try for yourself (7.0-2.3 on Mac): let $u := " http://www.larepublica.co/ocde-recomienda-fortalecer-el-sistema-de-planeaci%C3%B3n_124391 "
let $c := xdmp:http-get($u, <options xmlns="xdmp:http" xmlns:d="xdmp:document-get"> <verify-cert>false</verify-cert> <d:encoding>UTF-8</d:encoding> <d:repair>full</d:repair> </options> ) let $d := xdmp:tidy($c[2], <options xmlns="xdmp:tidy"> <new-blocklevel-tags>section, header, time, figure, nav, article</new-blocklevel-tags> <bare>yes</bare> <clean>yes</clean> <hide-comments>yes</hide-comments> </options> )[2] return $d log set to "finest" returns just this: Segmentation fault in thread 7411003392 addr 0x2aef14847 /usr/bin/pstack: No such file or directory 2014-06-05 00:33:07.647 Notice: Starting MarkLogic Server 7.0-2.3 x86_64 in /Users/jakob/Library/MarkLogic with data in /Users/jakob/Library/Application Support/MarkLogic/Data 2014-06-05 00:33:07.655 Info: Host jfix.local running Darwin 13.2.0 of course (and most fortunately) this requires some weirdness in the document passed to xdmp:tidy, but still a pain if you can't control the input you're getting... cheers, Jakob.
_______________________________________________ General mailing list General@developer.marklogic.com http://developer.marklogic.com/mailman/listinfo/general
