Lucence 4.0的入门示例
几年前学了2.2版本的，一直没有机会有使用到Lucense。给忘了差不多了，只留下一些简单印象。现在重新学习！
?
自己的测试用例：
?
import java.io.File;import java.io.IOException;import java.text.SimpleDateFormat;import java.util.Date;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.LongField;import org.apache.lucene.document.StoredField;import org.apache.lucene.document.StringField;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.search.Filter;import org.apache.lucene.search.IndexSearcher;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.SimpleFSDirectory;import org.apache.lucene.util.Version;import org.junit.Test;public class HelloWorld {private static String filePath = "D:\\workspace-java\\lucence\\data_sources\\20121212.txt";private static String indexDir = "D:\\workspace-java\\lucence\\index_dir";private static StandardAnalyzer analyzer = new StandardAnalyzer(Version.LUCENE_40);@Testpublic void createIndex() {File f = new File(filePath);SimpleDateFormat df = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss");StringField name = new StringField("name", f.getName(), Store.YES);TextField content = new TextField("content", File2DocumentUtils.readFileContent(filePath), Store.YES);StringField path = new StringField("path", f.getAbsolutePath(), Store.YES);// StringField date = new StringField("date",df.format(new Date()),Store.YES);// 表示只存储，不进行索引StoredField date = new StoredField("date", df.format(new Date()));LongField size = new LongField("size", f.length(), Store.YES);Document doc = new Document();doc.add(name);doc.add(content);doc.add(path);doc.add(date);doc.add(size);Directory directory = null;try {directory = new SimpleFSDirectory(new File(indexDir));IndexWriterConfig config = new IndexWriterConfig(Version.LUCENE_40, analyzer);config.setOpenMode(IndexWriterConfig.OpenMode.CREATE_OR_APPEND);IndexWriter indexWriter = new IndexWriter(directory, config);indexWriter.addDocument(doc);indexWriter.close();} catch (Exception e) {e.printStackTrace();}}@Testpublic void searchText() {// MultiPhraseQuery q = new MultiPhraseQuery();// q.add(new Term("bride"));//term表示查询条件。第一参数为将要查询的字段；第二参数为要查询的语句TermQuery q = new TermQuery(new Term("content", "dresses"));Directory directory = null;IndexReader indexReader = null;try {directory = new SimpleFSDirectory(new File(indexDir));indexReader = DirectoryReader.open(directory);IndexSearcher indexSearcher = new IndexSearcher(indexReader);Filter filter = null;TopDocs results = indexSearcher.search(q, filter, 100);System.out.println("Total hits:" + results.totalHits);ScoreDoc[] hits = results.scoreDocs;for (ScoreDoc hit : hits) {Document d = indexSearcher.doc(hit.doc);System.out.println(d.getField("name").stringValue() + ",score:" + hit.score);}} catch (Exception e) {e.printStackTrace();} finally {if (indexReader != null) {try {indexReader.close();} catch (IOException e) {e.printStackTrace();}}}}}??
?
从其他网看到的示例：
http://www.cnblogs.com/sunxucool/archive/2012/12/03/2799805.html
?
import java.io.File;import java.io.IOException;import java.io.StringReader;import org.apache.lucene.analysis.Analyzer;import org.apache.lucene.analysis.TokenStream;import org.apache.lucene.document.Document;import org.apache.lucene.document.Field.Store;import org.apache.lucene.document.TextField;import org.apache.lucene.index.IndexReader;import org.apache.lucene.index.IndexWriter;import org.apache.lucene.index.IndexWriterConfig;import org.apache.lucene.queryparser.classic.MultiFieldQueryParser;import org.apache.lucene.queryparser.classic.ParseException;import org.apache.lucene.queryparser.classic.QueryParser;import org.apache.lucene.search.IndexSearcher;import org.apache.lucene.search.Query;import org.apache.lucene.search.ScoreDoc;import org.apache.lucene.search.TopDocs;import org.apache.lucene.search.TopScoreDocCollector;import org.apache.lucene.search.highlight.Highlighter;import org.apache.lucene.search.highlight.InvalidTokenOffsetsException;import org.apache.lucene.search.highlight.QueryScorer;import org.apache.lucene.search.highlight.SimpleHTMLFormatter;import org.apache.lucene.store.Directory;import org.apache.lucene.store.FSDirectory;import org.apache.lucene.util.Version;import org.wltea.analyzer.lucene.IKAnalyzer;public class IndexTools {/** * 获得indexwriter对象 * * @param dir * @return * @throws IOException * @throws Exception */private IndexWriter getIndexWriter(Directory dir, Analyzer analyzer) throws IOException {IndexWriterConfig iwc = new IndexWriterConfig(Version.LUCENE_40, analyzer);return new IndexWriter(dir, iwc);}/** * 关闭indexwriter对象 * * @throws IOException * * @throws Exception */private void closeWriter(IndexWriter indexWriter) throws IOException {if (indexWriter != null) {indexWriter.close();}}/** * 创建索引 * * @throws InvalidTokenOffsetsException */public void createIndex() throws InvalidTokenOffsetsException {String indexPath = "D://luceneindex"; // 建立索引文件的目录// 默认IKAnalyzer()-false:实现最细粒度切分算法,true:分词器采用智能切分Analyzer analyzer = new IKAnalyzer(true);IndexWriter indexWriter = null;Directory directory = null;try {directory = FSDirectory.open(new File(indexPath));indexWriter = getIndexWriter(directory, analyzer);} catch (Exception e) {System.out.println("索引打开异常！");}// 添加索引try {Document document = new Document();document.add(new TextField("filename", "标题:起点", Store.YES));document.add(new TextField("content", "内容：我是一名程序员", Store.YES));indexWriter.addDocument(document);Document document1 = new Document();document1.add(new TextField("filename", "标题:终点", Store.YES));document1.add(new TextField("content", "内容：我不再只是程序员", Store.YES));indexWriter.addDocument(document1);indexWriter.commit();} catch (IOException e1) {System.out.println("索引创建异常！");}try {closeWriter(indexWriter);} catch (Exception e) {System.out.println("索引关闭异常！");}}/** * 搜索 * * @throws ParseException * @throws IOException * @throws InvalidTokenOffsetsException */@SuppressWarnings("deprecation")public void searchIndex() throws ParseException, IOException, InvalidTokenOffsetsException {String indexPath = "D://luceneindex"; // 建立索引文件的目录// 默认IKAnalyzer()-false:实现最细粒度切分算法,true:分词器采用智能切分Analyzer analyzer = new IKAnalyzer(true);Directory directory = null;try {directory = FSDirectory.open(new File(indexPath));} catch (Exception e) {System.out.println("索引打开异常！");}IndexReader ireader = null;IndexSearcher isearcher = null;try {ireader = IndexReader.open(directory);} catch (IOException e) {System.out.println("打开索引文件！");}isearcher = new IndexSearcher(ireader);String keyword = "程序员";// 使用QueryParser查询分析器构造Query对象// eg:单个字段查询// String fieldName = "content";// QueryParser qp = new QueryParser(Version.LUCENE_40, fieldName, analyzer);String[] fields = { "filename", "content" };QueryParser qp = new MultiFieldQueryParser(Version.LUCENE_40, fields, analyzer);qp.setDefaultOperator(QueryParser.AND_OPERATOR);Query query = qp.parse(keyword);// 搜索相似度最高的5条记录TopDocs topDocs = isearcher.search(query, 25);System.out.println("命中：" + topDocs.totalHits);// 输出结果ScoreDoc[] scoreDocs = topDocs.scoreDocs;for (int i = 0; i < topDocs.totalHits; i++) {Document targetDoc = isearcher.doc(scoreDocs[i].doc);System.out.println("内容：" + targetDoc.toString());}// 分页，高亮显示higherIndex(analyzer, isearcher, query, topDocs);}public static void main(String[] args) {IndexTools tool = new IndexTools();try {tool.searchIndex();} catch (ParseException e) {System.out.println("解析错误");} catch (IOException e) {System.out.println("读取文件流错误");} catch (InvalidTokenOffsetsException e) {System.out.println("查询失败");}}/** * 分页，高亮显示 * * @param analyzer * @param isearcher * @param query * @param topDocs * @throws IOException * @throws InvalidTokenOffsetsException */public void higherIndex(Analyzer analyzer, IndexSearcher isearcher, Query query, TopDocs topDocs) throws IOException, InvalidTokenOffsetsException {TopScoreDocCollector results = TopScoreDocCollector.create(topDocs.totalHits, false);isearcher.search(query, results);// 分页取出指定的doc(开始条数, 取几条)ScoreDoc[] docs = results.topDocs(1, 2).scoreDocs;for (int i = 0; i < docs.length; i++) {Document targetDoc = isearcher.doc(docs[i].doc);System.out.println("内容：" + targetDoc.toString());}// 关键字高亮显示的html标签，需要导入lucene-highlighter-3.5.0.jarSimpleHTMLFormatter simpleHTMLFormatter = new SimpleHTMLFormatter("<font color='red'>", "</font>");Highlighter highlighter = new Highlighter(simpleHTMLFormatter, new QueryScorer(query));for (int i = 0; i < docs.length; i++) {Document doc = isearcher.doc(docs[i].doc);// 标题增加高亮显示TokenStream tokenStream1 = analyzer.tokenStream("filename", new StringReader(doc.get("filename")));String title = highlighter.getBestFragment(tokenStream1, doc.get("filename"));// 内容增加高亮显示TokenStream tokenStream2 = analyzer.tokenStream("content", new StringReader(doc.get("content")));String content = highlighter.getBestFragment(tokenStream2, doc.get("content"));System.out.println(doc.get("filename") + " : " + title + " : " + content);}}}??
?
d