/**
 * Constructor for creating a new CorpusRepresentation from a FeatureInfo. 
 * 
 * @param fi FeatureInfo instance
 * @param targetType type of target
 */
public CorpusRepresentationMalletTarget(FeatureInfo fi, TargetType targetType) {
  featureInfo = fi;
  scalingMethod = fi.getGlobalScalingMethod();    
  this.targetType = targetType;
  LabelAlphabet targetAlphabet = (targetType == TargetType.NOMINAL) ? new LabelAlphabet() : null;
  Pipe innerPipe = new Noop(new LFAlphabet(), targetAlphabet);
  List<Pipe> pipes = new ArrayList<>();
  pipes.add(innerPipe);
  pipe = new LFPipe(pipes);
  pipe.setFeatureInfo(fi);
  instances = new LFInstanceList(pipe);
}
 

public CorpusRepresentationMalletLDA(FeatureInfo fi) {
  featureInfo = fi;  // always null
  // since we always pass a null feature info, the scaling method is hard-wired to be NONE
  scalingMethod = ScalingMethod.NONE;

  // TODO: we really do not need any of this, figure out if we can simplify,
  // but keeping this should not really do any harm!
  Pipe innerPipe = new Noop(new LFAlphabet(), null);
  List<Pipe> pipes = new ArrayList<>();
  pipes.add(innerPipe);
  pipe = new LFPipe(pipes);
  pipe.setFeatureInfo(fi);
  instances = new LFInstanceList(pipe);
  targetType = TargetType.NONE;
}
 

public CorpusRepresentationMalletSeq(FeatureInfo fi) {
  featureInfo = fi;
  scalingMethod = fi.getGlobalScalingMethod();

  Pipe innerPipe = new Noop(new LFAlphabet(), new LabelAlphabet());
  List<Pipe> pipes = new ArrayList<>();
  pipes.add(innerPipe);
  pipe = new LFPipe(pipes);
  pipe.setFeatureInfo(fi);
  instances = new LFInstanceList(pipe);
  targetType = TargetType.NOMINAL;
}
 

@Test
public void testPipeSerialization1() throws ResourceInstantiationException, IOException, ClassNotFoundException {
  String spec = "<ROOT>"+
          "<ATTRIBUTE><TYPE>theType</TYPE><FEATURE>feature1</FEATURE><DATATYPE>nominal</DATATYPE><CODEAS>number</CODEAS></ATTRIBUTE>"+
          "</ROOT>";    
  FeatureInfo fi = new FeatureSpecification(spec).getFeatureInfo();
  // Create a pipe with a data and target alphabet
  Pipe tmppipe = new Noop(new LFAlphabet(),new LabelAlphabet());
  List<Pipe> pipes = new ArrayList<>();
  pipes.add(tmppipe);
  LFPipe pipe = new LFPipe(pipes);
  pipe.setFeatureInfo(fi);
  
  // add an entry to the data alphabet
  pipe.getDataAlphabet().lookupIndex("feature1");
  // extract an instance - this should create/update the alphabet for the number representation of the feature
  Document doc = newDocument();
  Annotation instAnn = addAnn(doc,"",0,0,"theType",gate.Utils.featureMap("feature1","val1"));
  Instance inst = newInstance();
  FeatureSpecAttribute attr = fi.getAttributes().get(0);
  // make sure the attribute is a SimpleAttribute as expected
  assertEquals(FeatureSpecSimpleAttribute.class, attr.getClass());
  FeatureSpecSimpleAttribute sa = (FeatureSpecSimpleAttribute)attr;
  FeatureExtractionMalletSparse.extractFeature(inst, sa, doc.getAnnotations(), instAnn);
  // verify that we do have an alphabet in the attribute info
  assertNotNull(sa.alphabet);    
  System.err.println("DEBUG: the alphabet we have is "+sa.alphabet);
  assertTrue(sa.alphabet.contains("val1"));
  // remember that alphabet for later
  Alphabet valuealphabet = sa.alphabet;
  
  // No serialize the lfpipe
  File tmpFile = File.createTempFile("LF_test",".pipe");
  tmpFile.deleteOnExit();
  try (ObjectOutputStream oos = new ObjectOutputStream(new FileOutputStream(tmpFile))) {
    oos.writeObject(pipe);
  }    
  LFPipe pipe2;
  try ( // Now read it back and check if everything is there
          ObjectInputStream ois = new ObjectInputStream (new FileInputStream(tmpFile))) {
    pipe2 = (LFPipe) ois.readObject();
  }
  // check if the data and target alphabets match
  assertTrue(pipe2.alphabetsMatch(pipe));
  // Do we have a feature info?
  assertNotNull(pipe2.getFeatureInfo());
  // do we have attributes?
  assertNotNull(pipe2.getFeatureInfo().getAttributes());
  // is there exactly one attribute
  assertEquals(1, pipe2.getFeatureInfo().getAttributes().size());
  // does that attribute have an alphabet
  assertNotNull(((FeatureSpecSimpleAttribute)pipe2.getFeatureInfo().getAttributes().get(0)).alphabet);
  // is the alphabet identical to what we originally had
  assertEquals(valuealphabet,((FeatureSpecSimpleAttribute)pipe2.getFeatureInfo().getAttributes().get(0)).alphabet);
}
 

public LDAInstanceList(FastPreferenceData<U, I> preferences) {
    super(new Noop());
    this.preferences = preferences;
    this.alphabet = new LDAAlphabet(preferences.numItems());
}