Example usage for org.apache.lucene.index Fields terms

Introduction

In this page you can find the example usage for org.apache.lucene.index Fields terms.

Prototype

public abstract Terms terms(String field) throws IOException;

Source Link

Document

Get the Terms for this field.

Usage

From source file:org.elasticsearch.common.lucene.search.XTermsFilter.java

License:Apache License

@Override
public DocIdSet getDocIdSet(AtomicReaderContext context, Bits acceptDocs) throws IOException {
    final AtomicReader reader = context.reader();
    FixedBitSet result = null; // lazy init if needed - no need to create a big bitset ahead of time
    final Fields fields = reader.fields();
    final BytesRef spare = new BytesRef(this.termsBytes);
    if (fields == null) {
        return result;
    }/*from  ww w.jav  a  2s . c  om*/
    Terms terms = null;
    TermsEnum termsEnum = null;
    DocsEnum docs = null;
    for (TermsAndField termsAndField : this.termsAndFields) {
        if ((terms = fields.terms(termsAndField.field)) != null) {
            termsEnum = terms.iterator(termsEnum); // this won't return null
            for (int i = termsAndField.start; i < termsAndField.end; i++) {
                spare.offset = offsets[i];
                spare.length = offsets[i + 1] - offsets[i];
                if (termsEnum.seekExact(spare, false)) { // don't use cache since we could pollute the cache here easily
                    docs = termsEnum.docs(acceptDocs, docs, 0); // no freq since we don't need them
                    if (result == null) {
                        if (docs.nextDoc() != DocIdSetIterator.NO_MORE_DOCS) {
                            result = new FixedBitSet(reader.maxDoc());
                            // lazy init but don't do it in the hot loop since we could read many docs
                            result.set(docs.docID());
                        }
                    }
                    while (docs.nextDoc() != DocIdSetIterator.NO_MORE_DOCS) {
                        result.set(docs.docID());
                    }
                }
            }
        }
    }
    return result;
}

---

From source file:org.elasticsearch.common.lucene.uid.PerThreadIDAndVersionLookup.java

License:Apache License

/**
 * Initialize lookup for the provided segment
 *//*from  w w w. ja  v a  2s  . c o  m*/
public PerThreadIDAndVersionLookup(LeafReader reader) throws IOException {
    TermsEnum termsEnum = null;
    NumericDocValues versions = null;
    boolean hasPayloads = false;

    Fields fields = reader.fields();
    if (fields != null) {
        Terms terms = fields.terms(UidFieldMapper.NAME);
        if (terms != null) {
            hasPayloads = terms.hasPayloads();
            termsEnum = terms.iterator();
            assert termsEnum != null;
            versions = reader.getNumericDocValues(VersionFieldMapper.NAME);
        }
    }

    this.versions = versions;
    this.termsEnum = termsEnum;
    this.hasPayloads = hasPayloads;
}

---

From source file:org.elasticsearch.common.lucene.uid.VersionsResolver.java

License:Apache License

/**
 * Returns the sequence number for the given uid term, returning
 * {@code SequenceNumbersService.UNASSIGNED_SEQ_NO} if none is found.
 *//*from   www . j  a va 2 s. com*/
public static long loadSeqNo(IndexReader reader, Term term) throws IOException {
    assert term.field().equals(UidFieldMapper.NAME) : "can only load _seq_no by uid";
    List<LeafReaderContext> leaves = reader.leaves();
    if (leaves.isEmpty()) {
        return SequenceNumbersService.UNASSIGNED_SEQ_NO;
    }

    // iterate backwards to optimize for the frequently updated documents
    // which are likely to be in the last segments
    for (int i = leaves.size() - 1; i >= 0; i--) {
        LeafReader leaf = leaves.get(i).reader();
        Bits liveDocs = leaf.getLiveDocs();

        TermsEnum termsEnum = null;
        SortedNumericDocValues dvField = null;
        PostingsEnum docsEnum = null;

        final Fields fields = leaf.fields();
        if (fields != null) {
            Terms terms = fields.terms(UidFieldMapper.NAME);
            if (terms != null) {
                termsEnum = terms.iterator();
                assert termsEnum != null;
                dvField = leaf.getSortedNumericDocValues(SeqNoFieldMapper.NAME);
                assert dvField != null;

                final BytesRef id = term.bytes();
                if (termsEnum.seekExact(id)) {
                    // there may be more than one matching docID, in the
                    // case of nested docs, so we want the last one:
                    docsEnum = termsEnum.postings(docsEnum, 0);
                    int docID = DocIdSetIterator.NO_MORE_DOCS;
                    for (int d = docsEnum.nextDoc(); d != DocIdSetIterator.NO_MORE_DOCS; d = docsEnum
                            .nextDoc()) {
                        if (liveDocs != null && liveDocs.get(d) == false) {
                            continue;
                        }
                        docID = d;
                    }

                    if (docID != DocIdSetIterator.NO_MORE_DOCS) {
                        dvField.setDocument(docID);
                        assert dvField.count() == 1 : "expected only a single value for _seq_no but got "
                                + dvField.count();
                        return dvField.valueAt(0);
                    }
                }
            }
        }

    }
    return SequenceNumbersService.UNASSIGNED_SEQ_NO;
}

---

From source file:org.elasticsearch.common.lucene.uid.VersionsResolver.java

License:Apache License

/**
 * Returns the primary term for the given uid term, returning {@code 0} if none is found.
 *///w  w w  . j  av a  2  s.c o m
public static long loadPrimaryTerm(IndexReader reader, Term term) throws IOException {
    assert term.field().equals(UidFieldMapper.NAME) : "can only load _primary_term by uid";
    List<LeafReaderContext> leaves = reader.leaves();
    if (leaves.isEmpty()) {
        return 0;
    }

    // iterate backwards to optimize for the frequently updated documents
    // which are likely to be in the last segments
    for (int i = leaves.size() - 1; i >= 0; i--) {
        LeafReader leaf = leaves.get(i).reader();
        Bits liveDocs = leaf.getLiveDocs();

        TermsEnum termsEnum = null;
        NumericDocValues dvField = null;
        PostingsEnum docsEnum = null;

        final Fields fields = leaf.fields();
        if (fields != null) {
            Terms terms = fields.terms(UidFieldMapper.NAME);
            if (terms != null) {
                termsEnum = terms.iterator();
                assert termsEnum != null;
                dvField = leaf.getNumericDocValues(SeqNoFieldMapper.PRIMARY_TERM_NAME);
                assert dvField != null;

                final BytesRef id = term.bytes();
                if (termsEnum.seekExact(id)) {
                    // there may be more than one matching docID, in the
                    // case of nested docs, so we want the last one:
                    docsEnum = termsEnum.postings(docsEnum, 0);
                    int docID = DocIdSetIterator.NO_MORE_DOCS;
                    for (int d = docsEnum.nextDoc(); d != DocIdSetIterator.NO_MORE_DOCS; d = docsEnum
                            .nextDoc()) {
                        if (liveDocs != null && liveDocs.get(d) == false) {
                            continue;
                        }
                        docID = d;
                    }

                    if (docID != DocIdSetIterator.NO_MORE_DOCS) {
                        return dvField.get(docID);
                    }
                }
            }
        }

    }
    return 0;
}

---

From source file:org.elasticsearch.index.percolator.ExtractQueryTermsService.java

License:Apache License

/**
 * Creates a boolean query with a should clause for each term on all fields of the specified index reader.
 *//*from   w ww. ja  va2 s.  c  o m*/
public static Query createQueryTermsQuery(IndexReader indexReader, String queryMetadataField,
        String unknownQueryField) throws IOException {
    List<Term> extractedTerms = new ArrayList<>();
    extractedTerms.add(new Term(unknownQueryField));
    Fields fields = MultiFields.getFields(indexReader);
    for (String field : fields) {
        Terms terms = fields.terms(field);
        if (terms == null) {
            continue;
        }

        BytesRef fieldBr = new BytesRef(field);
        TermsEnum tenum = terms.iterator();
        for (BytesRef term = tenum.next(); term != null; term = tenum.next()) {
            BytesRefBuilder builder = new BytesRefBuilder();
            builder.append(fieldBr);
            builder.append(FIELD_VALUE_SEPARATOR);
            builder.append(term);
            extractedTerms.add(new Term(queryMetadataField, builder.toBytesRef()));
        }
    }
    return new TermsQuery(extractedTerms);
}

---

From source file:org.elasticsearch.index.termvectors.ShardTermVectorsService.java

License:Apache License

private Fields mergeFields(Fields fields1, Fields fields2) throws IOException {
    ParallelFields parallelFields = new ParallelFields();
    for (String fieldName : fields2) {
        Terms terms = fields2.terms(fieldName);
        if (terms != null) {
            parallelFields.addField(fieldName, terms);
        }/*www  .j a  v  a  2 s .c  o m*/
    }
    for (String fieldName : fields1) {
        if (parallelFields.fields.containsKey(fieldName)) {
            continue;
        }
        Terms terms = fields1.terms(fieldName);
        if (terms != null) {
            parallelFields.addField(fieldName, terms);
        }
    }
    return parallelFields;
}

---

From source file:org.elasticsearch.index.termvectors.TermVectorsService.java

License:Apache License

private static Fields mergeFields(Fields fields1, Fields fields2) throws IOException {
    ParallelFields parallelFields = new ParallelFields();
    for (String fieldName : fields2) {
        Terms terms = fields2.terms(fieldName);
        if (terms != null) {
            parallelFields.addField(fieldName, terms);
        }/*from   w  w w .j  ava 2 s.c o m*/
    }
    for (String fieldName : fields1) {
        if (parallelFields.fields.containsKey(fieldName)) {
            continue;
        }
        Terms terms = fields1.terms(fieldName);
        if (terms != null) {
            parallelFields.addField(fieldName, terms);
        }
    }
    return parallelFields;
}

---

From source file:org.elasticsearch.percolator.ExtractQueryTermsService.java

License:Apache License

/**
 * Creates a terms query containing all terms from all fields of the specified index reader.
 *//*from www  .j  a  v a  2  s .  co m*/
public static Query createQueryTermsQuery(IndexReader indexReader, String queryMetadataField,
        Term... optionalTerms) throws IOException {
    Objects.requireNonNull(queryMetadataField);

    List<Term> extractedTerms = new ArrayList<>();
    Collections.addAll(extractedTerms, optionalTerms);

    Fields fields = MultiFields.getFields(indexReader);
    for (String field : fields) {
        Terms terms = fields.terms(field);
        if (terms == null) {
            continue;
        }

        BytesRef fieldBr = new BytesRef(field);
        TermsEnum tenum = terms.iterator();
        for (BytesRef term = tenum.next(); term != null; term = tenum.next()) {
            BytesRefBuilder builder = new BytesRefBuilder();
            builder.append(fieldBr);
            builder.append(FIELD_VALUE_SEPARATOR);
            builder.append(term);
            extractedTerms.add(new Term(queryMetadataField, builder.toBytesRef()));
        }
    }
    return new TermsQuery(extractedTerms);
}

---

From source file:org.elasticsearch.search.lookup.IndexFieldTerm.java

License:Apache License

private DocsEnum getDocsAndPosEnum(int luceneFlags, AtomicReader reader) throws IOException {
    assert identifier.field() != null;
    assert identifier.bytes() != null;
    final Fields fields = reader.fields();
    DocsEnum newDocsEnum = null;//w w w .  java 2  s.  c o m
    if (fields != null) {
        final Terms terms = fields.terms(identifier.field());
        if (terms != null) {
            if (terms.hasPositions()) {
                final TermsEnum termsEnum = terms.iterator(null);
                if (termsEnum.seekExact(identifier.bytes())) {
                    newDocsEnum = termsEnum.docsAndPositions(reader.getLiveDocs(),
                            docsEnum instanceof DocsAndPositionsEnum ? (DocsAndPositionsEnum) docsEnum : null,
                            luceneFlags);
                }
            }
        }
    }
    return newDocsEnum;
}

---

From source file:org.elasticsearch.search.lookup.IndexFieldTerm.java

License:Apache License

private DocsEnum getOnlyDocsEnum(int luceneFlags, AtomicReader reader) throws IOException {
    assert identifier.field() != null;
    assert identifier.bytes() != null;
    final Fields fields = reader.fields();
    DocsEnum newDocsEnum = null;/*from  w w  w  . j  a va  2 s .c o m*/
    if (fields != null) {
        final Terms terms = fields.terms(identifier.field());
        if (terms != null) {
            TermsEnum termsEnum = terms.iterator(null);
            if (termsEnum.seekExact(identifier.bytes())) {
                newDocsEnum = termsEnum.docs(reader.getLiveDocs(), docsEnum, luceneFlags);
            }
        }
    }
    if (newDocsEnum == null) {
        newDocsEnum = EMPTY_DOCS_ENUM;
    }
    return newDocsEnum;
}

---

• «
• 1
• 2
• 3
• 4
• 5
• 6
• 7
• 8
• 9
• 10
• 11
• 12
• 13
• 14
• 15
• 16
• 17
• »