DriftLedger/tests/ocr.test.ts

import { describe, expect, it } from 'vitest';
import { matchOcrRule, parseOcrBill } from '../src/domain/ocr';
import { MockAiVisionProvider, MockOcrEngine, OcrProcessor, type OcrProcessResult } from '../src/domain/ocrProcessor';

describe('ocr - matchOcrRule', () => {
  it('微信支付规则匹配', () => {
    const text = '微信支付 金额 24.50 商户:星巴克 2026-07-13 14:30';
    const result = matchOcrRule(text, 'com.tencent.mm');
    expect(result.matched).toBe(true);
    expect(result.ruleName).toBe('微信支付');
    expect(result.event?.amount).toBe('-24.5');
    expect(result.event?.counterparty).toBe('星巴克');
    expect(result.event?.channel).toBe('WeChat');
  });

  it('支付宝规则匹配', () => {
    const text = '支付宝 收款方:肯德基 金额 35.00 支出';
    const result = matchOcrRule(text, 'com.eg.android.AlipayGphone');
    expect(result.matched).toBe(true);
    expect(result.ruleName).toBe('支付宝');
    expect(result.event?.direction).toBe('expense');
  });

  it('银行卡规则匹配（含尾号）', () => {
    const text = '尾号1234 信用卡 消费 100.50 商户:超市 2026-07-13 10:00';
    const result = matchOcrRule(text);
    expect(result.matched).toBe(true);
    expect(result.ruleName).toBe('银行卡');
    expect(result.event?.channel).toBe('Bank:1234');
    expect(result.event?.memo).toContain('1234');
  });

  it('收入方向识别', () => {
    const text = '微信支付 金额 5000 收款 2026-07-13 14:30';
    const result = matchOcrRule(text);
    expect(result.matched).toBe(true);
    expect(result.event?.direction).toBe('income');
    expect(result.event?.amount).toBe('5000');  // 收入为正
  });

  it('退款方向识别', () => {
    const text = '支付宝 金额 30 退款 2026-07-13 14:30';
    const result = matchOcrRule(text);
    expect(result.event?.direction).toBe('refund');
  });

  it('无金额不匹配', () => {
    const text = '微信支付 商户:星巴克';
    const result = matchOcrRule(text);
    expect(result.matched).toBe(false);
  });

  it('非账单内容不匹配', () => {
    const result = matchOcrRule('今天天气真好');
    expect(result.matched).toBe(false);
  });
});

describe('ocr - parseOcrBill 退化解析', () => {
  it('规则匹配命中时返回规则结果', () => {
    const event = parseOcrBill('微信支付 金额 10 商户:测试');
    expect(event?.channel).toBe('WeChat');
  });

  it('退化：提取金额 + 推断方向', () => {
    const event = parseOcrBill('您有一笔 50元 消费');
    expect(event).not.toBeNull();
    expect(event?.amount).toBe('-50');
    expect(event?.direction).toBe('expense');
  });

  it('无任何金额返回 null', () => {
    expect(parseOcrBill('纯文本无金额')).toBeNull();
  });
});

describe('OcrProcessor 分层处理', () => {
  it('Layer 1 规则命中', async () => {
    const engine = new MockOcrEngine();
    engine.defaultResponse = '微信支付 金额 24.50 商户:星巴克 2026-07-13 14:30';
    const processor = new OcrProcessor(engine);
    const result = await processor.process('img1', 'com.tencent.mm');
    expect(result.layer).toBe('layer1-rule');
    expect(result.event?.amount).toBe('-24.5');
  });

  it('Layer 2 退化解析（规则未命中但有金额）', async () => {
    const engine = new MockOcrEngine();
    engine.defaultResponse = '某App 消费 88元';
    const processor = new OcrProcessor(engine);
    const result = await processor.process('img2');
    expect(result.layer).toBe('layer2-ocr');
    expect(result.event?.amount).toBe('-88');
  });

  it('无文本时跳过到 Layer 3（未启用 AI → none）', async () => {
    const engine = new MockOcrEngine();
    engine.defaultResponse = '';
    const processor = new OcrProcessor(engine);
    const result = await processor.process('img3');
    expect(result.layer).toBe('none');
    expect(result.skipped).toBe('non-bill');
  });

  it('Layer 3 AI Vision 启用时降级', async () => {
    const engine = new MockOcrEngine();
    engine.defaultResponse = '非账单的随机文本';
    const aiProvider = new MockAiVisionProvider({
      id: 'ai-vision', occurredAt: '2026-07-13', amount: '99', currency: 'CNY', direction: 'expense',
      channel: 'AI', counterparty: 'AI识别', memo: '', raw: {},
    });
    const processor = new OcrProcessor(engine, aiProvider, { aiVisionEnabled: true, landscapeDnd: false });
    const result = await processor.process('img4');
    expect(result.layer).toBe('layer3-ai');
    expect(result.event?.amount).toBe('99');
  });

  it('横屏免打扰跳过', async () => {
    const engine = new MockOcrEngine();
    const processor = new OcrProcessor(engine, undefined, { aiVisionEnabled: false, landscapeDnd: true });
    const result = await processor.process('img5', undefined, true);
    expect(result.skipped).toBe('landscape-dnd');
  });

  it('去重：同一图片不重复处理', async () => {
    const engine = new MockOcrEngine();
    engine.defaultResponse = '微信支付 金额 10 商户:x';
    const processor = new OcrProcessor(engine);
    const r1 = await processor.process('same-image');
    const r2 = await processor.process('same-image');
    expect(r1.layer).toBe('layer1-rule');
    expect(r2.skipped).toBe('dedup');
  });

  it('串行化：处理中再次调用跳过', async () => {
    const engine = new MockOcrEngine();
    engine.defaultResponse = '微信支付 金额 10 商户:x';
    const processor = new OcrProcessor(engine);
    const p1 = processor.process('img-a');
    const p2 = processor.process('img-b');  // p1 未完成时
    const [r1, r2] = await Promise.all([p1, p2]);
    expect(r1.layer).toBe('layer1-rule');
    expect(r2.skipped).toBe('dedup');
  });

  it('reset 清除去重状态', async () => {
    const engine = new MockOcrEngine();
    engine.defaultResponse = '微信支付 金额 10 商户:x';
    const processor = new OcrProcessor(engine);
    await processor.process('img-reset');
    processor.reset();
    const result = await processor.process('img-reset');
    expect(result.layer).toBe('layer1-rule');  // reset 后可再次处理
  });
});