int correct = differ.getCorrectMatches();
int falsePositives = differ.getFalsePositivesStrict();
int missing = differ.getMissing();
System.out.println("Diff: correct="+correct+" false positives="+falsePositives+" missing="+missing);
File outFile = new File(testingDir,"news1pre_procBE"+backendNr+".xml");
FileUtils.writeStringToFile(outFile, doc.toXml(),"UTF-8");
// the 33 false Positives come from duplicates that are introduced from several list files
// and which are not removed by the ExtGaz
// the 2 missing come from matches within hyphenated words (after a hyphen) which are
// not found by ExtGaz because they occur inside a single Token (hyphens do not split up tokens)
assertEquals(194,correct);