MetonaSqlark/tests/engine/aria-compress.test.ts

/**
 * AriaEngine LZ4 压缩 + LSM Merge Iterator 单元测试
 * 注：LZ4 为简化演示实现（默认 compression:false），测试聚焦于「不卡死」
 */
import { compressLZ4, decompressLZ4 } from '../../src/engine/aria/compression/lz4';
import { MergeIterator, ArrayEntrySource } from '../../src/engine/aria/index/merge_iterator';

// ===================================================================
//  LZ4 压缩 — 安全烟雾测试（不卡死）
// ===================================================================
describe('AriaEngine — LZ4 Compression', () => {
  it('短于 4 字节时压缩为纯字面量 token 且往返一致', () => {
    const input = new Uint8Array([1, 2]);
    const compressed = compressLZ4(input);
    // token(lo=0) + 2 字节字面量
    expect(compressed.byteLength).toBe(3);
    expect(compressed[0]).toBe(0x20); // litLen=2, matchField=0
    const restored = decompressLZ4(compressed, 2);
    expect(Array.from(restored)).toEqual([1, 2]);
  });

  it('简单文本压缩不抛出异常且产生输出', () => {
    const input = new TextEncoder().encode('hello world hello world hello world');
    const compressed = compressLZ4(input);
    expect(compressed).toBeInstanceOf(Uint8Array);
    expect(compressed.byteLength).toBeGreaterThan(0);
  });

  it('重复数据有压缩效果', () => {
    const pattern = 'ABCD';
    const repeated = pattern.repeat(100);
    const input = new TextEncoder().encode(repeated);
    const compressed = compressLZ4(input);
    expect(compressed.byteLength).toBeLessThan(input.byteLength);
  });

  it('随机不可压缩数据不卡死', () => {
    const input = new Uint8Array(256);
    for (let i = 0; i < 256; i++) input[i] = Math.floor(Math.random() * 256);
    const compressed = compressLZ4(input);
    expect(compressed).toBeInstanceOf(Uint8Array);
    expect(compressed.byteLength).toBeGreaterThan(0);
  });

  it('长文本压缩不卡死', () => {
    const input = new TextEncoder().encode('The quick brown fox jumps over the lazy dog. '.repeat(10));
    const compressed = compressLZ4(input);
    expect(compressed).toBeTruthy();
    expect(compressed.byteLength).toBeGreaterThan(0);
  });

  it('多种长度输入均不卡死', () => {
    for (const size of [10, 50, 100, 200, 500]) {
      const input = new Uint8Array(size);
      for (let i = 0; i < size; i++) input[i] = i % 256;
      const compressed = compressLZ4(input);
      expect(compressed.byteLength).toBeLessThanOrEqual(input.byteLength + 16);
    }
  });

  it('解压不抛出异常', () => {
    const input = new TextEncoder().encode('test data for decompression smoke test');
    const compressed = compressLZ4(input);
    expect(() => decompressLZ4(compressed, input.byteLength)).not.toThrow();
  });

  // ---- v0.2.6 补强：压缩 → 解压 往返一致性 ----

  it('往返一致：重复模式数据', () => {
    const input = new TextEncoder().encode('ABCD'.repeat(100));
    const compressed = compressLZ4(input);
    const restored = decompressLZ4(compressed, input.byteLength);
    expect(Array.from(restored)).toEqual(Array.from(input));
  });

  it('往返一致：自然文本数据', () => {
    const input = new TextEncoder().encode(
      'The quick brown fox jumps over the lazy dog. '.repeat(10),
    );
    const compressed = compressLZ4(input);
    const restored = decompressLZ4(compressed, input.byteLength);
    expect(Array.from(restored)).toEqual(Array.from(input));
  });

  it('往返一致：随机不可压缩数据', () => {
    const input = new Uint8Array(512);
    for (let i = 0; i < 512; i++) input[i] = Math.floor(Math.random() * 256);
    const compressed = compressLZ4(input);
    const restored = decompressLZ4(compressed, input.byteLength);
    expect(Array.from(restored)).toEqual(Array.from(input));
  });

  it('往返一致：多种长度与字节模式', () => {
    for (const size of [4, 5, 15, 16, 17, 50, 100, 300, 1000]) {
      const input = new Uint8Array(size);
      for (let i = 0; i < size; i++) input[i] = i % 7 === 0 ? i % 256 : 0x41;
      const compressed = compressLZ4(input);
      const restored = decompressLZ4(compressed, input.byteLength);
      expect(Array.from(restored)).toEqual(Array.from(input));
    }
  });

  it('往返一致：恰好 15 字节字面量边界', () => {
    // 字面量长度恰好 15（token 上限）时不应丢字节
    const input = new Uint8Array(15);
    for (let i = 0; i < 15; i++) input[i] = i;
    const compressed = compressLZ4(input);
    const restored = decompressLZ4(compressed, input.byteLength);
    expect(Array.from(restored)).toEqual(Array.from(input));
  });

  it('往返一致：超过 15 字节的连续匹配', () => {
    const input = new TextEncoder().encode('X'.repeat(200) + 'Y' + 'X'.repeat(60));
    const compressed = compressLZ4(input);
    const restored = decompressLZ4(compressed, input.byteLength);
    expect(Array.from(restored)).toEqual(Array.from(input));
  });
});

// ===================================================================
//  MergeIterator — 归并迭代器单元测试
// ===================================================================
describe('AriaEngine — MergeIterator', () => {
  it('单数据源归并', () => {
    const mi = new MergeIterator();
    mi.addSource(new ArrayEntrySource([
      ['a', { v: 1 }],
      ['b', { v: 2 }],
      ['c', { v: 3 }],
    ]));
    const result = mi.drain();
    expect(result).toHaveLength(3);
    expect(result.map(([k]) => k)).toEqual(['a', 'b', 'c']);
  });

  it('多数据源归并去重（保留最新）', () => {
    const mi = new MergeIterator();
    mi.addSource(new ArrayEntrySource([['a', { v: 'new' }], ['c', { v: 3 }]]));
    mi.addSource(new ArrayEntrySource([['a', { v: 'old' }], ['b', { v: 2 }]]));
    const result = mi.drain();
    expect(result).toHaveLength(3);
    expect(result[0][0]).toBe('a');
    expect(result[0][1].v).toBe('new');
    expect(result[1][0]).toBe('b');
    expect(result[2][0]).toBe('c');
  });

  // ---- v0.2.6 回归：同 key 多来源时保留 sourceIndex 最小（最新）的条目 ----
  it('回归：同 key 出现在多个来源时返回 sourceIndex 最小（最新来源）的值', () => {
    const mi = new MergeIterator();
    // 语义：sourceIndex 越小越新（memtable=0 < immutable=1 < sstable=2+）
    mi.addSource(new ArrayEntrySource([['a', { v: 'source0' }]])); // 最新来源
    mi.addSource(new ArrayEntrySource([['a', { v: 'source1' }]]));
    mi.addSource(new ArrayEntrySource([['a', { v: 'source2' }]])); // 最旧来源
    const result = mi.drain();
    expect(result).toHaveLength(1);
    // 取的是 sourceIndex 最小（最新来源）的条目，而非堆序决定的任意条目
    expect(result[0][1].v).toBe('source0');
  });

  it('回归：最新来源的值位于中间 sourceIndex 时仍取 sourceIndex 最小者', () => {
    const mi = new MergeIterator();
    mi.addSource(new ArrayEntrySource([['a', { v: 'middle' }]])); // index 0 = 最新来源
    mi.addSource(new ArrayEntrySource([['a', { v: 'newest' }]])); // index 1
    mi.addSource(new ArrayEntrySource([['a', { v: 'oldest' }]])); // index 2
    const result = mi.drain();
    expect(result).toHaveLength(1);
    expect(result[0][1].v).toBe('middle'); // index 0 的条目胜出
  });

  it('回归：多个同 key 来源 + 其他独立 key 混合', () => {
    const mi = new MergeIterator();
    mi.addSource(new ArrayEntrySource([['a', { v: 1 }], ['b', { v: 10 }]]));
    mi.addSource(new ArrayEntrySource([['a', { v: 2 }]]));
    mi.addSource(new ArrayEntrySource([['a', { v: 3 }], ['c', { v: 30 }]]));
    const result = mi.drain();
    expect(result.map(([k]) => k)).toEqual(['a', 'b', 'c']);
    expect(result[0][1].v).toBe(1); // sourceIndex 0 = 最新
    expect(result[1][1].v).toBe(10);
    expect(result[2][1].v).toBe(30);
  });

  it('空数据源归并', () => {
    const mi = new MergeIterator();
    mi.addSource(new ArrayEntrySource([]));
    const result = mi.drain();
    expect(result).toHaveLength(0);
  });

  it('大数量归并', () => {
    const mi = new MergeIterator();
    for (let s = 0; s < 5; s++) {
      const entries: [string, Record<string, unknown>][] = [];
      for (let i = 0; i < 100; i++) {
        entries.push([`src${s}-key-${String(i).padStart(3, '0')}`, { src: s, idx: i }]);
      }
      mi.addSource(new ArrayEntrySource(entries));
    }
    const result = mi.drain();
    // 5 sources × 100 unique keys = 500 total (keys are unique per source)
    expect(result).toHaveLength(500);
  });

  it('ArrayEntrySource — 迭代器用完返回 null', () => {
    const src = new ArrayEntrySource([['k', { v: 1 }]]);
    expect(src.next()).not.toBeNull();
    expect(src.next()).toBeNull();
    expect(src.next()).toBeNull();
  });

  it('ArrayEntrySource — reset 重置', () => {
    const src = new ArrayEntrySource([['k1', { v: 1 }], ['k2', { v: 2 }]]);
    src.next();
    src.reset();
    const val = src.next();
    expect(val![0]).toBe('k1');
  });
});