我一直在尝试使用 facet 来获取字段的词频。我的查询只返回一个命中,所以我想让 facet 返回在特定字段中频率最高的术语。
我的映射:
{
"mappings":{
"document":{
"properties":{
"tags":{
"type":"object",
"properties":{
"title":{
"fields":{
"partial":{
"search_analyzer":"main",
"index_analyzer":"partial",
"type":"string",
"index" : "analyzed"
}
"title":{
"type":"string",
"analyzer":"main",
"index" : "analyzed"
}
},
"type":"multi_field"
}
}
}
}
}
},
"settings":{
"analysis":{
"filter":{
"name_ngrams":{
"side":"front",
"max_gram":50,
"min_gram":2,
"type":"edgeNGram"
}
},
"analyzer":{
"main":{
"filter": ["standard", "lowercase", "asciifolding"],
"type": "custom",
"tokenizer": "standard"
},
"partial":{
"filter":["standard","lowercase","asciifolding","name_ngrams"],
"type": "custom",
"tokenizer": "standard"
}
}
}
}
}
测试数据:
curl -XPUT localhost:9200/testindex/document -d '{"tags": {"title": "people also kill people"}}'
询问:
curl -XGET 'localhost:9200/testindex/document/_search?pretty=1' -d '
{
"query":
{
"term": { "tags.title": "people" }
},
"facets": {
"popular_tags": { "terms": {"field": "tags.title"}}
}
}'
这个结果
"hits" : {
"total" : 1,
"max_score" : 0.99381393,
"hits" : [ {
"_index" : "testindex",
"_type" : "document",
"_id" : "uI5k0wggR9KAvG9o7S7L2g",
"_score" : 0.99381393, "_source" : {"tags": {"title": "people also kill people"}}
} ]
},
"facets" : {
"popular_tags" : {
"_type" : "terms",
"missing" : 0,
"total" : 3,
"other" : 0,
"terms" : [ {
"term" : "people",
"count" : 1 // I expect this to be 2
}, {
"term" : "kill",
"count" : 1
}, {
"term" : "also",
"count" : 1
} ]
}
}
上面的结果不是我想要的。我想让频率计数为 2
"hits" : {
"total" : 1,
"max_score" : 0.99381393,
"hits" : [ {
"_index" : "testindex",
"_type" : "document",
"_id" : "uI5k0wggR9KAvG9o7S7L2g",
"_score" : 0.99381393, "_source" : {"tags": {"title": "people also kill people"}}
} ]
},
"facets" : {
"popular_tags" : {
"_type" : "terms",
"missing" : 0,
"total" : 3,
"other" : 0,
"terms" : [ {
"term" : "people",
"count" : 2
}, {
"term" : "kill",
"count" : 1
}, {
"term" : "also",
"count" : 1
} ]
}
}
我如何实现这一目标?刻面是错误的方式吗?