Example usage for org.apache.lucene.index IndexWriterConfig IndexWriterConfig

Introduction

In this page you can find the example usage for org.apache.lucene.index IndexWriterConfig IndexWriterConfig.

Prototype

public IndexWriterConfig(Analyzer analyzer) 

Source Link

Document

Creates a new config that with the provided Analyzer .

Usage

From source file:com.github.lucene.store.jdbc.AbstractJdbcDirectoryITest.java

License:Apache License

protected void addDocuments(final Directory directory, final OpenMode openMode, final boolean useCompoundFile,
        final Collection<String> docs) throws IOException {
    final IndexWriterConfig config = new IndexWriterConfig(analyzer);
    config.setOpenMode(OpenMode.CREATE);
    config.setUseCompoundFile(useCompoundFile);

    final DirectoryTemplate template = new DirectoryTemplate(directory);
    template.execute(new DirectoryTemplate.DirectoryCallbackWithoutResult() {
        @Override//from   w  w w .  j  a  v a2s.  co m
        public void doInDirectoryWithoutResult(final Directory dir) throws IOException {
            final IndexWriter writer = new IndexWriter(dir, config);
            for (final Object element : docs) {
                final Document doc = new Document();
                final String word = (String) element;
                // FIXME: review
                // doc.add(new Field("keyword", word, Field.Store.YES,
                // Field.Index.UN_TOKENIZED));
                // doc.add(new Field("unindexed", word, Field.Store.YES,
                // Field.Index.NO));
                // doc.add(new Field("unstored", word, Field.Store.NO,
                // Field.Index.TOKENIZED));
                // doc.add(new Field("text", word, Field.Store.YES,
                // Field.Index.TOKENIZED));
                doc.add(new StringField("keyword", word, Field.Store.YES));
                doc.add(new StringField("unindexed", word, Field.Store.YES));
                doc.add(new StringField("unstored", word, Field.Store.NO));
                doc.add(new StringField("text", word, Field.Store.YES));
                writer.addDocument(doc);
            }

            // FIXME: review
            // writer.optimize();
            writer.close();
        }
    });
}

---

From source file:com.github.mosuka.apache.lucene.example.cmd.AddCommand.java

License:Apache License

@Override
public void execute(Map<String, Object> attrs) {
    Map<String, Object> responseMap = new LinkedHashMap<String, Object>();

    String responseJSON = null;/*from  w ww . j a va  2  s.  c o  m*/
    Directory indexDir = null;
    IndexWriter writer = null;

    try {
        String index = (String) attrs.get("index");
        String uniqueId = (String) attrs.get("unique_id");
        String text = (String) attrs.get("text");

        indexDir = FSDirectory.open(new File(index).toPath());

        Document document = LuceneExampleUtil.createDocument(uniqueId, text);

        IndexWriterConfig config = new IndexWriterConfig(LuceneExampleUtil.createAnalyzerWrapper());
        config.setOpenMode(OpenMode.CREATE_OR_APPEND);

        writer = new IndexWriter(indexDir, config);
        writer.addDocument(document);
        writer.commit();

        responseMap.put("status", 0);
        responseMap.put("message", "OK");
    } catch (IOException e) {
        responseMap.put("status", 1);
        responseMap.put("message", e.getMessage());
    } finally {
        try {
            if (writer != null) {
                writer.close();
            }
        } catch (IOException e) {
            responseMap.put("status", 1);
            responseMap.put("message", e.getMessage());
        }
        try {
            if (indexDir != null) {
                indexDir.close();
            }
        } catch (IOException e) {
            responseMap.put("status", 1);
            responseMap.put("message", e.getMessage());
        }
    }

    try {
        ObjectMapper mapper = new ObjectMapper();
        responseJSON = mapper.writeValueAsString(responseMap);
    } catch (IOException e) {
        responseJSON = String.format("{\"status\":1, \"message\":\"%s\"}", e.getMessage());
    }
    System.out.println(responseJSON);
}

---

From source file:com.github.mosuka.apache.lucene.example.cmd.DeleteCommand.java

License:Apache License

@Override
public void execute(Map<String, Object> attrs) {
    Map<String, Object> responseMap = new LinkedHashMap<String, Object>();

    String responseJSON = null;//from ww  w. ja v  a 2  s .  c o m
    Directory indexDir = null;
    IndexWriter writer = null;

    try {
        String index = (String) attrs.get("index");
        String uniqueId = (String) attrs.get("unique_id");

        indexDir = FSDirectory.open(new File(index).toPath());

        IndexWriterConfig config = new IndexWriterConfig(LuceneExampleUtil.createAnalyzerWrapper());
        config.setOpenMode(OpenMode.CREATE_OR_APPEND);

        writer = new IndexWriter(indexDir, config);
        writer.deleteDocuments(new Term("id", uniqueId));
        writer.commit();

        responseMap.put("status", 0);
        responseMap.put("message", "OK");
    } catch (IOException e) {
        responseMap.put("status", 1);
        responseMap.put("message", e.getMessage());
    } finally {
        try {
            if (writer != null) {
                writer.close();
            }
        } catch (IOException e) {
            responseMap.put("status", 1);
            responseMap.put("message", e.getMessage());
        }
        try {
            if (indexDir != null) {
                indexDir.close();
            }
        } catch (IOException e) {
            responseMap.put("status", 1);
            responseMap.put("message", e.getMessage());
        }
    }

    try {
        ObjectMapper mapper = new ObjectMapper();
        responseJSON = mapper.writeValueAsString(responseMap);
    } catch (IOException e) {
        responseJSON = String.format("{\"status\":1, \"message\":\"%s\"}", e.getMessage());
    }
    System.out.println(responseJSON);
}

---

From source file:com.github.mosuka.apache.lucene.example.cmd.UpdateCommand.java

License:Apache License

@Override
public void execute(Map<String, Object> attrs) {
    Map<String, Object> responseMap = new LinkedHashMap<String, Object>();

    String responseJSON = null;//from   w  w  w .  j  a va2 s  .  com
    Directory indexDir = null;
    IndexWriter writer = null;

    try {
        String index = (String) attrs.get("index");
        String uniqueId = (String) attrs.get("unique_id");
        String text = (String) attrs.get("text");

        indexDir = FSDirectory.open(new File(index).toPath());

        Document document = LuceneExampleUtil.createDocument(uniqueId, text);

        IndexWriterConfig config = new IndexWriterConfig(LuceneExampleUtil.createAnalyzerWrapper());
        config.setOpenMode(OpenMode.CREATE_OR_APPEND);

        writer = new IndexWriter(indexDir, config);
        writer.updateDocument(new Term("id", document.get("id")), document);
        writer.commit();

        responseMap.put("status", 0);
        responseMap.put("message", "OK");
    } catch (IOException e) {
        responseMap.put("status", -1);
        responseMap.put("message", e.getMessage());
    } finally {
        try {
            if (writer != null) {
                writer.close();
            }
        } catch (IOException e) {
            responseMap.put("status", 1);
            responseMap.put("message", e.getMessage());
        }
        try {
            if (indexDir != null) {
                indexDir.close();
            }
        } catch (IOException e) {
            responseMap.put("status", 1);
            responseMap.put("message", e.getMessage());
        }
    }

    try {
        ObjectMapper mapper = new ObjectMapper();
        responseJSON = mapper.writeValueAsString(responseMap);
    } catch (IOException e) {
        responseJSON = String.format("{\"status\":1, \"message\":\"%s\"}", e.getMessage());
    }
    System.out.println(responseJSON);
}

---

From source file:com.github.msarhan.lucene.ArabicRootExtractorAnalyzerTests.java

License:Open Source License

@Test
public void testArabicRootIndex() throws IOException, ParseException, URISyntaxException {
    Directory index = new RAMDirectory();
    ArabicRootExtractorAnalyzer analyzer = new ArabicRootExtractorAnalyzer();
    IndexWriterConfig config = new IndexWriterConfig(analyzer);

    final AtomicInteger id = new AtomicInteger(0);
    IndexWriter w = new IndexWriter(index, config);
    URL url = ArabicRootExtractorStemmer.class.getClassLoader()
            .getResource("com/github/msarhan/lucene/fateha.txt");

    if (url == null) {
        fail("Not able to load data file!");
    }// w ww  . ja v a 2  s .c om

    Files.lines(new File(url.toURI()).toPath())
            .forEach(line -> addDoc(w, line, String.valueOf(id.incrementAndGet())));
    w.close();

    String querystr = "";
    Query q = new QueryParser("title", analyzer).parse(querystr);

    int hitsPerPage = 10;
    IndexReader reader = DirectoryReader.open(index);
    IndexSearcher searcher = new IndexSearcher(reader);
    TopDocs docs = searcher.search(q, hitsPerPage);

    //print(searcher, docs);

    assertEquals(2, docs.scoreDocs.length);
}

---

From source file:com.github.msarhan.lucene.ArabicRootExtractorAnalyzerTests.java

License:Open Source License

@Test
public void testInlineStemmer() throws IOException, ParseException {

    //Initialize the index
    Directory index = new RAMDirectory();
    Analyzer analyzer = new ArabicRootExtractorAnalyzer();
    IndexWriterConfig config = new IndexWriterConfig(analyzer);
    IndexWriter writer = new IndexWriter(index, config);

    Document doc = new Document();
    doc.add(new StringField("number", "1", Field.Store.YES));
    doc.add(new TextField("title", "?? ? ? ??",
            Field.Store.YES));/*from w w w  . jav  a2  s  . co  m*/
    writer.addDocument(doc);

    doc = new Document();
    doc.add(new StringField("number", "2", Field.Store.YES));
    doc.add(new TextField("title", "? ?? ? ?",
            Field.Store.YES));
    writer.addDocument(doc);

    doc = new Document();
    doc.add(new StringField("number", "3", Field.Store.YES));
    doc.add(new TextField("title", "? ??", Field.Store.YES));
    writer.addDocument(doc);
    writer.close();
    //~

    //Query the index
    String queryStr = "";
    Query query = new QueryParser("title", analyzer).parse(queryStr);

    int hitsPerPage = 5;
    IndexReader reader = DirectoryReader.open(index);
    IndexSearcher searcher = new IndexSearcher(reader);
    TopDocs docs = searcher.search(query, hitsPerPage, Sort.INDEXORDER);

    ScoreDoc[] hits = docs.scoreDocs;
    //~

    //Print results
    /*
    System.out.println("Found " + hits.length + " hits:");
    for (ScoreDoc hit : hits) {
       int docId = hit.doc;
       Document d = searcher.doc(docId);
       System.out.printf("\t(%s): %s\n", d.get("number"), d.get("title"));
    }
    */
    //~

}

---

From source file:com.github.s4ke.moar.lucene.query.test.BaseLuceneTest.java

License:Open Source License

public void clearIndex() throws IOException {
    System.out.println("clearing index");
    {/*w w w. java2 s.  c o  m*/
        WhitespaceAnalyzer analyzer = new WhitespaceAnalyzer();

        IndexWriterConfig iwc = new IndexWriterConfig(analyzer);
        try (IndexWriter iw = new IndexWriter(this.d, iwc)) {
            iw.deleteAll();
        }
    }
}

---

From source file:com.github.s4ke.moar.lucene.query.test.BaseLuceneTest.java

License:Open Source License

public void setupBackRefData() throws IOException {
    this.clearIndex();

    System.out.println("writing into index");
    WhitespaceAnalyzer analyzer = new WhitespaceAnalyzer();

    IndexWriterConfig iwc = new IndexWriterConfig(analyzer);
    try (IndexWriter iw = new IndexWriter(this.d, iwc)) {

        for (int i = 0; i < BACK_REF_DOC_COUNT; ++i) {
            Document doc = createDocument();
            int repeatCount = random.nextInt(100) + 1;
            Field idField = new Field("id", String.valueOf(i), ID_FIELD_TYPE);
            Field field = new Field("tag", randomString(WORD_COUNT_PER_DOCUMENT) + " "
                    + repeat("a", repeatCount) + "b" + repeat("a", repeatCount), TAGS_FIELD_TYPE);
            doc.add(field);/*from www  .  j a v a  2s.  c om*/
            doc.add(idField);
            iw.addDocument(doc);
            if (i % 100 == 0) {
                System.out.println(i);
            }

        }
        iw.commit();
    }
    System.out.println("finished setting up index data");
}

---

From source file:com.github.s4ke.moar.lucene.query.test.BaseLuceneTest.java

License:Open Source License

public IndexWriterConfig getIwc() {
    WhitespaceAnalyzer analyzer = new WhitespaceAnalyzer();
    return new IndexWriterConfig(analyzer);
}

---

From source file:com.github.tteofili.looseen.MinHashClassifier.java

License:Apache License

public MinHashClassifier(IndexReader reader, String textField, String categoryField, int min, int hashCount,
        int hashSize) {
    this.min = min;
    this.hashCount = hashCount;
    this.hashSize = hashSize;
    try {//from   w  w  w  . ja v a2s.  com
        Analyzer analyzer = createMinHashAnalyzer(min, hashCount, hashSize);
        IndexWriterConfig config = new IndexWriterConfig(analyzer);
        directory = new RAMDirectory();
        IndexWriter writer = new IndexWriter(directory, config);
        for (int i = 0; i < reader.maxDoc(); i++) {
            Document document = new Document();
            Document d = reader.document(i);
            String textValue = d.getField(textField).stringValue();
            String categoryValue = d.getField(categoryField).stringValue();
            document.add(new TextField(TEXT_FIELD, textValue, Field.Store.NO));
            document.add(new StringField(CLASS_FIELD, categoryValue, Field.Store.YES));
            writer.addDocument(document);
        }
        writer.commit();
        writer.close();
    } catch (IOException e) {
        throw new RuntimeException(e);
    }
    BooleanQuery.setMaxClauseCount(Integer.MAX_VALUE);
}

---

• «
• 1
• 2
• 3
• 4
• 5
• 6
• 7
• 8
• 9
• 10
• 11
• 12
• 13
• 14
• 15
• 16
• 17
• 18
• 19
• »