当我尝试使用search:estimate获取总搜索结果时，我得到了错误的结果..当我尝试从search:search解析总数时，它也会给我错误或从一个页面到另一个页面页面我获得了不同的总数。
如何获取搜索字符串的确切计数？
--- XXXX编辑问题------
我的数据库由JSON文档组成，这些JSON文档在结构上是分层的。例如：以下是样本，我保留在帖子的末尾..抱歉粘贴我的整个JSON结构，但我认为你明白了..
我在某些元素（如
）上创建了Field（s）/ Field（s）Range索引concept_species /species
concept_name /name
concept_registrar /registrar/name
cept_scientist /scientist/name
concept_supplier /suppliers/name
concept_entitySubType /entitySubType
concept_entityType /entityType
concept_createdDate /createdDate
concept_project /project/name
concept_moniker /moniker
当我的搜索中有一个作为“约束”时，我的xdmp：估计就好了......但是当我的搜索字符串中没有任何这些约束时，那么xdmp：估计是关闭的..我的搜索结果虽然很好..所有索引看起来都不错？为什么会这样？？因此我恢复了fn：count以获得总搜索结果。
这可能与这个问题无关，但为了完整性，我添加了这个..我创建了一个自定义约束，它基本上采用约束并将其转换为json中的路径。例如：让我们说用户想要搜索名称为“ATCC”的供应商..所以我没有用户输入整个路径，而是创建了一个自定义约束，其中就像json结构，我的constriant将其转换为实际的json路径..所以在这种情况下，搜索字符串将如下所示：((concept:suppliers.name:(ATCC))))我的自定义约束concept将其转换为以下cts：query
<cts:json-property-scope-query xmlns:cts="http://marklogic.com/cts">
<cts:property>suppliers</cts:property>
<cts:json-property-scope-query>
<cts:property>name</cts:property>
<cts:word-query>
<cts:text xml:lang="en">ATCC</cts:text>
<cts:option>case-insensitive</cts:option>
<cts:option>punctuation-insensitive</cts:option>
<cts:option>whitespace-insensitive</cts:option>
<cts:option>wildcarded</cts:option>
</cts:word-query>
</cts:json-property-scope-query>
</cts:json-property-scope-query>
这是我的JSON文档结构
{
"moniker": "",
"entityType": "",
"entitySubType": "",
"abbvNumber": "",
"bioSafetyLevel": "",
"name": "",
"extCorpID": "",
"extLotID": "",
"selectAgent": "",
"comments": "",
"nucleotideSeq": {
"seq": ""
},
"chains": [
{
"chainType": "",
"name": "",
"plasmidLotID": "",
"stochiometry": 0,
"aminoAcids": [
{
"sequence": "",
"predictedMatureSeqs": [
{
"encodedChainName": "",
"encodedChainType": "",
"sequence": "",
"domains": [
{
"allotype": "",
"domainType": "",
"entrezgeneID": "",
"geneSymbol": "",
"heavyChainIsoType": "",
"lightChainIsoType": "",
"name": "",
"regonizedAntigenFK": "",
"species": "",
"heavyChainIsoTypeMutation": "",
"antigens": [
{
"antiIdiotypeType": "",
"antibodyAntigen": "",
"corporateID": "",
"description": "",
"entrezgeneID": "",
"geneSymbol": "",
"name": "",
"relatedProtein": "",
"sequence": "",
"species": "",
"type": "",
"externalID": ""
}
]
}
]
}
],
"domains": [
{
"allotype": "",
"domainType": "",
"entrezgeneID": "",
"geneSymbol": "",
"heavyChainIsoType": "",
"lightChainIsoType": "",
"name": "",
"regonizedAntigenFK": "",
"species": "",
"heavyChainIsoTypeMutation": "",
"antigens": [
{
"antiIdiotypeType": "",
"antibodyAntigen": "",
"corporateID": "",
"description": "",
"entrezgeneID": "",
"geneSymbol": "",
"name": "",
"relatedProtein": "",
"sequence": "",
"species": "",
"type": "",
"externalID": ""
}
]
}
]
}
],
"constructs": [
{
"plasmidID": "",
"precursorAminoAcidSeq": ""
}
]
}
],
"supplier": {
"name": "",
"productID": "",
"atccCatalogNumber": "",
"lotID": ""
},
"preparation": {
"type": "",
"lotIDs": [
""
],
"amminoAcidDerivatization": "",
"chemicalConjugations": [
{
"name": "",
"dar": ""
}
],
"peptidateTreatment": "",
"proteinTreatment": "",
"purification": "",
"expressionSystem": "",
"empty": false
}
},
"project": {
"name": "",
"status": ""
},
"registrar": {
"username": "",
"email": "",
"name": "",
"upi": "",
"admin": false,
"curator": false,
"approvedUser": false
},
"scientist": {
"username": "",
"email": "",
"name": "",
"upi": "",
"admin": false,
"curator": false,
"approvedUser": false
},
"notebook": {
"elnPage": "",
"upi": "",
"location": "",
"subpage": ""
},
"growthFS": {
"mediumUsed": "",
"otherComponents": "",
"percentCO2": 0,
"percentHumudity": 0,
"percentSerum": 0,
"selectionMarker": "",
"spinnerPlateSpeed": 0,
"temp": 0,
"drugResistance": "",
"growthConditions": "",
"passageNumber": ""
},
"origin": {
"dateOfTransfection": "",
"hcAntibodyIsotype": "",
"lcAntibodyIsotype": "",
"parentCellLineLotID": "",
"parentChildRel": "",
"parentTissueSpecies": "",
"strain": "",
"tissueSource": "",
"celllineMemID": "",
"dateFrozen": "",
"strFingerprint": "",
"plasmidLotIDs": [
""
]
},
"miscellaneous": {
"expHostType": "",
"selEukaryote": "",
"selProkaryote": "",
"buffer": "",
"enotoxinLevel": "",
"enotoxinUnit": "",
"enotoxinMethod": "",
"concentrationLevel": "",
"concentrationUnit": "",
"concentrationMethod": "",
"mixture": "",
"proteinMw": 0
},
"nucleotideSeq": {
"seq": ""
},
"preparation": {
"type": "",
"lotIDs": [
""
],
"amminoAcidDerivatization": "",
"chemicalConjugations": [
{
"name": "",
"dar": ""
}
],
"peptidateTreatment": "",
"proteinTreatment": "",
"purification": "",
"expressionSystem": "",
"empty": false
},
"adc": {
"dars": [
{
"value": 0,
"method": "",
"precision": "",
"empty": false
}
],
"aggregations": [
{
"percentAggMethod": "",
"percentAggValue": 0
}
]
},
"createdBy": "",
"createdDate": "",
"modifiedBy": "",
"modifiedDate": "",
"alternateName": "",
"chains": [
{
"chainType": "",
"name": "",
"plasmidLotID": "",
"stochiometry": 0,
"aminoAcids": [
{
"sequence": "",
"predictedMatureSeqs": [
{
"avgMolWt": 0,
"encodedChainName": "",
"encodedChainType": "",
"length": 0,
"sequence": "",
"domains": [
{
"allotype": "",
"domainType": "",
"domainEnd": 0,
"entrezgeneID": "",
"geneSymbol": "",
"heavyChainIsoType": "",
"lightChainIsoType": "",
"name": "",
"regonizedAntigenFK": "",
"species": "",
"domainStart": 0,
"heavyChainIsoTypeMutation": "",
"antigens": [
{
"antiIdiotypeType": "",
"antibodyAntigen": "",
"corporateID": "",
"description": "",
"entrezgeneID": "",
"geneSymbol": "",
"name": "",
"relatedProtein": "",
"sequence": "",
"species": "",
"type": "",
"externalID": ""
}
]
}
]
}
],
"domains": [
{
"allotype": "",
"domainType": "",
"domainEnd": 0,
"entrezgeneID": "",
"geneSymbol": "",
"heavyChainIsoType": "",
"lightChainIsoType": "",
"name": "",
"regonizedAntigenFK": "",
"species": "",
"domainStart": 0,
"heavyChainIsoTypeMutation": "",
"antigens": [
{
"antiIdiotypeType": "",
"antibodyAntigen": "",
"corporateID": "",
"description": "",
"entrezgeneID": "",
"geneSymbol": "",
"name": "",
"relatedProtein": "",
"sequence": "",
"species": "",
"type": "",
"externalID": ""
}
]
}
]
}
],
"constructs": [
{
"plasmidID": "",
"precursorAminoAcidSeq": ""
}
]
}
],
"orfs": [
{
"orfEnd": 0,
"intronsPresent": "",
"orfStart": 0,
"promoters": [
""
],
"aminoAcids": [
{
"sequence": "",
"predictedMatureSeqs": [
{
"encodedChainName": "",
"encodedChainType": "",
"length": 0,
"sequence": "",
"domains": [
{
"allotype": "",
"domainType": "",
"domainEnd": 0,
"entrezgeneID": "",
"geneSymbol": "",
"heavyChainIsoType": "",
"lightChainIsoType": "",
"name": "",
"regonizedAntigenFK": "",
"species": "",
"domainStart": 0,
"heavyChainIsoTypeMutation": "",
"antigens": [
{
"antiIdiotypeType": "",
"antibodyAntigen": "",
"corporateID": "",
"description": "",
"entrezgeneID": "",
"geneSymbol": "",
"name": "",
"relatedProtein": "",
"sequence": "",
"species": "",
"type": "",
"externalID": ""
}
]
}
]
}
],
"domains": [
{
"allotype": "",
"domainType": "",
"domainEnd": 0,
"entrezgeneID": "",
"geneSymbol": "",
"heavyChainIsoType": "",
"lightChainIsoType": "",
"name": "",
"regonizedAntigenFK": "",
"species": "",
"domainStart": 0,
"heavyChainIsoTypeMutation": "",
"antigens": [
{
"antiIdiotypeType": "",
"antibodyAntigen": "",
"corporateID": "",
"description": "",
"entrezgeneID": "",
"geneSymbol": "",
"name": "",
"relatedProtein": "",
"sequence": "",
"species": "",
"type": "",
"externalID": ""
}
]
}
]
}
],
"ncSeq": {
"seq": ""
},
"label": "",
"note": ""
}
],
"antigens": [
{
"antiIdiotypeType": "",
"antibodyAntigen": "",
"corporateID": "",
"description": "",
"entrezgeneID": "",
"geneSymbol": "",
"name": "",
"relatedProtein": "",
"sequence": "",
"species": "",
"type": "",
"externalID": ""
}
],
"immunogens": [
{
"type": "",
"name": "",
"entrezgeneID": "",
"geneSymbol": "",
"corporateID": "",
"species": "",
"lotID": "",
"sequence": ""
}
],
"suppliers": [
{
"name": "",
"productID": "",
"atccCatalogNumber": "",
"lotID": ""
}
],
"domains": [
{
"allotype": "",
"domainType": "",
"domainEnd": 0,
"entrezgeneID": "",
"geneSymbol": "",
"heavyChainIsoType": "",
"lightChainIsoType": "",
"name": "",
"regonizedAntigenFK": "",
"species": "",
"domainStart": 0,
"heavyChainIsoTypeMutation": "",
"antigens": [
{
"antiIdiotypeType": "",
"antibodyAntigen": "",
"corporateID": "",
"description": "",
"entrezgeneID": "",
"geneSymbol": "",
"name": "",
"relatedProtein": "",
"sequence": "",
"species": "",
"type": "",
"externalID": ""
}
]
}
}
答案 0 :(得分：1)
Sam Mefford在他的评论中提供了更好的答案 - “请记住过滤与未过滤的搜索。如果您的查询和所有索引正确，这样您就可以运行未经过滤的搜索，您的查询将运行得更快，我相信您的搜索：估计和搜索：搜索总数将是准确的。“
fn：count（）永远不是最优的。仅用于计算小序列，文档集，结果集等。过滤搜索也明显慢于未过滤搜索。如果您调整索引，则可以获得未经过滤的搜索，其中包含来自搜索的精确计数：估计，xdmp：估计和搜索：搜索分页。
答案 1 :(得分：0)
所有关于碎片以及您看到的数字基于碎片估计的事实。如果你没有看到你的期望，那么有一些选项（更改文档，片段根/父母，过滤搜索等）..但是，正如wst提到 - 举个例子然后人们将能够给你更直接的指导..
答案 2 :(得分：0)
我受到了性能影响，但能够使用fn:count
我正在使用search:search自定义约束，所以在我的情况下我所要做的就是以下
fn:count(cts:search(fn:doc(), cts:query(search:parse($q, $options))))
答案 3 :(得分：0)
如果您没有定义任何fragmentation strategy，xdmp:estimate应该给出正确的结果。它会比fn:count快得多。 您可以重写代码 -
xdmp：estimate（cts：search（fn：doc（），cts：query（search：parse（$ q，$ options））））