使用Solrj 获取语句分词结果的代码

时间:2023-03-09 08:47:25
使用Solrj 获取语句分词结果的代码
import java.util.ArrayList;
import java.util.Iterator;
import java.util.List; import org.apache.log4j.Logger;
import org.apache.solr.client.solrj.impl.HttpSolrServer;
import org.apache.solr.client.solrj.request.FieldAnalysisRequest;
import org.apache.solr.client.solrj.response.AnalysisResponseBase.AnalysisPhase;
import org.apache.solr.client.solrj.response.AnalysisResponseBase.TokenInfo;
import org.apache.solr.client.solrj.response.FieldAnalysisResponse; import base.util.ConfigUtil; public class SolrService {
private static Logger log = Logger.getLogger(SolrService.class); private static HttpSolrServer solrServer; static {
solrServer = new HttpSolrServer(ConfigUtil.getValue("solr.url"));
solrServer.setConnectionTimeout(5000);
} /**
* 给指定的语句分词。
*
* @param sentence 被分词的语句
* @return 分词结果
*/
public static List<String> getAnalysis(String sentence) {
FieldAnalysisRequest request = new FieldAnalysisRequest(
"/analysis/field");
request.addFieldName("title");// 字段名,随便指定一个支持中文分词的字段
request.setFieldValue("");// 字段值,可以为空字符串,但是需要显式指定此参数
request.setQuery(sentence); FieldAnalysisResponse response = null;
try {
response = request.process(solrServer);
} catch (Exception e) {
log.error("获取查询语句的分词时遇到错误", e);
} List<String> results = new ArrayList<String>();
Iterator<AnalysisPhase> it = response.getFieldNameAnalysis("title")
.getQueryPhases().iterator();
while(it.hasNext()) {
AnalysisPhase pharse = (AnalysisPhase)it.next();
List<TokenInfo> list = pharse.getTokens();
for (TokenInfo info : list) {
results.add(info.getText());
} } return results;
} }
@Test
public void getAnalysis() {
List<String> results = SolrService.getAnalysis("DevNote与大家分享开发实践经验");
for (String word : results) {
System.out.println(word);
}
} 运行效果:
devnote

大家
分享
开发
实践经验