Examples with OffsetAttribute org.apache.lucene.analysis.tokenattributes.OffsetAttribute used on opensource projects

Example 1 with OffsetAttribute

use of org.apache.lucene.analysis.tokenattributes.OffsetAttribute in project elasticsearch by elastic.

the class TransportAnalyzeAction method simpleAnalyze.

private static List<AnalyzeResponse.AnalyzeToken> simpleAnalyze(AnalyzeRequest request, Analyzer analyzer, String field) {
    List<AnalyzeResponse.AnalyzeToken> tokens = new ArrayList<>();
    int lastPosition = -1;
    int lastOffset = 0;
    for (String text : request.text()) {
        try (TokenStream stream = analyzer.tokenStream(field, text)) {
            stream.reset();
            CharTermAttribute term = stream.addAttribute(CharTermAttribute.class);
            PositionIncrementAttribute posIncr = stream.addAttribute(PositionIncrementAttribute.class);
            OffsetAttribute offset = stream.addAttribute(OffsetAttribute.class);
            TypeAttribute type = stream.addAttribute(TypeAttribute.class);
            PositionLengthAttribute posLen = stream.addAttribute(PositionLengthAttribute.class);
            while (stream.incrementToken()) {
                int increment = posIncr.getPositionIncrement();
                if (increment > 0) {
                    lastPosition = lastPosition + increment;
                }
                tokens.add(new AnalyzeResponse.AnalyzeToken(term.toString(), lastPosition, lastOffset + offset.startOffset(), lastOffset + offset.endOffset(), posLen.getPositionLength(), type.type(), null));
            }
            stream.end();
            lastOffset += offset.endOffset();
            lastPosition += posIncr.getPositionIncrement();
            lastPosition += analyzer.getPositionIncrementGap(field);
            lastOffset += analyzer.getOffsetGap(field);
        } catch (IOException e) {
            throw new ElasticsearchException("failed to analyze", e);
        }
    }
    return tokens;
}

Example 2 with OffsetAttribute

use of org.apache.lucene.analysis.tokenattributes.OffsetAttribute in project languagetool by languagetool-org.

the class LanguageToolFilterTest method displayTokensWithFullDetails.

private static void displayTokensWithFullDetails(TokenStream stream) throws IOException {
    CharTermAttribute term = stream.addAttribute(CharTermAttribute.class);
    PositionIncrementAttribute posIncr = stream.addAttribute(PositionIncrementAttribute.class);
    OffsetAttribute offset = stream.addAttribute(OffsetAttribute.class);
    TypeAttribute type = stream.addAttribute(TypeAttribute.class);
    int position = 0;
    while (stream.incrementToken()) {
        int increment = posIncr.getPositionIncrement();
        if (increment > 0) {
            position = position + increment;
            System.out.println();
            System.out.print(position + ": ");
        }
        System.out.print("[" + term + ":" + offset.startOffset() + "->" + offset.endOffset() + ":" + type.type() + "] ");
    }
    System.out.println();
}

Example 3 with OffsetAttribute

use of org.apache.lucene.analysis.tokenattributes.OffsetAttribute in project lucene-solr by apache.

the class SpellCheckComponent method getTokens.

private Collection<Token> getTokens(String q, Analyzer analyzer) throws IOException {
    Collection<Token> result = new ArrayList<>();
    assert analyzer != null;
    try (TokenStream ts = analyzer.tokenStream("", q)) {
        ts.reset();
        // TODO: support custom attributes
        CharTermAttribute termAtt = ts.addAttribute(CharTermAttribute.class);
        OffsetAttribute offsetAtt = ts.addAttribute(OffsetAttribute.class);
        TypeAttribute typeAtt = ts.addAttribute(TypeAttribute.class);
        FlagsAttribute flagsAtt = ts.addAttribute(FlagsAttribute.class);
        PayloadAttribute payloadAtt = ts.addAttribute(PayloadAttribute.class);
        PositionIncrementAttribute posIncAtt = ts.addAttribute(PositionIncrementAttribute.class);
        while (ts.incrementToken()) {
            Token token = new Token();
            token.copyBuffer(termAtt.buffer(), 0, termAtt.length());
            token.setOffset(offsetAtt.startOffset(), offsetAtt.endOffset());
            token.setType(typeAtt.type());
            token.setFlags(flagsAtt.getFlags());
            token.setPayload(payloadAtt.getPayload());
            token.setPositionIncrement(posIncAtt.getPositionIncrement());
            result.add(token);
        }
        ts.end();
        return result;
    }
}

Example 4 with OffsetAttribute

use of org.apache.lucene.analysis.tokenattributes.OffsetAttribute in project lucene-solr by apache.

the class SimplePreAnalyzedParser method toFormattedString.

@Override
public String toFormattedString(Field f) throws IOException {
    StringBuilder sb = new StringBuilder();
    sb.append(VERSION + " ");
    if (f.fieldType().stored()) {
        String s = f.stringValue();
        if (s != null) {
            // encode the equals sign
            s = s.replaceAll("=", "\\=");
            sb.append('=');
            sb.append(s);
            sb.append('=');
        }
    }
    TokenStream ts = f.tokenStreamValue();
    if (ts != null) {
        StringBuilder tok = new StringBuilder();
        boolean next = false;
        while (ts.incrementToken()) {
            if (next) {
                sb.append(' ');
            } else {
                next = true;
            }
            tok.setLength(0);
            Iterator<Class<? extends Attribute>> it = ts.getAttributeClassesIterator();
            String cTerm = null;
            String tTerm = null;
            while (it.hasNext()) {
                Class<? extends Attribute> cl = it.next();
                Attribute att = ts.getAttribute(cl);
                if (att == null) {
                    continue;
                }
                if (cl.isAssignableFrom(CharTermAttribute.class)) {
                    CharTermAttribute catt = (CharTermAttribute) att;
                    cTerm = escape(catt.buffer(), catt.length());
                } else if (cl.isAssignableFrom(TermToBytesRefAttribute.class)) {
                    TermToBytesRefAttribute tatt = (TermToBytesRefAttribute) att;
                    char[] tTermChars = tatt.getBytesRef().utf8ToString().toCharArray();
                    tTerm = escape(tTermChars, tTermChars.length);
                } else {
                    if (tok.length() > 0)
                        tok.append(',');
                    if (cl.isAssignableFrom(FlagsAttribute.class)) {
                        tok.append("f=" + Integer.toHexString(((FlagsAttribute) att).getFlags()));
                    } else if (cl.isAssignableFrom(OffsetAttribute.class)) {
                        tok.append("s=" + ((OffsetAttribute) att).startOffset() + ",e=" + ((OffsetAttribute) att).endOffset());
                    } else if (cl.isAssignableFrom(PayloadAttribute.class)) {
                        BytesRef p = ((PayloadAttribute) att).getPayload();
                        if (p != null && p.length > 0) {
                            tok.append("p=" + bytesToHex(p.bytes, p.offset, p.length));
                        } else if (tok.length() > 0) {
                            // remove the last comma
                            tok.setLength(tok.length() - 1);
                        }
                    } else if (cl.isAssignableFrom(PositionIncrementAttribute.class)) {
                        tok.append("i=" + ((PositionIncrementAttribute) att).getPositionIncrement());
                    } else if (cl.isAssignableFrom(TypeAttribute.class)) {
                        tok.append("y=" + escape(((TypeAttribute) att).type()));
                    } else {
                        tok.append(cl.getName() + "=" + escape(att.toString()));
                    }
                }
            }
            String term = null;
            if (cTerm != null) {
                term = cTerm;
            } else {
                term = tTerm;
            }
            if (term != null && term.length() > 0) {
                if (tok.length() > 0) {
                    tok.insert(0, term + ",");
                } else {
                    tok.insert(0, term);
                }
            }
            sb.append(tok);
        }
    }
    return sb.toString();
}

Example 5 with OffsetAttribute

use of org.apache.lucene.analysis.tokenattributes.OffsetAttribute in project lucene-solr by apache.

the class TokenSourcesTest method testMaxStartOffsetConsistency.

public void testMaxStartOffsetConsistency() throws IOException {
    FieldType tvFieldType = new FieldType(TextField.TYPE_NOT_STORED);
    tvFieldType.setStoreTermVectors(true);
    tvFieldType.setStoreTermVectorOffsets(true);
    tvFieldType.setStoreTermVectorPositions(true);
    Directory dir = newDirectory();
    MockAnalyzer analyzer = new MockAnalyzer(random());
    //we don't necessarily consume the whole stream because of limiting by startOffset
    analyzer.setEnableChecks(false);
    Document doc = new Document();
    final String TEXT = " f gg h";
    doc.add(new Field("fld_tv", analyzer.tokenStream("fooFld", TEXT), tvFieldType));
    doc.add(new TextField("fld_notv", analyzer.tokenStream("barFld", TEXT)));
    IndexReader reader;
    try (RandomIndexWriter writer = new RandomIndexWriter(random(), dir)) {
        writer.addDocument(doc);
        reader = writer.getReader();
    }
    try {
        Fields tvFields = reader.getTermVectors(0);
        for (int maxStartOffset = -1; maxStartOffset <= TEXT.length(); maxStartOffset++) {
            TokenStream tvStream = TokenSources.getTokenStream("fld_tv", tvFields, TEXT, analyzer, maxStartOffset);
            TokenStream anaStream = TokenSources.getTokenStream("fld_notv", tvFields, TEXT, analyzer, maxStartOffset);
            //assert have same tokens, none of which has a start offset > maxStartOffset
            final OffsetAttribute tvOffAtt = tvStream.addAttribute(OffsetAttribute.class);
            final OffsetAttribute anaOffAtt = anaStream.addAttribute(OffsetAttribute.class);
            tvStream.reset();
            anaStream.reset();
            while (tvStream.incrementToken()) {
                assertTrue(anaStream.incrementToken());
                assertEquals(tvOffAtt.startOffset(), anaOffAtt.startOffset());
                if (maxStartOffset >= 0)
                    assertTrue(tvOffAtt.startOffset() <= maxStartOffset);
            }
            assertTrue(anaStream.incrementToken() == false);
            tvStream.end();
            anaStream.end();
            tvStream.close();
            anaStream.close();
        }
    } finally {
        reader.close();
    }
    dir.close();
}