feat: standardize Word export and Office conversion

offline-backend-20260512/backend/scripts/office_runtime_selfcheck.py

@@ -0,0 +1,78 @@
+#!/usr/bin/env python3
+"""Offline runtime smoke test for the LocalSandbox Office toolchain."""
+
+from __future__ import annotations
+
+import shutil
+import subprocess
+import tempfile
+from pathlib import Path
+
+
+def require_command(name: str) -> str:
+    path = shutil.which(name)
+    if path is None:
+        raise RuntimeError(f"missing command: {name}")
+    return path
+
+
+def assert_contains(text: str, expected: str, label: str) -> None:
+    normalized = text.replace("\\_", "_")
+    if expected not in normalized:
+        raise RuntimeError(f"{label} conversion lost test text: {text[:300]!r}")
+
+
+def main() -> int:
+    from docx import Document
+    from markitdown import MarkItDown
+    from openpyxl import Workbook
+    from pptx import Presentation
+
+    soffice = require_command("soffice")
+    require_command("pandoc")
+    require_command("pdftotext")
+    require_command("file")
+
+    subprocess.run(
+        [soffice, "--headless", "--version"],
+        check=True,
+        capture_output=True,
+        text=True,
+        timeout=30,
+    )
+
+    with tempfile.TemporaryDirectory(prefix="deerflow-office-selfcheck-") as temporary:
+        root = Path(temporary)
+
+        word_path = root / "word-test.docx"
+        document = Document()
+        document.add_heading("Word 自检", level=1)
+        document.add_paragraph("DEERFLOW_WORD_OK")
+        document.save(word_path)
+
+        excel_path = root / "excel-test.xlsx"
+        workbook = Workbook()
+        worksheet = workbook.active
+        worksheet.title = "自检"
+        worksheet.append(["状态", "DEERFLOW_EXCEL_OK"])
+        workbook.save(excel_path)
+
+        ppt_path = root / "ppt-test.pptx"
+        presentation = Presentation()
+        slide = presentation.slides.add_slide(presentation.slide_layouts[5])
+        slide.shapes.title.text = "DEERFLOW_PPT_OK"
+        presentation.save(ppt_path)
+
+        converter = MarkItDown()
+        assert_contains(converter.convert(word_path).text_content, "DEERFLOW_WORD_OK", "Word")
+        assert_contains(converter.convert(excel_path).text_content, "DEERFLOW_EXCEL_OK", "Excel")
+        assert_contains(converter.convert(ppt_path).text_content, "DEERFLOW_PPT_OK", "PowerPoint")
+
+    print("OFFICE_RUNTIME_SELF_CHECK=PASS")
+    print("支持：DOC/DOCX、XLS/XLSX、PPT/PPTX、ODT/ODS/ODP、PDF")
+    print("组件：MarkItDown、python-docx、openpyxl、python-pptx、LibreOffice、Pandoc、中文字体")
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())