locale-ai 0.6.3 → 0.6.4

package/README.md

@@ -35,7 +35,7 @@ Download 577 MB? (Y/n)
 - **Incremental**: only missing keys are translated, existing translations are kept, re-runs are no-ops. `--overwrite` re-translates everything.
 - **Structure**: key order, numbers, booleans, arrays, indentation and trailing newline are preserved.
 
-**Format notes**: for `.po`, `msgid` is the stable key (never changed) and `msgstr` is the translated value, as gettext expects — the English `.po` file's `msgstr` must hold the source text (most generators already fill it; an empty `msgstr` is treated as empty, not inherited from `msgid`), and `msgid_plural`/`msgstr[n]` plural entries pass through untranslated (translate those by hand, or use ICU plurals in `.arb`/JSON/YAML instead). For `.arb`, `@key` metadata and `@@locale` are never translated; `@@locale` is set to the target locale on output.
+**Format notes**: for `.po`, `msgid` is the stable key (never changed) and `msgstr` is the translated value, as gettext expects — the English `.po` file's `msgstr` must hold the source text (most generators already fill it; an empty `msgstr` is treated as empty, not inherited from `msgid`). `msgid_plural`/`msgstr[n]` plural entries are translated too (the singular and plural source forms), then expanded to however many `msgstr[n]` the target language's plural rules need (6 for Arabic, 1 for Japanese, ...) — not full grammatical inflection for in-between categories (`few`/`many`/...), which get the plural-sourced translation verbatim, the same simplification `addPluralForms` makes for i18next. `Plural-Forms` in the header is computed for the target language, not copied from the source; an existing target file's header is otherwise left as you last edited it (a hand-fixed `Plural-Forms`, `Last-Translator`, ...) instead of being regenerated on every rerun. For `.arb`, `@key` metadata and `@@locale` are never translated; `@@locale` is set to the target locale on output.
 
 ## Why locale-ai?
 
@@ -50,6 +50,7 @@ Download 577 MB? (Y/n)
 
 ```bash
 locale-ai translate --to fr,pt-BR [--from en] [--input dir] [--dry-run] [--overwrite] [--fast] [--report file] [-y]
+locale-ai check [--from en] [--input dir]   # CI: fails if a translated locale has missing keys or placeholder mismatches
 locale-ai models list [--from en]     # supported language pairs
 locale-ai models installed
 locale-ai models install en-de        # pre-download (e.g. in CI)

package/dist/cli.js

@@ -9,14 +9,19 @@ import { CATALOG, customEntries, findById, reachableTargets, resolveRoute, } fro
 import { translateStrings } from "./engine.js";
 import { CONFIG_FILE, glossaryLookup, loadConfig, protectRegex } from "./glossary.js";
 import { intlCode, parseLocale } from "./lang.js";
-import { addPluralForms, buildTarget, detectLayout, pendingStrings, readLocaleDoc, sourceFiles, targetFile, } from "./locales.js";
+import { addPluralForms, buildTarget, detectLayout, existingTargets, flattenStrings, pendingStrings, readLocaleDoc, sourceFiles, targetFile, } from "./locales.js";
 import { cacheRoot, install, isInstalled, loadTranslator, localModelProblem, planInstall, readManifest, uninstall, } from "./models.js";
+import { mask } from "./placeholders.js";
 /** Read from package.json so `npm version` is the single source of truth. */
 const VERSION = JSON.parse(fs.readFileSync(fileURLToPath(new URL("../package.json", import.meta.url)), "utf8")).version;
 const HELP = `locale-ai ${VERSION} — translate i18n locale files locally, on CPU, for free.
 
 Usage:
   locale-ai translate --to <locales> [options]
+  locale-ai check [--from <locale>]
+                        Validate that already-translated locales have the same keys and
+                        placeholders as the source, without translating. Exits non-zero
+                        on a mismatch (CI-friendly).
   locale-ai models list [--from <locale>]
   locale-ai models installed
   locale-ai models install <from-to | model-id> [--yes]
@@ -370,11 +375,70 @@ async function cmdModels(argv) {
             return sub ? 1 : 0;
     }
 }
+/**
+ * Validates already-translated locales against the source without translating:
+ * same key structure, and the same placeholders in each matching string. Meant for
+ * CI, so a mismatch (a key a translator dropped, a {name} a translation lost) fails
+ * the build instead of shipping silently.
+ */
+async function cmdCheck(argv) {
+    const { values } = parseArgs({
+        args: argv,
+        options: {
+            from: { type: "string", default: "en" },
+            input: { type: "string" },
+        },
+    });
+    const from = parseLocale(values.from);
+    const layout = detectLayout(process.cwd(), from.tag, values.input);
+    const sources = sourceFiles(layout, from.tag).map((f) => ({ file: f, doc: readLocaleDoc(f, from.tag) }));
+    const targets = existingTargets(layout, from.tag);
+    if (!targets.length) {
+        log(`No translated locales found next to ${from.tag}.`);
+        return 0;
+    }
+    let problems = 0;
+    for (const to of targets) {
+        let missing = 0;
+        let mismatched = 0;
+        for (const { file, doc } of sources) {
+            const target = targetFile(layout, from.tag, to, file);
+            if (!fs.existsSync(target)) {
+                missing += flattenStrings(doc.data).length;
+                log(`✗ ${to}: ${rel(target)} is missing entirely`);
+                continue;
+            }
+            const srcFlat = flattenStrings(doc.data);
+            const tgtByPath = new Map(flattenStrings(readLocaleDoc(target, to).data).map((e) => [e.path, e.value]));
+            for (const { path: p, value: srcVal } of srcFlat) {
+                const tgtVal = tgtByPath.get(p);
+                if (tgtVal === undefined) {
+                    missing++;
+                    log(`✗ ${to}: ${rel(target)} missing key "${p}"`);
+                    continue;
+                }
+                const srcTokens = mask(srcVal, "natural").tokens.toSorted();
+                const tgtTokens = mask(tgtVal, "natural").tokens.toSorted();
+                if (srcTokens.join("\u0001") !== tgtTokens.join("\u0001")) {
+                    mismatched++;
+                    log(`✗ ${to}: ${rel(target)} "${p}" placeholders differ: source [${srcTokens.join(", ")}], target [${tgtTokens.join(", ")}]`);
+                }
+            }
+        }
+        if (missing || mismatched)
+            problems++;
+        else
+            log(`✓ ${to}`);
+    }
+    return problems ? 1 : 0;
+}
 async function main() {
     const [cmd, ...rest] = process.argv.slice(2);
     switch (cmd) {
         case "translate":
             return cmdTranslate(rest);
+        case "check":
+            return cmdCheck(rest);
         case "models":
             return cmdModels(rest);
         case "-v":

package/dist/locales.js

@@ -82,6 +82,23 @@ export function targetFile(layout, from, to, src) {
         return path.join(layout.root, `${to}${layout.ext}`);
     return path.join(layout.root, to, path.relative(path.join(layout.root, from), src));
 }
+/** Locale tags already translated alongside `from` in this layout (for `locale-ai check`). */
+export function existingTargets(layout, from) {
+    if (layout.kind === "file") {
+        const ext = layout.ext;
+        return fs
+            .readdirSync(layout.root)
+            .filter((f) => f.endsWith(ext) && f.slice(0, -ext.length) !== from)
+            .map((f) => f.slice(0, -ext.length))
+            .sort();
+    }
+    return fs
+        .readdirSync(layout.root, { withFileTypes: true })
+        .filter((e) => e.isDirectory() && !e.name.startsWith(".") && e.name !== "node_modules" && e.name !== from)
+        .map((e) => e.name)
+        .filter((name) => listLocaleFiles(path.join(layout.root, name)).length > 0)
+        .sort();
+}
 const finalNewline = (text) => text === "" || text.endsWith("\n");
 const withNewline = (text, keep) => text.replace(/\n*$/, keep ? "\n" : "");
 function readJsonDoc(file, text) {
@@ -242,6 +259,10 @@ function pluralFormsHeader(lang) {
     const branches = Array.from({ length: n - 1 }, (_, i) => `n==${i + 1} ? ${i} :`).join(" ");
     return `nplurals=${n}; plural=(${branches} ${n - 1});`;
 }
+/** The `nplurals=N` count from pluralFormsHeader, for expanding msgstr[] to the right length. */
+function pluralCount(lang) {
+    return Number(/nplurals=(\d+)/.exec(pluralFormsHeader(lang))[1]);
+}
 function parsePo(text) {
     const entries = [];
     let leading = [];
@@ -318,12 +339,26 @@ function parsePo(text) {
     flushEntry();
     return { entries, leading };
 }
+/** Synthetic data keys for a plural entry's two translatable forms. */
+const pluralOneKey = (e) => poKey(e) + "\u0005one";
+const pluralOtherKey = (e) => poKey(e) + "\u0005other";
 function readPoDoc(file, text) {
     const { entries, leading } = parsePo(text);
     const data = newObj();
-    for (const e of entries)
-        if (!e.isHeader && e.msgidPlural === undefined)
+    for (const e of entries) {
+        if (e.isHeader)
+            continue;
+        if (e.msgidPlural === undefined)
             data[poKey(e)] = e.msgstr;
+        else {
+            // Like msgstr for a singular entry, msgstrPlural holds this FILE's own text: the
+            // English source form in the source .po, the translated forms in a target .po
+            // (msgid/msgid_plural are the stable keys, identical across every locale).
+            const forms = e.msgstrPlural ?? [];
+            data[pluralOneKey(e)] = forms[0] ?? "";
+            data[pluralOtherKey(e)] = forms[forms.length - 1] ?? forms[0] ?? "";
+        }
+    }
     const keepNewline = finalNewline(text);
     const serialize = (d, targetTag, existingText) => {
         const obj = isObj(d) ? d : newObj();
@@ -347,7 +382,19 @@ function readPoDoc(file, text) {
             }
             else if (e.msgidPlural !== undefined) {
                 lines.push(`msgid "${escapeC(e.msgid)}"`, `msgid_plural "${escapeC(e.msgidPlural)}"`);
-                (e.msgstrPlural ?? []).forEach((s, i) => lines.push(`msgstr[${i}] "${escapeC(s)}"`));
+                const oneKey = pluralOneKey(e);
+                const otherKey = pluralOtherKey(e);
+                seen.add(oneKey);
+                seen.add(otherKey);
+                const one = typeof obj[oneKey] === "string" ? obj[oneKey] : e.msgid;
+                const other = typeof obj[otherKey] === "string" ? obj[otherKey] : e.msgidPlural;
+                const n = pluralCount(targetTag);
+                // Not full grammatical inflection (same simplification as addPluralForms for
+                // i18next): index 0 gets the singular-sourced form, every other index the
+                // plural-sourced one. A language with only one category (ja, zh, ...) gets
+                // just the plural form, since it has no separate singular count.
+                for (let i = 0; i < n; i++)
+                    lines.push(`msgstr[${i}] "${escapeC(n === 1 ? other : i === 0 ? one : other)}"`);
             }
             else {
                 const key = poKey(e);
@@ -390,6 +437,17 @@ const isObj = (v) => typeof v === "object" && v !== null && !Array.isArray(v);
 const newObj = () => Object.create(null);
 /** A string needs translating when the target has no non-empty string at the same path. */
 const needsTranslation = (existing, overwrite) => overwrite || typeof existing !== "string" || existing === "";
+/** Flattens a locale tree into key-path -> string-value pairs (for `locale-ai check`). */
+export function flattenStrings(data, prefix = "", out = []) {
+    if (typeof data === "string")
+        out.push({ path: prefix || "(root)", value: data });
+    else if (Array.isArray(data))
+        data.forEach((v, i) => flattenStrings(v, `${prefix}[${i}]`, out));
+    else if (isObj(data))
+        for (const k of Object.keys(data))
+            flattenStrings(data[k], prefix ? `${prefix}.${k}` : k, out);
+    return out;
+}
 export function pendingStrings(source, existing, overwrite, out = []) {
     if (typeof source === "string") {
         if (needsTranslation(existing, overwrite))

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "locale-ai",
-  "version": "0.6.3",
+  "version": "0.6.4",
   "description": "Translate your i18n locale files locally on CPU. Free, offline, no API keys.",
   "author": "Taha KHABOUSS",
   "repository": {