vaultik/internal/database/repository_debug_test.go
sneak 78af626759 Major refactoring: UUID-based storage, streaming architecture, and CLI improvements
This commit represents a significant architectural overhaul of vaultik:

Database Schema Changes:
- Switch files table to use UUID primary keys instead of path-based keys
- Add UUID primary keys to blobs table for immediate chunk association
- Update all foreign key relationships to use UUIDs
- Add comprehensive schema documentation in DATAMODEL.md
- Add SQLite busy timeout handling for concurrent operations

Streaming and Performance Improvements:
- Implement true streaming blob packing without intermediate storage
- Add streaming chunk processing to reduce memory usage
- Improve progress reporting with real-time metrics
- Add upload metrics tracking in new uploads table

CLI Refactoring:
- Restructure CLI to use subcommands: snapshot create/list/purge/verify
- Add store info command for S3 configuration display
- Add custom duration parser supporting days/weeks/months/years
- Remove old backup.go in favor of enhanced snapshot.go
- Add --cron flag for silent operation

Configuration Changes:
- Remove unused index_prefix configuration option
- Add support for snapshot pruning retention policies
- Improve configuration validation and error messages

Testing Improvements:
- Add comprehensive repository tests with edge cases
- Add cascade delete debugging tests
- Fix concurrent operation tests to use SQLite busy timeout
- Remove tolerance for SQLITE_BUSY errors in tests

Documentation:
- Add MIT LICENSE file
- Update README with new command structure
- Add comprehensive DATAMODEL.md explaining database schema
- Update DESIGN.md with UUID-based architecture

Other Changes:
- Add test-config.yml for testing
- Update Makefile with better test output formatting
- Fix various race conditions in concurrent operations
- Improve error handling throughout
2025-07-22 14:56:44 +02:00

166 lines
3.9 KiB
Go

package database
import (
"context"
"testing"
"time"
)
// TestOrphanedFileCleanupDebug tests orphaned file cleanup with debug output
func TestOrphanedFileCleanupDebug(t *testing.T) {
db, cleanup := setupTestDB(t)
defer cleanup()
ctx := context.Background()
repos := NewRepositories(db)
// Create files
file1 := &File{
Path: "/orphaned.txt",
MTime: time.Now().Truncate(time.Second),
CTime: time.Now().Truncate(time.Second),
Size: 1024,
Mode: 0644,
UID: 1000,
GID: 1000,
}
file2 := &File{
Path: "/referenced.txt",
MTime: time.Now().Truncate(time.Second),
CTime: time.Now().Truncate(time.Second),
Size: 2048,
Mode: 0644,
UID: 1000,
GID: 1000,
}
err := repos.Files.Create(ctx, nil, file1)
if err != nil {
t.Fatalf("failed to create file1: %v", err)
}
t.Logf("Created file1 with ID: %s", file1.ID)
err = repos.Files.Create(ctx, nil, file2)
if err != nil {
t.Fatalf("failed to create file2: %v", err)
}
t.Logf("Created file2 with ID: %s", file2.ID)
// Create a snapshot and reference only file2
snapshot := &Snapshot{
ID: "test-snapshot",
Hostname: "test-host",
StartedAt: time.Now(),
}
err = repos.Snapshots.Create(ctx, nil, snapshot)
if err != nil {
t.Fatalf("failed to create snapshot: %v", err)
}
t.Logf("Created snapshot: %s", snapshot.ID)
// Check snapshot_files before adding
var count int
err = db.conn.QueryRow("SELECT COUNT(*) FROM snapshot_files").Scan(&count)
if err != nil {
t.Fatal(err)
}
t.Logf("snapshot_files count before add: %d", count)
// Add file2 to snapshot
err = repos.Snapshots.AddFileByID(ctx, nil, snapshot.ID, file2.ID)
if err != nil {
t.Fatalf("failed to add file to snapshot: %v", err)
}
t.Logf("Added file2 to snapshot")
// Check snapshot_files after adding
err = db.conn.QueryRow("SELECT COUNT(*) FROM snapshot_files").Scan(&count)
if err != nil {
t.Fatal(err)
}
t.Logf("snapshot_files count after add: %d", count)
// Check which files are referenced
rows, err := db.conn.Query("SELECT file_id FROM snapshot_files")
if err != nil {
t.Fatal(err)
}
defer func() {
if err := rows.Close(); err != nil {
t.Logf("failed to close rows: %v", err)
}
}()
t.Log("Files in snapshot_files:")
for rows.Next() {
var fileID string
if err := rows.Scan(&fileID); err != nil {
t.Fatal(err)
}
t.Logf(" - %s", fileID)
}
// Check files before cleanup
err = db.conn.QueryRow("SELECT COUNT(*) FROM files").Scan(&count)
if err != nil {
t.Fatal(err)
}
t.Logf("Files count before cleanup: %d", count)
// Run orphaned cleanup
err = repos.Files.DeleteOrphaned(ctx)
if err != nil {
t.Fatalf("failed to delete orphaned files: %v", err)
}
t.Log("Ran orphaned cleanup")
// Check files after cleanup
err = db.conn.QueryRow("SELECT COUNT(*) FROM files").Scan(&count)
if err != nil {
t.Fatal(err)
}
t.Logf("Files count after cleanup: %d", count)
// List remaining files
files, err := repos.Files.ListByPrefix(ctx, "/")
if err != nil {
t.Fatal(err)
}
t.Log("Remaining files:")
for _, f := range files {
t.Logf(" - ID: %s, Path: %s", f.ID, f.Path)
}
// Check that orphaned file is gone
orphanedFile, err := repos.Files.GetByID(ctx, file1.ID)
if err != nil {
t.Fatalf("error getting file: %v", err)
}
if orphanedFile != nil {
t.Error("orphaned file should have been deleted")
// Let's check why it wasn't deleted
var exists bool
err = db.conn.QueryRow(`
SELECT EXISTS(
SELECT 1 FROM snapshot_files
WHERE file_id = ?
)`, file1.ID).Scan(&exists)
if err != nil {
t.Fatal(err)
}
t.Logf("File1 exists in snapshot_files: %v", exists)
} else {
t.Log("Orphaned file was correctly deleted")
}
// Check that referenced file still exists
referencedFile, err := repos.Files.GetByID(ctx, file2.ID)
if err != nil {
t.Fatalf("error getting file: %v", err)
}
if referencedFile == nil {
t.Error("referenced file should not have been deleted")
} else {
t.Log("Referenced file correctly remains")
}
}