[lucene]初探bobo-browse

Bobo-browse是一个基于lucene的分面搜索插件，可以完成对搜索结果的分面统计，比如“男装（221） 女装（332）”等。

这里做首次尝试，只谈使用，不谈原理。用熟了才有可能去研究仔细。

lucene3 + bobo-browse2.5

建索引，更新索引跟它没关系，仅关注搜索。索引建立好后，开始进行分面搜索。

bobo-spring.xml

<?xml version="1.0" encoding="UTF-8"?> <beans xmlns="http://www.springframework.org/schema/beans" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.springframework.org/schema/beans http://www.springframework.org/schema/beans/spring-beans.xsd"> <!-- com.browseengine.bobo.facets.impl.SimpleFacetHandler no-analyzar com.browseengine.bobo.facets.impl.MultiValueFacetHandler analyzar-enable com.browseengine.bobo.facets.impl.CompactMultiValueFacetHandler analyzar-enable com.browseengine.bobo.facets.impl.PathFacetHandler no-analyzar com.browseengine.bobo.facets.impl.RangeFacetHandler no-analyzar --> <bean id="brand" class="com.browseengine.bobo.facets.impl.MultiValueFacetHandler"> <constructor-arg value="brand" /> </bean> <bean id="pic_url1" class="com.browseengine.bobo.facets.impl.PathFacetHandler"> <constructor-arg value="pic_url1" /> <constructor-arg value="true" /> <property name="separator" value="/" /> </bean> <bean id="sold_num" class="com.browseengine.bobo.facets.impl.SimpleFacetHandler"> <constructor-arg value="sold_num" /> </bean> <bean id="price" class="com.browseengine.bobo.facets.impl.RangeFacetHandler"> <constructor-arg value="price" /> <constructor-arg> <bean class="com.browseengine.bobo.facets.data.PredefinedTermListFactory"> <constructor-arg value="java.lang.Double"/> <constructor-arg value="00000000000000000000" /> </bean> </constructor-arg> <constructor-arg> <list> <value>[* TO 2]</value> <value>[3 TO 15000]</value> <value>[15001 TO 17500]</value> <value>[17501 TO *]</value> </list> </constructor-arg> </bean> <bean id="handlers" class="java.util.ArrayList"> <constructor-arg> <list> <ref bean="brand" /> <ref bean="pic_url1" /> <ref bean="price" /> <ref bean="sold_num" /> </list> </constructor-arg> </bean> </beans>

@SuppressWarnings("deprecation") public void testBoboBrowser(){ String splittype = "pic_url1"; String splittype2 = "price"; String splittype3 = "brand"; String splittype4 = "sold_num"; try { // 1 IndexReader indexReader = IndexReader.open( FSDirectory.open( new File("D://workspace2//normandy_normandypositionii//NormandyPositionII//luceneIndex//goods//"))); BoboIndexReader boboIndexReader = BoboIndexReader.getInstance(indexReader); BrowseRequest browseRequest = new BrowseRequest(); browseRequest.setCount(10); browseRequest.setOffset(0); // 2 String indexName = "brand"; String keywords = "飞扬"; Analyzer analyzer = new IKAnalyzer(); QueryParser queryParser = new QueryParser(Version.LUCENE_CURRENT, indexName, analyzer); Query query = queryParser.parse(keywords); browseRequest.setQuery(query); // 3 设置分面类型 FacetSpec facetSpec = new FacetSpec(); facetSpec.setMaxCount(10);// 搜索出来的标签数目 facetSpec.setOrderBy(FacetSortSpec.OrderHitsDesc); browseRequest.setFacetSpec(splittype, facetSpec); browseRequest.setFacetSpec(splittype2, facetSpec); browseRequest.setFacetSpec(splittype3, facetSpec); browseRequest.setFacetSpec(splittype4, facetSpec); // 4 Browsable browser = new BoboBrowser(boboIndexReader); BrowseResult browseResult = browser.browse(browseRequest); // 5 int totalHits = browseResult.getNumHits(); BrowseHit[] browseHit = browseResult.getHits(); System.out.println("total count:"+totalHits); // 上面添加了哪些分类字段，这里就有哪些分类字段可以被取值 for(BrowseHit b : browseHit){ System.out.println(b.getField(splittype2)); } // 搜索出来的标签 Map<String,FacetAccessible> facetMap = browseResult.getFacetMap(); System.out.println("bobo分面："+splittype+"-----------------------"); FacetAccessible colorFacets = facetMap.get(splittype); List<BrowseFacet> facetVals = colorFacets.getFacets(); for(BrowseFacet f:facetVals){ System.out.println(f.getValue() + "(" + f.getHitCount() + ")"); } System.out.println("bobo分面："+splittype2+"-----------------------"); colorFacets = facetMap.get(splittype2); facetVals = colorFacets.getFacets(); for(BrowseFacet f:facetVals){ System.out.println(f.getValue() + "(" + f.getHitCount() + ")"); } System.out.println("bobo分面："+splittype3+"-----------------------"); colorFacets = facetMap.get(splittype3); facetVals = colorFacets.getFacets(); for(BrowseFacet f:facetVals){ System.out.println(f.getValue() + "(" + f.getHitCount() + ")"); } System.out.println("bobo分面："+splittype4+"-----------------------"); colorFacets = facetMap.get(splittype4); facetVals = colorFacets.getFacets(); for(BrowseFacet f:facetVals){ System.out.println(f.getValue() + "(" + f.getHitCount() + ")"); } } catch (CorruptIndexException e) { e.printStackTrace(); } catch (IOException e) { e.printStackTrace(); } catch (ParseException e) { e.printStackTrace(); } catch (BrowseException e) { e.printStackTrace(); } }

结果：

total count:2
00000000000000000211
00000000000000001111
bobo分面：pic_url1-----------------------
分类1/(2)
bobo分面：price-----------------------
[3 TO 15000](2)
bobo分面：brand-----------------------
空间(2)
飞扬(2)
bobo分面：sold_num-----------------------
2(1)
3(1)