2024-06-19 11:54:34 +02:00
|
|
|
import htmlUtils, { extractHtmlBody, htmlDocIsImageOnly, removeWrappingParagraphAndTrailingEmptyElements } from './htmlUtils';
|
2022-01-15 18:53:24 +02:00
|
|
|
|
|
|
|
|
describe('htmlUtils', () => {
|
|
|
|
|
|
|
|
|
|
test('should strip off HTML', () => {
|
|
|
|
|
const testCases = [
|
|
|
|
|
[
|
|
|
|
|
'',
|
|
|
|
|
'',
|
|
|
|
|
],
|
|
|
|
|
[
|
|
|
|
|
'<b>test</b>',
|
|
|
|
|
'test',
|
|
|
|
|
],
|
|
|
|
|
[
|
|
|
|
|
'Joplin®',
|
|
|
|
|
'Joplin®',
|
|
|
|
|
],
|
|
|
|
|
[
|
|
|
|
|
'<b>test</b>',
|
|
|
|
|
'<b>test</b>',
|
|
|
|
|
],
|
|
|
|
|
];
|
|
|
|
|
|
|
|
|
|
for (const t of testCases) {
|
|
|
|
|
const [input, expected] = t;
|
|
|
|
|
const actual = htmlUtils.stripHtml(input);
|
|
|
|
|
expect(actual).toBe(expected);
|
|
|
|
|
}
|
|
|
|
|
});
|
|
|
|
|
|
2023-08-21 19:37:33 +02:00
|
|
|
test('should extract the HTML body', () => {
|
|
|
|
|
const testCases: [string, string][] = [
|
|
|
|
|
[
|
|
|
|
|
'Just <b>testing</b>',
|
|
|
|
|
'Just <b>testing</b>',
|
|
|
|
|
],
|
|
|
|
|
[
|
|
|
|
|
'',
|
|
|
|
|
'',
|
|
|
|
|
],
|
|
|
|
|
[
|
|
|
|
|
'<html><head></head><meta bla><body>Here is the body<img src="test.png"/></body></html>',
|
|
|
|
|
'Here is the body<img src="test.png"/>',
|
|
|
|
|
],
|
|
|
|
|
];
|
|
|
|
|
|
|
|
|
|
for (const [input, expected] of testCases) {
|
|
|
|
|
const actual = extractHtmlBody(input);
|
|
|
|
|
expect(actual).toBe(expected);
|
|
|
|
|
}
|
|
|
|
|
});
|
|
|
|
|
|
2023-11-17 18:47:05 +02:00
|
|
|
test('should tell if an HTML document is an image only', () => {
|
|
|
|
|
const testCases: [string, boolean][] = [
|
|
|
|
|
[
|
|
|
|
|
// This is the kind of HTML that's pasted when copying an image from Chrome
|
|
|
|
|
'<meta charset=\'utf-8\'>\n<img src="https://example.com/img.png"/>',
|
|
|
|
|
true,
|
|
|
|
|
],
|
|
|
|
|
[
|
|
|
|
|
'',
|
|
|
|
|
false,
|
|
|
|
|
],
|
|
|
|
|
[
|
|
|
|
|
'<img src="https://example.com/img.png"/>',
|
|
|
|
|
true,
|
|
|
|
|
],
|
|
|
|
|
[
|
|
|
|
|
'<img src="https://example.com/img.png"/><img src="https://example.com/img.png"/>',
|
|
|
|
|
false,
|
|
|
|
|
],
|
|
|
|
|
[
|
|
|
|
|
'<img src="https://example.com/img.png"/><p>Some text</p>',
|
|
|
|
|
false,
|
|
|
|
|
],
|
|
|
|
|
[
|
|
|
|
|
'<img src="https://example.com/img.png"/> Some text',
|
|
|
|
|
false,
|
|
|
|
|
],
|
|
|
|
|
];
|
|
|
|
|
|
|
|
|
|
for (const [input, expected] of testCases) {
|
|
|
|
|
const actual = htmlDocIsImageOnly(input);
|
|
|
|
|
expect(actual).toBe(expected);
|
|
|
|
|
}
|
|
|
|
|
});
|
|
|
|
|
|
2024-06-19 11:54:34 +02:00
|
|
|
it.each([
|
|
|
|
|
['<p>Test</p><div></div>', 'Test'],
|
|
|
|
|
['<p>Testing</p><p>A test</p>', '<p>Testing</p><p>A test</p>'],
|
|
|
|
|
['<p>Testing</p><hr/>', '<p>Testing</p><hr/>'],
|
|
|
|
|
['<p>Testing</p><div style="border: 2px solid red;"></div>', '<p>Testing</p><div style="border: 2px solid red;"></div>'],
|
|
|
|
|
['<p>Testing</p><style onload=""></style>', 'Testing'],
|
|
|
|
|
['<p>is</p>\n<style onload="console.log(\'test\')"></style>', 'is\n'],
|
|
|
|
|
])('should remove empty elements (case %#)', (before, expected) => {
|
|
|
|
|
expect(removeWrappingParagraphAndTrailingEmptyElements(before)).toBe(expected);
|
|
|
|
|
});
|
2022-01-15 18:53:24 +02:00
|
|
|
});
|
