@spintax/core 0.3.0 → 0.3.2

package/dist/index.d.cts

@@ -81,7 +81,7 @@ interface PluralIssue {
  * (which injects a fixture's `rng` strategy). Keeping the rng a parameter is what
  * lets the deterministic parity fixtures assert exact output.
  *
- * Order: strip stray sentinels → collapse-once #set + tree-walk (+ #include) →
+ * Order: strip stray sentinels → build vars, roll #def, tree-walk (+ #include) →
  * cosmetic post-process (if on) → mandatory neutralize safety-restore (always).
  */
 

package/dist/index.d.ts

@@ -81,7 +81,7 @@ interface PluralIssue {
  * (which injects a fixture's `rng` strategy). Keeping the rng a parameter is what
  * lets the deterministic parity fixtures assert exact output.
  *
- * Order: strip stray sentinels → collapse-once #set + tree-walk (+ #include) →
+ * Order: strip stray sentinels → build vars, roll #def, tree-walk (+ #include) →
  * cosmetic post-process (if on) → mandatory neutralize safety-restore (always).
  */
 

package/dist/index.js

@@ -21,13 +21,38 @@ function isParsedAst(value) {
   return typeof value === "object" && value !== null && value.astVersion === AST_VERSION && typeof value.source === "string" && Array.isArray(value.nodes);
 }
 
+// src/internal/neutralize.ts
+var STRUCTURAL = ["{", "}", "[", "]", "%", "#"];
+var SENTINEL_BASE = 57344;
+var SHIELD = /* @__PURE__ */ new Map();
+var RESTORE = /* @__PURE__ */ new Map();
+STRUCTURAL.forEach((ch, i) => {
+  const sentinel = String.fromCharCode(SENTINEL_BASE + i);
+  SHIELD.set(ch, sentinel);
+  RESTORE.set(sentinel, ch);
+});
+var SHIELD_RE = /[{}[\]%#]/gu;
+var RESTORE_RE = new RegExp(
+  `[${String.fromCharCode(SENTINEL_BASE)}-${String.fromCharCode(SENTINEL_BASE + STRUCTURAL.length - 1)}]`,
+  "gu"
+);
+function neutralize(value) {
+  return value.replace(SHIELD_RE, (ch) => SHIELD.get(ch) ?? ch);
+}
+function safetyRestore(text) {
+  return text.replace(RESTORE_RE, (ch) => RESTORE.get(ch) ?? ch);
+}
+function stripSentinels(text) {
+  return text.replace(RESTORE_RE, "");
+}
+
 // src/internal/parser.ts
 var VARIABLE_RE = /^%(\w+)%/;
 var DIRECTIVE_RE = /^[ \t]*#(set|def)[ \t]+%(\w+)%[ \t]*=[ \t]*(.*?)[ \t]*\r?$/gmu;
 var CONDITIONAL_NAME_RE = /^[A-Za-z_]\w*/;
 var PLURAL_PREFIX = "plural ";
 function parseTemplate(src) {
-  const { body, setDefs, defDefs } = extractDirectives(stripComments(src));
+  const { body, setDefs, defDefs } = extractDirectives(stripComments(stripSentinels(src)));
   return { astVersion: AST_VERSION, source: src, setDefs, defDefs, nodes: parseSequence(body) };
 }
 function extractDirectives(text) {
@@ -700,31 +725,6 @@ var NotImplementedError = class extends SpintaxError {
   }
 };
 
-// src/internal/neutralize.ts
-var STRUCTURAL = ["{", "}", "[", "]", "%", "#"];
-var SENTINEL_BASE = 57344;
-var SHIELD = /* @__PURE__ */ new Map();
-var RESTORE = /* @__PURE__ */ new Map();
-STRUCTURAL.forEach((ch, i) => {
-  const sentinel = String.fromCharCode(SENTINEL_BASE + i);
-  SHIELD.set(ch, sentinel);
-  RESTORE.set(sentinel, ch);
-});
-var SHIELD_RE = /[{}[\]%#]/gu;
-var RESTORE_RE = new RegExp(
-  `[${String.fromCharCode(SENTINEL_BASE)}-${String.fromCharCode(SENTINEL_BASE + STRUCTURAL.length - 1)}]`,
-  "gu"
-);
-function neutralize(value) {
-  return value.replace(SHIELD_RE, (ch) => SHIELD.get(ch) ?? ch);
-}
-function safetyRestore(text) {
-  return text.replace(RESTORE_RE, (ch) => RESTORE.get(ch) ?? ch);
-}
-function stripSentinels(text) {
-  return text.replace(RESTORE_RE, "");
-}
-
 // src/internal/render.ts
 var MAX_VARIABLE_DEPTH = 50;
 var INCLUDE_LINE_RE = /^[ \t]*#include[ \t\n\r\f\x0B]+"([^"]+)"[ \t\n\r\f\x0B]*$/gmu;
@@ -751,7 +751,7 @@ function resolveIncludes(text, ctx) {
       throw new IncludeResolverError(`includeResolver threw for "${ref}"`, { cause });
     }
     if (included === null) return "";
-    return renderAst(parseTemplate(stripSentinels(included)), {
+    return renderAst(parseTemplate(included), {
       ...ctx,
       runtimeContext: ctx.runtimeContext,
       // child inherits runtime, not parent #set
@@ -877,7 +877,7 @@ function renderPlural(node, opts) {
   if (/[{}[\]]/u.test(formsRaw)) {
     report({
       code: "plural.nested-brackets",
-      message: "Plural form slot contains nested spintax brackets; extract via #set first.",
+      message: "Plural form slot contains nested spintax brackets; extract via #def first \u2014 a #set is substituted verbatim and would put the brackets straight back.",
       construct: rawConstruct(countRaw, formsRaw),
       locale: base
     });
@@ -1036,8 +1036,9 @@ var SINGLE_ABBREVS = [
 var WS = " \\t\\r\\n\\f\\x0B";
 var S = `[${WS}]`;
 var DOMAIN_PART = "(?:(?:(?:xn--)?[\\p{L}\\p{N}]+(?:-[\\p{L}\\p{N}]+)*)\\.)+(?:xn--[a-z0-9\\-]{2,59}|[\\p{L}][\\p{L}\\p{N}-]{1,62})";
-var URL_RE = new RegExp(`(?:https?|ftp):\\/\\/[^${WS}<>"')\\]]+`, "giu");
-var MAILTEL_RE = new RegExp(`(?:mailto|tel):[^${WS}<>"')\\]]+`, "giu");
+var URI_BODY = `[^\\x00${WS}<>"')\\]]`;
+var URI_RE = new RegExp(`(?:(?:https?|ftp):\\/\\/|(?:mailto|tel):)${URI_BODY}+`, "giu");
+var MAILTEL_PREFIX_RE = /^(?:mailto|tel):/iu;
 var EMAIL_RE = new RegExp(`[a-z0-9._%+\\-]+@${DOMAIN_PART}\\b`, "giu");
 var DOMAIN_RE = new RegExp(`\\b${DOMAIN_PART}\\b`, "giu");
 var DECIMAL_RE = /\b\d+\.\d+\b/gu;
@@ -1058,6 +1059,18 @@ var CAP_AFTER_BLOCK_RE = new RegExp(
 );
 var CAP_AFTER_BREAK_RE = new RegExp(`(\\n${LEAD})(\\p{Ll})`, "gu");
 var up = (ch) => ch.toUpperCase();
+var SHIELD_PREFIXES = ["URL", "URI", "EMAIL", "DOM", "NUM", "ABBR"];
+var RESTORE_RE2 = new RegExp(`\\x00(?:${SHIELD_PREFIXES.join("|")})_\\d+\\x00`, "gu");
+function restore(text, input, placeholders) {
+  if (!input.includes("\0")) {
+    return text.replace(RESTORE_RE2, (key) => placeholders.get(key) ?? key);
+  }
+  let out = text;
+  for (const [key, value] of placeholders) {
+    out = out.split(key).join(value);
+  }
+  return out;
+}
 function postProcess(input) {
   const placeholders = /* @__PURE__ */ new Map();
   let counter = 0;
@@ -1077,8 +1090,10 @@ function postProcess(input) {
     return store(value, prefix);
   };
   let text = input;
-  text = text.replace(URL_RE, (m) => storeWithTrailingPunct(m, "URL"));
-  text = text.replace(MAILTEL_RE, (m) => storeWithTrailingPunct(m, "URI"));
+  text = text.replace(
+    URI_RE,
+    (m) => storeWithTrailingPunct(m, MAILTEL_PREFIX_RE.test(m) ? "URI" : "URL")
+  );
   text = text.replace(EMAIL_RE, (m) => store(m, "EMAIL"));
   text = text.replace(DOMAIN_RE, (m) => store(m, "DOM"));
   text = text.replace(DECIMAL_RE, (m) => store(m, "NUM"));
@@ -1093,10 +1108,7 @@ function postProcess(input) {
   text = text.replace(CAP_AFTER_SENTENCE_RE, (_m, p, gap, ch) => p + gap + up(ch));
   text = text.replace(CAP_AFTER_BLOCK_RE, (_m, tag, ch) => tag + up(ch));
   text = text.replace(CAP_AFTER_BREAK_RE, (_m, br, ch) => br + up(ch));
-  for (const [key, value] of placeholders) {
-    text = text.split(key).join(value);
-  }
-  return text.trim();
+  return restore(text, input, placeholders).trim();
 }
 
 // src/internal/pipeline.ts
@@ -1111,7 +1123,7 @@ function renderWith(input, rng, opts = {}) {
     includeStack: [],
     onPluralError: opts.onPluralError
   };
-  const ast = resolveAst(typeof input === "string" ? stripSentinels(input) : input);
+  const ast = resolveAst(input);
   let out = renderAst(ast, ctx);
   if (opts.postProcess !== false) out = postProcess(out);
   return safetyRestore(out);