath(t))
if !errors.Is(err, errNoDatabase) {
t.Fatalf("err = %v, want errNoDatabase", err)
}
}
func TestOpenReportDatabaseVersionMismatch(t *testing.T) {
t.Parallel()
path := testDBPath(t)
db, err := openScanDatabase(path)
if err != nil {
t.Fatal(err)
}
_, err = db.ExecContext(context.Background(), "PRAGMA user_version = 99")
if err != nil {
t.Fatal(err)
}
_ = db.Close()
_, err = openReportDatabase(path)
if !errors.Is(err, errSchemaVersion) {
t.Fatalf("err = %v, want errSchemaVersion", err)
}
}
func TestOpenReportDatabaseOK(t *testing.T) {
t.Parallel()
path := testDBPath(t)
db, err := openScanDatabase(path)
if err != nil {
t.Fatal(err)
}
_ = db.Close()
db, err = openReportDatabase(path)
if err != nil {
t.Fatalf("openReportDatabase: %v", err)
}
_ = db.Close()
}
func TestApplyChangesRoundTrip(t *testing.T) {
t.Parallel()
db := openTestDB(t)
// Paths may contain tabs and newlines; the database must store
// them byte-exactly.
recs := []scanRec{
{size: 2, mtime: 20, head: "h2", tail: "t2", path: "/a/tab\tnew\nline"},
{size: 1, mtime: 10, head: "h1", tail: "t1", path: "/a/x"},
}
err := applyChanges(db, recs, nil, newProgress("update", 2))
if err != nil {
t.Fatalf("applyChanges: %v", err)
}
got, err := loadFileRows(db)
if err != nil {
t.Fatal(err)
}
slices.SortFunc(got, func(a, b scanRec) int {
return strings.Compare(a.path, b.path)
})
if !slices.Equal(got, recs) {
t.Fatalf("rows = %+v, want %+v", got, recs)
}
// An upsert for an existing path updates in place; a delete
// removes exactly its path.
upd := scanRec{size: 3, mtime: 30, head: "h3", tail: "t3", path: "/a/x"}
err = applyChanges(db, []scanRec{upd},
[]string{"/a/tab\tnew\nline"}, newProgress("update", 2))
if err != nil {
t.Fatalf("applyChanges: %v", err)
}
got, err = loadFileRows(db)
if err != nil {
t.Fatal(err)
}
if len(got) != 1 || got[0] != upd {
t.Fatalf("rows = %+v, want just %+v", got, upd)
}
}
func TestApplyChangesBatching(t *testing.T) {
t.Parallel()
db := openTestDB(t)
// One more change than the batch size, so the update spans two
// transactions.
n := updateBatchSize + 1
recs := make([]scanRec, 0, n)
for i := range n {
recs = append(recs, scanRec{
size: int64(i), mtime: 1, head: "h", tail: "t",
path: fmt.Sprintf("/batch/%07d", i),
})
}
err := applyChanges(db, recs, nil, newProgress("update", int64(n)))
if err != nil {
t.Fatalf("applyChanges: %v", err)
}
got, err := loadFileRows(db)
if err != nil || len(got) != n {
t.Fatalf("loadFileRows = %d rows, %v; want %d", len(got), err, n)
}
deletes := make([]string, 0, n)
for _, r := range recs {
deletes = append(deletes, r.path)
}
err = applyChanges(db, nil, deletes, newProgress("update", int64(n)))
if err != nil {
t.Fatalf("applyChanges deletes: %v", err)
}
got, err = loadFileRows(db)
if err != nil || len(got) != 0 {
t.Fatalf("loadFileRows = %d rows, %v; want 0", len(got), err)
}
}