Lucene3.6.2入门系列

文章15 |   阅读 6826 |   点赞0

来源：https://blog.csdn.net/jadyer/category_1571227.html

【Lucene3.6.2入门系列】第09节_高级搜索之自定义QueryParser

转x33g5p2x  于2021-12-24 转载在 其他  
字(8.1k)|赞(0)|评价(0)|浏览(573)

完整版见 https://jadyer.github.io/2013/08/19/lucene-advanced-search-queryparser/

  1. package com.jadyer.lucene;
  3. import java.io.File;
  4. import java.io.IOException;
  5. import java.text.SimpleDateFormat;
  6. import java.util.Date;
  8. import org.apache.lucene.analysis.standard.StandardAnalyzer;
  9. import org.apache.lucene.document.Document;
  10. import org.apache.lucene.document.Field;
  11. import org.apache.lucene.document.NumericField;
  12. import org.apache.lucene.index.IndexReader;
  13. import org.apache.lucene.index.IndexWriter;
  14. import org.apache.lucene.index.IndexWriterConfig;
  15. import org.apache.lucene.queryParser.ParseException;
  16. import org.apache.lucene.queryParser.QueryParser;
  17. import org.apache.lucene.search.IndexSearcher;
  18. import org.apache.lucene.search.Query;
  19. import org.apache.lucene.search.ScoreDoc;
  20. import org.apache.lucene.search.TopDocs;
  21. import org.apache.lucene.store.Directory;
  22. import org.apache.lucene.store.FSDirectory;
  23. import org.apache.lucene.util.Version;
  25. import com.jadyer.custom.MyQueryParser;
  27. /**
  28.  * 【Lucene3.6.2入门系列】第09节_高级搜索之自定义QueryParser
  29.  * @create Aug 19, 2013 2:07:32 PM
  30.  * @author 玄玉<http://blog.csdn.net/jadyer>
  31.  */
  32. public class AdvancedSearch {
  33. 	private Directory directory;
  34. 	private IndexReader reader;
  35. 	
  36. 	public AdvancedSearch(){
  37. 		/**文件大小*/
  38. 		int[] sizes = {90, 10, 20, 10, 60, 50};
  39. 		/**文件名*/
  40. 		String[] names = {"Michael.java", "Scofield.ini", "Tbag.txt", "Jack", "Jade", "Jadyer"};
  41. 		/**文件内容*/
  42. 		String[] contents = {"my java blog is http://blog.csdn.net/jadyer",
  43. 							 "my Java Website is http://www.jadyer.cn",
  44. 							 "my name is jadyer",
  45. 							 "I am a Java Developer",
  46. 							 "I am from Haerbin",
  47. 							 "I like java of Lucene"};
  48. 		/**文件日期*/
  49. 		Date[] dates = new Date[sizes.length];
  50. 		SimpleDateFormat sdf = new SimpleDateFormat("yyyyMMdd HH:mm:ss");
  51. 		IndexWriter writer = null;
  52. 		Document doc = null;
  53. 		try {
  54. 			dates[0] = sdf.parse("20130407 15:25:30");
  55. 			dates[1] = sdf.parse("20130407 16:30:45");
  56. 			dates[2] = sdf.parse("20130213 11:15:25");
  57. 			dates[3] = sdf.parse("20130808 09:30:55");
  58. 			dates[4] = sdf.parse("20130526 13:54:22");
  59. 			dates[5] = sdf.parse("20130701 17:35:34");
  60. 			directory = FSDirectory.open(new File("myExample/01_index/"));
  61. 			writer = new IndexWriter(directory, new IndexWriterConfig(Version.LUCENE_36, new StandardAnalyzer(Version.LUCENE_36)));
  62. 			writer.deleteAll();
  63. 			for(int i=0; i<sizes.length; i++){
  64. 				doc = new Document();
  65. 				doc.add(new NumericField("size",Field.Store.YES, true).setIntValue(sizes[i]));
  66. 				doc.add(new Field("name", names[i], Field.Store.YES, Field.Index.ANALYZED_NO_NORMS));
  67. 				doc.add(new Field("content", contents[i], Field.Store.NO, Field.Index.ANALYZED));
  68. 				doc.add(new NumericField("date", Field.Store.YES, true).setLongValue(dates[i].getTime()));
  69. 				writer.addDocument(doc);
  70. 			}
  71. 		} catch (Exception e) {
  72. 			e.printStackTrace();
  73. 		} finally {
  74. 			if(null != writer){
  75. 				try {
  76. 					writer.close();
  77. 				} catch (IOException ce) {
  78. 					ce.printStackTrace();
  79. 				}
  80. 			}
  81. 		}
  82. 	}
  83. 	
  84. 	
  85. 	/**
  86. 	 * 获取IndexReader实例
  87. 	 */
  88. 	private IndexReader getIndexReader(){
  89. 		try {
  90. 			if(reader == null){
  91. 				reader = IndexReader.open(directory);
  92. 			}else{
  93. 				//if the index was changed since the provided reader was opened, open and return a new reader; else,return null
  94. 				//如果当前reader在打开期间index发生改变,则打开并返回一个新的IndexReader,否则返回null
  95. 				IndexReader ir = IndexReader.openIfChanged(reader);
  96. 				if(ir != null){
  97. 					reader.close(); //关闭原reader
  98. 					reader = ir;    //赋予新reader
  99. 				}
  100. 			}
  101. 			return reader;
  102. 		}catch(Exception e) {
  103. 			e.printStackTrace();
  104. 		}
  105. 		return null; //发生异常则返回null
  106. 	}
  108. 	
  109. 	/**
  110. 	 * 自定义QueryParser的搜索
  111. 	 * @param expr 搜索的表达式
  112. 	 */
  113. 	public void searchByCustomQueryParser(String expr){
  114. 		IndexSearcher searcher = new IndexSearcher(this.getIndexReader());
  115. 		QueryParser parser = new MyQueryParser(Version.LUCENE_36, "content", new StandardAnalyzer(Version.LUCENE_36));
  116. 		try {
  117. 			Query query = parser.parse(expr);
  118. 			TopDocs tds = searcher.search(query, 10);
  119. 			for(ScoreDoc sd : tds.scoreDocs){
  120. 				Document doc = searcher.doc(sd.doc);
  121. 				System.out.print("文档编号=" + sd.doc + "  文档权值=" + doc.getBoost() + "  文档评分=" + sd.score + "    ");
  122. 				System.out.println("size=" + doc.get("size") + "  date=" + new SimpleDateFormat("yyyyMMdd HH:mm:ss").format(new Date(Long.parseLong(doc.get("date")))) + "  name=" + doc.get("name"));
  123. 			}
  124. 		} catch (ParseException e) {
  125. 			System.err.println(e.getMessage());
  126. 		} catch (Exception e) {
  127. 			e.printStackTrace();
  128. 		} finally {
  129. 			if(null != searcher){
  130. 				try {
  131. 					searcher.close(); //记得关闭IndexSearcher
  132. 				} catch (IOException e) {
  133. 					e.printStackTrace();
  134. 				}
  135. 			}
  136. 		}
  137. 	}
  138. 	
  139. 	
  140. 	/**
  141. 	 * 测试一下搜索效果
  142. 	 */
  143. 	public static void main(String[] args) {
  144. 		AdvancedSearch advancedSearch = new AdvancedSearch();
  145. 		advancedSearch.searchByCustomQueryParser("name:Jadk~");
  146. 		advancedSearch.searchByCustomQueryParser("name:Ja??er");
  147. 		System.out.println("------------------------------------------------------------------------");
  148. 		advancedSearch.searchByCustomQueryParser("name:Jade");
  149. 		System.out.println("------------------------------------------------------------------------");
  150. 		advancedSearch.searchByCustomQueryParser("name:[h TO n]");
  151. 		System.out.println("------------------------------------------------------------------------");
  152. 		advancedSearch.searchByCustomQueryParser("size:[20 TO 80]");
  153. 		System.out.println("------------------------------------------------------------------------");
  154. 		advancedSearch.searchByCustomQueryParser("date:[20130407 TO 20130701]");
  155. 	}
  156. }

下面是自定义的MyQueryParser.java（这里主要实现了以下两个功能）

1)禁用模糊搜索和通配符搜索，以提高搜索性能

2)扩展基于数字和日期的搜索，使之支持数字和日期的搜索

  1. package com.jadyer.custom;
  3. import java.text.SimpleDateFormat;
  4. import java.util.regex.Pattern;
  6. import org.apache.lucene.analysis.Analyzer;
  7. import org.apache.lucene.queryParser.ParseException;
  8. import org.apache.lucene.queryParser.QueryParser;
  9. import org.apache.lucene.search.NumericRangeQuery;
  10. import org.apache.lucene.search.Query;
  11. import org.apache.lucene.util.Version;
  13. /**
  14.  * 自定义QueryParser
  15.  * @see --------------------------------------------------------------------------------------------------
  16.  * @see 实际使用QueryParser的过程中,通常会考虑两个问题
  17.  * @see 1)限制性能低的QueryParser--对于某些QueryParser在搜索时会使得性能降低,故考虑禁用这些搜索以提升性能
  18.  * @see 2)扩展基于数字和日期的搜索---有时需要进行一个数字的范围搜索,故需扩展原有的QueryParser才能实现此搜索
  19.  * @see --------------------------------------------------------------------------------------------------
  20.  * @see 限制性能低的QueryParser
  21.  * @see 继承QueryParser类并重载相应方法,比如getFuzzyQuery和getWildcardQuery
  22.  * @see 这样造成的结果就是,当输入普通的搜索表达式时,如'I AND Haerbin'可以正常搜索
  23.  * @see 但输入'name:Jadk~'或者'name:Ja??er'时,就会执行到重载方法中,这时就可以自行处理了,比如本例中禁止该功能
  24.  * @see --------------------------------------------------------------------------------------------------
  25.  * @see 扩展基于数字和日期的查询
  26.  * @see 思路就是继承QueryParser类后重载getRangeQuery()方法
  27.  * @see 再针对数字和日期的'域',做特殊处理(使用NumericRangeQuery.newIntRange()方法来搜索)
  28.  * @see --------------------------------------------------------------------------------------------------
  29.  * @create Aug 6, 2013 4:13:42 PM
  30.  * @author 玄玉<http://blog.csdn.net/jadyer>
  31.  */
  32. public class MyQueryParser extends QueryParser {
  33. 	public MyQueryParser(Version matchVersion, String f, Analyzer a) {
  34. 		super(matchVersion, f, a);
  35. 	}
  36. 	
  37. 	@Override
  38. 	protected Query getWildcardQuery(String field, String termStr) throws ParseException {
  39. 		throw new ParseException("由于性能原因，已禁用通配符搜索，请输入更精确的信息进行搜索 ^_^ ^_^");
  40. 	}
  41. 	
  42. 	@Override
  43. 	protected Query getFuzzyQuery(String field, String termStr, float minSimilarity) throws ParseException {
  44. 		throw new ParseException("由于性能原因，已禁用模糊搜索，请输入更精确的信息进行搜索 ^_^ ^_^");
  45. 	}
  46. 	
  47. 	@Override
  48. 	protected Query getRangeQuery(String field, String part1, String part2, boolean inclusive) throws ParseException {
  49. 		if(field.equals("size")){
  50. 			//默认的QueryParser.parse(String query)表达式中并不支持'size:[20 TO 80]'数字的域值
  51. 			//这样一来,针对数字的域值进行特殊处理,那么QueryParser表达式就支持数字了
  52. 			return NumericRangeQuery.newIntRange(field, Integer.parseInt(part1), Integer.parseInt(part2), inclusive, inclusive);
  53. 		}else if(field.equals("date")){
  54. 			String regex = "\\d{8}";
  55. 			String dateType = "yyyyMMdd";
  56. 			if(Pattern.matches(regex, part1) && Pattern.matches(regex, part2)){
  57. 				SimpleDateFormat sdf = new SimpleDateFormat(dateType);
  58. 				try {
  59. 					long min = sdf.parse(part1).getTime();
  60. 					long max = sdf.parse(part2).getTime();
  61. 					//使之支持日期的检索,应用时直接QueryParser.parse("date:[20130407 TO 20130701]")
  62. 					return NumericRangeQuery.newLongRange(field, min, max, inclusive, inclusive);
  63. 				} catch (java.text.ParseException e) {
  64. 					e.printStackTrace();
  65. 				}
  66. 			}else{
  67. 				throw new ParseException("Unknown date format, please use '" + dateType + "'");
  68. 			}
  69. 		}
  70. 		//如没找到匹配的Field域,那么返回默认的TermRangeQuery
  71. 		return super.getRangeQuery(field, part1, part2, inclusive);
  72. 	}
  73. }

版权说明 : 本文为转载文章, 版权归原作者所有 版权申明

原文链接 : https://blog.csdn.net/jadyer/article/details/10069095

内容来源于网络，如有侵权，请联系作者删除！

solrlucenequerytika

相关文章

    查看更多
    • 蜀ICP备13028337号-1 大数据知识库 https://www.saoniuhuo.com © All rights reserved
    • 本站内容来源互联网,如果侵犯您的权益请联系我们删除, 联系方式：448109455@qq.com