/**
* Read the data set incrementally---get the next instance in the data set or returns null if
* there are no more instances to get. If the structure hasn't yet been determined by a call to
* getStructure then method should do so before returning the next instance in the data set.
*
* @return the next instance in the data set as an Instance object or null if there are no more
* instances to be read
* @exception IOException if there is an error during parsing
*/
public Instance getNextInstance() throws IOException {
if (m_structure == null) {
getStructure();
}
if (getRetrieval() == BATCH) {
throw new IOException("Cannot mix getting Instances in both incremental and batch modes");
}
setRetrieval(INCREMENTAL);
if (!m_structure.readInstance(m_sourceReader)) {
return null;
}
Instance current = m_structure.instance(0);
m_structure.delete(0);
return current;
}
/**
* Return the full data set. If the structure hasn't yet been determined by a call to getStructure
* then method should do so before processing the rest of the data set.
*
* @return the structure of the data set as an empty set of Instances
* @exception IOException if there is no source or parsing fails
*/
public Instances getDataSet() throws IOException {
if (m_sourceReader == null) {
throw new IOException("No source has been specified");
}
if (getRetrieval() == INCREMENTAL) {
throw new IOException("Cannot mix getting Instances in both incremental and batch modes");
}
setRetrieval(BATCH);
if (m_structure == null) {
getStructure();
}
// Read all instances
// XXX This is inefficient because readInstance creates a new
// StringTokenizer each time: This will be fixed once all arff reading
// is moved out of Instances and into this Loader.
while (m_structure.readInstance(m_sourceReader)) ;
return m_structure;
}