Lucene学习
近来项目需要使用Lucene，工作之余上网学习了下相关内容，做个笔记
1.创建索引
步骤：创建IndexWriter
Java代码
IndexWriterwriter=newIndexWriter(
newNIOFSDirectory(newFile(path)),newStandardAnalyzer(
Version.LUCENE_30),MaxFieldLength.LIMITED);
IndexWriterwriter=newIndexWriter(
newNIOFSDirectory(newFile(path)),newStandardAnalyzer(
Version.LUCENE_30),MaxFieldLength.LIMITED);
创建Document
创建Field包含field名和field值
将Field通过Document的add方法添加到Document中
Java代码
Documentdoc=newDocument();
doc.add(newField("text","Itisatextarea",Store.YES,
Index.ANALYZED_NO_NORMS));
doc.add(newField("info","ItisaInfomationarea",Store.YES,
Index.ANALYZED_NO_NORMS));
Documentdoc=newDocument();
doc.add(newField("text","Itisatextarea",Store.YES,
Index.ANALYZED_NO_NORMS));
doc.add(newField("info","ItisaInfomationarea",Store.YES,
Index.ANALYZED_NO_NORMS));
将Document通过IndexWriter的addDocument方法添加到IndexWriter中
关闭IndexWriter
Java代码
writer.addDocument(doc);writer.close();
writer.addDocument(doc);writer.close();
2从索引中根据关键字查询
创建IndexSearcher
Java代码
IndexSearchersearcher=newIndexSearcher(newNIOFSDirectory(newFile(
path)));
IndexSearchersearcher=newIndexSearcher(newNIOFSDirectory(newFile(
path)));
创建Query
Java代码
Queryquery=newQueryParser(Version.LUCENE_30,field,
newStandardAnalyzer(Version.LUCENE_30)).parse(keyword);
Queryquery=newQueryParser(Version.LUCENE_30,field,
newStandardAnalyzer(Version.LUCENE_30)).parse(keyword);
通过IndexSearcher的search方法查找关键字，使用TopDocs封装结果集
Java代码
TopDocsdocs=searcher.search(query,10);
TopDocsdocs=searcher.search(query,10);
全部代码：(包换了合并内存索引到硬盘索引中)
Java代码
importjava.io.File;
importorg.apache.lucene.analysis.standard.StandardAnalyzer;
importorg.apache.lucene.document.Document;
importorg.apache.lucene.document.Field;
importorg.apache.lucene.document.Field.Index;
importorg.apache.lucene.document.Field.Store;
importorg.apache.lucene.index.IndexReader;
importorg.apache.lucene.index.IndexWriter;
importorg.apache.lucene.index.IndexWriter.MaxFieldLength;
importorg.apache.lucene.queryParser.QueryParser;
importorg.apache.lucene.search.IndexSearcher;
importorg.apache.lucene.search.Query;
importorg.apache.lucene.search.ScoreDoc;
importorg.apache.lucene.search.TopDocs;
importorg.apache.lucene.store.NIOFSDirectory;
importorg.apache.lucene.store.RAMDirectory;
importorg.apache.lucene.util.Version;
publicclassTestLucen{
publicstaticfinalStringpath="E:\\workspaces\\lucene\\index";
publicstaticvoidmain(String[]args)throwsException{
writeIndex();
readIndex("text","area");
}
publicstaticvoidwriteIndex()throwsException{
//硬盘索引
IndexWriterwriter=newIndexWriter(
newNIOFSDirectory(newFile(path)),newStandardAnalyzer(
Version.LUCENE_30),MaxFieldLength.LIMITED);
//Ram索引
RAMDirectoryram=newRAMDirectory();
IndexWriterramwriter=newIndexWriter(ram,newStandardAnalyzer(
Version.LUCENE_30),MaxFieldLength.LIMITED);
Documentdoc=newDocument();
Documentdoc1=newDocument();
doc.add(newField("text","Itisatextarea",Store.YES,
Index.ANALYZED_NO_NORMS));
doc.add(newField("info","ItisaInfomationarea",Store.YES,
Index.ANALYZED_NO_NORMS));
writer.addDocument(doc);
doc1.add(newField("text","itisanotherarea",Store.YES,
Index.ANALYZED));
ramwriter.addDocument(doc1);
ramwriter.optimize();
ramwriter.close();
//将Ram索引合并到硬盘索引上，必须先调用ram的close方法
writer.addIndexes(IndexReader.open(ram));
writer.optimize();
writer.close();
}
publicstaticvoidreadIndex(Stringfield,Stringkeyword)throwsException{
IndexSearchersearcher=newIndexSearcher(newNIOFSDirectory(newFile(
path)));
Queryquery=newQueryParser(Version.LUCENE_30,field,
newStandardAnalyzer(Version.LUCENE_30)).parse(keyword);
TopDocsdocs=searcher.search(query,10);
System.out.println("查找到"+docs.totalHits+"个\n对应的text为：");
ScoreDoc[]doc=docs.scoreDocs;
for(ScoreDocd:doc){
Documentdocu=searcher.doc(d.doc);
System.out.println(docu.get(field));
}
}
}
importjava.io.File;
importorg.apache.lucene.analysis.standard.StandardAnalyzer;
importorg.apache.lucene.document.Document;
importorg.apache.lucene.document.Field;
importorg.apache.lucene.document.Field.Index;
importorg.apache.lucene.document.Field.Store;
importorg.apache.lucene.index.IndexReader;
importorg.apache.lucene.index.IndexWriter;
importorg.apache.lucene.index.IndexWriter.MaxFieldLength;
importorg.apache.lucene.queryParser.QueryParser;
importorg.apache.lucene.search.IndexSearcher;
importorg.apache.lucene.search.Query;
importorg.apache.lucene.search.ScoreDoc;
importorg.apache.lucene.search.TopDocs;
importorg.apache.lucene.store.NIOFSDirectory;
importorg.apache.lucene.store.RAMDirectory;
importorg.apache.lucene.util.Version;
publicclassTestLucen{
publicstaticfinalStringpath="E:\\workspaces\\lucene\\index";
publicstaticvoidmain(String[]args)throwsException{
writeIndex();
readIndex("text","area");
}
publicstaticvoidwriteIndex()throwsException{
//硬盘索引
IndexWriterwriter=newIndexWriter(
newNIOFSDirectory(newFile(path)),newStandardAnalyzer(
Version.LUCENE_30),MaxFieldLength.LIMITED);
//Ram索引
RAMDirectoryram=newRAMDirectory();
IndexWriterramwriter=newIndexWriter(ram,newStandardAnalyzer(
Version.LUCENE_30),MaxFieldLength.LIMITED);
Documentdoc=newDocument();
Documentdoc1=newDocument();
doc.add(newField("text","Itisatextarea",Store.YES,
Index.ANALYZED_NO_NORMS));
doc.add(newField("info","ItisaInfomationarea",Store.YES,
Index.ANALYZED_NO_NORMS));
writer.addDocument(doc);
doc1.add(newField("text","itisanotherarea",Store.YES,
Index.ANALYZED));
ramwriter.addDocument(doc1);
ramwriter.optimize();
ramwriter.close();
//将Ram索引合并到硬盘索引上，必须先调用ram的close方法
writer.addIndexes(IndexReader.open(ram));
writer.optimize();
writer.close();
}
publicstaticvoidreadIndex(Stringfield,Stringkeyword)throwsException{
IndexSearchersearcher=newIndexSearcher(newNIOFSDirectory(newFile(
path)));
Queryquery=newQueryParser(Version.LUCENE_30,field,
newStandardAnalyzer(Version.LUCENE_30)).parse(keyword);
TopDocsdocs=searcher.search(query,10);
System.out.println("查找到"+docs.totalHits+"个\n对应的text为：");
ScoreDoc[]doc=docs.scoreDocs;
for(ScoreDocd:doc){
Documentdocu=searcher.doc(d.doc);
System.out.println(docu.get(field));
}
}
}
执行结果：
查找到2个
对应的text为：
Itisatextarea
itisanotherarea