package org.elasticsearch.api.demo.lucene; import org.apache.lucene.analysis.Analyzer; import org.apache.lucene.analysis.standard.StandardAnalyzer; import org.apache.lucene.document.*; import org.apache.lucene.index.IndexWriter; import org.apache.lucene.index.IndexWriterConfig; import org.apache.lucene.index.Term; import org.apache.lucene.store.Directory; import org.apache.lucene.store.FSDirectory; import java.io.BufferedReader; import java.io.IOException; import java.io.InputStream; import java.io.InputStreamReader; import java.nio.charset.StandardCharsets; import java.nio.file.*; import java.nio.file.attribute.BasicFileAttributes; import java.util.Date; /** * lucene官方例子 * @see <a href='https://lucene.apache.org/core/6_6_0/demo/src-html/org/apache/lucene/demo/IndexFiles.html'></a> * @auhthor [email protected] * @since . 2017-08-23 */ public class IndexFiles { private IndexFiles() {} public static void main(String[] args) { String indexPath = "index"; String docsPath = "/Users/admin/github/elasticsearch-full/JAVA-QUERY-API/"; boolean create = true; final Path docDir = Paths.get(docsPath); if (!Files.isReadable(docDir)) { System.out.println("Document directory '" + docDir.toAbsolutePath() + "' does not exist or is not readable, please check the path"); System.exit(1); } Date start = new Date(); try { System.out.println("Indexing to directory '" + indexPath + "'..."); Directory dir = FSDirectory.open(Paths.get(indexPath)); Analyzer analyzer = new StandardAnalyzer(); IndexWriterConfig iwc = new IndexWriterConfig(analyzer); if (create) { iwc.setOpenMode(IndexWriterConfig.OpenMode.CREATE); } else { iwc.setOpenMode(IndexWriterConfig.OpenMode.CREATE_OR_APPEND); } IndexWriter writer = new IndexWriter(dir, iwc); indexDocs(writer, docDir); writer.close(); Date end = new Date(); System.out.println(end.getTime() - start.getTime() + " total milliseconds"); } catch (Exception e) { System.out.println(" caught a " + e.getClass() + "\n with message: " + e.getMessage()); } } static void indexDocs(final IndexWriter writer, Path path) throws IOException { if (Files.isDirectory(path)) { Files.walkFileTree(path, new SimpleFileVisitor<Path>() { @Override public FileVisitResult visitFile(Path file, BasicFileAttributes attrs) throws IOException { try { indexDoc(writer, file, attrs.lastModifiedTime().toMillis()); } catch (IOException ignore) { // don't index files that can't be read. } return FileVisitResult.CONTINUE; } }); } else { indexDoc(writer, path, Files.getLastModifiedTime(path).toMillis()); } } static void indexDoc(IndexWriter writer, Path file, long lastModified) throws IOException { try (InputStream stream = Files.newInputStream(file)) { Document doc = new Document(); Field pathField = new StringField("path", file.toString(), Field.Store.YES); doc.add(pathField); doc.add(new LongPoint("modified", lastModified)); doc.add(new TextField("contents", new BufferedReader(new InputStreamReader(stream, StandardCharsets.UTF_8)))); if (writer.getConfig().getOpenMode() == IndexWriterConfig.OpenMode.CREATE) { System.out.println("adding " + file); writer.addDocument(doc); System.out.println("updating " + file); writer.updateDocument(new Term("path", file.toString()), doc); } } } }