/**
* Overwrite this method if you want to filter the input, apply hashing, etc.
*
* @param feature the current feature.
* @param document the current document.
* @param featureFieldName the field hashFunctionsFileName of the feature.
*/
protected void addToDocument(LireFeature feature, Document document, String featureFieldName) {
if (run == 0) {
} // just count documents
else if (run == 1) { // Select the representatives ...
if (representativesID.contains(docCount)
&& feature
.getClass()
.getCanonicalName()
.equals(featureClass.getCanonicalName())) { // it's a representative.
// put it into a temporary data structure ...
representatives.add(feature);
}
} else if (run
== 2) { // actual hashing: find the nearest representatives and put those as a hash into a
// document.
if (feature
.getClass()
.getCanonicalName()
.equals(featureClass.getCanonicalName())) { // it's a feature to be hashed
int[] hashes = getHashes(feature);
document.add(
new TextField(
featureFieldName + "_hash",
createDocumentString(hashes, hashes.length),
Field.Store.YES));
document.add(
new TextField(
featureFieldName + "_hash_q", createDocumentString(hashes, 10), Field.Store.YES));
}
document.add(new StoredField(featureFieldName, feature.getByteArrayRepresentation()));
}
}
/**
* Reads data from a file and writes it to an index.
*
* @param indexWriter the index to write to.
* @param inputFile the input data for the process.
* @throws IOException
* @throws InstantiationException
* @throws IllegalAccessException
* @throws ClassNotFoundException
*/
private void readFile(IndexWriter indexWriter, File inputFile)
throws IOException, InstantiationException, IllegalAccessException, ClassNotFoundException {
BufferedInputStream in = new BufferedInputStream(new FileInputStream(inputFile));
byte[] tempInt = new byte[4];
int tmp, tmpFeature, count = 0;
byte[] temp = new byte[100 * 1024];
// read file hashFunctionsFileName length:
while (in.read(tempInt, 0, 4) > 0) {
Document d = new Document();
tmp = SerializationUtils.toInt(tempInt);
// read file hashFunctionsFileName:
in.read(temp, 0, tmp);
String filename = new String(temp, 0, tmp);
// normalize Filename to full path.
filename =
inputFile
.getCanonicalPath()
.substring(0, inputFile.getCanonicalPath().lastIndexOf(inputFile.getName()))
+ filename;
d.add(new StringField(DocumentBuilder.FIELD_NAME_IDENTIFIER, filename, Field.Store.YES));
// System.out.print(filename);
while ((tmpFeature = in.read()) < 255) {
// System.out.print(", " + tmpFeature);
LireFeature f = (LireFeature) Class.forName(Extractor.features[tmpFeature]).newInstance();
// byte[] length ...
in.read(tempInt, 0, 4);
tmp = SerializationUtils.toInt(tempInt);
// read feature byte[]
in.read(temp, 0, tmp);
f.setByteArrayRepresentation(temp, 0, tmp);
addToDocument(f, d, Extractor.featureFieldNames[tmpFeature]);
// d.add(new StoredField(Extractor.featureFieldNames[tmpFeature],
// f.getByteArrayRepresentation()));
}
if (run == 2) indexWriter.addDocument(d);
docCount++;
// if (count%1000==0) System.out.print('.');
// if (count%10000==0) System.out.println(" " + count);
}
in.close();
}