Adding aggregations support for the _ignored field
#101373
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,6 @@ | ||
| pr: 101373 | ||
| summary: Adding aggregations support for the `_ignored` field | ||
| area: Search | ||
| type: feature | ||
| issues: | ||
| - 59946 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,302 @@ | ||
| setup: | ||
| - do: | ||
| indices.create: | ||
| index: test | ||
| body: | ||
| mappings: | ||
| properties: | ||
| city: | ||
| type: keyword | ||
| ignore_above: 10 | ||
| email: | ||
| type: keyword | ||
| ignore_above: 20 | ||
| date_of_birth: | ||
| type: date | ||
| format: "dd-MM-yyyy" | ||
| ignore_malformed: true | ||
| newsletter: | ||
| type: boolean | ||
| ignore_malformed: true | ||
| ip_address: | ||
| type: ip | ||
| ignore_malformed: true | ||
| products: | ||
| type: keyword | ||
| ignore_above: 12 | ||
| total_price: | ||
| type: double | ||
| ignore_malformed: true | ||
| location: | ||
| type: geo_point | ||
| ignore_malformed: true | ||
| order_datetime: | ||
| type: date | ||
| format: "yyyy-MM-dd HH:mm:ss" | ||
| ignore_malformed: true | ||
|
|
||
| - do: | ||
| bulk: | ||
| index: test | ||
| refresh: true | ||
| body: | ||
| - { "index": { "_id": "001" } } | ||
| - { "city": "Milano", email: "alice@gmail.com", date_of_birth: "12-03-1990", newsletter: true, ip_address: "130.34.45.202", products: ["it-002-4567", "it-001-6679"], total_price: "57.99", location: [45.46, 9.16], order_datetime: "2021-05-01 20:01:37" } | ||
| - { "index": { "_id": "002" } } | ||
| - { "city": "Roma", email: "bob@gmail.com", date_of_birth: "15-05-1991", newsletter: false, ip_address: "2001:0db8:85a3:0000:0000:8a2e:0370:7334", products: [ "it-002-112467", "it-002-5579" ], total_price: "10.99", location: [ -44.78, 19.20 ], order_datetime: "2021-05-01 20:01:37" } | ||
| - { "index": { "_id": "003" } } | ||
| - { "city": "Venezia", email: "alice@gmail.com", date_of_birth: "01-09-1994", newsletter: false, ip_address: "fe80::1", products: [ "it-002", "it-003-17171717" ], total_price: "-12.99", location: [ 182.22, "20.12" ], order_datetime: "2021-05-02" } | ||
| - { "index": { "_id": "004" } } | ||
| - { "city": "Cortina d'Ampezzo", email: "a-very-long-email-address-that-should-be-ignored@gmail.com", date_of_birth: "05-06-1989", newsletter: t, ip_address: "::1", products: [ "it101020203030", "it" ], total_price: "57", location: [ 0, 9.16 ], order_datetime: "2021-05-01-20:01:37" } | ||
| - { "index": { "_id": "005" } } | ||
| - { "city": "Cortina d'Ampezzo", email: "dave@gmail.com", date_of_birth: "12-03-1990 12:30:45", newsletter: t, ip_address: "130.999.36.201", products: [ "it-002-2213", "it-001-7709" ], total_price: "twentytree/12", location: [ "45.33, 8.20" ], order_datetime: "20210501 20:01:37" } | ||
| - { "index": { "_id": "006" } } | ||
| - { "city": "Milano", email: "eric@gmail.com", date_of_birth: "19-12-90", newsletter: f, ip_address: "130.34.45", products: [ "it-002-555", "it-001-5589990000" ], total_price: "", location: [ "45.99", "9.16" ], order_datetime: "2021-05-01 20:01:37.123" } | ||
| - { "index": { "_id": "007" } } | ||
| - { "city": "Venezia", email: "luke-skywalker@gmail.com", date_of_birth: "20/03/1992", newsletter: f, ip_address: "130..45.202", products: [ "it-002-1234", "it-001-1213" ], total_price: "57.99.12", location: [ 45, 20 ], order_datetime: "2021-05-03 19:38:22" } | ||
| - { "index": { "_id": "008" } } | ||
| - { "city": "Firenze", email: "bob@gmail.com", date_of_birth: "02311988", newsletter: "", ip_address: ":::1", products: ["", ""], total_price: "0.0", location: [ 46.22, 11.22 ], order_datetime: "2021-05-03 20:01" } | ||
| - { "index": { "_id": "009" } } | ||
| - { "city": "Firenze", email: "tom@gmail.com", date_of_birth: "16-11-1990", newsletter: "not_sure", ip_address: "2001:0db8::1234:5678::", products: "it-002-4567", total_price: "0,99", location: [ 18.18, 19.19 ], order_datetime: "2021-05-03 20-01-55" } | ||
| - { "index": { "_id": "010" } } | ||
| - { "city": "Cortina d'Ampezzo", email: "alice@gmail.com", date_of_birth: "18-12-1992", newsletter: "false", ip_address: ":::1", products: "it-002-1890994567", total_price: "14,27", location: [ 45.46-9.16 ], order_datetime: "2021-05-01 20:05:37" } | ||
| - { "index": { "_id": "011" } } | ||
| - { "city": "Roma", email: "paul@gmail.com", date_of_birth: "17.15.1990", newsletter: "true", ip_address: "", products: [ "it-002-1019", "it-001-5578", "it-009-9901256" ], total_price: "49.99", location: 45.22, order_datetime: "2021-05-01T20:02:00" } | ||
|
|
||
| --- | ||
| "terms aggregation on _ignored metadata field": | ||
| - skip: | ||
| version: " - 8.14.99" | ||
| reason: "_ignored metadata field aggregation support added in 8.15" | ||
| - do: | ||
| search: | ||
| body: | ||
| size: 0 | ||
| aggs: | ||
| ignored_terms: | ||
| terms: | ||
| field: _ignored | ||
|
|
||
| - match: { hits.total.value: 11 } | ||
| - length: { aggregations.ignored_terms.buckets: 9 } | ||
| - match: { aggregations.ignored_terms.buckets.0.key: "ip_address" } | ||
| - match: { aggregations.ignored_terms.buckets.0.doc_count: 7 } | ||
| - match: { aggregations.ignored_terms.buckets.1.key: "order_datetime" } | ||
| - match: { aggregations.ignored_terms.buckets.1.doc_count: 7 } | ||
| - match: { aggregations.ignored_terms.buckets.2.key: "products" } | ||
| - match: { aggregations.ignored_terms.buckets.2.doc_count: 6 } | ||
| - match: { aggregations.ignored_terms.buckets.3.key: "date_of_birth" } | ||
| - match: { aggregations.ignored_terms.buckets.3.doc_count: 5 } | ||
| - match: { aggregations.ignored_terms.buckets.4.key: "newsletter" } | ||
| - match: { aggregations.ignored_terms.buckets.4.doc_count: 5 } | ||
| - match: { aggregations.ignored_terms.buckets.5.key: "total_price" } | ||
| - match: { aggregations.ignored_terms.buckets.5.doc_count: 4 } | ||
| - match: { aggregations.ignored_terms.buckets.6.key: "city" } | ||
| - match: { aggregations.ignored_terms.buckets.6.doc_count: 3 } | ||
| - match: { aggregations.ignored_terms.buckets.7.key: "location" } | ||
| - match: { aggregations.ignored_terms.buckets.7.doc_count: 3 } | ||
| - match: { aggregations.ignored_terms.buckets.8.key: "email" } | ||
| - match: { aggregations.ignored_terms.buckets.8.doc_count: 2 } | ||
|
|
||
| --- | ||
| "terms aggregation on _ignored metadata field with top hits": | ||
| - skip: | ||
| version: " - 8.14.99" | ||
| reason: "_ignored metadata field aggregation support added in 8.15" | ||
| - do: | ||
| search: | ||
| body: | ||
| size: 0 | ||
| aggs: | ||
| ignored_terms: | ||
| terms: | ||
| field: _ignored | ||
| size: 3 | ||
| aggs: | ||
| top_by_datetime: | ||
| top_hits: | ||
| sort: | ||
| - order_datetime: { order: desc } | ||
| size: 1 | ||
|
|
||
| - match: { hits.total.value: 11 } | ||
| - length: { aggregations.ignored_terms.buckets: 3 } | ||
|
|
||
| - match: { aggregations.ignored_terms.buckets.0.key: "ip_address" } | ||
| - match: { aggregations.ignored_terms.buckets.0.doc_count: 7 } | ||
| - match: { aggregations.ignored_terms.buckets.0.top_by_datetime.hits.hits.0._ignored: ["date_of_birth", "email", "ip_address", "newsletter", "total_price"]} | ||
|
|
||
| - match: { aggregations.ignored_terms.buckets.1.key: "order_datetime" } | ||
| - match: { aggregations.ignored_terms.buckets.1.doc_count: 7 } | ||
| - match: { aggregations.ignored_terms.buckets.1.top_by_datetime.hits.hits.0._ignored: ["order_datetime", "products"]} | ||
|
|
||
| - match: { aggregations.ignored_terms.buckets.2.key: "products" } | ||
| - match: { aggregations.ignored_terms.buckets.2.doc_count: 6 } | ||
| - match: { aggregations.ignored_terms.buckets.2.top_by_datetime.hits.hits.0._ignored: ["city", "ip_address", "location", "products", "total_price"]} | ||
|
|
||
| --- | ||
| "date histogram aggregation with terms on _ignored metadata field": | ||
| - skip: | ||
| version: " - 8.14.99" | ||
| reason: "_ignored metadata field aggregation support added in 8.15" | ||
| - do: | ||
| search: | ||
| body: | ||
| size: 0 | ||
| aggs: | ||
| order_datetime_histo: | ||
| date_histogram: | ||
| field: order_datetime | ||
| calendar_interval: day | ||
| aggs: | ||
| ignored_terms: | ||
| terms: | ||
| field: _ignored | ||
| size: 2 | ||
|
|
||
| - match: { hits.total.value: 11 } | ||
| - length: { aggregations.order_datetime_histo.buckets: 3 } | ||
|
|
||
| - match: { aggregations.order_datetime_histo.buckets.0.key_as_string: "2021-05-01 00:00:00" } | ||
| - match: { aggregations.order_datetime_histo.buckets.0.doc_count: 3 } | ||
| - match: { aggregations.order_datetime_histo.buckets.0.ignored_terms.buckets.0: { key: "products", doc_count: 2 } } | ||
|
|
||
| - match: { aggregations.order_datetime_histo.buckets.1.key_as_string: "2021-05-02 00:00:00" } | ||
| - match: { aggregations.order_datetime_histo.buckets.1.doc_count: 0 } | ||
| - length: { aggregations.order_datetime_histo.buckets.1.ignored_terms.buckets: 0 } | ||
|
|
||
| - match: { aggregations.order_datetime_histo.buckets.2.key_as_string: "2021-05-03 00:00:00" } | ||
| - match: { aggregations.order_datetime_histo.buckets.2.doc_count: 1 } | ||
| - match: { aggregations.order_datetime_histo.buckets.2.ignored_terms.buckets.0: { key: "date_of_birth", doc_count: 1 } } | ||
| - match: { aggregations.order_datetime_histo.buckets.2.ignored_terms.buckets.1: { key: "email", doc_count: 1 } } | ||
|
|
||
| --- | ||
| "cardinality aggregation on _ignored metadata field": | ||
| - skip: | ||
| version: " - 8.14.99" | ||
| reason: "_ignored metadata field aggregation support added in 8.15" | ||
| - do: | ||
| search: | ||
| body: | ||
| size: 0 | ||
| aggs: | ||
| ignored_cardinality: | ||
| cardinality: | ||
| field: _ignored | ||
|
|
||
| - match: { hits.total.value: 11 } | ||
| - match: {aggregations.ignored_cardinality.value: 9 } | ||
|
|
||
| --- | ||
| "value count aggregation on _ignored metadata field": | ||
| - skip: | ||
| version: " - 8.14.99" | ||
| reason: "_ignored metadata field aggregation support added in 8.15" | ||
| - do: | ||
| search: | ||
| body: | ||
| size: 0 | ||
| aggs: | ||
| ignored_value_count: | ||
| value_count: | ||
| field: _ignored | ||
|
|
||
| - match: { hits.total.value: 11 } | ||
| - match: {aggregations.ignored_value_count.value: 42 } | ||
|
|
||
| --- | ||
| "date range aggregation with terms on _ignored metadata field": | ||
| - skip: | ||
| version: " - 8.14.99" | ||
| reason: "_ignored metadata field aggregation support added in 8.15" | ||
| - do: | ||
| search: | ||
| body: | ||
| size: 0 | ||
| aggs: | ||
| order_datetime_range: | ||
| date_range: | ||
| field: order_datetime | ||
| format: "dd-MM-yyyy" | ||
| ranges: | ||
| - to: "03-05-2021" | ||
| - from: "02-05-2021" | ||
| aggs: | ||
| ignored_terms: | ||
| terms: | ||
| field: _ignored | ||
|
|
||
| - match: { hits.total.value: 11 } | ||
| - length: { aggregations.order_datetime_range.buckets: 2 } | ||
|
|
||
| - match: { aggregations.order_datetime_range.buckets.0.to_as_string: "03-05-2021" } | ||
| - match: { aggregations.order_datetime_range.buckets.0.doc_count: 3 } | ||
| - length: { aggregations.order_datetime_range.buckets.0.ignored_terms.buckets: 5 } | ||
| - match: { aggregations.order_datetime_range.buckets.0.ignored_terms.buckets.0: { key: "products", doc_count: 2 } } | ||
| - match: { aggregations.order_datetime_range.buckets.0.ignored_terms.buckets.1: { key: "city", doc_count: 1 } } | ||
| - match: { aggregations.order_datetime_range.buckets.0.ignored_terms.buckets.2: { key: "ip_address", doc_count: 1 } } | ||
| - match: { aggregations.order_datetime_range.buckets.0.ignored_terms.buckets.3: { key: "location", doc_count: 1 } } | ||
| - match: { aggregations.order_datetime_range.buckets.0.ignored_terms.buckets.4: { key: "total_price", doc_count: 1 } } | ||
|
|
||
| - match: { aggregations.order_datetime_range.buckets.1.from_as_string: "02-05-2021" } | ||
| - match: { aggregations.order_datetime_range.buckets.1.doc_count: 1 } | ||
| - length: { aggregations.order_datetime_range.buckets.1.ignored_terms.buckets: 5 } | ||
| - match: { aggregations.order_datetime_range.buckets.1.ignored_terms.buckets.0: { key: "date_of_birth", doc_count: 1 } } | ||
| - match: { aggregations.order_datetime_range.buckets.1.ignored_terms.buckets.1: { key: "email", doc_count: 1 } } | ||
| - match: { aggregations.order_datetime_range.buckets.1.ignored_terms.buckets.2: { key: "ip_address", doc_count: 1 } } | ||
| - match: { aggregations.order_datetime_range.buckets.1.ignored_terms.buckets.3: { key: "newsletter", doc_count: 1 } } | ||
| - match: { aggregations.order_datetime_range.buckets.1.ignored_terms.buckets.4: { key: "total_price", doc_count: 1 } } | ||
|
|
||
| --- | ||
| "random sampler aggregation with terms on _ignored metadata field": | ||
| - skip: | ||
| version: " - 8.14.99" | ||
| reason: "_ignored metadata field aggregation support added in 8.15" | ||
| - do: | ||
| search: | ||
| body: | ||
| size: 0 | ||
| aggs: | ||
| sample: | ||
| random_sampler: | ||
| probability: 1.0 # make sure buckets count is consistent | ||
| seed: 43 | ||
| aggs: | ||
| ignored_terms: | ||
| terms: | ||
| field: _ignored | ||
|
|
||
| - match: { hits.total.value: 11 } | ||
| - length: { aggregations.sample.ignored_terms.buckets: 9 } | ||
| - match: { aggregations.sample.ignored_terms.buckets.0: { key: "ip_address", doc_count: 7 } } | ||
| - match: { aggregations.sample.ignored_terms.buckets.1: { key: "order_datetime", doc_count: 7 } } | ||
| - match: { aggregations.sample.ignored_terms.buckets.2: { key: "products", doc_count: 6 } } | ||
| - match: { aggregations.sample.ignored_terms.buckets.3: { key: "date_of_birth", doc_count: 5 } } | ||
| - match: { aggregations.sample.ignored_terms.buckets.4: { key: "newsletter", doc_count: 5 } } | ||
| - match: { aggregations.sample.ignored_terms.buckets.5: { key: "total_price", doc_count: 4 } } | ||
| - match: { aggregations.sample.ignored_terms.buckets.6: { key: "city", doc_count: 3 } } | ||
| - match: { aggregations.sample.ignored_terms.buckets.7: { key: "location", doc_count: 3 } } | ||
| - match: { aggregations.sample.ignored_terms.buckets.8: { key: "email", doc_count: 2 } } | ||
|
|
||
| --- | ||
| "filter aggregation on _ignored metadata field": | ||
| - skip: | ||
| version: " - 8.14.99" | ||
| reason: "_ignored metadata field aggregation support added in 8.15" | ||
| features: close_to | ||
| - do: | ||
| search: | ||
| body: | ||
| size: 0 | ||
| aggs: | ||
| total: | ||
| sum: | ||
| field: total_price | ||
| filter_ignored: | ||
| filter: | ||
| term: | ||
| _ignored: "email" | ||
|
|
||
| - match: { hits.total.value: 11 } | ||
| - close_to: { aggregations.total.value: { value: 162.98, error: 0.01 } } | ||
| - match: { aggregations.filter_ignored.doc_count: 2 } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This is not rerturned anymore because the field is not stored anymore.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
that makes sense, I was expecting this change.