lucene

<!--核心包 --><dependency><groupId>org.apache.lucene</groupId><artifactId>lucene-core</artifactId><version>5.3.1</version></dependency><!--一般分词器，适用于英文分词 --><dependency><groupId>org.apache.lucene</groupId><artifactId>lucene-analyzers-common</artifactId><version>5.3.1</version></dependency><!--中文分词器 --><dependency><groupId>org.apache.lucene</groupId><artifactId>lucene-analyzers-smartcn</artifactId><version>5.3.1</version></dependency><!--对分词索引查询解析 --><dependency><groupId>org.apache.lucene</groupId><artifactId>lucene-queryparser</artifactId><version>5.3.1</version></dependency><!--检索关键字高亮显示 --><dependency><groupId>org.apache.lucene</groupId><artifactId>lucene-highlighter</artifactId><version>5.3.1</version></dependency><!-- https://mvnrepository.com/artifact/commons-io/commons-io --><dependency><groupId>commons-io</groupId><artifactId>commons-io</artifactId><version>2.4</version></dependency>

package com.stevezong.lucene;import java.io.File;import java.nio.file.Path;import java.nio.file.Paths;import org.apache.commons.io.FileUtils;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.document.Field.Store;import org.apache.lucene.document.LongField;import org.apache.lucene.document.StoredField;import org.apache.lucene.document.TextField;import org.apache.lucene.index.IndexWriter;import org.apache.lucene.index.IndexWriterConfig;import org.apache.lucene.store.Directory;import org.apache.lucene.store.FSDirectory;public class LuceneTest { ???public static void main(String[] args) throws Exception { ???????// 1.2.1）指定索引库的存放位置Directory对象 ???????Path path = Paths.get("d:\\szTemp"); ???????Directory directory = FSDirectory.open(path); ???????// 1.2.2）指定一个分析器，对文档内容进行分析。 ???????Analyzer analyzer = new StandardAnalyzer(); ???????// 1.2.3) 配置对象 ???????IndexWriterConfig indexWriterConfig = new IndexWriterConfig(analyzer); ???????// 1.2创建一个indexwriter对象。 ???????IndexWriter indexWriter = new IndexWriter(directory, indexWriterConfig); ???????// 1.4创建field对象，将field添加到document对象中。 ???????File file = new File("F:\\5DWIFI最新字典\\新字典"); ???????File[] files = file.listFiles(); ???????for (File subFile : files) { ???????????// 文件名 ???????????String fileName = subFile.getName(); ???????????// 文件大小 ???????????long fileSize = FileUtils.sizeOf(subFile); ???????????// 文件路径 ???????????String filePath = subFile.getAbsolutePath(); ???????????// 文件内容 ???????????String fileContent = FileUtils.readFileToString(subFile); ???????????// 创建文件名域 ???????????// 第一个参数：域的名称 ???????????// 第二个参数：域的内容 ???????????// 第三个参数：是否存储 ???????????// 文件名域 ???????????Field fileNameField = new TextField("fileName", fileName, Store.YES); ???????????// 文件内容域 ???????????Field fileContentField = new TextField("fileContent", fileContent, Store.YES); ???????????// 文件路径域（不分析、不索引、只存储） ???????????Field filePathField = new StoredField("filePath", filePath); ???????????// 文件大小域 ???????????Field fileSizeField = new LongField("fileSize", fileSize, Store.YES); ???????????// 1.3创建document对象。 ???????????Document document = new Document(); ???????????document.add(fileSizeField); ???????????document.add(filePathField); ???????????document.add(fileContentField); ???????????document.add(fileNameField); ???????????// 1.5使用indexwriter对象将document对象写入索引库，此过程进行索引创建。并将索引和document对象写入索引库。 ???????????indexWriter.addDocument(document); ???????} ???????indexWriter.close(); ???????// 1.6关闭IndexWriter对象。 ???}}

package com.stevezong.lucene;import java.io.IOException;import java.nio.file.Path;import java.nio.file.Paths;import org.apache.lucene.document.Document;import org.apache.lucene.index.DirectoryReader;import org.apache.lucene.index.IndexReader;import org.apache.lucene.index.Term;import org.apache.lucene.search.IndexSearcher;import org.apache.lucene.search.Query;import org.apache.lucene.search.ScoreDoc;import org.apache.lucene.search.TermQuery;import org.apache.lucene.search.TopDocs;import org.apache.lucene.store.Directory;import org.apache.lucene.store.FSDirectory;public class LuceneTest2 { ???public static void main(String[] args) throws Exception { ???????// 1：创建一个Directory对象，也就是索引库存放的位置。 ???????Path path = Paths.get("d:\\szTemp"); ???????Directory directory = FSDirectory.open(path); ???????// 2：创建一个indexReader对象，需要指定Directory对象。 ???????IndexReader indexReader = DirectoryReader.open(directory); ???????// 3：创建一个indexsearcher对象，需要指定IndexReader对象 ???????IndexSearcher indexSearcher = new IndexSearcher(indexReader); ???????// 4：创建一个TermQuery对象，指定查询的域和查询的关键词。 ???????Term term = new Term("fileName", "2015"); ???????Query query = new TermQuery(term); ???????// 5：执行查询。 ???????TopDocs topDocs = indexSearcher.search(query, 2); ???????// 6：回查询结果。遍历查询结果并输出。 ???????ScoreDoc[] scoreDocs = topDocs.scoreDocs; ???????for (ScoreDoc scoreDoc : scoreDocs) { ???????????int doc = scoreDoc.doc; ???????????Document document = indexSearcher.doc(doc); ???????????String fileName = document.get("fileName"); ???????????String fileContent = document.get("fileContent"); ???????????String filePath = document.get("filePath"); ???????????String fileSize = document.get("fileSize"); ???????????System.out.println(fileName + ":" + filePath + ":" + fileSize + ":" + fileContent); ???????} ???????indexReader.close(); ???????// 7：关闭IndexReader对象 ???}}

package com.stevezong.lucene;import java.io.IOException;import java.nio.file.Path;import java.nio.file.Paths;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.Store;import org.apache.lucene.document.TextField;import org.apache.lucene.index.DirectoryReader;import org.apache.lucene.index.IndexReader;import org.apache.lucene.index.IndexWriter;import org.apache.lucene.index.IndexWriterConfig;import org.apache.lucene.index.Term;import org.apache.lucene.queryparser.classic.QueryParser;import org.apache.lucene.search.BooleanClause.Occur;import org.apache.lucene.search.BooleanQuery;import org.apache.lucene.search.IndexSearcher;import org.apache.lucene.search.MatchAllDocsQuery;import org.apache.lucene.search.NumericRangeQuery;import org.apache.lucene.search.Query;import org.apache.lucene.search.ScoreDoc;import org.apache.lucene.search.TermQuery;import org.apache.lucene.search.TopDocs;import org.apache.lucene.store.Directory;import org.apache.lucene.store.FSDirectory;import org.junit.Test;public class LuceneTest3 { ???@Test ???// 全删 ???public void testDel() throws Exception { ???????// 1.2.1）指定索引库的存放位置Directory对象 ???????Path path = Paths.get("d:\\szTemp"); ???????Directory directory = FSDirectory.open(path); ???????// 1.2.2）指定一个分析器，对文档内容进行分析。 ???????Analyzer analyzer = new StandardAnalyzer(); ???????// 1.2.3) 配置对象 ???????IndexWriterConfig indexWriterConfig = new IndexWriterConfig(analyzer); ???????// 1.2创建一个indexwriter对象。 ???????IndexWriter indexWriter = new IndexWriter(directory, indexWriterConfig); ???????// 全删 ???????indexWriter.deleteAll(); ???????indexWriter.close(); ???} ???@Test ???// 条件删 ???public void testDelBySome() throws Exception { ???????// 1.2.1）指定索引库的存放位置Directory对象 ???????Path path = Paths.get("d:\\szTemp"); ???????Directory directory = FSDirectory.open(path); ???????// 1.2.2）指定一个分析器，对文档内容进行分析。 ???????Analyzer analyzer = new StandardAnalyzer(); ???????// 1.2.3) 配置对象 ???????IndexWriterConfig indexWriterConfig = new IndexWriterConfig(analyzer); ???????// 1.2创建一个indexwriter对象。 ???????IndexWriter indexWriter = new IndexWriter(directory, indexWriterConfig); ???????// 创建删除条件 ???????Term term = new Term("fileName", "2015"); ???????Query query = new TermQuery(term); ???????// 条件删 ???????indexWriter.deleteDocuments(query); ???????indexWriter.close(); ???} ???@Test ???// 修改 ???public void testUpdate() throws Exception { ???????// 1.2.1）指定索引库的存放位置Directory对象 ???????Path path = Paths.get("d:\\szTemp"); ???????Directory directory = FSDirectory.open(path); ???????// 1.2.2）指定一个分析器，对文档内容进行分析。 ???????Analyzer analyzer = new StandardAnalyzer(); ???????// 1.2.3) 配置对象 ???????IndexWriterConfig indexWriterConfig = new IndexWriterConfig(analyzer); ???????// 1.2创建一个indexwriter对象。 ???????Document doc = new Document(); ???????TextField fileNameField = new TextField("fileName", "测试修改功能文件名", Store.YES); ???????TextField fileContentField = new TextField("fileContent", "测试修改功能文件内容", Store.YES); ???????doc.add(fileNameField); ???????doc.add(fileContentField); ???????IndexWriter indexWriter = new IndexWriter(directory, indexWriterConfig); ???????indexWriter.updateDocument(new Term("fileName", "50"), doc); ???????indexWriter.close(); ???} ???@Test ???// 查询所有 ???public void testSelectAll() throws Exception { ???????// 1：创建一个Directory对象，也就是索引库存放的位置。 ???????Path path = Paths.get("d:\\szTemp"); ???????Directory directory = FSDirectory.open(path); ???????// 2：创建一个indexReader对象，需要指定Directory对象。 ???????IndexReader indexReader = DirectoryReader.open(directory); ???????// 3：创建一个indexsearcher对象，需要指定IndexReader对象 ???????IndexSearcher indexSearcher = new IndexSearcher(indexReader); ???????// 实现类换了 ???????Query query = new MatchAllDocsQuery(); ???????TopDocs docs = indexSearcher.search(query, 20); ???????ScoreDoc[] scoreDocs = docs.scoreDocs; ???????for (ScoreDoc scoreDoc : scoreDocs) { ???????????int doc = scoreDoc.doc; ???????????Document document = indexSearcher.doc(doc); ???????????String fileName = document.get("fileName"); ???????????String fileContent = document.get("fileContent"); ???????????String filePath = document.get("filePath"); ???????????String fileSize = document.get("fileSize"); ???????????System.out.println(fileName + ":" + filePath + ":" + fileSize); ???????} ???????indexReader.close(); ???????// 7：关闭IndexReader对象 ???} ???@Test ???// 查询 根据数值范围查询 ???public void testSelectByFileSize() throws Exception { ???????// 1：创建一个Directory对象，也就是索引库存放的位置。 ???????Path path = Paths.get("d:\\szTemp"); ???????Directory directory = FSDirectory.open(path); ???????// 2：创建一个indexReader对象，需要指定Directory对象。 ???????IndexReader indexReader = DirectoryReader.open(directory); ???????// 3：创建一个indexsearcher对象，需要指定IndexReader对象 ???????IndexSearcher indexSearcher = new IndexSearcher(indexReader); ???????// 实现类换了 ???????Query query = NumericRangeQuery.newLongRange("fileSize", 0L, 500L, true, true); ???????TopDocs docs = indexSearcher.search(query, 20); ???????ScoreDoc[] scoreDocs = docs.scoreDocs; ???????for (ScoreDoc scoreDoc : scoreDocs) { ???????????int doc = scoreDoc.doc; ???????????Document document = indexSearcher.doc(doc); ???????????String fileName = document.get("fileName"); ???????????String fileContent = document.get("fileContent"); ???????????String filePath = document.get("filePath"); ???????????String fileSize = document.get("fileSize"); ???????????System.out.println(fileName + ":" + filePath + ":" + fileSize); ???????} ???????indexReader.close(); ???????// 7：关闭IndexReader对象 ???} ???@Test ???// 查询 组合查询 ???public void testSelectBooleanQuery() throws Exception { ???????// 1：创建一个Directory对象，也就是索引库存放的位置。 ???????Path path = Paths.get("d:\\szTemp"); ???????Directory directory = FSDirectory.open(path); ???????// 2：创建一个indexReader对象，需要指定Directory对象。 ???????IndexReader indexReader = DirectoryReader.open(directory); ???????// 3：创建一个indexsearcher对象，需要指定IndexReader对象 ???????IndexSearcher indexSearcher = new IndexSearcher(indexReader); ???????// 实现类换了 ???????BooleanQuery booleanQuery = new BooleanQuery(); ???????// 条件1 ???????Query query = NumericRangeQuery.newLongRange("fileSize", 0L, 500L, true, true); ???????// 条件2 ???????Query fileNameQuery = new TermQuery(new Term("fileName", "2015")); ???????// 将 两个条件 添加到 对象中 并设定 连接条件 必须 不必须 可能 过滤 ???????booleanQuery.add(query, Occur.MUST); ???????booleanQuery.add(fileNameQuery, Occur.SHOULD); ???????TopDocs docs = indexSearcher.search(booleanQuery, 20); ???????ScoreDoc[] scoreDocs = docs.scoreDocs; ???????for (ScoreDoc scoreDoc : scoreDocs) { ???????????int doc = scoreDoc.doc; ???????????Document document = indexSearcher.doc(doc); ???????????String fileName = document.get("fileName"); ???????????String fileContent = document.get("fileContent"); ???????????String filePath = document.get("filePath"); ???????????String fileSize = document.get("fileSize"); ???????????System.out.println(fileName + ":" + filePath + ":" + fileSize); ???????} ???????indexReader.close(); ???????// 7：关闭IndexReader对象 ???} ???@Test ???// 条件解析的对象查询 ???// 需要导包 ???public void testQueryParser() throws Exception { ???????// 1：创建一个Directory对象，也就是索引库存放的位置。 ???????Path path = Paths.get("d:\\szTemp"); ???????Directory directory = FSDirectory.open(path); ???????// 2：创建一个indexReader对象，需要指定Directory对象。 ???????IndexReader indexReader = DirectoryReader.open(directory); ???????// 3：创建一个indexsearcher对象，需要指定IndexReader对象 ???????IndexSearcher indexSearcher = new IndexSearcher(indexReader); ???????// 实现类换了 默认域 分词器 ???????QueryParser queryParser = new QueryParser("fileName", new StandardAnalyzer()); ???????// 查询所有 域:值 ???????// Query query = queryParser.parse("*:*"); ???????// fileName:2015 ???????// Query query = queryParser.parse("2015"); ???????// fileContent:cheese ???????// Query query = queryParser.parse("fileContent:cheese"); ???????// cheese is a java 88888888 经过分词器 后再去查找 ???????Query query = queryParser.parse("fileContent:cheese is a java 88888888"); ???????TopDocs docs = indexSearcher.search(query, 20); ???????ScoreDoc[] scoreDocs = docs.scoreDocs; ???????for (ScoreDoc scoreDoc : scoreDocs) { ???????????int doc = scoreDoc.doc; ???????????Document document = indexSearcher.doc(doc); ???????????String fileName = document.get("fileName"); ???????????String fileContent = document.get("fileContent"); ???????????String filePath = document.get("filePath"); ???????????String fileSize = document.get("fileSize"); ???????????System.out.println(fileName + ":" + filePath + ":" + fileSize); ???????} ???????indexReader.close(); ???????// 7：关闭IndexReader对象 ???}}