text extraction

Hi, I am new using xwiki. I would like to use lucene plug-in to extract textual area from pdf, wrod, html files. The plug-in work well but I could not find how to extract text from indexed files. I know that during indexation "lucene" read file by extracting text. Are there some person who can help. Thant you in advance Youcef National Institute of Informatics-Japan