Lucene 研究 1 座

     搜索是神奇的，世界上的知识对于个人来讲是无限的，也没有必要去追求完美。然而搜索似乎可以改变人们的生活一样，深深的扎根在现代人的生活中。因为项目原因接触了这方面的知识，于是想再走近看看清楚，作为入门，lucene似乎很被推荐。

 

献给刚刚对lucene感兴趣的人们！

 

附上我对搜索的感想： 我觉得也是蛮好理解的事情，对于所有的文件，资料，用不同的解析器对他们用不同的分词器进行分词建立索引，而搜索时建立在索引的基础上的，只要有索引，搜索变得异常简单。

 

-----------1，建立索引

注意点：不同的lucene jar包是不一样的，方法会有很大的不同，我在这里用的是2.40版

 

 

遍历文件夹下的所有文件：

 

package tool; import java.io.*; public class FileList { private static final String SEP = "/"; private static StringBuffer sb = new StringBuffer(); //返回数组 public static String[] getFiles(File f){ if(f.isDirectory()){ File[] fs = f.listFiles(); for(int i=0;i<fs.length;i++){ getFiles(fs[i]); } } else{ sb.append(f.getPath()+SEP); } String s=sb.toString(); String[] list =s.split(SEP); return list; } public static String[]getFile(String t)throws IOException{ File f = new File(t); if(f.isDirectory()){ File[] fs = f.listFiles(); for (int i = 0; i < fs.length; i++) { getFiles(fs[i]); } } else{ sb.append(f.getPath()+SEP); } String s = sb.toString(); String[] lists = s.split(SEP); return lists; } public static void main(String[] args)throws IOException{ String s[]=FileList.getFile("D:/test"); for (int i = 0; i < s.length; i++) { System.out.println(s[i]); } } }

 

 

建立文件夹下所有文件的索引：

package tool; import java.io.File; import java.io.IOException; 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.index.CorruptIndexException; import org.apache.lucene.index.IndexWriter; import org.apache.lucene.store.LockObtainFailedException; public class LoopIndexer { public static void main(String[] args) throws CorruptIndexException, LockObtainFailedException, IOException{ String indexPath="d:/loop"; Analyzer analyzer = new StandardAnalyzer(); IndexWriter writer = new IndexWriter(indexPath,analyzer,true,IndexWriter.MaxFieldLength.UNLIMITED); String[] files = FileList.getFile("d:/test"); for (int i = 0; i < files.length; i++) { Document doc = new Document(); File f = new File(files[i]); //创建Field -name String name = f.getName(); Field field = new Field("name",name,Field.Store.YES,Field.Index.ANALYZED); doc.add(field); //创建Field -content String content = FileText.getText(f); field = new Field("content",content,Field.Store.YES,Field.Index.ANALYZED); doc.add(field); //创建 -Path String path = f.getPath(); field = new Field("path",path,Field.Store.YES,Field.Index.ANALYZED); doc.add(field); System.out.println("Field"+name+"Indexed"); //添加document writer.addDocument(doc); } writer.close(); System.out.print("Loop Index Created"); } }

利用索引进行简单的查询：

package tool; import java.io.IOException; 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.index.CorruptIndexException; import org.apache.lucene.index.Term; import org.apache.lucene.queryParser.ParseException; import org.apache.lucene.queryParser.QueryParser; import org.apache.lucene.search.Hits; import org.apache.lucene.search.IndexSearcher; import org.apache.lucene.search.Query; import org.apache.lucene.search.ScoreDoc; import org.apache.lucene.search.TermQuery; import org.apache.lucene.search.TopDocCollector; import org.apache.lucene.search.TopDocs; public class BasicShearcher { public static void main(String[] args) throws CorruptIndexException, IOException, ParseException { String indexPath = "d:/loop"; String searchField = "name"; String searchValue ="马其顿"; Analyzer analyzer = new StandardAnalyzer(); IndexSearcher is = new IndexSearcher(indexPath); QueryParser q = new QueryParser(searchField,analyzer); org.apache.lucene.search.Query query = q.parse(searchValue); StringBuffer sb = new StringBuffer(); if(is!=null){ TopDocCollector collector = new TopDocCollector(8); is.search(query,collector); TopDocs top = collector.topDocs(); ScoreDoc[] docs =top.scoreDocs; System.out.println(docs.length+"----------------"); for (int i=0;i<docs.length;i++) { int docId = docs[i].doc; Document document = is.doc(docId); Field field1 = document.getField("name"); sb.append("name"+"/n"); sb.append(field1.stringValue()+"/n"); Field field2 = document.getField("content"); sb.append("content:"+"/n"); sb.append(field2.stringValue()); sb.append("=================================="+"/n"); } } is.close(); System.out.println(sb); } }

 

以上就是简单搜索功能的全部代码，以实现。