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.concursive.connect.web.modules.reviews.dao.ProjectRatingIndexer.java

License:Open Source License

/**
 * Description of the Method//from w ww.  ja  v  a 2 s  .  c om
 *
 * @param writer   Description of the Parameter
 * @param item     Description of the Parameter
 * @param modified Description of the Parameter
 * @throws IOException Description of the Exception
 */
public void add(IndexWriter writer, Object item, boolean modified) throws IOException {
    ProjectRating projectRating = (ProjectRating) item;
    // add the document
    Document document = new Document();
    document.add(new Field("type", "reviews", Field.Store.YES, Field.Index.UN_TOKENIZED));
    document.add(new Field("ratingId", String.valueOf(projectRating.getId()), Field.Store.YES,
            Field.Index.UN_TOKENIZED));
    document.add(new Field("projectId", String.valueOf(projectRating.getProjectId()), Field.Store.YES,
            Field.Index.UN_TOKENIZED));
    if (projectRating.getProjectId() > -1) {
        // use the project's general access to speedup guest projects
        Project project = ProjectUtils.loadProject(projectRating.getProjectId());
        document.add(new Field("projectCategoryId", String.valueOf(project.getCategoryId()), Field.Store.YES,
                Field.Index.UN_TOKENIZED));
        document.add(new Field("guests", (project.getFeatures().getAllowGuests() ? "1" : "0"), Field.Store.YES,
                Field.Index.UN_TOKENIZED));
        document.add(new Field("participants", (project.getFeatures().getAllowParticipants() ? "1" : "0"),
                Field.Store.YES, Field.Index.UN_TOKENIZED));
        // determine if membership is needed for this content based on a guest's access to the data
        int membership = project.getFeatures().getMembershipRequired() ? 1 : 0;
        if (membership == 1 && ProjectUtils.hasAccess(project.getId(), UserUtils.createGuestUser(),
                "project-reviews-view")) {
            membership = 0;
        }
        document.add(
                new Field("membership", String.valueOf(membership), Field.Store.YES, Field.Index.UN_TOKENIZED));
    }
    document.add(new Field("title", projectRating.getTitle(), Field.Store.YES, Field.Index.TOKENIZED));
    document.add(new Field("titleLower", projectRating.getTitle().toLowerCase(), Field.Store.YES,
            Field.Index.UN_TOKENIZED));
    document.add(new Field("contents",
            projectRating.getTitle() + " " + ContentUtils.toText(projectRating.getComment()), Field.Store.YES,
            Field.Index.TOKENIZED));
    if (projectRating.getModified() != null) {
        SimpleDateFormat formatter = new SimpleDateFormat("yyyyMMdd");
        document.add(new Field("lastModified", String.valueOf(formatter.format(projectRating.getModified())),
                Field.Store.YES, Field.Index.UN_TOKENIZED));
    }
    writer.addDocument(document);
    if (System.getProperty("DEBUG") != null && modified) {
        System.out.println("ProjectRatingIndexer-> Added: " + projectRating.getId());
    }
}

From source file:com.concursive.connect.web.modules.wiki.dao.WikiIndexer.java

License:Open Source License

/**
 * Description of the Method// www . ja  v  a2s  . c om
 *
 * @param writer   Description of the Parameter
 * @param item     Description of the Parameter
 * @param modified Description of the Parameter
 * @throws java.io.IOException Description of the Exception
 */
public void add(IndexWriter writer, Object item, boolean modified) throws IOException {
    Wiki wiki = (Wiki) item;
    // use the project's general access to speedup guest projects
    Project project = ProjectUtils.loadProject(wiki.getProjectId());
    // Use the wiki context
    WikiToHTMLContext wikiContext = new WikiToHTMLContext(wiki, new HashMap<String, ImageInfo>(), -1, false,
            "");
    // add the document
    Document document = new Document();
    document.add(new Field("type", "wiki", Field.Store.YES, Field.Index.UN_TOKENIZED));
    document.add(new Field("wikiId", String.valueOf(wiki.getId()), Field.Store.YES, Field.Index.UN_TOKENIZED));
    document.add(new Field("projectId", String.valueOf(wiki.getProjectId()), Field.Store.YES,
            Field.Index.UN_TOKENIZED));
    document.add(new Field("projectCategoryId", String.valueOf(project.getCategoryId()), Field.Store.YES,
            Field.Index.UN_TOKENIZED));
    document.add(new Field("instanceId", String.valueOf(project.getInstanceId()), Field.Store.YES,
            Field.Index.UN_TOKENIZED));
    // use the project to determine when this data can be viewed...
    document.add(new Field("guests", (project.getFeatures().getAllowGuests() ? "1" : "0"), Field.Store.YES,
            Field.Index.UN_TOKENIZED));
    document.add(new Field("participants", (project.getFeatures().getAllowParticipants() ? "1" : "0"),
            Field.Store.YES, Field.Index.UN_TOKENIZED));
    // determine if membership is needed for this content based on a guest's access to the data
    int membership = project.getFeatures().getMembershipRequired() ? 1 : 0;
    if (membership == 1
            && ProjectUtils.hasAccess(project.getId(), UserUtils.createGuestUser(), "project-wiki-view")) {
        membership = 0;
    }
    document.add(
            new Field("membership", String.valueOf(membership), Field.Store.YES, Field.Index.UN_TOKENIZED));
    document.add(new Field("title", wiki.getSubject(), Field.Store.YES, Field.Index.TOKENIZED));
    document.add(new Field("titleLower", wiki.getSubject().toLowerCase(), Field.Store.YES,
            Field.Index.UN_TOKENIZED));
    document.add(new Field("contents",
            wiki.getSubject() + " "
                    + ContentUtils.toText(ContentUtils
                            .stripHTML(StringUtils.fromHtmlValue(WikiToHTMLUtils.getHTML(wikiContext, null)))),
            Field.Store.YES, Field.Index.TOKENIZED));
    document.add(new Field("subjectLink", wiki.getSubjectLink(), Field.Store.YES, Field.Index.TOKENIZED));
    if (modified) {
        document.add(new Field("modified", String.valueOf(System.currentTimeMillis()), Field.Store.YES,
                Field.Index.UN_TOKENIZED));
    } else {
        document.add(new Field("modified", String.valueOf(wiki.getModified().getTime()), Field.Store.YES,
                Field.Index.UN_TOKENIZED));
    }
    writer.addDocument(document);
    if (System.getProperty("DEBUG") != null && modified) {
        System.out.println("WikiIndexer-> Added: " + wiki.getId());
    }
}

From source file:com.czw.search.lucene.example.facet.AssociationsFacetsExample.java

License:Apache License

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

    // Writes facet ords to a separate directory from the main index
    DirectoryTaxonomyWriter taxoWriter = new DirectoryTaxonomyWriter(taxoDir);

    Document doc = new Document();
    // 3 occurrences for tag 'lucene'
    doc.add(new IntAssociationFacetField(3, "tags", "lucene"));
    // 87% confidence level of genre 'computing'
    doc.add(new FloatAssociationFacetField(0.87f, "genre", "computing"));
    indexWriter.addDocument(config.build(taxoWriter, doc));

    doc = new Document();
    // 1 occurrence for tag 'lucene'
    doc.add(new IntAssociationFacetField(1, "tags", "lucene"));
    // 2 occurrence for tag 'solr'
    doc.add(new IntAssociationFacetField(2, "tags", "solr"));
    // 75% confidence level of genre 'computing'
    doc.add(new FloatAssociationFacetField(0.75f, "genre", "computing"));
    // 34% confidence level of genre 'software'
    doc.add(new FloatAssociationFacetField(0.34f, "genre", "software"));
    indexWriter.addDocument(config.build(taxoWriter, doc));

    indexWriter.close();//from  w w  w.  j ava 2 s.c o m
    taxoWriter.close();
}

From source file:com.czw.search.lucene.example.facet.DistanceFacetsExample.java

License:Apache License

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

    // TODO: we could index in radians instead ... saves all the conversions in getBoundingBoxFilter

    // Add documents with latitude/longitude location:
    // we index these both as DoublePoints (for bounding box/ranges) and as NumericDocValuesFields (for scoring)
    Document doc = new Document();
    doc.add(new DoublePoint("latitude", 40.759011));
    doc.add(new NumericDocValuesField("latitude", Double.doubleToRawLongBits(40.759011)));
    doc.add(new DoublePoint("longitude", -73.9844722));
    doc.add(new NumericDocValuesField("longitude", Double.doubleToRawLongBits(-73.9844722)));
    writer.addDocument(doc);

    doc = new Document();
    doc.add(new DoublePoint("latitude", 40.718266));
    doc.add(new NumericDocValuesField("latitude", Double.doubleToRawLongBits(40.718266)));
    doc.add(new DoublePoint("longitude", -74.007819));
    doc.add(new NumericDocValuesField("longitude", Double.doubleToRawLongBits(-74.007819)));
    writer.addDocument(doc);//ww w .  ja  v a2  s  . c  om

    doc = new Document();
    doc.add(new DoublePoint("latitude", 40.7051157));
    doc.add(new NumericDocValuesField("latitude", Double.doubleToRawLongBits(40.7051157)));
    doc.add(new DoublePoint("longitude", -74.0088305));
    doc.add(new NumericDocValuesField("longitude", Double.doubleToRawLongBits(-74.0088305)));
    writer.addDocument(doc);

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

From source file:com.czw.search.lucene.example.facet.ExpressionAggregationFacetsExample.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));

    // Writes facet ords to a separate directory from the main index
    DirectoryTaxonomyWriter taxoWriter = new DirectoryTaxonomyWriter(taxoDir);

    Document doc = new Document();
    doc.add(new TextField("c", "foo bar", Store.NO));
    doc.add(new NumericDocValuesField("popularity", 5L));
    doc.add(new FacetField("A", "B"));
    indexWriter.addDocument(config.build(taxoWriter, doc));

    doc = new Document();
    doc.add(new TextField("c", "foo foo bar", Store.NO));
    doc.add(new NumericDocValuesField("popularity", 3L));
    doc.add(new FacetField("A", "C"));
    indexWriter.addDocument(config.build(taxoWriter, doc));

    indexWriter.close();/*  w w  w. j a va2s.  c  o m*/
    taxoWriter.close();
}

From source file:com.czw.search.lucene.example.facet.MultiCategoryListsFacetsExample.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));

    // Writes facet ords to a separate directory from the main index
    DirectoryTaxonomyWriter taxoWriter = new DirectoryTaxonomyWriter(taxoDir);

    Document doc = new Document();
    doc.add(new FacetField("Author", "Bob"));
    doc.add(new FacetField("Publish Date", "2010", "10", "15"));
    indexWriter.addDocument(config.build(taxoWriter, doc));

    doc = new Document();
    doc.add(new FacetField("Author", "Lisa"));
    doc.add(new FacetField("Publish Date", "2010", "10", "20"));
    indexWriter.addDocument(config.build(taxoWriter, doc));

    doc = new Document();
    doc.add(new FacetField("Author", "Lisa"));
    doc.add(new FacetField("Publish Date", "2012", "1", "1"));
    indexWriter.addDocument(config.build(taxoWriter, doc));

    doc = new Document();
    doc.add(new FacetField("Author", "Susan"));
    doc.add(new FacetField("Publish Date", "2012", "1", "7"));
    indexWriter.addDocument(config.build(taxoWriter, doc));

    doc = new Document();
    doc.add(new FacetField("Author", "Frank"));
    doc.add(new FacetField("Publish Date", "1999", "5", "5"));
    indexWriter.addDocument(config.build(taxoWriter, doc));

    indexWriter.close();/*from  w  w w  . j  av a  2  s . co  m*/
    taxoWriter.close();
}

From source file:com.czw.search.lucene.example.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 LongPoint("timestamp", then));
        indexWriter.addDocument(doc);
    }/*from  w  ww. ja va2  s .com*/

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

From source file:com.czw.search.lucene.example.facet.SimpleFacetsExample.java

License:Apache License

/**
 * Build the example index./* www.  ja v a  2  s .  co  m*/
 */
private void index() throws IOException {
    IndexWriter indexWriter = new IndexWriter(indexDir,
            new IndexWriterConfig(new WhitespaceAnalyzer()).setOpenMode(OpenMode.CREATE));

    // Writes facet ords to a separate directory from the main index
    DirectoryTaxonomyWriter taxoWriter = new DirectoryTaxonomyWriter(taxoDir);

    Document doc = new Document();
    doc.add(new FacetField("Author", "Bob"));
    doc.add(new FacetField("Publish Date", "2010", "10", "15"));
    doc.add(new FacetField("Category", "art"));
    indexWriter.addDocument(config.build(taxoWriter, doc));

    doc = new Document();
    doc.add(new FacetField("Author", "Bob"));
    doc.add(new FacetField("Publish Date", "2010", "10", "15"));
    doc.add(new FacetField("Category", "biography"));
    indexWriter.addDocument(config.build(taxoWriter, doc));

    doc = new Document();
    doc.add(new FacetField("Author", "Lisa"));
    doc.add(new FacetField("Publish Date", "2010", "10", "20"));
    doc.add(new FacetField("Category", "fiction"));
    indexWriter.addDocument(config.build(taxoWriter, doc));

    doc = new Document();
    doc.add(new FacetField("Author", "Lisa"));
    doc.add(new FacetField("Publish Date", "2012", "1", "1"));
    doc.add(new FacetField("Category", "food"));
    indexWriter.addDocument(config.build(taxoWriter, doc));

    doc = new Document();
    doc.add(new FacetField("Author", "Susan"));
    doc.add(new FacetField("Publish Date", "2012", "1", "7"));
    doc.add(new FacetField("Category", "science"));
    indexWriter.addDocument(config.build(taxoWriter, doc));

    doc = new Document();
    doc.add(new FacetField("Author", "Frank"));
    doc.add(new FacetField("Publish Date", "1999", "5", "5"));
    doc.add(new FacetField("Category", "crime"));
    indexWriter.addDocument(config.build(taxoWriter, doc));

    doc = new Document();
    doc.add(new FacetField("Author", "Frank"));
    doc.add(new FacetField("Publish Date", "2011", "5", "15"));
    doc.add(new FacetField("Category", "fiction"));
    indexWriter.addDocument(config.build(taxoWriter, doc));

    doc = new Document();
    doc.add(new FacetField("Author", "Frank"));
    doc.add(new FacetField("Publish Date", "2017", "6", "5"));
    doc.add(new FacetField("Category", "science"));
    indexWriter.addDocument(config.build(taxoWriter, doc));

    indexWriter.close();
    taxoWriter.close();
}

From source file:com.czw.search.lucene.example.facet.SimpleSortedSetFacetsExample.java

License:Apache License

/**
 * Build the example index./* w  ww .  j av  a  2 s .  c  om*/
 */
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 source file:com.czw.search.lucene.example.IndexFiles.java

License:Apache License

/**
 * Indexes a single document/*from  www . j  a  v  a 2  s  .  c  o  m*/
 */
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();

        // Add the path of the file as a field named "path".  Use a
        // field that is indexed (i.e. searchable), but don't tokenize
        // the field into separate words and don't index term frequency
        // or positional information:
        Field pathField = new StringField("path", file.toString(), Field.Store.YES);
        doc.add(pathField);

        // Add the last modified date of the file a field named "modified".
        // Use a LongPoint that is indexed (i.e. efficiently filterable with
        // PointRangeQuery).  This indexes to milli-second resolution, which
        // is often too fine.  You could instead create a number based on
        // year/month/day/hour/minutes/seconds, down the resolution you require.
        // For example the long value 2011021714 would mean
        // February 17, 2011, 2-3 PM.
        doc.add(new LongPoint("modified", lastModified));

        // Add the contents of the file to a field named "contents".  Specify a Reader,
        // so that the text of the file is tokenized and indexed, but not stored.
        // Note that FileReader expects the file to be in UTF-8 encoding.
        // If that's not the case searching for special characters will fail.
        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
            // we use updateDocument instead to replace the old one matching the exact
            // path, if present:
            System.out.println("updating " + file);
            writer.updateDocument(new Term("path", file.toString()), doc);
        }
    }
}