如何从记录中获取所有languages 的值并使其唯一。
记录
PUT items/1
{ "language" : 10 }
PUT items/2
{ "language" : 11 }
PUT items/3
{ "language" : 10 }
查询
GET items/_search
{ ... }
# => Expected Response
[10, 11]
任何帮助都会很棒。
【问题讨论】：
fields: [languages] 将只给出给定字段的值，但在代码中使它们唯一可能更容易做到。虽然可能有一个方便的聚合可以为您完成。
标签： elasticsearch
您可以使用terms aggregation。
{
"size": 0,
"aggs" : {
"langs" : {
"terms" : { "field" : "language", "size" : 500 }
}
}}
聚合中的size 参数指定要包含在聚合结果中的最大项数。如果您需要所有结果，请将其设置为大于数据中唯一字词数量的值。
搜索将返回如下内容：
{
"took" : 16,
"timed_out" : false,
"_shards" : {
"total" : 2,
"successful" : 2,
"failed" : 0
},
"hits" : {
"total" : 1000000,
"max_score" : 0.0,
"hits" : [ ]
},
"aggregations" : {
"langs" : {
"buckets" : [ {
"key" : "10",
"doc_count" : 244812
}, {
"key" : "11",
"doc_count" : 136794
}, {
"key" : "12",
"doc_count" : 32312
} ]
}
}
}
【讨论】：
"fields" : ["language"] 带回相同的结果。您能否扩展您的答案以查看聚合框架是否可以仅返回语言值？ #=> [10, 11, 10]
language 有许多可能的值，您可能需要添加size=0 和shard_size=0，以确保获得所有 值。见elasticsearch.org/guide/en/elasticsearch/reference/current/…
我也在为自己寻找这种解决方案。我在terms aggregation 中找到了参考。
所以，按照下面的方法是正确的解决方案。
{
"aggs" : {
"langs" : {
"terms" : { "field" : "language",
"size" : 500 }
}
}}
但是如果你遇到以下错误：
"error": {
"root_cause": [
{
"type": "illegal_argument_exception",
"reason": "Fielddata is disabled on text fields by default. Set fielddata=true on [fastest_method] in order to load fielddata in memory by uninverting the inverted index. Note that this can however use significant memory. Alternatively use a keyword field instead."
}
]}
在这种情况下，您必须在请求中添加“KEYWORD”，如下所示：
{
"aggs" : {
"langs" : {
"terms" : { "field" : "language.keyword",
"size" : 500 }
}
}}
【讨论】：
如果您想获取每个language 字段唯一值的第一个文档，您可以这样做：
{
"query": {
"match_all": {
}
},
"collapse": {
"field": "language.keyword",
"inner_hits": {
"name": "latest",
"size": 1
}
}
}
【讨论】：
Elasticsearch 1.1+ 具有 Cardinality Aggregation，它将为您提供唯一计数
请注意，它实际上是一个近似值，精度可能会随着高基数数据集而降低，但在我的测试中它通常相当准确。
您还可以使用precision_threshold 参数调整精度。权衡或当然是内存使用。
文档中的这张图表显示了更高的precision_threshold 如何导致更准确的结果。
【讨论】：
如果您想在不使用任何近似值或设置幻数 (size: 500) 的情况下获得所有唯一值，请使用 COMPOSITE AGGREGATION (ES 6.5+)。
“如果您想检索嵌套术语聚合中的所有术语或所有术语组合您应该使用 COMPOSITE AGGREGATION，它允许对所有可能的术语进行分页而不是设置大小大于 terms 聚合中字段的基数。terms 聚合旨在返回顶部术语，不允许分页。”
JavaScript 中的实现示例：
const ITEMS_PER_PAGE = 1000;
const body = {
"size": 0, // Returning only aggregation results: https://www.elastic.co/guide/en/elasticsearch/reference/current/returning-only-agg-results.html
"aggs" : {
"langs": {
"composite" : {
"size": ITEMS_PER_PAGE,
"sources" : [
{ "language": { "terms" : { "field": "language" } } }
]
}
}
}
};
const uniqueLanguages = [];
while (true) {
const result = await es.search(body);
const currentUniqueLangs = result.aggregations.langs.buckets.map(bucket => bucket.key);
uniqueLanguages.push(...currentUniqueLangs);
const after = result.aggregations.langs.after_key;
if (after) {
// continue paginating unique items
body.aggs.langs.composite.after = after;
} else {
break;
}
}
console.log(uniqueLanguages);【讨论】：
size参数的问题
必须区分两个字段（derivative_id 和车辆类型）并按最便宜的汽车排序。不得不嵌套aggs。
GET /cars/_search
{
"size": 0,
"aggs": {
"distinct_by_derivative_id": {
"terms": {
"field": "derivative_id"
},
"aggs": {
"vehicle_type": {
"terms": {
"field": "vehicle_type"
},
"aggs": {
"cheapest_vehicle": {
"top_hits": {
"sort": [
{ "rental": { "order": "asc" } }
],
"_source": { "includes": [ "manufacturer_name",
"rental",
"vehicle_type"
]
},
"size": 1
}
}
}
}
}
}
}
}
结果：
{
"took" : 3,
"timed_out" : false,
"_shards" : {
"total" : 5,
"successful" : 5,
"skipped" : 0,
"failed" : 0
},
"hits" : {
"total" : {
"value" : 8,
"relation" : "eq"
},
"max_score" : null,
"hits" : [ ]
},
"aggregations" : {
"distinct_by_derivative_id" : {
"doc_count_error_upper_bound" : 0,
"sum_other_doc_count" : 0,
"buckets" : [
{
"key" : "04",
"doc_count" : 3,
"vehicle_type" : {
"doc_count_error_upper_bound" : 0,
"sum_other_doc_count" : 0,
"buckets" : [
{
"key" : "CAR",
"doc_count" : 2,
"cheapest_vehicle" : {
"hits" : {
"total" : {
"value" : 2,
"relation" : "eq"
},
"max_score" : null,
"hits" : [
{
"_index" : "cars",
"_type" : "_doc",
"_id" : "8",
"_score" : null,
"_source" : {
"vehicle_type" : "CAR",
"manufacturer_name" : "Renault",
"rental" : 89.99
},
"sort" : [
89.99
]
}
]
}
}
},
{
"key" : "LCV",
"doc_count" : 1,
"cheapest_vehicle" : {
"hits" : {
"total" : {
"value" : 1,
"relation" : "eq"
},
"max_score" : null,
"hits" : [
{
"_index" : "cars",
"_type" : "_doc",
"_id" : "7",
"_score" : null,
"_source" : {
"vehicle_type" : "LCV",
"manufacturer_name" : "Ford",
"rental" : 99.99
},
"sort" : [
99.99
]
}
]
}
}
}
]
}
},
{
"key" : "01",
"doc_count" : 2,
"vehicle_type" : {
"doc_count_error_upper_bound" : 0,
"sum_other_doc_count" : 0,
"buckets" : [
{
"key" : "CAR",
"doc_count" : 1,
"cheapest_vehicle" : {
"hits" : {
"total" : {
"value" : 1,
"relation" : "eq"
},
"max_score" : null,
"hits" : [
{
"_index" : "cars",
"_type" : "_doc",
"_id" : "1",
"_score" : null,
"_source" : {
"vehicle_type" : "CAR",
"manufacturer_name" : "Ford",
"rental" : 599.99
},
"sort" : [
599.99
]
}
]
}
}
},
{
"key" : "LCV",
"doc_count" : 1,
"cheapest_vehicle" : {
"hits" : {
"total" : {
"value" : 1,
"relation" : "eq"
},
"max_score" : null,
"hits" : [
{
"_index" : "cars",
"_type" : "_doc",
"_id" : "2",
"_score" : null,
"_source" : {
"vehicle_type" : "LCV",
"manufacturer_name" : "Ford",
"rental" : 599.99
},
"sort" : [
599.99
]
}
]
}
}
}
]
}
},
{
"key" : "02",
"doc_count" : 2,
"vehicle_type" : {
"doc_count_error_upper_bound" : 0,
"sum_other_doc_count" : 0,
"buckets" : [
{
"key" : "CAR",
"doc_count" : 2,
"cheapest_vehicle" : {
"hits" : {
"total" : {
"value" : 2,
"relation" : "eq"
},
"max_score" : null,
"hits" : [
{
"_index" : "cars",
"_type" : "_doc",
"_id" : "4",
"_score" : null,
"_source" : {
"vehicle_type" : "CAR",
"manufacturer_name" : "Audi",
"rental" : 499.99
},
"sort" : [
499.99
]
}
]
}
}
}
]
}
},
{
"key" : "03",
"doc_count" : 1,
"vehicle_type" : {
"doc_count_error_upper_bound" : 0,
"sum_other_doc_count" : 0,
"buckets" : [
{
"key" : "CAR",
"doc_count" : 1,
"cheapest_vehicle" : {
"hits" : {
"total" : {
"value" : 1,
"relation" : "eq"
},
"max_score" : null,
"hits" : [
{
"_index" : "cars",
"_type" : "_doc",
"_id" : "5",
"_score" : null,
"_source" : {
"vehicle_type" : "CAR",
"manufacturer_name" : "Audi",
"rental" : 399.99
},
"sort" : [
399.99
]
}
]
}
}
}
]
}
}
]
}
}
}
【讨论】：
默认情况下，aggs 将在数字值上工作，如果你想在字符串字段上工作，你应该在 fie 上启用它
【讨论】：