localewarden 0.1.1 → 0.3.0

package/dist/checks.js

@@ -1,6 +1,8 @@
 import { placeholderRegExp, placeholderSignature, placeholdersMatch } from './placeholders.js';
 import { GENDERED_FORMS, NO_AMPERSAND_LANGUAGES, SENTENCE_CASE_LANGUAGES, formalityRule, registerFor, withoutQuotedSpeech, } from './style.js';
-import { baseLanguage, escapeRegExp } from './util.js';
+import { PluginHost } from './plugins.js';
+import { Scope } from './scope.js';
+import { baseLanguage, escapeRegExp, isTraditionalChinese } from './util.js';
 export const CHECKS = [
     'placeholder',
     'unsafe',
@@ -8,6 +10,7 @@ export const CHECKS = [
     'markup',
     'years',
     'formality',
+    'length',
     'titlecase',
     'ampersand',
     'glossary',
@@ -21,17 +24,39 @@ export const FIXABLE_CHECKS = new Set([
     'markup',
     'years',
     'formality',
+    'length',
     'titlecase',
     'ampersand',
     'glossary',
     'partial',
 ]);
+/** Errors break the software (and fail `localewarden check`); everything else is a warning. */
+export const isError = (issue) => issue.severity === 'error' || ERROR_CHECKS.has(issue.check);
+/** Whether `--fix-flagged` may ask the model to fix the issue. */
+export const isFixable = (issue) => issue.fixable ?? FIXABLE_CHECKS.has(issue.check);
 export class Checker {
     config;
     placeholderRe;
-    constructor(config) {
+    scope;
+    /** Words of termNotes and doNotTranslate: terms a translation may keep in the source language. */
+    keptWords;
+    plugins;
+    constructor(config, plugins = new PluginHost()) {
         this.config = config;
+        this.plugins = plugins;
         this.placeholderRe = placeholderRegExp(config.placeholders);
+        this.scope = new Scope(config);
+        this.keptWords = new Set([...Object.keys(config.termNotes), ...config.doNotTranslate].flatMap(term => term.toLowerCase().split(/[^\p{L}]+/u)).filter(Boolean));
+    }
+    /** The text without doNotTranslate names, which stay the same in every language. */
+    withoutNames(text) {
+        return this.config.doNotTranslate.reduce((value, name) => value.split(name).join(' '), text);
+    }
+    /** "62 characters, limit 60", or null. */
+    tooLong(key, text) {
+        const max = this.scope.maxLength(key);
+        const length = [...text].length;
+        return max !== undefined && length > max ? `${length} characters, limit ${max}` : null;
     }
     get englishSource() {
         return baseLanguage(this.config.sourceLanguage) === 'en';
@@ -43,7 +68,7 @@ export class Checker {
         return `source has [${placeholderSignature(source, this.placeholderRe)}], got [${placeholderSignature(text, this.placeholderRe)}]`;
     }
     /** All issues of one translated string. */
-    checkString(lang, key, source, text) {
+    checkString(lang, key, source, text, file = '') {
         const issues = [];
         const add = (check, note) => issues.push({ check, note });
         const base = baseLanguage(lang);
@@ -88,16 +113,22 @@ export class Checker {
             this.config.sentenceCase &&
             SENTENCE_CASE_LANGUAGES.has(base) &&
             isEnglishTitleCase(source)) {
-            const capitals = midCapitals(text, source, this.config.doNotTranslate);
+            const capitals = midCapitals(text, source, this.config.doNotTranslate, lang);
             if (capitals.length >= (source.trim().split(/\s+/).length <= 3 ? 1 : 2)) {
                 add('titlecase', `capitalised: ${capitals.join(' ')}`);
             }
         }
+        const long = this.tooLong(key, text);
+        if (long)
+            add('length', long);
         const ampersands = (value) => value.split(' & ').length - 1;
         if (NO_AMPERSAND_LANGUAGES.has(base) && ampersands(text) > ampersands(source))
             add('ampersand');
-        if (isUnchangedProse(source, text, this.placeholderRe))
+        if (isUnchangedProse(this.withoutNames(source), this.withoutNames(text), this.placeholderRe))
             add('untranslated');
+        const short = muchShorter(lang, source, text);
+        if (short)
+            add('partial', short);
         if (this.englishSource && text !== source) {
             const copied = sourceRun(source, text);
             if (copied)
@@ -105,13 +136,16 @@ export class Checker {
             const lead = !copied ? sourceBoldLeadIn(source, text, this.config.doNotTranslate) : null;
             if (lead)
                 add('partial', `bold lead-in still in the source language: "${lead}"`);
-            const mixed = !copied && !lead ? englishInNativeScript(lang, source, text, this.placeholderRe) : null;
+            const mixed = !copied && !lead ? englishInNativeScript(lang, source, text, this.placeholderRe, this.keptWords) : null;
             if (mixed)
                 add('partial', mixed);
             if (droppedHedge(lang, source, text)) {
                 add('partial', 'hedge dropped: the source says "tend to", the translation states it as certain');
             }
         }
+        for (const issue of this.plugins.checks({ lang, key, file, source, text })) {
+            issues.push({ severity: 'warning', fixable: false, ...issue });
+        }
         return issues;
     }
     /**
@@ -121,13 +155,17 @@ export class Checker {
      *   soft: likely loss (tag count, missing year, source words left in). Retried once, then
      *         accepted; `localewarden check` keeps reporting it.
      */
-    defect(lang, key, source, text) {
+    defect(lang, key, source, text, file = '') {
         if (!text.trim())
             return { hard: 'empty translation', soft: null };
+        // A plugin error blocks writing, like a broken placeholder.
+        const pluginError = this.plugins.checks({ lang, key, file, source, text }).find(issue => issue.severity === 'error');
+        if (pluginError)
+            return { hard: `${pluginError.check}${pluginError.note ? `: ${pluginError.note}` : ''}`, soft: null };
         const placeholders = this.placeholdersMatch(key, source, text) ? null : `placeholder mismatch: ${this.placeholderNote(source, text)}`;
         const foreign = foreignScript(this.config.sourceLanguage, source) ? null : foreignScript(lang, text);
         const links = hrefSignature(source) !== hrefSignature(text) ? `links changed: [${hrefSignature(source)}] -> [${hrefSignature(text)}]` : null;
-        const echoed = isUnchangedProse(source, text, this.placeholderRe) ? 'returned the source text unchanged' : null;
+        const echoed = isUnchangedProse(this.withoutNames(source), this.withoutNames(text), this.placeholderRe) ? 'returned the source text unchanged' : null;
         const broken = brokenMarkup(source) ? null : brokenMarkup(text);
         const boldMarkers = (value) => (value.match(/\*\*/g) ?? []).length % 2;
         const brokenBold = boldMarkers(text) === 1 && boldMarkers(source) === 0 ? 'unbalanced ** markers' : null;
@@ -135,7 +173,7 @@ export class Checker {
         const hard = placeholders ?? unsafeAdditions(source, text) ?? foreign ?? links ?? echoed ?? broken ?? brokenBold ?? droppedBullets(source, text) ?? leaked;
         const tags = tagCount(source) !== tagCount(text) ? `${tagCount(source)} tags in the source, got ${tagCount(text)}` : null;
         const copied = this.englishSource && text !== source ? sourceRun(source, text) : null;
-        return { hard, soft: hard ?? tags ?? yearDifference(source, text) ?? (copied ? `source text left in: "${copied}"` : null) };
+        return { hard, soft: hard ?? this.tooLong(key, text) ?? muchShorter(lang, source, text) ?? tags ?? yearDifference(source, text) ?? (copied ? `source text left in: "${copied}"` : null) };
     }
 }
 // ---------------------------------------------------------------------------------------
@@ -188,8 +226,25 @@ const LATIN_LANGUAGES = new Set([
 ]);
 // Latin glued to a lookalike alphabet inside one word ("Вarda": Cyrillic В + Latin arda).
 const HOMOGLYPH_WORD = /(?=\p{L}*\p{Script=Latin})(?=\p{L}*[\p{Script=Cyrillic}\p{Script=Greek}])\p{L}+/u;
+// Common characters that exist in only one of the two Chinese scripts (pairs at the same index).
+const SIMPLIFIED_ONLY = '们这说时会来对个为发过还让现实动门问间题体关点应开东头书长见认学页电话语读写买卖钱网设计习惯觉机帮爱车钟儿气无边进选择检样经验数据项结种类业务环节';
+const TRADITIONAL_ONLY = '們這說時會來對個為發過還讓現實動門問間題體關點應開東頭書長見認學頁電話語讀寫買賣錢網設計習慣覺機幫愛車鐘兒氣無邊進選擇檢樣經驗數據項結種類業務環節';
+/** Simplified characters in Traditional Chinese text, or the reverse (2+ distinct ones). */
+export function wrongChineseScript(lang, text) {
+    if (baseLanguage(lang) !== 'zh')
+        return null;
+    const traditional = isTraditionalChinese(lang);
+    const wrong = traditional ? SIMPLIFIED_ONLY : TRADITIONAL_ONLY;
+    const found = [...new Set([...text].filter(ch => wrong.includes(ch)))];
+    return found.length >= 2
+        ? `${traditional ? 'Simplified' : 'Traditional'} Chinese characters in ${lang}: ${found.slice(0, 6).join('')}`
+        : null;
+}
 /** Why `text` contains letters that cannot belong to `lang`, or null. */
 export function foreignScript(lang, text) {
+    const chinese = wrongChineseScript(lang, text);
+    if (chinese)
+        return chinese;
     const base = baseLanguage(lang);
     const native = NATIVE_SCRIPTS[base] ?? (LATIN_LANGUAGES.has(base) ? [] : null);
     if (native === null)
@@ -218,13 +273,18 @@ const unescapeEntities = (text) => text
     .replace(/&quot;|&#0*34;|&#x0*22;/gi, '"')
     .replace(/&#0*39;|&#x0*27;|&apos;/gi, "'")
     .replace(/&colon;|&#0*58;|&#x0*3a;/gi, ':');
-/** Tag names, in lower case. Numbered <0> tags (react-i18next) are placeholders, not HTML. */
-const tagNames = (html) => new Set([...html.matchAll(/<\/?([a-z][\w-]*)/gi)].map(m => m[1].toLowerCase()));
+// HTML elements, so text in angle brackets ("<minutes>", "<your name>") is not taken for markup.
+const HTML_ELEMENTS = new Set(('a abbr address area article aside audio b base bdi bdo blockquote body br button canvas caption cite code col colgroup data datalist dd del details dfn dialog div dl dt em embed fieldset figcaption figure footer form frame frameset h1 h2 h3 h4 h5 h6 head header hr html i iframe img input ins kbd label legend li link main map mark math meta meter nav noscript object ol optgroup option output p param picture pre progress q rp rt ruby s samp script section select slot small source span strong style sub summary sup svg table tbody td template textarea tfoot th thead time title tr track u ul var video wbr animate foreignobject use image set').split(' '));
+/** HTML element names, in lower case. Numbered <0> tags (react-i18next) are placeholders. */
+const tagNames = (html) => new Set([...html.matchAll(/<\/?([a-z][\w-]*)/gi)].map(m => m[1].toLowerCase()).filter(tag => HTML_ELEMENTS.has(tag)));
 const TEXT_ATTRIBUTES = new Set(['title', 'alt', 'aria-label', 'aria-description', 'placeholder']);
 /** Every attribute as "name=value" (value without quotes), in lower case. */
 const attributes = (html) => {
     const found = new Set();
-    for (const [, inner] of html.matchAll(/<[a-z][\w-]*\s([^>]*)>?/gi)) {
+    for (const [, tag, inner] of html.matchAll(/<([a-z][\w-]*)\s([^>]*)>?/gi)) {
+        // "<dakika 20)" (sw: under 20 minutes) is text, not a tag.
+        if (!HTML_ELEMENTS.has(tag.toLowerCase()))
+            continue;
         for (const [, name, v1, v2, v3] of inner.matchAll(/([^\s"'=<>\/]+)(?:\s*=\s*(?:"([^"]*)"|'([^']*)'|([^\s"'>]+)))?/g)) {
             const attr = name.toLowerCase();
             // Text attributes are translated along with the visible text; only their presence counts.
@@ -234,7 +294,10 @@ const attributes = (html) => {
     }
     return found;
 };
-const DANGEROUS_URL = /(?:javascript|vbscript|data)\s*:/gi;
+// Script URLs in a link target or Markdown link. Plain "data:" in prose is a word (pt/it "date:").
+const DANGEROUS_URL = /(?:(?:href|src|action|formaction|xlink:href|poster|background)\s*=\s*["']?|\]\()\s*(?:javascript|vbscript|data)\s*:/gi;
+// Formatting a translator may add for emphasis or a title (no attributes): a markup warning, not a risk.
+const HARMLESS_TAGS = new Set(['br', 'i', 'b', 'em', 'strong', 'u', 's', 'sub', 'sup', 'small', 'mark', 'q', 'cite']);
 /**
  * Markup the translation adds that the source does not have: a new tag type, a new or changed
  * attribute, an event handler or a script URL. Translations are often rendered as raw HTML
@@ -244,7 +307,7 @@ const DANGEROUS_URL = /(?:javascript|vbscript|data)\s*:/gi;
 export function unsafeAdditions(source, text) {
     const [src, out] = [unescapeEntities(source), unescapeEntities(text)];
     const srcTags = tagNames(src);
-    const newTags = [...tagNames(out)].filter(tag => !srcTags.has(tag) && tag !== 'br');
+    const newTags = [...tagNames(out)].filter(tag => !srcTags.has(tag) && !HARMLESS_TAGS.has(tag));
     if (newTags.length > 0)
         return `HTML tag not in the source: <${newTags.join('>, <')}>`;
     const srcAttrs = attributes(src);
@@ -312,7 +375,8 @@ const asciiDigits = (text) => text.replace(/\p{Nd}/gu, ch => {
 export function yearDifference(source, text) {
     // Decades ("the 2020s") are written in words or with suffixes in many languages.
     const decades = new Set(asciiDigits(source).match(/(?<!\d)(?:19|20)\d0(?=['’]?s\b)/g) ?? []);
-    const years = (value) => (asciiDigits(value).match(/(?<!\d)(?:19|20)\d\d(?!\d)/g) ?? []).filter(y => !decades.has(y)).sort().join(',');
+    // "1,900", "1.900" and "1 900" are numbers, not years: drop thousands separators first.
+    const years = (value) => (asciiDigits(value).replace(/(\d)[,.\u00a0\u202f ](?=\d{3}(?!\d))/g, '$1').match(/(?<!\d)(?:19|20)\d\d(?!\d)/g) ?? []).filter(y => !decades.has(y)).sort().join(',');
     const [a, b] = [years(source), years(text)];
     return a === b ? null : `source years [${a}], got [${b}]`;
 }
@@ -359,20 +423,25 @@ export function keptNameMissing(name, source, text) {
 // ---------------------------------------------------------------------------------------
 // Title case
 const COMMON_NAMES = new Set(['iOS', 'Android', 'Apple', 'Google', 'iPhone', 'iPad', 'Mac', 'Windows', 'Linux', 'AI', 'API', 'URL', 'PDF', 'FAQ', 'OK']);
-function midCapitals(text, source, names) {
+// Polish capitalises "you" pronouns as a sign of respect ("W Twoim planie"): correct, not Title Case.
+const POLISH_RESPECT = /^(?:Ty|Twój|Twoja|Twoje|Twojego|Twojej|Twoim|Twoją|Twoich|Twoimi|Ciebie|Cię|Tobie|Tobą|Wy|Wasz|Wasza|Wasze|Wam|Was|Wami)$/u;
+function midCapitals(text, source, names, lang = '') {
     const allowed = new Set([...COMMON_NAMES, ...names.flatMap(name => name.split(/\s+/))]);
     const isName = (word) => allowed.has(word) ||
         new RegExp(`(?<!\\p{L})${escapeRegExp(word)}(?!\\p{L})`, 'u').test(source) ||
         [...allowed].some(name => name.length >= 4 && word.startsWith(name));
     return text
-        .split(/[.!?:—–\n•|]+/)
+        // Commas and brackets start segments too: list items ("SMART: Specific, Measurable") and
+        // bracketed words ("Customize (Optional)") are capitalised in many languages.
+        .split(/[.!?:—–\n•|,;()]+/)
         .flatMap(segment => {
         const words = segment.trim().split(/\s+/);
         const first = words.findIndex(word => /\p{L}/u.test(word));
         return first === -1 ? [] : words.slice(first + 1);
     })
         .map(word => word.replace(/^[^\p{L}]+|[^\p{L}]+$/gu, ''))
-        .filter(word => word.length >= 3 && /^\p{Lu}\p{Ll}/u.test(word) && !isName(word));
+        .filter(word => word.length >= 3 && /^\p{Lu}\p{Ll}/u.test(word) && !isName(word))
+        .filter(word => !(baseLanguage(lang) === 'pl' && POLISH_RESPECT.test(word)));
 }
 function isEnglishTitleCase(source) {
     const rest = source
@@ -430,26 +499,34 @@ function sourceBoldLeadIn(source, text, names) {
     for (const lead of bold(source)) {
         if (lead.length <= 15 || !/\p{Ll}{3}/u.test(lead) || names.some(name => lead.includes(name)))
             continue;
+        // Only capitalised words ("Apple App Store:", "Google Play"): a name, kept on purpose.
+        if (lead.split(/\s+/).every(word => !/\p{L}/u.test(word) || /^[^\p{L}]*\p{Lu}/u.test(word)))
+            continue;
         if (translated.has(lead))
             return lead;
     }
     return null;
 }
+const ICU_HEADER = /\{\s*[\w.-]+\s*,\s*(?:plural|select|selectordinal)\s*,/g;
+const ICU_HEADER_TEST = /\{\s*[\w.-]+\s*,\s*(?:plural|select|selectordinal)\s*,/;
 // Loanwords commonly written in Latin script inside non-Latin text.
 const LATIN_LOANWORDS = new Set(['email', 'online', 'offline', 'emoji', 'smartphone', 'podcast', 'podcasts', 'wifi', 'blog', 'login', 'like', 'likes']);
 /** Source-language words left inside a non-Latin-script translation ("Settings → Privacy"). */
-function englishInNativeScript(lang, source, text, placeholderRe) {
+function englishInNativeScript(lang, source, text, placeholderRe, allowed) {
     const base = baseLanguage(lang);
     // Greek writes many anglicisms in Latin script; not checked.
     if (!NATIVE_SCRIPTS[base] || base === 'el' || base === 'sr' || text === source)
         return null;
     const strip = (value) => withoutUrls(value.replace(/[\w.+-]+@[\w.-]+/g, ' ').replace(/<[^>]+>/g, ' '))
+        // ICU syntax ("{count, plural, one {…} other {…}}") is code, not English text.
+        .replace(ICU_HEADER, ' ')
+        .replace(ICU_HEADER_TEST.test(value) ? /(?:^|[\s}])(?:zero|one|two|few|many|other|=\d+|[\w-]+)\s*(?=\{)/g : /$^/g, ' ')
         .replace(placeholderRe, ' ')
         .replace(/[(（][^)）]*[)）]/g, ' ')
         .replace(/["“„«「『‘'][^"”“»」』’']*["”“»」』’']/g, ' ');
     const sourceWords = new Set(strip(source).match(/\b[a-z]{4,}\b/g) ?? []);
     const left = [
-        ...new Set((strip(text).match(/(?<![\p{L}-])[a-z]{4,}(?![\p{L}])/gu) ?? []).filter(word => sourceWords.has(word) && !LATIN_LOANWORDS.has(word))),
+        ...new Set((strip(text).match(/(?<![\p{L}-])[a-z]{4,}(?![\p{L}])/gu) ?? []).filter(word => sourceWords.has(word) && !LATIN_LOANWORDS.has(word) && !allowed.has(word))),
     ];
     const menu = /\b[A-Z][a-z]+ → [A-Z][a-z]+/.exec(text);
     if (menu && source.includes(menu[0]))
@@ -478,9 +555,22 @@ const HEDGE_MARKERS = {
     cs: /tendenc|obvykle|často|zpravidla|většinou|bývá|sklon|snadno|častěji|mív/iu,
     sk: /tendenc|obvykle|často|zvyčajne|väčšinou|býva|sklon|ľahko|častejšie|zvyk|skôr/iu,
     el: /τείν|συχνά|συνήθως|τάση|συνήθ|εύκολα|συχνότερα/iu,
-    fi: /taipu|usein|yleensä|tapaa|tavallisesti|tuppaa|tyypillisesti|taipumus|helposti|useimmiten|herkästi/iu,
+    fi: /taipu|tapana|usein|yleensä|tapaa|tavallisesti|tuppaa|tyypillisesti|taipumus|helposti|useimmiten|herkästi/iu,
     ca: /tendeix|tendència|sol|sovint|generalment|acostum|normalment|fàcilment|freqüent/iu,
 };
+// Chinese, Japanese and Korean need far fewer characters than English; Thai has no spaces.
+const COMPACT_SCRIPTS = new Set(['zh', 'ja', 'ko']);
+/**
+ * A translation with a fraction of the source's length lost content: cut off by the model, or
+ * the source grew after it was translated. Markup and placeholders are not counted.
+ */
+export function muchShorter(lang, source, text) {
+    const visible = (value) => [...value.replace(/<[^>]+>|\{\{?[^{}]*\}?\}/g, '').replace(/\s+/g, ' ').trim()].length;
+    const [a, b] = [visible(source), visible(text)];
+    // Real translations from English rarely drop below 60% (Chinese/Japanese/Korean: 25%).
+    const min = COMPACT_SCRIPTS.has(baseLanguage(lang)) ? 0.2 : 0.5;
+    return a >= 200 && b < a * min ? `translation much shorter than the source (${b} of ${a} characters): content missing?` : null;
+}
 function droppedHedge(lang, source, text) {
     const markers = HEDGE_MARKERS[baseLanguage(lang)];
     return Boolean(markers) && /\btends? to\b/i.test(source) && !markers.test(text);

package/dist/cli.js

@@ -1,11 +1,13 @@
 #!/usr/bin/env node
 import fs from 'node:fs';
 import path from 'node:path';
-import { ConfigError, CONFIG_FILE, loadConfig } from './config.js';
+import { ConfigError, CONFIG_FILE, loadConfig, selectGroups } from './config.js';
+import { loadPlugins } from './plugins.js';
+import { startUi } from './ui/server.js';
 import { CHECKS } from './checks.js';
 import { findSourceFiles } from './files.js';
 import { isReasoningModel } from './llm.js';
-import { checkProject, summaryTable } from './project.js';
+import { checkProject, fixPlaceholders, summaryTable } from './project.js';
 import { listReview, updateReview } from './review.js';
 import { run } from './translate.js';
 const HELP = `localewarden - incremental AI translation for JSON locale files
@@ -14,6 +16,7 @@ Usage:
   localewarden [translate] [options]   translate new and changed strings
   localewarden check [options]         quality check, no API calls (use in CI)
   localewarden review [options]        list and resolve hand-edited translations
+  localewarden ui [--port 4848]        local web interface (127.0.0.1 only)
   localewarden init                    create ${CONFIG_FILE}
 
 Translate options:
@@ -21,16 +24,21 @@ Translate options:
   --lang de,fr           only these languages
   --fix-flagged          let the model fix strings the quality check flags
   --retranslate-all      translate every string again (hand edits stay protected)
+  --retranslate-files <patterns>  translate every string of these files again, e.g. "locales/{lang}/onboarding.json"
+  --refresh-before <YYYY-MM-DD>   translate again what was written before that day (or adopted)
+  --group app,web        only these groups (config "groups")
   --overwrite-manual     also replace hand-edited translations
   --max-tokens <n>       token budget for this run (default: maxTokensPerRun)
   --verbose              more output
 
 Check options:
   --lang de,fr           only these languages
+  --group app,web        only these groups
   --verbose, -v          list findings, not only counts
   --limit <n>            findings shown per check with --verbose (default 20)
-  --strict               exit 1 on warnings too (default: only placeholder/script errors)
+  --strict               exit 1 on warnings too (default: only errors)
   --json                 print findings as JSON
+  --fix                  repair placeholders with exactly one possible fix ({heures} -> {hours})
 
 Review options:
   --all                  include approved entries
@@ -42,7 +50,7 @@ Global:
   --config <path>        config file (default ./${CONFIG_FILE})
   --help, --version
 `;
-const VALUE_FLAGS = new Set(['--lang', '--max-tokens', '--config', '--limit', '--approve', '--release']);
+const VALUE_FLAGS = new Set(['--port', '--lang', '--group', '--max-tokens', '--config', '--limit', '--approve', '--release', '--retranslate-files', '--refresh-before']);
 function parseArgs(argv) {
     const args = { command: 'translate', flags: new Set(), values: new Map() };
     let commandSet = false;
@@ -75,6 +83,7 @@ function parseArgs(argv) {
     }
     return args;
 }
+const listArg = (args, name) => args.values.get(name)?.flatMap(value => value.split(',')).map(v => v.trim()).filter(Boolean);
 const languagesArg = (args) => args.values.get('--lang')?.flatMap(value => value.split(',')).map(l => l.trim()).filter(Boolean);
 function version() {
     const pkg = JSON.parse(fs.readFileSync(new URL('../package.json', import.meta.url), 'utf8'));
@@ -93,6 +102,8 @@ const LAYOUTS = [
     'src/assets/i18n/{lang}.json',
     'i18n/{lang}.json',
     'lang/{lang}.json',
+    'lib/l10n/app_{lang}.arb',
+    'lib/l10n/intl_{lang}.arb',
 ];
 function init() {
     const file = path.resolve(CONFIG_FILE);
@@ -128,8 +139,14 @@ async function translateCommand(args) {
     const maxTokens = args.values.get('--max-tokens')?.[0];
     if (maxTokens !== undefined && !(Number(maxTokens) > 0))
         throw new ConfigError('--max-tokens must be a positive number');
+    const refreshBefore = args.values.get('--refresh-before')?.[0];
+    if (refreshBefore !== undefined && !/^\d{4}-\d{2}-\d{2}$/.test(refreshBefore))
+        throw new ConfigError('--refresh-before must be a date like 2026-10-01');
     const summary = await run(config, {
         languages: languagesArg(args),
+        groups: listArg(args, '--group'),
+        retranslateFiles: listArg(args, '--retranslate-files'),
+        refreshBefore,
         dryRun: args.flags.has('--dry-run'),
         retranslateAll: args.flags.has('--retranslate-all'),
         overwriteManual: args.flags.has('--overwrite-manual'),
@@ -147,6 +164,7 @@ async function translateCommand(args) {
         }
         // Rough: prompt overhead per request plus input and output text (~4 characters per token).
         const requests = Math.ceil(strings / config.batchSize) + Math.ceil(strings * 0.05);
+        // Groups may use different models; the estimate uses the first group's.
         const low = Math.round(requests * 900 + (chars / 4) * 2.2);
         const high = Math.round(low * (isReasoningModel(config.model) ? 3 : 1.5));
         console.log(`Dry run: ${strings} string(s), ${chars.toLocaleString('en')} characters to translate.`);
@@ -168,8 +186,10 @@ async function translateCommand(args) {
     if (rows.length === 0)
         console.log('Everything is up to date.');
     console.log(`\n${summary.filesWritten.length} file(s) written, ${summary.requests} request(s), ${summary.tokens.toLocaleString('en')} tokens.`);
+    if (summary.filesCopied.length > 0)
+        console.log(`${summary.filesCopied.length} file(s) copied to their regional locales.`);
     if (summary.stoppedByBudget)
-        console.log('Stopped at the token budget. Run again to continue.');
+        console.log(`Stopped: ${summary.stopReason ?? 'token budget reached'}. Run again to continue.`);
     if (summary.pendingReview > 0)
         console.log(`${summary.pendingReview} hand-edited translation(s) to review: npx localewarden review`);
     const failed = Object.values(summary.languages).some(s => s.failed > 0);
@@ -177,10 +197,22 @@ async function translateCommand(args) {
         console.log('Failed strings were not written and will be retried on the next run.');
     return 0;
 }
-function checkCommand(args) {
+async function checkCommand(args) {
     const config = loadConfig(args.values.get('--config')?.[0]);
-    const languages = languagesArg(args) ?? config.targetLanguages;
-    const findings = checkProject(config, languages);
+    const plugins = await loadPlugins(config);
+    const groupNames = listArg(args, '--group');
+    const groups = selectGroups(config, groupNames, languagesArg(args));
+    const languages = languagesArg(args) ?? [...new Set(groups.flatMap(g => g.targetLanguages))];
+    const options = { languages, groups: groupNames, plugins };
+    let findings = checkProject(config, options);
+    if (args.flags.has('--fix')) {
+        const fixed = fixPlaceholders(config, findings);
+        for (const f of fixed)
+            console.log(`fixed [${f.lang}] ${f.file} ${f.key}: ${f.text}`);
+        console.log(`${fixed.length} placeholder(s) repaired.\n`);
+        if (fixed.length > 0)
+            findings = checkProject(config, options);
+    }
     if (args.flags.has('--json')) {
         console.log(JSON.stringify(findings, null, 2));
     }
@@ -200,7 +232,17 @@ function checkCommand(args) {
                     console.log(`  ... ${items.length - limit} more (--limit <n>)`);
             }
         }
-        const errors = findings.filter(f => f.severity === 'error').length;
+        // Errors fail CI, so show them even without --verbose.
+        const errorItems = findings.filter(f => f.severity === 'error');
+        if (!args.flags.has('--verbose') && errorItems.length > 0) {
+            console.log('\nErrors:');
+            for (const f of errorItems.slice(0, 20)) {
+                console.log(`  [${f.lang}] ${f.file} ${f.key} - ${f.check}${f.note ? `: ${f.note}` : ''}`);
+            }
+            if (errorItems.length > 20)
+                console.log(`  ... ${errorItems.length - 20} more (--verbose)`);
+        }
+        const errors = errorItems.length;
         console.log(`\n${errors} error(s), ${findings.length - errors} warning(s).${findings.length && !args.flags.has('--verbose') ? ' Details: --verbose' : ''}`);
     }
     const errors = findings.some(f => f.severity === 'error');
@@ -231,6 +273,9 @@ function reviewCommand(args) {
     return 0;
 }
 async function main() {
+    const major = Number(process.versions.node.split('.')[0]);
+    if (major < 20)
+        throw new ConfigError(`localewarden needs Node.js 20 or newer; this is ${process.versions.node}.`);
     const args = parseArgs(process.argv.slice(2));
     if (args.flags.has('--help')) {
         console.log(HELP);
@@ -244,12 +289,23 @@ async function main() {
         case 'translate':
             return translateCommand(args);
         case 'check':
-            return checkCommand(args);
+            return await checkCommand(args);
         case 'review':
             return reviewCommand(args);
         case 'init':
             init();
             return 0;
+        case 'ui': {
+            const config = loadConfig(args.values.get('--config')?.[0]);
+            const port = args.values.get('--port')?.[0];
+            if (port !== undefined && !/^\d+$/.test(port))
+                throw new ConfigError('--port must be a number');
+            const ui = await startUi(config, { port: port === undefined ? undefined : Number(port) });
+            console.log(`localewarden interface: ${ui.url}`);
+            console.log('Only reachable from this computer. Press Ctrl+C to stop.');
+            await new Promise(() => { }); // runs until Ctrl+C
+            return 0;
+        }
         default:
             throw new ConfigError(`Unknown command "${args.command}". See --help.`);
     }

package/dist/config.d.ts

@@ -1,3 +1,4 @@
+import type { PluginSpec } from './plugins.js';
 export type Register = 'formal' | 'informal';
 export interface Config {
     /** Language of the source files. Default "en". Several checks assume English. */
@@ -24,6 +25,16 @@ export interface Config {
     termNotes: Record<string, string>;
     /** Extra instructions per language; "*" applies to every language. */
     instructions: Record<string, string>;
+    /**
+     * Keys whose values are not text (ids, types, image paths). Copied from the source, never
+     * translated. "*" matches within one key segment, "**" across segments; a pattern without
+     * a dot matches the last segment anywhere ("id" matches "steps.2.id").
+     */
+    ignoreKeys: string[];
+    /** Source files to skip, as path patterns relative to the config ("locales/{lang}/nav.json"). */
+    exclude: string[];
+    /** Maximum characters per key pattern: { "**.meta.title": 60 }. Told to the model and checked. */
+    maxLength: Record<string, number>;
     /** Regular expressions (as strings) that match placeholders. Replaces the built-in list. */
     placeholders?: string[];
     model: string;
@@ -42,14 +53,39 @@ export interface Config {
     batchSize: number;
     /** Where state, review list and repair report live, relative to the config file. */
     stateDir: string;
+    /**
+     * Target locales that are a copy of another one instead of a translation, e.g. store
+     * listings: { "en-GB": "en-US", "fr-CA": "fr-FR" }. The value may be the source language.
+     */
+    copies: Record<string, string>;
+    /** Strings longer than this many characters are translated paragraph by paragraph. */
+    chunkChars: number;
+    /** Plugin modules (relative to the config file), see plugins.ts. */
+    plugins: PluginSpec[];
+    /** Token limit per UTC day across runs; usage is kept in <stateDir>/usage.json. */
+    dailyTokenBudget?: number;
+    /** Group name, when this config is one of `groups`. */
+    name?: string;
+    /**
+     * Parts of the project with their own files and settings, translated in this order
+     * (e.g. app UI first, long-form content last). Each group inherits the top-level settings.
+     */
+    groups?: Config[];
     /** Directory of the config file; all relative paths resolve against it. */
     root: string;
 }
 export declare const CONFIG_FILE = "localewarden.config.json";
-export declare const DEFAULTS: Omit<Config, 'targetLanguages' | 'files' | 'root'>;
+export declare const DEFAULTS: Omit<Config, 'targetLanguages' | 'files' | 'root' | 'groups' | 'name'>;
 export declare class ConfigError extends Error {
 }
 /** Validates a parsed config object and fills in defaults. */
 export declare function resolveConfig(raw: unknown, root: string): Config;
+/** The groups of a config, or the config itself as its only group. */
+export declare const groupsOf: (config: Config) => Config[];
+/**
+ * The groups to work on, in config order, limited by name; unknown group or language names
+ * are an error (a typo must not turn into "nothing to do" or a green check).
+ */
+export declare function selectGroups(config: Config, names?: string[], languages?: string[]): Config[];
 /** Loads the config file (default: localewarden.config.json in the working directory). */
 export declare function loadConfig(configPath?: string): Config;