Function validate_document

docx/ooxml/scripts/pack.py:90–130

Validate document by converting to HTML with soffice.

(doc_path)

def validate_document(doc_path):
    """Validate document by converting to HTML with soffice."""
    # Determine the correct filter based on file extension
    match doc_path.suffix.lower():
        case ".docx":
            filter_name = "html:HTML"
        case ".pptx":
            filter_name = "html:impress_html_Export"
        case ".xlsx":
            filter_name = "html:HTML (StarCalc)"

    with tempfile.TemporaryDirectory() as temp_dir:
        try:
            result = subprocess.run(
                [
                    "soffice",
                    "--headless",
                    "--convert-to",
                    filter_name,
                    "--outdir",
                    temp_dir,
                    str(doc_path),
                ],
                capture_output=True,
                timeout=10,
                text=True,
            )
            if not (Path(temp_dir) / f"{doc_path.stem}.html").exists():
                error_msg = result.stderr.strip() or "Document validation failed"
                print(f"Validation error: {error_msg}", file=sys.stderr)
                return False
            return True
        except FileNotFoundError:
            print("Warning: soffice not found. Skipping validation.", file=sys.stderr)
            return True
        except subprocess.TimeoutExpired:
            print("Validation error: Timeout during conversion", file=sys.stderr)
            return False
        except Exception as e:
            print(f"Validation error: {e}", file=sys.stderr)
            return False


def condense_xml(xml_file):