@spintax/core 0.11.0 → 0.12.0

package/dist/index.js

@@ -1387,6 +1387,37 @@ function trimFragment(fragment) {
   if (fragment.lead === 0 && fragment.trail === 0) return fragment;
   return new Window(fragment, fragment.lead, fragment.length - fragment.trail);
 }
+function firstCodePointOf(fragment) {
+  const hi = charCodeAtOf(fragment, 0);
+  if (hi >= 55296 && hi <= 56319) {
+    const lo = charCodeAtOf(fragment, 1);
+    if (lo >= 56320 && lo <= 57343) return (hi - 55296) * 1024 + (lo - 56320) + 65536;
+  }
+  return hi;
+}
+function charCodeAtOf(fragment, index) {
+  let piece = fragment;
+  let at = index;
+  for (; ; ) {
+    if (at < 0 || at >= lengthOf(piece)) return -1;
+    if (typeof piece === "string") return piece.charCodeAt(at);
+    if (piece instanceof Window) {
+      at += piece.from;
+      piece = piece.base;
+      continue;
+    }
+    let offset = 0;
+    for (const child of piece.pieces) {
+      const length = lengthOf(child);
+      if (at < offset + length) {
+        piece = child;
+        at -= offset;
+        break;
+      }
+      offset += length;
+    }
+  }
+}
 function flatten(fragment) {
   if (typeof fragment === "string") return fragment;
   const out = [];
@@ -1780,7 +1811,12 @@ function assemblePermutation(node, rendered, opts) {
   max = Math.max(min, Math.min(max, total));
   const pick = randomInt(opts.rng, min, max);
   shuffle(elements, opts.rng);
-  return joinWithSeparators(elements.slice(0, pick), config.sep, config.lastsep ?? config.sep);
+  return joinWithSeparators(
+    elements.slice(0, pick),
+    config.sep,
+    config.lastsep ?? config.sep,
+    normalizeBaseLang(opts.locale)
+  );
 }
 function shuffle(arr, rng) {
   for (let i = arr.length - 1; i > 0; i -= 1) {
@@ -1790,7 +1826,7 @@ function shuffle(arr, rng) {
     arr[j] = tmp;
   }
 }
-function joinWithSeparators(elements, globalSep, globalLastsep) {
+function joinWithSeparators(elements, globalSep, globalLastsep, lang) {
   const count = elements.length;
   if (count === 0) return "";
   if (count === 1) return elements[0].text;
@@ -1798,14 +1834,23 @@ function joinWithSeparators(elements, globalSep, globalLastsep) {
   for (let i = 1; i < count; i += 1) {
     const el = elements[i];
     const sep = el.sep ?? (i === count - 1 ? globalLastsep : globalSep);
-    pieces.push(padSeparator(sep), el.text);
+    pieces.push(padSeparator(sep, lang, el.text), el.text);
   }
   return joinFragments(pieces);
 }
-var UNSPACED_SCRIPT_RE = /^[\p{Script=Han}\p{Script=Hiragana}\p{Script=Katakana}ーｰ]+$/u;
-function padSeparator(sep) {
+var UNSPACED_SCRIPT_RE = /^[\p{Script=Han}\p{Script=Hiragana}\p{Script=Katakana}ーｰ\p{Script=Thai}\p{Script=Lao}\p{Script=Khmer}\p{Script=Myanmar}]+$/u;
+var PROCLITICS = /* @__PURE__ */ new Map([
+  ["ar", { words: /* @__PURE__ */ new Set(["\u0648", "\u0641"]), letter: /^(?=\p{L})\p{Script=Arabic}$/u }],
+  ["he", { words: /* @__PURE__ */ new Set(["\u05D5"]), letter: /^(?=\p{L})\p{Script=Hebrew}$/u }]
+]);
+function padSeparator(sep, lang, next) {
   const trimmed = phpTrim(sep);
   if (trimmed === "") return sep;
+  const proclitic = PROCLITICS.get(lang);
+  if (proclitic !== void 0 && proclitic.words.has(trimmed)) {
+    const first = firstCodePointOf(next);
+    return first >= 0 && proclitic.letter.test(String.fromCodePoint(first)) ? ` ${trimmed}` : ` ${trimmed} `;
+  }
   if (/^\p{L}+$/u.test(trimmed) && !UNSPACED_SCRIPT_RE.test(trimmed)) return ` ${trimmed} `;
   return sep;
 }