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

Introduction

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

Prototype

public SortedSetDocValuesField(String name, BytesRef bytes) 

Source Link

Document

Create a new sorted DocValues field.

Usage

From source file:IndexTaxis.java

License:Apache License

static void addOneField(Document doc, String fieldName, String rawValue) {
    // nocommit/*from   w w  w . ja  v  a 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.github.tteofili.looseen.TestWikipediaClassification.java

License:Apache License

private static void importWikipedia(File dump, IndexWriter indexWriter) throws Exception {
    long start = System.currentTimeMillis();
    int count = 0;
    System.out.format("Importing %s...%n", dump);

    String title = null;/*ww w .j a v  a2  s .c  om*/
    String text = null;
    Set<String> cats = new HashSet<>();

    XMLInputFactory factory = XMLInputFactory.newInstance();
    StreamSource source;
    if (dump.getName().endsWith(".xml")) {
        source = new StreamSource(dump);
    } else {
        throw new RuntimeException("can index only wikipedia XML files");
    }
    XMLStreamReader reader = factory.createXMLStreamReader(source);
    while (reader.hasNext()) {
        if (count == Integer.MAX_VALUE) {
            break;
        }
        switch (reader.next()) {
        case XMLStreamConstants.START_ELEMENT:
            if ("title".equals(reader.getLocalName())) {
                title = reader.getElementText();
            } else if (TEXT_FIELD.equals(reader.getLocalName())) {
                text = reader.getElementText();
                Matcher matcher = pattern.matcher(text);
                int pos = 0;
                while (matcher.find(pos)) {
                    String group = matcher.group(1);
                    String catName = group.replaceAll("\\|\\s", "").replaceAll("\\|\\*", "");
                    Collections.addAll(cats, catName.split("\\|"));
                    pos = matcher.end();
                }
            }
            break;
        case XMLStreamConstants.END_ELEMENT:
            if ("page".equals(reader.getLocalName())) {
                Document page = new Document();
                if (title != null) {
                    page.add(new TextField(TITLE_FIELD, title, StoredField.Store.YES));
                }
                if (text != null) {
                    page.add(new TextField(TEXT_FIELD, text, StoredField.Store.YES));
                }
                for (String cat : cats) {
                    page.add(new StringField(CATEGORY_FIELD, cat, Field.Store.YES));
                    page.add(new SortedSetDocValuesField(CATEGORY_FIELD, new BytesRef(cat)));
                }
                indexWriter.addDocument(page);
                cats.clear();
                count++;
                if (count % 100000 == 0) {
                    indexWriter.commit();
                    System.out.format("Committed %d pages%n", count);
                }
            }
            break;
        }
    }

    indexWriter.commit();

    long millis = System.currentTimeMillis() - start;
    System.out.format("Imported %d pages in %d seconds (%.2fms/page)%n", count, millis / 1000,
            (double) millis / count);
}

---

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

License:Apache License

@Override
final public void fillValue(final Object value, final FieldConsumer consumer) {
    if (value instanceof BytesRef)
        consumer.accept(new SortedSetDocValuesField(fieldName, (BytesRef) value));
    else//from w ww. j  ava  2  s.  com
        consumer.accept(new SortedSetDocValuesField(fieldName, new BytesRef(value.toString())));
}

---

From source file:com.stratio.cassandra.lucene.schema.mapping.KeywordMapper.java

License:Apache License

/** {@inheritDoc} */
@Override//from  w  w  w. j a  v  a  2  s .  com
public Field sortedField(String name, String value, boolean isCollection) {
    BytesRef bytes = new BytesRef(value);
    if (isCollection) {
        return new SortedSetDocValuesField(name, bytes);
    } else {
        return new SortedDocValuesField(name, bytes);
    }
}

---

From source file:com.twentyn.patentSearch.DocumentIndexer.java

License:Open Source License

public Document patentDocToLuceneDoc(File path, PatentDocument patentDoc) {
    // With help from https://lucene.apache.org/core/5_2_0/demo/src-html/org/apache/lucene/demo/IndexFiles.html
    Document doc = new Document();
    doc.add(new StringField("file_name", path.getName(), Field.Store.YES));
    doc.add(new StringField("id", patentDoc.getFileId(), Field.Store.YES));
    doc.add(new StringField("grant_date", patentDoc.getGrantDate(), Field.Store.YES));
    doc.add(new StringField("main_classification", patentDoc.getMainClassification(), Field.Store.YES));
    doc.add(new TextField("title", patentDoc.getTitle(), Field.Store.YES));
    doc.add(new TextField("claims", StringUtils.join("\n", patentDoc.getClaimsText()), Field.Store.NO));
    doc.add(new TextField("description", StringUtils.join("\n", patentDoc.getTextContent()), Field.Store.NO));

    // TODO: verify that these are searchable as expected.
    for (String cls : patentDoc.getFurtherClassifications()) {
        doc.add(new SortedSetDocValuesField("further_classification", new BytesRef(cls)));
    }//  w w w  .j  a va  2s  . co  m
    for (String cls : patentDoc.getSearchedClassifications()) {
        doc.add(new SortedSetDocValuesField("searched_classification", new BytesRef(cls)));
    }

    return doc;
}

---

From source file:io.crate.expression.reference.doc.IpColumnReferenceTest.java

License:Apache License

private static void addIPv6Values(IndexWriter writer) throws IOException {
    for (int i = 10; i < 20; i++) {
        Document doc = new Document();
        doc.add(new StringField("_id", Integer.toString(i), Field.Store.NO));
        InetAddress address = InetAddresses
                .forString("7bd0:8082:2df8:487e:e0df:e7b5:9362:" + Integer.toHexString(i));
        doc.add(new SortedSetDocValuesField(IP_COLUMN, new BytesRef(InetAddressPoint.encode(address))));
        writer.addDocument(doc);//from   ww w  .ja va2 s .co m
    }
}

---

From source file:io.crate.expression.reference.doc.IpColumnReferenceTest.java

License:Apache License

private static void addIPv4Values(IndexWriter writer) throws IOException {
    for (int i = 0; i < 10; i++) {
        Document doc = new Document();
        doc.add(new StringField("_id", Integer.toString(i), Field.Store.NO));
        InetAddress address = InetAddresses.forString("192.168.0." + i);
        doc.add(new SortedSetDocValuesField(IP_COLUMN, new BytesRef(InetAddressPoint.encode(address))));
        if (i == 0) {
            address = InetAddresses.forString("192.168.0.1");
            doc.add(new SortedSetDocValuesField(IP_ARRAY_COLUMN,
                    new BytesRef(InetAddressPoint.encode(address))));
            address = InetAddresses.forString("192.168.0.2");
            doc.add(new SortedSetDocValuesField(IP_ARRAY_COLUMN,
                    new BytesRef(InetAddressPoint.encode(address))));
        }/*ww  w . java 2  s  . com*/
        writer.addDocument(doc);
    }
}

---

From source file:io.crate.operation.reference.doc.IpColumnReferenceTest.java

License:Apache License

@Override
protected void insertValues(IndexWriter writer) throws Exception {
    for (int i = 0; i < 10; i++) {
        Document doc = new Document();
        InetAddress address = InetAddresses.forString("192.168.0." + i);
        doc.add(new SortedSetDocValuesField(column, new BytesRef(InetAddressPoint.encode(address))));
        if (i == 0) {
            address = InetAddresses.forString("192.168.0.1");
            doc.add(new SortedSetDocValuesField(column_array, new BytesRef(InetAddressPoint.encode(address))));
            address = InetAddresses.forString("192.168.0.2");
            doc.add(new SortedSetDocValuesField(column_array, new BytesRef(InetAddressPoint.encode(address))));
        }//from w w w .ja v  a 2  s  . c  om
        writer.addDocument(doc);
    }
}

---

From source file:lucene.security.index.SecureAtomicReaderTestBase.java

License:Apache License

private Iterable<IndexableField> getDoc(int i) {
    Document document = new Document();
    document.add(new StringField("test", "test", Store.YES));
    document.add(new StringField("info", "info", Store.YES));
    if (i == 3) {
        document.add(new StringField("shouldnotsee", "shouldnotsee", Store.YES));
    }/*from w w  w.ja  v  a2 s  . com*/
    document.add(new NumericDocValuesField("number", i));
    document.add(new BinaryDocValuesField("bin", new BytesRef(Integer.toString(i).getBytes())));
    document.add(new SortedDocValuesField("sorted", new BytesRef(Integer.toString(i).getBytes())));
    document.add(new SortedSetDocValuesField("sortedset", new BytesRef(Integer.toString(i).getBytes())));
    document.add(
            new SortedSetDocValuesField("sortedset", new BytesRef(("0" + Integer.toString(i)).getBytes())));
    return document;
}

---

From source file:org.apache.solr.schema.SortableBinaryField.java

License:Apache License

@Override
public List<IndexableField> createFields(SchemaField field, Object value, float boost) {
    if (field.hasDocValues()) {
        List<IndexableField> fields = new ArrayList<>();
        IndexableField storedField = createField(field, value, boost);
        fields.add(storedField);//from   w ww .jav  a 2 s .  c  om
        ByteBuffer byteBuffer = toObject(storedField);
        BytesRef bytes = new BytesRef(byteBuffer.array(), byteBuffer.arrayOffset() + byteBuffer.position(),
                byteBuffer.remaining());
        if (field.multiValued()) {
            fields.add(new SortedSetDocValuesField(field.getName(), bytes));
        } else {
            fields.add(new SortedDocValuesField(field.getName(), bytes));
        }
        return fields;
    } else {
        return Collections.singletonList(createField(field, value, boost));
    }
}

---

• «
• 1
• 2
• 3
• 4
• 5
• »