Merge branch 'dev' of https://github.com/umami-software/umami into feat/clickhouse-mv

This commit is contained in:
Francis Cao 2024-07-19 11:27:03 -07:00
commit 77fcdc0646
157 changed files with 1780 additions and 1476 deletions

View file

@ -2,18 +2,19 @@ import { ClickHouseClient, createClient } from '@clickhouse/client';
import dateFormat from 'dateformat';
import debug from 'debug';
import { CLICKHOUSE } from 'lib/db';
import { QueryFilters, QueryOptions } from './types';
import { OPERATORS } from './constants';
import { PageParams, QueryFilters, QueryOptions } from './types';
import { DEFAULT_PAGE_SIZE, OPERATORS } from './constants';
import { fetchWebsite } from './load';
import { maxDate } from './date';
import { filtersToArray } from './params';
export const CLICKHOUSE_DATE_FORMATS = {
minute: '%Y-%m-%d %H:%i:00',
hour: '%Y-%m-%d %H:00:00',
day: '%Y-%m-%d',
month: '%Y-%m-01',
year: '%Y-01-01',
second: '%Y-%m-%dT%H:%i:%S',
minute: '%Y-%m-%dT%H:%i:00',
hour: '%Y-%m-%dT%H:00:00',
day: '%Y-%m-%dT00:00:00',
month: '%Y-%m-01T00:00:00',
year: '%Y-01-01T00:00:00',
};
const log = debug('umami:clickhouse');
@ -32,7 +33,7 @@ function getClient() {
} = new URL(process.env.CLICKHOUSE_URL);
const client = createClient({
host: `${protocol}//${hostname}:${port}`,
url: `${protocol}//${hostname}:${port}`,
database: pathname.replace('/', ''),
username: username,
password,
@ -47,11 +48,15 @@ function getClient() {
return client;
}
function getDateStringQuery(data: any, unit: string | number) {
function getDateStringSQL(data: any, unit: string | number, timezone?: string) {
if (timezone) {
return `formatDateTime(${data}, '${CLICKHOUSE_DATE_FORMATS[unit]}', '${timezone}')`;
}
return `formatDateTime(${data}, '${CLICKHOUSE_DATE_FORMATS[unit]}')`;
}
function getDateQuery(field: string, unit: string, timezone?: string) {
function getDateSQL(field: string, unit: string, timezone?: string) {
if (timezone) {
return `date_trunc('${unit}', ${field}, '${timezone}')`;
}
@ -95,6 +100,20 @@ function getFilterQuery(filters: QueryFilters = {}, options: QueryOptions = {})
return query.join('\n');
}
function getDateQuery(filters: QueryFilters = {}) {
const { startDate, endDate } = filters;
if (startDate) {
if (endDate) {
return `and created_at between {startDate:DateTime64} and {endDate:DateTime64}`;
} else {
return `and created_at >= {startDate:DateTime64}`;
}
}
return '';
}
function getFilterParams(filters: QueryFilters = {}) {
return filtersToArray(filters).reduce((obj, { name, value }) => {
if (name && value !== undefined) {
@ -110,6 +129,7 @@ async function parseFilters(websiteId: string, filters: QueryFilters = {}, optio
return {
filterQuery: getFilterQuery(filters, options),
dateQuery: getDateQuery(filters),
params: {
...getFilterParams(filters),
websiteId,
@ -119,6 +139,32 @@ async function parseFilters(websiteId: string, filters: QueryFilters = {}, optio
};
}
async function pagedQuery(
query: string,
queryParams: { [key: string]: any },
pageParams: PageParams = {},
) {
const { page = 1, pageSize, orderBy, sortDescending = false } = pageParams;
const size = +pageSize || DEFAULT_PAGE_SIZE;
const offset = +size * (page - 1);
const direction = sortDescending ? 'desc' : 'asc';
const statements = [
orderBy && `order by ${orderBy} ${direction}`,
+size > 0 && `limit ${+size} offset ${offset}`,
]
.filter(n => n)
.join('\n');
const count = await rawQuery(`select count(*) as num from (${query}) t`, queryParams).then(
res => res[0].num,
);
const data = await rawQuery(`${query}${statements}`, queryParams);
return { data, count, page: +page, pageSize: size, orderBy };
}
async function rawQuery<T = unknown>(
query: string,
params: Record<string, unknown> = {},
@ -136,7 +182,13 @@ async function rawQuery<T = unknown>(
format: 'JSONEachRow',
});
return resultSet.json();
return resultSet.json() as T;
}
async function insert(table: string, values: any[]) {
await connect();
return clickhouse.insert({ table, values, format: 'JSONEachRow' });
}
async function findUnique(data: any[]) {
@ -164,12 +216,14 @@ export default {
client: clickhouse,
log,
connect,
getDateStringQuery,
getDateQuery,
getDateStringSQL,
getDateSQL,
getDateFormat,
getFilterQuery,
parseFilters,
pagedQuery,
findUnique,
findFirst,
rawQuery,
insert,
};

View file

@ -292,7 +292,7 @@ export function getDateArray(data: any[], startDate: Date, endDate: Date, unit:
for (let i = 0; i <= n; i++) {
const t = start(add(startDate, i));
const y = data.find(({ x }) => start(getDateFromString(x)).getTime() === t.getTime())?.y || 0;
const y = data.find(({ x }) => start(new Date(x)).getTime() === t.getTime())?.y || 0;
arr.push({ x: t, y });
}

View file

@ -2,9 +2,9 @@ import path from 'path';
import { getClientIp } from 'request-ip';
import { browserName, detectOS } from 'detect-browser';
import isLocalhost from 'is-localhost-ip';
import ipaddr from 'ipaddr.js';
import maxmind from 'maxmind';
import { safeDecodeURIComponent } from 'next-basics';
import {
DESKTOP_OS,
MOBILE_OS,
@ -137,3 +137,31 @@ export async function getClientInfo(req: NextApiRequestCollect) {
return { userAgent, browser, os, ip, country, subdivision1, subdivision2, city, device };
}
export function hasBlockedIp(req: NextApiRequestCollect) {
const ignoreIps = process.env.IGNORE_IP;
if (ignoreIps) {
const ips = [];
if (ignoreIps) {
ips.push(...ignoreIps.split(',').map(n => n.trim()));
}
const clientIp = getIpAddress(req);
return ips.find(ip => {
if (ip === clientIp) return true;
// CIDR notation
if (ip.indexOf('/') > 0) {
const addr = ipaddr.parse(clientIp);
const range = ipaddr.parseCIDR(ip);
if (addr.kind() === range[0].kind() && addr.match(range)) return true;
}
});
}
return false;
}

View file

@ -61,8 +61,8 @@ function getDateFormat(date: Date, format?: string): string {
}
async function sendMessage(
message: { [key: string]: string | number },
topic: string,
message: { [key: string]: string | number },
): Promise<RecordMetadata[]> {
await connect();
@ -77,7 +77,7 @@ async function sendMessage(
});
}
async function sendMessages(messages: { [key: string]: string | number }[], topic: string) {
async function sendMessages(topic: string, messages: { [key: string]: string | number }[]) {
await connect();
await producer.send({

View file

@ -60,7 +60,7 @@ function getCastColumnQuery(field: string, type: string): string {
}
}
function getDateQuery(field: string, unit: string, timezone?: string): string {
function getDateSQL(field: string, unit: string, timezone?: string): string {
const db = getDatabaseType();
if (db === POSTGRESQL) {
@ -81,7 +81,19 @@ function getDateQuery(field: string, unit: string, timezone?: string): string {
}
}
function getTimestampDiffQuery(field1: string, field2: string): string {
export function getTimestampSQL(field: string) {
const db = getDatabaseType();
if (db === POSTGRESQL) {
return `floor(extract(epoch from ${field}))`;
}
if (db === MYSQL) {
return `UNIX_TIMESTAMP(${field})`;
}
}
function getTimestampDiffSQL(field1: string, field2: string): string {
const db = getDatabaseType();
if (db === POSTGRESQL) {
@ -93,7 +105,7 @@ function getTimestampDiffQuery(field1: string, field2: string): string {
}
}
function getSearchQuery(column: string): string {
function getSearchSQL(column: string): string {
const db = getDatabaseType();
const like = db === POSTGRESQL ? 'ilike' : 'like';
@ -137,6 +149,20 @@ function getFilterQuery(filters: QueryFilters = {}, options: QueryOptions = {}):
return query.join('\n');
}
function getDateQuery(filters: QueryFilters = {}) {
const { startDate, endDate } = filters;
if (startDate) {
if (endDate) {
return `and website_event.created_at between {{startDate}} and {{endDate}}`;
} else {
return `and website_event.created_at >= {{startDate}}`;
}
}
return '';
}
function getFilterParams(filters: QueryFilters = {}) {
return filtersToArray(filters).reduce((obj, { name, operator, value }) => {
obj[name] = [OPERATORS.contains, OPERATORS.doesNotContain].includes(operator)
@ -161,6 +187,7 @@ async function parseFilters(
? `inner join session on website_event.session_id = session.session_id`
: '',
filterQuery: getFilterQuery(filters, options),
dateQuery: getDateQuery(filters),
params: {
...getFilterParams(filters),
websiteId,
@ -191,8 +218,8 @@ async function rawQuery(sql: string, data: object): Promise<any> {
return prisma.rawQuery(query, params);
}
async function pagedQuery<T>(model: string, criteria: T, filters: PageParams) {
const { page = 1, pageSize, orderBy, sortDescending = false } = filters || {};
async function pagedQuery<T>(model: string, criteria: T, pageParams: PageParams) {
const { page = 1, pageSize, orderBy, sortDescending = false } = pageParams || {};
const size = +pageSize || DEFAULT_PAGE_SIZE;
const data = await prisma.client[model].findMany({
@ -256,11 +283,11 @@ export default {
getAddIntervalQuery,
getCastColumnQuery,
getDayDiffQuery,
getDateQuery,
getDateSQL,
getFilterQuery,
getSearchParameters,
getTimestampDiffQuery,
getSearchQuery,
getTimestampDiffSQL,
getSearchSQL,
getQueryMode,
pagedQuery,
parseFilters,