最后,我已经能够弄清楚以下技术。
我已经实现了custom analyzer
使用路径层次结构标记器,并且创建了称为的多字段,categories
以便您可以categories.facets
用于聚合/构面并使用进行普通文本搜索categories
。
定制分析器仅适用于 categories.facets
请注意"fielddata": "true"
我所在领域的财产categories.facet
PUT myindex
{
"settings": {
"analysis": {
"analyzer": {
"my_analyzer": {
"tokenizer": "my_tokenizer"
}
},
"tokenizer": {
"my_tokenizer": {
"type": "path_hierarchy",
"delimiter": ">"
}
}
}
},
"mappings": {
"mydocs": {
"properties": {
"categories": {
"type": "text",
"fields": {
"facet": {
"type": "text",
"analyzer": "my_analyzer",
"fielddata": "true"
}
}
}
}
}
}
}
POST myindex/mydocs/1
{
"categories" : "auto, tools & travel > luggage tags > luggage spotters"
}
POST myindex/mydocs/2
{
"categories" : "auto, tools & travel > luggage tags > luggage spotters"
}
POST myindex/mydocs/3
{
"categories" : "auto, tools & travel > luggage tags > luggage spotters"
}
POST myindex/mydocs/4
{
"categories" : "auto, tools & travel > luggage tags > something else"
}
您可以尝试以下查询。再次,我实现了Filter Aggregation,因为您只需要特定的单词以及Terms Aggregation。
{
"size": 0,
"aggs":{
"facets": {
"filter": {
"bool": {
"must": [
{ "match": { "categories": "luggage"} }
]
}
},
"aggs": {
"categories": {
"terms": {
"field": "categories.facet"
}
}
}
}
}
}
{
"took": 43,
"timed_out": false,
"_shards": {
"total": 1,
"successful": 1,
"skipped": 0,
"Failed": 0
},
"hits": {
"total": 11,
"max_score": 0,
"hits": []
},
"aggregations": {
"facets": {
"doc_count": 4,
"categories": {
"doc_count_error_upper_bound": 0,
"sum_other_doc_count": 0,
"buckets": [
{
"key": "auto, tools & travel ",
"doc_count": 4
},
{
"key": "auto, tools & travel > luggage tags ",
"doc_count": 4
},
{
"key": "auto, tools & travel > luggage tags > luggage spotters",
"doc_count": 3
},
{
"key": "auto, tools & travel > luggage tags > something else",
"doc_count": 1
}
]
}
}
}
}
POST myindex/_search
{
"size": 0,
"aggs":{
"facets": {
"filter": {
"bool": {
"must": [
{ "match": { "categories": "luggage"} }
]
}
},
"aggs": {
"categories": {
"terms": {
"field": "categories.facet",
"exclude": ".*>{1}.*>{1}.*"
}
}
}
}
}
}
请注意,我以这样的方式添加exclude
了一个regular expression
,即它不会考虑出现多个>
让我知道是否有帮助。