Examples of org.apache.lucene.index.IndexWriter.addDocument()

Class org.apache.lucene.index.IndexWriter

Examples of org.apache.lucene.index.IndexWriter.addDocument()

org.apache.lucene.index.IndexWriter.addDocument()
Adds a document to this index. If the document contains more than {@link #setMaxFieldLength(int)} terms for a given field, the remainder arediscarded.
Note that if an Exception is hit (for example disk full) then the index will be consistent, but this document may not have been added. Furthermore, it's possible the index will have one segment in non-compound format even when using compound files (when a merge has partially succeeded).

This method periodically flushes pending documents to the Directory (see above), and also periodically triggers segment merges in the index according to the {@link MergePolicy} in use.
Merges temporarily consume space in the directory. The amount of space required is up to 1X the size of all segments being merged, when no readers/searchers are open against the index, and up to 2X the size of all segments being merged when readers/searchers are open against the index (see {@link #optimize()} for details). The sequence ofprimitive merge operations performed is governed by the merge policy.
Note that each term in the document can be no longer than 16383 characters, otherwise an IllegalArgumentException will be thrown.

Note that it's possible to create an invalid Unicode string in java if a UTF16 surrogate pair is malformed. In this case, the invalid characters are silently replaced with the Unicode replacement character U+FFFD.

NOTE: if this method hits an OutOfMemoryError you should immediately close the writer. See above for details.
@throws CorruptIndexException if the index is corrupt @throws IOException if there is a low-level IO error

    IndexWriter writer = new IndexWriter(store, new SimpleAnalyzer(), true, IndexWriter.MaxFieldLength.LIMITED);


    Document d1 = new Document();
    d1.add(new Field("field", "a b", Field.Store.YES, Field.Index.ANALYZED));


    writer.addDocument(d1);
    writer.optimize();
    writer.close();


    Searcher searcher = new IndexSearcher(store, true);
      QueryParser parser = new QueryParser(Version.LUCENE_CURRENT, "field", new SimpleAnalyzer());

View Full Code Here

    for (int i = 0; i < numDocs; i++) {
      Document doc = new Document();
      doc.add(new Field(FIELD, English.intToEnglish(i), Field.Store.YES, Field.Index.ANALYZED));
      doc.add(new Field(MULTI_FIELD, English.intToEnglish(i) + "  " + English.intToEnglish(i), Field.Store.YES, Field.Index.ANALYZED));
      doc.add(new Field(NO_PAYLOAD_FIELD, English.intToEnglish(i), Field.Store.YES, Field.Index.ANALYZED));
      writer.addDocument(doc);
    }
    //writer.optimize();
    writer.close();


    IndexSearcher searcher = new IndexSearcher(directory, true);

View Full Code Here

    IndexWriter iw = new IndexWriter(ramDir, new WhitespaceAnalyzer(), true,
        IndexWriter.MaxFieldLength.LIMITED);
    Document doc = new Document();
    doc.add(new Field("content", "\u0633\u0627\u0628", Field.Store.YES,
        Field.Index.NOT_ANALYZED));
    iw.addDocument(doc);
    iw.close();
    IndexSearcher is = new IndexSearcher(ramDir, true);


    StandardQueryParser qp = new StandardQueryParser();
    qp.setAnalyzer(new WhitespaceAnalyzer());

View Full Code Here

    RAMDirectory indexStore = new RAMDirectory();
    IndexWriter writer = new IndexWriter(indexStore, new SimpleAnalyzer(), true, IndexWriter.MaxFieldLength.LIMITED);
    for (int i = 0; i < contents.length; ++i) {
      Document doc = new Document();
      doc.add(new Field(field, contents[i], Field.Store.YES, Field.Index.ANALYZED));
      writer.addDocument(doc);
    }
    writer.optimize();
    writer.close();


    return indexStore;

View Full Code Here

  public void testMultiPhraseQuery() throws Exception {
    MockRAMDirectory dir = new MockRAMDirectory();
    IndexWriter w = new IndexWriter(dir, new CannedAnalyzer(), IndexWriter.MaxFieldLength.UNLIMITED);
    Document doc = new Document();
    doc.add(new Field("field", "", Field.Store.NO, Field.Index.ANALYZED));
    w.addDocument(doc);
    IndexReader r = w.getReader();
    IndexSearcher s = new IndexSearcher(r);
    
    Query q = new StandardQueryParser(new CannedAnalyzer()).parse("\"a\"", "field");
    assertTrue(q instanceof MultiPhraseQuery);

View Full Code Here

    RAMDirectory dir = new RAMDirectory();
    IndexWriter iw = new IndexWriter(dir, new WhitespaceAnalyzer(), IndexWriter.MaxFieldLength.LIMITED);
    for (int i = 0; i < docs.length; i++) {
      Document doc = new Document();
      doc.add(new Field(field,docs[i],Store.NO,Index.ANALYZED));
      iw.addDocument(doc);
    }
    iw.close();
    
    IndexSearcher searcher = new IndexSearcher(dir, true);

View Full Code Here

      Document doc = new Document();
      String variedFieldValue = variedFieldValues[i % variedFieldValues.length];
      String repetitiveFieldValue = repetitiveFieldValues[i % repetitiveFieldValues.length];
      doc.add(new Field("variedField", variedFieldValue, Field.Store.YES, Field.Index.ANALYZED));
      doc.add(new Field("repetitiveField", repetitiveFieldValue, Field.Store.YES, Field.Index.ANALYZED));
      writer.addDocument(doc);
    }
    writer.close();
    reader = IndexReader.open(dir, true);
    protectedAnalyzer = new QueryAutoStopWordAnalyzer(Version.LUCENE_CURRENT, appAnalyzer);
  }

View Full Code Here

      Field noPayloadField = new Field(PayloadHelper.NO_PAYLOAD_FIELD, English.intToEnglish(i), Field.Store.YES, Field.Index.ANALYZED);
      //noPayloadField.setBoost(0);
      doc.add(noPayloadField);
      doc.add(new Field("field", English.intToEnglish(i), Field.Store.YES, Field.Index.ANALYZED));
      doc.add(new Field("multiField", English.intToEnglish(i) + "  " + English.intToEnglish(i), Field.Store.YES, Field.Index.ANALYZED));
      writer.addDocument(doc);
    }
    writer.optimize();
    writer.close();


    searcher = new IndexSearcher(directory, true);

View Full Code Here

    for (int i = 0; i < 1000; i++) {
      Document doc = new Document();
      doc.add(new Field("field", English.intToEnglish(i), Field.Store.YES, Field.Index.ANALYZED));
      String txt = English.intToEnglish(i) +' '+English.intToEnglish(i+1);
      doc.add(new Field("field2",  txt, Field.Store.YES, Field.Index.ANALYZED));
      writer.addDocument(doc);
    }
    writer.optimize();
    writer.close();


    searcher = new IndexSearcher(directory, true);

View Full Code Here

    RAMDirectory directory = new RAMDirectory();
    IndexWriter writer= new IndexWriter(directory, new WhitespaceAnalyzer(), true, IndexWriter.MaxFieldLength.LIMITED);
    for (int i = 0; i < docFields.length; i++) {
      Document doc = new Document();
      doc.add(new Field(FIELD, docFields[i], Field.Store.NO, Field.Index.ANALYZED));
      writer.addDocument(doc);
    }
    writer.close();
    searcher = new IndexSearcher(directory, true);
  }

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.