Example usage for org.apache.lucene.analysis.tokenattributes OffsetAttributeImpl OffsetAttributeImpl

Introduction

In this page you can find the example usage for org.apache.lucene.analysis.tokenattributes OffsetAttributeImpl OffsetAttributeImpl.

Prototype

public OffsetAttributeImpl() 

Source Link

Document

Initialize this attribute with startOffset and endOffset of 0.

Usage

From source file:org.hibernate.search.test.serialization.SerializationTest.java

License:Open Source License

private List<List<AttributeImpl>> buildTokenSteamWithAttributes() {
    List<List<AttributeImpl>> tokens = new ArrayList<List<AttributeImpl>>();
    tokens.add(new ArrayList<AttributeImpl>());
    AnalysisRequestHandlerBase.TokenTrackingAttributeImpl attrImpl = new AnalysisRequestHandlerBase.TokenTrackingAttributeImpl();
    attrImpl.reset(new int[] { 1, 2, 3 }, 4);
    tokens.get(0).add(attrImpl);//  w  w  w .jav  a  2  s . c o m

    CharTermAttributeImpl charAttr = new CharTermAttributeImpl();
    charAttr.append("Wazzza");
    tokens.get(0).add(charAttr);

    PayloadAttributeImpl payloadAttribute = new PayloadAttributeImpl();
    payloadAttribute.setPayload(new Payload(new byte[] { 0, 1, 2, 3 }));
    tokens.get(0).add(payloadAttribute);

    KeywordAttributeImpl keywordAttr = new KeywordAttributeImpl();
    keywordAttr.setKeyword(true);
    tokens.get(0).add(keywordAttr);

    PositionIncrementAttributeImpl posIncrAttr = new PositionIncrementAttributeImpl();
    posIncrAttr.setPositionIncrement(3);
    tokens.get(0).add(posIncrAttr);

    FlagsAttributeImpl flagsAttr = new FlagsAttributeImpl();
    flagsAttr.setFlags(435);
    tokens.get(0).add(flagsAttr);

    TypeAttributeImpl typeAttr = new TypeAttributeImpl();
    typeAttr.setType("acronym");
    tokens.get(0).add(typeAttr);

    OffsetAttributeImpl offsetAttr = new OffsetAttributeImpl();
    offsetAttr.setOffset(4, 7);
    tokens.get(0).add(offsetAttr);
    return tokens;
}

---

From source file:org.hibernate.search.test.util.SerializationTestHelper.java

License:LGPL

public static List<List<AttributeImpl>> buildTokenStreamWithAttributes() {
    List<List<AttributeImpl>> tokens = new ArrayList<>();
    tokens.add(new ArrayList<AttributeImpl>());

    CharTermAttributeImpl charAttr = new CharTermAttributeImpl();
    charAttr.append("Wazzza");
    tokens.get(0).add(charAttr);/*from  w ww .  j  av a 2 s  . c  o  m*/

    PayloadAttributeImpl payloadAttribute = new PayloadAttributeImpl();
    payloadAttribute.setPayload(new BytesRef(new byte[] { 0, 1, 2, 3 }));
    tokens.get(0).add(payloadAttribute);

    KeywordAttributeImpl keywordAttr = new KeywordAttributeImpl();
    keywordAttr.setKeyword(true);
    tokens.get(0).add(keywordAttr);

    PositionIncrementAttributeImpl posIncrAttr = new PositionIncrementAttributeImpl();
    posIncrAttr.setPositionIncrement(3);
    tokens.get(0).add(posIncrAttr);

    FlagsAttributeImpl flagsAttr = new FlagsAttributeImpl();
    flagsAttr.setFlags(435);
    tokens.get(0).add(flagsAttr);

    TypeAttributeImpl typeAttr = new TypeAttributeImpl();
    typeAttr.setType("acronym");
    tokens.get(0).add(typeAttr);

    OffsetAttributeImpl offsetAttr = new OffsetAttributeImpl();
    offsetAttr.setOffset(4, 7);
    tokens.get(0).add(offsetAttr);
    return tokens;
}

---

From source file:org.tallison.lucene.search.concordance.charoffsets.DocTokenOffsets.java

License:Apache License

public void addOffset(int start, int end) {
    OffsetAttributeImpl offset = new OffsetAttributeImpl();
    offset.setOffset(start, end);/* w  w  w.ja  va  2 s.c om*/
    offsets.add(offset);
}

---

From source file:org.tallison.lucene.search.concordance.classic.WindowBuilder.java

License:Apache License

private OffsetAttribute buildOffsetAttribute(int start, int end) {
    OffsetAttribute off = new OffsetAttributeImpl();
    off.setOffset(start, end);// ww  w  . j a v a 2s .  c  o  m
    return off;
}

---

From source file:org.tallison.lucene.search.concordance.windowvisitor.NGrammer.java

License:Apache License

private List<OffsetAttribute> getGramOffsets(List<String> strings) {
    List<OffsetAttribute> ret = new ArrayList<>();
    for (int i = 0; i < strings.size(); i++) {
        for (int j = i + getMinGram() - 1; j < i + getMaxGram() && j < strings.size(); j++) {
            OffsetAttribute off = new OffsetAttributeImpl();
            off.setOffset(i, j);/*w w  w  .j  a  v a  2  s . c o m*/
            ret.add(off);
        }
    }
    return ret;
}

---

From source file:org.tallison.lucene.search.concordance.windowvisitor.WGrammer.java

License:Apache License

private List<OffsetAttribute> getGramOffsets(List<String> strings, int min, int max) {
    //for now, copy strings to terms
    List<Term> terms = new ArrayList<>();
    for (String s : strings) {
        terms.add(new Term(fieldName, s));
    }/* ww  w  .j a  v  a2 s  .  co  m*/

    List<OffsetAttribute> ret = new ArrayList<>();
    for (int i = 0; i < strings.size(); i++) {
        if (ConcordanceArrayWindow.isStopOrFieldSeparator(strings.get(i))) {
            continue;
        } else if (!tokenBlackList.accept(terms.get(i))) {
            continue;
        }

        int nonStops = 0;
        for (int j = i; nonStops < max && j < strings.size(); j++) {
            String tmp = strings.get(j);
            if (ConcordanceArrayWindow.isStop(tmp) || !tokenBlackList.accept(terms.get(j))
                    || (allowFieldSeparators == true && ConcordanceArrayWindow.isFieldSeparator(tmp))) {
                continue;
            } else if (allowFieldSeparators == false && ConcordanceArrayWindow.isFieldSeparator(tmp)) {
                break;
            }
            nonStops++;
            if (nonStops >= min) {
                OffsetAttribute offset = new OffsetAttributeImpl();
                offset.setOffset(i, j);
                ret.add(offset);
            }
        }
    }
    return ret;
}

---