SubsetValidator.java 文件源码

public static Triple<Formatter,Float,Float> validate(LangDescriptor language,
                                                         List<InputDocument> documents,
                                                         InputDocument testDoc,
                                                         boolean saveOutput,
                                                         boolean computeEditDistance)
        throws Exception
    {
//      kNNClassifier.resetCache();
        Corpus corpus = new Corpus(documents, language);
        corpus.train();
//      System.out.printf("%d feature vectors\n", corpus.featureVectors.size());
        Formatter formatter = new Formatter(corpus, language.indentSize);
        String output = formatter.format(testDoc, false);
        float editDistance = 0;
        if ( computeEditDistance ) {
            editDistance = normalizedLevenshteinDistance(testDoc.content, output);
        }
        ClassificationAnalysis analysis = new ClassificationAnalysis(testDoc, formatter.getAnalysisPerToken());
//      System.out.println(testDoc.fileName+": edit distance = "+editDistance+", error rate = "+analysis.getErrorRate());
        if ( saveOutput ) {
            File dir = new File(outputDir+"/"+language.name);
            if ( saveOutput ) {
                dir = new File(outputDir+"/"+language.name);
                dir.mkdir();
            }
            Utils.writeFile(dir.getPath()+"/"+new File(testDoc.fileName).getName(), output);
        }
        return new Triple<>(formatter, editDistance, analysis.getErrorRate());
    }