[ML] Adds query history and improves performance for ES|QL Data visualizer (#179098)

## Summary

This PR adds query history (see
https://github.com/elastic/kibana/issues/179672) and improves
performance for ES|QL Data visualizer

![Screenshot 2024-04-15 at 11 53
27](eed6cc9b-c7be-4bfd-bc2c-b0241d8f34ac)



It:
- Adds drop_null_column=true to reduce making aggregations on empty
fields
- Adds better support for geo point/geo shape maps where time field is
not defined in the data view, but '@timestamp' does exist
- Adds a new Top sampled values to match with the unified field list
popover in Discover
- Removes ES|QL link from search bar if not enabled
![Screenshot 2024-04-15 at 11 57
29](23df6ac0-f584-4491-a57e-59812b195b45)
- Closes https://github.com/elastic/kibana/issues/180072

[Flaky test suite
runner](https://buildkite.com/elastic/kibana-flaky-test-suite-runner/builds/5699#018ee80e-3ebf-4d9b-ab79-c8013f3f4c1d)...
25/25 successful runs 

### Checklist

Delete any items that are not applicable to this PR.

- [ ] Any text added follows [EUI's writing
guidelines](https://elastic.github.io/eui/#/guidelines/writing), uses
sentence case text and includes [i18n
support](https://github.com/elastic/kibana/blob/main/packages/kbn-i18n/README.md)
- [ ]
[Documentation](https://www.elastic.co/guide/en/kibana/master/development-documentation.html)
was added for features that require explanation or tutorials
- [x] [Unit or functional
tests](https://www.elastic.co/guide/en/kibana/master/development-tests.html)
were updated or added to match the most common scenarios
- [ ] [Flaky Test
Runner](https://ci-stats.kibana.dev/trigger_flaky_test_runner/1) was
used on any tests changed
- [ ] Any UI touched in this PR is usable by keyboard only (learn more
about [keyboard accessibility](https://webaim.org/techniques/keyboard/))
- [ ] Any UI touched in this PR does not create any new axe failures
(run axe in browser:
[FF](https://addons.mozilla.org/en-US/firefox/addon/axe-devtools/),
[Chrome](https://chrome.google.com/webstore/detail/axe-web-accessibility-tes/lhdoppojpmngadmnindnejefpokejbdd?hl=en-US))
- [ ] If a plugin configuration key changed, check if it needs to be
allowlisted in the cloud and added to the [docker
list](https://github.com/elastic/kibana/blob/main/src/dev/build/tasks/os_packages/docker_generator/resources/base/bin/kibana-docker)
- [ ] This renders correctly on smaller devices using a responsive
layout. (You can test this [in your
browser](https://www.browserstack.com/guide/responsive-testing-on-local-server))
- [ ] This was checked for [cross-browser
compatibility](https://www.elastic.co/support/matrix#matrix_browsers)


### Risk Matrix

Delete this section if it is not applicable to this PR.

Before closing this PR, invite QA, stakeholders, and other developers to
identify risks that should be tested prior to the change/feature
release.

When forming the risk matrix, consider some of the following examples
and how they may potentially impact the change:

| Risk | Probability | Severity | Mitigation/Notes |

|---------------------------|-------------|----------|-------------------------|
| Multiple Spaces—unexpected behavior in non-default Kibana Space.
| Low | High | Integration tests will verify that all features are still
supported in non-default Kibana Space and when user switches between
spaces. |
| Multiple nodes—Elasticsearch polling might have race conditions
when multiple Kibana nodes are polling for the same tasks. | High | Low
| Tasks are idempotent, so executing them multiple times will not result
in logical error, but will degrade performance. To test for this case we
add plenty of unit tests around this logic and document manual testing
procedure. |
| Code should gracefully handle cases when feature X or plugin Y are
disabled. | Medium | High | Unit tests will verify that any feature flag
or plugin combination still results in our service operational. |
| [See more potential risk
examples](https://github.com/elastic/kibana/blob/main/RISK_MATRIX.mdx) |


### For maintainers

- [ ] This was checked for breaking API changes and was [labeled
appropriately](https://www.elastic.co/guide/en/kibana/master/contributing.html#kibana-release-notes-process)

---------

Co-authored-by: Stratoula Kalafateli <efstratia.kalafateli@elastic.co>
Co-authored-by: kibanamachine <42973632+kibanamachine@users.noreply.github.com>
This commit is contained in:
Quynh Nguyen (Quinn) 2024-04-16 14:04:38 -05:00 committed by GitHub
parent 20af76f331
commit 4546d274e8
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
24 changed files with 355 additions and 263 deletions

View file

@ -62,9 +62,16 @@ export interface FieldVisStats {
};
fieldName?: string;
isTopValuesSampled?: boolean;
topValuesSampleSize?: number;
max?: number;
median?: number;
min?: number;
sampledValues?: Array<{
key: number | string;
doc_count: number;
percent: number;
key_as_string?: string;
}>;
topValues?: Array<{
key: number | string;
doc_count: number;

View file

@ -93,6 +93,7 @@ export interface StringFieldStats {
fieldName: string;
isTopValuesSampled: boolean;
topValues: Bucket[];
sampledValues?: Bucket[];
topValuesSampleSize?: number;
topValuesSamplerShardSize?: number;
}

View file

@ -23,7 +23,8 @@ export const GeoPointContentWithMap: FC<{
dataView: DataView | undefined;
combinedQuery?: CombinedQuery;
esql?: string;
}> = ({ config, dataView, combinedQuery, esql }) => {
timeFieldName?: string;
}> = ({ config, dataView, combinedQuery, esql, timeFieldName }) => {
const { stats } = config;
const [layerList, setLayerList] = useState<LayerDescriptor[]>([]);
const {
@ -72,7 +73,7 @@ export const GeoPointContentWithMap: FC<{
},
],
dataViewId: dataView.id,
dateField: dataView.timeFieldName,
dateField: dataView.timeFieldName ?? timeFieldName,
geoField: config.fieldName,
esql,
narrowByGlobalSearch: true,

View file

@ -32,6 +32,7 @@ export const IndexBasedDataVisualizerExpandedRow = ({
onAddFilter,
esql,
totalDocuments,
timeFieldName,
typeAccessor = 'type',
}: {
item: FieldVisConfig;
@ -44,6 +45,7 @@ export const IndexBasedDataVisualizerExpandedRow = ({
* Callback to add a filter to filter bar
*/
onAddFilter?: (field: DataViewField | string, value: string, type: '+' | '-') => void;
timeFieldName?: string;
}) => {
const config = { ...item, stats: { ...item.stats, totalDocuments } };
const { loading, existsInDocs, fieldName } = config;
@ -77,6 +79,7 @@ export const IndexBasedDataVisualizerExpandedRow = ({
dataView={dataView}
combinedQuery={combinedQuery}
esql={esql}
timeFieldName={timeFieldName}
/>
);

View file

@ -55,6 +55,16 @@ export const KeywordContent: FC<FieldDataRowProps> = ({ config, onAddFilter }) =
barColor="success"
onAddFilter={onAddFilter}
/>
{config.stats?.sampledValues && fieldName !== undefined ? (
<TopValues
stats={stats}
fieldFormat={fieldFormat}
barColor="success"
onAddFilter={onAddFilter}
showSampledValues={true}
/>
) : null}
{EMSSuggestion && stats && <ChoroplethMap stats={stats} suggestion={EMSSuggestion} />}
</ExpandedRowContent>
);

View file

@ -37,6 +37,7 @@ interface Props {
barColor?: 'primary' | 'success' | 'danger' | 'subdued' | 'accent';
compressed?: boolean;
onAddFilter?: (field: DataViewField | string, value: string, type: '+' | '-') => void;
showSampledValues?: boolean;
}
function getPercentLabel(percent: number): string {
@ -47,7 +48,20 @@ function getPercentLabel(percent: number): string {
}
}
export const TopValues: FC<Props> = ({ stats, fieldFormat, barColor, compressed, onAddFilter }) => {
export const TopValues: FC<Props> = ({
stats,
fieldFormat,
barColor,
compressed,
onAddFilter,
/** Top values by default show % of time a value exist in sampled records/rows (i.e. value A exists in 10% of sampled records)
* showSampledValues: true shows % of times a value exist in all arrays of values that have been flattened
* Example for 4 records: ["a", "a", "b"], ["b", "b", "c"], "d", "e"
* "a" exists in 1/4 records (50% - showSampledValues: false),
* "a" exists in 2/8 sampled values (25% - showSampledValues: true).
*/
showSampledValues = false,
}) => {
const {
services: {
data: { fieldFormats },
@ -55,10 +69,71 @@ export const TopValues: FC<Props> = ({ stats, fieldFormat, barColor, compressed,
} = useDataVisualizerKibana();
if (stats === undefined || !stats.topValues) return null;
const { topValues: originalTopValues, fieldName, sampleCount } = stats;
const { fieldName, sampleCount } = stats;
const originalTopValues = (showSampledValues ? stats.sampledValues : stats.topValues) ?? [];
if (originalTopValues?.length === 0) return null;
const totalDocuments = Math.min(sampleCount ?? 0, stats.totalDocuments ?? 0);
const totalDocuments = showSampledValues
? stats.topValuesSampleSize ?? 0
: Math.min(sampleCount ?? 0, stats.totalDocuments ?? 0);
const getMessage = () => {
if (showSampledValues && stats.topValuesSampleSize !== undefined) {
return (
<FormattedMessage
id="xpack.dataVisualizer.dataGrid.field.topValues.calculatedFromSampleValuesLabel"
defaultMessage="Calculated from {sampledDocumentsFormatted} sample {sampledDocuments, plural, one {value} other {values}}."
values={{
sampledDocuments: stats.topValuesSampleSize,
sampledDocumentsFormatted: (
<strong>
{fieldFormats
.getDefaultInstance(KBN_FIELD_TYPES.NUMBER, [ES_FIELD_TYPES.INTEGER])
.convert(stats.topValuesSampleSize)}
</strong>
),
}}
/>
);
}
return totalDocuments > (sampleCount ?? 0) ? (
<FormattedMessage
id="xpack.dataVisualizer.dataGrid.field.topValues.calculatedFromSampleRecordsLabel"
defaultMessage="Calculated from {sampledDocumentsFormatted} sample {sampledDocuments, plural, one {record} other {records}}."
values={{
sampledDocuments: sampleCount,
sampledDocumentsFormatted: (
<strong>
{fieldFormats
.getDefaultInstance(KBN_FIELD_TYPES.NUMBER, [ES_FIELD_TYPES.INTEGER])
.convert(sampleCount)}
</strong>
),
}}
/>
) : (
<FormattedMessage
id="xpack.dataVisualizer.dataGrid.field.topValues.calculatedFromTotalRecordsLabel"
defaultMessage="Calculated from {totalDocumentsFormatted} {totalDocuments, plural, one {record} other {records}}."
values={{
totalDocuments,
totalDocumentsFormatted: (
<strong>
{fieldFormats
.getDefaultInstance(KBN_FIELD_TYPES.NUMBER, [ES_FIELD_TYPES.INTEGER])
.convert(totalDocuments ?? 0)}
</strong>
),
}}
/>
);
};
const countsElement = (
<EuiText color="subdued" size="xs">
{getMessage()}
</EuiText>
);
const topValues = originalTopValues.map((bucket) => ({
...bucket,
@ -70,52 +145,23 @@ export const TopValues: FC<Props> = ({ stats, fieldFormat, barColor, compressed,
1 - (topValues ? topValues.reduce((acc, bucket) => acc + bucket.percent, 0) : 0);
const topValuesOtherCount = Math.floor(topValuesOtherCountPercent * (sampleCount ?? 0));
const countsElement = (
<EuiText color="subdued" size="xs">
{totalDocuments > (sampleCount ?? 0) ? (
<FormattedMessage
id="xpack.dataVisualizer.dataGrid.field.topValues.calculatedFromSampleRecordsLabel"
defaultMessage="Calculated from {sampledDocumentsFormatted} sample {sampledDocuments, plural, one {record} other {records}}."
values={{
sampledDocuments: sampleCount,
sampledDocumentsFormatted: (
<strong>
{fieldFormats
.getDefaultInstance(KBN_FIELD_TYPES.NUMBER, [ES_FIELD_TYPES.INTEGER])
.convert(sampleCount)}
</strong>
),
}}
/>
) : (
<FormattedMessage
id="xpack.dataVisualizer.dataGrid.field.topValues.calculatedFromTotalRecordsLabel"
defaultMessage="Calculated from {totalDocumentsFormatted} {totalDocuments, plural, one {record} other {records}}."
values={{
totalDocuments,
totalDocumentsFormatted: (
<strong>
{fieldFormats
.getDefaultInstance(KBN_FIELD_TYPES.NUMBER, [ES_FIELD_TYPES.INTEGER])
.convert(totalDocuments ?? 0)}
</strong>
),
}}
/>
)}
</EuiText>
);
return (
<ExpandedRowPanel
dataTestSubj={'dataVisualizerFieldDataTopValues'}
className={classNames('dvPanel__wrapper', compressed ? 'dvPanel--compressed' : undefined)}
>
<ExpandedRowFieldHeader>
<FormattedMessage
id="xpack.dataVisualizer.dataGrid.field.topValuesLabel"
defaultMessage="Top values"
/>
{showSampledValues ? (
<FormattedMessage
id="xpack.dataVisualizer.dataGrid.field.topSampledValuesLabel"
defaultMessage="Top sampled values"
/>
) : (
<FormattedMessage
id="xpack.dataVisualizer.dataGrid.field.topValuesLabel"
defaultMessage="Top values"
/>
)}
</ExpandedRowFieldHeader>
<div

View file

@ -161,6 +161,7 @@ export const IndexDataVisualizerESQL: FC<IndexDataVisualizerESQLProps> = (dataVi
const {
totalCount,
progress: combinedProgress,
queryHistoryStatus,
overallStatsProgress,
configs,
documentCountStats,
@ -256,7 +257,7 @@ export const IndexDataVisualizerESQL: FC<IndexDataVisualizerESQLProps> = (dataVi
detectTimestamp={true}
hideMinimizeButton={true}
hideRunQueryText={false}
hideQueryHistory
isLoading={queryHistoryStatus ?? false}
/>
<EuiFlexGroup gutterSize="m" direction={isWithinLargeBreakpoint ? 'column' : 'row'}>

View file

@ -270,10 +270,13 @@ export const useESQLDataVisualizerData = (
documentCountStats,
totalCount,
overallStats,
totalFields,
overallStatsProgress,
columns,
cancelOverallStatsRequest,
timeFieldName,
queryHistoryStatus,
exampleDocs,
} = useESQLOverallStatsData(fieldStatsRequest);
const [metricConfigs, setMetricConfigs] = useState(defaults.metricConfigs);
@ -497,13 +500,7 @@ export const useESQLDataVisualizerData = (
if (!overallStats) return;
let _visibleFieldsCount = 0;
let _totalFieldsCount = 0;
Object.keys(overallStats).forEach((key) => {
const fieldsGroup = overallStats[key as keyof typeof overallStats];
if (Array.isArray(fieldsGroup) && fieldsGroup.length > 0) {
_totalFieldsCount += fieldsGroup.length;
}
});
const _totalFieldsCount = totalFields ?? 0;
if (showEmptyFields === true) {
_visibleFieldsCount = _totalFieldsCount;
@ -513,7 +510,7 @@ export const useESQLDataVisualizerData = (
overallStats.nonAggregatableExistsFields.length;
}
return { visibleFieldsCount: _visibleFieldsCount, totalFieldsCount: _totalFieldsCount };
}, [overallStats, showEmptyFields]);
}, [overallStats, showEmptyFields, totalFields]);
useEffect(
() => {
@ -533,9 +530,14 @@ export const useESQLDataVisualizerData = (
visibleFieldTypes
).filteredFields;
const examples = exampleDocs?.reduce((map, exampleDoc) => {
map.set(exampleDoc.fieldName, exampleDoc);
return map;
}, new Map());
if (fieldStatsProgress.loaded === 100 && fieldStats) {
combinedConfigs = combinedConfigs.map((c) => {
const loadedFullStats = fieldStats.get(c.fieldName) ?? {};
const loadedFullStats = fieldStats.get(c.fieldName) ?? examples?.get(c.fieldName) ?? {};
return loadedFullStats
? {
...c,
@ -555,6 +557,7 @@ export const useESQLDataVisualizerData = (
fieldStatsProgress.loaded,
dataVisualizerListState.pageIndex,
dataVisualizerListState.pageSize,
exampleDocs,
]
);
@ -570,13 +573,14 @@ export const useESQLDataVisualizerData = (
esql={query.esql}
totalDocuments={totalCount}
typeAccessor="secondaryType"
timeFieldName={timeFieldName}
/>
);
}
return map;
}, {} as ItemIdToExpandedRowMap);
},
[currentDataView, totalCount, query.esql]
[currentDataView, totalCount, query.esql, timeFieldName]
);
const combinedProgress = useMemo(
@ -626,5 +630,6 @@ export const useESQLDataVisualizerData = (
showEmptyFields,
fieldsCountStats,
timeFieldName,
queryHistoryStatus,
};
};

View file

@ -21,7 +21,6 @@ import { getESQLNumericFieldStats } from '../../search_strategy/esql_requests/ge
import { getESQLKeywordFieldStats } from '../../search_strategy/esql_requests/get_keyword_fields';
import { getESQLDateFieldStats } from '../../search_strategy/esql_requests/get_date_field_stats';
import { getESQLBooleanFieldStats } from '../../search_strategy/esql_requests/get_boolean_field_stats';
import { getESQLExampleFieldValues } from '../../search_strategy/esql_requests/get_text_field_stats';
export const useESQLFieldStatsData = <T extends Column>({
searchQuery,
@ -114,19 +113,6 @@ export const useESQLFieldStatsData = <T extends Column>({
esqlBaseQuery,
}).then(addToProcessedFieldStats);
// GETTING STATS FOR TEXT FIELDS
await getESQLExampleFieldValues({
columns: columns.filter(
(f) =>
f.secondaryType === 'text' ||
f.secondaryType === 'geo_point' ||
f.secondaryType === 'geo_shape'
),
filter,
runRequest,
esqlBaseQuery,
}).then(addToProcessedFieldStats);
// GETTING STATS FOR DATE FIELDS
await getESQLDateFieldStats({
columns: columns.filter((f) => f.secondaryType === 'date'),

View file

@ -9,12 +9,13 @@ import { ESQL_SEARCH_STRATEGY, KBN_FIELD_TYPES } from '@kbn/data-plugin/common';
import type { QueryDslQueryContainer } from '@kbn/data-views-plugin/common/types';
import type { AggregateQuery } from '@kbn/es-query';
import { i18n } from '@kbn/i18n';
import { useCallback, useEffect, useMemo, useReducer, useRef } from 'react';
import { useCallback, useEffect, useMemo, useReducer, useRef, useState } from 'react';
import { type UseCancellableSearch, useCancellableSearch } from '@kbn/ml-cancellable-search';
import type { estypes } from '@elastic/elasticsearch';
import type { ISearchOptions } from '@kbn/data-plugin/common';
import type { TimeBucketsInterval } from '@kbn/ml-time-buckets';
import { getESQLWithSafeLimit, ESQL_LATEST_VERSION } from '@kbn/esql-utils';
import { isDefined } from '@kbn/ml-is-defined';
import { OMIT_FIELDS } from '../../../../../common/constants';
import type {
DataStatsFetchProgress,
@ -25,7 +26,6 @@ import { useDataVisualizerKibana } from '../../../kibana_context';
import { getInitialProgress, getReducer } from '../../progress_utils';
import { getSafeESQLName, isESQLQuery } from '../../search_strategy/requests/esql_utils';
import type { NonAggregatableField } from '../../types/overall_stats';
import { getESQLSupportedAggs } from '../../utils/get_supported_aggs';
import { getESQLOverallStats } from '../../search_strategy/esql_requests/get_count_and_cardinality';
import type { AggregatableField } from '../../types/esql_data_visualizer';
import {
@ -33,13 +33,19 @@ import {
type HandleErrorCallback,
} from '../../search_strategy/esql_requests/handle_error';
export interface Column {
interface ESQLColumn {
type: string;
name: string;
}
interface ESQLResponse {
rawResponse: { columns: ESQLColumn[]; all_columns: ESQLColumn[]; values: unknown[][] };
}
export interface Column extends ESQLColumn {
secondaryType: string;
}
interface Data {
totalFields?: number;
timeFieldName?: string;
columns?: Column[];
totalCount?: number;
@ -52,6 +58,7 @@ interface Data {
nonAggregatableExistsFields: NonAggregatableField[];
nonAggregatableNotExistsFields: NonAggregatableField[];
};
exampleDocs: Array<{ fieldName: string; examples: string[] }> | undefined;
}
const getESQLDocumentCountStats = async (
@ -158,6 +165,8 @@ export const getInitialData = (): Data => ({
timeFieldName: undefined,
columns: undefined,
totalCount: undefined,
exampleDocs: undefined,
totalFields: undefined,
});
const NON_AGGREGATABLE_FIELD_TYPES = new Set<string>([
@ -201,6 +210,7 @@ export const useESQLOverallStatsData = (
const { runRequest, cancelRequest } = useCancellableSearch(data);
const [tableData, setTableData] = useReducer(getReducer<Data>(), getInitialData());
const [queryHistoryStatus, setQueryHistoryStatus] = useState<boolean | undefined>(false);
const [overallStatsProgress, setOverallStatsProgress] = useReducer(
getReducer<DataStatsFetchProgress>(),
getInitialProgress()
@ -244,24 +254,37 @@ export const useESQLOverallStatsData = (
// For doc count chart, we want the full base query without any limit
const esqlBaseQuery = searchQuery.esql;
const columnsResp = await runRequest(
setQueryHistoryStatus(true);
// Note: dropNullColumns will return empty [] for all_columns if limit size is 0
// So we are making a query with default limit
// And use this one query to
// 1) identify populated/empty fields
// 2) gather examples for populated text fields
const columnsResp = (await runRequest(
{
params: {
query: esqlBaseQuery + '| LIMIT 0',
// Doing this to match with the default limit
query: esqlBaseQuery,
...(filter ? { filter } : {}),
version: ESQL_LATEST_VERSION,
dropNullColumns: true,
},
},
{ strategy: ESQL_SEARCH_STRATEGY }
);
const columns = columnsResp?.rawResponse
? // @ts-expect-error ES types need to be updated with columns for ESQL queries
(columnsResp.rawResponse.columns.map((c) => ({
...c,
secondaryType: getSupportedFieldType(c.type),
})) as Column[])
)) as ESQLResponse | undefined;
setQueryHistoryStatus(false);
const columnInfo = columnsResp?.rawResponse
? columnsResp.rawResponse.all_columns ?? columnsResp.rawResponse.columns
: [];
const populatedColumns = new Set(columnsResp?.rawResponse.columns.map((c) => c.name));
const columns = columnInfo.map((c) => ({
...c,
secondaryType: getSupportedFieldType(c.type),
})) as Column[];
const timeFields = columns.filter((d) => d.type === 'date');
const dataViewTimeField = timeFields.find(
@ -324,20 +347,10 @@ export const useESQLOverallStatsData = (
setOverallStatsProgress({
loaded: 50,
});
const aggregatableFields: Array<{
fieldName: string;
name: string;
type: string;
supportedAggs: Set<string>;
secondaryType: string;
aggregatable: boolean;
}> = [];
const nonAggregatableFields: Array<{
fieldName: string;
name: string;
type: string;
secondaryType: string;
}> = [];
const aggregatableNotExistsFields: AggregatableField[] = [];
const nonAggregatableNotExistsFields: NonAggregatableField[] = [];
const fields = columns
// Some field types are not supported by ESQL yet
// Also, temporarily removing null columns because it causes problems with some aggs
@ -346,30 +359,33 @@ export const useESQLOverallStatsData = (
.map((field) => {
return { ...field, aggregatable: !NON_AGGREGATABLE_FIELD_TYPES.has(field.type) };
});
const populatedFields = fields.filter((field) => populatedColumns.has(field.name));
fields?.forEach((field) => {
const fieldName = field.name;
if (!OMIT_FIELDS.includes(fieldName)) {
if (!field.aggregatable) {
nonAggregatableFields.push({
...field,
fieldName: field.name,
secondaryType: getSupportedFieldType(field.type),
});
if (!populatedColumns.has(fieldName)) {
nonAggregatableNotExistsFields.push({
...field,
fieldName: field.name,
secondaryType: getSupportedFieldType(field.type),
existsInDocs: false,
});
}
} else {
aggregatableFields.push({
...field,
fieldName: field.name,
secondaryType: getSupportedFieldType(field.type),
supportedAggs: getESQLSupportedAggs(field, true),
aggregatable: true,
});
if (!populatedColumns.has(fieldName)) {
aggregatableNotExistsFields.push({
...field,
fieldName: field.name,
aggregatable: true,
existsInDocs: false,
});
}
}
}
});
setTableData({ aggregatableFields, nonAggregatableFields });
// COUNT + CARDINALITY
// For % count & cardinality, we want the full base query WITH specified limit
// to safeguard against huge datasets
@ -394,20 +410,40 @@ export const useESQLOverallStatsData = (
if (totalCount > 0 && fields.length > 0) {
const stats = await getESQLOverallStats({
runRequest,
fields,
// Only need to fetch stats for fields we know are populated
fields: populatedFields,
esqlBaseQueryWithLimit,
filter,
limitSize: limit,
totalCount,
onError,
});
if (!stats) return;
stats.aggregatableNotExistsFields = aggregatableNotExistsFields;
stats.nonAggregatableNotExistsFields = nonAggregatableNotExistsFields;
setTableData({ overallStats: stats });
setTableData({ overallStats: stats, totalFields: columns.length });
setOverallStatsProgress({
loaded: 100,
isRunning: false,
error: undefined,
});
const columnsWithExamples = columnInfo.reduce((hashmap, curr, idx) => {
if (curr.type === 'text' || curr.type === 'geo_point' || curr.type === 'geo_shape') {
hashmap[curr.name] = idx;
}
return hashmap;
}, {} as Record<string, number>);
const exampleDocs = Object.entries(columnsWithExamples).map(([fieldName, idx]) => {
const examples = [...new Set(columnsResp?.rawResponse?.values.map((row) => row[idx]))]
.filter(isDefined)
.slice(0, 10);
return { fieldName, examples: examples as string[] };
});
setTableData({ exampleDocs });
}
} catch (error) {
// If error already handled in sub functions, no need to propogate
@ -415,10 +451,10 @@ export const useESQLOverallStatsData = (
toasts.addError(error, {
title: fieldStatsErrorTitle,
});
// Log error to console for better debugging
// eslint-disable-next-line no-console
console.error(`${fieldStatsErrorTitle}: fetchOverallStats`, error);
}
// Log error to console for better debugging
// eslint-disable-next-line no-console
console.error(`${fieldStatsErrorTitle}: fetchOverallStats`, error);
}
},
// eslint-disable-next-line react-hooks/exhaustive-deps
@ -431,7 +467,12 @@ export const useESQLOverallStatsData = (
}, [startFetch]);
return useMemo(
() => ({ ...tableData, overallStatsProgress, cancelOverallStatsRequest: cancelRequest }),
[tableData, overallStatsProgress, cancelRequest]
() => ({
...tableData,
overallStatsProgress,
cancelOverallStatsRequest: cancelRequest,
queryHistoryStatus,
}),
[tableData, overallStatsProgress, cancelRequest, queryHistoryStatus]
);
};

View file

@ -318,7 +318,6 @@ export function useOverallStats<TParams extends OverallStatsSearchStrategyParams
const docs = resp.rawResponse.hits.hits.map((d) =>
d.fields ? getProcessedFields(d.fields) : {}
);
sampledNonAggregatableFieldsExamples = docs;
}
if (isAggregatableFieldOverallStats(resp)) {

View file

@ -7,7 +7,7 @@
import '../_index.scss';
import { pick } from 'lodash';
import type { FC } from 'react';
import React, { useCallback, useEffect, useState } from 'react';
import React, { useCallback, useEffect, useState, useMemo } from 'react';
import { useHistory, useLocation } from 'react-router-dom';
import { parse, stringify } from 'query-string';
import { isEqual } from 'lodash';
@ -30,6 +30,9 @@ import {
UrlStateProvider,
} from '@kbn/ml-url-state';
import type { SavedSearch } from '@kbn/saved-search-plugin/public';
import { ENABLE_ESQL } from '@kbn/discover-utils';
import { EuiCallOut } from '@elastic/eui';
import { FormattedMessage } from '@kbn/i18n-react';
import { getCoreStart, getPluginsStart } from '../../kibana_services';
import {
type IndexDataVisualizerViewProps,
@ -85,6 +88,22 @@ export const getLocatorParams = (params: {
};
const DataVisualizerESQLStateContextProvider = () => {
const { services } = useDataVisualizerKibana();
const isEsqlEnabled = useMemo(() => services.uiSettings.get(ENABLE_ESQL), [services.uiSettings]);
if (!isEsqlEnabled) {
return (
<EuiCallOut
title={
<FormattedMessage
id="xpack.dataVisualizer.esqlNotEnabledCalloutTitle"
defaultMessage="ES|QL is not enabled"
/>
}
/>
);
}
return (
<UrlStateProvider>
<IndexDataVisualizerESQL />
@ -314,6 +333,7 @@ export const IndexDataVisualizer: FC<Props> = ({
charts,
unifiedSearch,
};
const datePickerDeps: DatePickerDependencies = {
...pick(services, ['data', 'http', 'notifications', 'theme', 'uiSettings', 'i18n']),
uiSettingsKeys: UI_SETTINGS,

View file

@ -9,6 +9,7 @@ import type { UseCancellableSearch } from '@kbn/ml-cancellable-search';
import type { QueryDslQueryContainer } from '@kbn/data-views-plugin/common/types';
import { ESQL_SEARCH_STRATEGY } from '@kbn/data-plugin/common';
import pLimit from 'p-limit';
import { ESQL_LATEST_VERSION } from '@kbn/esql-utils';
import type { Column } from '../../hooks/esql/use_esql_overall_stats_data';
import { getSafeESQLName } from '../requests/esql_utils';
import { isFulfilled, isRejected } from '../../../common/util/promise_all_settled_utils';
@ -45,6 +46,7 @@ export const getESQLBooleanFieldStats = async ({
params: {
query: esqlBaseQuery + query,
...(filter ? { filter } : {}),
version: ESQL_LATEST_VERSION,
},
},
};

View file

@ -102,6 +102,7 @@ const getESQLOverallStatsInChunk = async ({
countQuery += fieldsToFetch.map((field) => field.query).join(',');
const query = esqlBaseQueryWithLimit + (evalQuery ? ' | EVAL ' + evalQuery : '') + countQuery;
const request = {
params: {
query,

View file

@ -9,6 +9,7 @@ import type { UseCancellableSearch } from '@kbn/ml-cancellable-search';
import type { QueryDslQueryContainer } from '@kbn/data-views-plugin/common/types';
import { ESQL_SEARCH_STRATEGY } from '@kbn/data-plugin/common';
import pLimit from 'p-limit';
import { ESQL_LATEST_VERSION } from '@kbn/esql-utils';
import type { Column } from '../../hooks/esql/use_esql_overall_stats_data';
import { getSafeESQLName } from '../requests/esql_utils';
import { isFulfilled, isRejected } from '../../../common/util/promise_all_settled_utils';
@ -33,17 +34,19 @@ export const getESQLKeywordFieldStats = async ({
const keywordFields = columns.map((field) => {
const query =
esqlBaseQuery +
`| STATS ${getSafeESQLName(`${field.name}_terms`)} = count(${getSafeESQLName(
`| STATS ${getSafeESQLName(`${field.name}_in_records`)} = count(MV_MIN(${getSafeESQLName(
field.name
)}) BY ${getSafeESQLName(field.name)}
| LIMIT 10
| SORT ${getSafeESQLName(`${field.name}_terms`)} DESC`;
)})), ${getSafeESQLName(`${field.name}_in_values`)} = count(${getSafeESQLName(field.name)})
BY ${getSafeESQLName(field.name)}
| SORT ${getSafeESQLName(`${field.name}_in_records`)} DESC
| LIMIT 10`;
return {
field,
request: {
params: {
query,
...(filter ? { filter } : {}),
version: ESQL_LATEST_VERSION,
},
},
};
@ -61,17 +64,31 @@ export const getESQLKeywordFieldStats = async ({
if (!resp) return;
if (isFulfilled(resp)) {
const results = resp.value?.rawResponse.values as Array<[BucketCount, BucketTerm]>;
const results = resp.value?.rawResponse?.values as Array<
[BucketCount, BucketCount, BucketTerm]
>;
if (results) {
const topValuesSampleSize = results.reduce((acc, row) => {
return row[1] + acc;
}, 0);
const sampledValues = results.map((row) => ({
key: row[2],
doc_count: row[1],
}));
const terms = results.map((row) => ({
key: row[1],
key: row[2],
doc_count: row[0],
}));
return {
fieldName: field.name,
topValues: terms,
isTopValuesSampled: false,
sampledValues,
isTopValuesSampled: true,
topValuesSampleSize,
} as StringFieldStats;
}
return;

View file

@ -1,68 +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; you may not use this file except in compliance with the Elastic License
* 2.0.
*/
import type { UseCancellableSearch } from '@kbn/ml-cancellable-search';
import type { QueryDslQueryContainer } from '@kbn/data-views-plugin/common/types';
import { ESQL_SEARCH_STRATEGY } from '@kbn/data-plugin/common';
import { ESQL_LATEST_VERSION } from '@kbn/esql-utils';
import type { Column } from '../../hooks/esql/use_esql_overall_stats_data';
import type { FieldExamples, FieldStatsError } from '../../../../../common/types/field_stats';
interface Params {
runRequest: UseCancellableSearch['runRequest'];
columns: Column[];
esqlBaseQuery: string;
filter?: QueryDslQueryContainer;
}
/**
* Make one query that gets the top 10 rows for each text field requested
* then process the values to showcase examples for each field
* @param
* @returns
*/
export const getESQLExampleFieldValues = async ({
runRequest,
columns: textFields,
esqlBaseQuery,
filter,
}: Params): Promise<Array<FieldExamples | FieldStatsError>> => {
try {
if (textFields.length > 0) {
const request = {
params: {
query:
esqlBaseQuery +
`| KEEP ${textFields.map((f) => f.name).join(',')}
| LIMIT 10`,
...(filter ? { filter } : {}),
version: ESQL_LATEST_VERSION,
},
};
const textFieldsResp = await runRequest(request, { strategy: ESQL_SEARCH_STRATEGY });
if (textFieldsResp) {
return textFields.map((textField, idx) => {
const examples = [
...new Set((textFieldsResp.rawResponse.values as unknown[][]).map((row) => row[idx])),
];
return {
fieldName: textField.name,
examples,
} as FieldExamples;
});
}
}
} catch (error) {
return textFields.map((textField, idx) => ({
fieldName: textField.name,
error,
})) as FieldStatsError[];
}
return [];
};

View file

@ -6,7 +6,7 @@
*/
import type { DocumentCountStats } from '../../../../common/types/field_stats';
import type { SupportedFieldType } from '../../../../common/types';
export interface AggregatableField {
fieldName: string;
stats: {
@ -25,6 +25,7 @@ export interface NonAggregatableField {
sampleCount?: number;
};
existsInDocs: boolean;
secondaryType?: SupportedFieldType;
}
export interface OverallStats {

View file

@ -77,7 +77,8 @@
"@kbn/utility-types",
"@kbn/visualization-utils",
"@kbn/ml-time-buckets",
"@kbn/aiops-log-rate-analysis"
"@kbn/aiops-log-rate-analysis",
"@kbn/discover-utils"
],
"exclude": [
"target/**/*",

View file

@ -6,7 +6,7 @@
*/
import type { FC } from 'react';
import React, { Fragment } from 'react';
import React, { Fragment, useMemo } from 'react';
import {
EuiButton,
@ -25,6 +25,7 @@ import {
import { i18n } from '@kbn/i18n';
import { FormattedMessage } from '@kbn/i18n-react';
import { useTimefilter } from '@kbn/ml-date-picker';
import { ENABLE_ESQL } from '@kbn/discover-utils';
import { isFullLicense } from '../license';
import { useMlKibana, useNavigateToPath } from '../contexts/kibana';
import { HelpMenu } from '../components/help_menu';
@ -61,8 +62,10 @@ export const DatavisualizerSelector: FC = () => {
http: { basePath },
docLinks,
dataVisualizer,
uiSettings,
},
} = useMlKibana();
const isEsqlEnabled = useMemo(() => uiSettings.get(ENABLE_ESQL), [uiSettings]);
const helpLink = docLinks.links.ml.guide;
const navigateToPath = useNavigateToPath();
@ -160,60 +163,62 @@ export const DatavisualizerSelector: FC = () => {
data-test-subj="mlDataVisualizerCardIndexData"
/>
</EuiFlexItem>
<EuiFlexItem>
<EuiCard
hasBorder
icon={<EuiIcon size="xxl" type="dataVisualizer" />}
title={
<EuiTextAlign textAlign="center">
<>
<FormattedMessage
id="xpack.ml.datavisualizer.selector.selectESQLTitle"
defaultMessage="Visualize data using ES|QL"
/>{' '}
<EuiBetaBadge
label=""
iconType="beaker"
size="m"
color="hollow"
tooltipContent={
<FormattedMessage
id="xpack.ml.datavisualizer.selector.technicalPreviewBadge.titleMsg"
defaultMessage="ES|QL is in technical preview."
/>
}
tooltipPosition={'right'}
aria-label={i18n.translate(
'xpack.ml.datavisualizer.selector.technicalPreviewBadge.ariaLabel',
{
defaultMessage: 'ES|QL is in technical preview.',
{isEsqlEnabled ? (
<EuiFlexItem>
<EuiCard
hasBorder
icon={<EuiIcon size="xxl" type="dataVisualizer" />}
title={
<EuiTextAlign textAlign="center">
<>
<FormattedMessage
id="xpack.ml.datavisualizer.selector.selectESQLTitle"
defaultMessage="Visualize data using ES|QL"
/>{' '}
<EuiBetaBadge
label=""
iconType="beaker"
size="m"
color="hollow"
tooltipContent={
<FormattedMessage
id="xpack.ml.datavisualizer.selector.technicalPreviewBadge.titleMsg"
defaultMessage="ES|QL is in technical preview."
/>
}
)}
/>
</>
</EuiTextAlign>
}
description={
<FormattedMessage
id="xpack.ml.datavisualizer.selector.technicalPreviewBadge.contentMsg"
defaultMessage="Use ES|QL queries to visualize information about any data set."
/>
}
footer={
<EuiButton
target="_self"
onClick={() => navigateToPath(ML_PAGES.DATA_VISUALIZER_ESQL)}
data-test-subj="mlDataVisualizerSelectESQLButton"
>
tooltipPosition={'right'}
aria-label={i18n.translate(
'xpack.ml.datavisualizer.selector.technicalPreviewBadge.ariaLabel',
{
defaultMessage: 'ES|QL is in technical preview.',
}
)}
/>
</>
</EuiTextAlign>
}
description={
<FormattedMessage
id="xpack.ml.datavisualizer.selector.useESQLButtonLabel"
defaultMessage="Use ES|QL"
id="xpack.ml.datavisualizer.selector.technicalPreviewBadge.contentMsg"
defaultMessage="Use ES|QL queries to visualize information about any data set."
/>
</EuiButton>
}
data-test-subj="mlDataVisualizerCardESQLData"
/>
</EuiFlexItem>
}
footer={
<EuiButton
target="_self"
onClick={() => navigateToPath(ML_PAGES.DATA_VISUALIZER_ESQL)}
data-test-subj="mlDataVisualizerSelectESQLButton"
>
<FormattedMessage
id="xpack.ml.datavisualizer.selector.useESQLButtonLabel"
defaultMessage="Use ES|QL"
/>
</EuiButton>
}
data-test-subj="mlDataVisualizerCardESQLData"
/>
</EuiFlexItem>
) : null}
</EuiFlexGrid>
{startTrialVisible === true && (
<Fragment>

View file

@ -50,6 +50,7 @@ import type { SavedSearchPublicPluginStart } from '@kbn/saved-search-plugin/publ
import type { PresentationUtilPluginStart } from '@kbn/presentation-util-plugin/public';
import type { DataViewEditorStart } from '@kbn/data-view-editor-plugin/public';
import type { FieldFormatsRegistry } from '@kbn/field-formats-plugin/common';
import { ENABLE_ESQL } from '@kbn/discover-utils';
import type { MlSharedServices } from './application/services/get_shared_ml_services';
import { getMlSharedServices } from './application/services/get_shared_ml_services';
import { registerManagementSection } from './application/management';
@ -222,6 +223,8 @@ export class MlPlugin implements Plugin<MlPluginSetup, MlPluginStart> {
const { capabilities } = coreStart.application;
const mlCapabilities = capabilities.ml as MlCapabilities;
const isEsqlEnabled = core.uiSettings.get(ENABLE_ESQL);
// register various ML plugin features which require a full license
// note including registerHomeFeature in register_helper would cause the page bundle size to increase significantly
if (mlEnabled) {
@ -236,7 +239,13 @@ export class MlPlugin implements Plugin<MlPluginSetup, MlPluginStart> {
registerSearchLinks,
registerCasesAttachments,
} = await import('./register_helper');
registerSearchLinks(this.appUpdater$, fullLicense, mlCapabilities, this.isServerless);
registerSearchLinks(
this.appUpdater$,
fullLicense,
mlCapabilities,
this.isServerless,
isEsqlEnabled
);
if (
pluginsSetup.triggersActionsUi &&

View file

@ -16,7 +16,8 @@ export function registerSearchLinks(
appUpdater: BehaviorSubject<AppUpdater>,
isFullLicense: boolean,
mlCapabilities: MlCapabilities,
isServerless: boolean
isServerless: boolean,
isEsqlEnabled?: boolean
) {
appUpdater.next(() => ({
keywords: [
@ -24,6 +25,6 @@ export function registerSearchLinks(
defaultMessage: 'ML',
}),
],
deepLinks: getDeepLinks(isFullLicense, mlCapabilities, isServerless),
deepLinks: getDeepLinks(isFullLicense, mlCapabilities, isServerless, isEsqlEnabled),
}));
}

View file

@ -15,7 +15,8 @@ import { ML_PAGES } from '../../../common/constants/locator';
function createDeepLinks(
mlCapabilities: MlCapabilities,
isFullLicense: boolean,
isServerless: boolean
isServerless: boolean,
esqlEnabled?: boolean
) {
return {
getOverviewLinkDeepLink: (): AppDeepLink<LinkId> | null => {
@ -238,7 +239,8 @@ function createDeepLinks(
};
},
getESQLDataVisualizerDeepLink: (): AppDeepLink<LinkId> => {
getESQLDataVisualizerDeepLink: (): AppDeepLink<LinkId> | null => {
if (!esqlEnabled) return null;
return {
id: 'esqlDataVisualizer',
title: i18n.translate('xpack.ml.deepLink.esqlDataVisualizer', {
@ -263,9 +265,10 @@ function createDeepLinks(
export function getDeepLinks(
isFullLicense: boolean,
mlCapabilities: MlCapabilities,
isServerless: boolean
isServerless: boolean,
esqlEnabled?: boolean
): Array<AppDeepLink<LinkId>> {
const links = createDeepLinks(mlCapabilities, isFullLicense, isServerless);
const links = createDeepLinks(mlCapabilities, isFullLicense, isServerless, esqlEnabled);
return Object.values(links)
.map((link) => link())
.filter((link): link is AppDeepLink<LinkId> => link !== null);

View file

@ -124,5 +124,6 @@
"@kbn/presentation-containers",
"@kbn/presentation-panel-plugin",
"@kbn/shared-ux-utility",
"@kbn/discover-utils",
],
}

View file

@ -132,7 +132,7 @@ const esqlSampleLogData: TestData = {
sourceIndexOrSavedSearch: 'ft_module_sample_logs',
expected: {
hasDocCountChart: false,
totalDocCountFormatted: '149',
totalDocCountFormatted: '143',
metricFields: [
{
fieldName: 'max_bytes_kb',
@ -140,7 +140,7 @@ const esqlSampleLogData: TestData = {
existsInDocs: true,
aggregatable: true,
loading: false,
docCountFormatted: '143 (95.97%)',
docCountFormatted: '143 (100%)',
statsMaxDecimalPlaces: 3,
topValuesCount: 12,
viewableInLens: false,
@ -151,7 +151,7 @@ const esqlSampleLogData: TestData = {
existsInDocs: true,
aggregatable: true,
loading: false,
docCountFormatted: '143 (95.97%)',
docCountFormatted: '143 (100%)',
statsMaxDecimalPlaces: 3,
topValuesCount: 20,
viewableInLens: false,
@ -164,7 +164,7 @@ const esqlSampleLogData: TestData = {
existsInDocs: true,
aggregatable: true,
loading: false,
docCountFormatted: '143 (95.97%)',
docCountFormatted: '143 (100%)',
exampleCount: 10,
viewableInLens: false,
},
@ -174,7 +174,7 @@ const esqlSampleLogData: TestData = {
existsInDocs: true,
aggregatable: true,
loading: false,
docCountFormatted: '143 (95.97%)',
docCountFormatted: '143 (100%)',
exampleCount: 11,
viewableInLens: false,
},
@ -314,8 +314,7 @@ export default function ({ getPageObject, getService }: FtrProviderContext) {
runTests(esqlFarequoteData);
});
// FAILING ES PROMOTION: https://github.com/elastic/kibana/issues/180072
describe.skip('with module_sample_logs ', function () {
describe('with module_sample_logs ', function () {
runTests(esqlSampleLogData);
});
});