I am using xdmp:word-convert to convert DOC/DOCX files to XHTML and xdmp:pdf-convert for PDF to XHTML conversion. While the conversion works as expected for smaller files (e.g., a 28KB document), it fails to produce any output for larger files, such as a 119MB DOC file.

It doesn’t return anything (just an empty sequence).

I need to convert large DOC/DOCX/PDF files to XHTML effectively in MarkLogic. Can anyone provide technical guidance on handling this issue?

import module namespace c = "http://marklogic.com/leapfrog/config" at "/ada/config.xqy";


let $source1 := xdmp:document-get("file:///C:/28-KB-file.doc")
let $source := xdmp:document-get("file:///C:/119-MB-doc-file.doc")


let $new-uri := "document.doc"
let $doc-format := $c:doc-format-doc
let $results :=
switch ($doc-format)
    case $c:doc-format-doc return                                   
        xdmp:word-convert($source, $new-uri)
    case $c:doc-format-ppt return
        xdmp:powerpoint-convert($source, $new-uri)
    case $c:doc-format-xls return
        xdmp:excel-convert($source, $new-uri)
    default return
        xdmp:pdf-convert($source, $new-uri)
return $results