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.spike.text.lucene.util.LuceneTestBookIndexingUtil.java

License:Apache License

public static void main(String[] args) throws IOException {
    String dataDir = LuceneAppConstants.BOOK_DATA_DIR;
    String indexDir = LuceneAppConstants.BOOK_INDEX_DIR;

    List<File> results = new ArrayList<File>();
    findFiles(results, new File(dataDir));
    System.out.println(results.size() + " books to index");
    Directory directory = FSDirectory.open(Paths.get(indexDir));

    IndexWriterConfig config = new IndexWriterConfig(new MyStandardAnalyzer());
    config.setCommitOnClose(true);/*from w  w  w  .j  ava  2 s  .c  o m*/
    IndexWriter indexWriter = new IndexWriter(directory, config);

    for (File file : results) {
        Document document = getDocument(dataDir, file);
        indexWriter.addDocument(document);
    }

    indexWriter.close();
    directory.close();
}

---

From source file:com.sun.javaee.blueprints.carstore.search.UpdateIndex.java

License:Berkeley License

public void updateDocTag(String indexFile, String sxTagField, String tagString, String sxDocId, String type)
        throws IOException {
    if (bDebug)// www  .ja v  a 2 s .com
        System.out.println("Tagging document:" + sxDocId + " with \"" + sxTagField + " - " + tagString + "\"");
    Document doc = deleteIndex(indexFile, sxDocId);

    /*
    // get document to update, so data can be added
    SearchIndex si=new SearchIndex();
    si.query(indexFile, sxDocId, "uid");
            
    Hits hits=si.getHitsNative();
    // should only have one return
    if(hits.length() > 1) {
    // exception, should only be one
       throw new IllegalStateException("Should only have one document in index with uid=" + sxDocId);
    }
            
    Document doc=(Document)hits.doc(0);
    if(bDebug) System.out.println("HAVE DOC " + doc);
            
    // Read index and delete targeted doc through a term
    IndexReader reader=IndexReader.open(indexFile);
    // delete document by term
    int del=reader.deleteDocuments(new Term("uid", sxDocId));
    if(bDebug) {
    System.out.println("return Number of items deleted:"  + del);
    int deleted=0;
    for(int ii=0; ii < reader.numDocs(); ii++) {
        if(reader.isDeleted(ii)) {
            deleted++;
        }
    }
    if(bDebug) System.out.println("Number of deleted items in the whole index:" + deleted);
    }
    reader.close();
    */

    // update document with tag information or add to tag that exists
    // NOTE: The tag information should be persisted in another place, 
    // incase indexes need to be rebuilt
    Field field = doc.getField(sxTagField);
    if (field == null) {
        // create new tag field
        field = new Field(sxTagField, tagString, Field.Store.YES, Field.Index.TOKENIZED);
    } else {
        if (type.equals(APPEND_FIELD)) {
            // get existing field and append new tag with space
            tagString = field.stringValue() + " " + tagString;
        }
        doc.removeField(sxTagField);
        field = new Field(sxTagField, tagString, Field.Store.YES, Field.Index.TOKENIZED);
    }

    doc.add(field);
    if (bDebug)
        System.out.println("Added field \n" + field + " doc to index = \n" + doc);
    // open writer to re-add document (no update in Lucene)
    Analyzer analyzer = new StandardAnalyzer();
    IndexWriter writer = new IndexWriter(indexFile, analyzer, false);
    if (bDebug)
        System.out.println("Before optimize = " + writer.docCount());
    writer.optimize();
    if (bDebug)
        System.out.println("Before add = " + writer.docCount());
    writer.addDocument(doc);
    if (bDebug)
        System.out.println("after add = " + writer.docCount());
    writer.close();
}

---

From source file:com.sun.socialsite.business.impl.LuceneSearchManagerImpl.java

License:Open Source License

/**
 * @return false if the index entry was not updated because it
 * was already current; true otherwise./* w  w  w. j a va2 s.c  om*/
 */
public boolean addToIndex(final App app) throws IOException {

    boolean needNewEntry = true;

    String key = getKey(app);
    String url = app.getURL().toExternalForm();
    String title = app.getTitle();
    String description = app.getDescription();

    IndexReader reader = IndexReader.open(indexDir);
    TermDocs termDocs = reader.termDocs(new Term("key", key));
    while (termDocs.next()) {
        Document existingDoc = reader.document(termDocs.doc());
        if (areEqual("app", existingDoc.get("class")) && areEqual(url, existingDoc.get("url"))
                && areEqual(title, existingDoc.get("title"))
                && areEqual(description, existingDoc.get("description"))) {
            needNewEntry = false;
        }
    }
    termDocs.close();
    reader.close();

    if (needNewEntry) {
        Document newDoc = new Document();
        newDoc.add(new Field("key", key, Field.Store.YES, Field.Index.UN_TOKENIZED));
        newDoc.add(new Field("class", "app", Field.Store.YES, Field.Index.UN_TOKENIZED));
        newDoc.add(new Field("url", url, Field.Store.YES, Field.Index.TOKENIZED));
        if (title != null)
            newDoc.add(new Field("title", title, Field.Store.YES, Field.Index.TOKENIZED));
        if (description != null)
            newDoc.add(new Field("description", description, Field.Store.YES, Field.Index.TOKENIZED));

        IndexWriter writer = null;
        try {
            writer = new IndexWriter(indexDir, analyzer, false);
            writer.deleteDocuments(new Term("key", key)); // Delete old entry, if present
            writer.addDocument(newDoc);
        } finally {
            if (writer != null)
                try {
                    writer.close();
                } catch (Exception e) {
                }
            ;
        }

        log.trace(String.format("Indexed app[url=%s,title=%s,description=%s]", url, title, description));
    }

    return needNewEntry;
}

---

From source file:com.sun.socialsite.business.impl.LuceneSearchManagerImpl.java

License:Open Source License

/**
 * @return false if the index entry was not updated because it
 * was already current; true otherwise.//from   w  w  w.ja v a2  s  .c om
 */
public boolean addToIndex(final Group group) throws IOException {

    boolean needNewEntry = true;

    String key = getKey(group);
    String handle = group.getHandle();
    String name = group.getName();
    String description = group.getDescription();

    IndexReader reader = IndexReader.open(indexDir);
    TermDocs termDocs = reader.termDocs(new Term("key", key));
    while (termDocs.next()) {
        Document existingDoc = reader.document(termDocs.doc());
        if (areEqual("group", existingDoc.get("class")) && areEqual(handle, existingDoc.get("handle"))
                && areEqual(name, existingDoc.get("name"))
                && areEqual(description, existingDoc.get("description"))) {
            needNewEntry = false;
        }
    }
    termDocs.close();
    reader.close();

    if (needNewEntry) {
        Document newDoc = new Document();
        newDoc.add(new Field("key", key, Field.Store.YES, Field.Index.UN_TOKENIZED));
        newDoc.add(new Field("class", "group", Field.Store.YES, Field.Index.UN_TOKENIZED));
        newDoc.add(new Field("handle", handle, Field.Store.YES, Field.Index.TOKENIZED));
        newDoc.add(new Field("name", name, Field.Store.YES, Field.Index.TOKENIZED));
        if (description != null)
            newDoc.add(new Field("description", description, Field.Store.YES, Field.Index.TOKENIZED));

        IndexWriter writer = null;
        try {
            writer = new IndexWriter(indexDir, analyzer, false);
            writer.deleteDocuments(new Term("key", key)); // Delete old entry, if present
            writer.addDocument(newDoc);
        } finally {
            if (writer != null)
                try {
                    writer.close();
                } catch (Exception e) {
                }
            ;
        }

        log.trace(String.format("Indexed group[handle=%s,name=%s,description=%s]", name, handle, description));
    }

    return needNewEntry;
}

---

From source file:com.sun.socialsite.business.impl.LuceneSearchManagerImpl.java

License:Open Source License

/**
 * @return false if the index entry was not updated because it
 * was already current; true otherwise./*from   w  ww  . j av  a2s . com*/
 */
public boolean addToIndex(final Profile profile) throws IOException {

    boolean needNewEntry = true;

    String key = getKey(profile);
    String userId = profile.getUserId();
    String firstName = profile.getFirstName();
    String middleName = profile.getMiddleName();
    String lastName = profile.getLastName();
    String nickName = profile.getNickName();
    String primaryEmail = profile.getPrimaryEmail();
    String displayName = profile.getDisplayName();

    IndexReader reader = IndexReader.open(indexDir);
    TermDocs termDocs = reader.termDocs(new Term("key", key));
    while (termDocs.next()) {
        Document existingDoc = reader.document(termDocs.doc());
        if (areEqual("profile", existingDoc.get("class")) && areEqual(userId, existingDoc.get("userId"))
                && areEqual(firstName, existingDoc.get("firstName"))
                && areEqual(middleName, existingDoc.get("middleName"))
                && areEqual(lastName, existingDoc.get("lastName"))
                && areEqual(nickName, existingDoc.get("nickName"))
                && areEqual(primaryEmail, existingDoc.get("primaryEmail"))
                && areEqual(displayName, existingDoc.get("displayName"))) {
            needNewEntry = false;
        }
    }
    termDocs.close();
    reader.close();

    if (needNewEntry) {
        Document newDoc = new Document();
        newDoc.add(new Field("key", key, Field.Store.YES, Field.Index.UN_TOKENIZED));
        newDoc.add(new Field("class", "profile", Field.Store.YES, Field.Index.UN_TOKENIZED));
        newDoc.add(new Field("userId", userId, Field.Store.YES, Field.Index.UN_TOKENIZED));
        if (firstName != null)
            newDoc.add(new Field("firstName", firstName, Field.Store.YES, Field.Index.TOKENIZED));
        if (middleName != null)
            newDoc.add(new Field("middleName", middleName, Field.Store.YES, Field.Index.TOKENIZED));
        if (lastName != null)
            newDoc.add(new Field("lastName", lastName, Field.Store.YES, Field.Index.TOKENIZED));
        if (nickName != null)
            newDoc.add(new Field("nickName", nickName, Field.Store.YES, Field.Index.TOKENIZED));
        if (primaryEmail != null)
            newDoc.add(new Field("primaryEmail", primaryEmail, Field.Store.YES, Field.Index.UN_TOKENIZED));
        if (displayName != null)
            newDoc.add(new Field("displayName", displayName, Field.Store.YES, Field.Index.TOKENIZED));

        IndexWriter writer = null;
        try {
            writer = new IndexWriter(indexDir, analyzer, false);
            writer.deleteDocuments(new Term("key", key)); // Delete old entry, if present
            writer.addDocument(newDoc);
        } finally {
            if (writer != null)
                try {
                    writer.close();
                } catch (Exception e) {
                }
            ;
        }

        log.trace(String.format(
                "Indexed profile[userId=%s,firstName=%s,lastName=%s,nickName=%s,primaryEmail=%s,displayName=%s]",
                userId, firstName, lastName, nickName, primaryEmail, displayName));
    }

    return needNewEntry;
}

---

From source file:com.svenjacobs.lugaene.GaeDirectoryTest.java

License:Apache License

@Test
public void wholeCycle() throws Exception {

    // Index/*ww  w . ja  v  a2 s .  c o m*/

    final Directory directory = new GaeDirectory("Test");
    final Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_44);

    final IndexWriterConfig config = GaeIndexWriterConfigHelper.create(Version.LUCENE_44, analyzer);
    final IndexWriter indexWriter = new IndexWriter(directory, config);

    final Document doc1 = new Document();

    doc1.add(new StringField(FIELD_TITLE, "Title1", Field.Store.YES));
    doc1.add(new TextField(FIELD_CONTENTS, "keyword1 keyword2 lorem ipsum", Field.Store.NO));

    indexWriter.addDocument(doc1);

    final Document doc2 = new Document();

    doc2.add(new StringField(FIELD_TITLE, "Title2", Field.Store.YES));
    doc2.add(new TextField(FIELD_CONTENTS, "keyword3 keyword4 lorem ipsum", Field.Store.NO));

    indexWriter.addDocument(doc2);

    indexWriter.close();

    // Search

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

    final BooleanQuery query = new BooleanQuery();

    query.add(new TermQuery(new Term(FIELD_TITLE, "Title1")), BooleanClause.Occur.MUST);
    query.add(new TermQuery(new Term(FIELD_CONTENTS, "lorem")), BooleanClause.Occur.MUST);

    ScoreDoc[] hits = searcher.search(query, 100).scoreDocs;

    assertThat(hits.length, is(1));
    assertThat(searcher.doc(hits[0].doc).get(FIELD_TITLE), is("Title1"));

    hits = searcher.search(new TermQuery(new Term(FIELD_CONTENTS, "lorem")), 100).scoreDocs;

    assertThat(hits.length, is(2));
    assertThat(searcher.doc(hits[0].doc).get(FIELD_TITLE), is("Title1"));
    assertThat(searcher.doc(hits[1].doc).get(FIELD_TITLE), is("Title2"));

    hits = searcher.search(new TermQuery(new Term(FIELD_CONTENTS, "keyword3")), 100).scoreDocs;

    assertThat(hits.length, is(1));
    assertThat(searcher.doc(hits[0].doc).get(FIELD_TITLE), is("Title2"));
}

---

From source file:com.sxc.lucene.analysis.codec.MetaphoneAnalyzerTest.java

License:Apache License

public void testKoolKat() throws Exception {
    RAMDirectory directory = new RAMDirectory();
    Analyzer analyzer = new MetaphoneReplacementAnalyzer();
    IndexWriterConfig indexWriterConfig = new IndexWriterConfig(Version.LUCENE_47, analyzer);
    IndexWriter writer = new IndexWriter(directory, indexWriterConfig);
    Document doc = new Document();
    doc.add(new TextField("contents", "cool cat", Field.Store.YES));
    writer.addDocument(doc);
    writer.close();/* w w w .j a  va  2  s.c o m*/
    IndexSearcher searcher = new IndexSearcher(DirectoryReader.open(directory));
    Query query = new QueryParser(Version.LUCENE_47, "contents", analyzer).parse("kool kat");
    TopDocs hits = searcher.search(query, 1);
    assertEquals(1, hits.totalHits);
    int docID = hits.scoreDocs[0].doc;
    doc = searcher.doc(docID);
    assertEquals("cool cat", doc.get("contents"));
    searcher.getIndexReader().close();
}

---

From source file:com.sxc.lucene.analysis.synonym.SynonymAnalyzerTest.java

License:Apache License

public void setUp() throws Exception {
    RAMDirectory directory = new RAMDirectory();
    IndexWriterConfig indexWriterConfig = new IndexWriterConfig(Version.LUCENE_47, synonymAnalyzer);
    IndexWriter writer = new IndexWriter(directory, indexWriterConfig);
    Document doc = new Document();
    doc.add(new TextField("content", "The quick brown fox jumps over the lazy dog", Field.Store.YES)); //#2
    writer.addDocument(doc);

    writer.close();//  w w  w . j  a  v  a 2  s  .co m

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

---

From source file:com.sxc.lucene.index.IndexingTest.java

License:Apache License

protected void setUp() throws Exception { // 1
    directory = FSDirectory.open(new File("D:/programming/lucene/indexingTest"));

    IndexWriter writer = getWriter(); // 2
    writer.deleteAll();//w ww  .  ja  v  a 2s.c  o m

    for (int i = 0; i < ids.length; i++) { // 3
        Document doc = new Document();
        doc.add(new StringField("id", ids[i], Field.Store.YES));
        doc.add(new StringField("country", unindexed[i], Field.Store.YES));
        doc.add(new TextField("contents", unstored[i], Field.Store.NO));
        doc.add(new TextField("city", text[i], Field.Store.YES));

        writer.addDocument(doc);
    }
    writer.close();
}

---

From source file:com.sxc.lucene.searching.PhraseQueryTest.java

License:Apache License

protected void setUp() throws IOException {
    dir = FSDirectory.open(new File("D:/programming/lucene/PhraseQueryTest"));
    IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_47,
            new SmartChineseAnalyzer(Version.LUCENE_47));
    config.setOpenMode(OpenMode.CREATE);
    IndexWriter writer = new IndexWriter(dir, config);

    Document doc = new Document();
    doc.add(new TextField("field", // 1
            "the quick brown fox jumped over the lazy dog", // 1
            Field.Store.YES)); // 1
    writer.addDocument(doc);
    writer.close();//w  ww  . ja va2s  . c om

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

---

• «
• 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
• »