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

List of usage examples for org.apache.lucene.document SortedNumericDocValuesField SortedNumericDocValuesField

  1. HOME
  2. Java
  3. org.apache.lucene
  4. org.apache.lucene.document.*
  5. SortedNumericDocValuesField
  6. SortedNumericDocValuesField

Introduction

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

Prototype

public SortedNumericDocValuesField(String name, long value)

Source Link

Document

Creates a new DocValues field with the specified 64-bit long value

Usage

From source file:IndexTaxis.java

License:Apache License

static void addOneField(Document doc, String fieldName, String rawValue) {
    // nocommit/*w w w . j a  va  2  s .c  o  m*/
    /*
    if (fieldName.equals("pick_up_lat")) {
      double value = Double.parseDouble(rawValue);
      doc.add(new DoublePoint(fieldName, value));
      doc.add(new SortedNumericDocValuesField(fieldName, NumericUtils.doubleToSortableLong(value)));
    }
    */
    switch (fieldName) {
    case "vendor_id":
    case "cab_color":
    case "payment_type":
    case "trip_type":
    case "rate_code":
    case "store_and_fwd_flag":
        doc.add(new StringField(fieldName, rawValue, Field.Store.NO));
        doc.add(new SortedSetDocValuesField(fieldName, new BytesRef(rawValue)));
        break;
    case "vendor_name":
        doc.add(new TextField(fieldName, rawValue, Field.Store.NO));
        break;
    case "pick_up_date_time":
    case "drop_off_date_time": {
        long value = Long.parseLong(rawValue);
        doc.add(new LongPoint(fieldName, value));
        doc.add(new SortedNumericDocValuesField(fieldName, value));
    }
        break;
    case "passenger_count": {
        int value = Integer.parseInt(rawValue);
        doc.add(new IntPoint(fieldName, value));
        doc.add(new SortedNumericDocValuesField(fieldName, value));
    }
        break;
    case "trip_distance":
    case "pick_up_lat":
    case "pick_up_lon":
    case "drop_off_lat":
    case "drop_off_lon":
    case "fare_amount":
    case "surcharge":
    case "mta_tax":
    case "extra":
    case "ehail_fee":
    case "improvement_surcharge":
    case "tip_amount":
    case "tolls_amount":
    case "total_amount": {
        double value;
        try {
            value = Double.parseDouble(rawValue);
        } catch (NumberFormatException nfe) {
            System.out.println(
                    "WARNING: failed to parse \"" + rawValue + "\" as double for field \"" + fieldName + "\"");
            return;
        }
        doc.add(new DoublePoint(fieldName, value));
        doc.add(new SortedNumericDocValuesField(fieldName, NumericUtils.doubleToSortableLong(value)));
    }
        break;
    default:
        throw new AssertionError("failed to handle field \"" + fieldName + "\"");
    }
}

From source file:com.icdd.lucence.IndexFiles.java

License:Apache License

static void indexDoc(IndexWriter writer, Path file, long lastModified) throws IOException {
    try (InputStream stream = Files.newInputStream(file)) {
        // make a new,empty document
        Document doc = new Document();

        Field pathField = new StringField("path", file.toString(), Field.Store.YES);

        doc.add(pathField);/*from w w w  .j a  v a 2 s . c  om*/
        doc.add(new SortedNumericDocValuesField("modified", lastModified));
        doc.add(new TextField("contents",
                new BufferedReader(new InputStreamReader(stream, StandardCharsets.UTF_8))));

        if (writer.getConfig().getOpenMode() == OpenMode.CREATE) {
            // New index, so we just add the document (no old document can
            // be there):
            System.out.println("adding " + file);
            writer.addDocument(doc);
        } else {
            // Existing index (an old copy of this document may have been
            // indexed) so
            // path, if present:
            System.out.println("updating " + file);
            writer.updateDocument(new Term("path", file.toString()), doc);
        }
    }
}

From source file:com.icdd.lucene.CreateIndex.java

License:Apache License

static void indexDoc(IndexWriter writer, Path file, long lastModified) throws IOException {
    // filter non-xml files
    if (filter.accept(file.toFile())) {

        System.out.println("num: " + num);
        num++;//  w w  w  .jav a  2  s . c om
        if (num < endset && num >= offset) {

            try (InputStream stream = Files.newInputStream(file)) {
                // make a new,empty document
                Document doc = new Document();

                Field pathField = new StringField("path", file.toString(), Field.Store.YES);
                String filename = file.getFileName().toString();
                int post = filename.indexOf('_');
                if (post > 0) {
                    filename = filename.substring(post + 1, filename.length() - 4);
                }

                doc.add(pathField);
                doc.add(new StringField("title", filename, Field.Store.YES));
                doc.add(new SortedNumericDocValuesField("modified", lastModified));
                doc.add(new TextField("contents",
                        new BufferedReader(new InputStreamReader(stream, StandardCharsets.UTF_8))));

                if (writer.getConfig().getOpenMode() == OpenMode.CREATE) {
                    // New index, so we just add the document (no old
                    // document
                    // can
                    // be there):
                    logger.info("adding " + file);
                    writer.addDocument(doc);
                } else {
                    // Existing index (an old copy of this document may have
                    // been
                    // indexed) so
                    // path, if present:
                    logger.info("updating " + file);
                    writer.updateDocument(new Term("path", file.toString()), doc);
                }
            }
        }
    }
}

From source file:com.qwazr.search.field.SortedDoubleDocValuesType.java

License:Apache License

@Override
final public void fillValue(final Object value, final FieldConsumer consumer) {
    if (value instanceof Number)
        consumer.accept(new SortedNumericDocValuesField(fieldName,
                NumericUtils.doubleToSortableLong(((Number) value).doubleValue())));
    else/*w ww.ja  v  a 2s  .c om*/
        consumer.accept(new SortedNumericDocValuesField(fieldName,
                NumericUtils.doubleToSortableLong(Double.parseDouble(value.toString()))));

}

From source file:com.qwazr.search.field.SortedFloatDocValuesType.java

License:Apache License

@Override
final public void fillValue(final Object value, final FieldConsumer consumer) {
    if (value instanceof Number)
        consumer.accept(new SortedNumericDocValuesField(fieldName,
                NumericUtils.floatToSortableInt(((Number) value).floatValue())));
    else//  ww  w  .  ja v a  2s.com
        consumer.accept(new SortedNumericDocValuesField(fieldName,
                NumericUtils.floatToSortableInt(Float.parseFloat(value.toString()))));
}

From source file:com.qwazr.search.field.SortedIntDocValuesType.java

License:Apache License

@Override
final public void fillValue(final Object value, final FieldConsumer consumer) {
    if (value instanceof Number)
        consumer.accept(new SortedNumericDocValuesField(fieldName, ((Number) value).intValue()));
    else/* ww w. j a  va  2 s.  c o m*/
        consumer.accept(new SortedNumericDocValuesField(fieldName, Integer.parseInt(value.toString())));
}

From source file:com.qwazr.search.field.SortedLongDocValuesType.java

License:Apache License

@Override
final public void fillValue(final Object value, final FieldConsumer consumer) {
    if (value instanceof Number)
        consumer.accept(new SortedNumericDocValuesField(fieldName, ((Number) value).longValue()));
    else//w  w w. j  a  v a2  s .c om
        consumer.accept(new SortedNumericDocValuesField(fieldName, Long.parseLong(value.toString())));
}

From source file:com.rapidminer.search.GlobalSearchUtilities.java

License:Open Source License

/**
 * Creates a search document {@link Field} for sorting with long values.
 *
 * @param value//from  w ww. j av a  2 s  .c o m
 *       the long value. Higher values are sorted higher than lower values
 * @return the field which is used for sorting, never {@code null}
 */
public Field createSortingField(final long value) {
    return new SortedNumericDocValuesField("sort", value);
}

From source file:gov.nist.basekb.FreebaseIndexer.java

License:LGPL

public void indexRecord(IndexWriter writer, String subject, Map<String, List<String>> predValues)
        throws Exception {
    Document doc = new Document();
    Field subjField = new StringField(FIELD_NAME_SUBJECT, normalizeUri(subject), Field.Store.YES);
    //printlnDbg("DBG: indexRecord: " + subject);
    doc.add(subjField);//  w w w  . j  a  v a  2  s.c  o m

    FieldType IndexedField = new FieldType(TextField.TYPE_NOT_STORED);
    IndexedField.setStoreTermVectors(INDEX_TERMVECTORS);

    FieldType IndexedStoredField = new FieldType(TextField.TYPE_STORED);
    IndexedStoredField.setStoreTermVectors(INDEX_TERMVECTORS);

    long pagerank = 0;

    for (Map.Entry<String, List<String>> entry : predValues.entrySet()) {
        String predicate = normalizeUri(entry.getKey());
        List<String> values = entry.getValue();

        //printlnDbg("DBG:  " + predicate + ": " + values);
        for (String value : values) {
            String valueType = getValueType(value);
            value = normalizeValue(value);
            if (isIndexedPredicate(predicate)) {
                if (valueType == VALUE_TYPE_URI)
                    // treat URI elements as atomic strings (e.g., types):
                    doc.add(new Field(predicate, value, StoredField.TYPE));
                else if (valueType == VALUE_TYPE_INT)
                    if (predicate.equals("pr_bin"))
                        pagerank = Long.parseLong(value);
                    else
                        doc.add(new SortedNumericDocValuesField(predicate, Long.parseLong(value)));
                else {
                    // all others, run through the analyzer:
                    String lang = INDEX_LANGUAGE ? getValueLanguage(value) : null;
                    if (INDEX_LANGUAGE && lang != null
                            && (isSupportedLanguage(lang) || isSupportedLanguage(getLanguageRoot(lang)))) {
                        // multi-lingual indexing: if we have a supported language, we store the field
                        // and then add an index entry with the language-qualified predicate:
                        doc.add(new Field(predicate, value, StoredField.TYPE));
                        if (INDEX_PREDICATES)
                            doc.add(new Field(languageQualifiedPredicate(predicate, lang), value,
                                    IndexedStoredField));
                        if (INDEX_TEXT)
                            doc.add(new Field(languageQualifiedPredicate(FIELD_NAME_TEXT, lang), value,
                                    IndexedField));
                    } else {
                        // mono-lingual indexing or no language designation:
                        if (INDEX_PREDICATES)
                            doc.add(new Field(predicate, value, IndexedStoredField));
                        if (INDEX_TEXT) {
                            doc.add(new Field(FIELD_NAME_TEXT, value, IndexedField));
                            // make sure we store the triple if it wasn't already:
                            if (!INDEX_PREDICATES)
                                doc.add(new Field(predicate, value, StoredField.TYPE));
                        }
                    }
                }
            } else
                doc.add(new Field(predicate, value, StoredField.TYPE));
        }
    }
    doc.add(new SortedNumericDocValuesField("pr_bin", pagerank));

    Labeling lab = classify(doc, classifier);
    doc.add(new Field("best_class", lab.getBestLabel().toString(), StoredField.TYPE));
    doc.add(new Field("all_classes", labelsToString(lab), StoredField.TYPE));

    // we are creating the index from scratch, so we just add the document:
    writer.addDocument(doc);
}

From source file:gov.nist.basekb.FreebaseTools.java

License:LGPL

public void indexRecord(IndexWriter writer, String subject, Map<String, List<String>> predValues)
        throws IOException {
    Document doc = new Document();
    Field subjField = new StringField(FIELD_NAME_SUBJECT, normalizeUri(subject), Field.Store.YES);
    //printlnDbg("DBG: indexRecord: " + subject);
    doc.add(subjField);/* w w  w  .  ja va 2 s .c  o m*/

    FieldType VectorField = new FieldType(StringField.TYPE_STORED);
    VectorField.setStoreTermVectors(true);

    FieldType TokVectorField = new FieldType(TextField.TYPE_STORED);
    TokVectorField.setStoreTermVectors(true);

    long pagerank = 0;

    for (Map.Entry<String, List<String>> entry : predValues.entrySet()) {
        String predicate = normalizeUri(entry.getKey());
        List<String> values = entry.getValue();

        //printlnDbg("DBG:  " + predicate + ": " + values);
        for (String value : values) {
            String valueType = getValueType(value);
            value = normalizeValue(value);
            if (isIndexedPredicate(predicate)) {
                if (valueType == VALUE_TYPE_URI)
                    // treat URI elements as atomic strings (e.g., types):
                    doc.add(new Field(predicate, value, VectorField));
                else if (valueType == VALUE_TYPE_INT)
                    if (predicate.equals("pr_bin"))
                        pagerank = Long.parseLong(value);
                    else
                        doc.add(new SortedNumericDocValuesField(predicate, Long.parseLong(value)));
                else {
                    // all others, run through the analyzer:
                    String lang = INDEX_LANGUAGE ? getValueLanguage(value) : null;
                    if (INDEX_LANGUAGE && lang != null
                            && (isSupportedLanguage(lang) || isSupportedLanguage(getLanguageRoot(lang)))) {
                        // multi-lingual indexing: if we have a supported language, we store the field
                        // and then add an index entry with the language-qualified predicate:
                        doc.add(new Field(predicate, value, VectorField));
                        if (INDEX_PREDICATES)
                            doc.add(new Field(languageQualifiedPredicate(predicate, lang), value,
                                    TokVectorField));
                        if (INDEX_TEXT)
                            doc.add(new Field(languageQualifiedPredicate(FIELD_NAME_TEXT, lang), value,
                                    TokVectorField));
                    } else {
                        // mono-lingual indexing or no language designation:
                        if (INDEX_PREDICATES)
                            doc.add(new Field(predicate, value, TokVectorField));
                        if (INDEX_TEXT) {
                            doc.add(new Field(FIELD_NAME_TEXT, value, TokVectorField));
                            // make sure we store the triple if it wasn't already:
                            if (!INDEX_PREDICATES)
                                doc.add(new Field(predicate, value, VectorField));
                        }
                    }
                }
            } else
                doc.add(new Field(predicate, value, VectorField));
        }
    }
    doc.add(new SortedNumericDocValuesField("pr_bin", pagerank));

    // we are creating the index from scratch, so we just add the document:
    writer.addDocument(doc);
}