locale-ai 0.6.7 → 0.6.8

package/README.md

@@ -35,7 +35,7 @@ Download 577 MB? (Y/n)
 - **Incremental, and edit-aware**: only missing or changed keys are translated; untouched translations are kept, so re-runs are no-ops. A small `locale-ai.lock.json` (commit it, like a package lock) remembers a hash of each source string and of the output last written for it per target locale — so editing a source string gets it re-translated automatically (it isn't enough for the target to already hold *some* text), while editing a target string by hand is detected and reported for review instead of being silently overwritten on the next run. `--overwrite` bypasses the lock and 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`). `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.
+**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. For `.strings`, a file saved as UTF-16 (Xcode's traditional default) is read like a UTF-8 one, an unquoted key (`title = "Settings";`, without quotes around `title`) is read the same as a quoted one, and `\U00e9`-style escapes are decoded — output is always written as UTF-8 with quoted keys, regardless of how the source was saved.
 
 ## Why locale-ai?
 

package/dist/locales.js

@@ -151,19 +151,28 @@ function readYamlDoc(file, text, tag) {
 }
 /** Apple .strings: `"key" = "value";`, optionally preceded by a `/* ... *\/` comment. */
 function unescapeC(s) {
-    return s.replace(/\\(.)/g, (_, c) => ({ n: "\n", t: "\t", r: "\r", '"': '"', "\\": "\\" })[c] ?? c);
+    return s.replace(/\\(?:U([0-9a-fA-F]{4})|(.))/g, (_, hex, c) => {
+        // \Uxxxx is a UTF-16 code unit; two in a row combine into one character via
+        // ordinary JS string concatenation when they're a surrogate pair.
+        if (hex !== undefined)
+            return String.fromCharCode(parseInt(hex, 16));
+        return ({ n: "\n", t: "\t", r: "\r", '"': '"', "\\": "\\" })[c] ?? c;
+    });
 }
 function escapeC(s) {
     return s.replace(/[\\"\n\t\r]/g, (c) => ({ "\\": "\\\\", '"': '\\"', "\n": "\\n", "\t": "\\t", "\r": "\\r" })[c]);
 }
 function readStringsDoc(file, text) {
     // A key's preceding comment is either a /* ... */ block, or one or more consecutive // lines.
-    const PAIR = /(?:((?:\/\*[\s\S]*?\*\/)|(?:\/\/[^\r\n]*(?:\r?\n[ \t]*\/\/[^\r\n]*)*))[ \t]*\r?\n+)?[ \t]*"((?:\\.|[^"\\])*)"\s*=\s*"((?:\\.|[^"\\])*)"\s*;/g;
+    // The old NeXT/Apple plist-string format allows a bare, unquoted key (no spaces,
+    // "=" or ";") as well as a quoted one — Xcode itself only ever writes quoted keys,
+    // but hand-edited or third-party-exported .strings files sometimes have both.
+    const PAIR = /(?:((?:\/\*[\s\S]*?\*\/)|(?:\/\/[^\r\n]*(?:\r?\n[ \t]*\/\/[^\r\n]*)*))[ \t]*\r?\n+)?[ \t]*(?:"((?:\\.|[^"\\])*)"|([^\s"=;]+))\s*=\s*"((?:\\.|[^"\\])*)"\s*;/g;
     const data = newObj();
     const entries = [];
     for (const m of text.matchAll(PAIR)) {
-        const key = unescapeC(m[2]);
-        data[key] = unescapeC(m[3]);
+        const key = m[2] !== undefined ? unescapeC(m[2]) : m[3];
+        data[key] = unescapeC(m[4]);
         entries.push({ key, comment: m[1] });
     }
     if (entries.length === 0 && text.trim() !== "") {
@@ -431,9 +440,28 @@ function readPoDoc(file, text) {
     };
     return { data, serialize };
 }
+/**
+ * Decodes a locale file's raw bytes to text, detecting a UTF-16 BOM first — Xcode's
+ * traditional default for `.strings` files, which `fs.readFileSync(file, "utf8")`
+ * would otherwise mangle into unreadable text (and then "no entries found").
+ */
+function readText(file) {
+    const buf = fs.readFileSync(file);
+    if (buf.length >= 2 && buf[0] === 0xff && buf[1] === 0xfe)
+        return buf.subarray(2).toString("utf16le");
+    if (buf.length >= 2 && buf[0] === 0xfe && buf[1] === 0xff) {
+        const swapped = Buffer.alloc(buf.length - 2);
+        for (let i = 2; i + 1 < buf.length; i += 2) {
+            swapped[i - 2] = buf[i + 1];
+            swapped[i - 1] = buf[i];
+        }
+        return swapped.toString("utf16le");
+    }
+    return buf.toString("utf8").replace(/^/, "");
+}
 /** `tag` is the locale this file is for (the source tag, or an existing target's own tag). */
 export function readLocaleDoc(file, tag) {
-    const text = fs.readFileSync(file, "utf8").replace(/^/, "");
+    const text = readText(file);
     const ext = path.extname(file).toLowerCase();
     if (ext === ".yaml" || ext === ".yml")
         return readYamlDoc(file, text, tag);

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "locale-ai",
-  "version": "0.6.7",
+  "version": "0.6.8",
   "description": "Translate your i18n locale files locally on CPU. Free, offline, no API keys.",
   "author": "Taha KHABOUSS",
   "repository": {