vaultik/internal/database/chunk_files_test.go

package database

import (
	"context"
	"testing"
	"time"
)

func TestChunkFileRepository(t *testing.T) {
	db, cleanup := setupTestDB(t)
	defer cleanup()

	ctx := context.Background()
	repo := NewChunkFileRepository(db)
	fileRepo := NewFileRepository(db)
	chunksRepo := NewChunkRepository(db)

	// Create test files first
	testTime := time.Now().Truncate(time.Second)
	file1 := &File{
		Path:       "/file1.txt",
		MTime:      testTime,
		CTime:      testTime,
		Size:       1024,
		Mode:       0644,
		UID:        1000,
		GID:        1000,
		LinkTarget: "",
	}
	err := fileRepo.Create(ctx, nil, file1)
	if err != nil {
		t.Fatalf("failed to create file1: %v", err)
	}

	file2 := &File{
		Path:       "/file2.txt",
		MTime:      testTime,
		CTime:      testTime,
		Size:       1024,
		Mode:       0644,
		UID:        1000,
		GID:        1000,
		LinkTarget: "",
	}
	err = fileRepo.Create(ctx, nil, file2)
	if err != nil {
		t.Fatalf("failed to create file2: %v", err)
	}

	// Create chunk first
	chunk := &Chunk{
		ChunkHash: "chunk1",
		Size:      1024,
	}
	err = chunksRepo.Create(ctx, nil, chunk)
	if err != nil {
		t.Fatalf("failed to create chunk: %v", err)
	}

	// Test Create
	cf1 := &ChunkFile{
		ChunkHash:  "chunk1",
		FileID:     file1.ID,
		FileOffset: 0,
		Length:     1024,
	}

	err = repo.Create(ctx, nil, cf1)
	if err != nil {
		t.Fatalf("failed to create chunk file: %v", err)
	}

	// Add same chunk in different file (deduplication scenario)
	cf2 := &ChunkFile{
		ChunkHash:  "chunk1",
		FileID:     file2.ID,
		FileOffset: 2048,
		Length:     1024,
	}
	err = repo.Create(ctx, nil, cf2)
	if err != nil {
		t.Fatalf("failed to create second chunk file: %v", err)
	}

	// Test GetByChunkHash
	chunkFiles, err := repo.GetByChunkHash(ctx, "chunk1")
	if err != nil {
		t.Fatalf("failed to get chunk files: %v", err)
	}
	if len(chunkFiles) != 2 {
		t.Errorf("expected 2 files for chunk, got %d", len(chunkFiles))
	}

	// Verify both files are returned
	foundFile1 := false
	foundFile2 := false
	for _, cf := range chunkFiles {
		if cf.FileID == file1.ID && cf.FileOffset == 0 {
			foundFile1 = true
		}
		if cf.FileID == file2.ID && cf.FileOffset == 2048 {
			foundFile2 = true
		}
	}
	if !foundFile1 || !foundFile2 {
		t.Error("not all expected files found")
	}

	// Test GetByFileID
	chunkFiles, err = repo.GetByFileID(ctx, file1.ID)
	if err != nil {
		t.Fatalf("failed to get chunks by file ID: %v", err)
	}
	if len(chunkFiles) != 1 {
		t.Errorf("expected 1 chunk for file, got %d", len(chunkFiles))
	}
	if chunkFiles[0].ChunkHash != "chunk1" {
		t.Errorf("wrong chunk hash: expected chunk1, got %s", chunkFiles[0].ChunkHash)
	}

	// Test duplicate insert (should be idempotent)
	err = repo.Create(ctx, nil, cf1)
	if err != nil {
		t.Fatalf("failed to create duplicate chunk file: %v", err)
	}
}

func TestChunkFileRepositoryComplexDeduplication(t *testing.T) {
	db, cleanup := setupTestDB(t)
	defer cleanup()

	ctx := context.Background()
	repo := NewChunkFileRepository(db)
	fileRepo := NewFileRepository(db)
	chunksRepo := NewChunkRepository(db)

	// Create test files
	testTime := time.Now().Truncate(time.Second)
	file1 := &File{Path: "/file1.txt", MTime: testTime, CTime: testTime, Size: 3072, Mode: 0644, UID: 1000, GID: 1000}
	file2 := &File{Path: "/file2.txt", MTime: testTime, CTime: testTime, Size: 3072, Mode: 0644, UID: 1000, GID: 1000}
	file3 := &File{Path: "/file3.txt", MTime: testTime, CTime: testTime, Size: 2048, Mode: 0644, UID: 1000, GID: 1000}

	if err := fileRepo.Create(ctx, nil, file1); err != nil {
		t.Fatalf("failed to create file1: %v", err)
	}
	if err := fileRepo.Create(ctx, nil, file2); err != nil {
		t.Fatalf("failed to create file2: %v", err)
	}
	if err := fileRepo.Create(ctx, nil, file3); err != nil {
		t.Fatalf("failed to create file3: %v", err)
	}

	// Create chunks first
	chunks := []string{"chunk1", "chunk2", "chunk3", "chunk4"}
	for _, chunkHash := range chunks {
		chunk := &Chunk{
			ChunkHash: chunkHash,
			Size:      1024,
		}
		err := chunksRepo.Create(ctx, nil, chunk)
		if err != nil {
			t.Fatalf("failed to create chunk %s: %v", chunkHash, err)
		}
	}

	// Simulate a scenario where multiple files share chunks
	// File1: chunk1, chunk2, chunk3
	// File2: chunk2, chunk3, chunk4
	// File3: chunk1, chunk4

	chunkFiles := []ChunkFile{
		// File1
		{ChunkHash: "chunk1", FileID: file1.ID, FileOffset: 0, Length: 1024},
		{ChunkHash: "chunk2", FileID: file1.ID, FileOffset: 1024, Length: 1024},
		{ChunkHash: "chunk3", FileID: file1.ID, FileOffset: 2048, Length: 1024},
		// File2
		{ChunkHash: "chunk2", FileID: file2.ID, FileOffset: 0, Length: 1024},
		{ChunkHash: "chunk3", FileID: file2.ID, FileOffset: 1024, Length: 1024},
		{ChunkHash: "chunk4", FileID: file2.ID, FileOffset: 2048, Length: 1024},
		// File3
		{ChunkHash: "chunk1", FileID: file3.ID, FileOffset: 0, Length: 1024},
		{ChunkHash: "chunk4", FileID: file3.ID, FileOffset: 1024, Length: 1024},
	}

	for _, cf := range chunkFiles {
		err := repo.Create(ctx, nil, &cf)
		if err != nil {
			t.Fatalf("failed to create chunk file: %v", err)
		}
	}

	// Test chunk1 (used by file1 and file3)
	files, err := repo.GetByChunkHash(ctx, "chunk1")
	if err != nil {
		t.Fatalf("failed to get files for chunk1: %v", err)
	}
	if len(files) != 2 {
		t.Errorf("expected 2 files for chunk1, got %d", len(files))
	}

	// Test chunk2 (used by file1 and file2)
	files, err = repo.GetByChunkHash(ctx, "chunk2")
	if err != nil {
		t.Fatalf("failed to get files for chunk2: %v", err)
	}
	if len(files) != 2 {
		t.Errorf("expected 2 files for chunk2, got %d", len(files))
	}

	// Test file2 chunks
	file2Chunks, err := repo.GetByFileID(ctx, file2.ID)
	if err != nil {
		t.Fatalf("failed to get chunks for file2: %v", err)
	}
	if len(file2Chunks) != 3 {
		t.Errorf("expected 3 chunks for file2, got %d", len(file2Chunks))
	}
}