A happier, groovier way to parse RTF: apache_tika + XmlSlurper

ParseRtf.groovy

package org.akhikhl.test

import org.apache.tika.metadata.Metadata
import org.apache.tika.parser.rtf.RTFParser

class ParseRtf {

  def parse(String rtfText) {
    // not validating, not ns-aware
    XmlSlurper slurper = new XmlSlurper(false, false) 
    InputStream rtfStream = new ByteArrayInputStream(value.getBytes())
    new RTFParser().parse(rtfStream, slurper, new Metadata())
    slurper.document.'body'.p.each { p -> 
      println "Got paragraph: ${p.text()}" 
    }
  }
}