lucene3使用示例
lucene插入document建立索引代码
import java.io.File;import java.io.FileInputStream;import java.io.IOException;import java.io.InputStreamReader;import java.util.List;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.Directory;import org.apache.lucene.store.FSDirectory;import org.apache.lucene.store.LockObtainFailedException;import org.apache.lucene.util.Version;public class DocInsert {private static IndexWriter indexwrite = null;static{ Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_CURRENT); // Store the index in memory:// Directory directory = new RAMDirectory(); // To store an index on disk, use this instead: try { Directory directory = FSDirectory.open(new File("E:\\output\\lucence\\index")); indexwrite = new IndexWriter(directory, analyzer, true, new IndexWriter.MaxFieldLength(25000));} catch (CorruptIndexException e) {// TODO Auto-generated catch blocke.printStackTrace();} catch (LockObtainFailedException e) {// TODO Auto-generated catch blocke.printStackTrace();} catch (IOException e) {// TODO Auto-generated catch blocke.printStackTrace();} }public static void createDoc() throws CorruptIndexException, IOException{List<String> datalist = org.apache.commons.io.IOUtils.readLines(new InputStreamReader(new FileInputStream(new File("E:\\output\\lucence\\data\\data.txt")),"GBK")); for(String str:datalist){Document doc = new Document(); String[] text = str.split("\t"); if(text.length < 2){ continue; } doc.add(new Field("context", text[1], Field.Store.YES, Field.Index.ANALYZED)); doc.add(new Field("id", text[0], Field.Store.YES, Field.Index.ANALYZED)); indexwrite.addDocument(doc); }}public static void main(String[] args) throws CorruptIndexException, IOException {createDoc();indexwrite.commit();indexwrite.close();}}?
数据格式为：
??4915779球泡灯套件
491577715018506651求购三星i559 i569 i5794915775采购雪纺格子印花面料4915773汽泡信封袋4915771电泳加工49157696405 2RS4915767蓝色丁腈手套4915765采购求购KO3-15T八角4915763胸杯4915761封箱胶带49157596404 2RS4915757Ipad 车载支架4915755礼品,文具,墙贴,基督教礼品4915753品牌内衣4915751聚丙烯酸4915749餐饮消毒毛巾、湿巾4915747提花49157456403 2RS4915743采购如:葛根粉丝、蕨根粉丝、南瓜粉丝、野菜粉丝、香菇粉丝等4915741二手摩托车4915739急需采购PVC特殊袋子4915737女士T恤4915735烤弯镀膜玻璃4915731批发野生羊肚菌4915733ABS管道粘结剂 ABS胶
?
检索代码示例如下：
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.index.IndexReader;import org.apache.lucene.queryParser.ParseException;import org.apache.lucene.queryParser.QueryParser;import org.apache.lucene.search.IndexSearcher;import org.apache.lucene.search.Query;import org.apache.lucene.search.ScoreDoc;import org.apache.lucene.store.Directory;import org.apache.lucene.store.FSDirectory;import org.apache.lucene.util.Version;public class DocSearch {private static IndexSearcher isearcher = null;public static void search(String key) throws IOException, ParseException{ Directory directory = FSDirectory.open(new File("E:\\output\\lucence\\index")); // Now search the index: IndexReader ireader = IndexReader.open(directory); // read-only=true isearcher = new IndexSearcher(ireader); // Parse a simple query that searches for "text": Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_CURRENT); QueryParser parser = new QueryParser(Version.LUCENE_CURRENT,"context", analyzer); Query query = parser.parse(key); ScoreDoc[] hits = isearcher.search(query, null, 1000).scoreDocs; // Iterate through the results: for (int i = 0; i < hits.length; i++) { Document hitDoc = isearcher.doc(hits[i].doc); System.out.println(hitDoc.getValues("id")[0] + "\t" + hitDoc.getValues("context")[0] + "\t" + hits[i].score); }}public static void main(String[] args) throws IOException, ParseException {search("旧水泥袋");isearcher.close();}}?执行结果：
??4801857采购旧编织袋、旧水泥袋4.0172114
4829927水泥1.75855854903199采购水泥电阻1.05513514815595求购水泥输送链条和提升机0.7034234448612331万5 潜水料啤酒手提包 手提袋0.479820884815637大量采购包装用的编织袋（新的旧的，有无商标皆可）0.479132624915391铁泥 铁灰0.462506354889169废旧砂轮0.399939724903163软陶泥，超轻粘土0.346879784801611水泵0.301146334801911手袋0.298629764889443水锈石 上水石 吸水石0.26080044861275足浴袋 泡脚袋 异形袋0.258620954801871手提袋制袋机0.253395744915383回收库存废旧油墨油漆0.249962334903189回收库存旧油漆134630485720.249962334903187求购废旧油漆油墨134630485720.249962334903175求购库存旧化工树脂0.249962334903245污水泵0.240917074801705出水霜0.240917074874727服裝紙袋0.23890384829965工作证袋0.23890384815531棉布袋0.23890384815479冷敷冰袋0.2389038
?
?
可以看到这个检索结果：
1.默认的分词是最终分成一个汉字，
2.匹配出来的分数还是比较靠谱。
?
?
?
如何用lucene设计一个搜索引擎如何考虑的问题太多：
1.如何设计一个分布式查询；
2.数据增量更新，全量更新如何处理，不影响当前的查询引擎；
3.性能如何保证，更好地利用缓存，分布式？
4.如果设计得更通用，需要添加字段，添加排序字段，统计字段的时候能够做到快速满足需求？
5.分词模块的选择和处理
。。。
?
后续慢慢研究