如何解决ElasticSearch 如何管理 ngram 查询中的分数结果?
我的索引中有数百种化学物质结果climate_change
我正在使用 ngram 研究,这是我用于索引的设置。
{
"settings": {
"index.max_ngram_diff": 30,"index": {
"analysis": {
"analyzer": {
"analyzer": {
"tokenizer": "test_ngram","filter": [
"lowercase"
]
},"search_analyzer": {
"tokenizer": "test_ngram","filter": [
"lowercase"
]
}
},"tokenizer": {
"test_ngram": {
"type": "edge_ngram","min_gram": 1,"max_gram": 30,"token_chars": [
"letter","digit"
]
}
}
}
}
}
}
我的主要问题是,如果我尝试进行这样的查询
GET climate_change/_search?size=1000
{
"query": {
"match": {
"description": {
"query":"oxygen"
}
}
}
}
我看到很多结果的相同的分数是 7.381186..但这很奇怪
{
"_index" : "climate_change","_type" : "_doc","_id" : "XXX","_score" : 7.381186,"_source" : {
"recordtype" : "chemicals","description" : "carbon/oxygen"
}
},{
"_index" : "climate_change","_id" : "YYY","description" : "oxygen"
}
怎么可能? 在上面的例子中,如果我使用 ngram 并且我在 description 字段中搜索 oxygen,我希望第二个结果将比第一个得分更大。 我还尝试在设置中指定标记器“standard”和“whitespace”的类型,但无济于事。 也许是描述中的“/”字符?
非常感谢!
解决方法
您还需要在映射中为 2021.04.19 10:22:41 ERROR web[AXjnbvmjDDAgbPTbAAdV][o.s.s.w.WebServiceEngine] Fail to process request http://[server]:9000/sonarqube/batch/project.protobuf?key=[projectkey]
java.lang.NullPointerException: null
at com.google.protobuf.Internal.checkNotNull(Internal.java:64)
at com.google.protobuf.MapField$MutatabilityAwareMap.putAll(MapField.java:338)
at org.sonarqube.ws.Batch$WsProjectResponse$Builder.putAllFileDataByModuleAndPath(Batch.java:2244)
at org.sonar.server.batch.ProjectAction.buildResponse(ProjectAction.java:108)
at org.sonar.server.batch.ProjectAction.handle(ProjectAction.java:99)
at org.sonar.server.ws.WebServiceEngine.execute(WebServiceEngine.java:110)
at org.sonar.server.ws.WebServiceFilter.doFilter(WebServiceFilter.java:88)
at org.sonar.server.platform.web.MasterServletFilter$GodFilterChain.doFilter(MasterServletFilter.java:126)
at org.sonar.server.platform.web.MasterServletFilter.doFilter(MasterServletFilter.java:95)
at org.apache.catalina.core.ApplicationFilterChain.internalDoFilter(ApplicationFilterChain.java:193)
at org.apache.catalina.core.ApplicationFilterChain.doFilter(ApplicationFilterChain.java:166)
at org.sonar.server.user.UserSessionFilter.doFilter(UserSessionFilter.java:87)
at org.sonar.server.user.UserSessionFilter.doFilter(UserSessionFilter.java:71)
at org.apache.catalina.core.ApplicationFilterChain.internalDoFilter(ApplicationFilterChain.java:193)
at org.apache.catalina.core.ApplicationFilterChain.doFilter(ApplicationFilterChain.java:166)
at org.sonar.server.platform.web.CacheControlFilter.doFilter(CacheControlFilter.java:76)
at org.apache.catalina.core.ApplicationFilterChain.internalDoFilter(ApplicationFilterChain.java:193)
at org.apache.catalina.core.ApplicationFilterChain.doFilter(ApplicationFilterChain.java:166)
at org.sonar.server.platform.web.SecurityServletFilter.doHttpFilter(SecurityServletFilter.java:76)
at org.sonar.server.platform.web.SecurityServletFilter.doFilter(SecurityServletFilter.java:48)
at org.apache.catalina.core.ApplicationFilterChain.internalDoFilter(ApplicationFilterChain.java:193)
at org.apache.catalina.core.ApplicationFilterChain.doFilter(ApplicationFilterChain.java:166)
at org.sonar.server.platform.web.RedirectFilter.doFilter(RedirectFilter.java:58)
at org.apache.catalina.core.ApplicationFilterChain.internalDoFilter(ApplicationFilterChain.java:193)
at org.apache.catalina.core.ApplicationFilterChain.doFilter(ApplicationFilterChain.java:166)
at org.sonar.server.platform.web.requestid.RequestIdFilter.doFilter(RequestIdFilter.java:63)
at org.apache.catalina.core.ApplicationFilterChain.internalDoFilter(ApplicationFilterChain.java:193)
at org.apache.catalina.core.ApplicationFilterChain.doFilter(ApplicationFilterChain.java:166)
at org.sonar.server.platform.web.RootFilter.doFilter(RootFilter.java:62)
at org.apache.catalina.core.ApplicationFilterChain.internalDoFilter(ApplicationFilterChain.java:193)
at org.apache.catalina.core.ApplicationFilterChain.doFilter(ApplicationFilterChain.java:166)
at org.apache.catalina.filters.SetCharacterEncodingFilter.doFilter(SetCharacterEncodingFilter.java:109)
at org.apache.catalina.core.ApplicationFilterChain.internalDoFilter(ApplicationFilterChain.java:193)
at org.apache.catalina.core.ApplicationFilterChain.doFilter(ApplicationFilterChain.java:166)
at org.apache.catalina.core.StandardWrapperValve.invoke(StandardWrapperValve.java:199)
at org.apache.catalina.core.StandardContextValve.invoke(StandardContextValve.java:96)
at org.apache.catalina.authenticator.AuthenticatorBase.invoke(AuthenticatorBase.java:493)
at org.apache.catalina.core.StandardHostValve.invoke(StandardHostValve.java:140)
at org.apache.catalina.valves.ErrorReportValve.invoke(ErrorReportValve.java:81)
at ch.qos.logback.access.tomcat.LogbackValve.invoke(LogbackValve.java:256)
at org.apache.catalina.core.StandardEngineValve.invoke(StandardEngineValve.java:87)
at org.apache.catalina.connector.CoyoteAdapter.service(CoyoteAdapter.java:342)
at org.apache.coyote.http11.Http11Processor.service(Http11Processor.java:800)
at org.apache.coyote.AbstractProcessorLight.process(AbstractProcessorLight.java:66)
at org.apache.coyote.AbstractProtocol$ConnectionHandler.process(AbstractProtocol.java:806)
at org.apache.tomcat.util.net.NioEndpoint$SocketProcessor.doRun(NioEndpoint.java:1498)
at org.apache.tomcat.util.net.SocketProcessorBase.run(SocketProcessorBase.java:49)
at java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1128)
at java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:628)
at org.apache.tomcat.util.threads.TaskThread$WrappingRunnable.run(TaskThread.java:61)
at java.base/java.lang.Thread.run(Thread.java:834)
字段定义分析器。
添加一个包含索引数据、映射、搜索查询和搜索结果的工作示例
description
索引数据:
{
"settings": {
"analysis": {
"analyzer": {
"my_analyzer": {
"tokenizer": "test_ngram","filter": [
"lowercase"
]
},"search_analyzer": {
"tokenizer": "test_ngram","filter": [
"lowercase"
]
}
},"tokenizer": {
"test_ngram": {
"type": "edge_ngram","min_gram": 1,"max_gram": 30,"token_chars": [
"letter","digit"
]
}
}
}
},"mappings": {
"properties": {
"description": {
"type": "text","analyzer": "my_analyzer"
}
}
}
}
搜索查询:
{
"recordtype": "chemicals","description": "carbon/oxygen"
}
{
"recordtype": "chemicals","description": "oxygen"
}
搜索结果:
{
"query": {
"match": {
"description": {
"query":"oxygen"
}
}
}
}
版权声明:本文内容由互联网用户自发贡献,该文观点与技术仅代表作者本人。本站仅提供信息存储空间服务,不拥有所有权,不承担相关法律责任。如发现本站有涉嫌侵权/违法违规的内容, 请发送邮件至 dio@foxmail.com 举报,一经查实,本站将立刻删除。