Skip to content

Meta: use decodeHTMLStrict instead of decodeHTML5 #652

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
nleush merged 2 commits into from
Apr 30, 2026
Merged

Meta: use decodeHTMLStrict instead of decodeHTML5 #652

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
2724623
meta: use `decodeHTMLStrict` instead of `decodeHTML5`
nleush Apr 30, 2026
d12f422
replace all `decodeHTML5` with `decodeHTMLStrict`
nleush Apr 30, 2026
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
10 changes: 5 additions & 5 deletions lib/plugins/system/meta/HTMLMetaHandler.js
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
import { decodeHTML5 } from 'entities';
import { decodeHTMLStrict } from 'entities';
import * as url from 'url';
import * as utils from '../../../utils.js';
import { ldParser } from './ld-json.js';
Expand Down Expand Up @@ -57,7 +57,7 @@ HTMLMetaHandler.prototype.onopentag = function(name, attributes) {
if (tagName) {

if (/&[^;]+;/i.test(tagName)) {
tagName = decodeHTML5(tagName);
tagName = decodeHTMLStrict(tagName);
}
var propertyParts = tagName.split(/(?::|\.)/);

Expand Down Expand Up @@ -98,7 +98,7 @@ HTMLMetaHandler.prototype.onopentag = function(name, attributes) {
var refresh = metaTag.content && metaTag.content.match(/url=(?:'|")?([^'"]+)(?:'|")?/i);

if (refresh) {
this._refresh = decodeHTML5(refresh[1]);
this._refresh = decodeHTMLStrict(refresh[1]);
}

} else if (metaTag.name == "description") {
Expand Down Expand Up @@ -265,11 +265,11 @@ HTMLMetaHandler.prototype._finalMerge = function(tag) {
if (typeof(obj[k]) == 'string'){
// decode HTML entities after decoding the charset
// otherwise we would end up with a string with mixed encoding
obj[k] = decodeHTML5(encodeText(that._charset, obj[k]));
obj[k] = decodeHTMLStrict(encodeText(that._charset, obj[k]));

if (k === 'href') {
try {
// Process 'href' after decodeHTML5.
// Process 'href' after decodeHTMLStrict.
var href = obj[k];
href = href.replace(/(\r\n|\n|\r)/gm,"");
href = url.resolve(that._uri, href);
Expand Down
10 changes: 5 additions & 5 deletions plugins/domains/dailymail.com/dailymail.video.js
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
import { decodeHTML5 } from 'entities';
import { decodeHTMLStrict } from 'entities';

export default {

Expand All @@ -13,15 +13,15 @@ export default {

if ($player.length == 1) {
return {
dailymailVideo: JSON.parse(decodeHTML5($player.attr('data-opts')))
dailymailVideo: JSON.parse(decodeHTMLStrict($player.attr('data-opts')))
}
}
},

getMeta: function(dailymailVideo, decode) {
return {
title: decodeHTML5(decode(dailymailVideo.title)),
description: decodeHTML5(decode(dailymailVideo.descr))
title: decodeHTMLStrict(decode(dailymailVideo.title)),
description: decodeHTMLStrict(decode(dailymailVideo.descr))
}
},

Expand All @@ -48,4 +48,4 @@ export default {
"https://www.dailymail.com/video/news/video-2895505/SVB-members-sets-bank-culture-apart-others.html",
"https://www.dailymail.com/video/news/video-3639123/Trump-says-expects-bomb-Iran-ceasefire-deal-ends.html",
]
};
};
4 changes: 2 additions & 2 deletions plugins/domains/google.com/docs.google.com.js
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
import { decodeHTML5 } from 'entities';
import { decodeHTMLStrict } from 'entities';

export default {

Expand Down Expand Up @@ -132,7 +132,7 @@ export default {

var key = $el.attr('itemprop');
if (key) {
var value = decodeHTML5(decode($el.attr('content') || $el.attr('href')));
var value = decodeHTMLStrict(decode($el.attr('content') || $el.attr('href')));
result[key] = value;
}
});
Expand Down
4 changes: 2 additions & 2 deletions plugins/links/embedURL/embedURL.js
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
import { decodeHTML5 } from 'entities';
import { decodeHTMLStrict } from 'entities';

export default {

Expand Down Expand Up @@ -55,7 +55,7 @@ export default {

var key = $el.attr('itemprop');
if (key) {
var value = decodeHTML5(decode($el.attr('content') || $el.attr('href')));
var value = decodeHTMLStrict(decode($el.attr('content') || $el.attr('href')));
result[key] = value;
}
});
Expand Down
4 changes: 2 additions & 2 deletions plugins/meta/description-from-p-tag.js
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
import { decodeHTML5 } from 'entities';
import { decodeHTMLStrict } from 'entities';

export default {

Expand All @@ -11,7 +11,7 @@ export default {
cheerio("body p").each(function() {
var $p = cheerio(this);
if ($p.children("label, input, button, div, script, span").length === 0 && !$p.parents("noscript, header,#header,[role='banner']").length) {
var someText = decodeHTML5(decode($p.text()));
var someText = decodeHTMLStrict(decode($p.text()));
var requiredLimit = Number.isInteger(__allowPTagDescription) ? __allowPTagDescription : 64;
if (someText.length > requiredLimit) {
description = someText;
Expand Down
Loading