html.addRule(new ParameterExtractingRule(page)); // <parameter> blocks
html.addRule(new ContentBlockExtractingRule(page)); // <content> blocks
// Capture properties written to documents by MS Office (author, version, company, etc).
// Note: These properties are from the xml state, not the html state.
xml.addRule(new MSOfficeDocumentPropertiesRule(page));
}