Lucene开发实例：Lucene中文分词

1、准备工作


下载lucene 3.6.1 ： http://lucene.apache.org/


下载中文分词IK Analyzer： http://code.google.com/p/ik-analyzer/downloads/list （注意下载的是IK Analyzer 2012_u5_source.zip，其他版本有bug）


下载solr 3.6.1：  http://lucene.apache.org/solr/（编译IK Analyzer时需引用包）


OK，将lucene 、solr 相关包（lucene-core-3.6.1.jar、lucene-highlighter-3.6.1.jar、lucene-analyzers-3.6.1.jar、apache-solr-core-3.6.1.jar、apache-solr-solrj-3.6.1.jar）拷贝到项目lib下，IK源码置于项目src下。

2、从Oracle数据库中取数据创建索引（使用IK分词）

<pre style="line-height:normal;background-color:#f0f0f0;margin-top:4px;margin-bottom:4px;font-size:12px;" class="html" name="code" snippet_file_name="blog_20140526_1_1960266" code_snippet_id="363583">package lucene.util; import org.apache.lucene.index.IndexWriter; import org.apache.lucene.index.IndexWriterConfig; import org.apache.lucene.index.CorruptIndexException; import org.apache.lucene.store.FSDirectory; import org.apache.lucene.store.Directory; import org.apache.lucene.analysis.Analyzer; import org.apache.lucene.analysis.standard.StandardAnalyzer; import org.apache.lucene.util.Version; import org.apache.lucene.document.Document; import org.apache.lucene.document.Field; import org.wltea.analyzer.lucene.IKAnalyzer; import java.sql.Connection; import java.io.File; import java.io.IOException; import java.util.ArrayList; import java.util.Date; import modules.gk.Gk_info; import modules.gk.Gk_infoSub; import web.sys.Globals; import web.db.DBConnector; import web.db.ObjectCtl; import web.util.StringUtil; //Wizzer.cn public class LuceneIndex { IndexWriter writer = null; FSDirectory dir = null; boolean create = true; public void init() { long a1 = System.currentTimeMillis(); System.out.println("[Lucene 开始执行：" + new Date() + "]"); Connection con = DBConnector.getconecttion(); //取得一个数据库连接 try { final File docDir = new File(Globals.SYS_COM_CONFIG.get("sys.index.path").toString());//E:\lucene if (!docDir.exists()) { docDir.mkdirs(); } String cr = Globals.SYS_COM_CONFIG.get("sys.index.create").toString();//true or false if ("false".equals(cr.toLowerCase())) { create = false; } Directory dir = FSDirectory.open(docDir); // Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_36); Analyzer analyzer = new IKAnalyzer(true); IndexWriterConfig iwc = new IndexWriterConfig(Version.LUCENE_36, analyzer); if (create) { // Create a new index in the directory, removing any // previously indexed documents: iwc.setOpenMode(IndexWriterConfig.OpenMode.CREATE); } else { // Add new documents to an existing index: iwc.setOpenMode(IndexWriterConfig.OpenMode.CREATE_OR_APPEND); } IndexWriter writer = new IndexWriter(dir, iwc); String sql = "SELECT indexno,title,describes,pdate,keywords FROM TABLEA WHERE STATE=1 AND SSTAG<>1 "; int rowCount = ObjectCtl.getRowCount(con, sql); int pageSize = StringUtil.StringToInt(Globals.SYS_COM_CONFIG.get("sys.index.size").toString()); //每页记录数 int pages = (rowCount - 1) / pageSize + 1; //计算总页数 ArrayList list = null; Gk_infoSub gk = null; for (int i = 1; i < pages+1; i++) { long a = System.currentTimeMillis(); list = ObjectCtl.listPage(con, sql, i, pageSize, new Gk_infoSub()); for (int j = 0; j < list.size(); j++) { gk = (Gk_infoSub) list.get(j); Document doc = new Document(); doc.add(new Field("indexno", StringUtil.null2String(gk.getIndexno()), Field.Store.YES, Field.Index.NOT_ANALYZED_NO_NORMS));//主键不分词 doc.add(new Field("title", StringUtil.null2String(gk.getTitle()), Field.Store.YES, Field.Index.ANALYZED)); doc.add(new Field("describes", StringUtil.null2String(gk.getDescribes()), Field.Store.YES, Field.Index.ANALYZED)); doc.add(new Field("pdate", StringUtil.null2String(gk.getPdate()), Field.Store.YES, Field.Index.NOT_ANALYZED_NO_NORMS));//日期不分词 doc.add(new Field("keywords", StringUtil.null2String(gk.getKeywords()), Field.Store.YES, Field.Index.ANALYZED)); writer.addDocument(doc); ObjectCtl.executeUpdateBySql(con,"UPDATE TABLEA SET SSTAG=1 WHERE indexno='"+gk.getIndexno()+"'");//更新已索引状态 } long b = System.currentTimeMillis(); long c = b - a; System.out.println("[Lucene " + rowCount + "条，" + pages + "页，第" + i + "页花费时间：" + c + "毫秒]"); } writer.commit(); } catch (Exception e) { e.printStackTrace(); } finally { DBConnector.freecon(con); //释放数据库连接 try { if (writer != null) { writer.close(); } } catch (CorruptIndexException e) { e.printStackTrace(); } catch (IOException e) { e.printStackTrace(); } finally { try { if (dir != null && IndexWriter.isLocked(dir)) { IndexWriter.unlock(dir);//注意解锁 } } catch (IOException e) { e.printStackTrace(); } } } long b1 = System.currentTimeMillis(); long c1 = b1 - a1; System.out.println("[Lucene 执行完毕，花费时间：" + c1 + "毫秒，完成时间：" + new Date() + "]"); } }</pre>

3、单字段查询以及多字段分页查询高亮显示

<pre style="line-height:normal;background-color:#f0f0f0;margin-top:4px;margin-bottom:4px;font-size:12px;" class="html" name="code" snippet_file_name="blog_20140526_2_4010390" code_snippet_id="363583">package lucene.util; import org.apache.lucene.store.FSDirectory; import org.apache.lucene.store.Directory; import org.apache.lucene.search.; import org.apache.lucene.search.highlight.SimpleHTMLFormatter; import org.apache.lucene.search.highlight.Highlighter; import org.apache.lucene.search.highlight.SimpleFragmenter; import org.apache.lucene.search.highlight.QueryScorer; import org.apache.lucene.queryParser.QueryParser; import org.apache.lucene.queryParser.MultiFieldQueryParser; import org.apache.lucene.analysis.TokenStream; import org.apache.lucene.analysis.Analyzer; import org.apache.lucene.analysis.KeywordAnalyzer; import org.apache.lucene.document.Document; import org.apache.lucene.index.IndexReader; import org.apache.lucene.index.Term; import org.apache.lucene.util.Version; import modules.gk.Gk_infoSub; import java.util.ArrayList; import java.io.File; import java.io.StringReader; import java.lang.reflect.Constructor; import web.util.StringUtil; import web.sys.Globals; import org.wltea.analyzer.lucene.IKAnalyzer; //Wizzer.cn public class LuceneQuery { private static String indexPath;// 索引生成的目录 private int rowCount;// 记录数 private int pages;// 总页数 private int currentPage;// 当前页数 private int pageSize; //每页记录数 public LuceneQuery() { this.indexPath = Globals.SYS_COM_CONFIG.get("sys.index.path").toString(); } public int getRowCount() { return rowCount; } public int getPages() { return pages; } public int getPageSize() { return pageSize; } public int getCurrentPage() { return currentPage; } /** 函数功能:根据字段查询索引 / public ArrayList queryIndexTitle(String keyWord, int curpage, int pageSize) { ArrayList list = new ArrayList(); try { if (curpage <= 0) { curpage = 1; } if (pageSize <= 0) { pageSize = 20; } this.pageSize = pageSize; //每页记录数 this.currentPage = curpage; //当前页 int start = (curpage - 1) pageSize; Directory dir = FSDirectory.open(new File(indexPath)); IndexReader reader = IndexReader.open(dir); IndexSearcher searcher = new IndexSearcher(reader); Analyzer analyzer = new IKAnalyzer(true); QueryParser queryParser = new QueryParser(Version.LUCENE_36, "title", analyzer); queryParser.setDefaultOperator(QueryParser.AND_OPERATOR); Query query = queryParser.parse(keyWord); int hm = start + pageSize; TopScoreDocCollector res = TopScoreDocCollector.create(hm, false); searcher.search(query, res); SimpleHTMLFormatter simpleHTMLFormatter = new SimpleHTMLFormatter("<span style='color:red'>", "</span>"); Highlighter highlighter = new Highlighter(simpleHTMLFormatter, new QueryScorer(query)); this.rowCount = res.getTotalHits(); this.pages = (rowCount - 1) / pageSize + 1; //计算总页数 TopDocs tds = res.topDocs(start, pageSize); ScoreDoc[] sd = tds.scoreDocs; for (int i = 0; i < sd.length; i++) { Document hitDoc = reader.document(sd[i].doc); list.add(createObj(hitDoc, analyzer, highlighter)); } } catch (Exception e) { e.printStackTrace(); } return list; } / 函数功能:根据字段查询索引 / public ArrayList queryIndexFields(String allkeyword, String onekeyword, String nokeyword, int curpage, int pageSize) { ArrayList list = new ArrayList(); try { if (curpage <= 0) { curpage = 1; } if (pageSize <= 0) { pageSize = 20; } this.pageSize = pageSize; //每页记录数 this.currentPage = curpage; //当前页 int start = (curpage - 1) * pageSize; Directory dir = FSDirectory.open(new File(indexPath)); IndexReader reader = IndexReader.open(dir); IndexSearcher searcher = new IndexSearcher(reader); BooleanQuery bQuery = new BooleanQuery(); //组合查询 if (!"".equals(allkeyword)) {//包含全部关键词 KeywordAnalyzer analyzer = new KeywordAnalyzer(); BooleanClause.Occur[] flags = {BooleanClause.Occur.SHOULD, BooleanClause.Occur.SHOULD, BooleanClause.Occur.SHOULD};//AND Query query = MultiFieldQueryParser.parse(Version.LUCENE_36, allkeyword, new String[]{"title", "describes", "keywords"}, flags, analyzer); bQuery.add(query, BooleanClause.Occur.MUST); //AND } if (!"".equals(onekeyword)) { //包含任意关键词 Analyzer analyzer = new IKAnalyzer(true); BooleanClause.Occur[] flags = {BooleanClause.Occur.SHOULD, BooleanClause.Occur.SHOULD, BooleanClause.Occur.SHOULD};//OR Query query = MultiFieldQueryParser.parse(Version.LUCENE_36, onekeyword, new String[]{"title", "describes", "keywords"}, flags, analyzer); bQuery.add(query, BooleanClause.Occur.MUST); //AND } if (!"".equals(nokeyword)) { //排除关键词 Analyzer analyzer = new IKAnalyzer(true); BooleanClause.Occur[] flags = {BooleanClause.Occur.SHOULD, BooleanClause.Occur.SHOULD, BooleanClause.Occur.SHOULD};//NOT Query query = MultiFieldQueryParser.parse(Version.LUCENE_36, nokeyword, new String[]{"title", "describes", "keywords"}, flags, analyzer); bQuery.add(query, BooleanClause.Occur.MUST_NOT); //AND } int hm = start + pageSize; TopScoreDocCollector res = TopScoreDocCollector.create(hm, false); searcher.search(bQuery, res); SimpleHTMLFormatter simpleHTMLFormatter = new SimpleHTMLFormatter("<span style='color:red'>", "</span>"); Highlighter highlighter = new Highlighter(simpleHTMLFormatter, new QueryScorer(bQuery)); this.rowCount = res.getTotalHits(); this.pages = (rowCount - 1) / pageSize + 1; //计算总页数 System.out.println("rowCount:" + rowCount); TopDocs tds = res.topDocs(start, pageSize); ScoreDoc[] sd = tds.scoreDocs; Analyzer analyzer = new IKAnalyzer(); for (int i = 0; i < sd.length; i++) { Document hitDoc = reader.document(sd[i].doc); list.add(createObj(hitDoc, analyzer, highlighter)); } } catch (Exception e) { e.printStackTrace(); } return list; } / 创建返回对象（高亮） / private synchronized static Object createObj(Document doc, Analyzer analyzer, Highlighter highlighter) { Gk_infoSub gk = new Gk_infoSub(); try { if (doc != null) { gk.setIndexno(StringUtil.null2String(doc.get("indexno"))); gk.setPdate(StringUtil.null2String(doc.get("pdate"))); String title = StringUtil.null2String(doc.get("title")); gk.setTitle(title); if (!"".equals(title)) { highlighter.setTextFragmenter(new SimpleFragmenter(title.length())); TokenStream tk = analyzer.tokenStream("title", new StringReader(title)); String htext = StringUtil.null2String(highlighter.getBestFragment(tk, title)); if (!"".equals(htext)) { gk.setTitle(htext); } } String keywords = StringUtil.null2String(doc.get("keywords")); gk.setKeywords(keywords); if (!"".equals(keywords)) { highlighter.setTextFragmenter(new SimpleFragmenter(keywords.length())); TokenStream tk = analyzer.tokenStream("keywords", new StringReader(keywords)); String htext = StringUtil.null2String(highlighter.getBestFragment(tk, keywords)); if (!"".equals(htext)) { gk.setKeywords(htext); } } String describes = StringUtil.null2String(doc.get("describes")); gk.setDescribes(describes); if (!"".equals(describes)) { highlighter.setTextFragmenter(new SimpleFragmenter(describes.length())); TokenStream tk = analyzer.tokenStream("keywords", new StringReader(describes)); String htext = StringUtil.null2String(highlighter.getBestFragment(tk, describes)); if (!"".equals(htext)) { gk.setDescribes(htext); } } } return gk; } catch (Exception e) { e.printStackTrace(); return null; } finally { gk = null; } } private synchronized static Object createObj(Document doc) { Gk_infoSub gk = new Gk_infoSub(); try { if (doc != null) { gk.setIndexno(StringUtil.null2String(doc.get("indexno"))); gk.setPdate(StringUtil.null2String(doc.get("pdate"))); gk.setTitle(StringUtil.null2String(doc.get("title"))); gk.setKeywords(StringUtil.null2String(doc.get("keywords"))); gk.setDescribes(StringUtil.null2String(doc.get("describes"))); } return gk; } catch (Exception e) { e.printStackTrace(); return null; } finally { gk = null; } } }</pre>
单字段查询：
<pre style="line-height:normal;background-color:#f0f0f0;margin-top:4px;margin-bottom:4px;font-size:12px;" class="html" name="code" snippet_file_name="blog_20140526_3_1152688" code_snippet_id="363583">long a = System.currentTimeMillis(); try { int curpage = StringUtil.StringToInt(StringUtil.null2String(form.get("curpage"))); int pagesize = StringUtil.StringToInt(StringUtil.null2String(form.get("pagesize"))); String title = StringUtil.replaceLuceneStr(StringUtil.null2String(form.get("title"))); LuceneQuery lu = new LuceneQuery(); form.addResult("list", lu.queryIndexTitle(title, curpage, pagesize)); form.addResult("curPage", lu.getCurrentPage()); form.addResult("pageSize", lu.getPageSize()); form.addResult("rowCount", lu.getRowCount()); form.addResult("pageCount", lu.getPages()); } catch (Exception e) { e.printStackTrace(); } long b = System.currentTimeMillis(); long c = b - a; System.out.println("[搜索信息花费时间：" + c + "毫秒]");</pre>
多字段查询：

<pre style="line-height:normal;background-color:#f0f0f0;margin-top:4px;margin-bottom:4px;font-size:12px;" class="html" name="code" snippet_file_name="blog_20140526_4_9931188" code_snippet_id="363583">long a = System.currentTimeMillis(); try { int curpage = StringUtil.StringToInt(StringUtil.null2String(form.get("curpage"))); int pagesize = StringUtil.StringToInt(StringUtil.null2String(form.get("pagesize"))); String allkeyword = StringUtil.replaceLuceneStr(StringUtil.null2String(form.get("allkeyword"))); String onekeyword = StringUtil.replaceLuceneStr(StringUtil.null2String(form.get("onekeyword"))); String nokeyword = StringUtil.replaceLuceneStr(StringUtil.null2String(form.get("nokeyword"))); LuceneQuery lu = new LuceneQuery(); form.addResult("list", lu.queryIndexFields(allkeyword,onekeyword,nokeyword, curpage, pagesize)); form.addResult("curPage", lu.getCurrentPage()); form.addResult("pageSize", lu.getPageSize()); form.addResult("rowCount", lu.getRowCount()); form.addResult("pageCount", lu.getPages()); } catch (Exception e) { e.printStackTrace(); } long b = System.currentTimeMillis(); long c = b - a; System.out.println("[高级检索花费时间：" + c + "毫秒]");</pre>

4、Lucene通配符查询

<pre style="line-height:normal;background-color:#f0f0f0;margin-top:4px;margin-bottom:4px;font-size:12px;" class="html" name="code" snippet_file_name="blog_20140526_5_7837637" code_snippet_id="363583"> BooleanQuery bQuery = new BooleanQuery(); //组合查询 if (!"".equals(title)) { WildcardQuery w1 = new WildcardQuery(new Term("title", title+ "")); bQuery.add(w1, BooleanClause.Occur.MUST); //AND } int hm = start + pageSize; TopScoreDocCollector res = TopScoreDocCollector.create(hm, false); searcher.search(bQuery, res);</pre>

5、Lucene嵌套查询


实现SQL：(unitid like 'unitid%'  and idml like 'id2%') or (tounitid like 'unitid%' and tomlid like 'id2%' and tostate=1)

<pre style="line-height:normal;background-color:#f0f0f0;margin-top:4px;margin-bottom:4px;font-size:12px;" class="html" name="code" snippet_file_name="blog_20140526_6_519834" code_snippet_id="363583">BooleanQuery bQuery = new BooleanQuery(); BooleanQuery b1 = new BooleanQuery(); WildcardQuery w1 = new WildcardQuery(new Term("unitid", unitid + "")); WildcardQuery w2 = new WildcardQuery(new Term("idml", id2 + "")); b1.add(w1, BooleanClause.Occur.MUST);//AND b1.add(w2, BooleanClause.Occur.MUST);//AND bQuery.add(b1, BooleanClause.Occur.SHOULD);//OR BooleanQuery b2 = new BooleanQuery(); WildcardQuery w3 = new WildcardQuery(new Term("tounitid", unitid + "")); WildcardQuery w4 = new WildcardQuery(new Term("tomlid", id2 + "*")); WildcardQuery w5 = new WildcardQuery(new Term("tostate", "1")); b2.add(w3, BooleanClause.Occur.MUST);//AND b2.add(w4, BooleanClause.Occur.MUST);//AND b2.add(w5, BooleanClause.Occur.MUST);//AND bQuery.add(b2, BooleanClause.Occur.SHOULD);//OR</pre>

6、Lucene先根据时间排序后分页
<pre style="line-height:normal;background-color:#f0f0f0;margin-top:4px;margin-bottom:4px;font-size:12px;" class="html" name="code" snippet_file_name="blog_20140526_7_6266691" code_snippet_id="363583"> int hm = start + pageSize; Sort sort = new Sort(new SortField("pdate", SortField.STRING, true)); TopScoreDocCollector res = TopScoreDocCollector.create(pageSize, false); searcher.search(bQuery, res); this.rowCount = res.getTotalHits(); this.pages = (rowCount - 1) / pageSize + 1; //计算总页数 TopDocs tds =searcher.search(bQuery,rowCount,sort);// res.topDocs(start, pageSize); ScoreDoc[] sd = tds.scoreDocs; System.out.println("rowCount:" + rowCount); int i=0; for (ScoreDoc scoreDoc : sd) { i++; if(i<start){ continue; } if(i>hm){ break; } Document doc = searcher.doc(scoreDoc.doc); list.add(createObj(doc));</pre>

这个效率不高，正常的做法是创建索引的时候进行排序，之后使用分页方法，不要这样进行2次查询。

推荐阅读：Lucene开发实例教程-基于Lucene4.6+Solr4.6+Heritrix1.14+S2SH实战开发从无到有垂直搜索引擎http://www.ibeifeng.com/goods-378.html