Lucene全文檢索引擎
阿新 • • 發佈:2017-11-10
getname 通過 nal dem 檢索 數據庫 project cep 關閉
<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd"> <modelVersion>4.0.0</modelVersion> <groupId>demo.lucene</groupId> <artifactId>Lucene01</artifactId> <version>0.0.1-SNAPSHOT</version> <build/> <dependencies> <!-- lucene核心包 --> <dependency> <groupId>org.apache.lucene</groupId> <artifactId>lucene-core</artifactId> <version>5.3.1</version> </dependency> <!-- lucene查詢解析包 --> <dependency> <groupId>org.apache.lucene</groupId> <artifactId>lucene-queryparser</artifactId> <version>5.3.1</version> </dependency> <!-- lucene解析器包 --> <dependency> <groupId>org.apache.lucene</groupId> <artifactId>lucene-analyzers-common</artifactId> <version>5.3.1</version> </dependency> </dependencies> </project>
import java.io.File; import java.io.FileReader; import java.nio.file.Paths; import org.apache.lucene.analysis.Analyzer; import org.apache.lucene.analysis.standard.StandardAnalyzer; import org.apache.lucene.document.Document; import org.apache.lucene.document.Field; import org.apache.lucene.document.TextField; import org.apache.lucene.index.IndexWriter; import org.apache.lucene.index.IndexWriterConfig; import org.apache.lucene.store.Directory; import org.apache.lucene.store.FSDirectory; /** * 建立索引的類 * @author Ni Shengwu * */ public class Indexer { private IndexWriter writer; //寫索引實例 //構造方法,實例化IndexWriter public Indexer(String indexDir) throws Exception { Directory dir = FSDirectory.open(Paths.get(indexDir)); Analyzer analyzer = new StandardAnalyzer(); //標準分詞器,會自動去掉空格啊,is a the等單詞 IndexWriterConfig config = new IndexWriterConfig(analyzer); //將標準分詞器配到寫索引的配置中 writer = new IndexWriter(dir, config); //實例化寫索引對象 } //關閉寫索引 public void close() throws Exception { writer.close(); } //索引指定目錄下的所有文件 public int indexAll(String dataDir) throws Exception { File[] files = new File(dataDir).listFiles(); //獲取該路徑下的所有文件 for(File file : files) { indexFile(file); //調用下面的indexFile方法,對每個文件進行索引 } return writer.numDocs(); //返回索引的文件數 } //索引指定的文件 private void indexFile(File file) throws Exception { System.out.println("索引文件的路徑:" + file.getCanonicalPath()); Document doc = getDocument(file); //獲取該文件的document writer.addDocument(doc); //調用下面的getDocument方法,將doc添加到索引中 } //獲取文檔,文檔裏再設置每個字段,就類似於數據庫中的一行記錄 private Document getDocument(File file) throws Exception{ Document doc = new Document(); //添加字段 doc.add(new TextField("contents", new FileReader(file))); //添加內容 doc.add(new TextField("fileName", file.getName(), Field.Store.YES)); //添加文件名,並把這個字段存到索引文件裏 doc.add(new TextField("fullPath", file.getCanonicalPath(), Field.Store.YES)); //添加文件路徑 return doc; } public static void main(String[] args) { String indexDir = "D:\\lucene"; //將索引保存到的路徑 String dataDir = "D:\\lucene\\data"; //需要索引的文件數據存放的目錄 Indexer indexer = null; int indexedNum = 0; long startTime = System.currentTimeMillis(); //記錄索引開始時間 try { indexer = new Indexer(indexDir); indexedNum = indexer.indexAll(dataDir); } catch (Exception e) { e.printStackTrace(); } finally { try { indexer.close(); } catch (Exception e) { e.printStackTrace(); } } long endTime = System.currentTimeMillis(); //記錄索引結束時間 System.out.println("索引耗時" + (endTime-startTime) + "毫秒"); System.out.println("共索引了" + indexedNum + "個文件"); } }
import java.nio.file.Paths; import org.apache.lucene.analysis.Analyzer; import org.apache.lucene.analysis.standard.StandardAnalyzer; import org.apache.lucene.document.Document; import org.apache.lucene.index.DirectoryReader; import org.apache.lucene.index.IndexReader; import org.apache.lucene.queryparser.classic.QueryParser; import org.apache.lucene.search.IndexSearcher; import org.apache.lucene.search.Query; import org.apache.lucene.search.ScoreDoc; import org.apache.lucene.search.TopDocs; import org.apache.lucene.store.Directory; import org.apache.lucene.store.FSDirectory; public class Searcher { public static void search(String indexDir, String q) throws Exception { Directory dir = FSDirectory.open(Paths.get(indexDir)); //獲取要查詢的路徑,也就是索引所在的位置 IndexReader reader = DirectoryReader.open(dir); IndexSearcher searcher = new IndexSearcher(reader); Analyzer analyzer = new StandardAnalyzer(); //標準分詞器,會自動去掉空格啊,is a the等單詞 QueryParser parser = new QueryParser("contents", analyzer); //查詢解析器 Query query = parser.parse(q); //通過解析要查詢的String,獲取查詢對象 long startTime = System.currentTimeMillis(); //記錄索引開始時間 TopDocs docs = searcher.search(query, 10);//開始查詢,查詢前10條數據,將記錄保存在docs中 long endTime = System.currentTimeMillis(); //記錄索引結束時間 System.out.println("匹配" + q + "共耗時" + (endTime-startTime) + "毫秒"); System.out.println("查詢到" + docs.totalHits + "條記錄"); for(ScoreDoc scoreDoc : docs.scoreDocs) { //取出每條查詢結果 Document doc = searcher.doc(scoreDoc.doc); //scoreDoc.doc相當於docID,根據這個docID來獲取文檔 System.out.println(doc.get("fullPath")); //fullPath是剛剛建立索引的時候我們定義的一個字段 } reader.close(); } public static void main(String[] args) { String indexDir = "D:\\lucene"; String q = "generate-maven-artifacts"; //查詢這個字符串 try { search(indexDir, q); } catch (Exception e) { e.printStackTrace(); } } }
pom.xml
Lucene全文檢索引擎