Skip to content

chore: replace cheerio with htmlparser2 #1176

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

Open
trivikr wants to merge 2 commits into
base: main
Choose a base branch
from
Open

chore: replace cheerio with htmlparser2 #1176

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
28d2e21
chore: replace cheerio with htmlparser2
trivikr Aug 29, 2026
eac8cb9
test: improve links coverage
trivikr Aug 31, 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
42 changes: 27 additions & 15 deletions lib/links.js
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
import * as cheerio from 'cheerio';
import { Parser } from 'htmlparser2';

const FIXES_RE = /(Close[ds]?|Fix(e[ds])?|Resolve[sd]?)\s*:\s*(\S+)/mgi;
const FIX_RE = /(Close[ds]?|Fix(e[ds])?|Resolve[sd]?)\s*:\s*(\S+)/i;
Expand All @@ -13,7 +13,26 @@ export class LinkParser {
constructor(owner, repo, html) {
this.owner = owner;
this.repo = repo;
this.$ = cheerio.load(html);
this.text = '';
this.links = [];

let currentLink;
const parser = new Parser({
onopentag: (name, attributes) => {
if (name === 'a') {
currentLink = { href: attributes.href, text: '' };
this.links.push(currentLink);
}
},
ontext: (text) => {
this.text += text;
if (currentLink) currentLink.text += text;
},
onclosetag: (name) => {
if (name === 'a') currentLink = undefined;
}
});
parser.end(html);
}

getFixesUrlsFromArray(arr) {
Expand Down Expand Up @@ -55,32 +74,25 @@ export class LinkParser {
// Do this so we can reliably get the correct url.
// Otherwise, the number could reference a PR or an issue.
getUrlFromOP(ref) {
const as = this.$('a');
const links = as.map((i, el) => this.$(el)).get();
for (const link of links) {
const text = link.text();
if (text === ref) {
const href = link.attr('href');
if (href) return href;
for (const link of this.links) {
if (link.text === ref) {
if (link.href) return link.href;
}
}
}

getFixes() {
const text = this.$.text();
const fixes = text.match(FIXES_RE) || [];
const fixes = this.text.match(FIXES_RE) || [];
return this.getFixesUrlsFromArray(fixes);
}

getRefs() {
const text = this.$.text();
const refs = text.match(REFS_RE) || [];
const refs = this.text.match(REFS_RE) || [];
return this.getRefsUrlsFromArray(refs);
}

getAltPrUrl() {
const text = this.$.text();
const refs = text.match(PR_RE) || [];
const refs = this.text.match(PR_RE) || [];
return this.getPRUrlsFromArray(refs);
}
}
Expand Down
Loading
Loading