solr4.9 拼音检索

最新推荐文章于 2017-10-30 15:24:04 发布

qiruiduni

最新推荐文章于 2017-10-30 15:24:04 发布

阅读量1.3k

点赞数

分类专栏： solr 文章标签： solr 拼音检索 pinyin4j

本文链接：https://blog.csdn.net/qiruiduni/article/details/38733767

版权

solr 专栏收录该内容

5 篇文章 0 订阅

订阅专栏

1、在apache-tomcat-8.0.9\webapps\solr\WEB-INF\lib目录下，添加pinyin4j-2.5.0.jar、pinyinAnalyzer4.3.1.jar、lucene-analyzers-smartcn-4.9.0.jar jar包

2、创建用于拼音检索的字段类型：

<fieldType name="text_pinyin" class="solr.TextField" positionIncrementGap="0"> 
     <analyzer type="index"> 
     		<tokenizer class="org.apache.lucene.analysis.cn.smart.SmartChineseSentenceTokenizerFactory"/> 
     		<filter class="org.apache.lucene.analysis.cn.smart.SmartChineseWordTokenFilterFactory"/> 
     		<filter class="com.shentong.search.analyzers.PinyinTransformTokenFilterFactory" minTermLenght="2" /> 
     		<filter class="com.shentong.search.analyzers.PinyinNGramTokenFilterFactory" minGram="6" maxGram="20" /> 
     </analyzer> 
     <analyzer type="query"> 
     		<tokenizer class="org.apache.lucene.analysis.cn.smart.SmartChineseSentenceTokenizerFactory" /> 
     		<filter class="org.apache.lucene.analysis.cn.smart.SmartChineseWordTokenFilterFactory" /> 
     		<filter class="com.shentong.search.analyzers.PinyinTransformTokenFilterFactory" minTermLenght="2" /> 
     		<filter class="com.shentong.search.analyzers.PinyinNGramTokenFilterFactory" minGram="6" maxGram="20" /> 
     </analyzer> 
</fieldType>

3、创建需要使用的拼音检索的字段

<field name="news_pinyin" type="text_pinyin" indexed="true" stored="true" multiValued="true" />
<copyField source="news_title" dest="news_pinyin" />
<copyField source="news_source" dest="news_pinyin" />

4、测试用例：

<span style="white-space:pre">	</span>/**
	 * 拼音检索
	 * @param pinyin 中文拼音串
	 */
	public static void pinyinQuery(String pinyin) {
		try {
			SolrServer server = SolrUtils.getInstance().getSolrServer();
			SolrQuery query = new SolrQuery();
			query.set("q", "news_pinyin:" + pinyin); 

			QueryResponse qr = server.query(query); 
			SolrDocumentList dlist = qr.getResults();

			System.out.println("总数：" + dlist.getNumFound());
			for (SolrDocument doc : dlist) {
				System.out.println("newsId: " + doc.getFieldValue("id").toString() 
						+ ", news_title: " + doc.getFieldValue("news_title") 
						+ ", news_source: " + doc.getFieldValue("news_source")
						+ ", url: " + doc.getFieldValue("source_url"));
			}
		} catch (SolrServerException e) {
			e.printStackTrace();
		}
	}