vaultik/internal/database/chunk_files_test.go

package database

import (
	"context"
	"testing"
)

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

	ctx := context.Background()
	repo := NewChunkFileRepository(db)

	// Test Create
	cf1 := &ChunkFile{
		ChunkHash:  "chunk1",
		FilePath:   "/file1.txt",
		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",
		FilePath:   "/file2.txt",
		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.FilePath == "/file1.txt" && cf.FileOffset == 0 {
			foundFile1 = true
		}
		if cf.FilePath == "/file2.txt" && cf.FileOffset == 2048 {
			foundFile2 = true
		}
	}
	if !foundFile1 || !foundFile2 {
		t.Error("not all expected files found")
	}

	// Test GetByFilePath
	chunkFiles, err = repo.GetByFilePath(ctx, "/file1.txt")
	if err != nil {
		t.Fatalf("failed to get chunks by file path: %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)

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

	chunkFiles := []ChunkFile{
		// File1
		{ChunkHash: "chunk1", FilePath: "/file1.txt", FileOffset: 0, Length: 1024},
		{ChunkHash: "chunk2", FilePath: "/file1.txt", FileOffset: 1024, Length: 1024},
		{ChunkHash: "chunk3", FilePath: "/file1.txt", FileOffset: 2048, Length: 1024},
		// File2
		{ChunkHash: "chunk2", FilePath: "/file2.txt", FileOffset: 0, Length: 1024},
		{ChunkHash: "chunk3", FilePath: "/file2.txt", FileOffset: 1024, Length: 1024},
		{ChunkHash: "chunk4", FilePath: "/file2.txt", FileOffset: 2048, Length: 1024},
		// File3
		{ChunkHash: "chunk1", FilePath: "/file3.txt", FileOffset: 0, Length: 1024},
		{ChunkHash: "chunk4", FilePath: "/file3.txt", 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
	chunks, err := repo.GetByFilePath(ctx, "/file2.txt")
	if err != nil {
		t.Fatalf("failed to get chunks for file2: %v", err)
	}
	if len(chunks) != 3 {
		t.Errorf("expected 3 chunks for file2, got %d", len(chunks))
	}
}