1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
use serde::Serialize;
use crate::{search::*, util::*};
#[derive(Debug, Clone, Deserialize, Serialize, PartialEq)]
/// A multi-bucket value source based aggregation where buckets are dynamically
/// built - one per unique value.
///
/// <https://www.elastic.co/guide/en/opensearch/reference/current/search-aggregations-bucket-terms-aggregation.html>
pub struct TermsAggregation {
terms: TermsAggregationInner,
#[serde(default, skip_serializing_if = "ShouldSkip::should_skip")]
aggs: Aggregations,
}
#[derive(Debug, Clone, Deserialize, Serialize, PartialEq)]
struct TermsAggregationInner {
#[serde(default, skip_serializing_if = "ShouldSkip::should_skip")]
field: Option<String>,
#[serde(default, skip_serializing_if = "ShouldSkip::should_skip")]
size: Option<u64>,
#[serde(default, skip_serializing_if = "ShouldSkip::should_skip")]
show_term_doc_count_error: Option<bool>,
#[serde(default, skip_serializing_if = "ShouldSkip::should_skip")]
order: TermsOrderCollection,
#[serde(default, skip_serializing_if = "ShouldSkip::should_skip")]
min_doc_count: Option<u16>,
#[serde(default, skip_serializing_if = "ShouldSkip::should_skip")]
missing: Option<Term>,
#[serde(default, skip_serializing_if = "ShouldSkip::should_skip")]
include: Option<TermsInclude>,
#[serde(default, skip_serializing_if = "ShouldSkip::should_skip")]
exclude: Option<TermsExclude>,
#[serde(default, skip_serializing_if = "ShouldSkip::should_skip")]
script: Option<Script>,
}
impl Aggregation {
/// Creates an instance of [`TermsAggregation`]
///
/// - `field` - field to group by
pub fn terms<T>(field: T) -> TermsAggregation
where
T: ToString,
{
TermsAggregation {
terms: TermsAggregationInner {
field: Some(field.to_string()),
size: None,
show_term_doc_count_error: None,
order: Default::default(),
min_doc_count: None,
missing: None,
include: None,
exclude: None,
script: None,
},
aggs: Aggregations::new(),
}
}
/// Creates an instance of [`TermsAggregation`] with a script
pub fn terms_with_script(script: Script) -> TermsAggregation {
TermsAggregation {
terms: TermsAggregationInner {
field: None,
size: None,
show_term_doc_count_error: None,
order: Default::default(),
min_doc_count: None,
missing: None,
include: None,
exclude: None,
script: Some(script),
},
aggs: Aggregations::new(),
}
}
}
impl TermsAggregation {
/// The `size` parameter can be set to define how many term buckets should be returned out of the overall terms list.
///
/// By default, the node coordinating the search process will request each shard to provide its own top `size` term buckets
/// and once all shards respond, it will reduce the results to the final list that will then be returned to the client.
///
/// This means that if the number of unique terms is greater than `size`, the returned list is slightly off and not accurate
/// (it could be that the term counts are slightly off and it could even be that a term that should have been in the top `size` buckets was not returned).
pub fn size(mut self, size: u64) -> Self {
self.terms.size = Some(size);
self
}
/// Shows an error value for each term returned by the aggregation which represents the worst case error in the document
/// count and can be useful when deciding on a value for the shard_size parameter.
/// This is calculated by summing the document counts for the last term returned by all shards which did not return the term.
pub fn show_term_doc_count_error(mut self, show_term_doc_count_error: bool) -> Self {
self.terms.show_term_doc_count_error = Some(show_term_doc_count_error);
self
}
/// The order of the buckets can be customized by setting the order parameter.
/// By default, the buckets are ordered by their doc_count descending.
/// Order field allows changing this behavior.
///
/// > Sorting by ascending `_count` or by sub aggregation is discouraged as it increases the
/// > [error](https://www.elastic.co/guide/en/elasticsearch/reference/current/search-aggregations-bucket-terms-aggregation.html#search-aggregations-bucket-terms-aggregation-approximate-counts)
/// > on document counts. It is fine when a single shard is queried, or when the field that is
/// > being aggregated was used as a routing key at index time: in these cases results will be
/// > accurate since shards have disjoint values. However otherwise, errors are unbounded.
/// > One particular case that could still be useful is sorting by
/// > [min](https://www.elastic.co/guide/en/elasticsearch/reference/current/search-aggregations-metrics-min-aggregation.html) or
/// > [max](https://www.elastic.co/guide/en/elasticsearch/reference/current/search-aggregations-metrics-max-aggregation.html)
/// > aggregation: counts will not be accurate but at least the top buckets will be correctly picked.
pub fn order<T>(mut self, order: T) -> Self
where
T: Into<TermsOrderCollection>,
{
self.terms.order = order.into();
self
}
/// Only returns terms that match more than a configured number of hits using the `min_doc_count`
///
/// Default value is `1`
pub fn min_doc_count(mut self, min_doc_count: u16) -> Self {
self.terms.min_doc_count = Some(min_doc_count);
self
}
/// The missing parameter defines how documents that are missing a value should be treated.
/// By default they will be ignored but it is also possible to treat them as if they had a value.
pub fn missing<T>(mut self, missing: T) -> Self
where
T: Serialize,
{
self.terms.missing = Term::new(missing);
self
}
/// The `include` parameter can be set to include only specific terms in the response.
pub fn include<T>(mut self, include: T) -> Self
where
T: Into<TermsInclude>,
{
self.terms.include = Some(include.into());
self
}
/// The `exclude` parameter can be set to exclude specific terms from the response.
pub fn exclude<T>(mut self, exclude: T) -> Self
where
T: Into<TermsExclude>,
{
self.terms.exclude = Some(exclude.into());
self
}
/// Sets the script for the aggregation.
pub fn script(mut self, script: Script) -> Self {
self.terms.script = Some(script);
self
}
/// The field can be Keyword, Numeric, ip, boolean, or binary.
pub fn field<T>(mut self, field: T) -> Self
where
T: Into<String>,
{
self.terms.field = Some(field.into());
self
}
add_aggregate!();
}
#[cfg(test)]
mod tests {
use super::*;
#[test]
fn serialization() {
assert_serialize_aggregation(
Aggregation::terms("test_field"),
json!({ "terms": { "field": "test_field" } }),
);
assert_serialize_aggregation(
Aggregation::terms("test_field")
.size(5)
.min_doc_count(2)
.show_term_doc_count_error(false)
.missing("N/A")
.order(TermsOrder::new("test_order", SortOrder::Asc)),
json!({
"terms": {
"field": "test_field",
"size": 5,
"min_doc_count": 2,
"show_term_doc_count_error": false,
"missing": "N/A",
"order": [
{ "test_order": "asc" }
]
}
}),
);
assert_serialize_aggregation(
Aggregation::terms("test_field")
.size(0)
.order(TermsOrder::ascending("test_order"))
.missing(123)
.include(["mazda", "honda"])
.exclude("water_.*")
.aggregate(
"test_sub_agg",
Aggregation::terms("test_field2")
.size(3)
.missing(false)
.include([0, 20]),
),
json!({
"terms": {
"field": "test_field",
"size": 0,
"missing": 123,
"include": ["mazda", "honda"],
"exclude": "water_.*",
"order": [
{ "test_order": "asc" }
]
},
"aggs": {
"test_sub_agg": {
"terms": {
"field": "test_field2",
"size": 3,
"missing": false,
"include": {
"partition": 0,
"num_partitions": 20
}
}
}
}
}),
);
assert_serialize_aggregation(
Aggregation::terms_with_script(
Script::source("if (!doc['field1'].isEmpty()) { return 'f2'; } if (!doc['field2'].isEmpty()) { return 'f1'; } return 'unknown';")
.lang("painless")
).size(10),
json!({
"terms": {
"script": {
"source": "if (!doc['field1'].isEmpty()) { return 'f2'; } if (!doc['field2'].isEmpty()) { return 'f1'; } return 'unknown';",
"lang": "painless"
},
"size": 10
}
}),
);
}
}