@spintax/core 0.12.0 → 0.13.0

package/CHANGELOG.md

@@ -3,6 +3,44 @@
 All notable changes to `@spintax/core` are documented here. This project adheres to
 [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## 0.13.0 — 2026-10-19
+
+A minor: the post-process moves rendered text for a token that starts with a dot, for a bare `//`
+scheme, and for a sentence opening on `i` under Turkish or Azerbaijani. No verdict changes and no API
+change; `render()` already took the `locale` the post-process now also reads.
+
+### Fixed
+
+- **A dot that starts a token is not a sentence end (#91).** `.NET`, a dotfile, a file extension were
+  taken for sentence punctuation: the space before the dot was removed, a space was inserted after it and
+  the token was capitalized — `and .NET` rendered `and. NET`, `the .apk file` rendered `the. Apk file`.
+  A token that begins with a dot — `.NET`, `.gitignore`, `.env.local`, `.tar.gz`, `.xlsx`, `.5` — is now
+  shielded like a domain or a URL when it follows the text start, whitespace, an opening bracket, a quote,
+  a tag or a path separator (`src/.env`, `dir\.env`); trailing punctuation stays outside it (`.NET.`).
+  Unchanged: `word .` → `Word.`, `end . Next` → `End. Next`, `end.Next`, `ASP.NET`, `3.5`, and an ellipsis
+  glued to a word (`see...and` → `See... And`). The cost: `end .Next` — a sentence typed with the space on
+  the wrong side of the dot — is no longer repaired.
+- **Turkish and Azerbaijani capital İ (#94).** Under `locale: 'tr'` or `'az'` (any region, `-` or `_`) a
+  sentence that opens on dotted `i` is capitalized to `İ`, not `I` — `istanbul` → `İstanbul`; dotless `ı`
+  still becomes `I`. An explicit mapping, not `toLocaleUpperCase`, so the result does not depend on the
+  host's ICU data. Other locales are unchanged.
+- **A bare `//` scheme is a URL.** Prose that names the protocol — `(https://)` — got a space after its
+  colon: `(https: //)`. A `//` scheme with no body is now shielded like a URL, in any case (`HTTPS://`).
+  `mailto:` and `tel:` still need a body, so `Tel: 555` opening a sentence is capitalized and spaced as
+  before.
+
+Measured before the change over the family's stored content (2 581 production templates in four
+languages, 163 more in ten): every changed document is a fix — 21 renders of a published article that
+read `the. Apk file`, 11 that read `(https: //)` — and nothing else moves.
+
+### Corpus
+
+424 cases (+16), all in `render-postprocess.json`: `postprocess/turkish-*`, `postprocess/azerbaijani-*`,
+`postprocess/turkic-locale-case-and-underscore`, `postprocess/dotted-capital-only-under-turkic-locales`,
+`postprocess/dot-token-*` (openers, punctuation, text and line start, a digit, UCP whitespace, both path
+separators, and the negatives with the accepted cost), `postprocess/bare-scheme-*` and
+`postprocess/bare-mailto-and-tel-are-not-uris`.
+
 ## 0.12.0 — 2026-10-06
 
 A minor: rendered text moves for permutation separators in Arabic, Hebrew, Thai and Lao. No verdict

package/README.md

@@ -19,7 +19,7 @@ parse, render, validate, extract, analyze, and neutralize spintax templates.
   [`spintax-core`](https://pypi.org/project/spintax-core/) (Python), an Object Pascal engine,
   [`Spintax.Core`](https://www.nuget.org/packages/Spintax.Core/) (.NET), and
   the [Spintax WordPress plugin](https://wordpress.org/plugins/spintax/) are all held to the same
-  behavior contract by a **shared golden corpus of 408 fixtures** — deterministic verdicts, plural
+  behavior contract by a **shared golden corpus of 424 fixtures** — deterministic verdicts, plural
   buckets, conditionals, `#set`/`#def` semantics and post-processing agree everywhere, so a
   template is an asset you can move between runtimes, not a lock-in.
 - **MIT** licensed.

package/dist/index.cjs

@@ -1919,7 +1919,7 @@ 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");
@@ -1968,12 +1968,15 @@ 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(`^(${LEAD})(\\p{Ll})`, "u");
 var up = (ch) => ch.toUpperCase();
+var upTurkic = (ch) => ch === "i" ? "\u0130" : ch.toUpperCase();
+var TURKIC_LANGS = /* @__PURE__ */ new Set(["tr", "az"]);
 function indexLeads(text) {
   const n = text.length;
   const leadEnd = new Int32Array(n + 1);
@@ -2006,7 +2009,7 @@ function leadEndFrom(text, i, leads) {
   }
   return j < text.length ? leads().leadEnd[j] : j;
 }
-function capitalizeAfter(text, lower, next, context) {
+function capitalizeAfter(text, lower, next, context, upper) {
   const leads = () => {
     if (context.leads === null || context.leads.leadEnd.length !== text.length + 1) context.leads = indexLeads(text);
     return context.leads;
@@ -2021,7 +2024,7 @@ function capitalizeAfter(text, lower, next, context) {
     if (cp === void 0) continue;
     const ch = String.fromCodePoint(cp);
     if (!lower.test(ch)) continue;
-    out += text.slice(emitted, at) + up(ch);
+    out += text.slice(emitted, at) + upper(ch);
     emitted = at + ch.length;
     from = emitted;
   }
@@ -2054,7 +2057,7 @@ var afterLineBreak = (text, from) => {
   const at = text.indexOf("\n", from);
   return at === -1 ? null : { leadStart: at + 1, resume: at + 1 };
 };
-var SHIELD_PREFIXES = ["URL", "URI", "EMAIL", "DOM", "NUM", "ABBR"];
+var SHIELD_PREFIXES = ["URL", "URI", "EMAIL", "DOTTOK", "DOM", "NUM", "ABBR"];
 var RESTORE_RE2 = new RegExp(`\\x00(?:${SHIELD_PREFIXES.join("|")})_\\d+\\x00`, "gu");
 function restore(text, input, placeholders) {
   if (!input.includes("\0")) {
@@ -2089,7 +2092,8 @@ 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) => {
@@ -2109,6 +2113,7 @@ 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"));
@@ -2118,11 +2123,11 @@ 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();
 }
 
@@ -2143,7 +2148,7 @@ 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) {