Example usage for org.apache.lucene.search.highlight Scorer startFragment

Introduction

In this page you can find the example usage for org.apache.lucene.search.highlight Scorer startFragment.

Prototype

public void startFragment(TextFragment newFragment);

Source Link

Document

Called when a new fragment is started for consideration.

Usage

From source file:it.cnr.ilc.lc.clavius.search.ClaviusHighlighter.java

public final List<Annotation> getBestTextClaviusFragments(TokenStream tokenStream, String idDoc,
        boolean mergeContiguousFragments, int maxNumFragments)
        throws IOException, InvalidTokenOffsetsException {

    List<Annotation> ret = new ArrayList<>();

    ArrayList<ClaviusTextFragment> docFrags = new ArrayList<>();
    StringBuilder newText = new StringBuilder();

    Scorer fragmentScorer = getFragmentScorer();
    Fragmenter textFragmenter = getTextFragmenter();
    int maxDocCharsToAnalyze = getMaxDocCharsToAnalyze();
    Encoder encoder = getEncoder();

    CharTermAttribute termAtt = tokenStream.addAttribute(CharTermAttribute.class);
    OffsetAttribute offsetAtt = tokenStream.addAttribute(OffsetAttribute.class);
    ClaviusTextFragment currentFrag = new ClaviusTextFragment(newText, newText.length(), docFrags.size());

    if (fragmentScorer instanceof QueryScorer) {
        ((QueryScorer) fragmentScorer).setMaxDocCharsToAnalyze(Integer.MAX_VALUE);
    }/*from  w w w .j  a v a2 s  .co  m*/

    TokenStream newStream = fragmentScorer.init(tokenStream);
    if (newStream != null) {
        tokenStream = newStream;
    }
    fragmentScorer.startFragment(currentFrag);
    docFrags.add(currentFrag);

    //        FragmentQueue fragQueue = new FragmentQueue(maxNumFragments);
    try {

        String tokenText;
        int startOffset;
        int endOffset;
        int lastEndOffset = 0;
        //textFragmenter.start(text, tokenStream);

        ClaviusTokenGroup tokenGroup = new ClaviusTokenGroup(tokenStream);

        tokenStream.reset();
        // log.info("tokenGroup.getNumTokens() A: " + tokenGroup.getNumTokens());

        for (boolean next = tokenStream.incrementToken(); next
                && (offsetAtt.startOffset() < maxDocCharsToAnalyze); next = tokenStream.incrementToken()) {

            //                if ((offsetAtt.endOffset() > text.length())
            //                        || (offsetAtt.startOffset() > text.length())) {
            //                    throw new InvalidTokenOffsetsException("Token " + termAtt.toString()
            //                            + " exceeds length of provided text sized " + text.length());
            //                }
            //  log.info("newText: A (" + newText.toString() + "), fragmentScorer.getTokenScore()("+fragmentScorer.getTokenScore()+")");
            tokenGroup.addToken(fragmentScorer.getTokenScore());

        } // END FOR
          //  log.info("tokenGroup.getNumTokens() B: " + tokenGroup.getNumTokens());

        for (int i = 0; i < tokenGroup.getNumTokens(); i++) {
            //log.info("tokenGroup[" + i + "]: token: " + tokenGroup.getToken(i) + ", score: " + tokenGroup.getScore(i));
            if (tokenGroup.getScore(i) > 0) {
                Annotation a = new Annotation();
                a.setMatched(tokenGroup.getToken(i).toString());
                a.setIdDoc(idDoc);
                //contesto sinistro
                Token[] t = Arrays.copyOfRange(tokenGroup.getTokens(), (i > ctxLenght) ? i - ctxLenght : 0, i);
                StringBuilder sb = new StringBuilder();
                for (int j = 0; j < t.length; j++) {
                    sb.append(t[j].toString());
                    if (j < t.length - 1) {
                        sb.append(" ");
                    }
                }
                a.setLeftContext(sb.toString());
                sb.setLength(0);
                //contesto destro
                t = Arrays.copyOfRange(tokenGroup.getTokens(), i + 1,
                        (i + ctxLenght + 1 < tokenGroup.getNumTokens() ? i + ctxLenght + 1
                                : tokenGroup.getNumTokens()));
                sb = new StringBuilder();
                for (int j = 0; j < t.length; j++) {
                    sb.append(t[j].toString());
                    if (j < t.length - 1) {
                        sb.append(" ");
                    }
                }
                a.setRightContext(sb.toString());

                a.setConcept("");
                a.setType("");
                a.setIdNeo4j(-1l);
                a.setPageNum(-1l);
                a.setResourceObject("");
                a.setId(-1l);

                ret.add(a);
            }
        }

        return ret;

    } finally {
        if (tokenStream != null) {
            try {
                tokenStream.end();
                tokenStream.close();
            } catch (Exception e) {
            }
        }
    }
}

---

From source file:it.cnr.ilc.lc.claviusweb.fulltextsearch.ClaviusHighlighter.java

public final List<Annotation> getBestTextClaviusFragments(TokenStream tokenStream, Document document,
        boolean mergeContiguousFragments, int maxNumFragments)
        throws IOException, InvalidTokenOffsetsException {

    List<Annotation> ret = new ArrayList<>();

    ArrayList<ClaviusTextFragment> docFrags = new ArrayList<>();
    StringBuilder newText = new StringBuilder();

    Scorer fragmentScorer = getFragmentScorer();
    Fragmenter textFragmenter = getTextFragmenter();
    int maxDocCharsToAnalyze = getMaxDocCharsToAnalyze();
    Encoder encoder = getEncoder();

    CharTermAttribute termAtt = tokenStream.addAttribute(CharTermAttribute.class);
    OffsetAttribute offsetAtt = tokenStream.addAttribute(OffsetAttribute.class);
    ClaviusTextFragment currentFrag = new ClaviusTextFragment(newText, newText.length(), docFrags.size());

    if (fragmentScorer instanceof QueryScorer) {
        ((QueryScorer) fragmentScorer).setMaxDocCharsToAnalyze(Integer.MAX_VALUE);
    }/*ww  w  .ja v  a  2  s  .com*/

    TokenStream newStream = fragmentScorer.init(tokenStream);
    if (newStream != null) {
        tokenStream = newStream;
    }
    fragmentScorer.startFragment(currentFrag);
    docFrags.add(currentFrag);

    //        FragmentQueue fragQueue = new FragmentQueue(maxNumFragments);
    try {

        String tokenText;
        int startOffset;
        int endOffset;
        int lastEndOffset = 0;
        //textFragmenter.start(text, tokenStream);

        ClaviusTokenGroup tokenGroup = new ClaviusTokenGroup(tokenStream);

        tokenStream.reset();
        //log.info("tokenGroup.getNumTokens() A: " + tokenGroup.getNumTokens());

        for (boolean next = tokenStream.incrementToken(); next
                && (offsetAtt.startOffset() < maxDocCharsToAnalyze); next = tokenStream.incrementToken()) {

            //                if ((offsetAtt.endOffset() > text.length())
            //                        || (offsetAtt.startOffset() > text.length())) {
            //                    throw new InvalidTokenOffsetsException("Token " + termAtt.toString()
            //                            + " exceeds length of provided text sized " + text.length());
            //                }
            //  log.info("newText: A (" + newText.toString() + "), fragmentScorer.getTokenScore()("+fragmentScorer.getTokenScore()+")");
            tokenGroup.addToken(fragmentScorer.getTokenScore());

        } // END FOR
          //log.info("tokenGroup.getNumTokens() B: " + tokenGroup.getNumTokens());

        for (int i = 0; i < tokenGroup.getNumTokens(); i++) {
            //log.info("tokenGroup[" + i + "]: token: " + tokenGroup.getToken(i) + ", score: " + tokenGroup.getScore(i));
            if (tokenGroup.getScore(i) > 0) {
                Annotation a = new Annotation();
                a.setMatched(tokenGroup.getToken(i).toString());
                a.setIdDoc(document.get("idDoc"));
                //contesto sinistro
                Token[] t = Arrays.copyOfRange(tokenGroup.getTokens(), (i > ctxLenght) ? i - ctxLenght : 0, i);
                StringBuilder sb = new StringBuilder();
                for (int j = 0; j < t.length; j++) {
                    sb.append(t[j].toString());
                    if (j < t.length - 1) {
                        sb.append(" ");
                    }
                }
                a.setLeftContext(sb.toString());
                sb.setLength(0);
                //contesto destro
                t = Arrays.copyOfRange(tokenGroup.getTokens(), i + 1,
                        (i + ctxLenght + 1 < tokenGroup.getNumTokens() ? i + ctxLenght + 1
                                : tokenGroup.getNumTokens()));
                sb = new StringBuilder();
                for (int j = 0; j < t.length; j++) {
                    sb.append(t[j].toString());
                    if (j < t.length - 1) {
                        sb.append(" ");
                    }
                }
                a.setRightContext(sb.toString());

                a.setConcept("");
                a.setType("");
                a.setPageNum(-1l);
                // a.setIdNeo4j(Long.parseLong(document.get("idNeo4j")));
                a.setIdNeo4j(Long.parseLong(document.get("idDoc")));
                a.setResourceObject("");
                a.setId(-1l);

                ret.add(a);
            }
        }

        return ret;

    } finally {
        if (tokenStream != null) {
            try {
                tokenStream.end();
                tokenStream.close();
            } catch (Exception e) {
            }
        }
    }
}

---