memind/mindspace-docx-export.mjs

const W_NS = 'http://schemas.openxmlformats.org/wordprocessingml/2006/main';
const R_NS = 'http://schemas.openxmlformats.org/officeDocument/2006/relationships';

const CONTENT_TYPES = `<?xml version="1.0" encoding="UTF-8"?>
<Types xmlns="http://schemas.openxmlformats.org/package/2006/content-types">
  <Default Extension="rels" ContentType="application/vnd.openxmlformats-package.relationships+xml"/>
  <Default Extension="xml" ContentType="application/xml"/>
  <Override PartName="/word/document.xml" ContentType="application/vnd.openxmlformats-officedocument.wordprocessingml.document.main+xml"/>
</Types>`;

const ROOT_RELS = `<?xml version="1.0" encoding="UTF-8"?>
<Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships">
  <Relationship Id="rId1" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/officeDocument" Target="word/document.xml"/>
</Relationships>`;

const DOCUMENT_RELS = `<?xml version="1.0" encoding="UTF-8"?>
<Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships"></Relationships>`;

function escapeXml(value) {
  return String(value ?? '')
    .replace(/&/g, '&amp;')
    .replace(/</g, '&lt;')
    .replace(/>/g, '&gt;')
    .replace(/"/g, '&quot;');
}

function decodeHtmlEntities(value) {
  return String(value ?? '')
    .replace(/&nbsp;/gi, ' ')
    .replace(/&amp;/gi, '&')
    .replace(/&lt;/gi, '<')
    .replace(/&gt;/gi, '>')
    .replace(/&quot;/gi, '"')
    .replace(/&#39;/gi, "'")
    .replace(/&#(\d+);/g, (_, code) => String.fromCodePoint(Number(code)))
    .replace(/&#x([0-9a-f]+);/gi, (_, code) => String.fromCodePoint(Number.parseInt(code, 16)));
}

export function extractPlainTextFromHtml(html) {
  return decodeHtmlEntities(
    String(html ?? '')
      .replace(/<script[\s\S]*?<\/script>/gi, ' ')
      .replace(/<style[\s\S]*?<\/style>/gi, ' ')
      .replace(/<\/(?:p|div|section|article|header|footer|h[1-6]|li|tr|blockquote)>/gi, '\n')
      .replace(/<br\s*\/?>/gi, '\n')
      .replace(/<[^>]+>/g, ' ')
      .replace(/[ \t\r\f\v]+/g, ' ')
      .replace(/\n[ \t]+/g, '\n')
      .replace(/[ \t]+\n/g, '\n')
      .replace(/\n{3,}/g, '\n\n')
      .trim(),
  );
}

function normalizeParagraphs(content) {
  return String(content ?? '')
    .split(/\n{1,}/)
    .map((line) => line.replace(/^#{1,6}\s+/, '').replace(/[*_`~]/g, '').trim())
    .filter(Boolean)
    .slice(0, 500);
}

function paragraphXml(text, { heading = false } = {}) {
  const style = heading ? '<w:pPr><w:pStyle w:val="Title"/></w:pPr>' : '';
  const runStyle = heading ? '<w:rPr><w:b/><w:sz w:val="32"/></w:rPr>' : '';
  return `<w:p>${style}<w:r>${runStyle}<w:t xml:space="preserve">${escapeXml(text)}</w:t></w:r></w:p>`;
}

function documentXml({ title, paragraphs }) {
  const body = [
    title ? paragraphXml(title, { heading: true }) : '',
    ...paragraphs.map((paragraph) => paragraphXml(paragraph)),
  ].join('');
  return `<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<w:document xmlns:w="${W_NS}" xmlns:r="${R_NS}">
  <w:body>${body}<w:sectPr><w:pgSz w:w="11906" w:h="16838"/><w:pgMar w:top="1440" w:right="1440" w:bottom="1440" w:left="1440"/></w:sectPr></w:body>
</w:document>`;
}

const CRC_TABLE = (() => {
  const table = new Uint32Array(256);
  for (let n = 0; n < 256; n += 1) {
    let c = n;
    for (let k = 0; k < 8; k += 1) c = c & 1 ? 0xedb88320 ^ (c >>> 1) : c >>> 1;
    table[n] = c >>> 0;
  }
  return table;
})();

function crc32(buffer) {
  let crc = 0xffffffff;
  for (const byte of buffer) crc = CRC_TABLE[(crc ^ byte) & 0xff] ^ (crc >>> 8);
  return (crc ^ 0xffffffff) >>> 0;
}

function dosDateTime(date = new Date()) {
  const year = Math.max(1980, date.getFullYear());
  const dosTime = (date.getHours() << 11) | (date.getMinutes() << 5) | Math.floor(date.getSeconds() / 2);
  const dosDate = ((year - 1980) << 9) | ((date.getMonth() + 1) << 5) | date.getDate();
  return { dosTime, dosDate };
}

function writeZipEntry(name, content, offset) {
  const nameBuffer = Buffer.from(name);
  const data = Buffer.isBuffer(content) ? content : Buffer.from(String(content), 'utf8');
  const checksum = crc32(data);
  const { dosTime, dosDate } = dosDateTime();
  const local = Buffer.alloc(30 + nameBuffer.length);
  local.writeUInt32LE(0x04034b50, 0);
  local.writeUInt16LE(20, 4);
  local.writeUInt16LE(0, 6);
  local.writeUInt16LE(0, 8);
  local.writeUInt16LE(dosTime, 10);
  local.writeUInt16LE(dosDate, 12);
  local.writeUInt32LE(checksum, 14);
  local.writeUInt32LE(data.length, 18);
  local.writeUInt32LE(data.length, 22);
  local.writeUInt16LE(nameBuffer.length, 26);
  nameBuffer.copy(local, 30);

  const central = Buffer.alloc(46 + nameBuffer.length);
  central.writeUInt32LE(0x02014b50, 0);
  central.writeUInt16LE(20, 4);
  central.writeUInt16LE(20, 6);
  central.writeUInt16LE(0, 8);
  central.writeUInt16LE(0, 10);
  central.writeUInt16LE(dosTime, 12);
  central.writeUInt16LE(dosDate, 14);
  central.writeUInt32LE(checksum, 16);
  central.writeUInt32LE(data.length, 20);
  central.writeUInt32LE(data.length, 24);
  central.writeUInt16LE(nameBuffer.length, 28);
  central.writeUInt32LE(offset, 42);
  nameBuffer.copy(central, 46);
  return { local, data, central };
}

function zip(entries) {
  let offset = 0;
  const locals = [];
  const centrals = [];
  for (const [name, content] of entries) {
    const entry = writeZipEntry(name, content, offset);
    locals.push(entry.local, entry.data);
    centrals.push(entry.central);
    offset += entry.local.length + entry.data.length;
  }
  const centralSize = centrals.reduce((sum, item) => sum + item.length, 0);
  const end = Buffer.alloc(22);
  end.writeUInt32LE(0x06054b50, 0);
  end.writeUInt16LE(entries.length, 8);
  end.writeUInt16LE(entries.length, 10);
  end.writeUInt32LE(centralSize, 12);
  end.writeUInt32LE(offset, 16);
  return Buffer.concat([...locals, ...centrals, end]);
}

export function generateDocxBuffer({ title = '文档', content = '', contentFormat = 'markdown' } = {}) {
  const plain = contentFormat === 'html' ? extractPlainTextFromHtml(content) : String(content ?? '');
  const paragraphs = normalizeParagraphs(plain);
  return zip([
    ['[Content_Types].xml', CONTENT_TYPES],
    ['_rels/.rels', ROOT_RELS],
    ['word/document.xml', documentXml({ title, paragraphs: paragraphs.length > 0 ? paragraphs : [''] })],
    ['word/_rels/document.xml.rels', DOCUMENT_RELS],
  ]);
}