aboutsummaryrefslogtreecommitdiffstats
path: root/names/translate.js
diff options
context:
space:
mode:
authorAdam Soltys <[email protected]>2026-10-09 10:36:39 -0700
committerAdam Soltys <[email protected]>2026-10-09 10:36:39 -0700
commit41d7b9d4e5d0e10cdac708d9c9cd4838e47240ec (patch)
tree767d6dffc8dc14b90c368606d8fc39c68b050fb2 /names/translate.js
parentad028dd1c61e41913e4628046b96bf162bc4ba4a (diff)
downloadcoinosv3-41d7b9d4e5d0e10cdac708d9c9cd4838e47240ec.tar.gz
coinosv3-41d7b9d4e5d0e10cdac708d9c9cd4838e47240ec.zip
Translation: posts in another language are shown in yours — "Translated from Spanish · Show original" under the words, automatic by default for posts the language guess calls foreign (Settings → Nostr → Translation switches it off and leaves a Translate link instead), and ⋯ → Translate for any post. The browser's on-device Translator does it when the language pair is already installed (desktop Chrome); otherwise the registrar's new POST /translate (names/translate.js): a cached, 4-at-a-time front for a LibreTranslate container on cs (names/compose-libretranslate.yml, v1.9.6, 32 languages; none for sw/mr/ta/te, so those readers get no offer). Links, nostr: mentions, :emoji:, #tags and long codes are never sent to the model — only the prose between them, batched in one call (src/translate-split.js, shared). Translations are remembered (coinos-translations, 300). tools/translate-test.js
Co-Authored-By: Claude Opus 5.5 <[email protected]> Claude-Session: https://claude.ai/code/session_01Vps2H27rhbG9ZqseGfMrc3
Diffstat (limited to 'names/translate.js')
-rw-r--r--names/translate.js82
1 files changed, 82 insertions, 0 deletions
diff --git a/names/translate.js b/names/translate.js
new file mode 100644
index 0000000..7d6181d
--- /dev/null
+++ b/names/translate.js
@@ -0,0 +1,82 @@
+// Post translation for coinos v3: a thin, cached front for a LibreTranslate
+// container on the same docker network. Notes are public, so nothing private
+// passes through here; the cache keys on the text itself, so a popular post
+// is translated once whoever asks.
+import { createHash } from 'node:crypto';
+import { splitProse, hasWords, translatePieces } from '../src/translate-split.js';
+
+const LT = process.env.LT_URL || 'http://libretranslate:5000';
+const MAX_CHARS = 5000;
+const CACHE_MAX = 20000;
+const BUSY_MAX = 4; // LibreTranslate is CPU-bound: a few at once, the rest wait their turn
+const cache = new Map(); // sha256(target|text) -> { text, source }
+let busy = 0;
+const waiting = [];
+let langs = null, langsAt = 0;
+
+async function slot() {
+ if (busy < BUSY_MAX) { busy++; return; }
+ await new Promise((r) => waiting.push(r));
+ busy++;
+}
+function release() { busy--; const next = waiting.shift(); if (next) next(); }
+
+// The languages the container has models for: { code: [targets] }
+export async function languages() {
+ if (langs && Date.now() - langsAt < 3600_000) return langs;
+ const r = await fetch(LT + '/languages', { signal: AbortSignal.timeout(5000) });
+ if (!r.ok) throw new Error('languages ' + r.status);
+ const list = await r.json();
+ langs = Object.fromEntries(list.map((l) => [l.code, l.targets || []]));
+ if (langs['zh-Hans']) langs.zh = langs['zh-Hans']; // the app says 'zh'
+ langsAt = Date.now();
+ return langs;
+}
+
+// The app's locale codes ↔ LibreTranslate's ('zh' is Simplified there).
+const norm = (c) => String(c || '').toLowerCase().split(/[-_]/)[0];
+const toLt = (c) => (c === 'zh' ? 'zh-Hans' : c);
+
+export async function translate(text, target, source = 'auto') {
+ text = String(text || '');
+ target = norm(target);
+ source = source && source !== 'auto' ? norm(source) : 'auto';
+ if (!text.trim()) return { text: '', source };
+ if (text.length > MAX_CHARS) throw Object.assign(new Error('too long'), { status: 413 });
+ const have = await languages();
+ if (!have[toLt(target)]) throw Object.assign(new Error('unsupported language'), { status: 422 });
+ const key = createHash('sha256').update(target + '|' + source + '|' + text).digest('hex');
+ const hit = cache.get(key);
+ if (hit) { cache.delete(key); cache.set(key, hit); return hit; }
+ const prose = splitProse(text).filter((p) => p.prose && hasWords(p.prose));
+ if (!prose.length) return { text, source: source === 'auto' ? null : source };
+ await slot();
+ try {
+ const call = async (path, body) => {
+ const r = await fetch(LT + path, {
+ method: 'POST', headers: { 'content-type': 'application/json' },
+ body: JSON.stringify(body), signal: AbortSignal.timeout(30_000),
+ });
+ const out = await r.json().catch(() => ({}));
+ if (!r.ok) throw Object.assign(new Error(out.error || path + ' ' + r.status), { status: r.status === 400 ? 422 : 502 });
+ return out;
+ };
+ let from = source, confidence = null;
+ if (from === 'auto') {
+ const d = await call('/detect', { q: prose.map((p) => p.prose).join('\n') });
+ from = norm(d[0]?.language) || null;
+ confidence = d[0]?.confidence ?? null;
+ if (!from) throw Object.assign(new Error('unknown language'), { status: 422 });
+ }
+ if (from === target) return { text, source: from, confidence };
+ if (!have[toLt(from)]) throw Object.assign(new Error('unsupported language'), { status: 422 });
+ const translated = await translatePieces(text, async (qs) => {
+ const r = await call('/translate', { q: qs, source: toLt(from), target: toLt(target), format: 'text' });
+ return Array.isArray(r.translatedText) ? r.translatedText : [r.translatedText];
+ });
+ const out = { text: translated, source: from, confidence };
+ cache.set(key, out);
+ if (cache.size > CACHE_MAX) cache.delete(cache.keys().next().value);
+ return out;
+ } finally { release(); }
+}