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.mathworks.xzheng.analysis.codec.MetaphoneAnalyzerTest.java

License:Apache License

public void testKoolKat() throws Exception {
    RAMDirectory directory = new RAMDirectory();
    Analyzer analyzer = new MetaphoneReplacementAnalyzer();

    IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_46, analyzer);
    config.setOpenMode(IndexWriterConfig.OpenMode.CREATE);

    IndexWriter writer = new IndexWriter(directory, config);

    Document doc = new Document();
    doc.add(new Field("contents", //#A
            "cool cat", Field.Store.YES, Field.Index.ANALYZED));
    writer.addDocument(doc);
    writer.close();//from  ww w . ja  v  a2 s  .c o  m

    IndexSearcher searcher = new IndexSearcher(DirectoryReader.open(directory));

    Query query = new QueryParser(Version.LUCENE_46, //#B
            "contents", analyzer) //#B
                    .parse("kool kat"); //#B

    TopDocs hits = searcher.search(query, 1);
    assertEquals(1, hits.totalHits); //#C
    int docID = hits.scoreDocs[0].doc;
    doc = searcher.doc(docID);
    assertEquals("cool cat", doc.get("contents")); //#D

}

---

From source file:com.mathworks.xzheng.analysis.keyword.KeywordAnalyzerTest.java

License:Apache License

public void setUp() throws Exception {
    Directory directory = new RAMDirectory();

    IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_46, new SimpleAnalyzer(Version.LUCENE_46));

    IndexWriter writer = new IndexWriter(directory, config);

    Document doc = new Document();
    doc.add(new Field("partnum", "Q36", Field.Store.NO, Field.Index.NOT_ANALYZED_NO_NORMS)); //A
    doc.add(new Field("description", "Illidium Space Modulator", Field.Store.YES, Field.Index.ANALYZED));
    writer.addDocument(doc);

    writer.close();// w  w w. ja  v  a  2  s . com

    searcher = new IndexSearcher(DirectoryReader.open(directory));
}

---

From source file:com.mathworks.xzheng.analysis.positional.PositionalPorterStopAnalyzerTest.java

License:Apache License

public void setUp() throws Exception {

    RAMDirectory directory = new RAMDirectory();
    IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_46, porterAnalyzer);
    IndexWriter writer = new IndexWriter(directory, config);

    Document doc = new Document();
    doc.add(new Field("contents", "The quick brown fox jumps over the lazy dog", Field.Store.YES,
            Field.Index.ANALYZED));
    writer.addDocument(doc);
    writer.close();/*  ww  w.j  a v  a 2s .c om*/
    searcher = new IndexSearcher(DirectoryReader.open(directory));
    parser = new QueryParser(Version.LUCENE_46, "contents", porterAnalyzer);
}

---

From source file:com.mathworks.xzheng.analysis.synonym.SynonymAnalyzerTest.java

License:Apache License

public void setUp() throws Exception {
    RAMDirectory directory = new RAMDirectory();

    IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_46, synonymAnalyzer);
    IndexWriter writer = new IndexWriter(directory, config); //#1
    Document doc = new Document();
    doc.add(new Field("content", "The quick brown fox jumps over the lazy dog", Field.Store.YES,
            Field.Index.ANALYZED)); //#2
    writer.addDocument(doc);

    writer.close();/*from   ww w. j a v a2  s.  c  om*/

    searcher = new IndexSearcher(DirectoryReader.open(directory));
}

---

From source file:com.mathworks.xzheng.analysis.UsingAnalyzersExample.java

License:Apache License

/**
 * This method doesn't do anything, except compile correctly.
 * This is used to show snippets of how Analyzers are used.
 *///  ww  w  .  ja v  a  2  s  . co m
public void someMethod() throws IOException, ParseException {
    RAMDirectory directory = new RAMDirectory();

    Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_46);

    IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_46, analyzer);
    IndexWriter writer = new IndexWriter(directory, config);

    Document doc = new Document();
    doc.add(new Field("title", "This is the title", Field.Store.YES, Field.Index.ANALYZED));
    doc.add(new Field("contents", "...document contents...", Field.Store.NO, Field.Index.ANALYZED));
    writer.addDocument(doc);

    writer.addDocument(doc, analyzer);

    String expression = "some query";

    Query query = new QueryParser(Version.LUCENE_46, "contents", analyzer).parse(expression);

    QueryParser parser = new QueryParser(Version.LUCENE_46, "contents", analyzer);
    query = parser.parse(expression);
}

---

From source file:com.mathworks.xzheng.common.CreateTestIndex.java

License:Apache License

public static void main(String[] args) throws IOException {
    String dataDir = args[0];/*www  . j av  a 2  s  .  c o  m*/
    String indexDir = args[1];
    List<File> results = new ArrayList<File>();
    findFiles(results, new File(dataDir));
    System.out.println(results.size() + " books to index");
    Directory dir = FSDirectory.open(new File(indexDir));
    IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_46, new MyStandardAnalyzer());
    config.setOpenMode(IndexWriterConfig.OpenMode.CREATE);
    IndexWriter w = new IndexWriter(dir, config);
    for (File file : results) {
        Document doc = getDocument(dataDir, file);
        w.addDocument(doc);
    }
    w.close();
    dir.close();
}

---

From source file:com.mathworks.xzheng.indexing.Fragments.java

License:Apache License

public void docBoostMethod() throws IOException {

    Directory dir = new RAMDirectory();
    IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_46,
            new StandardAnalyzer(Version.LUCENE_46));
    IndexWriter writer = new IndexWriter(dir, config);

    // START/* www  .ja  v  a2s.c om*/
    Document doc = new Document();
    String senderEmail = getSenderEmail();
    String senderName = getSenderName();
    String subject = getSubject();
    String body = getBody();
    doc.add(new Field("senderEmail", senderEmail, Field.Store.YES, Field.Index.NOT_ANALYZED));
    doc.add(new Field("senderName", senderName, Field.Store.YES, Field.Index.ANALYZED));
    doc.add(new Field("subject", subject, Field.Store.YES, Field.Index.ANALYZED));
    doc.add(new Field("body", body, Field.Store.NO, Field.Index.ANALYZED));
    String lowerDomain = getSenderDomain().toLowerCase();
    if (isImportant(lowerDomain)) {
        doc.setBoost(1.5F); //1
    } else if (isUnimportant(lowerDomain)) {
        doc.setBoost(0.1F); //2 
    }
    writer.addDocument(doc);
    // END
    writer.close();

    /*
      #1 Good domain boost factor: 1.5
      #2 Bad domain boost factor: 0.1
    */
}

---

From source file:com.mathworks.xzheng.indexing.IndexingTest.java

License:Apache License

public void testMaxFieldLength() throws IOException {

    assertEquals(1, getHitCount("contents", "bridges")); //1
    IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_46,
            new WhitespaceAnalyzer(Version.LUCENE_46));
    IndexWriter writer = new IndexWriter(directory, config); //2
    Document doc = new Document(); // 3
    doc.add(new Field("contents", "these bridges can't be found", // 3
            Field.Store.NO, Field.Index.ANALYZED)); // 3
    writer.addDocument(doc); // 3
    writer.close(); // 3

    assertEquals(1, getHitCount("contents", "bridges")); //4
}

---

From source file:com.mathworks.xzheng.indexing.VerboseIndexing.java

License:Apache License

private void index() throws IOException {

    Directory dir = new RAMDirectory();
    IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_46,
            new WhitespaceAnalyzer(Version.LUCENE_46));
    IndexWriter writer = new IndexWriter(dir, config);

    config.setInfoStream(System.out);

    for (int i = 0; i < 100; i++) {
        Document doc = new Document();
        doc.add(new Field("keyword", "goober", Field.Store.YES, Field.Index.NOT_ANALYZED));
        writer.addDocument(doc);
    }/*from  w  w w  .  ja  v  a  2s . c o m*/
    //writer.optimize();
    writer.forceMerge(Integer.MAX_VALUE);
    writer.close();
}

---

From source file:com.mathworks.xzheng.searching.NearRealTimeTest.java

License:Apache License

public void testNearRealTime() throws Exception {
    Directory dir = new RAMDirectory();

    IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_46,
            new StandardAnalyzer(Version.LUCENE_46));
    IndexWriter writer = new IndexWriter(dir, config);
    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);
    }//from   ww  w .j av  a 2  s.  co m
    IndexReader reader = DirectoryReader.open(writer.getDirectory()); // #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
    IndexReader newReader = DirectoryReader.open(writer.getDirectory()); // #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();
}

---

• «
• 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
• »