package lemmaextractor;

import edu.stanford.nlp.ling.CoreAnnotations;
import edu.stanford.nlp.ling.CoreLabel;
import edu.stanford.nlp.pipeline.Annotation;
import edu.stanford.nlp.pipeline.StanfordCoreNLP;
import edu.stanford.nlp.util.CoreMap;
import lemmaextractor.results.Result;

import java.util.Properties;

/**
 * Created with IntelliJ IDEA.
 * User: michal
 * Date: 24.03.14
 * Time: 14:15
 * To change this template use File | Settings | File Templates.
 */
public class DummyProcessor implements LanguageProcessor{

    private String lang;
    StanfordCoreNLP pipeline;

    public DummyProcessor(String lang){
        this.lang = lang;
        Properties props = new Properties();
        props.put("annotators", "tokenize, ssplit");
        pipeline = new StanfordCoreNLP(props);
    }
    @Override
    public Result processFull(String text) {
        return processLemmas(text);
    }

    @Override
    public Result processLemmas(String text){
        Result result = new Result(lang);
        Annotation document = new Annotation(text);
        pipeline.annotate(document);
        int positionInText = 0;
        for(CoreMap sentence: document.get(CoreAnnotations.SentencesAnnotation.class)) {
            for (CoreLabel token : sentence.get(CoreAnnotations.TokensAnnotation.class)) {
                String word = token.get(CoreAnnotations.TextAnnotation.class);
                int token_start = text.indexOf(word, positionInText);
                int token_end = token_start + word.length();
                result.addLemma(word, token_start, token_end);
                positionInText = token_end;

            }
        }
        return result;
    }

    public void setLang(String lang){
        this.lang = lang;
    }
}