BPOS-MVP/apps/api/src/app/__tests__/upload-extract.test.ts

/**
 * 上传件读文本 —— **这段错了不报错,只是活动拿到一份读不懂的料**。
 *
 * 测法不用录制的样本文件:测里现造一个**真的 xlsx**(ZIP + 那几份 XML,按规范逐字节拼),
 * 再让被测代码去读。造的那一侧与读的那一侧互不共享代码,读得回来才算真的读得懂。
 */
import { describe, expect, it } from 'vitest';
import { deflateRawSync } from 'node:zlib';
import { extractText } from '../upload-extract.ts';

/* ==================== 现造一个 xlsx ==================== */

const enc = (s: string): Uint8Array => new TextEncoder().encode(s);

/** 按 ZIP 规范拼一个包:本地头 + 数据 + 中央目录 + EOCD */
function makeZip(entries: ReadonlyArray<{ name: string; body: Uint8Array; store?: boolean }>): Uint8Array {
  const locals: Uint8Array[] = [];
  const centrals: Uint8Array[] = [];
  let offset = 0;

  for (const e of entries) {
    const name = enc(e.name);
    const data = e.store === true ? e.body : new Uint8Array(deflateRawSync(e.body));
    const method = e.store === true ? 0 : 8;

    const local = new Uint8Array(30 + name.length + data.length);
    const lv = new DataView(local.buffer);
    lv.setUint32(0, 0x04034b50, true);
    lv.setUint16(8, method, true);
    lv.setUint32(18, data.length, true);
    lv.setUint32(22, e.body.length, true);
    lv.setUint16(26, name.length, true);
    local.set(name, 30);
    local.set(data, 30 + name.length);
    locals.push(local);

    const central = new Uint8Array(46 + name.length);
    const cv = new DataView(central.buffer);
    cv.setUint32(0, 0x02014b50, true);
    cv.setUint16(10, method, true);
    cv.setUint32(20, data.length, true);
    cv.setUint32(24, e.body.length, true);
    cv.setUint16(28, name.length, true);
    cv.setUint32(42, offset, true);
    central.set(name, 46);
    centrals.push(central);

    offset += local.length;
  }

  const centralSize = centrals.reduce((n, c) => n + c.length, 0);
  const eocd = new Uint8Array(22);
  const ev = new DataView(eocd.buffer);
  ev.setUint32(0, 0x06054b50, true);
  ev.setUint16(8, entries.length, true);
  ev.setUint16(10, entries.length, true);
  ev.setUint32(12, centralSize, true);
  ev.setUint32(16, offset, true);

  const total = offset + centralSize + eocd.length;
  const out = new Uint8Array(total);
  let at = 0;
  for (const b of [...locals, ...centrals, eocd]) {
    out.set(b, at);
    at += b.length;
  }
  return out;
}

/** 一份两列三行的 BOM:表头 + 两条料 —— 字符串走共享串表,数字直接落 `<v>` */
function bomXlsx(): Uint8Array {
  const strings = ['型号', '年用量', 'LM358DR', 'NE555P'];
  const sharedXml =
    `<?xml version="1.0"?><sst count="4" uniqueCount="4">` +
    strings.map((s) => `<si><t>${s}</t></si>`).join('') +
    `</sst>`;
  const sheetXml =
    `<?xml version="1.0"?><worksheet><sheetData>` +
    `<row r="1"><c r="A1" t="s"><v>0</v></c><c r="B1" t="s"><v>1</v></c></row>` +
    `<row r="2"><c r="A2" t="s"><v>2</v></c><c r="B2"><v>12000</v></c></row>` +
    `<row r="3"><c r="A3" t="s"><v>3</v></c><c r="B3"><v>5000</v></c></row>` +
    `<row r="4"/>` +
    `</sheetData></worksheet>`;
  return makeZip([
    { name: '[Content_Types].xml', body: enc('<?xml version="1.0"?><Types/>') },
    { name: 'xl/sharedStrings.xml', body: enc(sharedXml) },
    { name: 'xl/worksheets/sheet1.xml', body: enc(sheetXml) },
  ]);
}

/* ==================== 断言 ==================== */

describe('xlsx —— 一份真的表读得成行列', () => {
  const got = extractText('BOM.xlsx', 'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet', bomXlsx());

  it('读得出内容,而不是回一句「读不出」', () => {
    expect(got.text).toBeDefined();
  });

  it('共享串表查得对 —— 字符串单元格不是数字下标', () => {
    expect(got.text).toContain('LM358DR');
    expect(got.text).toContain('型号');
  });

  it('数字单元格取原值,不查串表(查了会变成别的字)', () => {
    expect(got.text).toContain('12000');
  });

  it('一行一行、制表符分列 —— 行列对齐了模型才拆得动', () => {
    expect(got.text?.split('\n')).toEqual(['型号\t年用量', 'LM358DR\t12000', 'NE555P\t5000']);
  });

  it('整行皆空的不留 —— 表尾那些格式化过的空行不该占一行', () => {
    expect(got.text?.split('\n')).toHaveLength(3);
  });

  it('读数如实报行数', () => {
    expect(got.note).toContain('3 行');
  });
});

describe('不压缩的条目也读得了 —— store(0) 与 deflate(8) 都是 xlsx 的出厂法', () => {
  it('store 法存的表照样读得出', () => {
    const zip = makeZip([
      {
        name: 'xl/worksheets/sheet1.xml',
        body: enc('<worksheet><sheetData><row r="1"><c r="A1" t="inlineStr"><is><t>直存</t></is></c></row></sheetData></worksheet>'),
        store: true,
      },
    ]);
    expect(extractText('a.xlsx', '', zip).text).toBe('直存');
  });
});

describe('读不出来就说读不出来 —— 绝不编一段内容出来', () => {
  it('不是 ZIP 的 .xlsx:如实说打不开', () => {
    const got = extractText('坏的.xlsx', '', enc('这不是一个 zip'));
    expect(got.text).toBeUndefined();
    expect(got.note).toContain('打不开');
  });

  it('二进制类型(pdf):说清只有文件名进得了活动', () => {
    const got = extractText('规格书.pdf', 'application/pdf', new Uint8Array([1, 2, 3]));
    expect(got.text).toBeUndefined();
    expect(got.note).toContain('读不出文本');
  });

  it('空表:不是「读出 0 行」,是明说这份表是空的', () => {
    const zip = makeZip([{ name: 'xl/worksheets/sheet1.xml', body: enc('<worksheet><sheetData/></worksheet>') }]);
    expect(extractText('空.xlsx', '', zip).note).toContain('空的');
  });
});

describe('纯文本族 —— 按 UTF-8 直接解', () => {
  it('csv 原样读出(中文不乱码)', () => {
    const got = extractText('bom.csv', 'text/csv', enc('型号,年用量\nLM358DR,12000'));
    expect(got.text).toBe('型号,年用量\nLM358DR,12000');
  });

  it('超长的截断,并在读数里说明截了', () => {
    const got = extractText('big.txt', 'text/plain', enc('x'.repeat(30_000)));
    expect(got.text).toHaveLength(20_000);
    expect(got.note).toContain('截断');
  });
});

describe('XML 实体还原 —— `&amp;lt;` 之流不能原样端给模型', () => {
  it('转义字符还原成本来的字', () => {
    const zip = makeZip([
      // 表里真实存的形态:`A&B <100>` 在 XML 里写作 `A&amp;B &lt;100&gt;`
      { name: 'xl/sharedStrings.xml', body: enc('<sst><si><t>A&amp;B &lt;100&gt;</t></si></sst>') },
      {
        name: 'xl/worksheets/sheet1.xml',
        body: enc('<worksheet><sheetData><row r="1"><c r="A1" t="s"><v>0</v></c></row></sheetData></worksheet>'),
      },
    ]);
    expect(extractText('e.xlsx', '', zip).text).toBe('A&B <100>');
  });
});