Skip to content

fix: normalize unicode chars in title matching for artifact URL lookup #12

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
vahldiek merged 1 commit into from
May 15, 2026
Merged

fix: normalize unicode chars in title matching for artifact URL lookup #12

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
17 changes: 12 additions & 5 deletions src/assets/js/reprodb-profile-page.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,6 +24,13 @@
return u;
}

function normalizeTitle(t) {
return t.replace(/\.+$/, '').toLowerCase()
.replace(/[\u2013\u2014]/g, '-')
.replace(/[\u2018\u2019\u2032]/g, "'")
.replace(/[\u201c\u201d]/g, '"');
}

function availTag(url) {
if (!url) return '';
var n = url.replace(/\/+$/, '');
Expand Down Expand Up @@ -89,7 +96,7 @@
columns: [
{ title: '#', formatter: 'rownum', width: 50, headerSort: false },
{ title: 'Title', field: 'title', formatter: function(cell) {
var d = cell.getData(), t = d.title.replace(/\.+$/, '').toLowerCase(), u = artifactUrlMap[t] || '';
var d = cell.getData(), t = normalizeTitle(d.title), u = artifactUrlMap[t] || '';
return (u ? '<a href="' + escHtml(u) + '" target="_blank" rel="noopener">' + escHtml(d.title) + '</a>' : escHtml(d.title)) + availTag(u);
}, headerSort: false },
{ title: 'Conference', field: 'conference' },
Expand Down Expand Up @@ -255,8 +262,8 @@
affProfiles.forEach(function(p) {
(p.papers || []).forEach(function(paper) {
if (!paperMap[paper.title]) {
var t = paper.title.replace(/\.+$/, '');
paperMap[paper.title] = { title: paper.title, authors: [], conference: paper.conference, year: paper.year, badges: paper.badges, url: artifactUrlMap[t.toLowerCase()] || '' };
var t = normalizeTitle(paper.title);
paperMap[paper.title] = { title: paper.title, authors: [], conference: paper.conference, year: paper.year, badges: paper.badges, url: artifactUrlMap[t] || '' };
}
paperMap[paper.title].authors.push(p.name);
});
Expand Down Expand Up @@ -451,11 +458,11 @@
citedArtifactsMap = res[2] || {};
authorRankHistory = res[3] || [];

// Build artifact URL map (lowercase keys for case-insensitive lookup)
// Build artifact URL map (normalizeTitle for case+unicode-insensitive lookup)
(res[4] || []).forEach(function(a) {
var urls = a.artifact_urls || [];
var u = urls.length ? urls[0] : (a.artifact_url || a.repository_url || '');
if (a.title && u) artifactUrlMap[a.title.replace(/\.+$/, '').toLowerCase()] = normalizeUrl(u);
if (a.title && u) artifactUrlMap[normalizeTitle(a.title)] = normalizeUrl(u);
});

// Build paper index
Expand Down