Lucene3实例总结

「爱情、让人受尽委屈。」 2022-08-07 03:45 133阅读 0赞

参考网页：[http://footman265.iteye.com/blog/849744][http_footman265.iteye.com_blog_849744]

搞了一天半，终于利用lucene工具Demo完了我想要的功能，这其中包括为数据库建立增量索引、从索引文件根据id删除索引、单字段查询功能、多字段查询功能、多条件查询功能以及查询结果关键字高亮显示的功能。今天晚些的时候把这些功能进行了整理。看样子一时半会还下不了班，就把Demo的结果 一 一 列举下来吧。。。

理论参考：[http://lianj-lee.iteye.com/category/69005?show\_full=true][http_lianj-lee.iteye.com_category_69005_show_full_true]

Lucene3.0对数据库建立索引：[http://269181927.iteye.com/blog/789779][http_269181927.iteye.com_blog_789779]

**1. 所需要的文件(见附件)**

**依赖包：**

lucene-core-2.4.0.jar lucene工具包

lucene-highlighter-2.4.0.jar 高亮显示工具包

IKAnalyzer2.0.2OBF.jar 分词工具(支持字典分词)

mysql-connector-java-5.0.3-bin 链接mysql驱动

**数据表：**

pd\_ugc.sql(所在数据库为lucenetest)

**类文件：**

在附件index.rar和test.rar，解压后放入java工程中的src下即可

**2. 为数据库建立增量索引**

参考网页：http://www.blogjava.net/laoding/articles/279230.html

Java代码 [ ![复制代码][icon_copy.gif]][_icon_copy.gif]  ![收藏代码][icon_star.png]![spinner.gif][]

1. package index;
2. //--------------------- Change Logs----------------------
3. // @author zhiqiang.zhang Initial Created at 2010-12-23
4. //-------------------------------------------------------
5. import java.io.BufferedReader;
6. import java.io.File;
7. import java.io.FileReader;
8. import java.io.FileWriter;
9. import java.io.IOException;
10. import java.io.PrintWriter;
11. import java.sql.Connection;
12. import java.sql.DriverManager;
13. import java.sql.ResultSet;
14. import java.sql.Statement;
15. import java.util.Date;
16. 
17. import org.apache.lucene.analysis.Analyzer;
18. import org.apache.lucene.analysis.standard.StandardAnalyzer;
19. import org.apache.lucene.document.Document;
20. import org.apache.lucene.document.Field;
21. import org.apache.lucene.index.IndexWriter;
22. 
23. //增量索引
24. /\*
25. \* 实现思路:首次查询数据库表所有记录，对每条记录建立索引，并将最后一条记录的id存储到storeId.txt文件中
26. \* 当新插入一条记录时，再建立索引时不必再对所有数据重新建一遍索引，
27. \* 可根据存放在storeId.txt文件中的id查出新插入的数据，只对新增的数据新建索引，并把新增的索引追加到原来的索引文件中
28. \* \*/
29. public class IncrementIndex \{
30. 
31. public static void main(String\[\] args) \{
32. try \{
33. IncrementIndex index = new IncrementIndex();
34. String path = "E:\\\\workspace2\\\\Test\\\\lucene\_test\\\\poiIdext";//索引文件的存放路径
35. String storeIdPath = "E:\\\\workspace2\\\\Test\\\\lucene\_test\\\\storeId.txt";//存储ID的路径
36. String storeId = "";
37. Date date1 = new Date();
38. storeId = index.getStoreId(storeIdPath);
39. ResultSet rs = index.getResult(storeId);
40. System.out.println("开始建立索引。。。。");
41. index.indexBuilding(path, storeIdPath, rs);
42. Date date2 = new Date();
43. System.out.println("耗时："\+(date2.getTime()-date1.getTime())+"ms");
44. storeId = index.getStoreId(storeIdPath);
45. System.out.println(storeId);//打印出这次存储起来的ID
46. \} catch (Exception e) \{
47. e.printStackTrace();
48. \}
49. \}
50. 
51. public static void buildIndex(String indexFile, String storeIdFile) \{
52. try \{
53. String path = indexFile;//索引文件的存放路径
54. String storeIdPath = storeIdFile;//存储ID的路径
55. String storeId = "";
56. storeId = getStoreId(storeIdPath);
57. ResultSet rs = getResult(storeId);
58. indexBuilding(path, storeIdPath, rs);
59. storeId = getStoreId(storeIdPath);
60. System.out.println(storeId);//打印出这次存储起来的ID
61. \} catch (Exception e) \{
62. e.printStackTrace();
63. \}
64. \}
65. 
66. public static ResultSet getResult(String storeId) throws Exception \{
67. Class.forName("com.mysql.jdbc.Driver").newInstance();
68. String url = "jdbc:mysql://localhost:3306/lucenetest";
69. String userName = "root";
70. String password = "\*\*\*\*";
71. Connection conn = DriverManager.getConnection(url, userName, password);
72. Statement stmt = conn.createStatement();
73. String sql = "select \* from pd\_ugc";
74. ResultSet rs = stmt.executeQuery(sql + " where id > '" \+ storeId + "'order by id");
75. return rs;
76. \}
77. 
78. public static boolean indexBuilding(String path, String storeIdPath, ResultSet rs) \{
79. try \{
80. Analyzer luceneAnalyzer = new StandardAnalyzer();
81. // 取得存储起来的ID，以判定是增量索引还是重新索引
82. boolean isEmpty = true;
83. try \{
84. File file = new File(storeIdPath);
85. if (!file.exists()) \{
86. file.createNewFile();
87. \}
88. FileReader fr = new FileReader(storeIdPath);
89. BufferedReader br = new BufferedReader(fr);
90. if (br.readLine() != null) \{
91. isEmpty = false;
92. \}
93. br.close();
94. fr.close();
95. \} catch (IOException e) \{
96. e.printStackTrace();
97. \}
98. //isEmpty=false表示增量索引
99. IndexWriter writer = new IndexWriter(path, luceneAnalyzer, isEmpty);
100. String storeId = "";
101. boolean indexFlag = false;
102. String id;
103. String name;
104. String address;
105. String citycode;
106. while (rs.next()) \{
107. id = rs.getInt("id") + "";
108. name = rs.getString("name");
109. address = rs.getString("address");
110. citycode = rs.getString("citycode");
111. writer.addDocument(Document(id, name, address, citycode));
112. storeId = id;//将拿到的id给storeId，这种拿法不合理，这里为了方便
113. indexFlag = true;
114. \}
115. writer.optimize();
116. writer.close();
117. if (indexFlag) \{
118. // 将最后一个的ID存到磁盘文件中
119. writeStoreId(storeIdPath, storeId);
120. \}
121. return true;
122. \} catch (Exception e) \{
123. e.printStackTrace();
124. System.out.println("出错了" \+ e.getClass() + "\\n 错误信息为: " \+ e.getMessage());
125. return false;
126. \}
127. 
128. \}
129. 
130. public static Document Document(String id, String name, String address, String citycode) \{
131. Document doc = new Document();
132. doc.add(new Field("id", id, Field.Store.YES, Field.Index.TOKENIZED));
133. doc.add(new Field("name", name, Field.Store.YES, Field.Index.TOKENIZED));//查询字段
134. doc.add(new Field("address", address, Field.Store.YES, Field.Index.TOKENIZED));
135. doc.add(new Field("citycode", citycode, Field.Store.YES, Field.Index.TOKENIZED));//查询字段
136. return doc;
137. \}
138. 
139. // 取得存储在磁盘中的ID
140. public static String getStoreId(String path) \{
141. String storeId = "";
142. try \{
143. File file = new File(path);
144. if (!file.exists()) \{
145. file.createNewFile();
146. \}
147. FileReader fr = new FileReader(path);
148. BufferedReader br = new BufferedReader(fr);
149. storeId = br.readLine();
150. if (storeId == null || storeId == "") storeId = "0";
151. br.close();
152. fr.close();
153. \} catch (Exception e) \{
154. e.printStackTrace();
155. \}
156. return storeId;
157. \}
158. 
159. // 将ID写入到磁盘文件中
160. public static boolean writeStoreId(String path, String storeId) \{
161. boolean b = false;
162. try \{
163. File file = new File(path);
164. if (!file.exists()) \{
165. file.createNewFile();
166. \}
167. FileWriter fw = new FileWriter(path);
168. PrintWriter out = new PrintWriter(fw);
169. out.write(storeId);
170. out.close();
171. fw.close();
172. b = true;
173. \} catch (IOException e) \{
174. e.printStackTrace();
175. \}
176. return b;
177. \}
178. \}

package index;
 //--------------------- Change Logs----------------------
 // @author zhiqiang.zhang Initial Created at 2010-12-23
 //-------------------------------------------------------
 import java.io.BufferedReader;
 import java.io.File;
 import java.io.FileReader;
 import java.io.FileWriter;
 import java.io.IOException;
 import java.io.PrintWriter;
 import java.sql.Connection;
 import java.sql.DriverManager;
 import java.sql.ResultSet;
 import java.sql.Statement;
 import java.util.Date;
 
 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.IndexWriter;
 
 //增量索引
 /*
 * 实现思路:首次查询数据库表所有记录，对每条记录建立索引，并将最后一条记录的id存储到storeId.txt文件中
 * 当新插入一条记录时，再建立索引时不必再对所有数据重新建一遍索引，
 * 可根据存放在storeId.txt文件中的id查出新插入的数据，只对新增的数据新建索引，并把新增的索引追加到原来的索引文件中
 * */
 public class IncrementIndex {
 
 public static void main(String[] args) {
 try {
 IncrementIndex index = new IncrementIndex();
 String path = "E:\\workspace2\\Test\\lucene_test\\poiIdext";//索引文件的存放路径
 String storeIdPath = "E:\\workspace2\\Test\\lucene_test\\storeId.txt";//存储ID的路径
 String storeId = "";
 Date date1 = new Date();
 storeId = index.getStoreId(storeIdPath);
 ResultSet rs = index.getResult(storeId);
 System.out.println("开始建立索引。。。。");
 index.indexBuilding(path, storeIdPath, rs);
 Date date2 = new Date();
 System.out.println("耗时："+(date2.getTime()-date1.getTime())+"ms");
 storeId = index.getStoreId(storeIdPath);
 System.out.println(storeId);//打印出这次存储起来的ID
 } catch (Exception e) {
 e.printStackTrace();
 }
 }
 
 public static void buildIndex(String indexFile, String storeIdFile) {
 try {
 String path = indexFile;//索引文件的存放路径
 String storeIdPath = storeIdFile;//存储ID的路径
 String storeId = "";
 storeId = getStoreId(storeIdPath);
 ResultSet rs = getResult(storeId);
 indexBuilding(path, storeIdPath, rs);
 storeId = getStoreId(storeIdPath);
 System.out.println(storeId);//打印出这次存储起来的ID
 } catch (Exception e) {
 e.printStackTrace();
 }
 }
 
 public static ResultSet getResult(String storeId) throws Exception {
 Class.forName("com.mysql.jdbc.Driver").newInstance();
 String url = "jdbc:mysql://localhost:3306/lucenetest";
 String userName = "root";
 String password = "****";
 Connection conn = DriverManager.getConnection(url, userName, password);
 Statement stmt = conn.createStatement();
 String sql = "select * from pd_ugc";
 ResultSet rs = stmt.executeQuery(sql + " where id > '" + storeId + "'order by id");
 return rs;
 }
 
 public static boolean indexBuilding(String path, String storeIdPath, ResultSet rs) {
 try {
 Analyzer luceneAnalyzer = new StandardAnalyzer();
 // 取得存储起来的ID，以判定是增量索引还是重新索引
 boolean isEmpty = true;
 try {
 File file = new File(storeIdPath);
 if (!file.exists()) {
 file.createNewFile();
 }
 FileReader fr = new FileReader(storeIdPath);
 BufferedReader br = new BufferedReader(fr);
 if (br.readLine() != null) {
 isEmpty = false;
 }
 br.close();
 fr.close();
 } catch (IOException e) {
 e.printStackTrace();
 }
 //isEmpty=false表示增量索引
 IndexWriter writer = new IndexWriter(path, luceneAnalyzer, isEmpty);
 String storeId = "";
 boolean indexFlag = false;
 String id;
 String name;
 String address;
 String citycode;
 while (rs.next()) {
 id = rs.getInt("id") + "";
 name = rs.getString("name");
 address = rs.getString("address");
 citycode = rs.getString("citycode");
 writer.addDocument(Document(id, name, address, citycode));
 storeId = id;//将拿到的id给storeId，这种拿法不合理，这里为了方便
 indexFlag = true;
 }
 writer.optimize();
 writer.close();
 if (indexFlag) {
 // 将最后一个的ID存到磁盘文件中
 writeStoreId(storeIdPath, storeId);
 }
 return true;
 } catch (Exception e) {
 e.printStackTrace();
 System.out.println("出错了" + e.getClass() + "\n 错误信息为: " + e.getMessage());
 return false;
 }
 
 }
 
 public static Document Document(String id, String name, String address, String citycode) {
 Document doc = new Document();
 doc.add(new Field("id", id, Field.Store.YES, Field.Index.TOKENIZED));
 doc.add(new Field("name", name, Field.Store.YES, Field.Index.TOKENIZED));//查询字段
 doc.add(new Field("address", address, Field.Store.YES, Field.Index.TOKENIZED));
 doc.add(new Field("citycode", citycode, Field.Store.YES, Field.Index.TOKENIZED));//查询字段
 return doc;
 }
 
 // 取得存储在磁盘中的ID
 public static String getStoreId(String path) {
 String storeId = "";
 try {
 File file = new File(path);
 if (!file.exists()) {
 file.createNewFile();
 }
 FileReader fr = new FileReader(path);
 BufferedReader br = new BufferedReader(fr);
 storeId = br.readLine();
 if (storeId == null || storeId == "") storeId = "0";
 br.close();
 fr.close();
 } catch (Exception e) {
 e.printStackTrace();
 }
 return storeId;
 }
 
 // 将ID写入到磁盘文件中
 public static boolean writeStoreId(String path, String storeId) {
 boolean b = false;
 try {
 File file = new File(path);
 if (!file.exists()) {
 file.createNewFile();
 }
 FileWriter fw = new FileWriter(path);
 PrintWriter out = new PrintWriter(fw);
 out.write(storeId);
 out.close();
 fw.close();
 b = true;
 } catch (IOException e) {
 e.printStackTrace();
 }
 return b;
 }
 }

**3. 索引操作**

Java代码 [ ![复制代码][icon_copy.gif]][_icon_copy.gif]  ![收藏代码][icon_star.png]![spinner.gif][]

1. package index;
2. 
3. import java.io.IOException;
4. import java.io.Reader;
5. import java.io.StringReader;
6. import java.util.ArrayList;
7. import java.util.Date;
8. import java.util.List;
9. 
10. import org.apache.lucene.analysis.Analyzer;
11. import org.apache.lucene.analysis.StopFilter;
12. import org.apache.lucene.analysis.Token;
13. import org.apache.lucene.analysis.TokenStream;
14. import org.apache.lucene.analysis.standard.StandardAnalyzer;
15. import org.apache.lucene.document.Document;
16. import org.apache.lucene.index.CorruptIndexException;
17. import org.apache.lucene.index.IndexReader;
18. import org.apache.lucene.index.Term;
19. import org.apache.lucene.queryParser.MultiFieldQueryParser;
20. import org.apache.lucene.queryParser.ParseException;
21. import org.apache.lucene.queryParser.QueryParser;
22. import org.apache.lucene.search.BooleanClause;
23. import org.apache.lucene.search.BooleanQuery;
24. import org.apache.lucene.search.Hits;
25. import org.apache.lucene.search.IndexSearcher;
26. import org.apache.lucene.search.Query;
27. import org.apache.lucene.search.ScoreDoc;
28. import org.apache.lucene.search.TopDocCollector;
29. import org.apache.lucene.search.highlight.Highlighter;
30. import org.apache.lucene.search.highlight.QueryScorer;
31. import org.apache.lucene.search.highlight.SimpleFragmenter;
32. import org.apache.lucene.search.highlight.SimpleHTMLFormatter;
33. import org.mira.lucene.analysis.IK\_CAnalyzer;
34. 
35. public class IndexUtils \{
36. 
37. //0. 创建增量索引
38. public static void buildIndex(String indexFile, String storeIdFile) \{
39. IncrementIndex.buildIndex(indexFile, storeIdFile);
40. \}
41. 
42. //1. 单字段查询
43. @SuppressWarnings("deprecation")
44. public static List<IndexResult> queryByOneKey(IndexSearcher indexSearcher, String field,
45. String key) \{
46. try \{
47. Date date1 = new Date();
48. QueryParser queryParser = new QueryParser(field, new StandardAnalyzer());
49. Query query = queryParser.parse(key);
50. Hits hits = indexSearcher.search(query);
51. Date date2 = new Date();
52. System.out.println("耗时：" \+ (date2.getTime() - date1.getTime()) + "ms");
53. List<IndexResult> list = new ArrayList<IndexResult>();
54. for (int i = 0; i < hits.length(); i++) \{
55. list.add(getIndexResult(hits.doc(i)));
56. \}
57. return list;
58. \} catch (ParseException e) \{
59. e.printStackTrace();
60. \} catch (IOException e) \{
61. e.printStackTrace();
62. \}
63. return null;
64. \}
65. 
66. //2. 多条件查询。这里实现的是and操作
67. //注：要查询的字段必须是index的
68. //即doc.add(new Field("pid", rs.getString("pid"), Field.Store.YES,Field.Index.TOKENIZED)); 
69. @SuppressWarnings("deprecation")
70. public static List<IndexResult> queryByMultiKeys(IndexSearcher indexSearcher, String\[\] fields,
71. String\[\] keys) \{
72. 
73. try \{
74. BooleanQuery m\_BooleanQuery = new BooleanQuery();
75. if (keys != null && keys.length > 0) \{
76. for (int i = 0; i < keys.length; i++) \{
77. QueryParser queryParser = new QueryParser(fields\[i\], new StandardAnalyzer());
78. Query query = queryParser.parse(keys\[i\]);
79. m\_BooleanQuery.add(query, BooleanClause.Occur.MUST);//and操作
80. \}
81. Hits hits = indexSearcher.search(m\_BooleanQuery);
82. List<IndexResult> list = new ArrayList<IndexResult>();
83. for (int i = 0; i < hits.length(); i++) \{
84. list.add(getIndexResult(hits.doc(i)));
85. \}
86. return list;
87. \}
88. \} catch (ParseException e) \{
89. e.printStackTrace();
90. \} catch (IOException e) \{
91. e.printStackTrace();
92. \}
93. return null;
94. \}
95. 
96. //3.高亮显示 实现了单条件查询
97. //可改造为多条件查询
98. public static List<IndexResult> highlight(IndexSearcher indexSearcher, String key) \{
99. try \{
100. QueryParser queryParser = new QueryParser("name", new StandardAnalyzer());
101. Query query = queryParser.parse(key);
102. TopDocCollector collector = new TopDocCollector(800);
103. indexSearcher.search(query, collector);
104. ScoreDoc\[\] hits = collector.topDocs().scoreDocs;
105. 
106. Highlighter highlighter = null;
107. SimpleHTMLFormatter simpleHTMLFormatter = new SimpleHTMLFormatter("",
108. "");
109. highlighter = new Highlighter(simpleHTMLFormatter, new QueryScorer(query));
110. highlighter.setTextFragmenter(new SimpleFragmenter(200));
111. List<IndexResult> list = new ArrayList<IndexResult>();
112. Document doc;
113. for (int i = 0; i < hits.length; i++) \{
114. //System.out.println(hits\[i\].score);
115. doc = indexSearcher.doc(hits\[i\].doc);
116. TokenStream tokenStream = new StandardAnalyzer().tokenStream("name",
117. new StringReader(doc.get("name")));
118. IndexResult ir = getIndexResult(doc);
119. ir.setName(highlighter.getBestFragment(tokenStream, doc.get("name")));
120. list.add(ir);
121. \}
122. return list;
123. \} catch (ParseException e) \{
124. e.printStackTrace();
125. \} catch (IOException e) \{
126. e.printStackTrace();
127. \}
128. return null;
129. 
130. \}
131. 
132. //4. 多字段查询
133. @SuppressWarnings("deprecation")
134. public static List<IndexResult> queryByMultiFileds(IndexSearcher indexSearcher,
135. String\[\] fields, String key) \{
136. try \{
137. MultiFieldQueryParser mfq = new MultiFieldQueryParser(fields, new StandardAnalyzer());
138. Query query = mfq.parse(key);
139. Hits hits = indexSearcher.search(query);
140. List<IndexResult> list = new ArrayList<IndexResult>();
141. for (int i = 0; i < hits.length(); i++) \{
142. list.add(getIndexResult(hits.doc(i)));
143. \}
144. 
145. return list;
146. \} catch (ParseException e) \{
147. e.printStackTrace();
148. \} catch (IOException e) \{
149. e.printStackTrace();
150. \}
151. return null;
152. \}
153. 
154. //5. 删除索引
155. public static void deleteIndex(String indexFile, String id) throws CorruptIndexException,
156. IOException \{
157. IndexReader indexReader = IndexReader.open(indexFile);
158. indexReader.deleteDocuments(new Term("id", id));
159. indexReader.close();
160. \}
161. 
162. //6. 一元分词
163. @SuppressWarnings("deprecation")
164. public static String Standard\_Analyzer(String str) \{
165. Analyzer analyzer = new StandardAnalyzer();
166. Reader r = new StringReader(str);
167. StopFilter sf = (StopFilter) analyzer.tokenStream("", r);
168. System.out.println("=====StandardAnalyzer====");
169. System.out.println("分析方法：默认没有词只有字（一元分词）");
170. Token t;
171. String results = "";
172. try \{
173. while ((t = sf.next()) != null) \{
174. System.out.println(t.termText());
175. results = results + " " \+ t.termText();
176. \}
177. \} catch (IOException e) \{
178. e.printStackTrace();
179. \}
180. return results;
181. \}
182. 
183. //7. 字典分词
184. @SuppressWarnings("deprecation")
185. public static String ik\_CAnalyzer(String str) \{
186. Analyzer analyzer = new IK\_CAnalyzer();
187. Reader r = new StringReader(str);
188. TokenStream ts = (TokenStream) analyzer.tokenStream("", r);
189. System.out.println("=====IK\_CAnalyzer====");
190. System.out.println("分析方法:字典分词,正反双向搜索");
191. Token t;
192. String results = "";
193. try \{
194. while ((t = ts.next()) != null) \{
195. System.out.println(t.termText());
196. results = results + " " \+ t.termText();
197. \}
198. \} catch (IOException e) \{
199. e.printStackTrace();
200. \}
201. return results;
202. \}
203. 
204. //在结果中搜索
205. public static void queryFromResults() \{
206. 
207. \}
208. 
209. //组装对象
210. public static IndexResult getIndexResult(Document doc) \{
211. IndexResult ir = new IndexResult();
212. ir.setId(doc.get("id"));
213. ir.setName(doc.get("name"));
214. ir.setAddress(doc.get("address"));
215. ir.setCitycode(doc.get("citycode"));
216. return ir;
217. \}
218. \}

package index;
 
 import java.io.IOException;
 import java.io.Reader;
 import java.io.StringReader;
 import java.util.ArrayList;
 import java.util.Date;
 import java.util.List;
 
 import org.apache.lucene.analysis.Analyzer;
 import org.apache.lucene.analysis.StopFilter;
 import org.apache.lucene.analysis.Token;
 import org.apache.lucene.analysis.TokenStream;
 import org.apache.lucene.analysis.standard.StandardAnalyzer;
 import org.apache.lucene.document.Document;
 import org.apache.lucene.index.CorruptIndexException;
 import org.apache.lucene.index.IndexReader;
 import org.apache.lucene.index.Term;
 import org.apache.lucene.queryParser.MultiFieldQueryParser;
 import org.apache.lucene.queryParser.ParseException;
 import org.apache.lucene.queryParser.QueryParser;
 import org.apache.lucene.search.BooleanClause;
 import org.apache.lucene.search.BooleanQuery;
 import org.apache.lucene.search.Hits;
 import org.apache.lucene.search.IndexSearcher;
 import org.apache.lucene.search.Query;
 import org.apache.lucene.search.ScoreDoc;
 import org.apache.lucene.search.TopDocCollector;
 import org.apache.lucene.search.highlight.Highlighter;
 import org.apache.lucene.search.highlight.QueryScorer;
 import org.apache.lucene.search.highlight.SimpleFragmenter;
 import org.apache.lucene.search.highlight.SimpleHTMLFormatter;
 import org.mira.lucene.analysis.IK_CAnalyzer;
 
 public class IndexUtils {
 
 //0. 创建增量索引
 public static void buildIndex(String indexFile, String storeIdFile) {
 IncrementIndex.buildIndex(indexFile, storeIdFile);
 }
 
 //1. 单字段查询
 @SuppressWarnings("deprecation")
 public static List<IndexResult> queryByOneKey(IndexSearcher indexSearcher, String field,
 String key) {
 try {
 Date date1 = new Date();
 QueryParser queryParser = new QueryParser(field, new StandardAnalyzer());
 Query query = queryParser.parse(key);
 Hits hits = indexSearcher.search(query);
 Date date2 = new Date();
 System.out.println("耗时：" + (date2.getTime() - date1.getTime()) + "ms");
 List<IndexResult> list = new ArrayList<IndexResult>();
 for (int i = 0; i < hits.length(); i++) {
 list.add(getIndexResult(hits.doc(i)));
 }
 return list;
 } catch (ParseException e) {
 e.printStackTrace();
 } catch (IOException e) {
 e.printStackTrace();
 }
 return null;
 }
 
 //2. 多条件查询。这里实现的是and操作
 //注：要查询的字段必须是index的
 //即doc.add(new Field("pid", rs.getString("pid"), Field.Store.YES,Field.Index.TOKENIZED)); 
 @SuppressWarnings("deprecation")
 public static List<IndexResult> queryByMultiKeys(IndexSearcher indexSearcher, String[] fields,
 String[] keys) {
 
 try {
 BooleanQuery m_BooleanQuery = new BooleanQuery();
 if (keys != null && keys.length > 0) {
 for (int i = 0; i < keys.length; i++) {
 QueryParser queryParser = new QueryParser(fields[i], new StandardAnalyzer());
 Query query = queryParser.parse(keys[i]);
 m_BooleanQuery.add(query, BooleanClause.Occur.MUST);//and操作
 }
 Hits hits = indexSearcher.search(m_BooleanQuery);
 List<IndexResult> list = new ArrayList<IndexResult>();
 for (int i = 0; i < hits.length(); i++) {
 list.add(getIndexResult(hits.doc(i)));
 }
 return list;
 }
 } catch (ParseException e) {
 e.printStackTrace();
 } catch (IOException e) {
 e.printStackTrace();
 }
 return null;
 }
 
 //3.高亮显示 实现了单条件查询
 //可改造为多条件查询
 public static List<IndexResult> highlight(IndexSearcher indexSearcher, String key) {
 try {
 QueryParser queryParser = new QueryParser("name", new StandardAnalyzer());
 Query query = queryParser.parse(key);
 TopDocCollector collector = new TopDocCollector(800);
 indexSearcher.search(query, collector);
 ScoreDoc[] hits = collector.topDocs().scoreDocs;
 
 Highlighter highlighter = null;
 SimpleHTMLFormatter simpleHTMLFormatter = new SimpleHTMLFormatter("",
 "");
 highlighter = new Highlighter(simpleHTMLFormatter, new QueryScorer(query));
 highlighter.setTextFragmenter(new SimpleFragmenter(200));
 List<IndexResult> list = new ArrayList<IndexResult>();
 Document doc;
 for (int i = 0; i < hits.length; i++) {
 //System.out.println(hits[i].score);
 doc = indexSearcher.doc(hits[i].doc);
 TokenStream tokenStream = new StandardAnalyzer().tokenStream("name",
 new StringReader(doc.get("name")));
 IndexResult ir = getIndexResult(doc);
 ir.setName(highlighter.getBestFragment(tokenStream, doc.get("name")));
 list.add(ir);
 }
 return list;
 } catch (ParseException e) {
 e.printStackTrace();
 } catch (IOException e) {
 e.printStackTrace();
 }
 return null;
 
 }
 
 //4. 多字段查询
 @SuppressWarnings("deprecation")
 public static List<IndexResult> queryByMultiFileds(IndexSearcher indexSearcher,
 String[] fields, String key) {
 try {
 MultiFieldQueryParser mfq = new MultiFieldQueryParser(fields, new StandardAnalyzer());
 Query query = mfq.parse(key);
 Hits hits = indexSearcher.search(query);
 List<IndexResult> list = new ArrayList<IndexResult>();
 for (int i = 0; i < hits.length(); i++) {
 list.add(getIndexResult(hits.doc(i)));
 }
 
 return list;
 } catch (ParseException e) {
 e.printStackTrace();
 } catch (IOException e) {
 e.printStackTrace();
 }
 return null;
 }
 
 //5. 删除索引
 public static void deleteIndex(String indexFile, String id) throws CorruptIndexException,
 IOException {
 IndexReader indexReader = IndexReader.open(indexFile);
 indexReader.deleteDocuments(new Term("id", id));
 indexReader.close();
 }
 
 //6. 一元分词
 @SuppressWarnings("deprecation")
 public static String Standard_Analyzer(String str) {
 Analyzer analyzer = new StandardAnalyzer();
 Reader r = new StringReader(str);
 StopFilter sf = (StopFilter) analyzer.tokenStream("", r);
 System.out.println("=====StandardAnalyzer====");
 System.out.println("分析方法：默认没有词只有字（一元分词）");
 Token t;
 String results = "";
 try {
 while ((t = sf.next()) != null) {
 System.out.println(t.termText());
 results = results + " " + t.termText();
 }
 } catch (IOException e) {
 e.printStackTrace();
 }
 return results;
 }
 
 //7. 字典分词
 @SuppressWarnings("deprecation")
 public static String ik_CAnalyzer(String str) {
 Analyzer analyzer = new IK_CAnalyzer();
 Reader r = new StringReader(str);
 TokenStream ts = (TokenStream) analyzer.tokenStream("", r);
 System.out.println("=====IK_CAnalyzer====");
 System.out.println("分析方法:字典分词,正反双向搜索");
 Token t;
 String results = "";
 try {
 while ((t = ts.next()) != null) {
 System.out.println(t.termText());
 results = results + " " + t.termText();
 }
 } catch (IOException e) {
 e.printStackTrace();
 }
 return results;
 }
 
 //在结果中搜索
 public static void queryFromResults() {
 
 }
 
 //组装对象
 public static IndexResult getIndexResult(Document doc) {
 IndexResult ir = new IndexResult();
 ir.setId(doc.get("id"));
 ir.setName(doc.get("name"));
 ir.setAddress(doc.get("address"));
 ir.setCitycode(doc.get("citycode"));
 return ir;
 }
 }

**查询索引结果对象：IndexResult**

Java代码 [ ![复制代码][icon_copy.gif]][_icon_copy.gif]  ![收藏代码][icon_star.png]![spinner.gif][]

1.  package index;
2.  
3.  public class IndexResult \{
4.  
5.  private String id;
6.  
7.  private String name;
8.  
9.  private String address;
10. 
11. private String citycode;
12. 
13. 
14. public String getId() \{
15. return id;
16. \}
17. public void setId(String id) \{
18. this.id = id;
19. \}
20. public String getName() \{
21. return name;
22. \}
23. public void setName(String name) \{
24. this.name = name;
25. \}
26. 
27. 
28. public String getAddress() \{
29. return address;
30. \}
31. public void setAddress(String address) \{
32. this.address = address;
33. \}
34. public String getCitycode() \{
35. return citycode;
36. \}
37. public void setCitycode(String citycode) \{
38. this.citycode = citycode;
39. \}
40. 
41. \}

package index;
    
    public class IndexResult {
    
        private String id;
    
        private String name;
    
        private String address;
    
        private String citycode;
    
        
        public String getId() {
            return id;
        }
        public void setId(String id) {
            this.id = id;
        }
        public String getName() {
            return name;
        }
        public void setName(String name) {
            this.name = name;
        }
    
        
        public String getAddress() {
            return address;
        }
        public void setAddress(String address) {
            this.address = address;
        }
        public String getCitycode() {
            return citycode;
        }
        public void setCitycode(String citycode) {
            this.citycode = citycode;
        }
        
    }

**4. 测试类**

Java代码 [ ![复制代码][icon_copy.gif]][_icon_copy.gif]  ![收藏代码][icon_star.png]![spinner.gif][]

1. package test;
2. 
3. /\*\*
4. \* $Id$
5. \* Copyright 2009-2010 Oak Pacific Interactive. All rights reserved.
6. \*/
7. 
8. import index.IndexResult;
9. import index.IndexUtils;
10. 
11. import java.util.Date;
12. import java.util.List;
13. 
14. import org.apache.lucene.search.IndexSearcher;
15. 
16. public class Test \{
17. 
18. //存放索引文件
19. private static String indexFile = "E:\\\\workspace2\\\\Test\\\\lucene\_test\\\\poiIdext";
20. 
21. //存放id
22. private static String storeIdFile = "E:\\\\workspace2\\\\Test\\\\lucene\_test\\\\storeId.txt";
23. 
24. public static void main(String\[\] args) throws Exception \{
25. //0. 创建增量索引
26. IndexUtils.buildIndex(indexFile, storeIdFile);
27. 
28. IndexSearcher indexSearcher = new IndexSearcher(indexFile);
29. String key = IndexUtils.ik\_CAnalyzer("静安中心");
30. 
31. //1.单字段查询
32. Date date1 = new Date();
33. List<IndexResult> list = IndexUtils.queryByOneKey(indexSearcher, "name", key);
34. Date date2 = new Date();
35. System.out.println("耗时：" \+ (date2.getTime() - date1.getTime()) + "ms\\n" \+ list.size()
36. \+ "条=======================================单字段查询");
37. //printResults(list);
38. 
39. //2.多条件查询
40. String\[\] fields = \{ "name", "citycode" \};
41. String\[\] keys = \{ IndexUtils.ik\_CAnalyzer("静安中心"), "0000" \};
42. date1 = new Date();
43. list = IndexUtils.queryByMultiKeys(indexSearcher, fields, keys);
44. date2 = new Date();
45. System.out.println("耗时：" \+ (date2.getTime() - date1.getTime()) + "ms\\n" \+ list.size()
46. \+ "条\\n===============================多条件查询");
47. printResults(list);
48. 
49. //3.高亮显示 单字段查询
50. System.out.println("\\n\\n");
51. date1 = new Date();
52. list = IndexUtils.highlight(indexSearcher, key);
53. date2 = new Date();
54. System.out.println("耗时：" \+ (date2.getTime() - date1.getTime()) + "ms\\n" \+ list.size()
55. \+ "条\\n======================================高亮显示");
56. // printResults(list);
57. 
58. //4. 多字段查询
59. date1 = new Date();
60. list = IndexUtils.queryByMultiFileds(indexSearcher, fields, key);
61. date2 = new Date();
62. System.out.println("耗时：" \+ (date2.getTime() - date1.getTime()) + "ms\\n" \+ list.size()
63. \+ "条\\n=====================================多字段查询");
64. // printResults(list);
65. 
66. //5. 删除索引中的字段 根据id进行删除
67. IndexUtils.deleteIndex(indexFile, "123");
68. \}
69. 
70. //打印结果
71. public static void printResults(List<IndexResult> list) \{
72. if (list != null && list.size() > 0) \{
73. for (int i = 0; i < list.size(); i++) \{
74. System.out.println(list.get(i).getId() + "," \+ list.get(i).getName() + ","
75. \+ list.get(i).getAddress() + "," \+ list.get(i).getCitycode()+"--->"\+i);
76. \}
77. \}
78. \}
79. \}

package test;
 
 /**
 * $Id$
 * Copyright 2009-2010 Oak Pacific Interactive. All rights reserved.
 */
 
 import index.IndexResult;
 import index.IndexUtils;
 
 import java.util.Date;
 import java.util.List;
 
 import org.apache.lucene.search.IndexSearcher;
 
 public class Test {
 
 //存放索引文件
 private static String indexFile = "E:\\workspace2\\Test\\lucene_test\\poiIdext";
 
 //存放id
 private static String storeIdFile = "E:\\workspace2\\Test\\lucene_test\\storeId.txt";
 
 public static void main(String[] args) throws Exception {
 //0. 创建增量索引
 IndexUtils.buildIndex(indexFile, storeIdFile);
 
 IndexSearcher indexSearcher = new IndexSearcher(indexFile);
 String key = IndexUtils.ik_CAnalyzer("静安中心");
 
 //1.单字段查询
 Date date1 = new Date();
 List<IndexResult> list = IndexUtils.queryByOneKey(indexSearcher, "name", key);
 Date date2 = new Date();
 System.out.println("耗时：" + (date2.getTime() - date1.getTime()) + "ms\n" + list.size()
 + "条=======================================单字段查询");
 //printResults(list);
 
 //2.多条件查询
 String[] fields = { "name", "citycode" };
 String[] keys = { IndexUtils.ik_CAnalyzer("静安中心"), "0000" };
 date1 = new Date();
 list = IndexUtils.queryByMultiKeys(indexSearcher, fields, keys);
 date2 = new Date();
 System.out.println("耗时：" + (date2.getTime() - date1.getTime()) + "ms\n" + list.size()
 + "条\n===============================多条件查询");
 printResults(list);
 
 //3.高亮显示 单字段查询
 System.out.println("\n\n");
 date1 = new Date();
 list = IndexUtils.highlight(indexSearcher, key);
 date2 = new Date();
 System.out.println("耗时：" + (date2.getTime() - date1.getTime()) + "ms\n" + list.size()
 + "条\n======================================高亮显示");
 // printResults(list);
 
 //4. 多字段查询
 date1 = new Date();
 list = IndexUtils.queryByMultiFileds(indexSearcher, fields, key);
 date2 = new Date();
 System.out.println("耗时：" + (date2.getTime() - date1.getTime()) + "ms\n" + list.size()
 + "条\n=====================================多字段查询");
 // printResults(list);
 
 //5. 删除索引中的字段 根据id进行删除
 IndexUtils.deleteIndex(indexFile, "123");
 }
 
 //打印结果
 public static void printResults(List<IndexResult> list) {
 if (list != null && list.size() > 0) {
 for (int i = 0; i < list.size(); i++) {
 System.out.println(list.get(i).getId() + "," + list.get(i).getName() + ","
 + list.get(i).getAddress() + "," + list.get(i).getCitycode()+"--->"+i);
 }
 }
 }
 }

**5. 其它**

全文索引：

目前的情况是，搜索hello,"hello world"、"hi hello, how are you"但"worldhello"显示不出来

默认情况下，QueryParser不支持通配符打头的查询（如，\*ook）。不过在Lucene 2.1版本以后，他们可以通过调用QueryParser.setAllowLeadingWildcard( true )的 方法打开这一功能。注意，这是一个开销很大的操作：它需要扫描索引中全部记号的列表，来寻找匹配这个模式的词。**(译注：高效支持这种后缀查询的办法是，建立反序的记号表，Lucene没有实现这一模式。)http://www.codechina.org/faq/show/42/**

支持空格分词搜索："厕所 26 沈阳" 这是三个词

不支持：“厕所沈阳”这是一个词

### [Lucene能实现“在搜索结果中搜索”的功能么，也就是说第二个搜索仅在第一个搜索结果中进行？][Lucene] ###

http://www.codechina.org/faq/show/63/

可以。主要有两种做法：

*  使用QueryFilter把第一个查询当作一个过滤器处理。（你可以在Lucene的邮件列表里面搜索 QueryFilter， Doug Cutting（Lucene的最初作者）反对这种做法。）
 *  用BooleanQuery把前后两个查询结合起来，前一个查询使用 required选项。

我们推荐使用BooleanQuery的方法。

============

// 创建标准文本分析器， 标准的是可以支持的中文的

Analyzer luceneAnalyzer = new StandardAnalyzer();

indexWriter = new IndexWriter(indexDir, luceneAnalyzer, true);

// 可以说是创建一个新的写入工具

// 第一个参数是要索引建立在哪个目录里

// 第二个参数是新建一个文本分析器,这里用的是标准的大家也可以自己写一个

// 第三个参数如果是true，在建立索引之前先将c: \\\\index目录清空

poi\_data\_ugc搜索中，索引放在内存里还是磁盘上？？？？

**针对于lucene使用和优化**

http://hi.baidu.com/lewutian/blog/item/48a86d03de58b984d43f7c1b.html

ucene入门实例(1):索引文本文件

http://www.java3z.com/cwbwebhome/article/article5/51021.html

[http_footman265.iteye.com_blog_849744]: http://footman265.iteye.com/blog/849744
[http_lianj-lee.iteye.com_category_69005_show_full_true]: http://lianj-lee.iteye.com/category/69005?show_full=true
[http_269181927.iteye.com_blog_789779]: http://269181927.iteye.com/blog/789779
[icon_copy.gif]: http://zzqrj.iteye.com/images/icon_copy.gif
[_icon_copy.gif]: http://zzqrj.iteye.com/blog/849719#
[icon_star.png]: http://zzqrj.iteye.com/images/icon_star.png
[spinner.gif]: /images/20220805/34cdf9273c1045fbbbd1794ef25485e7.png
[Lucene]: http://www.codechina.org/faq/show/62/