对于Elastic Search来说还算是新手,所以可能要面对我。我遇到一个问题,如果我使用20个或更少的字符来搜索文档,则会显示该文档,但是查询中同一单词中的任何其他字符,我没有结果:
这是我要使用的查询:
{
"match_phrase": {
"genericNames.name": {
"query": "phenoxymethylpenicillin",
"slop": 15,
"zero_terms_query": "NONE",
"boost": 1.0
}
}
}
这是完整的查询:https : //pastebin.com/DEJvP2uS
就像我说的那样,我还很陌生,这可能是因为您没有寻找正确的区域。
所以我的问题是,什么可能的区域会导致这种情况,为什么?
谢谢!
编辑:提供的是从样本数据中的一个文档中提取的内容。由于它很敏感,因此我不能显示很多,幸好我可以共享示例数据中的名称。这来自我要搜索的数据:
"genericNames":[
{
"nameType":1,
"name":"Phenoxymethylpenicillin 250mg tablets",
"nameChangeCode":"0000",
"nameBasisCode":"0001",
"nameTypeDescription":"Name",
"startDate":"1948-01-01T00:00:00.000000+0000",
"endDate":"3456-02-01T00:00:00.000000+0000"
},
{
"nameType":5,
"name":"Penicillin V 250mg tablets",
"nameTypeDescription":"Alternative Name 3",
"startDate":"1948-01-01T00:00:00.000000+0000",
"endDate":"3456-02-01T00:00:00.000000+0000"
}
],
我还提供了索引映射,因为它可能会提供其他信息:
{
"amp": {
"mappings": {
"properties": {
"_class": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"ampId": {
"type": "long"
},
"amppId": {
"type": "long"
},
"attributes": {
"type": "nested",
"properties": {
"attributeQualifier": {
"type": "keyword"
},
"attributeType": {
"type": "integer"
},
"attributeTypeDescription": {
"type": "keyword"
},
"attributeValue": {
"type": "text",
"fields": {
"raw": {
"type": "keyword"
}
}
},
"countryId": {
"type": "long"
},
"decodedValue": {
"type": "text",
"fields": {
"raw": {
"type": "keyword"
}
}
},
"endDate": {
"type": "date",
"format": "uuuu-MM-dd'T'HH:mm:ss.SSSSSSZ"
},
"startDate": {
"type": "date",
"format": "uuuu-MM-dd'T'HH:mm:ss.SSSSSSZ"
}
}
},
"dictionaries": {
"type": "nested",
"properties": {
"abbreviation": {
"type": "text",
"fields": {
"raw": {
"type": "keyword"
}
}
},
"description": {
"type": "text",
"fields": {
"raw": {
"type": "keyword"
}
}
},
"dictId": {
"type": "integer"
},
"endDate": {
"type": "date",
"format": "uuuu-MM-dd'T'HH:mm:ss.SSSSSSZ"
},
"startDate": {
"type": "date",
"format": "uuuu-MM-dd'T'HH:mm:ss.SSSSSSZ"
}
}
},
"endDate": {
"type": "date",
"format": "uuuu-MM-dd'T'HH:mm:ss.SSSSSSZ"
},
"excipients": {
"type": "nested",
"properties": {
"basisOfStrengthCode": {
"type": "keyword"
},
"bossId": {
"type": "long"
},
"endDate": {
"type": "date",
"format": "uuuu-MM-dd'T'HH:mm:ss.SSSSSSZ"
},
"id": {
"type": "long"
},
"ingredientNames": {
"properties": {
"endDate": {
"type": "date"
},
"name": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"startDate": {
"type": "date"
}
}
},
"startDate": {
"type": "date",
"format": "uuuu-MM-dd'T'HH:mm:ss.SSSSSSZ"
},
"strengthDenominatorUnitOfMeasureCode": {
"type": "keyword"
},
"strengthDenominatorValue": {
"type": "keyword"
},
"strengthNumeratorUnitOfMeasureCode": {
"type": "keyword"
},
"strengthNumeratorValue": {
"type": "keyword"
},
"strengthVal": {
"type": "keyword"
},
"unitOfMeasure": {
"type": "keyword"
}
}
},
"extractableEntry": {
"type": "boolean"
},
"genericNames": {
"type": "nested",
"properties": {
"endDate": {
"type": "date",
"format": "uuuu-MM-dd'T'HH:mm:ss.SSSSSSZ"
},
"name": {
"type": "text",
"ignore_above": 256,
"fields": {
"raw": {
"type": "keyword"
}
},
"analyzer": "autocomplete_index",
"search_analyzer": "autocomplete_search"
},
"nameBasisCode": {
"type": "keyword"
},
"nameChangeCode": {
"type": "keyword"
},
"nameType": {
"type": "integer"
},
"nameTypeDescription": {
"type": "text",
"fields": {
"raw": {
"type": "keyword"
}
}
},
"startDate": {
"type": "date",
"format": "uuuu-MM-dd'T'HH:mm:ss.SSSSSSZ"
}
}
},
"id": {
"type": "keyword"
},
"ingredients": {
"type": "nested",
"properties": {
"basisOfStrengthCode": {
"type": "keyword"
},
"bossId": {
"type": "long"
},
"endDate": {
"type": "date",
"format": "uuuu-MM-dd'T'HH:mm:ss.SSSSSSZ"
},
"id": {
"type": "long"
},
"ingredientNames": {
"properties": {
"endDate": {
"type": "date"
},
"name": {
"type": "text",
"fields": {
"keyword": {
"type": "keyword",
"ignore_above": 256
}
}
},
"startDate": {
"type": "date"
}
}
},
"startDate": {
"type": "date",
"format": "uuuu-MM-dd'T'HH:mm:ss.SSSSSSZ"
},
"strengthDenominatorUnitOfMeasureCode": {
"type": "keyword"
},
"strengthDenominatorValue": {
"type": "keyword"
},
"strengthNumeratorUnitOfMeasureCode": {
"type": "keyword"
},
"strengthNumeratorValue": {
"type": "keyword"
},
"strengthVal": {
"type": "keyword"
},
"unitOfMeasure": {
"type": "keyword"
}
}
},
"invalidEntry": {
"type": "boolean"
},
"pitId": {
"type": "integer"
},
"ppaCodes": {
"type": "nested",
"properties": {
"code": {
"type": "text",
"fields": {
"raw": {
"type": "keyword"
}
}
},
"endDate": {
"type": "date",
"format": "uuuu-MM-dd'T'HH:mm:ss.SSSSSSZ"
},
"startDate": {
"type": "date",
"format": "uuuu-MM-dd'T'HH:mm:ss.SSSSSSZ"
}
}
},
"proprietaryNames": {
"type": "nested",
"properties": {
"endDate": {
"type": "date",
"format": "uuuu-MM-dd'T'HH:mm:ss.SSSSSSZ"
},
"name": {
"type": "text",
"ignore_above": 256,
"fields": {
"raw": {
"type": "keyword"
}
},
"analyzer": "autocomplete_index",
"search_analyzer": "autocomplete_search"
},
"nameBasisCode": {
"type": "keyword"
},
"nameChangeCode": {
"type": "keyword"
},
"nameType": {
"type": "integer"
},
"nameTypeDescription": {
"type": "text",
"fields": {
"raw": {
"type": "keyword"
}
}
},
"startDate": {
"type": "date",
"format": "uuuu-MM-dd'T'HH:mm:ss.SSSSSSZ"
}
}
},
"qpuUomCde": {
"type": "keyword"
},
"qpuVal": {
"type": "keyword"
},
"qtyUomCde": {
"type": "keyword"
},
"qtyVal": {
"type": "keyword"
},
"snomedCodes": {
"type": "nested",
"properties": {
"endDate": {
"type": "date",
"format": "uuuu-MM-dd'T'HH:mm:ss.SSSSSSZ"
},
"ppaNextNo": {
"type": "text",
"fields": {
"raw": {
"type": "keyword"
}
}
},
"snomed": {
"type": "text",
"fields": {
"raw": {
"type": "keyword"
}
}
},
"startDate": {
"type": "date",
"format": "uuuu-MM-dd'T'HH:mm:ss.SSSSSSZ"
}
}
},
"snomedDescriptions": {
"type": "nested",
"properties": {
"endDate": {
"type": "date",
"format": "uuuu-MM-dd'T'HH:mm:ss.SSSSSSZ"
},
"ppaNextNo": {
"type": "text",
"fields": {
"raw": {
"type": "keyword"
}
}
},
"snomed": {
"type": "text",
"fields": {
"raw": {
"type": "keyword"
}
}
},
"startDate": {
"type": "date",
"format": "uuuu-MM-dd'T'HH:mm:ss.SSSSSSZ"
}
}
},
"startDate": {
"type": "date",
"format": "uuuu-MM-dd'T'HH:mm:ss.SSSSSSZ"
},
"suppliers": {
"type": "nested",
"properties": {
"endDate": {
"type": "date",
"format": "uuuu-MM-dd'T'HH:mm:ss.SSSSSSZ"
},
"id": {
"type": "long"
},
"names": {
"type": "nested",
"properties": {
"endDate": {
"type": "date",
"format": "uuuu-MM-dd'T'HH:mm:ss.SSSSSSZ"
},
"name": {
"type": "text",
"fields": {
"raw": {
"type": "keyword"
}
},
"analyzer": "autocomplete_index",
"search_analyzer": "autocomplete_search"
},
"nameBasisCode": {
"type": "keyword"
},
"nameChangeCode": {
"type": "keyword"
},
"nameType": {
"type": "integer"
},
"nameTypeDescription": {
"type": "text",
"fields": {
"raw": {
"type": "keyword"
}
}
},
"startDate": {
"type": "date",
"format": "uuuu-MM-dd'T'HH:mm:ss.SSSSSSZ"
}
}
},
"startDate": {
"type": "date",
"format": "uuuu-MM-dd'T'HH:mm:ss.SSSSSSZ"
}
}
},
"udfs": {
"type": "nested",
"properties": {
"ddIndicator": {
"type": "integer"
},
"endDate": {
"type": "date",
"format": "uuuu-MM-dd'T'HH:mm:ss.SSSSSSZ"
},
"startDate": {
"type": "date",
"format": "uuuu-MM-dd'T'HH:mm:ss.SSSSSSZ"
},
"udfsUomCode": {
"type": "keyword"
},
"udfsValue": {
"type": "keyword"
},
"vmpUomCode": {
"type": "keyword"
}
}
},
"vmpId": {
"type": "long"
},
"vmppId": {
"type": "long"
},
"vtms": {
"type": "nested",
"properties": {
"endDate": {
"type": "date",
"format": "uuuu-MM-dd'T'HH:mm:ss.SSSSSSZ"
},
"id": {
"type": "long"
},
"startDate": {
"type": "date",
"format": "uuuu-MM-dd'T'HH:mm:ss.SSSSSSZ"
}
}
}
}
}
}
}
编辑:添加了指向完整的查询- https://pastebin.com/DEJvP2uS
编辑:索引设置:
{
"index": {
"max_ngram_diff": "20",
"analysis": {
"filter": {
"autocomplete_suffix_filter": {
"type": "ngram",
"min_gram": "1",
"max_gram": "20"
},
"autocomplete_filter": {
"type": "edge_ngram",
"min_gram": "1",
"max_gram": "20"
}
},
"analyzer": {
"autocomplete_index": {
"filter": [
"lowercase",
"autocomplete_filter",
"autocomplete_suffix_filter"
],
"type": "custom",
"tokenizer": "standard"
},
"autocomplete_search": {
"filter": [
"lowercase"
],
"type": "custom",
"tokenizer": "standard"
}
}
},
"number_of_replicas": "1"
}
}
这一定是由于您在genericNames.name
字段中使用的自定义分析器,您有不同的自定义分析器,正在使用的索引时间autocomplete_index
和搜索时间autocomplete_search
分析器而发生的,但问题中未提供这些分析器的定义,仅mapping
提供了一部分。
请_setting
在您的索引上提供API的输出,有关更多信息,请参阅https://www.elastic.co/guide/en/elasticsearch/reference/current/indices-get-settings.html。
您需要检查生成的令牌phenoxymethylpenicillin
使用分析API两个autocomplete_index
和autocomplete_search
分析,你会发现其中的差别。
本文收集自互联网,转载请注明来源。
如有侵权,请联系[email protected] 删除。
我来说两句