Lucene

 1 package xyz.zerone.lucene.pojo; 2 ?3 public class Book { 4 ????private Integer id; 5 ????private String name; 6 ????private Float price; 7 ????private String pic; 8 ????private String description; 9 ????public Integer getId() {10 ????????return id;11 ????}12 ????public void setId(Integer id) {13 ????????this.id = id;14 ????}15 ????public String getName() {16 ????????return name;17 ????}18 ????public void setName(String name) {19 ????????this.name = name;20 ????}21 ????public Float getPrice() {22 ????????return price;23 ????}24 ????public void setPrice(Float price) {25 ????????this.price = price;26 ????}27 ????public String getPic() {28 ????????return pic;29 ????}30 ????public void setPic(String pic) {31 ????????this.pic = pic;32 ????}33 ????public String getDescription() {34 ????????return description;35 ????}36 ????public void setDescription(String description) {37 ????????this.description = description;38 ????}39 ????@Override40 ????public String toString() {41 ????????return "Book [id=" + id + ", name=" + name + ", price=" + price + ", pic=" + pic + ", description="42 ????????????????+ description + "]";43 ????}44 ????45 }

 1 package xyz.zerone.lucene.dao; 2 ?3 import java.sql.Connection; 4 import java.sql.DriverManager; 5 import java.sql.ResultSet; 6 import java.util.ArrayList; 7 import java.util.List; 8 import java.sql.PreparedStatement; 9 10 11 import xyz.zerone.lucene.pojo.Book;12 13 public class BookDaoImp implements BookDao {14 ????private static String sql = "select * from book";15 16 ????@Override17 ????public List<Book> findBookAll() throws Exception {18 ????????Connection connection = null;19 ????????PreparedStatement preparedStatement = null;20 ????????ResultSet resultSet = null;21 ????????List<Book> list = new ArrayList<Book>();22 ????????try {23 ????????????Class.forName("com.mysql.jdbc.Driver");24 ????????????connection = DriverManager.getConnection("jdbc:mysql://192.168.3.8:3306/lucenedb", "root", "123456");25 ????????????preparedStatement = connection.prepareStatement(sql);26 ????????????ResultSet rs = preparedStatement.executeQuery();27 ????????????while (rs.next()) {28 ????????????????Book book = new Book();29 ????????????????book.setId(rs.getInt("id"));30 ????????????????book.setName(rs.getString("name"));31 ????????????????book.setPrice(rs.getFloat("price"));32 ????????????????book.setPic(rs.getString("pic"));33 ????????????????book.setDescription(rs.getString("description"));34 ????????????????list.add(book);35 ????????????}36 ????????} catch (Exception e) {37 ????????????e.printStackTrace();38 ????????}39 ????????return list;40 ????}41 42 }

 ?1 package xyz.zerone.lucene.first; ?2 ??3 import java.io.File; ?4 import java.io.IOException; ?5 import java.util.ArrayList; ?6 import java.util.List; ?7 ??8 import org.apache.lucene.analysis.Analyzer; ?9 import org.apache.lucene.analysis.standard.StandardAnalyzer; 10 import org.apache.lucene.document.Document; 11 import org.apache.lucene.document.Field.Store; 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.classic.ParseException; 16 import org.apache.lucene.queryparser.classic.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.document.FloatField; 22 import org.apache.lucene.document.StoredField; 23 import org.apache.lucene.document.StringField; 24 import org.apache.lucene.document.TextField; 25 import org.apache.lucene.store.Directory; 26 import org.apache.lucene.store.FSDirectory; 27 import org.apache.lucene.util.Version; 28 import org.apache.lucene.index.Term; 29 import org.junit.Test; 30 ?31 import xyz.zerone.lucene.dao.BookDaoImp; 32 import xyz.zerone.lucene.pojo.Book; 33 ?34 public class LuceneCore { 35 ????// 创建索引库生成到指定目录中 36 ????@Test 37 ????public void createIndexFromDb() throws Exception { 38 ????????// 定义List存储document 39 ????????List<Document> docs = new ArrayList<Document>(); 40 ????????// 从数据库获取book表的集合数据 41 ????????List<Book> bookList = new BookDaoImp().findBookAll(); 42 ????????for (Book book : bookList) { 43 ????????????// 创建Document 44 ????????????Document doc = new Document(); 45 ????????????// 创建Field域 46 ????????????// -创建book表字段id的field域 47 ????????????// --参数：域名、域中的value值、是否存储到文件系统 48 ????????????/** 49 ?????????????* 根据实际的需求： 这里的Field属性设置可以有三种（是否分词、是否索引、是否存储）； 详见createAutoIndexDate(); 50 ?????????????*/ 51 ????????????TextField id = new TextField("id", book.getId().toString(), Store.YES); 52 ????????????TextField name = new TextField("name", book.getName(), Store.YES); 53 ????????????FloatField price = new FloatField("price", book.getPrice(), Store.YES); 54 ????????????TextField pic = new TextField("pic", book.getPic(), Store.YES); 55 ????????????TextField description = new TextField("description", book.getDescription(), Store.YES); 56 ????????????// 将field域加入到documet中 57 ????????????doc.add(id); 58 ????????????doc.add(name); 59 ????????????doc.add(price); 60 ????????????doc.add(pic); 61 ????????????doc.add(description); 62 ????????????// 将document加入集合 63 ????????????docs.add(doc); 64 ????????} 65 ????????// 创建一个标准的分词器 66 ????????Analyzer analyzer = new StandardAnalyzer(); 67 ????????// 创建索引目录的流对象，指定索引库存放位置 68 ????????Directory d = FSDirectory.open(new File("C:\\Users\\dangxiaopeng\\Desktop\\LuceneIndexData")); 69 ????????// IndexWriter配置对象 70 ????????// 参数：lucene版本、分词器 71 ????????IndexWriterConfig conf = new IndexWriterConfig(Version.LUCENE_4_10_3, analyzer); 72 ????????// 创建索引操作对象，提供了很多方法操作索引文件（添加、修改、删除） 73 ????????IndexWriter indexWriter = new IndexWriter(d, conf); 74 ????????// 通过indexWriter创建索引 75 ????????for (Document doc : docs) { 76 ????????????indexWriter.addDocument(doc); 77 ????????} 78 ????????indexWriter.commit(); 79 ????????indexWriter.close(); 80 ????} 81 ?82 ????// 根据实际需求创建索引库生成到指定目录中 83 ????@Test 84 ????public void createAutoIndexFromDb() throws Exception { 85 ????????// 定义List存储document 86 ????????List<Document> docs = new ArrayList<Document>(); 87 ????????// 从数据库获取book表的集合数据 88 ????????List<Book> bookList = new BookDaoImp().findBookAll(); 89 ????????for (Book book : bookList) { 90 ????????????// 创建Document 91 ????????????Document doc = new Document(); 92 ????????????// 创建Field域 93 ????????????// -创建book表字段id的field域 94 ????????????// --参数：域名、域中的value值、是否存储到文件系统 95 ????????????// 图书id，不要分词，要索引，要存储 96 ????????????StringField id = new StringField("id", book.getId().toString(), Store.YES); 97 ????????????// 图书名称，要分词，要索引，要存储 98 ????????????TextField name = new TextField("name", book.getName(), Store.YES); 99 ????????????// 图书价格，要分词（Lucene需要的对价格数字特殊处理分词，以便处理范围查询），要索引，要存储100 ????????????FloatField price = new FloatField("price", book.getPrice(), Store.YES);101 ????????????// 图书图片，不要分词，不要索引，要存储102 ????????????StoredField pic = new StoredField("pic", book.getPic());103 ????????????// 图书描述，要分词，要索引，不要存储104 ????????????TextField description = new TextField("description", book.getDescription(), Store.YES);105 ????????????// 将field域加入到documet中106 ????????????doc.add(id);107 ????????????doc.add(name);108 ????????????doc.add(price);109 ????????????doc.add(pic);110 ????????????doc.add(description);111 ????????????// 将document加入集合112 ????????????docs.add(doc);113 ????????}114 ????????// 创建一个标准的分词器115 ????????Analyzer analyzer = new StandardAnalyzer();116 ????????// 创建索引目录的流对象，指定索引库存放位置117 ????????Directory d = FSDirectory.open(new File("C:\\Users\\dangxiaopeng\\Desktop\\LuceneIndexData"));118 ????????// IndexWriter配置对象119 ????????// 参数：lucene版本、分词器120 ????????IndexWriterConfig conf = new IndexWriterConfig(Version.LUCENE_4_10_3, analyzer);121 ????????// 创建索引操作对象，提供了很多方法操作索引文件（添加、修改、删除）122 ????????IndexWriter indexWriter = new IndexWriter(d, conf);123 ????????// 通过indexWriter创建索引124 ????????for (Document doc : docs) {125 ????????????indexWriter.addDocument(doc);126 ????????}127 ????????indexWriter.commit();128 ????????indexWriter.close();129 ????}130 131 ????// 删除索引132 ????@Test133 ????public void deleteIndex() throws IOException, ParseException {134 135 ????????// 调用indexWriter中删除索引方法136 137 ????????// 创建分词器138 ????????Analyzer analyzer = new StandardAnalyzer();139 140 ????????// 创建索引目录 的流对象,指定索引目录 的位置141 ????????Directory d = FSDirectory.open(new File("C:\\Users\\dangxiaopeng\\Desktop\\LuceneIndexData"));142 143 ????????// IndexWriter配置对象144 ????????// 参数：lucene的版本，分词器145 ????????IndexWriterConfig conf = new IndexWriterConfig(Version.LUCENE_4_10_3, analyzer);146 147 ????????// 创建indexWriter148 ????????IndexWriter indexWriter = new IndexWriter(d, conf);149 150 ????????// 删除全部索引151 ????????// indexWriter.deleteAll();152 153 ????????// 查询分析器154 ????????// 第一个参数：指定默认搜索的域,第二个：分词器155 ????????QueryParser queryParser = new QueryParser("description", analyzer);156 157 ????????// 创建查询对象158 ????????Query query = queryParser.parse("description:java");159 ????????// 删除符合条件的索引，删除符合query查询的所有document160 ????????indexWriter.deleteDocuments(query);161 ????????// 提交162 ????????indexWriter.commit();163 ????????// 关闭资源164 ????????indexWriter.close();165 166 ????}167 168 ????// 更新索引169 ????@Test170 ????public void updateIndex() throws IOException {171 ????????// 调用indexWriter中更新索引方法172 ????????// 创建分词器173 ????????Analyzer analyzer = new StandardAnalyzer();174 175 ????????// 创建索引目录 的流对象,指定索引目录 的位置176 ????????Directory d = FSDirectory.open(new File("C:\\Users\\dangxiaopeng\\Desktop\\LuceneIndexData"));177 178 ????????// IndexWriter配置对象179 ????????// 参数：lucene的版本，分词器180 ????????IndexWriterConfig conf = new IndexWriterConfig(Version.LUCENE_4_10_3, analyzer);181 182 ????????// 创建indexWriter183 ????????IndexWriter indexWriter = new IndexWriter(d, conf);184 185 ????????// 创建一个term作为查询条件186 ????????// 参数：field域名称，值187 ????????Term term = new Term("id", "1");188 189 ????????// 创建document，新的document，替换id等的1的document190 ????????Document doc = new Document();191 ????????// 图书id，不要分词，要索引、要存储192 ????????StringField id = new StringField("id", "1".toString(), Store.YES);193 194 ????????// 图书名称：要分词，要索引，要存储195 ????????TextField name = new TextField("name", "java编程思想第三版", Store.YES);196 197 ????????doc.add(id);198 ????????doc.add(name);199 200 ????????// 更新思路：根据term的信息查询document，找到之后删除document，添加doc中的添加到索引库201 ????????// 总之：先查询、再删除、再添加，建议根据主键field查询document。202 ????????indexWriter.updateDocument(term, doc);203 ????????// 提交204 ????????indexWriter.commit();205 ????????// 关闭资源206 ????????indexWriter.close();207 ????}208 209 ????// 搜索索引210 ????@Test211 ????public void searchIndex() throws ParseException, IOException {212 ????????// 分词，搜索过程使用的分词器要和创建索引时使用的分词器一致213 ????????Analyzer analyzer = new StandardAnalyzer();214 ????????// 查询分析器215 ????????// 参数：指定默认搜索field域、分词器216 ????????QueryParser queryParser = new QueryParser("description", analyzer);217 ????????// 创建查询对象(这里是使用了查询语法指定了description域如果不指定按照上面默认的field域)218 ????????Query query = queryParser.parse("description:java");219 ????????// 创建索引目录的流对象，指定索引目录位置220 ????????Directory d = FSDirectory.open(new File("C:\\Users\\dangxiaopeng\\Desktop\\LuceneIndexData"));221 ????????// 索引读取对象222 ????????// 指定读取索引的目录223 ????????IndexReader indexReader = IndexReader.open(d);224 ????????// 索引搜索对象225 ????????IndexSearcher indexSearcher = new IndexSearcher(indexReader);226 ????????// 执行搜索227 ????????// 参数：query查询对象、取出匹配度高的前n条记录228 ????????TopDocs topDocs = indexSearcher.search(query, 100);229 ????????// 取出匹配上的文档230 ????????ScoreDoc[] scoreDocs = topDocs.scoreDocs;231 ????????for (ScoreDoc scoreDoc : scoreDocs) {232 ????????????// document的id233 ????????????int docId = scoreDoc.doc;234 ????????????// 从indexReader根据docId获取document235 ????????????Document doc = indexReader.document(docId);236 ????????????// 取出doc中field域的内容237 ????????????// 参数指定field域名238 ????????????String id = doc.get("id");239 ????????????String name = doc.get("name");240 ????????????Float price = Float.parseFloat(doc.get("price"));241 ????????????String pic = doc.get("pic");242 243 ????????????System.out.println(id + "-" + name + "-" + price + "-" + pic);244 ????????}245 ????????// 关闭资源246 ????????indexReader.close();247 ????}248 }