Integrating Spring 3.1 and Lucene 4

Integrating Spring 3.1 and Lucene 4 is a fairly trivial matter, but I didn’t want to use the XML configuration so utilizing the @Configuration annotation, I was able to configure the Lucene indexer, analyzer and queryParser. ┬áHere is the configuration code:

 

...

@Configuration
@PropertySource("classpath:/app.properties")
@ComponentScan(basePackages={"com.doozer"})
public class AppConfig {

    private @Value("#{appProperties['index.location']}") String indexLocation;
    private @Value("#{appProperties['index.source']}") String indexSource;
  
    @Bean(name="analyzer")
    public Analyzer getAnalyzer() {

        return new StandardAnalyzer(Version.LUCENE_40);
    }

    @Bean(name="fsDirectory")
    @DependsOn("analyzer")
    public FSDirectory getFSDirectory() throws IOException {

         File location = new File(indexLocation);

        if (!location.exists() || !location.canRead()) {
              System.out.println("Creating directory: '" +location.getAbsolutePath()+ "'");
              location.mkdirs();
         }

        return FSDirectory.open(location, new NativeFSLockFactory() );
     }


    @Bean(name="indexWriter")
    @DependsOn("fsDirectory")
    public IndexWriter getIndexWriter() throws IOException {
        IndexWriterConfig iwc = new IndexWriterConfig(Version.LUCENE_40, getAnalyzer());
        iwc.setOpenMode(OpenMode.CREATE_OR_APPEND);
         // Optional: for better indexing performance, if you
           // are indexing many documents, increase the RAM
             // buffer.  But if you do this, increase the max heap
           // size to the JVM (eg add -Xmx512m or -Xmx1g):
             //
               // iwc.setRAMBufferSizeMB(256.0);

        // NOTE: if you want to maximize search performance,
        // you can optionally call forceMerge here.  This can be
          // a terribly costly operation, so generally it's only
        // worth it when your index is relatively static (ie
           // you're done adding documents to it):
           //
          // writer.forceMerge(1);

        IndexWriter writer = null;
     try {
        writer = new IndexWriter(getFSDirectory(), iwc);
        indexDocs(writer,  new File(indexSource));

     } catch (Throwable t) {

         System.out.println("Unable to create IndexWriter!: " + t.getMessage());
         t.printStackTrace();

     }

        return writer;
    }




    @Bean(name="indexSearcher")
    @DependsOn("indexWriter")
    public IndexSearcher getIndexSearcher() throws IOException {

        return new IndexSearcher(DirectoryReader.open(getFSDirectory()));
    }



    @Bean(name="queryParser")
    @DependsOn("analyzer")
    public StandardQueryParser getQueryParser() throws IOException {

        return new StandardQueryParser(getAnalyzer());
    }

 
    static void indexDocs(IndexWriter writer, File file)  throws IOException {
      // do not try to index files that cannot be read
       if (file.canRead()) {
          if (file.isDirectory()) {
            String[] files = file.list();
            // an IO error could occur
             if (files != null) {
              for (int i = 0; i < files.length; i++) {
                indexDocs(writer, new File(file, files[i]));
              }
            }
          } else {

            FileInputStream fis;
           try {
              fis = new FileInputStream(file);
            } catch (FileNotFoundException fnfe) {
              // at least on windows, some temporary files raise this exception with an "access denied" message
              // checking if the file can be read doesn't help
              return;
            }

           try {

              // 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.getPath(), 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", file.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(fis, "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.getPath()), doc);
              }

            } finally {
              fis.close();
            }
         }
       }
    }
}


...

@Configurable
public class App
{

    @Autowired
    public MongoOperations mongoOperation;
    @Autowired
    public StorageService storageService;

    ApplicationContext ctx;

    public App() {

      ctx =  new AnnotationConfigApplicationContext(AppConfig.class);

About these ads

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s