Skip to content

Encode html entities for attribute updates #406

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
May 3, 2020
Merged

Encode html entities for attribute updates #406

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
31c9ef6
Add failing test
s0ph1e May 3, 2020
ae6e64c
Use html entity escape for attrs, add test
s0ph1e May 3, 2020
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
4 changes: 3 additions & 1 deletion lib/resource-handler/html/html-source-element.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,7 +38,9 @@ class HtmlSourceElement {
* @param {string} newData
*/
setData (newData) {
this.rule.attr ? this.el.attr(this.rule.attr, newData) : this.el.text(newData);
// todo: encode can be removed after https://github.com/cheeriojs/cheerio/issues/957 fixed
const escapedData = utils.encodeHtmlEntities(newData);
this.rule.attr ? this.el.attr(this.rule.attr, escapedData) : this.el.text(newData);
}

removeIntegrityCheck () {
Expand Down
5 changes: 5 additions & 0 deletions lib/utils/index.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -146,6 +146,10 @@ function decodeHtmlEntities (text) {
return typeof text === 'string' ? htmlEntities.decode(text) : '';
}

function encodeHtmlEntities (text) {
return typeof text === 'string' ? htmlEntities.escape(text) : '';
}

function clone (obj) {
return Object.assign({}, obj);
}
Expand Down Expand Up @@ -188,6 +192,7 @@ module.exports = {
getTypeByMime,
getTypeByFilename,
decodeHtmlEntities,
encodeHtmlEntities,
clone,
extend,
union,
Expand Down
14 changes: 11 additions & 3 deletions ...ities-in-url/html-entities-in-url.test.js → ...ional/html-entities/html-entities.test.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,7 @@ var scrape = require('../../../index');
var testDirname = __dirname + '/.tmp';
var mockDirname = __dirname + '/mocks';

describe('Functional: html entities in url', function() {
describe('Functional: html entities', function() {

beforeEach(function() {
nock.cleanAll();
Expand All @@ -27,7 +27,9 @@ describe('Functional: html entities in url', function() {
// /fonts?family=Myriad&v=2 => /fonts?family=Myriad&v=2
nock('http://example.com/').get('/fonts?family=Myriad&v=2').reply(200, 'fonts.css', {'content-type': 'text/css'});
// /?a=1&style-attr.png => /?a=1&style-attr.png
nock('http://example.com/').get('/style-attr.png?a=1&style-attr.png').reply(200, 'style-attr.png', {'content-type': 'text/css'});
nock('http://example.com/').get('/style-attr.png?a=1&style-attr.png').reply(200, 'style-attr.png');
// "style-attr2.png" => style-attr2.png
nock('http://example.com/').get('/style-attr2.png').reply(200, 'style-attr2.png');
// /?a=1&b=2 => /?a=1&b=2
nock('http://example.com/').get('/img.png?a=1&b=2').reply(200, 'img.png');
// /test?b=2&c=3&d=4 => /test?b=2&c=3&d=4
Expand Down Expand Up @@ -56,10 +58,16 @@ describe('Functional: html entities in url', function() {
fs.existsSync(testDirname + '/local/fonts.css').should.be.eql(true);
should(fs.readFileSync(testDirname + '/local/fonts.css').toString()).be.eql('fonts.css');

should(indexHtml).containEql('background: url(\'local/style-attr.png\')');
// single quote (') replaced with ' in attribute
should(indexHtml).containEql('background: url('local/style-attr.png')');
fs.existsSync(testDirname + '/local/style-attr.png').should.be.eql(true);
should(fs.readFileSync(testDirname + '/local/style-attr.png').toString()).be.eql('style-attr.png');

// double quote (") replaced with " in attribute
should(indexHtml).containEql('background: url("local/style-attr2.png")');
fs.existsSync(testDirname + '/local/style-attr2.png').should.be.eql(true);
should(fs.readFileSync(testDirname + '/local/style-attr2.png').toString()).be.eql('style-attr2.png');

should(indexHtml).containEql('img src="local/img.png');
fs.existsSync(testDirname + '/local/img.png').should.be.eql(true);
should(fs.readFileSync(testDirname + '/local/img.png').toString()).be.eql('img.png');
Expand Down
1 change: 1 addition & 0 deletions ...nal/html-entities-in-url/mocks/index.html → ...functional/html-entities/mocks/index.html
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,7 @@
</head>
<body>
<div style="background: url('http://example.com/style-attr.png?a=1&amp;style-attr.png')"></div>
<div style="background: url(&quot;http://example.com/style-attr2.png&quot;)"></div>
<img src="http://example.com/img.png?a=1&amp;b=2" />
<a href="?b=2&amp;c=3&amp;d=4">test</a>
</body>
Expand Down
0 ...onal/html-entities-in-url/mocks/style.css → .../functional/html-entities/mocks/style.css
View file
Open in desktop
File renamed without changes.
23 changes: 23 additions & 0 deletions test/unit/resource-handler/html.test.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -267,4 +267,27 @@ describe('ResourceHandler: Html', () => {
resource.getText().should.not.containEql('integrity="sha256-X+Q/xqnlEgxCczSjjpp2AUGGgqM5gcBzhRQ0p+EAUEk="');
});
});

it('should use html entities for updated attributes', () => {
const sources = [
{ selector: '[style]', attr: 'style' },
];
downloadChildrenPaths.onFirstCall().resolves('width: 300px; height: 300px; background-image:url("./images/cat.jpg")');
htmlHandler = new HtmlHandler({sources}, {downloadChildrenPaths});

const html = `
<html>
<body>
<div style="width: 300px; height: 300px; background-image:url(&quot;http://example.com/cat.jpg&quot;)"></div>
</body>
</html>
`;

const resource = new Resource('http://example.com', 'index.html');
resource.setText(html);

return htmlHandler.handle(resource).then(() => {
resource.getText().should.containEql('style="width: 300px; height: 300px; background-image:url(&quot;./images/cat.jpg&quot;)"');
});
});
});