Example usage for org.apache.lucene.index IndexWriter addDocument

List of usage examples for org.apache.lucene.index IndexWriter addDocument

  1. HOME
  2. Java
  3. org.apache.lucene
  4. org.apache.lucene.index.*
  5. IndexWriter
  6. addDocument

Introduction

In this page you can find the example usage for org.apache.lucene.index IndexWriter addDocument.

Prototype

public long addDocument(Iterable<? extends IndexableField> doc) throws IOException

Source Link

Document

Adds a document to this index.

Usage

From source file:com.search.lucene.demo.facet.RangeFacetsExample.java

License:Apache License

/** Build the example index. */
public void index() throws IOException {
    IndexWriter indexWriter = new IndexWriter(indexDir,
            new IndexWriterConfig(new WhitespaceAnalyzer()).setOpenMode(OpenMode.CREATE));

    // Add documents with a fake timestamp, 1000 sec before
    // "now", 2000 sec before "now", ...:
    for (int i = 0; i < 100; i++) {
        Document doc = new Document();
        long then = nowSec - i * 1000;
        // Add as doc values field, so we can compute range facets:
        doc.add(new NumericDocValuesField("timestamp", then));
        // Add as numeric field so we can drill-down:
        doc.add(new LongField("timestamp", then, Field.Store.NO));
        indexWriter.addDocument(doc);
    }//from w  w w  .  j ava 2  s. c o  m

    // Open near-real-time searcher
    searcher = new IndexSearcher(DirectoryReader.open(indexWriter, true));
    indexWriter.close();
}

From source file:com.search.lucene.demo.facet.SimpleSortedSetFacetsExample.java

License:Apache License

/** Build the example index. */
private void index() throws IOException {
    IndexWriter indexWriter = new IndexWriter(indexDir,
            new IndexWriterConfig(new WhitespaceAnalyzer()).setOpenMode(OpenMode.CREATE));
    Document doc = new Document();
    doc.add(new SortedSetDocValuesFacetField("Author", "Bob"));
    doc.add(new SortedSetDocValuesFacetField("Publish Year", "2010"));
    indexWriter.addDocument(config.build(doc));

    doc = new Document();
    doc.add(new SortedSetDocValuesFacetField("Author", "Lisa"));
    doc.add(new SortedSetDocValuesFacetField("Publish Year", "2010"));
    indexWriter.addDocument(config.build(doc));

    doc = new Document();
    doc.add(new SortedSetDocValuesFacetField("Author", "Lisa"));
    doc.add(new SortedSetDocValuesFacetField("Publish Year", "2012"));
    indexWriter.addDocument(config.build(doc));

    doc = new Document();
    doc.add(new SortedSetDocValuesFacetField("Author", "Susan"));
    doc.add(new SortedSetDocValuesFacetField("Publish Year", "2012"));
    indexWriter.addDocument(config.build(doc));

    doc = new Document();
    doc.add(new SortedSetDocValuesFacetField("Author", "Frank"));
    doc.add(new SortedSetDocValuesFacetField("Publish Year", "1999"));
    indexWriter.addDocument(config.build(doc));

    indexWriter.close();/*from   w w  w.j  a v a  2 s. c o  m*/
}

From source file:com.searchlocal.lucene.IndexBeanList.java

License:Open Source License

public static void makeWordindex(IndexWriter indexWriter, WordFileBean bean)
        throws CorruptIndexException, IOException {
    Document document = new Document();
    document.add(//  w  w w .  ja v a 2  s.c  o m
            new Field("paragraphNo", String.valueOf(bean.getParagraphNo()), Field.Store.YES, Field.Index.NO));

    document.add(new Field("filename", bean.getFilename(), Field.Store.YES, Field.Index.ANALYZED));
    document.add(new Field("path", bean.getPath(), Field.Store.YES, Field.Index.NOT_ANALYZED));
    document.add(new Field("content", bean.getContent(), Field.Store.YES, Field.Index.ANALYZED,
            Field.TermVector.WITH_POSITIONS_OFFSETS));

    document.add(
            new Field("lastmodify", DateTools.timeToString(bean.getLastmodify(), DateTools.Resolution.MINUTE),
                    Field.Store.YES, Field.Index.NO));
    indexWriter.addDocument(document);
}

From source file:com.searchlocal.lucene.IndexBeanList.java

License:Open Source License

public static void makeExcelindex(IndexWriter indexWriter, ExcelFileBean bean)
        throws CorruptIndexException, IOException {
    Document document = new Document();
    document.add(new Field("sheetname", bean.getSheetname(), Field.Store.YES, Field.Index.NO));
    document.add(new Field("rownb", String.valueOf(bean.getRownb()), Field.Store.YES, Field.Index.NO));

    document.add(new Field("filename", bean.getFilename(), Field.Store.YES, Field.Index.ANALYZED));
    document.add(new Field("path", bean.getPath(), Field.Store.YES, Field.Index.NOT_ANALYZED));
    document.add(new Field("content", bean.getContent(), Field.Store.YES, Field.Index.ANALYZED,
            Field.TermVector.WITH_POSITIONS_OFFSETS));

    document.add(//from ww  w . j a va  2s. c om
            new Field("lastmodify", DateTools.timeToString(bean.getLastmodify(), DateTools.Resolution.MINUTE),
                    Field.Store.YES, Field.Index.NO));
    indexWriter.addDocument(document);
}

From source file:com.searchlocal.lucene.IndexBeanList.java

License:Open Source License

public static void makePdfindex(IndexWriter indexWriter, PdfFileBean bean)
        throws CorruptIndexException, IOException {
    Document document = new Document();
    document.add(new Field("page", String.valueOf(bean.getPage()), Field.Store.YES, Field.Index.NO));

    document.add(new Field("filename", bean.getFilename(), Field.Store.YES, Field.Index.ANALYZED));
    document.add(new Field("path", bean.getPath(), Field.Store.YES, Field.Index.NOT_ANALYZED));
    document.add(new Field("content", bean.getContent(), Field.Store.YES, Field.Index.ANALYZED,
            Field.TermVector.WITH_POSITIONS_OFFSETS));

    document.add(// w  ww .java2s .com
            new Field("lastmodify", DateTools.timeToString(bean.getLastmodify(), DateTools.Resolution.MINUTE),
                    Field.Store.YES, Field.Index.NO));
    indexWriter.addDocument(document);
}

From source file:com.searchlocal.lucene.IndexBeanList.java

License:Open Source License

public static void makePptindex(IndexWriter indexWriter, PptFileBean bean)
        throws CorruptIndexException, IOException {
    Document document = new Document();
    document.add(new Field("page", String.valueOf(bean.getPage()), Field.Store.YES, Field.Index.NO));

    document.add(new Field("filename", bean.getFilename(), Field.Store.YES, Field.Index.ANALYZED));
    document.add(new Field("path", bean.getPath(), Field.Store.YES, Field.Index.NOT_ANALYZED));
    document.add(new Field("content", bean.getContent(), Field.Store.YES, Field.Index.ANALYZED,
            Field.TermVector.WITH_POSITIONS_OFFSETS));

    document.add(/* www  .jav a2s.co m*/
            new Field("lastmodify", DateTools.timeToString(bean.getLastmodify(), DateTools.Resolution.MINUTE),
                    Field.Store.YES, Field.Index.NO));
    indexWriter.addDocument(document);
}

From source file:com.searchlocal.lucene.IndexBeanList.java

License:Open Source License

public static void makeChmindex(IndexWriter indexWriter, ChmFileBean bean)
        throws CorruptIndexException, IOException {
    Document document = new Document();
    document.add(new Field("catalogname", bean.getCatalogname(), Field.Store.YES, Field.Index.NO));

    document.add(new Field("filename", bean.getFilename(), Field.Store.YES, Field.Index.ANALYZED));
    document.add(new Field("path", bean.getPath(), Field.Store.YES, Field.Index.NOT_ANALYZED));
    document.add(new Field("content", bean.getContent(), Field.Store.YES, Field.Index.ANALYZED,
            Field.TermVector.WITH_POSITIONS_OFFSETS));

    document.add(/*w ww  .j ava  2 s  .  c  om*/
            new Field("lastmodify", DateTools.timeToString(bean.getLastmodify(), DateTools.Resolution.MINUTE),
                    Field.Store.YES, Field.Index.NO));
    indexWriter.addDocument(document);
}

From source file:com.searchlocal.lucene.IndexBeanList.java

License:Open Source License

public static void makeHtmlindex(IndexWriter indexWriter, HtmlFileBean bean)
        throws CorruptIndexException, IOException {
    Document document = new Document();

    document.add(new Field("filename", bean.getFilename(), Field.Store.YES, Field.Index.ANALYZED));
    document.add(new Field("path", bean.getPath(), Field.Store.YES, Field.Index.NOT_ANALYZED));
    document.add(new Field("content", bean.getContent(), Field.Store.YES, Field.Index.ANALYZED,
            Field.TermVector.WITH_POSITIONS_OFFSETS));

    document.add(/* www  . ja v a 2s  . co  m*/
            new Field("lastmodify", DateTools.timeToString(bean.getLastmodify(), DateTools.Resolution.MINUTE),
                    Field.Store.YES, Field.Index.NO));
    indexWriter.addDocument(document);
}

From source file:com.searchlocal.lucene.IndexBeanList.java

License:Open Source License

public static void makeTxtindex(IndexWriter indexWriter, TxtFileBean bean)
        throws CorruptIndexException, IOException {
    Document document = new Document();
    document.add(new Field("rownb", String.valueOf(bean.getRownb()), Field.Store.YES, Field.Index.NO));

    document.add(new Field("filename", bean.getFilename(), Field.Store.YES, Field.Index.ANALYZED));
    document.add(new Field("path", bean.getPath(), Field.Store.YES, Field.Index.NOT_ANALYZED));
    document.add(new Field("content", bean.getContent(), Field.Store.YES, Field.Index.ANALYZED,
            Field.TermVector.WITH_POSITIONS_OFFSETS));

    document.add(/*ww  w. j  a v  a2  s . co m*/
            new Field("lastmodify", DateTools.timeToString(bean.getLastmodify(), DateTools.Resolution.MINUTE),
                    Field.Store.YES, Field.Index.NO));
    indexWriter.addDocument(document);
}

From source file:com.senseidb.abacus.api.codec.CodecTest.java

License:Apache License

static Directory buildIndex(Iterable<String> datasrc, Codec codec) throws Exception {
    String idxname = codec == null ? "lucene" : codec.getName();
    Directory dir = FSDirectory.open(new File("/tmp/codectest", idxname));//new RAMDirectory();
    //Directory dir = new RAMDirectory();
    IndexWriterConfig conf = new IndexWriterConfig(Version.LUCENE_44, new StandardAnalyzer(Version.LUCENE_44));
    conf.setUseCompoundFile(false);/*from   www  .  j a v a  2 s  .  c  o m*/
    if (codec != null) {
        conf.setCodec(codec);
    }

    IndexWriter writer = new IndexWriter(dir, conf);

    for (String doc : datasrc) {
        if (doc == null)
            break;
        doc = doc.trim();
        if (doc.length() == 0)
            continue;
        Document d = new Document();
        FieldType ft = new FieldType();
        ft.setIndexed(true);
        ft.setStored(false);
        ft.setIndexOptions(IndexOptions.DOCS_ONLY);
        ft.setOmitNorms(true);
        Field f = new Field(FIELD, doc, ft);
        d.add(f);
        writer.addDocument(d);
    }
    writer.forceMerge(1);
    writer.commit();
    writer.close();
    return dir;
}