thegeneralist01/archivr
1
Fork 0
mirror of https://github.com/thegeneralist01/archivr synced 2026-07-21 18:55:36 +02:00
Code Issues Activity

feat: suppress rendered media attachment URLs from tweet text

Browse source 
renderTweetTextJSX now accepts skipSpans=[] as third param.
Skip-span boundaries are added to the pts split set so a trailing
media t.co inside a plain segment still gets isolated and suppressed—
not re-linked by linkifyText. Early return only when both anns and
skipSpans are empty.

TweetCard computes mediaSkipSpans after building photos/videoItems:
for each rawMedia item whose src resolved (photo src match; any video),
resolveEntityBounds(m, ft, m.url) gives the precise [s,e] span using
indices/fromIndex first, indexOf fallback—then the span is passed to
renderTweetTextJSX so the t.co attachment URL is silently dropped.
This commit is contained in:
TheGeneralist 2026-07-12 16:09:35 +02:00
parent 1589eb68b5
commit 46a5251316
Signed by: thegeneralist01
SSH key fingerprint: SHA256:pp9qddbCNmVNoSjevdvQvM5z0DHN7LTa8qBMbcMq/R4
3 changed files with 44 additions and 16 deletions
Download patch file Download diff file Expand all files Collapse all files

22
crates/archivr-server/static/assets/index-CBWT1bsB.js → crates/archivr-server/static/assets/index-Gm5awz10.js
View file

File diff suppressed because one or more lines are too long

2
crates/archivr-server/static/index.html
View file

@ -4,7 +4,7 @@
<meta charset="utf-8" />
<meta name="viewport" content="width=device-width, initial-scale=1" />
<title>Archivr</title>
<script type="module" crossorigin src="/assets/index-CBWT1bsB.js"></script>
<script type="module" crossorigin src="/assets/index-Gm5awz10.js"></script>
<link rel="stylesheet" crossorigin href="/assets/index-C89vW3ol.css">
</head>
<body>

36
frontend/src/components/TweetPreview.jsx
View file

@ -523,25 +523,37 @@ function linkifyText(text, linkStyle) {
return parts;
}
function renderTweetTextJSX(fullText, entities) {
function renderTweetTextJSX(fullText, entities, skipSpans = []) {
if (!fullText) return null;
const anns = [
...(entities.urls || []).map(u => normalizeUrlAnn(u, fullText)).filter(Boolean),
...(entities.user_mentions || []).map(m => normalizeMentionAnn(m, fullText)).filter(Boolean),
];
if (anns.length === 0) return linkifyText(decodeEnt(fullText), S.link);
// If there are no annotations and no spans to skip, fast path.
if (anns.length === 0 && skipSpans.length === 0) return linkifyText(decodeEnt(fullText), S.link);
const pts = new Set([0, fullText.length]);
for (const a of anns) {
if (a.s >= 0 && a.s <= fullText.length) pts.add(a.s);
if (a.e >= 0 && a.e <= fullText.length) pts.add(a.e);
}
// Skip-span boundaries MUST be in pts so a media t.co that lives inside a
// larger plain-text segment still gets split out and suppressed.
for (const [ss, se] of skipSpans) {
if (ss >= 0 && ss <= fullText.length) pts.add(ss);
if (se >= 0 && se <= fullText.length) pts.add(se);
}
const isSkipped = (s, e) => skipSpans.some(([ss, se]) => ss <= s && se >= e);
const sorted = [...pts].sort((a, b) => a - b);
return sorted.slice(0, -1).map((s, i) => {
const e = sorted[i + 1];
// Suppress spans whose range is covered by a rendered media item.
if (isSkipped(s, e)) return null;
const seg = fullText.slice(s, e);
const active = anns.filter(a => a.s <= s && a.e >= e);
@ -570,7 +582,7 @@ function renderTweetTextJSX(fullText, entities) {
}
return <span key={i}>{linkifyText(decodeEnt(seg), S.link)}</span>;
});
}).filter(n => n !== null);
}
// ── Article inline text renderer ───────────────────────────────────────────────
@ -1025,6 +1037,7 @@ function TweetCard({ tweet, isInThread, isLast, artifactMap }) {
const showConnector = isInThread && !isLast;
const isQT = tweet.is_quote_status === true;
const rowStyle = isInThread ? S.tweetRowThread : S.tweetRow;
const ft = tweet.full_text || '';
// Build resolved media lists first; skip the grid entirely if every item resolves to null.
const rawMedia = (tweet.extended_entities?.media?.length
@ -1049,6 +1062,21 @@ function TweetCard({ tweet, isInThread, isLast, artifactMap }) {
}
}
// Suppress media attachment t.co links from the tweet text when the media
// actually rendered. Uses resolveEntityBounds (prefers indices/fromIndex,
// falls back to indexOf) so the span is always precise.
const mediaSkipSpans = [];
for (const m of rawMedia) {
if (!m.url) continue;
const rendered =
m.type === 'photo'
? photos.some(p => p.src === resolveUrl(m.local_path, m.media_url_https, artifactMap))
: videoItems.length > 0;
if (!rendered) continue;
const b = resolveEntityBounds(m, ft, m.url);
if (b) mediaSkipSpans.push([b.s, b.e]);
}
return (
<>
{lightboxIdx !== null && (
@ -1080,7 +1108,7 @@ function TweetCard({ tweet, isInThread, isLast, artifactMap }) {
</div>
<div style={S.tweetText}>
{renderTweetTextJSX(tweet.full_text || '', entities)}
{renderTweetTextJSX(ft, entities, mediaSkipSpans)}
</div>
{photos.length > 0 && (