import com.aliasi.chunk.CharLmHmmChunker;

import com.aliasi.corpus.parsers.GeneTagParser;

import com.aliasi.hmm.HmmCharLmEstimator;

import com.aliasi.tokenizer.IndoEuropeanTokenizerFactory;
import com.aliasi.tokenizer.TokenizerFactory;

import com.aliasi.util.AbstractExternalizable;
import com.aliasi.util.Streams;

import java.io.File;
import java.io.IOException;

public class TrainGeneTag {

    static final int MAX_N_GRAM = 8;
    static final int NUM_CHARS = 256;
    static final double LM_INTERPOLATION = MAX_N_GRAM; // default behavior

    // java TrainGeneTag <trainingInputFile> <modelOutputFile>
    public static void main(String[] args) throws IOException {
        File corpusFile = new File(args[0]);
        File modelFile = new File(args[1]);

        System.out.println("Setting up Chunker Estimator");
        TokenizerFactory factory
            = IndoEuropeanTokenizerFactory.INSTANCE;
        HmmCharLmEstimator hmmEstimator
            = new HmmCharLmEstimator(MAX_N_GRAM,NUM_CHARS,LM_INTERPOLATION);
        CharLmHmmChunker chunkerEstimator
            = new CharLmHmmChunker(factory,hmmEstimator);

        System.out.println("Setting up Data Parser");
        GeneTagParser parser = new GeneTagParser();
        parser.setHandler(chunkerEstimator);

        System.out.println("Training with Data from File=" + corpusFile);
        parser.parse(corpusFile);

        System.out.println("Compiling and Writing Model to File=" + modelFile);
        AbstractExternalizable.compileTo(chunkerEstimator,modelFile);
    }

}