@spintax/core 0.12.0 → 0.13.0

package/dist/index.js

@@ -1917,7 +1917,7 @@ var TLD_UPPER = "\\p{Lu}\\p{Lt}\\p{Lm}\\p{Lo}";
 var TLD = `(?:${XN}[a-zA-Z0-9\\-\\u017F\\u212A]{2,59}|[${TLD_LOWER}][${TLD_LOWER}\\p{N}-]{1,62}|[${TLD_UPPER}][${TLD_UPPER}\\p{N}-]{1,62})`;
 var DOMAIN_PART = `(?:${LABEL}\\.)+${TLD}`;
 var URI_BODY = `[^\\x00${WS}<>"')\\]]`;
-var URI_RE = new RegExp(`(?:(?:https?|ftp):\\/\\/|(?:mailto|tel):)${URI_BODY}+`, "giu");
+var URI_RE = new RegExp(`(?:(?:https?|ftp):\\/\\/${URI_BODY}*|(?:mailto|tel):${URI_BODY}+)`, "giu");
 var MAILTEL_PREFIX_RE = /^(?:mailto|tel):/iu;
 var DOMAIN_AT_RE = new RegExp(`${DOMAIN_PART}${WORD_BOUNDARY}`, "uy");
 var DOMAIN_SCAN_RE = new RegExp(`${AFTER_NON_WORD}(?:(${DOMAIN_PART}${WORD_BOUNDARY})|(?:${LABEL}\\.)*${LABEL})`, "gu");
@@ -1966,12 +1966,15 @@ var SENTENCE_OPENERS = "\xBF\xA1";
 var LEAD = `(?:<[^>]+>|[${SENTENCE_OPENERS}]|${S})*`;
 var QUOTES = `"'\xAB\xBB\u2039\u203A\u201C\u201D\u2018\u2019`;
 var CLOSER = `[)\\]]|[${QUOTES}]+(?=${S}|$|<|\\/?>|[.,;:!?\u2026)\\]\u2014\u2013])`;
+var DOT_TOKEN_RE = new RegExp(`(?<=^|${S}|[(\\[{>/\\\\${QUOTES}])\\.[\\p{L}\\p{N}][\\p{L}\\p{N}_.\\-]*`, "gu");
 var SPACE_BEFORE_PUNCT_RE = new RegExp(`(?<!${S})${S}+([,;:!?.])`, "gu");
 var SPACE_AFTER_COMMA_RE = new RegExp(`([,;:])(?!\\p{Nd})(?!${S}|$|<|${CLOSER})`, "gu");
 var SPACE_AFTER_SENTENCE_RE = new RegExp(`(?<![.!?])([.!?]+)(?![.!?])(?!\\p{Nd})(?!${S}|$|<|${CLOSER})`, "gu");
 var SPACE_AFTER_OPENER_RE = new RegExp(`([${SENTENCE_OPENERS}])${S}+`, "gu");
 var CAP_FIRST_RE = new RegExp(`^(${LEAD})(\\p{Ll})`, "u");
 var up = (ch) => ch.toUpperCase();
+var upTurkic = (ch) => ch === "i" ? "\u0130" : ch.toUpperCase();
+var TURKIC_LANGS = /* @__PURE__ */ new Set(["tr", "az"]);
 function indexLeads(text) {
   const n = text.length;
   const leadEnd = new Int32Array(n + 1);
@@ -2004,7 +2007,7 @@ function leadEndFrom(text, i, leads) {
   }
   return j < text.length ? leads().leadEnd[j] : j;
 }
-function capitalizeAfter(text, lower, next, context) {
+function capitalizeAfter(text, lower, next, context, upper) {
   const leads = () => {
     if (context.leads === null || context.leads.leadEnd.length !== text.length + 1) context.leads = indexLeads(text);
     return context.leads;
@@ -2019,7 +2022,7 @@ function capitalizeAfter(text, lower, next, context) {
     if (cp === void 0) continue;
     const ch = String.fromCodePoint(cp);
     if (!lower.test(ch)) continue;
-    out += text.slice(emitted, at) + up(ch);
+    out += text.slice(emitted, at) + upper(ch);
     emitted = at + ch.length;
     from = emitted;
   }
@@ -2052,7 +2055,7 @@ var afterLineBreak = (text, from) => {
   const at = text.indexOf("\n", from);
   return at === -1 ? null : { leadStart: at + 1, resume: at + 1 };
 };
-var SHIELD_PREFIXES = ["URL", "URI", "EMAIL", "DOM", "NUM", "ABBR"];
+var SHIELD_PREFIXES = ["URL", "URI", "EMAIL", "DOTTOK", "DOM", "NUM", "ABBR"];
 var RESTORE_RE2 = new RegExp(`\\x00(?:${SHIELD_PREFIXES.join("|")})_\\d+\\x00`, "gu");
 function restore(text, input, placeholders) {
   if (!input.includes("\0")) {
@@ -2087,7 +2090,8 @@ function restoreAsTheLoopDoes(text, placeholders) {
   }
   return out;
 }
-function postProcess(input) {
+function postProcess(input, locale = "") {
+  const upper = TURKIC_LANGS.has(normalizeBaseLang(locale)) ? upTurkic : up;
   const placeholders = /* @__PURE__ */ new Map();
   let counter = 0;
   const store = (value, prefix) => {
@@ -2107,6 +2111,7 @@ function postProcess(input) {
     (m) => storeWithTrailingPunct(m, MAILTEL_PREFIX_RE.test(m) ? "URI" : "URL")
   );
   text = shieldEmails(text, (m) => store(m, "EMAIL"));
+  text = text.replace(DOT_TOKEN_RE, (m) => storeWithTrailingPunct(m, "DOTTOK"));
   text = shieldDomains(text, (m) => store(m, "DOM"));
   text = text.replace(DECIMAL_RE, (m) => store(m, "NUM"));
   text = text.replace(MULTI_ABBR_RE, (m) => store(m, "ABBR"));
@@ -2116,11 +2121,11 @@ function postProcess(input) {
   text = text.replace(SPACE_AFTER_COMMA_RE, "$1 ");
   text = text.replace(SPACE_AFTER_SENTENCE_RE, "$1 ");
   text = text.replace(SPACE_AFTER_OPENER_RE, "$1");
-  text = text.replace(CAP_FIRST_RE, (_m, lead, ch) => lead + up(ch));
+  text = text.replace(CAP_FIRST_RE, (_m, lead, ch) => lead + upper(ch));
   const leadContext = { leads: null };
-  text = capitalizeAfter(text, LOWER_RE, afterSentenceEnd, leadContext);
-  text = capitalizeAfter(text, LOWER_RE, afterBlockTag(), leadContext);
-  text = capitalizeAfter(text, LOWER_RE, afterLineBreak, leadContext);
+  text = capitalizeAfter(text, LOWER_RE, afterSentenceEnd, leadContext, upper);
+  text = capitalizeAfter(text, LOWER_RE, afterBlockTag(), leadContext, upper);
+  text = capitalizeAfter(text, LOWER_RE, afterLineBreak, leadContext, upper);
   return restore(text, input, placeholders).trim();
 }
 
@@ -2141,7 +2146,7 @@ function renderWith(input, rng, opts = {}) {
   };
   const ast = resolveAst(input);
   let out = renderAst(ast, ctx);
-  if (opts.postProcess !== false) out = postProcess(out);
+  if (opts.postProcess !== false) out = postProcess(out, ctx.locale);
   return safetyRestore(out);
 }
 function resolveAst(input) {