Solr JAVA客户端SolrJ 4.9使用示例教程

http://my.oschina.net/cloudcoder/blog/305024

 

简介

SolrJ是操作Solr的JAVA客户端，它提供了增加、修改、删除、查询Solr索引的JAVA接口。SolrJ针对 Solr提供了Rest 的HTTP接口进行了封装， SolrJ底层是通过使用httpClient中的方法来完成Solr的操作。

SolrJ/Solr 跨版本兼容性

SolrJ通常向后保持兼容性，可以使用新版本的SolrJ访问较旧的Solr,反之亦然。建议使用同Solr server同版本的SolrJ,

详见 http://wiki.apache.org/solr/Solrj 中关于兼容性的描述。

示例代码

•    采用 SolrInputDocument对象 增加、删除索引

• import java.util.ArrayList;
  import java.util.Collection; import java.util.List; import org.apache.solr.client.solrj.impl.HttpSolrServer; import org.apache.solr.common.SolrInputDocument; public class AddDocsDemo {  public static final String SOLR_URL = "http://172.168.63.233:8983/solr";  public static void main(String[] args) {   //通过浏览器查看结果   //http://172.168.63.233:8983/solr/collection1/select?q=name%3A%E6%94%B9%E9%9D%A9&wt=json&indent=true   //AddDocs();   delDocs();  }  public static void AddDocs() {   String[] words = { "中央全面深化改革领导小组", "第四次会议", "审议了国企薪酬制度改革", "考试招生制度改革",     "传统媒体与新媒体融合等", "相关内容文件", "强调要", "逐步规范国有企业收入分配秩序",     "实现薪酬水平适当", "结构合理、管理规范、监督有效", "对不合理的偏高", "过高收入进行调整",     "深化考试招生制度改革", "总的目标是形成分类考试", "综合评价", "多元录取的考试招生模式", "健全促进公平",     "科学选才", "监督有力的体制机制", "着力打造一批形态多样", "手段先进", "具有竞争力的新型主流媒体",     "建成几家拥有强大实力和传播力", "公信力", "影响力的新型媒体集团" };   long start = System.currentTimeMillis();   Collection<SolrInputDocument> docs = new ArrayList<SolrInputDocument>();   for (int i = 1; i < 300; i++) {    SolrInputDocument doc1 = new SolrInputDocument();    doc1.addField("id", "id" + i, 1.0f);    doc1.addField("name", words[i % 21], 1.0f);    doc1.addField("price", 10 * i);    docs.add(doc1);   }   try {    HttpSolrServer server = new HttpSolrServer(SOLR_URL);    // 可以通过三种方式增加docs,其中server.add(docs.iterator())效率最高    // 增加后通过执行commit函数commit (936ms) // server.add(docs); // server.commit();    // 增加doc后立即commit (946ms) // UpdateRequest req = new UpdateRequest(); // req.setAction(ACTION.COMMIT, false, false); // req.add(docs); // UpdateResponse rsp = req.process(server);    // the most optimal way of updating all your docs    // in one http request(432ms)    server.add(docs.iterator());   } catch (Exception e) {    System.out.println(e);   }   System.out.println("time elapsed(ms):"     + (System.currentTimeMillis() - start));  }  public static void delDocs() {   long start = System.currentTimeMillis();   try {    HttpSolrServer server = new HttpSolrServer(SOLR_URL);    List<String> ids = new ArrayList<String>();    for (int i = 1; i < 300; i++) { ids.add("id" + i); } server.deleteById(ids); server.commit(); } catch (Exception e) { System.out.println(e); } System.out.println("time elapsed(ms):" + (System.currentTimeMillis() - start)); } }

•     采用POJOs增加、删除索引

• import java.util.ArrayList;
  import java.util.Arrays; import java.util.Collection; import java.util.List; import java.util.Random; import org.apache.solr.client.solrj.beans.DocumentObjectBinder; import org.apache.solr.client.solrj.impl.BinaryRequestWriter; import org.apache.solr.client.solrj.impl.HttpSolrServer; import org.apache.solr.common.SolrInputDocument; public class AddBeansDemo {  public static final String SOLR_URL = "http://172.168.63.233:8983/solr";  public static void main(String[] args) {   // 通过浏览器查看结果   // 要保证bean中各属性的名称在conf/schema.xml中存在，如果查询，要保存被索引   // http://172.168.63.233:8983/solr/collection1/select?q=description%3A%E6%94%B9%E9%9D%A9&wt=json&indent=true // delBeans();   AddBeans();  }  public static Random rand = new Random(47);  public static String[] authors = { "张三", "李四", "王五", "赵六", "张飞", "刘备",    "关云长" };  public static String[] links = {    "http://repository.sonatype.org/content/sites/forge-sites/m2e/",    "http://news.ifeng.com/a/20140818/41626965_0.shtml",    "http://news.ifeng.com/a/20140819/41631363_0.shtml?wratingModule_1_9_1",    "http://news.ifeng.com/topic/19382/",    "http://news.ifeng.com/topic/19644/" };  public static String genAuthors() {   List<String> list = Arrays.asList(authors).subList(0, rand.nextInt(7));   String str = "";   for (String tmp : list) {    str += " " + tmp;   }   return str;  }  public static List<String> genLinks() {   return Arrays.asList(links).subList(0, rand.nextInt(5));  }  public static void AddBeans() {   String[] words = { "中央全面深化改革领导小组", "第四次会议", "审议了国企薪酬制度改革", "考试招生制度改革",     "传统媒体与新媒体融合等", "相关内容文件", "强调要", "逐步规范国有企业收入分配秩序",     "实现薪酬水平适当", "结构合理、管理规范、监督有效", "对不合理的偏高", "过高收入进行调整",     "深化考试招生制度改革", "总的目标是形成分类考试", "综合评价", "多元录取的考试招生模式", "健全促进公平",     "科学选才", "监督有力的体制机制", "着力打造一批形态多样", "手段先进", "具有竞争力的新型主流媒体",     "建成几家拥有强大实力和传播力", "公信力", "影响力的新型媒体集团" };   long start = System.currentTimeMillis();   Collection<NewsBean> docs = new ArrayList<NewsBean>(); // DocumentObjectBinder binder = new DocumentObjectBinder();   for (int i = 1; i < 300; i++) {    NewsBean news = new NewsBean();    news.setId("id" + i);    news.setName("news" + i);    news.setAuthor(genAuthors());    news.setDescription(words[i % 21]);    news.setRelatedLinks(genLinks()); // SolrInputDocument doc1 = binder.toSolrInputDocument(news); docs.add(news); } try { HttpSolrServer server = new HttpSolrServer(SOLR_URL); server.setRequestWriter(new BinaryRequestWriter()); // 可以通过二种方式增加docs,其中server.add(docs.iterator())效率最高 // 增加后通过执行commit函数commit (981ms) // server.addBeans(docs); // server.commit(); // the most optimal way of updating all your docs // in one http request(481ms) server.addBeans(docs.iterator()); server.optimize(); //time elasped 1176ms } catch (Exception e) { System.out.println(e); } System.out.println("time elapsed(ms):" + (System.currentTimeMillis() - start)); } public static void delBeans() { long start = System.currentTimeMillis(); try { HttpSolrServer server = new HttpSolrServer(SOLR_URL); List<String> ids = new ArrayList<String>(); for (int i = 1; i < 300; i++) { ids.add("id" + i); } server.deleteById(ids); server.commit(); } catch (Exception e) { System.out.println(e); } System.out.println("time elapsed(ms):" + (System.currentTimeMillis() - start)); } }

  import java.util.List;
  
  import org.apache.solr.client.solrj.beans.Field; class NewsBean {  @Field  private String id;  @Field  private String name;  @Field  private String author;  @Field  private String description;  @Field("links")  private List<String> relatedLinks;   public NewsBean(){    }  public String getId() {   return id;  }  public void setId(String id) {   this.id = id;  }   public String getName() {   return name;  }  public void setName(String name) {   this.name = name;  }  public String getAuthor() {   return author;  }  public void setAuthor(String author) {   this.author = author;  }  public String getDescription() {   return description;  }  public void setDescription(String description) {   this.description = description;  }  public List<String> getRelatedLinks() {   return relatedLinks;  }  public void setRelatedLinks(List<String> relatedLinks) {   this.relatedLinks = relatedLinks;  } }

•     普通方式处理查询结果

• import java.io.IOException;
  
  import org.apache.solr.client.solrj.SolrQuery; import org.apache.solr.client.solrj.SolrQuery.ORDER; import org.apache.solr.client.solrj.SolrServerException; import org.apache.solr.client.solrj.impl.BinaryRequestWriter; import org.apache.solr.client.solrj.impl.HttpSolrServer; import org.apache.solr.client.solrj.impl.XMLResponseParser; import org.apache.solr.client.solrj.response.QueryResponse; import org.apache.solr.common.SolrDocument; public class QueryDocsDemo { // public static final String SOLR_URL = "http://192.168.230.128:8983/solr";  public static final String SOLR_URL = "http://172.168.63.233:8983/solr";  public static void main(String[] args) throws SolrServerException, IOException {   HttpSolrServer server = new HttpSolrServer(SOLR_URL);   server.setMaxRetries(1);   server.setMaxRetries(1); // defaults to 0. > 1 not recommended.   server.setConnectionTimeout(5000); // 5 seconds to establish TCP   //正常情况下，以下参数无须设置   //使用老版本solrj操作新版本的solr时，因为两个版本的javabin incompatible,所以需要设置Parser   server.setParser(new XMLResponseParser());   server.setSoTimeout(1000); // socket read timeout   server.setDefaultMaxConnectionsPerHost(100);   server.setMaxTotalConnections(100);   server.setFollowRedirects(false); // defaults to false   // allowCompression defaults to false.   // Server side must support gzip or deflate for this to have any effect.   server.setAllowCompression(true);   //使用ModifiableSolrParams传递参数 // ModifiableSolrParams params = new ModifiableSolrParams(); // // 192.168.230.128:8983/solr/select?q=video&fl=id,name,price&sort=price asc&start=0&rows=2&wt=json // // 设置参数，实现上面URL中的参数配置 // // 查询关键词 // params.set("q", "video"); // // 返回信息 // params.set("fl", "id,name,price,score"); // // 排序 // params.set("sort", "price asc"); // // 分页,start=0就是从0开始,rows=5当前返回5条记录,第二页就是变化start这个值为5就可以了 // params.set("start", 2); // params.set("rows", 2); // // 返回格式 // params.set("wt", "javabin"); // QueryResponse response = server.query(params);   //使用SolrQuery传递参数，SolrQuery的封装性更好   server.setRequestWriter(new BinaryRequestWriter());   SolrQuery query = new SolrQuery();   query.setQuery("video");   query.setFields("id","name","price","score");   query.setSort("price", ORDER.asc);   query.setStart(0);   query.setRows(2); // query.setRequestHandler("/select");   QueryResponse response = server.query( query );         // 搜索得到的结果数   System.out.println("Find:" + response.getResults().getNumFound());   // 输出结果   int iRow = 1;   for (SolrDocument doc : response.getResults()) {    System.out.println("----------" + iRow + "------------");    System.out.println("id: " + doc.getFieldValue("id").toString());    System.out.println("name: " + doc.getFieldValue("name").toString());    System.out.println("price: "      + doc.getFieldValue("price").toString());    System.out.println("score: " + doc.getFieldValue("score"));    iRow++;   }  } }

•     采用POJOs方式处理查询结果

• import java.io.IOException;
  import java.util.List; import org.apache.solr.client.solrj.SolrQuery; import org.apache.solr.client.solrj.SolrQuery.ORDER; import org.apache.solr.client.solrj.SolrServerException; import org.apache.solr.client.solrj.beans.DocumentObjectBinder; import org.apache.solr.client.solrj.impl.HttpSolrServer; import org.apache.solr.client.solrj.response.FacetField; import org.apache.solr.client.solrj.response.QueryResponse; import org.apache.solr.common.SolrDocument; import org.apache.solr.common.SolrDocumentList; public class QueryBeanDemo {  public static final String SOLR_URL = "http://172.168.63.233:8983/solr";  public static void main(String[] args) throws SolrServerException,    IOException {   // http://172.168.63.233:8983/solr/collection1/select?q=description%3A%E6%80%BB%E7%9B%AE%E6%A0%87&facet=true&facet.field=author_s   HttpSolrServer server = new HttpSolrServer(SOLR_URL);   server.setMaxRetries(1);   server.setMaxRetries(1); // defaults to 0. > 1 not recommended.   server.setConnectionTimeout(5000); // 5 seconds to establish TCP   // server.setRequestWriter(new BinaryRequestWriter());   SolrQuery query = new SolrQuery();   query.setQuery("description:改革");   query.setStart(0);   query.setRows(2);   query.setFacet(true);   query.addFacetField("author_s");   QueryResponse response = server.query(query);   // 搜索得到的结果数   System.out.println("Find:" + response.getResults().getNumFound());   // 输出结果   int iRow = 1;     //response.getBeans存在BUG,将DocumentObjectBinder引用的Field应该为 org.apache.solr.client.solrj.beans.Field   SolrDocumentList list = response.getResults();   DocumentObjectBinderL binder = new DocumentObjectBinderL();   List<NewsBean> beanList=binder.getBeans(NewsBean.class, list);   for(NewsBean news:beanList){    System.out.println(news.getId());   }   for (SolrDocument doc : response.getResults()) {    System.out.println("----------" + iRow + "------------");    System.out.println("id: " + doc.getFieldValue("id").toString());    System.out.println("name: " + doc.getFieldValue("name").toString());    iRow++;   }   for (FacetField ff : response.getFacetFields()) {    System.out.println(ff.getName() + "," + ff.getValueCount() + ","      + ff.getValues());   }  } }