1、创建SolrServer类
SolrServer类:提供与Solr实例的连接与通信。
往Solr里添加索引数据,据说有好几种办法,这边利用SolrJ操作solr API完成index操作,具体SolrJ是个什么东西,有多么强大的功能,日后在消灭你,今儿放你一马。
简单来说就是配置SolrServer的一些信息,比如solr的服务器地址,超时时间等
以下是我的配置,把这些个信息封装在一个SolrServer类中
import org.apache.solr.client.solrj.impl.HttpSolrServer;
......
......
public class SolrServer {
private static SolrServer solrServer = null;
private static HttpSolrServer server = null; public static synchronized SolrServer getInstance() {
if (solrServer == null) {
solrServer = new SolrServer();
}
return solrServer;
} public static HttpSolrServer getServer() {
server = new HttpSolrServer(SysConstants.SOLR_SERVER);
server.setSoTimeout(20000); // socket read timeout
server.setConnectionTimeout(20000);
server.setDefaultMaxConnectionsPerHost(100);
server.setMaxTotalConnections(100);
server.setFollowRedirects(false); // defaults to false
server.setAllowCompression(true);
server.setMaxRetries(1); // defaults to 0. > 1 not recommended.
return server;
}
}
SysConstants.SOLR_SERVER=http://localhost:8080/solr/collection1
2、添加索引数据
以下是我的配置,传入的参数是一个List,这样就可以添加SolrInputDocument集合了
public static int newsIndexToSolr(List<News> newsList){
HttpSolrServer solrServer = SolrServer.getInstance().getServer();
List<SolrInputDocument> docsList = new ArrayList<SolrInputDocument>();
int iReturn = -1;
for(News news:newsList) {
SolrInputDocument doc = new SolrInputDocument();
doc.addField("id", news.getId());
String title = SolrUtil.rmHtmlTag(news.getTitle());
String content = SolrUtil.rmHtmlTag(news.getContent());
doc.addField("title", title);
doc.addField("content", content);
doc.addField("mediaId", news.getMediaId());
doc.addField("pointCode", news.getPointCode());
Date publishTime = news.getPublishTime();
doc.addField("publishTime", publishTime.getTime());
......
...... docsList.add(doc);
}
try {
solrServer.add(docsList);
UpdateResponse response = solrServer.commit();
iReturn = response.getStatus();
} catch (SolrServerException e) {
e.printStackTrace();
iReturn = -1;
} catch (IOException e) {
e.printStackTrace();
iReturn = -1;
}finally{
solrServer.shutdown();
solrServer = null;
}
return iReturn;
}
OK!collection1中已经有数据了,接下来就是各种玩了,上张图呗,不然全篇都是文字,效果不好
3、搜索结果说明
<?xml version="1.0" encoding="UTF-8"?>
<response> <lst name="responseHeader">
<int name="status">0</int>
<int name="QTime">1</int>//<!--查询耗时(毫秒)Solr有一些缓存(保存过去的搜索结果),提高了搜索效率-->
<lst name="params">//<!--查询的参数-->
<str name="indent">true</str>//<!--是否缩进XML文件-->
<str name="q">*:*</str>
<str name="_">1389874266090</str>//<!--版本信息-->
<str name="wt">xml</str>
<str name="rows">100</str>//<!--返回的结果条数-->
</lst>
</lst> //<!--numFound是找到几条,start从第几条开始显示-->
//<!--这里并没有显示得分情况(非full interface),但结果其实已经按照得分排序了(Solr默认)-->
//<!--如果是full interface查询,result会包括maxScore属性,标识最高得分-->
<result name="response" numFound="20004" start="0">
<doc>
<str name="id">change.me</str>
<str name="title">change.me</str>
<long name="_version_">1457195667361366016</long></doc>
//<!--默认情况Solr会列出所有存储的fields //(不是所有field都需要存储,虽然可能根据它来查索引,但不用包含在就结果中) // --> // <!-- //注意,某些field是多值的,由arr标签标记的 // --> <doc>
<str name="id">123456789</str>
<str name="title">标题测试啦</str>
<str name="content">内容测试啦我勒个去</str>
<long name="_version_">1457297718869229568</long></doc>
<doc>
<str name="id">123456789111</str>
<str name="title">标题测试啦111</str>
<str name="content">内容测试啦我勒个去111</str>
<long name="_version_">1457297750709239808</long></doc>
<doc>
<str name="id">22222222</str>
<str name="title">正常数据结构一个是需要考虑中文分词</str>
<str name="content">不存在不需要索引、也不需要分词,也不需要存储的字段,因为这样的字段在Lucene中无意义。</str>
<long name="_version_">1457297868749537280</long></doc>
<doc>
<str name="id">20130416092253920700002</str>
<long name="_version_">1457378992085532672</long></doc>
<doc>
<str name="id">20130416092255050701069</str>
<long name="_version_">1457378992088678400</long></doc>
<doc>
<str name="id">20130416092837610701043</str>
<long name="_version_">1457378992089726976</long></doc>
<doc>
<str name="id">20130412103434210700066</str>
<long name="_version_">1457378992091824128</long></doc>
<doc>
<str name="id">20130412103435370700004</str>
<long name="_version_">1457378992093921280</long></doc>
<doc>
<str name="id">20130412103436450701083</str>
<long name="_version_">1457378992096018432</long></doc>
</result>
</response>
在路上……