Improve URL checks to reduce false-negatives
This commit improves the URL health checking mechanism to reduce false negatives. - Treat all 2XX status codes as successful, addressing issues with codes like `204`. - Improve URL matching to exclude URLs within Markdown inline code block and support URLs containing parentheses. - Add `forceHttpGetForUrlPatterns` to customize HTTP method per URL to allow verifying URLs behind CDN/WAFs that do not respond to HTTP HEAD. - Send the Host header for improved handling of webpages behind proxies. - Improve formatting and context for output messages. - Fix the defaulting options for redirects and cookie handling. - Update the user agent pool to modern browsers and platforms. - Add support for randomizing TLS fingerprint to mimic various clients better, improving the effectiveness of checks. However, this is not fully supported by Node.js's HTTP client; see nodejs/undici#1983 for more details. - Use `AbortSignal` instead of `AbortController` as more modern and simpler way to handle timeouts.
This commit is contained in:
@@ -1,4 +1,4 @@
|
||||
import { splitTextIntoLines, indentText } from '../utils/text';
|
||||
import { indentText, splitTextIntoLines } from '@tests/shared/Text';
|
||||
import { log, die } from '../utils/log';
|
||||
import { readAppLogFile } from './app-logs';
|
||||
import { STDERR_IGNORE_PATTERNS } from './error-ignore-patterns';
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
import { filterEmpty } from '@tests/shared/Text';
|
||||
import { runCommand } from '../../utils/run-command';
|
||||
import { log, LogLevel } from '../../utils/log';
|
||||
import { SupportedPlatform, CURRENT_PLATFORM } from '../../utils/platform';
|
||||
import { filterEmpty } from '../../utils/text';
|
||||
|
||||
export async function captureWindowTitles(processId: number) {
|
||||
if (!processId) { throw new Error('Missing process ID.'); }
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
import { indentText } from '@tests/shared/Text';
|
||||
import { logCurrentArgs, CommandLineFlag, hasCommandLineFlag } from './cli-args';
|
||||
import { log, die } from './utils/log';
|
||||
import { ensureNpmProjectDir, npmInstall, npmBuild } from './utils/npm';
|
||||
@@ -15,7 +16,6 @@ import {
|
||||
APP_EXECUTION_DURATION_IN_SECONDS,
|
||||
SCREENSHOT_PATH,
|
||||
} from './config';
|
||||
import { indentText } from './utils/text';
|
||||
import type { ExtractionResult } from './app/extractors/common/extraction-result';
|
||||
|
||||
export async function main(): Promise<void> {
|
||||
|
||||
@@ -1,5 +1,6 @@
|
||||
import { exec, type ExecOptions, type ExecException } from 'node:child_process';
|
||||
import { indentText } from './text';
|
||||
import { exec } from 'child_process';
|
||||
import { indentText } from '@tests/shared/Text';
|
||||
import type { ExecOptions, ExecException } from 'child_process';
|
||||
|
||||
const TIMEOUT_IN_SECONDS = 180;
|
||||
const MAX_OUTPUT_BUFFER_SIZE = 1024 * 1024; // 1 MB
|
||||
|
||||
@@ -1,29 +0,0 @@
|
||||
import { isString } from '@/TypeHelpers';
|
||||
|
||||
export function indentText(
|
||||
text: string,
|
||||
indentLevel = 1,
|
||||
): string {
|
||||
validateText(text);
|
||||
const indentation = '\t'.repeat(indentLevel);
|
||||
return splitTextIntoLines(text)
|
||||
.map((line) => (line ? `${indentation}${line}` : line))
|
||||
.join('\n');
|
||||
}
|
||||
|
||||
export function splitTextIntoLines(text: string): string[] {
|
||||
validateText(text);
|
||||
return text
|
||||
.split(/[\r\n]+/);
|
||||
}
|
||||
|
||||
export function filterEmpty(texts: readonly (string | undefined | null)[]): string[] {
|
||||
return texts
|
||||
.filter((title): title is string => Boolean(title));
|
||||
}
|
||||
|
||||
function validateText(text: string): void {
|
||||
if (!isString(text)) {
|
||||
throw new Error(`text is not a string. It is: ${typeof text}\n${text}`);
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user