mirror of
https://github.com/elastic/kibana.git
synced 2025-04-24 01:38:56 -04:00
[ES|QL] Automate the retrieval of grouping functions (#210513)
## Summary Closes https://github.com/elastic/kibana/issues/210313 Automates the retrieval of grouping functions ( categorize and bucket ) for both the functions definitions and docs. Buckets signatures are tricky so I overwrite them with our implementation. Everything else is being retrieved by ES
This commit is contained in:
Stratoula Kalafateli
GitHub
parent
bcfdd13c11
commit
7683f01564
17 changed files with 1077 additions and 351 deletions
|
|
@ -20,7 +20,8 @@ interface DocsSectionContent {
|
|||
|
||||
(function () {
|
||||
const pathToElasticsearch = process.argv[2];
|
||||
const { scalarFunctions, aggregationFunctions } = loadFunctionDocs(pathToElasticsearch);
|
||||
const { scalarFunctions, aggregationFunctions, groupingFunctions } =
|
||||
loadFunctionDocs(pathToElasticsearch);
|
||||
writeFunctionDocs(
|
||||
scalarFunctions,
|
||||
path.join(__dirname, '../src/sections/generated/scalar_functions.tsx')
|
||||
|
|
@ -29,6 +30,10 @@ interface DocsSectionContent {
|
|||
aggregationFunctions,
|
||||
path.join(__dirname, '../src/sections/generated/aggregation_functions.tsx')
|
||||
);
|
||||
writeFunctionDocs(
|
||||
groupingFunctions,
|
||||
path.join(__dirname, '../src/sections/generated/grouping_functions.tsx')
|
||||
);
|
||||
})();
|
||||
|
||||
function loadFunctionDocs(pathToElasticsearch: string) {
|
||||
|
|
@ -48,6 +53,7 @@ function loadFunctionDocs(pathToElasticsearch: string) {
|
|||
|
||||
const scalarFunctions = new Map<string, DocsSectionContent>();
|
||||
const aggregationFunctions = new Map<string, DocsSectionContent>();
|
||||
const groupingFunctions = new Map<string, DocsSectionContent>();
|
||||
|
||||
// Iterate over each file in the directory
|
||||
for (const file of docsFiles) {
|
||||
|
|
@ -80,10 +86,16 @@ function loadFunctionDocs(pathToElasticsearch: string) {
|
|||
preview: functionDefinition.preview,
|
||||
});
|
||||
}
|
||||
if (functionDefinition.type === 'grouping') {
|
||||
groupingFunctions.set(functionName, {
|
||||
description: content,
|
||||
preview: functionDefinition.preview,
|
||||
});
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return { scalarFunctions, aggregationFunctions };
|
||||
return { scalarFunctions, aggregationFunctions, groupingFunctions };
|
||||
}
|
||||
|
||||
function writeFunctionDocs(functionDocs: Map<string, DocsSectionContent>, pathToDocsFile: string) {
|
||||
|
|
|
|||
|
|
@ -682,139 +682,6 @@ Refer to **Operators** for an overview of the supported operators.
|
|||
],
|
||||
};
|
||||
|
||||
export const groupingFunctions = {
|
||||
label: i18n.translate('languageDocumentation.documentationESQL.groupingFunctions', {
|
||||
defaultMessage: 'Grouping functions',
|
||||
}),
|
||||
description: i18n.translate(
|
||||
'languageDocumentation.documentationESQL.groupingFunctionsDocumentationESQLDescription',
|
||||
{
|
||||
defaultMessage: `These grouping functions can be used with \`STATS...BY\`:`,
|
||||
}
|
||||
),
|
||||
items: [
|
||||
{
|
||||
label: i18n.translate('languageDocumentation.documentationESQL.autoBucketFunction', {
|
||||
defaultMessage: 'BUCKET',
|
||||
}),
|
||||
description: (
|
||||
<Markdown
|
||||
markdownContent={i18n.translate(
|
||||
'languageDocumentation.documentationESQL.autoBucketFunction.markdown',
|
||||
{
|
||||
defaultMessage: `### BUCKET
|
||||
Creates groups of values - buckets - out of a datetime or numeric input. The size of the buckets can either be provided directly, or chosen based on a recommended count and values range.
|
||||
|
||||
\`BUCKET\` works in two modes:
|
||||
|
||||
1. Where the size of the bucket is computed based on a buckets count recommendation (four parameters) and a range.
|
||||
2. Where the bucket size is provided directly (two parameters).
|
||||
|
||||
Using a target number of buckets, a start of a range, and an end of a range, \`BUCKET\` picks an appropriate bucket size to generate the target number of buckets or fewer.
|
||||
|
||||
For example, requesting up to 20 buckets for a year will organize data into monthly intervals:
|
||||
|
||||
\`\`\`
|
||||
FROM employees
|
||||
| WHERE hire_date >= "1985-01-01T00:00:00Z" AND hire_date < "1986-01-01T00:00:00Z"
|
||||
| STATS hire_date = MV_SORT(VALUES(hire_date)) BY month = BUCKET(hire_date, 20, "1985-01-01T00:00:00Z", "1986-01-01T00:00:00Z")
|
||||
| SORT hire_date
|
||||
\`\`\`
|
||||
|
||||
**NOTE**: The goal isn’t to provide the exact target number of buckets, it’s to pick a range that provides _at most_ the target number of buckets.
|
||||
|
||||
You can combine \`BUCKET\` with an aggregation to create a histogram:
|
||||
|
||||
\`\`\`
|
||||
FROM employees
|
||||
| WHERE hire_date >= "1985-01-01T00:00:00Z" AND hire_date < "1986-01-01T00:00:00Z"
|
||||
| STATS hires_per_month = COUNT(*) BY month = BUCKET(hire_date, 20, "1985-01-01T00:00:00Z", "1986-01-01T00:00:00Z")
|
||||
| SORT month
|
||||
\`\`\`
|
||||
|
||||
**NOTE**: \`BUCKET\` does not create buckets that match zero documents. That’s why the previous example is missing \`1985-03-01\` and other dates.
|
||||
|
||||
Asking for more buckets can result in a smaller range. For example, requesting at most 100 buckets in a year results in weekly buckets:
|
||||
|
||||
\`\`\`
|
||||
FROM employees
|
||||
| WHERE hire_date >= "1985-01-01T00:00:00Z" AND hire_date < "1986-01-01T00:00:00Z"
|
||||
| STATS hires_per_week = COUNT(*) BY week = BUCKET(hire_date, 100, "1985-01-01T00:00:00Z", "1986-01-01T00:00:00Z")
|
||||
| SORT week
|
||||
\`\`\`
|
||||
|
||||
**NOTE**: \`BUCKET\` does not filter any rows. It only uses the provided range to pick a good bucket size. For rows with a value outside of the range, it returns a bucket value that corresponds to a bucket outside the range. Combine \`BUCKET\` with \`WHERE\` to filter rows.
|
||||
|
||||
If the desired bucket size is known in advance, simply provide it as the second argument, leaving the range out:
|
||||
|
||||
\`\`\`
|
||||
FROM employees
|
||||
| WHERE hire_date >= "1985-01-01T00:00:00Z" AND hire_date < "1986-01-01T00:00:00Z"
|
||||
| STATS hires_per_week = COUNT(*) BY week = BUCKET(hire_date, 1 week)
|
||||
| SORT week
|
||||
\`\`\`
|
||||
|
||||
**NOTE**: When providing the bucket size as the second parameter, it must be a time duration or date period.
|
||||
|
||||
\`BUCKET\` can also operate on numeric fields. For example, to create a salary histogram:
|
||||
|
||||
\`\`\`
|
||||
FROM employees
|
||||
| STATS COUNT(*) by bs = BUCKET(salary, 20, 25324, 74999)
|
||||
| SORT bs
|
||||
\`\`\`
|
||||
|
||||
Unlike the earlier example that intentionally filters on a date range, you rarely want to filter on a numeric range. You have to find the min and max separately. ES|QL doesn’t yet have an easy way to do that automatically.
|
||||
|
||||
The range can be omitted if the desired bucket size is known in advance. Simply provide it as the second argument:
|
||||
|
||||
\`\`\`
|
||||
FROM employees
|
||||
| WHERE hire_date >= "1985-01-01T00:00:00Z" AND hire_date < "1986-01-01T00:00:00Z"
|
||||
| STATS c = COUNT(1) BY b = BUCKET(salary, 5000.)
|
||||
| SORT b
|
||||
\`\`\`
|
||||
|
||||
**NOTE**: When providing the bucket size as the second parameter, it must be of a **floating point type**.
|
||||
|
||||
Here's an example to create hourly buckets for the last 24 hours, and calculate the number of events per hour:
|
||||
|
||||
\`\`\`
|
||||
FROM sample_data
|
||||
| WHERE @timestamp >= NOW() - 1 day and @timestamp < NOW()
|
||||
| STATS COUNT(*) BY bucket = BUCKET(@timestamp, 25, NOW() - 1 day, NOW())
|
||||
\`\`\`
|
||||
|
||||
Here's an example to create monthly buckets for the year 1985, and calculate the average salary by hiring month:
|
||||
|
||||
\`\`\`
|
||||
FROM employees
|
||||
| WHERE hire_date >= "1985-01-01T00:00:00Z" AND hire_date < "1986-01-01T00:00:00Z"
|
||||
| STATS AVG(salary) BY bucket = BUCKET(hire_date, 20, "1985-01-01T00:00:00Z", "1986-01-01T00:00:00Z")
|
||||
| SORT bucket
|
||||
\`\`\`
|
||||
|
||||
\`BUCKET\` may be used in both the aggregating and grouping part of the \`STATS … BY …\` command, provided that in the aggregating part the function is **referenced by an alias defined in the grouping part**, or that it is invoked with the exact same expression.
|
||||
|
||||
For example:
|
||||
|
||||
\`\`\`
|
||||
FROM employees
|
||||
| STATS s1 = b1 + 1, s2 = BUCKET(salary / 1000 + 999, 50.) + 2 BY b1 = BUCKET(salary / 100 + 99, 50.), b2 = BUCKET(salary / 1000 + 999, 50.)
|
||||
| SORT b1, b2
|
||||
| KEEP s1, b1, s2, b2
|
||||
\`\`\`
|
||||
`,
|
||||
description:
|
||||
'Text is in markdown. Do not translate function names, special characters, or field names like sum(bytes)',
|
||||
}
|
||||
)}
|
||||
/>
|
||||
),
|
||||
},
|
||||
],
|
||||
};
|
||||
|
||||
export const operators = {
|
||||
label: i18n.translate('languageDocumentation.documentationESQL.operators', {
|
||||
defaultMessage: 'Operators',
|
||||
|
|
@ -1005,3 +872,4 @@ FROM employees
|
|||
|
||||
export { functions as scalarFunctions } from './generated/scalar_functions';
|
||||
export { functions as aggregationFunctions } from './generated/aggregation_functions';
|
||||
export { functions as groupingFunctions } from './generated/grouping_functions';
|
||||
|
|
|
|||
|
|
@ -0,0 +1,99 @@
|
|||
/*
|
||||
* Copyright Elasticsearch B.V. and/or licensed to Elasticsearch B.V. under one
|
||||
* or more contributor license agreements. Licensed under the "Elastic License
|
||||
* 2.0", the "GNU Affero General Public License v3.0 only", and the "Server Side
|
||||
* Public License v 1"; you may not use this file except in compliance with, at
|
||||
* your election, the "Elastic License 2.0", the "GNU Affero General Public
|
||||
* License v3.0 only", or the "Server Side Public License, v 1".
|
||||
*/
|
||||
|
||||
import React from 'react';
|
||||
import { i18n } from '@kbn/i18n';
|
||||
import { Markdown } from '@kbn/shared-ux-markdown';
|
||||
|
||||
// DO NOT RENAME!
|
||||
export const functions = {
|
||||
label: i18n.translate('languageDocumentation.documentationESQL.groupingFunctions', {
|
||||
defaultMessage: 'Grouping functions',
|
||||
}),
|
||||
description: i18n.translate(
|
||||
'languageDocumentation.documentationESQL.groupingFunctionsDocumentationESQLDescription',
|
||||
{
|
||||
defaultMessage: `These grouping functions can be used with \`STATS...BY\`:`,
|
||||
}
|
||||
),
|
||||
// items are managed by scripts/generate_esql_docs.ts
|
||||
items: [
|
||||
// Do not edit manually... automatically generated by scripts/generate_esql_docs.ts
|
||||
{
|
||||
label: i18n.translate('languageDocumentation.documentationESQL.bucket', {
|
||||
defaultMessage: 'BUCKET',
|
||||
}),
|
||||
preview: false,
|
||||
description: (
|
||||
<Markdown
|
||||
openLinksInNewTab
|
||||
readOnly
|
||||
enableSoftLineBreaks
|
||||
markdownContent={i18n.translate(
|
||||
'languageDocumentation.documentationESQL.bucket.markdown',
|
||||
{
|
||||
defaultMessage: `<!--
|
||||
This is generated by ESQL's AbstractFunctionTestCase. Do no edit it. See ../README.md for how to regenerate it.
|
||||
-->
|
||||
|
||||
### BUCKET
|
||||
Creates groups of values - buckets - out of a datetime or numeric input.
|
||||
The size of the buckets can either be provided directly, or chosen based on a recommended count and values range.
|
||||
|
||||
\`\`\`
|
||||
FROM employees
|
||||
| WHERE hire_date >= "1985-01-01T00:00:00Z" AND hire_date < "1986-01-01T00:00:00Z"
|
||||
| STATS hire_date = MV_SORT(VALUES(hire_date)) BY month = BUCKET(hire_date, 20, "1985-01-01T00:00:00Z", "1986-01-01T00:00:00Z")
|
||||
| SORT hire_date
|
||||
\`\`\`
|
||||
`,
|
||||
description:
|
||||
'Text is in markdown. Do not translate function names, special characters, or field names like sum(bytes)',
|
||||
ignoreTag: true,
|
||||
}
|
||||
)}
|
||||
/>
|
||||
),
|
||||
},
|
||||
// Do not edit manually... automatically generated by scripts/generate_esql_docs.ts
|
||||
{
|
||||
label: i18n.translate('languageDocumentation.documentationESQL.categorize', {
|
||||
defaultMessage: 'CATEGORIZE',
|
||||
}),
|
||||
preview: true,
|
||||
description: (
|
||||
<Markdown
|
||||
openLinksInNewTab
|
||||
readOnly
|
||||
enableSoftLineBreaks
|
||||
markdownContent={i18n.translate(
|
||||
'languageDocumentation.documentationESQL.categorize.markdown',
|
||||
{
|
||||
defaultMessage: `<!--
|
||||
This is generated by ESQL's AbstractFunctionTestCase. Do no edit it. See ../README.md for how to regenerate it.
|
||||
-->
|
||||
|
||||
### CATEGORIZE
|
||||
Groups text messages into categories of similarly formatted text values.
|
||||
|
||||
\`\`\`
|
||||
FROM sample_data
|
||||
| STATS count=COUNT() BY category=CATEGORIZE(message)
|
||||
\`\`\`
|
||||
`,
|
||||
description:
|
||||
'Text is in markdown. Do not translate function names, special characters, or field names like sum(bytes)',
|
||||
ignoreTag: true,
|
||||
}
|
||||
)}
|
||||
/>
|
||||
),
|
||||
},
|
||||
],
|
||||
};
|
||||
|
|
@ -212,42 +212,6 @@ export const functions = {
|
|||
| EVAL fn_length = LENGTH(city), fn_bit_length = BIT_LENGTH(city)
|
||||
\`\`\`
|
||||
Note: All strings are in UTF-8, so a single character can use multiple bytes.
|
||||
`,
|
||||
description:
|
||||
'Text is in markdown. Do not translate function names, special characters, or field names like sum(bytes)',
|
||||
ignoreTag: true,
|
||||
}
|
||||
)}
|
||||
/>
|
||||
),
|
||||
},
|
||||
{
|
||||
label: i18n.translate('languageDocumentation.documentationESQL.bucket', {
|
||||
defaultMessage: 'BUCKET',
|
||||
}),
|
||||
preview: false,
|
||||
description: (
|
||||
<Markdown
|
||||
openLinksInNewTab
|
||||
readOnly
|
||||
enableSoftLineBreaks
|
||||
markdownContent={i18n.translate(
|
||||
'languageDocumentation.documentationESQL.bucket.markdown',
|
||||
{
|
||||
defaultMessage: `<!--
|
||||
This is generated by ESQL's AbstractFunctionTestCase. Do no edit it. See ../README.md for how to regenerate it.
|
||||
-->
|
||||
|
||||
### BUCKET
|
||||
Creates groups of values - buckets - out of a datetime or numeric input.
|
||||
The size of the buckets can either be provided directly, or chosen based on a recommended count and values range.
|
||||
|
||||
\`\`\`
|
||||
FROM employees
|
||||
| WHERE hire_date >= "1985-01-01T00:00:00Z" AND hire_date < "1986-01-01T00:00:00Z"
|
||||
| STATS hire_date = MV_SORT(VALUES(hire_date)) BY month = BUCKET(hire_date, 20, "1985-01-01T00:00:00Z", "1986-01-01T00:00:00Z")
|
||||
| SORT hire_date
|
||||
\`\`\`
|
||||
`,
|
||||
description:
|
||||
'Text is in markdown. Do not translate function names, special characters, or field names like sum(bytes)',
|
||||
|
|
@ -334,37 +298,6 @@ export const functions = {
|
|||
/>
|
||||
),
|
||||
},
|
||||
{
|
||||
label: i18n.translate('languageDocumentation.documentationESQL.categorize', {
|
||||
defaultMessage: 'CATEGORIZE',
|
||||
}),
|
||||
preview: true,
|
||||
description: (
|
||||
<Markdown
|
||||
openLinksInNewTab
|
||||
readOnly
|
||||
enableSoftLineBreaks
|
||||
markdownContent={i18n.translate(
|
||||
'languageDocumentation.documentationESQL.categorize.markdown',
|
||||
{
|
||||
defaultMessage: `<!--
|
||||
This is generated by ESQL's AbstractFunctionTestCase. Do no edit it. See ../README.md for how to regenerate it.
|
||||
-->
|
||||
### CATEGORIZE
|
||||
Groups text messages into categories of similarly formatted text values.
|
||||
\`\`\`
|
||||
FROM sample_data
|
||||
| STATS count=COUNT() BY category=CATEGORIZE(message)
|
||||
\`\`\`
|
||||
`,
|
||||
description:
|
||||
'Text is in markdown. Do not translate function names, special characters, or field names like sum(bytes)',
|
||||
ignoreTag: true,
|
||||
}
|
||||
)}
|
||||
/>
|
||||
),
|
||||
},
|
||||
// Do not edit manually... automatically generated by scripts/generate_esql_docs.ts
|
||||
{
|
||||
label: i18n.translate('languageDocumentation.documentationESQL.cbrt', {
|
||||
|
|
|
|||
|
|
@ -12,7 +12,12 @@ import { writeFile } from 'fs/promises';
|
|||
import { join } from 'path';
|
||||
import _ from 'lodash';
|
||||
import type { RecursivePartial } from '@kbn/utility-types';
|
||||
import { FunctionDefinition, FunctionParameterType, Signature } from '../src/definitions/types';
|
||||
import {
|
||||
FunctionDefinition,
|
||||
FunctionParameterType,
|
||||
FunctionReturnType,
|
||||
Signature,
|
||||
} from '../src/definitions/types';
|
||||
import { FULL_TEXT_SEARCH_FUNCTIONS } from '../src/shared/constants';
|
||||
const aliasTable: Record<string, string[]> = {
|
||||
to_version: ['to_ver'],
|
||||
|
|
@ -25,6 +30,52 @@ const aliasTable: Record<string, string[]> = {
|
|||
};
|
||||
const aliases = new Set(Object.values(aliasTable).flat());
|
||||
|
||||
const bucketParameterTypes: Array<
|
||||
[
|
||||
FunctionParameterType,
|
||||
FunctionParameterType,
|
||||
FunctionParameterType | null,
|
||||
FunctionParameterType | null,
|
||||
FunctionReturnType
|
||||
]
|
||||
> = [
|
||||
// field // bucket //from // to //result
|
||||
['date', 'date_period', null, null, 'date'],
|
||||
['date', 'integer', 'date', 'date', 'date'],
|
||||
// Modified time_duration to time_literal
|
||||
['date', 'time_literal', null, null, 'date'],
|
||||
['double', 'double', null, null, 'double'],
|
||||
['double', 'integer', 'double', 'double', 'double'],
|
||||
['double', 'integer', 'double', 'integer', 'double'],
|
||||
['double', 'integer', 'double', 'long', 'double'],
|
||||
['double', 'integer', 'integer', 'double', 'double'],
|
||||
['double', 'integer', 'integer', 'integer', 'double'],
|
||||
['double', 'integer', 'integer', 'long', 'double'],
|
||||
['double', 'integer', 'long', 'double', 'double'],
|
||||
['double', 'integer', 'long', 'integer', 'double'],
|
||||
['double', 'integer', 'long', 'long', 'double'],
|
||||
['integer', 'double', null, null, 'double'],
|
||||
['integer', 'integer', 'double', 'double', 'double'],
|
||||
['integer', 'integer', 'double', 'integer', 'double'],
|
||||
['integer', 'integer', 'double', 'long', 'double'],
|
||||
['integer', 'integer', 'integer', 'double', 'double'],
|
||||
['integer', 'integer', 'integer', 'integer', 'double'],
|
||||
['integer', 'integer', 'integer', 'long', 'double'],
|
||||
['integer', 'integer', 'long', 'double', 'double'],
|
||||
['integer', 'integer', 'long', 'integer', 'double'],
|
||||
['integer', 'integer', 'long', 'long', 'double'],
|
||||
['long', 'double', null, null, 'double'],
|
||||
['long', 'integer', 'double', 'double', 'double'],
|
||||
['long', 'integer', 'double', 'integer', 'double'],
|
||||
['long', 'integer', 'double', 'long', 'double'],
|
||||
['long', 'integer', 'integer', 'double', 'double'],
|
||||
['long', 'integer', 'integer', 'integer', 'double'],
|
||||
['long', 'integer', 'integer', 'long', 'double'],
|
||||
['long', 'integer', 'long', 'double', 'double'],
|
||||
['long', 'integer', 'long', 'integer', 'double'],
|
||||
['long', 'integer', 'long', 'long', 'double'],
|
||||
];
|
||||
|
||||
const scalarSupportedCommandsAndOptions = {
|
||||
supportedCommands: ['stats', 'inlinestats', 'metrics', 'eval', 'where', 'row', 'sort'],
|
||||
supportedOptions: ['by'],
|
||||
|
|
@ -36,7 +87,7 @@ const aggregationSupportedCommandsAndOptions = {
|
|||
|
||||
// coalesce can be removed when a test is added for version type
|
||||
// (https://github.com/elastic/elasticsearch/pull/109032#issuecomment-2150033350)
|
||||
const excludedFunctions = new Set(['bucket', 'case', 'categorize']);
|
||||
const excludedFunctions = new Set(['case']);
|
||||
|
||||
const extraFunctions: FunctionDefinition[] = [
|
||||
{
|
||||
|
|
@ -609,6 +660,38 @@ const replaceParamName = (str: string) => {
|
|||
}
|
||||
};
|
||||
|
||||
const enrichGrouping = (
|
||||
groupingFunctionDefinitions: FunctionDefinition[]
|
||||
): FunctionDefinition[] => {
|
||||
return groupingFunctionDefinitions.map((op) => {
|
||||
if (op.name === 'bucket') {
|
||||
const signatures = [
|
||||
...bucketParameterTypes.map((signature) => {
|
||||
const [fieldType, bucketType, fromType, toType, resultType] = signature;
|
||||
return {
|
||||
params: [
|
||||
{ name: 'field', type: fieldType },
|
||||
{ name: 'buckets', type: bucketType, constantOnly: true },
|
||||
...(fromType ? [{ name: 'startDate', type: fromType, constantOnly: true }] : []),
|
||||
...(toType ? [{ name: 'endDate', type: toType, constantOnly: true }] : []),
|
||||
],
|
||||
returnType: resultType,
|
||||
};
|
||||
}),
|
||||
];
|
||||
return {
|
||||
...op,
|
||||
signatures,
|
||||
supportedOptions: ['by'],
|
||||
};
|
||||
}
|
||||
return {
|
||||
...op,
|
||||
supportedOptions: ['by'],
|
||||
};
|
||||
});
|
||||
};
|
||||
|
||||
const enrichOperators = (
|
||||
operatorsFunctionDefinitions: FunctionDefinition[]
|
||||
): FunctionDefinition[] => {
|
||||
|
|
@ -686,7 +769,7 @@ const enrichOperators = (
|
|||
|
||||
function printGeneratedFunctionsFile(
|
||||
functionDefinitions: FunctionDefinition[],
|
||||
functionsType: 'aggregation' | 'scalar' | 'operators'
|
||||
functionsType: 'aggregation' | 'scalar' | 'operators' | 'grouping'
|
||||
) {
|
||||
/**
|
||||
* Deals with asciidoc internal cross-references in the function descriptions
|
||||
|
|
@ -823,6 +906,7 @@ ${functionsType === 'operators' ? `import { isNumericType } from '../../shared/e
|
|||
const scalarFunctionDefinitions: FunctionDefinition[] = [];
|
||||
const aggFunctionDefinitions: FunctionDefinition[] = [];
|
||||
const operatorDefinitions: FunctionDefinition[] = [];
|
||||
const groupingFunctionDefinitions: FunctionDefinition[] = [];
|
||||
|
||||
for (const ESDefinition of ESFunctionDefinitions) {
|
||||
if (aliases.has(ESDefinition.name) || excludedFunctions.has(ESDefinition.name)) {
|
||||
|
|
@ -843,6 +927,8 @@ ${functionsType === 'operators' ? `import { isNumericType } from '../../shared/e
|
|||
scalarFunctionDefinitions.push(functionDefinition);
|
||||
} else if (functionDefinition.type === 'agg') {
|
||||
aggFunctionDefinitions.push(functionDefinition);
|
||||
} else if (functionDefinition.type === 'grouping') {
|
||||
groupingFunctionDefinitions.push(functionDefinition);
|
||||
}
|
||||
}
|
||||
|
||||
|
|
@ -860,4 +946,8 @@ ${functionsType === 'operators' ? `import { isNumericType } from '../../shared/e
|
|||
join(__dirname, '../src/definitions/generated/operators.ts'),
|
||||
printGeneratedFunctionsFile(enrichOperators(operatorDefinitions), 'operators')
|
||||
);
|
||||
await writeFile(
|
||||
join(__dirname, '../src/definitions/generated/grouping_functions.ts'),
|
||||
printGeneratedFunctionsFile(enrichGrouping(groupingFunctionDefinitions), 'grouping')
|
||||
);
|
||||
})();
|
||||
|
|
|
|||
|
|
@ -57,7 +57,12 @@ describe('autocomplete.suggest', () => {
|
|||
describe('... <aggregates> ...', () => {
|
||||
test('lists possible aggregations on space after command', async () => {
|
||||
const { assertSuggestions } = await setup();
|
||||
const expected = ['var0 = ', ...allAggFunctions, ...allEvaFunctions];
|
||||
const expected = [
|
||||
'var0 = ',
|
||||
...allAggFunctions,
|
||||
...allGroupingFunctions,
|
||||
...allEvaFunctions,
|
||||
];
|
||||
|
||||
await assertSuggestions('from a | stats /', expected);
|
||||
await assertSuggestions('FROM a | STATS /', expected);
|
||||
|
|
@ -66,7 +71,11 @@ describe('autocomplete.suggest', () => {
|
|||
test('on assignment expression, shows all agg and eval functions', async () => {
|
||||
const { assertSuggestions } = await setup();
|
||||
|
||||
await assertSuggestions('from a | stats a=/', [...allAggFunctions, ...allEvaFunctions]);
|
||||
await assertSuggestions('from a | stats a=/', [
|
||||
...allAggFunctions,
|
||||
...allGroupingFunctions,
|
||||
...allEvaFunctions,
|
||||
]);
|
||||
});
|
||||
|
||||
test('on space after aggregate field', async () => {
|
||||
|
|
@ -81,6 +90,7 @@ describe('autocomplete.suggest', () => {
|
|||
await assertSuggestions('from a | stats a=max(b), /', [
|
||||
'var0 = ',
|
||||
...allAggFunctions,
|
||||
...allGroupingFunctions,
|
||||
...allEvaFunctions,
|
||||
]);
|
||||
});
|
||||
|
|
@ -99,7 +109,6 @@ describe('autocomplete.suggest', () => {
|
|||
await assertSuggestions('from a | stats round(/', [
|
||||
...getFunctionSignaturesByReturnType('stats', roundParameterTypes, {
|
||||
agg: true,
|
||||
grouping: true,
|
||||
}),
|
||||
...getFieldNamesByType(roundParameterTypes),
|
||||
...getFunctionSignaturesByReturnType(
|
||||
|
|
@ -206,11 +215,13 @@ describe('autocomplete.suggest', () => {
|
|||
// TODO verify that this change is ok
|
||||
...allAggFunctions,
|
||||
...allEvaFunctions,
|
||||
...allGroupingFunctions,
|
||||
]);
|
||||
await assertSuggestions('from a | stats var0=min(b),var1=c,/', [
|
||||
'var2 = ',
|
||||
...allAggFunctions,
|
||||
...allEvaFunctions,
|
||||
...allGroupingFunctions,
|
||||
]);
|
||||
});
|
||||
});
|
||||
|
|
@ -252,6 +263,7 @@ describe('autocomplete.suggest', () => {
|
|||
'var0 = ',
|
||||
...allAggFunctions,
|
||||
...allEvaFunctions,
|
||||
...allGroupingFunctions,
|
||||
]);
|
||||
await assertSuggestions('from a | stats avg(b) by c, /', [
|
||||
'var0 = ',
|
||||
|
|
|
|||
|
|
@ -14,7 +14,7 @@ import { builtinFunctions } from '../../definitions/builtin';
|
|||
import { NOT_SUGGESTED_TYPES } from '../../shared/resources_helpers';
|
||||
import { aggregationFunctionDefinitions } from '../../definitions/generated/aggregation_functions';
|
||||
import { timeUnitsToSuggest } from '../../definitions/literals';
|
||||
import { groupingFunctionDefinitions } from '../../definitions/grouping';
|
||||
import { groupingFunctionDefinitions } from '../../definitions/generated/grouping_functions';
|
||||
import * as autocomplete from '../autocomplete';
|
||||
import type { ESQLCallbacks } from '../../shared/types';
|
||||
import type { EditorContext, SuggestionRawDefinition } from '../types';
|
||||
|
|
@ -159,8 +159,6 @@ export function getFunctionSignaturesByReturnType(
|
|||
const list = [];
|
||||
if (agg) {
|
||||
list.push(...aggregationFunctionDefinitions);
|
||||
// right now all grouping functions are agg functions too
|
||||
list.push(...groupingFunctionDefinitions);
|
||||
}
|
||||
if (grouping) {
|
||||
list.push(...groupingFunctionDefinitions);
|
||||
|
|
|
|||
|
|
@ -593,7 +593,11 @@ describe('autocomplete', () => {
|
|||
// STATS argument
|
||||
testSuggestions('FROM index1 | STATS f/', [
|
||||
'var0 = ',
|
||||
...getFunctionSignaturesByReturnType('stats', 'any', { scalar: true, agg: true }),
|
||||
...getFunctionSignaturesByReturnType('stats', 'any', {
|
||||
scalar: true,
|
||||
agg: true,
|
||||
grouping: true,
|
||||
}),
|
||||
]);
|
||||
|
||||
// STATS argument BY
|
||||
|
|
@ -953,9 +957,11 @@ describe('autocomplete', () => {
|
|||
'FROM a | STATS /',
|
||||
[
|
||||
'var0 = ',
|
||||
...getFunctionSignaturesByReturnType('stats', 'any', { scalar: true, agg: true }).map(
|
||||
attachAsSnippet
|
||||
),
|
||||
...getFunctionSignaturesByReturnType('stats', 'any', {
|
||||
scalar: true,
|
||||
agg: true,
|
||||
grouping: true,
|
||||
}).map(attachAsSnippet),
|
||||
].map(attachTriggerCommand)
|
||||
);
|
||||
|
||||
|
|
|
|||
|
|
@ -1151,6 +1151,8 @@ async function getFunctionArgsSuggestions(
|
|||
} else {
|
||||
fnToIgnore.push(
|
||||
...getFunctionsToIgnoreForStats(command, finalCommandArgIndex),
|
||||
// ignore grouping functions, they are only used for grouping
|
||||
...getAllFunctions({ type: 'grouping' }).map(({ name }) => name),
|
||||
...(isAggFunctionUsedAlready(command, finalCommandArgIndex)
|
||||
? getAllFunctions({ type: 'agg' }).map(({ name }) => name)
|
||||
: [])
|
||||
|
|
|
|||
|
|
@ -10,7 +10,7 @@
|
|||
import { i18n } from '@kbn/i18n';
|
||||
import { memoize } from 'lodash';
|
||||
import { SuggestionRawDefinition } from './types';
|
||||
import { groupingFunctionDefinitions } from '../definitions/grouping';
|
||||
import { groupingFunctionDefinitions } from '../definitions/generated/grouping_functions';
|
||||
import { aggregationFunctionDefinitions } from '../definitions/generated/aggregation_functions';
|
||||
import { scalarFunctionDefinitions } from '../definitions/generated/scalar_functions';
|
||||
import { getFunctionSignatures } from '../definitions/helpers';
|
||||
|
|
|
|||
|
|
@ -0,0 +1,839 @@
|
|||
/*
|
||||
* Copyright Elasticsearch B.V. and/or licensed to Elasticsearch B.V. under one
|
||||
* or more contributor license agreements. Licensed under the "Elastic License
|
||||
* 2.0", the "GNU Affero General Public License v3.0 only", and the "Server Side
|
||||
* Public License v 1"; you may not use this file except in compliance with, at
|
||||
* your election, the "Elastic License 2.0", the "GNU Affero General Public
|
||||
* License v3.0 only", or the "Server Side Public License, v 1".
|
||||
*/
|
||||
|
||||
/**
|
||||
* __AUTOGENERATED FILE. DO NOT EDIT THIS FILE DIRECTLY.__
|
||||
*
|
||||
* @note This file is generated by the `generate_function_definitions.ts`
|
||||
* script. Do not edit it manually.
|
||||
*
|
||||
*
|
||||
*
|
||||
*
|
||||
*
|
||||
*
|
||||
*
|
||||
*
|
||||
*
|
||||
*
|
||||
*
|
||||
*
|
||||
*/
|
||||
|
||||
import { i18n } from '@kbn/i18n';
|
||||
import type { FunctionDefinition } from '../types';
|
||||
|
||||
// Do not edit this manually... generated by scripts/generate_function_definitions.ts
|
||||
const bucketDefinition: FunctionDefinition = {
|
||||
type: 'grouping',
|
||||
name: 'bucket',
|
||||
description: i18n.translate('kbn-esql-validation-autocomplete.esql.definitions.bucket', {
|
||||
defaultMessage:
|
||||
'Creates groups of values - buckets - out of a datetime or numeric input.\nThe size of the buckets can either be provided directly, or chosen based on a recommended count and values range.',
|
||||
}),
|
||||
preview: false,
|
||||
alias: undefined,
|
||||
signatures: [
|
||||
{
|
||||
params: [
|
||||
{
|
||||
name: 'field',
|
||||
type: 'date',
|
||||
},
|
||||
{
|
||||
name: 'buckets',
|
||||
type: 'date_period',
|
||||
constantOnly: true,
|
||||
},
|
||||
],
|
||||
returnType: 'date',
|
||||
},
|
||||
{
|
||||
params: [
|
||||
{
|
||||
name: 'field',
|
||||
type: 'date',
|
||||
},
|
||||
{
|
||||
name: 'buckets',
|
||||
type: 'integer',
|
||||
constantOnly: true,
|
||||
},
|
||||
{
|
||||
name: 'startDate',
|
||||
type: 'date',
|
||||
constantOnly: true,
|
||||
},
|
||||
{
|
||||
name: 'endDate',
|
||||
type: 'date',
|
||||
constantOnly: true,
|
||||
},
|
||||
],
|
||||
returnType: 'date',
|
||||
},
|
||||
{
|
||||
params: [
|
||||
{
|
||||
name: 'field',
|
||||
type: 'date',
|
||||
},
|
||||
{
|
||||
name: 'buckets',
|
||||
type: 'time_literal',
|
||||
constantOnly: true,
|
||||
},
|
||||
],
|
||||
returnType: 'date',
|
||||
},
|
||||
{
|
||||
params: [
|
||||
{
|
||||
name: 'field',
|
||||
type: 'double',
|
||||
},
|
||||
{
|
||||
name: 'buckets',
|
||||
type: 'double',
|
||||
constantOnly: true,
|
||||
},
|
||||
],
|
||||
returnType: 'double',
|
||||
},
|
||||
{
|
||||
params: [
|
||||
{
|
||||
name: 'field',
|
||||
type: 'double',
|
||||
},
|
||||
{
|
||||
name: 'buckets',
|
||||
type: 'integer',
|
||||
constantOnly: true,
|
||||
},
|
||||
{
|
||||
name: 'startDate',
|
||||
type: 'double',
|
||||
constantOnly: true,
|
||||
},
|
||||
{
|
||||
name: 'endDate',
|
||||
type: 'double',
|
||||
constantOnly: true,
|
||||
},
|
||||
],
|
||||
returnType: 'double',
|
||||
},
|
||||
{
|
||||
params: [
|
||||
{
|
||||
name: 'field',
|
||||
type: 'double',
|
||||
},
|
||||
{
|
||||
name: 'buckets',
|
||||
type: 'integer',
|
||||
constantOnly: true,
|
||||
},
|
||||
{
|
||||
name: 'startDate',
|
||||
type: 'double',
|
||||
constantOnly: true,
|
||||
},
|
||||
{
|
||||
name: 'endDate',
|
||||
type: 'integer',
|
||||
constantOnly: true,
|
||||
},
|
||||
],
|
||||
returnType: 'double',
|
||||
},
|
||||
{
|
||||
params: [
|
||||
{
|
||||
name: 'field',
|
||||
type: 'double',
|
||||
},
|
||||
{
|
||||
name: 'buckets',
|
||||
type: 'integer',
|
||||
constantOnly: true,
|
||||
},
|
||||
{
|
||||
name: 'startDate',
|
||||
type: 'double',
|
||||
constantOnly: true,
|
||||
},
|
||||
{
|
||||
name: 'endDate',
|
||||
type: 'long',
|
||||
constantOnly: true,
|
||||
},
|
||||
],
|
||||
returnType: 'double',
|
||||
},
|
||||
{
|
||||
params: [
|
||||
{
|
||||
name: 'field',
|
||||
type: 'double',
|
||||
},
|
||||
{
|
||||
name: 'buckets',
|
||||
type: 'integer',
|
||||
constantOnly: true,
|
||||
},
|
||||
{
|
||||
name: 'startDate',
|
||||
type: 'integer',
|
||||
constantOnly: true,
|
||||
},
|
||||
{
|
||||
name: 'endDate',
|
||||
type: 'double',
|
||||
constantOnly: true,
|
||||
},
|
||||
],
|
||||
returnType: 'double',
|
||||
},
|
||||
{
|
||||
params: [
|
||||
{
|
||||
name: 'field',
|
||||
type: 'double',
|
||||
},
|
||||
{
|
||||
name: 'buckets',
|
||||
type: 'integer',
|
||||
constantOnly: true,
|
||||
},
|
||||
{
|
||||
name: 'startDate',
|
||||
type: 'integer',
|
||||
constantOnly: true,
|
||||
},
|
||||
{
|
||||
name: 'endDate',
|
||||
type: 'integer',
|
||||
constantOnly: true,
|
||||
},
|
||||
],
|
||||
returnType: 'double',
|
||||
},
|
||||
{
|
||||
params: [
|
||||
{
|
||||
name: 'field',
|
||||
type: 'double',
|
||||
},
|
||||
{
|
||||
name: 'buckets',
|
||||
type: 'integer',
|
||||
constantOnly: true,
|
||||
},
|
||||
{
|
||||
name: 'startDate',
|
||||
type: 'integer',
|
||||
constantOnly: true,
|
||||
},
|
||||
{
|
||||
name: 'endDate',
|
||||
type: 'long',
|
||||
constantOnly: true,
|
||||
},
|
||||
],
|
||||
returnType: 'double',
|
||||
},
|
||||
{
|
||||
params: [
|
||||
{
|
||||
name: 'field',
|
||||
type: 'double',
|
||||
},
|
||||
{
|
||||
name: 'buckets',
|
||||
type: 'integer',
|
||||
constantOnly: true,
|
||||
},
|
||||
{
|
||||
name: 'startDate',
|
||||
type: 'long',
|
||||
constantOnly: true,
|
||||
},
|
||||
{
|
||||
name: 'endDate',
|
||||
type: 'double',
|
||||
constantOnly: true,
|
||||
},
|
||||
],
|
||||
returnType: 'double',
|
||||
},
|
||||
{
|
||||
params: [
|
||||
{
|
||||
name: 'field',
|
||||
type: 'double',
|
||||
},
|
||||
{
|
||||
name: 'buckets',
|
||||
type: 'integer',
|
||||
constantOnly: true,
|
||||
},
|
||||
{
|
||||
name: 'startDate',
|
||||
type: 'long',
|
||||
constantOnly: true,
|
||||
},
|
||||
{
|
||||
name: 'endDate',
|
||||
type: 'integer',
|
||||
constantOnly: true,
|
||||
},
|
||||
],
|
||||
returnType: 'double',
|
||||
},
|
||||
{
|
||||
params: [
|
||||
{
|
||||
name: 'field',
|
||||
type: 'double',
|
||||
},
|
||||
{
|
||||
name: 'buckets',
|
||||
type: 'integer',
|
||||
constantOnly: true,
|
||||
},
|
||||
{
|
||||
name: 'startDate',
|
||||
type: 'long',
|
||||
constantOnly: true,
|
||||
},
|
||||
{
|
||||
name: 'endDate',
|
||||
type: 'long',
|
||||
constantOnly: true,
|
||||
},
|
||||
],
|
||||
returnType: 'double',
|
||||
},
|
||||
{
|
||||
params: [
|
||||
{
|
||||
name: 'field',
|
||||
type: 'integer',
|
||||
},
|
||||
{
|
||||
name: 'buckets',
|
||||
type: 'double',
|
||||
constantOnly: true,
|
||||
},
|
||||
],
|
||||
returnType: 'double',
|
||||
},
|
||||
{
|
||||
params: [
|
||||
{
|
||||
name: 'field',
|
||||
type: 'integer',
|
||||
},
|
||||
{
|
||||
name: 'buckets',
|
||||
type: 'integer',
|
||||
constantOnly: true,
|
||||
},
|
||||
{
|
||||
name: 'startDate',
|
||||
type: 'double',
|
||||
constantOnly: true,
|
||||
},
|
||||
{
|
||||
name: 'endDate',
|
||||
type: 'double',
|
||||
constantOnly: true,
|
||||
},
|
||||
],
|
||||
returnType: 'double',
|
||||
},
|
||||
{
|
||||
params: [
|
||||
{
|
||||
name: 'field',
|
||||
type: 'integer',
|
||||
},
|
||||
{
|
||||
name: 'buckets',
|
||||
type: 'integer',
|
||||
constantOnly: true,
|
||||
},
|
||||
{
|
||||
name: 'startDate',
|
||||
type: 'double',
|
||||
constantOnly: true,
|
||||
},
|
||||
{
|
||||
name: 'endDate',
|
||||
type: 'integer',
|
||||
constantOnly: true,
|
||||
},
|
||||
],
|
||||
returnType: 'double',
|
||||
},
|
||||
{
|
||||
params: [
|
||||
{
|
||||
name: 'field',
|
||||
type: 'integer',
|
||||
},
|
||||
{
|
||||
name: 'buckets',
|
||||
type: 'integer',
|
||||
constantOnly: true,
|
||||
},
|
||||
{
|
||||
name: 'startDate',
|
||||
type: 'double',
|
||||
constantOnly: true,
|
||||
},
|
||||
{
|
||||
name: 'endDate',
|
||||
type: 'long',
|
||||
constantOnly: true,
|
||||
},
|
||||
],
|
||||
returnType: 'double',
|
||||
},
|
||||
{
|
||||
params: [
|
||||
{
|
||||
name: 'field',
|
||||
type: 'integer',
|
||||
},
|
||||
{
|
||||
name: 'buckets',
|
||||
type: 'integer',
|
||||
constantOnly: true,
|
||||
},
|
||||
{
|
||||
name: 'startDate',
|
||||
type: 'integer',
|
||||
constantOnly: true,
|
||||
},
|
||||
{
|
||||
name: 'endDate',
|
||||
type: 'double',
|
||||
constantOnly: true,
|
||||
},
|
||||
],
|
||||
returnType: 'double',
|
||||
},
|
||||
{
|
||||
params: [
|
||||
{
|
||||
name: 'field',
|
||||
type: 'integer',
|
||||
},
|
||||
{
|
||||
name: 'buckets',
|
||||
type: 'integer',
|
||||
constantOnly: true,
|
||||
},
|
||||
{
|
||||
name: 'startDate',
|
||||
type: 'integer',
|
||||
constantOnly: true,
|
||||
},
|
||||
{
|
||||
name: 'endDate',
|
||||
type: 'integer',
|
||||
constantOnly: true,
|
||||
},
|
||||
],
|
||||
returnType: 'double',
|
||||
},
|
||||
{
|
||||
params: [
|
||||
{
|
||||
name: 'field',
|
||||
type: 'integer',
|
||||
},
|
||||
{
|
||||
name: 'buckets',
|
||||
type: 'integer',
|
||||
constantOnly: true,
|
||||
},
|
||||
{
|
||||
name: 'startDate',
|
||||
type: 'integer',
|
||||
constantOnly: true,
|
||||
},
|
||||
{
|
||||
name: 'endDate',
|
||||
type: 'long',
|
||||
constantOnly: true,
|
||||
},
|
||||
],
|
||||
returnType: 'double',
|
||||
},
|
||||
{
|
||||
params: [
|
||||
{
|
||||
name: 'field',
|
||||
type: 'integer',
|
||||
},
|
||||
{
|
||||
name: 'buckets',
|
||||
type: 'integer',
|
||||
constantOnly: true,
|
||||
},
|
||||
{
|
||||
name: 'startDate',
|
||||
type: 'long',
|
||||
constantOnly: true,
|
||||
},
|
||||
{
|
||||
name: 'endDate',
|
||||
type: 'double',
|
||||
constantOnly: true,
|
||||
},
|
||||
],
|
||||
returnType: 'double',
|
||||
},
|
||||
{
|
||||
params: [
|
||||
{
|
||||
name: 'field',
|
||||
type: 'integer',
|
||||
},
|
||||
{
|
||||
name: 'buckets',
|
||||
type: 'integer',
|
||||
constantOnly: true,
|
||||
},
|
||||
{
|
||||
name: 'startDate',
|
||||
type: 'long',
|
||||
constantOnly: true,
|
||||
},
|
||||
{
|
||||
name: 'endDate',
|
||||
type: 'integer',
|
||||
constantOnly: true,
|
||||
},
|
||||
],
|
||||
returnType: 'double',
|
||||
},
|
||||
{
|
||||
params: [
|
||||
{
|
||||
name: 'field',
|
||||
type: 'integer',
|
||||
},
|
||||
{
|
||||
name: 'buckets',
|
||||
type: 'integer',
|
||||
constantOnly: true,
|
||||
},
|
||||
{
|
||||
name: 'startDate',
|
||||
type: 'long',
|
||||
constantOnly: true,
|
||||
},
|
||||
{
|
||||
name: 'endDate',
|
||||
type: 'long',
|
||||
constantOnly: true,
|
||||
},
|
||||
],
|
||||
returnType: 'double',
|
||||
},
|
||||
{
|
||||
params: [
|
||||
{
|
||||
name: 'field',
|
||||
type: 'long',
|
||||
},
|
||||
{
|
||||
name: 'buckets',
|
||||
type: 'double',
|
||||
constantOnly: true,
|
||||
},
|
||||
],
|
||||
returnType: 'double',
|
||||
},
|
||||
{
|
||||
params: [
|
||||
{
|
||||
name: 'field',
|
||||
type: 'long',
|
||||
},
|
||||
{
|
||||
name: 'buckets',
|
||||
type: 'integer',
|
||||
constantOnly: true,
|
||||
},
|
||||
{
|
||||
name: 'startDate',
|
||||
type: 'double',
|
||||
constantOnly: true,
|
||||
},
|
||||
{
|
||||
name: 'endDate',
|
||||
type: 'double',
|
||||
constantOnly: true,
|
||||
},
|
||||
],
|
||||
returnType: 'double',
|
||||
},
|
||||
{
|
||||
params: [
|
||||
{
|
||||
name: 'field',
|
||||
type: 'long',
|
||||
},
|
||||
{
|
||||
name: 'buckets',
|
||||
type: 'integer',
|
||||
constantOnly: true,
|
||||
},
|
||||
{
|
||||
name: 'startDate',
|
||||
type: 'double',
|
||||
constantOnly: true,
|
||||
},
|
||||
{
|
||||
name: 'endDate',
|
||||
type: 'integer',
|
||||
constantOnly: true,
|
||||
},
|
||||
],
|
||||
returnType: 'double',
|
||||
},
|
||||
{
|
||||
params: [
|
||||
{
|
||||
name: 'field',
|
||||
type: 'long',
|
||||
},
|
||||
{
|
||||
name: 'buckets',
|
||||
type: 'integer',
|
||||
constantOnly: true,
|
||||
},
|
||||
{
|
||||
name: 'startDate',
|
||||
type: 'double',
|
||||
constantOnly: true,
|
||||
},
|
||||
{
|
||||
name: 'endDate',
|
||||
type: 'long',
|
||||
constantOnly: true,
|
||||
},
|
||||
],
|
||||
returnType: 'double',
|
||||
},
|
||||
{
|
||||
params: [
|
||||
{
|
||||
name: 'field',
|
||||
type: 'long',
|
||||
},
|
||||
{
|
||||
name: 'buckets',
|
||||
type: 'integer',
|
||||
constantOnly: true,
|
||||
},
|
||||
{
|
||||
name: 'startDate',
|
||||
type: 'integer',
|
||||
constantOnly: true,
|
||||
},
|
||||
{
|
||||
name: 'endDate',
|
||||
type: 'double',
|
||||
constantOnly: true,
|
||||
},
|
||||
],
|
||||
returnType: 'double',
|
||||
},
|
||||
{
|
||||
params: [
|
||||
{
|
||||
name: 'field',
|
||||
type: 'long',
|
||||
},
|
||||
{
|
||||
name: 'buckets',
|
||||
type: 'integer',
|
||||
constantOnly: true,
|
||||
},
|
||||
{
|
||||
name: 'startDate',
|
||||
type: 'integer',
|
||||
constantOnly: true,
|
||||
},
|
||||
{
|
||||
name: 'endDate',
|
||||
type: 'integer',
|
||||
constantOnly: true,
|
||||
},
|
||||
],
|
||||
returnType: 'double',
|
||||
},
|
||||
{
|
||||
params: [
|
||||
{
|
||||
name: 'field',
|
||||
type: 'long',
|
||||
},
|
||||
{
|
||||
name: 'buckets',
|
||||
type: 'integer',
|
||||
constantOnly: true,
|
||||
},
|
||||
{
|
||||
name: 'startDate',
|
||||
type: 'integer',
|
||||
constantOnly: true,
|
||||
},
|
||||
{
|
||||
name: 'endDate',
|
||||
type: 'long',
|
||||
constantOnly: true,
|
||||
},
|
||||
],
|
||||
returnType: 'double',
|
||||
},
|
||||
{
|
||||
params: [
|
||||
{
|
||||
name: 'field',
|
||||
type: 'long',
|
||||
},
|
||||
{
|
||||
name: 'buckets',
|
||||
type: 'integer',
|
||||
constantOnly: true,
|
||||
},
|
||||
{
|
||||
name: 'startDate',
|
||||
type: 'long',
|
||||
constantOnly: true,
|
||||
},
|
||||
{
|
||||
name: 'endDate',
|
||||
type: 'double',
|
||||
constantOnly: true,
|
||||
},
|
||||
],
|
||||
returnType: 'double',
|
||||
},
|
||||
{
|
||||
params: [
|
||||
{
|
||||
name: 'field',
|
||||
type: 'long',
|
||||
},
|
||||
{
|
||||
name: 'buckets',
|
||||
type: 'integer',
|
||||
constantOnly: true,
|
||||
},
|
||||
{
|
||||
name: 'startDate',
|
||||
type: 'long',
|
||||
constantOnly: true,
|
||||
},
|
||||
{
|
||||
name: 'endDate',
|
||||
type: 'integer',
|
||||
constantOnly: true,
|
||||
},
|
||||
],
|
||||
returnType: 'double',
|
||||
},
|
||||
{
|
||||
params: [
|
||||
{
|
||||
name: 'field',
|
||||
type: 'long',
|
||||
},
|
||||
{
|
||||
name: 'buckets',
|
||||
type: 'integer',
|
||||
constantOnly: true,
|
||||
},
|
||||
{
|
||||
name: 'startDate',
|
||||
type: 'long',
|
||||
constantOnly: true,
|
||||
},
|
||||
{
|
||||
name: 'endDate',
|
||||
type: 'long',
|
||||
constantOnly: true,
|
||||
},
|
||||
],
|
||||
returnType: 'double',
|
||||
},
|
||||
],
|
||||
supportedCommands: ['stats', 'inlinestats', 'metrics'],
|
||||
supportedOptions: ['by'],
|
||||
validate: undefined,
|
||||
examples: [
|
||||
'FROM employees\n| WHERE hire_date >= "1985-01-01T00:00:00Z" AND hire_date < "1986-01-01T00:00:00Z"\n| STATS hire_date = MV_SORT(VALUES(hire_date)) BY month = BUCKET(hire_date, 20, "1985-01-01T00:00:00Z", "1986-01-01T00:00:00Z")\n| SORT hire_date',
|
||||
'FROM employees\n| WHERE hire_date >= "1985-01-01T00:00:00Z" AND hire_date < "1986-01-01T00:00:00Z"\n| STATS hires_per_month = COUNT(*) BY month = BUCKET(hire_date, 20, "1985-01-01T00:00:00Z", "1986-01-01T00:00:00Z")\n| SORT month',
|
||||
'FROM employees\n| WHERE hire_date >= "1985-01-01T00:00:00Z" AND hire_date < "1986-01-01T00:00:00Z"\n| STATS hires_per_week = COUNT(*) BY week = BUCKET(hire_date, 100, "1985-01-01T00:00:00Z", "1986-01-01T00:00:00Z")\n| SORT week',
|
||||
'FROM employees\n| WHERE hire_date >= "1985-01-01T00:00:00Z" AND hire_date < "1986-01-01T00:00:00Z"\n| STATS hires_per_week = COUNT(*) BY week = BUCKET(hire_date, 1 week)\n| SORT week',
|
||||
'FROM employees\n| STATS COUNT(*) by bs = BUCKET(salary, 20, 25324, 74999)\n| SORT bs',
|
||||
'FROM employees\n| WHERE hire_date >= "1985-01-01T00:00:00Z" AND hire_date < "1986-01-01T00:00:00Z"\n| STATS c = COUNT(1) BY b = BUCKET(salary, 5000.)\n| SORT b',
|
||||
'FROM sample_data \n| WHERE @timestamp >= NOW() - 1 day and @timestamp < NOW()\n| STATS COUNT(*) BY bucket = BUCKET(@timestamp, 25, NOW() - 1 day, NOW())',
|
||||
'FROM employees\n| WHERE hire_date >= "1985-01-01T00:00:00Z" AND hire_date < "1986-01-01T00:00:00Z"\n| STATS AVG(salary) BY bucket = BUCKET(hire_date, 20, "1985-01-01T00:00:00Z", "1986-01-01T00:00:00Z")\n| SORT bucket',
|
||||
'FROM employees\n| STATS s1 = b1 + 1, s2 = BUCKET(salary / 1000 + 999, 50.) + 2 BY b1 = BUCKET(salary / 100 + 99, 50.), b2 = BUCKET(salary / 1000 + 999, 50.)\n| SORT b1, b2\n| KEEP s1, b1, s2, b2',
|
||||
'FROM employees\n| STATS dates = MV_SORT(VALUES(birth_date)) BY b = BUCKET(birth_date + 1 HOUR, 1 YEAR) - 1 HOUR\n| EVAL d_count = MV_COUNT(dates)\n| SORT d_count, b\n| LIMIT 3',
|
||||
],
|
||||
};
|
||||
|
||||
// Do not edit this manually... generated by scripts/generate_function_definitions.ts
|
||||
const categorizeDefinition: FunctionDefinition = {
|
||||
type: 'grouping',
|
||||
name: 'categorize',
|
||||
description: i18n.translate('kbn-esql-validation-autocomplete.esql.definitions.categorize', {
|
||||
defaultMessage: 'Groups text messages into categories of similarly formatted text values.',
|
||||
}),
|
||||
preview: true,
|
||||
alias: undefined,
|
||||
signatures: [
|
||||
{
|
||||
params: [
|
||||
{
|
||||
name: 'field',
|
||||
type: 'keyword',
|
||||
optional: false,
|
||||
},
|
||||
],
|
||||
returnType: 'keyword',
|
||||
},
|
||||
{
|
||||
params: [
|
||||
{
|
||||
name: 'field',
|
||||
type: 'text',
|
||||
optional: false,
|
||||
},
|
||||
],
|
||||
returnType: 'keyword',
|
||||
},
|
||||
],
|
||||
supportedCommands: ['stats', 'inlinestats', 'metrics'],
|
||||
supportedOptions: ['by'],
|
||||
validate: undefined,
|
||||
examples: ['FROM sample_data\n| STATS count=COUNT() BY category=CATEGORIZE(message)'],
|
||||
};
|
||||
export const groupingFunctionDefinitions = [bucketDefinition, categorizeDefinition];
|
||||
|
|
@ -1,124 +0,0 @@
|
|||
/*
|
||||
* Copyright Elasticsearch B.V. and/or licensed to Elasticsearch B.V. under one
|
||||
* or more contributor license agreements. Licensed under the "Elastic License
|
||||
* 2.0", the "GNU Affero General Public License v3.0 only", and the "Server Side
|
||||
* Public License v 1"; you may not use this file except in compliance with, at
|
||||
* your election, the "Elastic License 2.0", the "GNU Affero General Public
|
||||
* License v3.0 only", or the "Server Side Public License, v 1".
|
||||
*/
|
||||
|
||||
import { i18n } from '@kbn/i18n';
|
||||
import { FunctionDefinition, FunctionParameterType, FunctionReturnType } from './types';
|
||||
|
||||
const groupingTypeTable: Array<
|
||||
[
|
||||
FunctionParameterType,
|
||||
FunctionParameterType,
|
||||
FunctionParameterType | null,
|
||||
FunctionParameterType | null,
|
||||
FunctionReturnType
|
||||
]
|
||||
> = [
|
||||
// field // bucket //from // to //result
|
||||
['date', 'date_period', null, null, 'date'],
|
||||
['date', 'integer', 'date', 'date', 'date'],
|
||||
// Modified time_duration to time_literal
|
||||
['date', 'time_literal', null, null, 'date'],
|
||||
['double', 'double', null, null, 'double'],
|
||||
['double', 'integer', 'double', 'double', 'double'],
|
||||
['double', 'integer', 'double', 'integer', 'double'],
|
||||
['double', 'integer', 'double', 'long', 'double'],
|
||||
['double', 'integer', 'integer', 'double', 'double'],
|
||||
['double', 'integer', 'integer', 'integer', 'double'],
|
||||
['double', 'integer', 'integer', 'long', 'double'],
|
||||
['double', 'integer', 'long', 'double', 'double'],
|
||||
['double', 'integer', 'long', 'integer', 'double'],
|
||||
['double', 'integer', 'long', 'long', 'double'],
|
||||
['integer', 'double', null, null, 'double'],
|
||||
['integer', 'integer', 'double', 'double', 'double'],
|
||||
['integer', 'integer', 'double', 'integer', 'double'],
|
||||
['integer', 'integer', 'double', 'long', 'double'],
|
||||
['integer', 'integer', 'integer', 'double', 'double'],
|
||||
['integer', 'integer', 'integer', 'integer', 'double'],
|
||||
['integer', 'integer', 'integer', 'long', 'double'],
|
||||
['integer', 'integer', 'long', 'double', 'double'],
|
||||
['integer', 'integer', 'long', 'integer', 'double'],
|
||||
['integer', 'integer', 'long', 'long', 'double'],
|
||||
['long', 'double', null, null, 'double'],
|
||||
['long', 'integer', 'double', 'double', 'double'],
|
||||
['long', 'integer', 'double', 'integer', 'double'],
|
||||
['long', 'integer', 'double', 'long', 'double'],
|
||||
['long', 'integer', 'integer', 'double', 'double'],
|
||||
['long', 'integer', 'integer', 'integer', 'double'],
|
||||
['long', 'integer', 'integer', 'long', 'double'],
|
||||
['long', 'integer', 'long', 'double', 'double'],
|
||||
['long', 'integer', 'long', 'integer', 'double'],
|
||||
['long', 'integer', 'long', 'long', 'double'],
|
||||
];
|
||||
export const groupingFunctionDefinitions: FunctionDefinition[] = [
|
||||
{
|
||||
name: 'bucket',
|
||||
alias: ['bin'],
|
||||
description: i18n.translate('kbn-esql-validation-autocomplete.esql.definitions.autoBucketDoc', {
|
||||
defaultMessage: `Automatically bucket dates based on a given range and bucket target.`,
|
||||
}),
|
||||
// type agg because it can also be used as an aggregation...
|
||||
type: 'agg',
|
||||
supportedCommands: ['stats'],
|
||||
supportedOptions: ['by'],
|
||||
signatures: [
|
||||
...groupingTypeTable.map((signature) => {
|
||||
const [fieldType, bucketType, fromType, toType, resultType] = signature;
|
||||
return {
|
||||
params: [
|
||||
{ name: 'field', type: fieldType },
|
||||
{ name: 'buckets', type: bucketType, constantOnly: true },
|
||||
...(fromType ? [{ name: 'startDate', type: fromType, constantOnly: true }] : []),
|
||||
...(toType ? [{ name: 'endDate', type: toType, constantOnly: true }] : []),
|
||||
],
|
||||
returnType: resultType,
|
||||
};
|
||||
}),
|
||||
],
|
||||
examples: [
|
||||
'from index | eval hd = bucket(bytes, 1 hour)',
|
||||
'from index | eval hd = bucket(hire_date, 1 hour)',
|
||||
'from index | eval hd = bucket(hire_date, 20, "1985-01-01T00:00:00Z", "1986-01-01T00:00:00Z")',
|
||||
'from index | eval hd = bucket(hire_date, 20, "1985-01-01T00:00:00Z", "1986-01-01T00:00:00Z")',
|
||||
'from index | eval bs = bucket(bytes, 20, 25324, 74999)',
|
||||
],
|
||||
},
|
||||
{
|
||||
name: 'categorize',
|
||||
alias: ['bin'],
|
||||
description: i18n.translate('kbn-esql-validation-autocomplete.esql.definitions.categorize', {
|
||||
defaultMessage: `Groups text messages into categories of similarly formatted text values.`,
|
||||
}),
|
||||
type: 'agg',
|
||||
supportedCommands: ['stats'],
|
||||
supportedOptions: ['by'],
|
||||
signatures: [
|
||||
{
|
||||
params: [
|
||||
{
|
||||
name: 'field',
|
||||
type: 'keyword',
|
||||
optional: false,
|
||||
},
|
||||
],
|
||||
returnType: 'keyword',
|
||||
},
|
||||
{
|
||||
params: [
|
||||
{
|
||||
name: 'field',
|
||||
type: 'text',
|
||||
optional: false,
|
||||
},
|
||||
],
|
||||
returnType: 'keyword',
|
||||
},
|
||||
],
|
||||
examples: ['FROM sample_data\n| STATS count=COUNT() BY category=CATEGORIZE(message)'],
|
||||
},
|
||||
];
|
||||
|
|
@ -170,7 +170,7 @@ export interface Signature {
|
|||
}
|
||||
|
||||
export interface FunctionDefinition {
|
||||
type: 'builtin' | 'agg' | 'scalar' | 'operator';
|
||||
type: 'builtin' | 'agg' | 'scalar' | 'operator' | 'grouping';
|
||||
preview?: boolean;
|
||||
ignoreAsSuggestion?: boolean;
|
||||
name: string;
|
||||
|
|
|
|||
|
|
@ -29,7 +29,7 @@ import { aggregationFunctionDefinitions } from '../definitions/generated/aggrega
|
|||
import { builtinFunctions } from '../definitions/builtin';
|
||||
import { commandDefinitions } from '../definitions/commands';
|
||||
import { scalarFunctionDefinitions } from '../definitions/generated/scalar_functions';
|
||||
import { groupingFunctionDefinitions } from '../definitions/grouping';
|
||||
import { groupingFunctionDefinitions } from '../definitions/generated/grouping_functions';
|
||||
import { getTestFunctions } from './test_functions';
|
||||
import { getFunctionSignatures } from '../definitions/helpers';
|
||||
import { timeUnits } from '../definitions/literals';
|
||||
|
|
|
|||
File diff suppressed because one or more lines are too long
File diff suppressed because one or more lines are too long
|
|
@ -5277,7 +5277,6 @@
|
|||
"kbn-esql-validation-autocomplete.esql.definitions.asin": "返回输入数字表达式的反正弦作为角度，以弧度表示。",
|
||||
"kbn-esql-validation-autocomplete.esql.definitions.atan": "返回输入数字表达式的反正切作为角度，以弧度表示。",
|
||||
"kbn-esql-validation-autocomplete.esql.definitions.atan2": "笛卡儿平面中正 x 轴与从原点到点 (x , y) 构成的射线之间的角度，以弧度表示。",
|
||||
"kbn-esql-validation-autocomplete.esql.definitions.autoBucketDoc": "根据给定范围和存储桶目标自动收集存储桶日期。",
|
||||
"kbn-esql-validation-autocomplete.esql.definitions.avg": "数字字段的平均值。",
|
||||
"kbn-esql-validation-autocomplete.esql.definitions.byDoc": "依据",
|
||||
"kbn-esql-validation-autocomplete.esql.definitions.case": "接受成对的条件和值。此函数返回属于第一个评估为 `true` 的条件的值。如果参数数量为奇数，则最后一个参数为在无条件匹配时返回的默认值。",
|
||||
|
|
@ -5533,8 +5532,6 @@
|
|||
"languageDocumentation.documentationESQL.atan.markdown": "<!-- This is generated by ESQL's AbstractFunctionTestCase. Do no edit it. See ../README.md for how to regenerate it. --> ### ATAN 以角度形式返回输入数字表达式的反正切，以弧度表示。``` ROW a=12.9 | EVAL atan=ATAN(a) ```",
|
||||
"languageDocumentation.documentationESQL.atan2": "ATAN2",
|
||||
"languageDocumentation.documentationESQL.atan2.markdown": "<!-- This is generated by ESQL's AbstractFunctionTestCase. Do no edit it. See ../README.md for how to regenerate it. --> ### ATAN2 笛卡儿平面中正 x 轴与从原点到点 (x , y) 构成的射线之间的角度，以弧度表示。``` ROW y=12.9, x=.6 | EVAL atan2=ATAN2(y, x) ```",
|
||||
"languageDocumentation.documentationESQL.autoBucketFunction": "BUCKET",
|
||||
"languageDocumentation.documentationESQL.autoBucketFunction.markdown": "### BUCKET 用日期时间或数字输入创建值（存储桶）的分组。存储桶的大小可以直接提供，或基于建议的计数和值范围进行选择。`BUCKET` 以两种模式运行：1.在此模式下基于存储桶计数建议（四个参数）和范围计算存储桶的大小。2.在此模式下直接提供存储桶大小（两个参数）。使用存储桶的目标数量、起始范围和结束范围，`BUCKET` 将选取适当的存储桶大小以生成目标数量或更小数量的存储桶。例如，一年请求多达 20 个存储桶会按每月时间间隔组织数据：``` FROM employees | WHERE hire_date >= \"1985-01-01T00:00:00Z\" AND hire_date < \"1986-01-01T00:00:00Z\" | STATS hire_date = MV_SORT(VALUES(hire_date)) BY month = BUCKET(hire_date, 20, \"1985-01-01T00:00:00Z\", \"1986-01-01T00:00:00Z\") | SORT hire_date ``` **注意**：目标并不是提供存储桶的确切目标数量，而是选择一个范围，最多提供存储桶的目标数量。可以组合 `BUCKET` 与聚合以创建直方图：``` FROM employees | WHERE hire_date >= \"1985-01-01T00:00:00Z\" AND hire_date < \"1986-01-01T00:00:00Z\" | STATS hires_per_month = COUNT(*) BY month = BUCKET(hire_date, 20, \"1985-01-01T00:00:00Z\", \"1986-01-01T00:00:00Z\") | SORT month ``` **注意**：`BUCKET` 不会创建未匹配任何文档的存储桶。因此，上一示例缺少 `1985-03-01` 和其他日期。如果需要更多存储桶，可能导致更小的范围。例如，如果一年内最多请求 100 个存储桶，则会生成周期为周的存储桶：``` FROM employees | WHERE hire_date >= \"1985-01-01T00:00:00Z\" AND hire_date < \"1986-01-01T00:00:00Z\" | STATS hires_per_week = COUNT(*) BY week = BUCKET(hire_date, 100, \"1985-01-01T00:00:00Z\", \"1986-01-01T00:00:00Z\") | SORT week ``` **注意**：`BUCKET` 不筛选任何行。它只会使用提供的范围来选取适当的存储桶大小。对于值超出范围的行，它会返回与超出范围的存储桶对应的存储桶值。组合 `BUCKET` 与 `WHERE` 可筛选行。如果提前已知所需存储桶大小，则只需提供它作为第二个参数，而忽略范围：``` FROM employees | WHERE hire_date >= \"1985-01-01T00:00:00Z\" AND hire_date < \"1986-01-01T00:00:00Z\" | STATS hires_per_week = COUNT(*) BY week = BUCKET(hire_date, 1 week) | SORT week ``` **注意**：提供存储桶大小作为第二个参数时，它必须为持续时间或日期期间。`BUCKET` 还可对数字字段执行操作。例如，要创建工资直方图：``` FROM employees | STATS COUNT(*) by bs = BUCKET(salary, 20, 25324, 74999) | SORT bs ```与前面有意筛选日期范围的示例不同，您极少想要筛选数值范围。您必须分别查找最小值和最大值。ES|QL 尚未提供简便方法来自动执行此操作。如果提前已知所需存储桶大小，则可以忽略该范围。只需提供它作为第二个参数即可：``` FROM employees | WHERE hire_date >= \"1985-01-01T00:00:00Z\" AND hire_date < \"1986-01-01T00:00:00Z\" | STATS c = COUNT(1) BY b = BUCKET(salary, 5000.) | SORT b ``` **注意**：提供存储桶大小作为第二个参数时，它必须为 **浮点类型**。这里提供了一个示例，用于为过去 24 小时创建小时存储桶，并计算每小时的事件数：``` FROM sample_data | WHERE @timestamp >= NOW() - 1 day and @timestamp < NOW() | STATS COUNT(*) BY bucket = BUCKET(@timestamp, 25, NOW() - 1 day, NOW()) ```这里提供了一个示例，用于为 1985 年创建月度存储桶，并按聘用月份计算平均工资：``` FROM employees | WHERE hire_date >= \"1985-01-01T00:00:00Z\" AND hire_date < \"1986-01-01T00:00:00Z\" | STATS AVG(salary) BY bucket = BUCKET(hire_date, 20, \"1985-01-01T00:00:00Z\", \"1986-01-01T00:00:00Z\") | SORT bucket ``` `BUCKET` 可用在 `STATS … BY …` 命令的聚合和分组部分， 前提是在聚合部分中，该函数 **由在分组部分中定义的别名引用**，或使用完全相同的表达式调用。例如：``` FROM employees | STATS s1 = b1 + 1, s2 = BUCKET(salary / 1000 + 999, 50.) + 2 BY b1 = BUCKET(salary / 100 + 99, 50.), b2 = BUCKET(salary / 1000 + 999, 50.) | SORT b1, b2 | KEEP s1, b1, s2, b2 ```",
|
||||
"languageDocumentation.documentationESQL.avg": "AVG",
|
||||
"languageDocumentation.documentationESQL.avg.markdown": "<!-- This is generated by ESQL's AbstractFunctionTestCase. Do no edit it. See ../README.md for how to regenerate it. --> ### AVG 数字字段的平均值。``` FROM employees | STATS AVG(height) ```",
|
||||
"languageDocumentation.documentationESQL.binaryOperators": "二进制运算符",
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue