Search on Mercury provided by ApacheSolr and hosted in tomcat. Tomcat is running on port 80. When a request contains UTF-8 characters there are percent encoding and Tomcat can't deal with it by default. See : http://wiki.apache.org/solr/SolrTomcat#URI_Charset_Config
If you are going to query Solr using international characters (>127) using HTTP-GET, you must configure Tomcat to conform to the URI standard by accepting percent-encoded UTF-8.
Edit Tomcat's conf/server.xml and add the following attribute to the correct Connector element: URIEncoding="UTF-8".
<Connector ... URIEncoding="UTF-8"/>
This is only an issue when sending non-ascii characters in a query request... no configuration is needed for Solr/Tomcat to return non-ascii chars in a response, or accept non-ascii chars in an HTTP-POST body.
Following the above advice, the ApacheSolr search works ok for non-English words, like for CJK and others. I thought to share this here since this might be an issue for others as well with multilingual sites or non English user content.