Example usage for org.apache.lucene.document StoredField StoredField

Introduction

In this page you can find the example usage for org.apache.lucene.document StoredField StoredField.

Prototype

public StoredField(String name, double value) 

Source Link

Document

Create a stored-only field with the given double value.

Usage

From source file:com.vmware.xenon.services.common.LuceneDocumentIndexService.java

License:Open Source License

public static Document addNumericField(Document doc, String propertyName, long propertyValue, boolean stored) {
    // StoredField is used if the property needs to be stored in the lucene document
    if (stored) {
        doc.add(new StoredField(propertyName, propertyValue));
    }/*from  w w  w  . j a va 2s.  co m*/

    // LongPoint adds an index field to the document that allows for efficient search
    // and range queries
    doc.add(new LongPoint(propertyName, propertyValue));

    // NumericDocValues allow for efficient group operations for a property.
    // TODO Investigate and revert code to use 'sort' to determine the type of DocValuesField
    doc.add(new NumericDocValuesField(propertyName, propertyValue));
    return doc;
}

---

From source file:com.vmware.xenon.services.common.LuceneDocumentIndexService.java

License:Open Source License

public static Document addNumericField(Document doc, String propertyName, double propertyValue,
        boolean stored) {
    long longPropertyValue = NumericUtils.doubleToSortableLong(propertyValue);

    // StoredField is used if the property needs to be stored in the lucene document
    if (stored) {
        doc.add(new StoredField(propertyName, propertyValue));
    }//w  w  w . ja v  a2  s  .  c o  m

    // DoublePoint adds an index field to the document that allows for efficient search
    // and range queries
    doc.add(new DoublePoint(propertyName, propertyValue));

    // NumericDocValues allow for efficient group operations for a property.
    // TODO Investigate and revert code to use 'sort' to determine the type of DocValuesField
    doc.add(new NumericDocValuesField(propertyName, longPropertyValue));
    return doc;
}

---

From source file:com.vmware.xenon.services.common.LuceneIndexDocumentHelper.java

License:Open Source License

void addNumericField(String propertyName, long propertyValue, boolean isStored, boolean isCollectionItem,
        boolean sorted) {
    if (isStored) {
        Field field = isCollectionItem ? new StoredField(propertyName, propertyValue)
                : getAndSetStoredField(propertyName, propertyValue);
        this.doc.add(field);
    }// w w w .  j  av a  2 s.  com

    // LongPoint adds an index field to the document that allows for efficient search
    // and range queries
    if (isCollectionItem) {
        this.doc.add(new LongPoint(propertyName, propertyValue));
    } else {
        LongPoint lpField = this.longPointFields.computeIfAbsent(propertyName, (k) -> {
            return new LongPoint(propertyName, propertyValue);
        });
        lpField.setLongValue(propertyValue);
        this.doc.add(lpField);
    }

    // NumericDocValues allow for efficient group operations for a property.
    NumericDocValuesField ndField = getAndSetNumericField(propertyName, propertyValue, isCollectionItem);
    this.doc.add(ndField);

    if (sorted) {
        // special handling for groupBy queries, docValuesField can not be added twice
        // We suffix the property name with "_group", add a SortedDocValuesField
        Field sdField = getAndSetSortedStoredField(propertyName + GROUP_BY_PROPERTY_NAME_SUFFIX,
                Long.toString(propertyValue));
        this.doc.add(sdField);
    }
}

---

From source file:com.vmware.xenon.services.common.LuceneIndexDocumentHelper.java

License:Open Source License

private void addNumericField(String propertyName, double propertyValue, boolean stored,
        boolean isCollectionItem, boolean sorted) {
    long longPropertyValue = NumericUtils.doubleToSortableLong(propertyValue);

    if (stored) {
        Field field = isCollectionItem ? new StoredField(propertyName, propertyValue)
                : getAndSetStoredField(propertyName, propertyValue);
        this.doc.add(field);
    }/*  ww w. j ava  2 s  .  c o m*/

    // DoublePoint adds an index field to the document that allows for efficient search
    // and range queries
    if (isCollectionItem) {
        this.doc.add(new DoublePoint(propertyName, propertyValue));
    } else {
        DoublePoint dpField = this.doublePointFields.computeIfAbsent(propertyName, (k) -> {
            return new DoublePoint(propertyName, propertyValue);
        });
        dpField.setDoubleValue(propertyValue);
        this.doc.add(dpField);
    }

    NumericDocValuesField ndField = getAndSetNumericField(propertyName, longPropertyValue, isCollectionItem);
    this.doc.add(ndField);

    if (sorted) {
        // special handling for groupBy queries
        Field sdField = getAndSetSortedStoredField(propertyName + GROUP_BY_PROPERTY_NAME_SUFFIX,
                Double.toString(propertyValue));
        this.doc.add(sdField);
    }

}

---

From source file:com.vmware.xenon.services.common.LuceneIndexDocumentHelper.java

License:Open Source License

private Field getAndSetStoredField(String name, Long value) {
    Field f = this.storedFields.computeIfAbsent(name, (k) -> {
        return new StoredField(name, value);
    });/* ww  w  . j ava 2  s.co  m*/
    f.setLongValue(value);
    return f;
}

---

From source file:com.vmware.xenon.services.common.LuceneIndexDocumentHelper.java

License:Open Source License

private Field getAndSetStoredField(String name, Double value) {
    Field f = this.storedFields.computeIfAbsent(name, (k) -> {
        return new StoredField(name, value);
    });//w  w  w . j a  v  a2  s .  c o m
    f.setDoubleValue(value);
    return f;
}

---

From source file:de.carne.filescanner.swt.main.SearchIndex.java

License:Open Source License

private Document buildDocument(BytesRef resultKey, long resultEnd, String resultContent) {
    Document document = new Document();

    document.add(new SortedDocValuesField(FIELD_ID, resultKey));
    document.add(new StoredField(FIELD_KEY_STORED, resultKey));
    document.add(new StoredField(FIELD_END_STORED, resultEnd));
    document.add(new TextField(FIELD_CONTENT, resultContent, Store.NO));
    return document;
}

---

From source file:de.dfki.km.leech.parser.incremental.IncrementalCrawlingHistory.java

License:Open Source License

/**
 * Remarks a new data entity, together with the current time as 'last crawled/checked time'.
 * //from   w w w  .  ja va  2  s . c  o m
 * @param strDataEntityId an identifier for a data entity that is independent from the content of this entity. It is only for identifying the occurence, not to
 *            check whether it has changed (e.g. a filename)
 * @param strDataEntityContentFingerprint some fingerprint/identifier that gives the hint whether the content of the data entity has changed, e.g. the modifed date of
 *            a file
 * @param strMasterDataEntityId optional: an EntityId of another data entity that is our 'master' which means that when the master is updated with
 *            {@link #updateDataEntityLastCrawledTime(String)}, all associated slaves will be also updated. This is e.g. for the case when you are in a second run for
 *            RSS-File indexing, and leech recognizes that this file didn't changed. Now we don't want to go unnecessarily into the fil and mark each entry on it's
 *            own. We know no subentry has changed, and can immediately mark them as processed with {@link #updateDataEntityLastCrawledTime(String)} on the master
 *            dataEntityId, which is the one from the RSS file. Leave it null or empty in the case you don't need to use it.
 * 
 * @throws IOException
 * @throws CorruptIndexException
 */
public void addDataEntity(String strDataEntityId, String strDataEntityContentFingerprint,
        String strMasterDataEntityId) throws CorruptIndexException, IOException {

    Document doc = new Document();

    doc.add(new StringField(dataEntityId, strDataEntityId, Store.YES));
    doc.add(new StringField(dataEntityContentFingerprint, strDataEntityContentFingerprint, Store.YES));
    doc.add(new LongPoint(lastCrawledTime, System.currentTimeMillis()));
    doc.add(new StoredField(lastCrawledTime, System.currentTimeMillis()));
    if (!StringUtils.nullOrWhitespace(strMasterDataEntityId))
        doc.add(new StringField(masterDataEntityId, strMasterDataEntityId, Store.YES));

    m_indexWriter.addDocument(doc);

}

---

From source file:de.dfki.km.leech.parser.incremental.IncrementalCrawlingHistory.java

License:Open Source License

/**
 * Updates a whole data entity - same as addDataEntity, but removes a former entry before storing the new one
 * /*from  ww w  . ja  va  2s  .  c o m*/
 * @param strDataEntityId an identifier for a data entity that is independent from the content of this entity. It is only for identifying the occurence, not to
 *            check whether it has changed (e.g. a filename)
 * @param strDataEntityContentFingerprint some fingerprint/identifier that gives the hint whether the content of the data entity has changed, e.g. the modifed date of
 *            a file
 * @param strMasterDataEntityId optional: an EntityId of another data entity that is our 'master' which means that when the master is updated with
 *            {@link #updateDataEntityLastCrawledTime(String)}, all associated slaves will be also updated. This is e.g. for the case when you are in a second run for
 *            RSS-File indexing, and leech recognizes that this file didn't changed. Now we don't want to go unnecessarily into the fil and mark each entry on it's
 *            own. We know no subentry has changed, and can immediately mark them as processed with {@link #updateDataEntityLastCrawledTime(String)} on the master
 *            dataEntityId, which is the one from the RSS file. Leave it null or empty in the case you don't need to use it.
 * 
 * @throws IOException
 * @throws CorruptIndexException
 */
public void updateDataEntity(String strDataEntityId, String strDataEntityContentFingerprint,
        String strMasterDataEntityId) throws CorruptIndexException, IOException {

    Term termId = new Term(dataEntityId, strDataEntityId);

    Document doc = new Document();

    doc.add(new StringField(dataEntityId, strDataEntityId, Store.YES));
    doc.add(new StringField(dataEntityContentFingerprint, strDataEntityContentFingerprint, Store.YES));
    doc.add(new LongPoint(lastCrawledTime, System.currentTimeMillis()));
    doc.add(new StoredField(lastCrawledTime, System.currentTimeMillis()));
    if (!StringUtils.nullOrWhitespace(strMasterDataEntityId))
        doc.add(new StringField(masterDataEntityId, strMasterDataEntityId, Store.YES));

    m_indexWriter.updateDocument(termId, doc);

}

---

From source file:de.dfki.km.leech.parser.incremental.IncrementalCrawlingHistory.java

License:Open Source License

/**
 * Sets a data entities 'last crawled/checked time' entry to the current time. In the case this data entity is a master entity, all slave documents will be updated
 * also. You can set an entity as a master entity with {@link #addDataEntity(String, String, String)} or {@link #updateDataEntity(String, String, String)}
 * /*  w  w w .  j  av  a 2 s. c  om*/
 * @param strDataEntityId the data entity which is finally checked/crawled
 * 
 * @throws IOException
 * @throws CorruptIndexException
 */
public void updateDataEntityLastCrawledTime(String strDataEntityId) throws CorruptIndexException, IOException {

    Term termId = new Term(dataEntityId, strDataEntityId);

    refreshIndexReaderz();
    TopDocs topDocs = m_indexSearcher.search(new TermQuery(termId), 1);

    if (topDocs.totalHits == 0)
        throw new IllegalStateException("there has to be an data entry with Id " + strDataEntityId
                + " for updating. Nothing was found.");

    long lCurrentTime = System.currentTimeMillis();

    Document doc = m_indexReader.document(topDocs.scoreDocs[0].doc);

    doc.removeFields(lastCrawledTime);
    doc.add(new LongPoint(lastCrawledTime, lCurrentTime));
    doc.add(new StoredField(lastCrawledTime, lCurrentTime));

    m_indexWriter.updateDocument(termId, doc);

    // wenn das Teil eine MasterDataEntity ist, dann mssen alle assoziierten Sklaven auch noch aktualisiert werden

    termId = new Term(masterDataEntityId, strDataEntityId);

    topDocs = m_indexSearcher.search(new TermQuery(termId), Integer.MAX_VALUE);

    for (int i = 0; i < topDocs.scoreDocs.length; i++) {

        Document slaveDoc = m_indexReader.document(topDocs.scoreDocs[i].doc);

        slaveDoc.removeFields(lastCrawledTime);
        slaveDoc.add(new LongPoint(lastCrawledTime, lCurrentTime));
        slaveDoc.add(new StoredField(lastCrawledTime, lCurrentTime));

        m_indexWriter.updateDocument(termId, doc);
    }

}

---

• «
• 1
• 2
• 3
• 4
• 5
• 6
• 7
• 8
• 9
• 10
• 11
• 12
• 13
• 14
• 15
• 16
• 17
• 18
• 19
• 20
• 21
• 22
• 23
• 24
• 25
• 26
• 27
• 28
• »