|
using System;
namespace OpenNLP.Tools.POSTagger
{
/// <summary> An implementation of EventStream whcih assumes the data stream gives a
/// sentence at a time with tokens as word_tag pairs.
/// </summary>
public class PosEventReader : SharpEntropy.ITrainingEventReader
{
private IPosContextGenerator ContextGenerator;
private SharpEntropy.ITrainingDataReader Data;
private SharpEntropy.TrainingEvent[] Events;
private int EventIndex;
public PosEventReader(SharpEntropy.ITrainingDataReader data):this(data, new DefaultPosContextGenerator())
{
}
public PosEventReader(SharpEntropy.ITrainingDataReader data, IPosContextGenerator contextGenerator)
{
ContextGenerator = contextGenerator;
Data = data;
EventIndex = 0;
if (Data.HasNext())
{
AddNewEvents((string) Data.NextToken());
}
else
{
Events = new SharpEntropy.TrainingEvent[0];
}
}
public virtual bool HasNext()
{
return (EventIndex < Events.Length || Data.HasNext());
}
public virtual SharpEntropy.TrainingEvent ReadNextEvent()
{
if (EventIndex == Events.Length)
{
AddNewEvents((string) Data.NextToken());
EventIndex = 0;
}
return ((SharpEntropy.TrainingEvent) Events[EventIndex++]);
}
private void AddNewEvents(string sentence)
{
//String sentence = "the_DT stories_NNS about_IN well-heeled_JJ communities_NNS and_CC developers_NNS";
SharpEntropy.IEventCollector oEventCollector = new PosEventCollector(new System.IO.StringReader(sentence), ContextGenerator);
Events = oEventCollector.GetEvents();
}
[STAThread]
public static void Main(string[] args)
{
EventStream oEventStream = new PosEventStream(new Maxent.PlainTextByLineDataStream(new System.IO.StreamReader(System.Console.In)));
while (oEventStream.HasNext())
{
System.Console.Out.WriteLine(oEventStream.GetNextEvent());
}
}
}
}
|
By viewing downloads associated with this article you agree to the Terms of Service and the article's licence.
If a file you wish to view isn't highlighted, and is a text file (not binary), please
let us know and we'll add colourisation support for it.
This article has no explicit license attached to it but may contain usage terms in the article text or the download files themselves. If in doubt please contact the author via the discussion board below.
A list of licenses authors might use can be found here
Richard Northedge is a senior developer with a UK Microsoft Gold Partner company. He has a postgraduate degree in English Literature, has been programming professionally since 1998 and has been an MCSD since 2000.