Skip to content

feat: Optimize and fix filtering on toStartOfX primary key expressions #1265

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Oct 27, 2025
Merged

feat: Optimize and fix filtering on toStartOfX primary key expressions #1265

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
c2726c5
feat: Optimize and fix filtering on toStartOfX primary key expressions
pulpdrew Oct 15, 2025
19fd772
Merge branch 'main' into drew/optimize-timestamp-filters
kodiakhq[bot] Oct 27, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions .changeset/fluffy-mails-sparkle.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,6 @@
---
"@hyperdx/common-utils": patch
"@hyperdx/app": patch
---

feat: Optimize and fix filtering on toStartOfX primary key expressions
223 changes: 219 additions & 4 deletions packages/common-utils/src/__tests__/renderChartConfig.test.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,15 +1,15 @@
import { chSql, parameterizedQueryToSql } from '@/clickhouse';
import { chSql, ColumnMeta, parameterizedQueryToSql } from '@/clickhouse';
import { Metadata } from '@/metadata';
import {
ChartConfigWithOptDateRange,
DisplayType,
MetricsDataType,
} from '@/types';

import { renderChartConfig } from '../renderChartConfig';
import { renderChartConfig, timeFilterExpr } from '../renderChartConfig';

describe('renderChartConfig', () => {
let mockMetadata: Metadata;
let mockMetadata: jest.Mocked<Metadata>;

beforeEach(() => {
mockMetadata = {
Expand All @@ -19,7 +19,10 @@ describe('renderChartConfig', () => {
]),
getMaterializedColumnsLookupTable: jest.fn().mockResolvedValue(null),
getColumn: jest.fn().mockResolvedValue({ type: 'DateTime' }),
} as unknown as Metadata;
getTableMetadata: jest
.fn()
.mockResolvedValue({ primary_key: 'timestamp' }),
} as unknown as jest.Mocked<Metadata>;
});

const gaugeConfiguration: ChartConfigWithOptDateRange = {
Expand Down Expand Up @@ -630,4 +633,216 @@ describe('renderChartConfig', () => {
expect(actual).toMatchSnapshot();
});
});

describe('timeFilterExpr', () => {
type TimeFilterExprTestCase = {
timestampValueExpression: string;
dateRangeStartInclusive?: boolean;
dateRangeEndInclusive?: boolean;
dateRange: [Date, Date];
includedDataInterval?: string;
expected: string;
description: string;
tableName?: string;
databaseName?: string;
primaryKey?: string;
};

const testCases: TimeFilterExprTestCase[] = [
{
description: 'with basic timestampValueExpression',
timestampValueExpression: 'timestamp',
dateRange: [
new Date('2025-02-12 00:12:34Z'),
new Date('2025-02-14 00:12:34Z'),
],
expected: `(timestamp >= fromUnixTimestamp64Milli(${new Date('2025-02-12 00:12:34Z').getTime()}) AND timestamp <= fromUnixTimestamp64Milli(${new Date('2025-02-14 00:12:34Z').getTime()}))`,
},
{
description: 'with dateRangeEndInclusive=false',
timestampValueExpression: 'timestamp',
dateRange: [
new Date('2025-02-12 00:12:34Z'),
new Date('2025-02-14 00:12:34Z'),
],
dateRangeEndInclusive: false,
expected: `(timestamp >= fromUnixTimestamp64Milli(${new Date('2025-02-12 00:12:34Z').getTime()}) AND timestamp < fromUnixTimestamp64Milli(${new Date('2025-02-14 00:12:34Z').getTime()}))`,
},
{
description: 'with dateRangeStartInclusive=false',
timestampValueExpression: 'timestamp',
dateRange: [
new Date('2025-02-12 00:12:34Z'),
new Date('2025-02-14 00:12:34Z'),
],
dateRangeStartInclusive: false,
expected: `(timestamp > fromUnixTimestamp64Milli(${new Date('2025-02-12 00:12:34Z').getTime()}) AND timestamp <= fromUnixTimestamp64Milli(${new Date('2025-02-14 00:12:34Z').getTime()}))`,
},
{
description: 'with includedDataInterval',
timestampValueExpression: 'timestamp',
dateRange: [
new Date('2025-02-12 00:12:34Z'),
new Date('2025-02-14 00:12:34Z'),
],
includedDataInterval: '1 WEEK',
expected: `(timestamp >= toStartOfInterval(fromUnixTimestamp64Milli(${new Date('2025-02-12 00:12:34Z').getTime()}), INTERVAL 1 WEEK) - INTERVAL 1 WEEK AND timestamp <= toStartOfInterval(fromUnixTimestamp64Milli(${new Date('2025-02-14 00:12:34Z').getTime()}), INTERVAL 1 WEEK) + INTERVAL 1 WEEK)`,
},
{
description: 'with date type timestampValueExpression',
timestampValueExpression: 'date',
dateRange: [
new Date('2025-02-12 00:12:34Z'),
new Date('2025-02-14 00:12:34Z'),
],
expected: `(date >= toDate(fromUnixTimestamp64Milli(${new Date('2025-02-12 00:12:34Z').getTime()})) AND date <= toDate(fromUnixTimestamp64Milli(${new Date('2025-02-14 00:12:34Z').getTime()})))`,
},
{
description: 'with multiple timestampValueExpression parts',
timestampValueExpression: 'timestamp, date',
dateRange: [
new Date('2025-02-12 00:12:34Z'),
new Date('2025-02-14 00:12:34Z'),
],
expected: `(timestamp >= fromUnixTimestamp64Milli(${new Date('2025-02-12 00:12:34Z').getTime()}) AND timestamp <= fromUnixTimestamp64Milli(${new Date('2025-02-14 00:12:34Z').getTime()}))AND(date >= toDate(fromUnixTimestamp64Milli(${new Date('2025-02-12 00:12:34Z').getTime()})) AND date <= toDate(fromUnixTimestamp64Milli(${new Date('2025-02-14 00:12:34Z').getTime()})))`,
},
{
description: 'with toStartOfDay() in timestampExpr',
timestampValueExpression: 'toStartOfDay(timestamp)',
dateRange: [
new Date('2025-02-12 00:12:34Z'),
new Date('2025-02-14 00:12:34Z'),
],
expected: `(toStartOfDay(timestamp) >= toStartOfDay(fromUnixTimestamp64Milli(${new Date('2025-02-12 00:12:34Z').getTime()})) AND toStartOfDay(timestamp) <= toStartOfDay(fromUnixTimestamp64Milli(${new Date('2025-02-14 00:12:34Z').getTime()})))`,
},
{
description: 'with toStartOfDay () in timestampExpr',
timestampValueExpression: 'toStartOfDay (timestamp)',
dateRange: [
new Date('2025-02-12 00:12:34Z'),
new Date('2025-02-14 00:12:34Z'),
],
expected: `(toStartOfDay (timestamp) >= toStartOfDay(fromUnixTimestamp64Milli(${new Date('2025-02-12 00:12:34Z').getTime()})) AND toStartOfDay (timestamp) <= toStartOfDay(fromUnixTimestamp64Milli(${new Date('2025-02-14 00:12:34Z').getTime()})))`,
},
{
description: 'with toStartOfInterval() in timestampExpr',
timestampValueExpression:
'toStartOfInterval(timestamp, INTERVAL 12 MINUTE)',
dateRange: [
new Date('2025-02-12 00:12:34Z'),
new Date('2025-02-14 00:12:34Z'),
],
expected: `(toStartOfInterval(timestamp, INTERVAL 12 MINUTE) >= toStartOfInterval(fromUnixTimestamp64Milli(${new Date('2025-02-12 00:12:34Z').getTime()}), INTERVAL 12 MINUTE) AND toStartOfInterval(timestamp, INTERVAL 12 MINUTE) <= toStartOfInterval(fromUnixTimestamp64Milli(${new Date('2025-02-14 00:12:34Z').getTime()}), INTERVAL 12 MINUTE))`,
},
{
description:
'with toStartOfInterval() with lowercase interval in timestampExpr',
timestampValueExpression:
'toStartOfInterval(timestamp, interval 1 minute)',
dateRange: [
new Date('2025-02-12 00:12:34Z'),
new Date('2025-02-14 00:12:34Z'),
],
expected: `(toStartOfInterval(timestamp, interval 1 minute) >= toStartOfInterval(fromUnixTimestamp64Milli(${new Date('2025-02-12 00:12:34Z').getTime()}), interval 1 minute) AND toStartOfInterval(timestamp, interval 1 minute) <= toStartOfInterval(fromUnixTimestamp64Milli(${new Date('2025-02-14 00:12:34Z').getTime()}), interval 1 minute))`,
},
{
description: 'with toStartOfInterval() with timezone and offset',
timestampValueExpression: `toStartOfInterval(timestamp, INTERVAL 1 MINUTE, toDateTime('2023-01-01 14:35:30'), 'America/New_York')`,
dateRange: [
new Date('2025-02-12 00:12:34Z'),
new Date('2025-02-14 00:12:34Z'),
],
expected: `(toStartOfInterval(timestamp, INTERVAL 1 MINUTE, toDateTime('2023-01-01 14:35:30'), 'America/New_York') >= toStartOfInterval(fromUnixTimestamp64Milli(${new Date('2025-02-12 00:12:34Z').getTime()}), INTERVAL 1 MINUTE, toDateTime('2023-01-01 14:35:30'), 'America/New_York') AND toStartOfInterval(timestamp, INTERVAL 1 MINUTE, toDateTime('2023-01-01 14:35:30'), 'America/New_York') <= toStartOfInterval(fromUnixTimestamp64Milli(${new Date('2025-02-14 00:12:34Z').getTime()}), INTERVAL 1 MINUTE, toDateTime('2023-01-01 14:35:30'), 'America/New_York'))`,
},
{
description: 'with nonstandard spacing',
timestampValueExpression: ` toStartOfInterval ( timestamp , INTERVAL 1 MINUTE , toDateTime ( '2023-01-01 14:35:30' ), 'America/New_York' ) `,
dateRange: [
new Date('2025-02-12 00:12:34Z'),
new Date('2025-02-14 00:12:34Z'),
],
expected: `(toStartOfInterval ( timestamp , INTERVAL 1 MINUTE , toDateTime ( '2023-01-01 14:35:30' ), 'America/New_York' ) >= toStartOfInterval(fromUnixTimestamp64Milli(${new Date('2025-02-12 00:12:34Z').getTime()}), INTERVAL 1 MINUTE, toDateTime ( '2023-01-01 14:35:30' ), 'America/New_York') AND toStartOfInterval ( timestamp , INTERVAL 1 MINUTE , toDateTime ( '2023-01-01 14:35:30' ), 'America/New_York' ) <= toStartOfInterval(fromUnixTimestamp64Milli(${new Date('2025-02-14 00:12:34Z').getTime()}), INTERVAL 1 MINUTE, toDateTime ( '2023-01-01 14:35:30' ), 'America/New_York'))`,
},
{
description: 'with optimizable timestampValueExpression',
timestampValueExpression: `timestamp`,
primaryKey:
"toStartOfMinute(timestamp), ServiceName, ResourceAttributes['timestamp'], timestamp",
dateRange: [
new Date('2025-02-12 00:12:34Z'),
new Date('2025-02-14 00:12:34Z'),
],
expected: `(timestamp >= fromUnixTimestamp64Milli(1739319154000) AND timestamp <= fromUnixTimestamp64Milli(1739491954000))AND(toStartOfMinute(timestamp) >= toStartOfMinute(fromUnixTimestamp64Milli(1739319154000)) AND toStartOfMinute(timestamp) <= toStartOfMinute(fromUnixTimestamp64Milli(1739491954000)))`,
},
{
description: 'with synthetic timestamp value expression for CTE',
timestampValueExpression: `__hdx_time_bucket`,
dateRange: [
new Date('2025-02-12 00:12:34Z'),
new Date('2025-02-14 00:12:34Z'),
],
databaseName: '',
tableName: 'Bucketed',
primaryKey:
"toStartOfMinute(timestamp), ServiceName, ResourceAttributes['timestamp'], timestamp",
expected: `(__hdx_time_bucket >= fromUnixTimestamp64Milli(1739319154000) AND __hdx_time_bucket <= fromUnixTimestamp64Milli(1739491954000))`,
},

{
description: 'with toStartOfMinute in timestampValueExpression',
timestampValueExpression: `toStartOfMinute(timestamp)`,
dateRange: [
new Date('2025-02-12 00:12:34Z'),
new Date('2025-02-14 00:12:34Z'),
],
primaryKey:
"toStartOfMinute(timestamp), ServiceName, ResourceAttributes['timestamp'], timestamp",
expected: `(toStartOfMinute(timestamp) >= toStartOfMinute(fromUnixTimestamp64Milli(1739319154000)) AND toStartOfMinute(timestamp) <= toStartOfMinute(fromUnixTimestamp64Milli(1739491954000)))`,
},
];

beforeEach(() => {
mockMetadata.getColumn.mockImplementation(async ({ column }) =>
column === 'date'
? ({ type: 'Date' } as ColumnMeta)
: ({ type: 'DateTime' } as ColumnMeta),
);
});

it.each(testCases)(
'should generate a time filter expression $description',
async ({
timestampValueExpression,
dateRangeEndInclusive = true,
dateRangeStartInclusive = true,
dateRange,
expected,
includedDataInterval,
tableName = 'target_table',
databaseName = 'default',
primaryKey,
}) => {
if (primaryKey) {
mockMetadata.getTableMetadata.mockResolvedValue({
primary_key: primaryKey,
} as any);
}

const actual = await timeFilterExpr({
timestampValueExpression,
dateRangeEndInclusive,
dateRangeStartInclusive,
dateRange,
connectionId: 'test-connection',
databaseName,
tableName,
metadata: mockMetadata,
includedDataInterval,
});

const actualSql = parameterizedQueryToSql(actual);
expect(actualSql).toBe(expected);
},
);
});
});
Loading
Loading