word转pdf问题修复

control-plane/src/document-converter.ts

@@ -237,6 +237,11 @@ export async function convertDocumentToPdf(
       '--nolockcheck',
       '--nofirststartwizard',
       `-env:UserInstallation=${pathToFileURL(profileDirectory).href}`,
+      // Default HTML import can lose the first paragraph and emit a blank page
+      // in LibreOffice 7.4. Use Writer's HTML importer for HTML-in-DOC as well.
+      ...(isHtmlDocument(inputName, input.contentType, input.content)
+        ? ['--infilter=HTML (StarWriter)']
+        : []),
       '--convert-to',
       `pdf:${PDF_EXPORT_FILTER}`,
       '--outdir',

control-plane/test/document-converter.test.ts

@@ -46,6 +46,55 @@ test('conversion failure falls back to the source file', async () => {
   assert.deepEqual(result.content, content);
 });
 
+test('PDF conversion selects Writer HTML import only for HTML documents', {
+  skip: process.platform === 'win32' ? 'Unix fake converter fixture is not executable through Windows execFile.' : false
+}, async (t) => {
+  const temporaryDirectory = await mkdtemp(join(tmpdir(), 'ltjt-converter-import-test-'));
+  const converterPath = join(temporaryDirectory, 'fake-soffice.sh');
+  await writeFile(converterPath, [
+    '#!/bin/sh',
+    'outdir=""',
+    'next_is_outdir=0',
+    'for arg in "$@"; do',
+    '  if [ "$next_is_outdir" = "1" ]; then outdir="$arg"; next_is_outdir=0; continue; fi',
+    '  if [ "$arg" = "--outdir" ]; then next_is_outdir=1; fi',
+    'done',
+    'printf "%s\\n" "%PDF-1.7" "$@" > "$outdir/team.pdf"'
+  ].join('\n'), { mode: 0o700 });
+  await chmod(converterPath, 0o700);
+  const cases = [
+    { name: 'ERP Word HTML with vendor MIME', fileName: 'team.doc', contentType: 'application/vnd.ms-word; Charset=UTF-8', content: '\uFEFF\r\n<html><body><p>确认书标题</p><p>正文</p></body></html>', html: true },
+    { name: 'HTML doctype in a Word file', fileName: 'team.doc', contentType: 'application/msword', content: '<!DOCTYPE HTML><HTML><BODY>确认书</BODY></HTML>', html: true },
+    { name: 'legacy body-only Word HTML', fileName: 'team.doc', contentType: 'application/msword', content: '<body><p>确认书</p></body>', html: true },
+    { name: 'HTML extension', fileName: 'team.html', contentType: 'application/octet-stream', content: '<p>确认书</p>', html: true },
+    { name: 'HTML MIME without extension', fileName: 'team', contentType: 'text/html; charset=utf-8', content: '<p>确认书</p>', html: true },
+    { name: 'binary Word', fileName: 'team.doc', contentType: 'application/msword', content: Buffer.from([0xd0, 0xcf, 0x11, 0xe0, 0xa1, 0xb1, 0x1a, 0xe1]), html: false },
+    { name: 'DOCX package', fileName: 'team.docx', contentType: 'application/vnd.openxmlformats-officedocument.wordprocessingml.document', content: Buffer.from([0x50, 0x4b, 0x03, 0x04]), html: false },
+    { name: 'RTF', fileName: 'team.rtf', contentType: 'application/rtf', content: '{\\rtf1 Confirmation}', html: false }
+  ];
+  try {
+    for (const item of cases) {
+      await t.test(item.name, async () => {
+        const result = await convertDocumentToPdf(testConfig(converterPath), {
+          fileName: item.fileName,
+          contentType: item.contentType,
+          content: Buffer.from(item.content),
+          maxBytes: 10_000
+        });
+        assert.equal(result.converted, true);
+        const args = result.content.toString('utf8').split('\n');
+        assert.deepEqual(
+          args.filter((arg) => arg.startsWith('--infilter')),
+          item.html ? ['--infilter=HTML (StarWriter)'] : []
+        );
+        assert.ok(args.includes('pdf:writer_pdf_Export'));
+      });
+    }
+  } finally {
+    await rm(temporaryDirectory, { recursive: true, force: true });
+  }
+});
+
 test('a valid converter output replaces the source with a PDF', {
   skip: process.platform === 'win32' ? 'Unix fake converter fixture is not executable through Windows execFile.' : false
 }, async () => {