lucene3.3的简单例子

论坛 › 期权论坛 › 脚本     
匿名技术用户   2021-1-12 13:51   532   0
这里主要写一个lucene3.3的简单例子：
首先，当然是helloworld程序：
Java代码 收藏代码
  1. package com.lucene.demo;
  3. import java.io.File;
  4. import java.util.List;
  6. import org.apache.lucene.analysis.Analyzer;
  7. import org.apache.lucene.analysis.cn.smart.SmartChineseAnalyzer;
  8. import org.apache.lucene.document.Document;
  9. import org.apache.lucene.index.IndexWriter;
  10. import org.apache.lucene.index.IndexWriterConfig;
  11. import org.apache.lucene.queryParser.MultiFieldQueryParser;
  12. import org.apache.lucene.queryParser.QueryParser;
  13. import org.apache.lucene.search.IndexSearcher;
  14. import org.apache.lucene.search.Query;
  15. import org.apache.lucene.store.Directory;
  16. import org.apache.lucene.store.FSDirectory;
  17. import org.apache.lucene.util.Version;
  18. import org.junit.Test;
  20. import com.lucene.model.SerachResult;
  21. import com.lucene.utils.FileToDocument;
  22. import com.lucene.utils.SerachUtil;
  24. public class HelloWorld {
  26. File indexPath=new File("F:\\java\\Workspaces\\Lucene\\luceneIndex");//存放索引文件目录
  27. Analyzer analyzer=new SmartChineseAnalyzer(Version.LUCENE_33);
  28. IndexWriterConfig conf = new IndexWriterConfig(Version.LUCENE_33, analyzer);
  29. Document doc=FileToDocument.file2Document(new File("F:\\java\\Workspaces\\Lucene\\datasooruce\\IndexWriter.txt"));
  30. Document doc1=FileToDocument.file2Document(new File("F:\\java\\Workspaces\\Lucene\\datasooruce\\china.txt"));
  31. Document doc2=FileToDocument.file2Document(new File("F:\\java\\Workspaces\\Lucene\\datasooruce\\开玩笑.txt"));
  32. /**
  33. * 创建索引
  34. */
  35. @Test
  36. public void createIndex() throws Exception{
  37. conf.setOpenMode(IndexWriterConfig.OpenMode.CREATE);//总是重新创建
  38. Directory fsDir =FSDirectory.open(indexPath);
  39. long startTime =System.currentTimeMillis();
  40. IndexWriter indexWriter =new IndexWriter(fsDir, conf);
  41. indexWriter.addDocument(doc);
  42. indexWriter.addDocument(doc1);
  43. indexWriter.addDocument(doc2);
  44. indexWriter.optimize();
  45. indexWriter.close();
  46. long endTime=System.currentTimeMillis();
  47. System.out.println("共有"+indexWriter.numDocs()+"条索引");
  48. System.out.println("建立索引用时: " + (endTime-startTime)+"毫秒");
  49. }
  51. /**
  52. * 搜索
  53. */
  54. @Test
  55. public void serach() throws Exception {
  56. //1 把要搜素的文本解析为QUery
  57. String queryString ="开玩笑";
  58. String [] fields = {"name","content"};
  59. QueryParser queryParser =new MultiFieldQueryParser(Version.LUCENE_33, fields, analyzer);
  60. Query query =queryParser.parse(queryString);
  63. Directory fsDir =FSDirectory.open(indexPath);
  65. IndexSearcher indexSearcher= new IndexSearcher(fsDir);
  66. SerachResult serachResult=SerachUtil.serach(1, 3, query,analyzer,indexSearcher,null);
  67. System.out.println("总共有[ "+serachResult.getTotalCount()+" ]条匹配结果");
  68. //3 打印结果
  69. for (Document doc : (List<Document>)serachResult.getRecords()) {
  70. System.out.println();
  71. FileToDocument.printDocumentInfo(doc);
  72. }
  73. indexSearcher.close();
  74. }
  75. }

其中用到了2个util类：
Java代码 收藏代码
  1. package com.lucene.utils;
  3. import java.util.ArrayList;
  4. import java.util.List;
  5. import java.io.BufferedReader;
  6. import java.io.File;
  7. import java.io.FileFilter;
  8. import java.io.FileInputStream;
  9. import java.io.InputStreamReader;
  11. import org.apache.lucene.document.Document;
  12. import org.apache.lucene.document.Field;
  13. import org.apache.lucene.document.Field.Index;
  14. import org.apache.lucene.document.Field.Store;
  15. import org.apache.lucene.util.NumericUtils;
  17. public class FileToDocument {
  18. /**
  19. * 将文件转换成document
  20. * @param file
  21. * @return
  22. */
  23. public static Document file2Document(File file) {
  24. Document doc= new Document();
  25. doc.add(new Field("name",file.getName(),Store.YES,Index.ANALYZED));
  26. doc.add(new Field("content",readFile(file),Store.YES,Index.ANALYZED));
  27. doc.add(new Field("size",NumericUtils.longToPrefixCoded(file.length()),Store.YES,Index.NOT_ANALYZED));
  28. doc.add(new Field("path",file.getAbsolutePath(),Store.YES,Index.ANALYZED));
  29. return doc;
  30. }
  32. /**
  33. * 读取文件内容
  34. * @param file
  35. * @return
  36. */
  37. private static String readFile(File file) {
  38. StringBuffer content =new StringBuffer();
  39. try {
  40. BufferedReader reader =new BufferedReader(new InputStreamReader(new FileInputStream(file)));
  41. for(String line =null;(line=reader.readLine())!=null;) {
  42. content.append(line).append("\n");
  43. }
  44. } catch (Exception e) {
  45. e.printStackTrace();
  46. }
  47. return content.toString();
  48. }
  51. /**
  52. * 打印document
  53. * 获取name熟悉的值的两种方法
  54. * 1 FIeld f=doc.getField("name");
  55. * f.StringValue();
  56. * 2 doc.get("name");
  57. * @param doc
  58. */
  59. public static void printDocumentInfo(Document doc) {
  61. System.out.println("name = "+doc.get("name"));
  62. System.out.println("content = "+doc.get("content"));
  63. System.out.println("size = "+NumericUtils.prefixCodedToLong(doc.get("size")));
  64. System.out.println("path = "+doc.get("path"));
  65. System.out.println("comment = "+doc.get("comment"));
  66. }
  68. /**
  69. * 得到该目录下得所有文件（非目录，可读，非一次，存在）
  70. * @param sourceDir
  71. * @return
  72. */
  73. public List<File> index(File sourceDir) {
  74. File[] files=sourceDir.listFiles();
  75. List<File> fileList= new ArrayList<File>();
  76. for (int i = 0; i < files.length; i++) {
  77. File f=files[i];
  78. if(!f.isDirectory() && f.canRead() && !f.isHidden() && f.exists()){
  79. fileList.add(f);
  80. }
  81. }
  82. return fileList;
  83. }
  86. /**
  87. * 只接受txt文件的拦截器
  88. * @author Administrator
  89. *
  90. */
  91. private static class MyFileFilter implements FileFilter{
  93. @Override
  94. public boolean accept(File pathname) {
  95. return pathname.getName().toLowerCase().endsWith(".txt");
  96. }
  98. }
  99. }



Java代码 收藏代码
  1. package com.lucene.utils;
  3. import java.util.ArrayList;
  4. import java.util.List;
  5. import org.apache.lucene.analysis.Analyzer;
  6. import org.apache.lucene.analysis.TokenStream;
  7. import org.apache.lucene.document.Document;
  8. import org.apache.lucene.document.Field;
  9. import org.apache.lucene.document.Field.Index;
  10. import org.apache.lucene.document.Field.Store;
  11. import org.apache.lucene.queryParser.MultiFieldQueryParser;
  12. import org.apache.lucene.queryParser.QueryParser;
  13. import org.apache.lucene.search.Filter;
  14. import org.apache.lucene.search.IndexSearcher;
  15. import org.apache.lucene.search.Query;
  16. import org.apache.lucene.search.ScoreDoc;
  17. import org.apache.lucene.search.TopDocs;
  18. import org.apache.lucene.search.highlight.Formatter;
  19. import org.apache.lucene.search.highlight.Fragmenter;
  20. import org.apache.lucene.search.highlight.Highlighter;
  21. import org.apache.lucene.search.highlight.QueryScorer;
  22. import org.apache.lucene.search.highlight.Scorer;
  23. import org.apache.lucene.search.highlight.SimpleFragmenter;
  24. import org.apache.lucene.search.highlight.SimpleHTMLFormatter;
  25. import org.apache.lucene.util.Version;
  27. import com.lucene.model.SerachResult;
  29. /**
  30. *
  31. * @author: agoni
  32. * @date： Aug 13, 2011
  33. * @function:
  34. *
  35. */
  36. public class SerachUtil {
  38. public static SerachResult serach(int pageNo,int pageSize ,Query query,Analyzer analyzer,IndexSearcher indexSearcher,Filter filter) throws Exception {
  40. SerachResult serachResult = new SerachResult();
  43. long startTime =System.currentTimeMillis();
  47. //2 进行查询,并进行过滤
  48. TopDocs topDocs=indexSearcher.search(query, filter, 10000);
  49. //准备高亮器
  50. Formatter formatter = new SimpleHTMLFormatter("<font color='red'>","</font>");
  51. Scorer scorer = new QueryScorer(query);
  52. Highlighter highlighter = new Highlighter(formatter, scorer);
  53. Fragmenter fragmenter = new SimpleFragmenter(100);//摘要信息的长度
  54. highlighter.setTextFragmenter(fragmenter);
  58. //分页读取数据
  59. List<Document> recordList =new ArrayList<Document>();
  60. int end=Math.min(pageNo*pageSize,topDocs.totalHits);
  61. for(int i=(pageNo-1)*pageSize;i<end;i++) {
  62. ScoreDoc scoreDoc = topDocs.scoreDocs[i];//读取第几条记录
  63. int docSn=scoreDoc.doc; //文档内部编号
  64. Document document=indexSearcher.doc(docSn);
  66. //高亮
  67. //当正文中没有出现关键字， 返回null
  68. String hc=highlighter.getBestFragment(analyzer, "content",document.get("content"));
  69. if(hc==null) {
  70. String content =document.get("content");
  71. int endIndex=Math.min(100, content.length());
  72. hc=content.substring(0,endIndex);
  73. }
  74. Field contentField=(Field) document.getFieldable("content");
  75. contentField.setValue(hc);
  76. document.add(new Field("comment",hc,Store.YES,Index.ANALYZED));//将搜索的提示信息放入文档中
  78. recordList.add(document);
  79. }
  80. serachResult.setPageNo(pageNo);
  81. serachResult.setPageSize(pageSize);
  82. serachResult.setTotalCount(topDocs.totalHits);
  83. serachResult.setRecords(recordList);
  84. long endTime=System.currentTimeMillis();
  85. serachResult.setTime(endTime-startTime);
  87. return serachResult;
  88. }
  91. }




对搜索结果封装的类：
Java代码 收藏代码
  1. package com.lucene.model;
  3. import java.util.List;
  5. import org.apache.lucene.document.Document;
  7. /**
  8. *
  9. * @author: agoni
  10. * @date： Aug 13, 2011
  11. * @function:
  12. *
  13. */
  14. public class SerachResult {
  15. private int totalCount; //搜索的总记录数
  16. private List<Document> records; //返回当前页的结果
  17. private long Time; //搜索用时
  18. private int pageNo; //当前页
  19. private int pageSize; //每页数量
  21. public SerachResult() {
  22. }
  24. /**
  25. * @param totalCount
  26. * @param recordList
  27. * @param time
  28. */
  29. public SerachResult(int totalCount, List<Document> recordList, long time) {
  30. super();
  31. this.totalCount = totalCount;
  32. this.setRecords(recordList);
  33. Time = time;
  34. }
  35. public int getTotalCount() {
  36. return totalCount;
  37. }
  38. public void setTotalCount(int totalCount) {
  39. this.totalCount = totalCount;
  40. }
  42. public long getTime() {
  43. return Time;
  44. }
  45. public void setTime(long time) {
  46. Time = time;
  47. }
  48. public int getPageNo() {
  49. return pageNo;
  50. }
  51. public void setPageNo(int pageNo) {
  52. this.pageNo = pageNo;
  53. }
  54. public int getPageSize() {
  55. return pageSize;
  56. }
  57. public void setPageSize(int pageSize) {
  58. this.pageSize = pageSize;
  59. }
  61. public void setRecords(List<Document> records) {
  62. this.records = records;
  63. }
  65. public List<Document> getRecords() {
  66. return records;
  67. }
  69. }




helloworld程序到此结束。

下面是测试中文分词器和英文分词器的简单例子:
Java代码 收藏代码
  1. package com.lucene.demo;
  3. import java.io.IOException;
  4. import java.io.StringReader;
  6. import org.apache.lucene.analysis.Analyzer;
  7. import org.apache.lucene.analysis.TokenStream;
  8. import org.apache.lucene.analysis.cn.smart.SmartChineseAnalyzer;
  9. import org.apache.lucene.analysis.en.EnglishAnalyzer;
  10. import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
  11. import org.apache.lucene.analysis.tokenattributes.TypeAttribute;
  12. import org.apache.lucene.util.Version;
  13. import org.junit.Test;
  15. /**
  16. *
  17. * @author: agoni
  18. * @date： Aug 14, 2011
  19. * @function:
  20. *
  21. */
  22. public class TestAnalyze {
  23. private String enText= "IndexWriter addDocument's a javadoc.txt menu_down up-down";
  24. private String chText="衣服 矿泉水和分词器-看不起一个人的审美";
  25. Analyzer enAnalyzer = new EnglishAnalyzer(Version.LUCENE_33);
  26. Analyzer chAnalyzer = new SmartChineseAnalyzer(Version.LUCENE_33);
  29. @Test
  30. public void testAnalyze() throws IOException {
  31. analyze(enAnalyzer, enText);
  32. System.out.println("---------------------------------------------------------------------------------------------------");
  33. analyze(enAnalyzer, chText);
  34. System.out.println("---------------------------------------------------------------------------------------------------");
  35. analyze(chAnalyzer, enText);
  36. System.out.println("---------------------------------------------------------------------------------------------------");
  37. analyze(chAnalyzer, chText);
  38. }
  39. /**
  40. *
  41. * @param analyzer
  42. * @param text
  43. * @throws IOException
  44. */
  45. public void analyze(Analyzer analyzer ,String text) throws IOException {
  46. System.out.println("-----------分词器："+analyzer.getClass().getName()+"------------");
  47. System.out.println("输入："+text);
  48. TokenStream tokenStream = analyzer.tokenStream("content",new StringReader(text));
  49. displayTokenStream(tokenStream);
  50. }
  52. private static void displayTokenStream(TokenStream ts) throws IOException
  53. {
  54. CharTermAttribute termAtt = (CharTermAttribute)ts.getAttribute(CharTermAttribute.class);
  55. TypeAttribute typeAtt = (TypeAttribute)ts.getAttribute(TypeAttribute.class);
  57. while (ts.incrementToken())
  58. {
  59. System.out.println("type="+typeAtt.type()+ " "+termAtt);
  60. }
  61. System.out.println(' ');
  62. }
  63. }


下面是测试几种常用query的例子：
Java代码 收藏代码
  1. package com.lucene.demo;
  4. import java.io.File;
  5. import java.util.List;
  7. import org.apache.lucene.analysis.Analyzer;
  8. import org.apache.lucene.analysis.cn.smart.SmartChineseAnalyzer;
  9. import org.apache.lucene.document.Document;
  10. import org.apache.lucene.index.IndexWriterConfig;
  11. import org.apache.lucene.index.Term;
  12. import org.apache.lucene.search.BooleanClause.Occur;
  13. import org.apache.lucene.search.BooleanQuery;
  14. import org.apache.lucene.search.IndexSearcher;
  15. import org.apache.lucene.search.PhraseQuery;
  16. import org.apache.lucene.search.Query;
  17. import org.apache.lucene.search.TermQuery;
  18. import org.apache.lucene.search.TermRangeQuery;
  19. import org.apache.lucene.search.WildcardQuery;
  20. import org.apache.lucene.store.Directory;
  21. import org.apache.lucene.store.FSDirectory;
  22. import org.apache.lucene.util.NumericUtils;
  23. import org.apache.lucene.util.Version;
  24. import org.junit.Test;
  25. import org.apache.lucene.search.FuzzyLikeThisQuery;
  26. import com.lucene.model.SerachResult;
  27. import com.lucene.utils.FileToDocument;
  28. import com.lucene.utils.SerachUtil;
  30. /**
  31. *
  32. * @author: agoni
  33. * @date： Aug 14, 2011
  34. * @function:
  35. *
  36. */
  37. public class TestQuery {
  38. File indexPath=new File("F:\\java\\Workspaces\\Lucene\\luceneIndex");//存放索引文件目录
  39. Analyzer analyzer=new SmartChineseAnalyzer(Version.LUCENE_33);
  40. IndexWriterConfig conf = new IndexWriterConfig(Version.LUCENE_33, analyzer);
  41. Document doc=FileToDocument.file2Document(new File("F:\\java\\Workspaces\\Lucene\\datasooruce\\IndexWriter.txt"));
  42. Document doc1=FileToDocument.file2Document(new File("F:\\java\\Workspaces\\Lucene\\datasooruce\\china.txt"));
  43. Document doc2=FileToDocument.file2Document(new File("F:\\java\\Workspaces\\Lucene\\datasooruce\\开玩笑.txt"));
  45. /**
  46. * 搜索
  47. */
  48. public void serach(Query query) {
  49. Directory fsDir;
  50. try {
  51. fsDir = FSDirectory.open(indexPath);
  52. IndexSearcher indexSearcher= new IndexSearcher(fsDir);
  53. SerachResult serachResult=SerachUtil.serach(1, 10, query,analyzer,indexSearcher,null);
  54. System.out.println("总共有[ "+serachResult.getTotalCount()+" ]条匹配结果");
  55. //3 打印结果
  56. for (Document doc : (List<Document>)serachResult.getRecords()) {
  57. System.out.println("--------------------------------------------------------------------------------------------------------------------------------------");
  58. FileToDocument.printDocumentInfo(doc);//打印文档
  59. }
  60. indexSearcher.close();
  61. } catch (Exception e) {
  62. e.printStackTrace();
  63. }
  65. }
  68. /**
  69. * 关键字查询
  70. */
  71. @Test
  72. public void testTermQuery() {
  73. //Term term = new Term("name","开玩笑");
  74. Term term = new Term("content","缓存");
  75. Query query = new TermQuery(term);
  76. serach(query);
  77. }
  79. /**
  80. * 范围查询
  81. * 参数3.4 是否包含上下边界
  82. */
  83. @Test
  84. public void testTermRangeQuery() {
  86. TermRangeQuery query =new TermRangeQuery("size",NumericUtils.longToPrefixCoded(100),NumericUtils.longToPrefixCoded(1000)
  87. , true, true);
  88. serach(query);//查询文件大小为100到1000之间的数据
  89. }
  92. /**
  93. * 模糊查询
  94. * ？表示一位 * 表示多位
  95. */
  96. @Test
  97. public void testWildcardQuery() {
  98. //Term term = new Term("name","index*"); //Index* 将查询不到任何结果，因为建立索引已将所有大写转为小写
  99. //Term term = new Term("name","?ndex*");
  100. //Term term = new Term("name","*dex*");
  101. Term term = new Term("name","*玩?");
  102. Query query = new WildcardQuery(term);
  103. serach(query);
  104. }
  109. /**
  110. * 短语查询
  111. */
  112. @Test
  113. public void testPhraseQuery() {
  114. PhraseQuery phraseQuery = new PhraseQuery();
  115. //phraseQuery.add(new Term("content","优化"),1);
  116. //phraseQuery.add(new Term("content","缓存"),3);
  118. phraseQuery.add(new Term("content","优化"));
  119. phraseQuery.add(new Term("content","缓存"));
  120. phraseQuery.setSlop(10);//表示分词之后 两个词的相隔的次数上限
  122. serach(phraseQuery);
  123. }
  127. /**
  128. * 最常使用的就是booleanquery了，可以将各种条件组合一起形成复杂查询
  129. **/
  130. @Test
  131. public void testBooleanQuery() {
  132. //条件一
  133. PhraseQuery phraseQuery = new PhraseQuery();
  134. phraseQuery.add(new Term("content","小弟"));
  135. phraseQuery.add(new Term("content","分词"));
  136. phraseQuery.setSlop(100);//两词组间隔最大距离
  138. //条件二
  139. TermRangeQuery query =new TermRangeQuery("size",NumericUtils.longToPrefixCoded(100),NumericUtils.longToPrefixCoded(500)
  140. , true, true);
  142. BooleanQuery booleanQuery = new BooleanQuery();
  143. booleanQuery.add(phraseQuery, Occur.MUST);
  144. booleanQuery.add(query,Occur.MUST);
  147. serach(booleanQuery);
  148. }
  150. }

回复
分享到 :
0 人收藏
返回列表
高级模式
B Color Image Link Quote Code Smilies
您需要登录后才可以回帖 登录 | 立即注册

本版积分规则

16级独孤
匿名技术用户

积分:7942463
帖子:1588486
精华:0
+ 关注 私信
期权论坛 期权论坛
期权网络科技版权所有
关于我们
联系我们
加入我们
反馈问题
免责声明
积分充值
统一社会信用代码
积分规则
网站地图
爱文库
下属网站
官方
新浪微博
微信公众号
◆
下载
表情包
App下载
期权论坛 期权论坛

QQ咨询|关于我们|Archiver|手机版|小黑屋|( 辽ICP备15012455号-4 ) Powered by 期权论坛 X3.2 © 2001-2016 期权工具网&期权论坛 Inc.

发布
内容

下载期权论坛手机APP