lucene 搜索入门实例

1. Y_indexer.java建索引
2. packagecom.hapark.lucene;
4. importjava.io.BufferedReader;
5. importjava.io.File;
6. importjava.io.FileInputStream;
7. importjava.io.IOException;
8. importjava.io.InputStreamReader;
9. importjava.util.ArrayList;
10. importjava.util.Date;
12. importorg.apache.lucene.analysis.Analyzer;
13. importorg.apache.lucene.analysis.standard.StandardAnalyzer;
14. importorg.apache.lucene.document.Document;
15. importorg.apache.lucene.document.Field;
16. importorg.apache.lucene.index.IndexWriter;
18. publicclassY_indexer{
19. publicstaticvoidmain(String[]args)throwsException{
20. /*指明要索引文件夹的位置,这里是D盘的y文件夹下*/
21. FilefileDir=newFile("d:\\y");
23. /*这里放索引文件的位置*/
24. FileindexDir=newFile("d:\\index");
25. AnalyzerluceneAnalyzer=newStandardAnalyzer();
26. IndexWriterindexWriter=newIndexWriter(indexDir,luceneAnalyzer,
27. true);
28. ArrayListlist=newArrayList();
29. getList(fileDir,list);
30. File[]textFiles=(File[])list.toArray(newFile[0]);
31. System.out.println(textFiles.length);
32. longstartTime=newDate().getTime();
34. //增加document到索引去
35. for(inti=0;i<textFiles.length;i++){
36. if(textFiles[i].isFile()
37. &&textFiles[i].getName().endsWith(".html")){
38. System.out.println("File"+textFiles[i].getCanonicalPath()
39. +"正在被索引....");
40. Stringtemp=FileReaderAll(textFiles[i].getCanonicalPath(),
41. "GBK");
42. System.out.println(temp);
43. Documentdocument=newDocument();
44. FieldFieldPath=newField("path",textFiles[i].getPath(),
45. Field.Store.YES,Field.Index.NO);
46. FieldFieldBody=newField("body",temp,Field.Store.YES,
47. Field.Index.TOKENIZED,
48. Field.TermVector.WITH_POSITIONS_OFFSETS);
49. FieldFieldTitle=newField("title",temp,Field.Store.YES,
50. Field.Index.TOKENIZED,
51. Field.TermVector.WITH_POSITIONS_OFFSETS);
52. document.add(FieldPath);
53. document.add(FieldBody);
54. document.add(FieldTitle);
55. indexWriter.addDocument(document);
56. }
57. }
58. //optimize()方法是对索引进行优化
59. indexWriter.optimize();
60. indexWriter.close();
62. //测试一下索引的时间
63. longendTime=newDate().getTime();
64. System.out
65. .println("这花费了"
66. +(endTime-startTime)
67. +"毫秒来把文档增加到索引里面去!"
68. +fileDir.getPath());
69. }
72. /**
73. *多层文件夹
74. *@paramfile
75. *@paramlist
76. */
77. publicstaticvoidgetList(Filefile,ArrayListlist){
78. if(file.isDirectory()&&file.getName().indexOf(".")!=0){
80. File[]file2=file.listFiles();
81. for(inti=0;i<file2.length;i++)
82. getList(file2[i],list);
83. }else{
84. list.add(file);
85. }
86. }
88. publicstaticStringFileReaderAll(StringFileName,Stringcharset)
89. throwsIOException{
90. BufferedReaderreader=newBufferedReader(newInputStreamReader(
91. newFileInputStream(FileName),charset));
92. Stringline=newString();
93. Stringtemp=newString();
95. while((line=reader.readLine())!=null){
96. temp+=line;
97. }
98. reader.close();
99. returntemp;
100. }
101. }

1. Y_searcherlucene搜索
2. packagecom.hapark.lucene;
4. importjava.io.IOException;
5. importjava.util.ArrayList;
6. importjava.util.Date;
7. importjava.util.List;
9. importorg.apache.lucene.analysis.Analyzer;
10. importorg.apache.lucene.analysis.standard.StandardAnalyzer;
11. importorg.apache.lucene.queryParser.ParseException;
12. importorg.apache.lucene.queryParser.QueryParser;
13. importorg.apache.lucene.search.Hits;
14. importorg.apache.lucene.search.IndexSearcher;
15. importorg.apache.lucene.search.Query;
16. publicclassY_searcher{
18. publicListsearch(){
19. ListsearchResult=newArrayList();//创建一个List接口的一个实例类ArrayList类
20. try{
21. Hitshits=null;
22. Stringkey="苏";
23. Queryquery=null;
24. IndexSearchersearcher=newIndexSearcher("d:\\yuyang");
25. Analyzeranalyzer=newStandardAnalyzer();//创建一个Analyzer接口的一个实例类StandardAnalyzer
27. QueryParserqp=newQueryParser("title",analyzer);
28. query=qp.parse(key);
30. if(searcher!=null){
31. Datestart=newDate();
32. hits=searcher.search(query);//遍历hist结果的length
33. if(hits.length()==0){
34. System.out.println("对不起。没你想要的结果!");
35. }
36. else{
37. for(inti=0;i<hits.length();i++){
38. Dateend=newDate();
39. //System.out.println("找到:"+hits.length()+"Totalresult!");
40. System.out.println("文件的路径:"+hits.doc(i).get("path"));
41. //System.out.println("内容:"+hits.doc(i).get("body"));
42. System.out.println(hits.doc(i).get("title"));
43. System.out.println("检索完成，用时"+(end.getTime()-start.getTime())+"毫秒");
44. }
45. }
46. }
47. }
48. catch(ParseExceptionex){
50. }
51. catch(IOExceptione){
53. }
54. returnsearchResult;
55. }
57. publicstaticvoidmain(Stringargs[]){
58. Y_searchery_s=newY_searcher();
59. y_s.search();
60. }
62. }