*lucene索引_的删除和更新

1 package cn.hk.index;
2
3 import java.io.File;
4 import java.io.IOException;
5
6 import org.apache.lucene.analysis.standard.StandardAnalyzer;
7 import org.apache.lucene.document.Document;
8 import org.apache.lucene.document.Field;
9 import org.apache.lucene.index.CorruptIndexException;
10 import org.apache.lucene.index.IndexReader;
11 import org.apache.lucene.index.IndexWriter;
12 import org.apache.lucene.index.IndexWriterConfig;
13 import org.apache.lucene.index.StaleReaderException;
14 import org.apache.lucene.index.Term;
15 import org.apache.lucene.store.Directory;
16 import org.apache.lucene.store.FSDirectory;
17 import org.apache.lucene.store.LockObtainFailedException;
18 import org.apache.lucene.util.Version;
19
20 public class IndexUtil {
21 private String[] ids &＃61; {"1","2","3","4","5","6"};
22 private String[] emails &＃61; {"aa&＃64;hk.arg","bb&＃64;hk.org","cc&＃64;hk.arg",
23 "dd&＃64;hk.org","ee&＃64;hk.org","ff&＃64;hk.org"};
24 private String[] content &＃61; {
25 "welcome to visited the space","hello boy","my name is aa","i like football",
26 "I like football and I like Basketball too","I like movie and swim"
27 };
28 private int[] attachs &＃61; {2,3,1,4,5,5};
29 private String[] names &＃61; {"zhangsan","lisi","john","mike","jetty","jake"};
30
31 private Directory directory &＃61; null;
32
33 public IndexUtil(){
34 try {
35 directory &＃61; FSDirectory.open(new File("d://lucene/index02"));
36 } catch (IOException e) {
37 e.printStackTrace();
38 }
39 }
40
41 public void update(){
42 IndexWriter writer &＃61;null;
43 try {
44 writer &＃61; new IndexWriter(directory,
45 new IndexWriterConfig(Version.LUCENE_35,new StandardAnalyzer(Version.LUCENE_35)));
46 /*
47 * lucene并没有提供更新的方法&＃xff0c;这里的更新其实是提供如下两个操作&＃xff1a;
48 * 先删除之后再添加
49 */
50 Document doc &＃61; new Document();
51 doc.add(new Field("id","11",Field.Store.YES,Field.Index.NOT_ANALYZED_NO_NORMS));
52 doc.add(new Field("email",emails[0],Field.Store.YES,Field.Index.NOT_ANALYZED));
53 doc.add(new Field("content",content[0],Field.Store.NO,Field.Index.ANALYZED));
54 doc.add(new Field("name",names[0],Field.Store.YES,Field.Index.NOT_ANALYZED_NO_NORMS));
55 writer.updateDocument(new Term("id","1"),doc);
56 } catch (CorruptIndexException e) {
57 e.printStackTrace();
58 } catch (LockObtainFailedException e) {
59 e.printStackTrace();
60 } catch (IOException e) {
61 e.printStackTrace();
62 }finally{
63 if(writer !&＃61; null)
64 try {
65 writer.close();
66 } catch (CorruptIndexException e) {
67 e.printStackTrace();
68 } catch (IOException e) {
69 e.printStackTrace();
70 }
71 }
72
73 }
74
75
76 public void merge(){
77 IndexWriter writer &＃61; null;
78 try {
79 writer &＃61; new IndexWriter(directory,
80 new IndexWriterConfig(Version.LUCENE_35, new StandardAnalyzer(Version.LUCENE_35)));
81 //会将索引合并为2段&＃xff0c;这两段中的被删除的数据会被清空
82 //特别注意&＃xff1a;此处在lucene3.5后不建议使用&＃xff0c;因为会消耗大量的开销&＃xff0c;
83 //lucene会根据情况自动处理的
84 writer.forceMerge(2);
85 } catch (CorruptIndexException e) {
86 e.printStackTrace();
87 } catch (LockObtainFailedException e) {
88 e.printStackTrace();
89 } catch (IOException e) {
90 e.printStackTrace();
91 }finally{
92 if(writer !&＃61; null)
93 try {
94 writer.close();
95 } catch (CorruptIndexException e) {
96 e.printStackTrace();
97 } catch (IOException e) {
98 e.printStackTrace();
99 }
100 }
101 }
102
103 public void forceDelete(){
104 IndexWriter writer &＃61; null;
105 try {
106 writer &＃61; new IndexWriter(directory,
107 new IndexWriterConfig(Version.LUCENE_35,new StandardAnalyzer(Version.LUCENE_35)));
108 writer.forceMergeDeletes();
109 } catch (CorruptIndexException e) {
110 e.printStackTrace();
111 } catch (LockObtainFailedException e) {
112 e.printStackTrace();
113 } catch (IOException e) {
114 e.printStackTrace();
115 }finally{
116 if(writer !&＃61; null)
117 try {
118 writer.close();
119 } catch (CorruptIndexException e) {
120 e.printStackTrace();
121 } catch (IOException e) {
122 e.printStackTrace();
123 }
124 }
125 }
126
127
128 public void undelete(){
129 //使用IndexReader进行恢复
130 try {
131 IndexReader reader &＃61; IndexReader.open(directory,false);
132 //回复时&＃xff0c;必须把IndexReader的只读&＃xff08;readyonly&＃xff09;设置为FALSE
133 reader.undeleteAll();
134 reader.close();
135 } catch (StaleReaderException e) {
136
137 e.printStackTrace();
138 } catch (CorruptIndexException e) {
139
140 e.printStackTrace();
141 } catch (LockObtainFailedException e) {
142
143 e.printStackTrace();
144 } catch (IOException e) {
145 // TODO Auto-generated catch block
146 e.printStackTrace();
147 }
148 }
149
150
151
152
153
154 public void delete(){
155 IndexWriter writer &＃61; null;
156 try {
157 writer &＃61; new IndexWriter(directory,
158 new IndexWriterConfig(Version.LUCENE_35, new StandardAnalyzer(Version.LUCENE_35)));
159 //删除ID为1的文档
160 //参数可以是一个选项&＃xff0c;可以是一个Query&＃xff0c;也可以是一个Term&＃xff0c;Term是一个精确查找的值
161 //此时删除的文档并不会被完全删除&＃xff0c;而是存储在回收站中的&＃xff0c;可以恢复
162 writer.deleteDocuments(new Term("id","1"));
163 } catch (CorruptIndexException e) {
164
165 e.printStackTrace();
166 } catch (LockObtainFailedException e) {
167
168 e.printStackTrace();
169 } catch (IOException e) {
170
171 e.printStackTrace();
172 }finally{
173 if(writer !&＃61; null)
174 try {
175 writer.close();
176 } catch (CorruptIndexException e) {
177
178 e.printStackTrace();
179 } catch (IOException e) {
180
181 e.printStackTrace();
182 }
183 }
184 }
185
186
187
188 public void query(){
189 try {
190 IndexReader reader &＃61; IndexReader.open(directory);
191 //通过reader可以获取文档的数量
192 System.out.println("numDocs:" &＃43; reader.numDocs());
193 System.out.println("maxDocs" &＃43; reader.maxDoc());
194 System.out.println("deleteDocs:" &＃43; reader.numDeletedDocs());
195 reader.close();
196 } catch (CorruptIndexException e) {
197
198 e.printStackTrace();
199 } catch (IOException e) {
200
201 e.printStackTrace();
202 }
203 }
204
205
206 public void index(){
207 IndexWriter writer &＃61; null;
208 try {
209 writer &＃61; new IndexWriter(directory,new IndexWriterConfig(Version.LUCENE_35, new StandardAnalyzer(Version.LUCENE_35)));
210 Document doc &＃61; null;
211 for(int i&＃61;0;i){
212 doc &＃61; new Document();
213 doc.add(new Field("id",ids[i],Field.Store.YES,Field.Index.NOT_ANALYZED_NO_NORMS));
214 doc.add(new Field("email",emails[i],Field.Store.YES,Field.Index.NOT_ANALYZED));
215 doc.add(new Field("content",content[i],Field.Store.NO,Field.Index.ANALYZED));
216 doc.add(new Field("name",names[i],Field.Store.YES,Field.Index.NOT_ANALYZED_NO_NORMS));
217 writer.addDocument(doc);
218 }
219 } catch (CorruptIndexException e) {
220 e.printStackTrace();
221 } catch (LockObtainFailedException e) {
222 e.printStackTrace();
223 } catch (IOException e) {
224 e.printStackTrace();
225 }finally{
226 if(writer !&＃61; null)
227 try {
228 writer.close();
229 } catch (CorruptIndexException e) {
230
231 e.printStackTrace();
232 } catch (IOException e) {
233
234 e.printStackTrace();
235 }
236
237 }
238 }
239
240 }

1 package cn.hk.test;
2
3 import org.junit.Test;
4
5 import cn.hk.index.IndexUtil;
6
7 public class TestIndex {
8
9 &＃64;Test
10 public void testIndex(){
11 IndexUtil iu &＃61; new IndexUtil();
12 iu.index();
13 }
14
15 &＃64;Test
16 public void testQuery(){
17 IndexUtil iu &＃61; new IndexUtil();
18 iu.query();
19 }
20
21 &＃64;Test
22 public void testDelete(){
23 IndexUtil iu &＃61; new IndexUtil();
24 iu.delete();
25 }
26
27 &＃64;Test
28 public void testUnDelete(){
29 IndexUtil iu &＃61; new IndexUtil();
30 iu.undelete();
31 }
32
33 &＃64;Test
34 public void testForceDelete(){
35 IndexUtil iu &＃61; new IndexUtil();
36 iu.forceDelete();
37 }
38
39 public void testMerge(){
40 IndexUtil iu &＃61; new IndexUtil();
41 iu.merge();
42 }
43
44 &＃64;Test
45 public void testUpdate(){
46 IndexUtil iu &＃61; new IndexUtil();
47 iu.update();
48 }
49 }