Example usage for org.apache.lucene.index IndexWriter 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.leavesfly.lia.searching.NearRealTimeTest.java

License:Apache License

public void testNearRealTime() throws Exception {
    Directory dir = new RAMDirectory();
    IndexWriter writer = new IndexWriter(dir, new StandardAnalyzer(Version.LUCENE_30),
            IndexWriter.MaxFieldLength.UNLIMITED);
    for (int i = 0; i < 10; i++) {
        Document doc = new Document();
        doc.add(new Field("id", "" + i, Field.Store.NO, Field.Index.NOT_ANALYZED_NO_NORMS));
        doc.add(new Field("text", "aaa", Field.Store.NO, Field.Index.ANALYZED));
        writer.addDocument(doc);
    }// w  w w  .j  ava 2s.  com
    IndexReader reader = writer.getReader(); // #1
    IndexSearcher searcher = new IndexSearcher(reader); // #A

    Query query = new TermQuery(new Term("text", "aaa"));
    TopDocs docs = searcher.search(query, 1);
    assertEquals(10, docs.totalHits); // #B

    writer.deleteDocuments(new Term("id", "7")); // #2

    Document doc = new Document(); // #3
    doc.add(new Field("id", // #3
            "11", // #3
            Field.Store.NO, // #3
            Field.Index.NOT_ANALYZED_NO_NORMS)); // #3
    doc.add(new Field("text", // #3
            "bbb", // #3
            Field.Store.NO, // #3
            Field.Index.ANALYZED)); // #3
    writer.addDocument(doc); // #3

    IndexReader newReader = reader.reopen(); // #4
    assertFalse(reader == newReader); // #5
    reader.close(); // #6
    searcher = new IndexSearcher(newReader);

    TopDocs hits = searcher.search(query, 10); // #7
    assertEquals(9, hits.totalHits); // #7

    query = new TermQuery(new Term("text", "bbb")); // #8
    hits = searcher.search(query, 1); // #8
    assertEquals(1, hits.totalHits); // #8

    newReader.close();
    writer.close();
}

---

From source file:com.leavesfly.lia.searching.PhraseQueryTest.java

License:Apache License

protected void setUp() throws IOException {
    dir = new RAMDirectory();
    IndexWriter writer = new IndexWriter(dir, new WhitespaceAnalyzer(), IndexWriter.MaxFieldLength.UNLIMITED);
    Document doc = new Document();
    doc.add(new Field("field", // 1
            "the quick brown fox jumped over the lazy dog", // 1
            Field.Store.YES, // 1
            Field.Index.ANALYZED)); // 1
    writer.addDocument(doc);
    writer.close();/*from  ww  w.ja  va 2 s  .  c o  m*/

    searcher = new IndexSearcher(dir);
}

---

From source file:com.leavesfly.lia.searching.ScoreTest.java

License:Apache License

private void indexSingleFieldDocs(Field[] fields) throws Exception {
    IndexWriter writer = new IndexWriter(directory, new WhitespaceAnalyzer(),
            IndexWriter.MaxFieldLength.UNLIMITED);
    for (Field f : fields) {
        Document doc = new Document();
        doc.add(f);/* w w w  .ja v a2  s.  c  om*/
        writer.addDocument(doc);
    }
    writer.optimize();
    writer.close();
}

---

From source file:com.leavesfly.lia.tool.ChainedFilterTest.java

License:Apache License

public void setUp() throws Exception {
    directory = new RAMDirectory();
    IndexWriter writer = new IndexWriter(directory, new WhitespaceAnalyzer(),
            IndexWriter.MaxFieldLength.UNLIMITED);

    Calendar cal = Calendar.getInstance();
    cal.set(2009, 1, 1, 0, 0); // A

    for (int i = 0; i < MAX; i++) {
        Document doc = new Document();
        doc.add(new Field("key", "" + (i + 1), Field.Store.YES, Field.Index.NOT_ANALYZED));
        doc.add(new Field("owner", (i < MAX / 2) ? "bob" : "sue", Field.Store.YES, Field.Index.NOT_ANALYZED));
        doc.add(new Field("date", DateTools.timeToString(cal.getTimeInMillis(), DateTools.Resolution.DAY),
                Field.Store.YES, Field.Index.NOT_ANALYZED));
        writer.addDocument(doc);

        cal.add(Calendar.DATE, 1);
    }/*ww w  .  j  a v a2 s . co  m*/

    writer.close();

    searcher = new IndexSearcher(directory);

    BooleanQuery bq = new BooleanQuery(); // B
    bq.add(new TermQuery(new Term("owner", "bob")), // B
            BooleanClause.Occur.SHOULD); // B
    bq.add(new TermQuery(new Term("owner", "sue")), // B
            BooleanClause.Occur.SHOULD); // B
    query = bq;

    cal.set(2099, 1, 1, 0, 0);
    dateFilter = TermRangeFilter.Less("date", // C
            DateTools.timeToString( // C
                    cal.getTimeInMillis(), // C
                    DateTools.Resolution.DAY));// C

    bobFilter = new CachingWrapperFilter( // D
            new QueryWrapperFilter( // D
                    new TermQuery(new Term("owner", "bob")))); // D

    sueFilter = new CachingWrapperFilter( // E
            new QueryWrapperFilter( // E
                    new TermQuery(new Term("owner", "sue")))); // E
}

---

From source file:com.leavesfly.lia.tool.SpatialLuceneExample.java

License:Apache License

private void addLocation(IndexWriter writer, String name, double lat, double lng) throws IOException {

    Document doc = new Document();
    doc.add(new Field("name", name, Field.Store.YES, Field.Index.ANALYZED));

    doc.add(new Field(latField, NumericUtils.doubleToPrefixCoded(lat), // #A
            Field.Store.YES, Field.Index.NOT_ANALYZED)); // #A
    doc.add(new Field(lngField, NumericUtils.doubleToPrefixCoded(lng), // #A
            Field.Store.YES, Field.Index.NOT_ANALYZED)); // #A

    doc.add(new Field("metafile", "doc", Field.Store.YES, Field.Index.ANALYZED));

    IProjector projector = new SinusoidalProjector(); // #B

    int startTier = 5; // #C
    int endTier = 15; // #C

    for (; startTier <= endTier; startTier++) {
        CartesianTierPlotter ctp;/*from ww w . j  a  v a 2  s  . c  om*/
        ctp = new CartesianTierPlotter(startTier, // #D
                projector, tierPrefix); // #D

        double boxId = ctp.getTierBoxId(lat, lng); // #D
        System.out.println("Adding field " + ctp.getTierFieldName() + ":" + boxId);
        doc.add(new Field(ctp.getTierFieldName(), NumericUtils // #E
                .doubleToPrefixCoded(boxId), Field.Store.YES, Field.Index.NOT_ANALYZED_NO_NORMS));

    }

    writer.addDocument(doc);
    System.out.println("===== Added Doc to index ====");
}

---

From source file:com.leixl.easyframework.lucene.impl.LuceneEMovieDaoImpl.java

License:Open Source License

public Integer index(IndexWriter writer, Date startDate, Date endDate, Integer startId, Integer max)
        throws CorruptIndexException, IOException {
    Finder f = Finder.create("select bean from EMovie bean");

    f.append(" where 1=1");
    if (startId != null) {
        f.append(" and bean.id > :startId");
        f.setParam("startId", startId);
    }//from  ww w. j a  v  a  2  s.  c o m
    if (startDate != null) {
        f.append(" and bean.createDate >= :startDate");
        f.setParam("startDate", startDate);
    }
    if (endDate != null) {
        f.append(" and bean.createDate <= :endDate");
        f.setParam("endDate", endDate);
    }
    f.append(" order by bean.id asc");
    if (max != null) {
        f.setMaxResults(max);
    }
    Session session = getSession();
    ScrollableResults movies = f.createQuery(getSession()).setCacheMode(CacheMode.IGNORE)
            .scroll(ScrollMode.FORWARD_ONLY);
    int count = 0;
    EMovie movie = null;
    while (movies.next()) {
        movie = (EMovie) movies.get(0);
        writer.addDocument(LuceneContent.createDocument(movie));
        if (++count % 20 == 0) {
            session.clear();
        }
    }
    if (count < max || movie == null) {
        // ????????
        return null;
    } else {
        // ?ID
        return movie.getId();
    }

}

---

From source file:com.lin.studytest.lucene.IndexFiles.java

License:Apache License

/** Indexes a single document */
static void indexDoc(IndexWriter writer, Path file, long lastModified) throws IOException {
    try {/*  www  . j  a  va 2s.c o  m*/
        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 LongField that is indexed (i.e. efficiently filterable with
        // NumericRangeFilter).  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 LongField("modified", lastModified, Field.Store.NO));

        // 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);
        }
    } finally {

    }
}

---

From source file:com.liusoft.dlog4j.search.SearchProxy.java

License:Open Source License

/**
 * //  w  w  w .j a va 2  s  . c o m
 * @param doc
 * @throws Exception 
 */
public static synchronized void add(SearchEnabled doc) throws Exception {
    if (doc == null)
        return;

    Document lucene_doc = new Document();

    //Set keyword field
    String key = getField(doc, doc.getKeywordField());
    lucene_doc.add(Keyword(doc.getKeywordField(), key));

    //Set identity(classname) of object
    lucene_doc.add(Keyword(CLASSNAME_FIELD, doc.getClass().getName()));

    //Set storage field
    String[] storeFields = doc.getStoreFields();
    for (int i = 0; storeFields != null && i < storeFields.length; i++) {
        String propertyValue = getField(doc, storeFields[i]);
        if (propertyValue != null)
            lucene_doc.add(Keyword(storeFields[i], propertyValue));
    }
    //Set indexed field
    String[] indexFields = doc.getIndexFields();
    for (int i = 0; indexFields != null && i < indexFields.length; i++) {
        String propertyValue = getField(doc, indexFields[i]);
        lucene_doc.add(UnStored(indexFields[i], propertyValue));
    }
    //Write document
    IndexWriter writer = getWriter(doc.name());
    try {
        writer.addDocument(lucene_doc);
        writer.optimize();
    } finally {
        try {
            writer.close();
        } catch (Exception e) {
            log.error("Error occur when closing IndexWriter", e);
        } finally {
            writer = null;
        }
        lucene_doc = null;
    }

}

---

From source file:com.lorelib.analyzer.sample.LuceneIndexAndSearchDemo.java

License:Apache License

/**
 * /*from   ww  w  .  j a  v a  2 s .c o  m*/
 * ???
 * @param args
 */
public static void main(String[] args) {
    //Lucene Document??
    String fieldName = "text";
    //
    String text = "IK Analyzer???????";

    //IKAnalyzer?
    Analyzer analyzer = new IKAnalyzer(true);

    Directory directory = null;
    IndexWriter iwriter = null;
    IndexReader ireader = null;
    IndexSearcher isearcher = null;
    try {
        //
        directory = new RAMDirectory();

        //?IndexWriterConfig
        IndexWriterConfig iwConfig = new IndexWriterConfig(analyzer);
        iwConfig.setOpenMode(OpenMode.CREATE_OR_APPEND);
        iwriter = new IndexWriter(directory, iwConfig);
        //
        Document doc = new Document();
        doc.add(new StringField("ID", "10000", Field.Store.YES));
        doc.add(new TextField(fieldName, text, Field.Store.YES));
        iwriter.addDocument(doc);
        iwriter.close();

        //?**********************************
        //?
        ireader = DirectoryReader.open(directory);
        isearcher = new IndexSearcher(ireader);

        String keyword = "?";
        //QueryParser?Query
        QueryParser qp = new QueryParser(fieldName, analyzer);
        qp.setDefaultOperator(QueryParser.AND_OPERATOR);
        Query query = qp.parse(keyword);
        System.out.println("Query = " + query);

        //?5?
        TopDocs topDocs = isearcher.search(query, 5);
        System.out.println("" + topDocs.totalHits);
        //
        ScoreDoc[] scoreDocs = topDocs.scoreDocs;
        for (int i = 0; i < topDocs.totalHits; i++) {
            Document targetDoc = isearcher.doc(scoreDocs[i].doc);
            System.out.println("" + targetDoc.toString());
        }

    } catch (CorruptIndexException e) {
        e.printStackTrace();
    } catch (LockObtainFailedException e) {
        e.printStackTrace();
    } catch (IOException e) {
        e.printStackTrace();
    } catch (ParseException e) {
        e.printStackTrace();
    } finally {
        if (ireader != null) {
            try {
                ireader.close();
            } catch (IOException e) {
                e.printStackTrace();
            }
        }
        if (directory != null) {
            try {
                directory.close();
            } catch (IOException e) {
                e.printStackTrace();
            }
        }
    }
}

---

From source file:com.luc.indexer.LuceneCommonIndexer.java

License:Apache License

private static void indexFile(IndexWriter writer, File file) throws IOException, SAXException, TikaException {

    if (file.isHidden() || !file.exists() || !file.canRead()) {
        return;/*from  www.jav  a 2  s.  com*/
    }

    /*
            
    System.out.println("Indexing " + file.getCanonicalPath());
            
    */

    is = new FileInputStream(file);
    textHandler = new BodyContentHandler();
    metadata = new Metadata();

    commonParser = new AutoDetectParser();
    commonParser.parse(is, textHandler, metadata, new ParseContext());

    Document doc = new Document();

    doc.add(new Field("contents", textHandler.toString(), Field.Store.NO, Field.Index.ANALYZED));
    doc.add(new Field("filename", file.getCanonicalPath(), Field.Store.YES, Field.Index.NOT_ANALYZED));
    writer.addDocument(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
• 29
• 30
• 31
• 32
• 33
• 34
• 35
• 36
• 37
• 38
• 39
• 40
• 41
• 42
• 43
• 44
• 45
• 46
• 47
• 48
• 49
• 50
• »