/**
* 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()));
}
}
private int[] getHashes(LireFeature feature) {
// result = new int[maximumHits];
hashingResultScoreDocs.clear();
maxDistance = 0f;
tmpScore = 0f;
int rep = 0;
LireFeature tmpFeature;
for (Iterator<LireFeature> iterator = representatives.iterator(); iterator.hasNext(); ) {
tmpFeature = iterator.next();
tmpScore = tmpFeature.getDistance(feature);
if (hashingResultScoreDocs.size() < maximumHits) {
hashingResultScoreDocs.add(new SimpleResult(tmpScore, null, rep));
maxDistance = Math.max(maxDistance, tmpScore);
} else if (tmpScore < maxDistance) {
hashingResultScoreDocs.add(new SimpleResult(tmpScore, null, rep));
}
while (hashingResultScoreDocs.size() > maximumHits) {
hashingResultScoreDocs.remove(hashingResultScoreDocs.last());
maxDistance = hashingResultScoreDocs.last().getDistance();
}
rep++;
}
rep = 0;
for (Iterator<SimpleResult> iterator = hashingResultScoreDocs.iterator();
iterator.hasNext(); ) {
SimpleResult next = iterator.next();
result[rep] = next.getIndexNumber();
rep++;
}
return result;
}
protected TestConfig[] generateTestConfigs(
int numberOfTests, TestDoc[] testDocs, TestFieldSetting[] fieldSettings) {
ArrayList<TestConfig> configs = new ArrayList<TestConfig>();
for (int i = 0; i < numberOfTests; i++) {
ArrayList<String> selectedFields = null;
if (randomBoolean()) {
// used field selection
selectedFields = new ArrayList<String>();
if (randomBoolean()) {
selectedFields.add("Doesnt_exist"); // this will be ignored.
}
for (TestFieldSetting field : fieldSettings)
if (randomBoolean()) {
selectedFields.add(field.name);
}
if (selectedFields.size() == 0) {
selectedFields = null; // 0 length set is not supported.
}
}
TestConfig config =
new TestConfig(
testDocs[randomInt(testDocs.length - 1)],
selectedFields == null ? null : selectedFields.toArray(new String[] {}),
randomBoolean(),
randomBoolean(),
randomBoolean());
configs.add(config);
}
// always adds a test that fails
configs.add(
new TestConfig(
new TestDoc("doesnt_exist", new TestFieldSetting[] {}, new String[] {})
.index("doesn't_exist"),
new String[] {"doesnt_exist"},
true,
true,
true)
.expectedException(IndexMissingException.class));
refresh();
return configs.toArray(new TestConfig[] {});
}