Java DocumentBuilder.createDocument方法代码示例

import net.semanticmetadata.lire.DocumentBuilder; //导入方法依赖的package包/类
/**
 * Index for each builder type
 * @param image
 * @param picture_id
 * @param prefix
 * @param builder
 * @param conf
 * @throws IOException
 */
private static void luceneIndexer(BufferedImage image, UUID picture_id, String prefix, DocumentBuilder builder, IndexWriterConfig conf)
    throws IOException
{
    File path = getPath(prefix);
    log.debug("creating indexed path " + path.getAbsolutePath());
    IndexWriter iw = new IndexWriter(FSDirectory.open(path), conf);

    try {
        Document document = builder.createDocument(image, picture_id.toString());
        iw.addDocument(document);

    } catch (Exception e) {
        System.err.println("Error reading image or indexing it.");
        e.printStackTrace();
    }

    // closing the IndexWriter
    iw.close();
}
 

import net.semanticmetadata.lire.DocumentBuilder; //导入方法依赖的package包/类
private void indexFiles(ArrayList<String> images, DocumentBuilder builder, String indexPath) throws IOException {
        System.out.println(">> Indexing " + images.size() + " files.");
        IndexWriter iw = LuceneUtils.createIndexWriter(indexPath, true);
        int count = 0;
        long time = System.currentTimeMillis();
        for (String identifier : images) {
            Document doc = builder.createDocument(new FileInputStream(identifier), identifier);
            iw.addDocument(doc);
            count++;
            if (count % 100 == 0) System.out.println(count + " files indexed.");
//            if (count == 200) break;
        }
        long timeTaken = (System.currentTimeMillis() - time);
        float sec = ((float) timeTaken) / 1000f;

        System.out.println(sec + " seconds taken, " + (timeTaken / count) + " ms per image.");
        iw.close();
    }
 

import net.semanticmetadata.lire.DocumentBuilder; //导入方法依赖的package包/类
public static double[] processImage(BufferedImage img, String imgName, int imageGrid, DocumentBuilder builder, 
			String featureName, double[] featureOutput, Map<String, LireFeature> lireFeatures, int featureUsed) throws IOException, DecoderException {
		
		for (int i = 0; i < imageGrid; i++) {
			for (int j = 0; j < imageGrid; j++) {
				String subImgName = imgName + i + "," + j;
				Document document = builder.createDocument(getSubImageByRowAndColumn(img, i, j, imageGrid), subImgName);
				featureOutput[i * imageGrid + j] = getFeatures(document, featureName, lireFeatures)[featureUsed];
//				if (i == 0 && j == 0) {
//					System.out.println(featureName + " : " + getFeatures(document, featureName, lireFeatures).length);
//				}
			}
		}
		
		// normalize
		featureOutput = HistUtil.normalizeArray(featureOutput);
		
		return featureOutput;
	}
 

import net.semanticmetadata.lire.DocumentBuilder; //导入方法依赖的package包/类
public void testIndexing() throws IOException, ParserConfigurationException, SAXException {
    IndexWriterConfig iwConf = new IndexWriterConfig(Version.LUCENE_42, new SimpleAnalyzer(Version.LUCENE_42));
    IndexWriter iw = new IndexWriter(FSDirectory.open(testIndex), iwConf);
    // if you want to append the index to a pre-existing one use the next line.
    // iwConf.setOpenMode(IndexWriterConfig.OpenMode.APPEND);
    // create a LIRE DocumentBuilder for extracting FCTH (just an example, every other feature will do).
    DocumentBuilder builder = DocumentBuilderFactory.getFCTHDocumentBuilder();
    ArrayList<File> files = FileUtils.getAllImageFiles(new File("testdata/ferrari"), true);
    // for handling the XML of the test data set
    SAXParserFactory spf = SAXParserFactory.newInstance();
    spf.setNamespaceAware(true);
    SAXParser saxParser = spf.newSAXParser();
    XMLReader xmlReader = saxParser.getXMLReader();
    for (Iterator<File> iterator = files.iterator(); iterator.hasNext(); ) {
        File img = iterator.next();
        String path = img.getCanonicalPath();
        // create the document with the LIRE DocumentBuilder, this adds the image features to the document.
        Document d = builder.createDocument(new FileInputStream(img), path);
        // handling the XML of the test data set
        path = path.substring(0,path.lastIndexOf('.')) + ".xml";
        TagHandler handler = new TagHandler();
        xmlReader.setContentHandler(handler);
        xmlReader.parse(new InputSource(new File(path).toURI().toString()));
        // add the text to the document ...
        d.add(new TextField("tags", handler.getTags(), Field.Store.YES));
        // don't forget to add the document to the index.
        iw.addDocument(d);
    }
    iw.close();
}
 

import net.semanticmetadata.lire.DocumentBuilder; //导入方法依赖的package包/类
public static void main(String[] args) throws IOException {
    // Checking if arg[0] is there and if it is a directory.
    boolean passed = false;
    if (args.length > 0) {
        File f = new File(args[0]);
        System.out.println("Indexing images in " + args[0]);
        if (f.exists() && f.isDirectory()) passed = true;
    }
    if (!passed) {
        System.out.println("No directory given as first argument.");
        System.out.println("Run \"Indexer <directory>\" to index files of a directory.");
        System.exit(1);
    }
    // Getting all images from a directory and its sub directories.
    ArrayList<String> images = FileUtils.getAllImages(new File(args[0]), true);

    // Creating a CEDD document builder and indexing all files.
    DocumentBuilder builder = DocumentBuilderFactory.getCEDDDocumentBuilder();
    // Creating an Lucene IndexWriter
    IndexWriterConfig conf = new IndexWriterConfig(LuceneUtils.LUCENE_VERSION,
            new WhitespaceAnalyzer(LuceneUtils.LUCENE_VERSION));
    IndexWriter iw = new IndexWriter(FSDirectory.open(new File("index")), conf);
    // Iterating through images building the low level features
    for (Iterator<String> it = images.iterator(); it.hasNext(); ) {
        String imageFilePath = it.next();
        System.out.println("Indexing " + imageFilePath);
        try {
            BufferedImage img = ImageIO.read(new FileInputStream(imageFilePath));
            Document document = builder.createDocument(img, imageFilePath);
            iw.addDocument(document);
        } catch (Exception e) {
            System.err.println("Error reading image or indexing it.");
            e.printStackTrace();
        }
    }
    // closing the IndexWriter
    iw.close();
    System.out.println("Finished indexing.");
}