langtell 0.6.1 → 0.7.0

package/README.md

@@ -116,6 +116,28 @@ classifyBySnippet("Мова і культура Беларусі маюць ба
 // → { language: "be", … }        widen the roster and the text stops arguing
 ```
 
+#### Mixed scripts: judge each script on its own evidence (opt-in)
+
+The classifier scopes to the text's dominant script by letter count. In the default
+behaviour, a title whose Latin product name outweighs its Cyrillic clause is decided
+by the lone Latin candidate. That candidate can't lose, so its win says only which
+script had more letters. `isolateScripts` changes that:
+
+```ts
+const title = "Самые дешевые в Украине | Victron Multiplus II 48V 6k5va";
+classifyBySnippet(title, [uk, en, ru]);
+// → { language: "en", discriminating: false, … }   22 Latin letters outvote 20 Cyrillic
+classifyBySnippet(title, [uk, en, ru], undefined, { isolateScripts: true });
+// → { language: "ru", rung: 1, discriminating: true, … }
+```
+
+With it on, a minority script that holds ≥2 candidates and at least
+`MINORITY_MIN_LETTERS` letters is classified on its own (rungs 1–2) when the
+dominant script holds only one. The rung-3 resolver also receives only the scope's
+own script (`textInScope`), so Latin letters can't lift a short Cyrillic name over a
+trigram length floor. `compile({ isolateScripts: true })` and
+`createFrancEngine(candidates, { isolateScripts: true })` forward the same option.
+
 The measurement is exported too, for callers that have to _explain_ a verdict
 rather than only act on it. Derive the text's own alphabet once, then ask each
 candidate to account for it:

package/dist/chrome-ai.d.ts

@@ -1,4 +1,4 @@
-import { A as AsyncSource } from './types-DkB4436E.js';
+import { A as AsyncSource } from './types-DbPJ0sxF.js';
 
 /**
  * `langtell/chrome-ai` — the opt-in on-device engine wrapping the browser's

package/dist/{chunk-7N545CET.js → chunk-66W4QJGT.js}

@@ -1,10 +1,10 @@
-import { classifyBySnippet } from './chunk-SOTZVW3I.js';
+import { classifyBySnippet } from './chunk-VWKQLGB4.js';
 
 // src/text.ts
-function evidenceFromText(text, candidates, rung3) {
+function evidenceFromText(text, candidates, rung3, options) {
   if (text === void 0 || text.trim().length === 0) return [];
   if (candidates === void 0 || candidates.length === 0) return [];
-  const verdict = classifyBySnippet(text, candidates, rung3);
+  const verdict = classifyBySnippet(text, candidates, rung3, options);
   if (verdict.language === "unknown") return [];
   const item = {
     kind: "title-script",
@@ -31,5 +31,5 @@ function clamp01(value) {
 }
 
 export { evidenceFromText };
-//# sourceMappingURL=chunk-7N545CET.js.map
-//# sourceMappingURL=chunk-7N545CET.js.map
+//# sourceMappingURL=chunk-66W4QJGT.js.map
+//# sourceMappingURL=chunk-66W4QJGT.js.map

package/dist/chunk-66W4QJGT.js.map

@@ -0,0 +1 @@
+{"version":3,"sources":["../src/text.ts"],"names":[],"mappings":";;;AAwBO,SAAS,gBAAA,CACd,IAAA,EACA,UAAA,EACA,KAAA,EACA,OAAA,EACoB;AACpB,EAAA,IAAI,IAAA,KAAS,UAAa,IAAA,CAAK,IAAA,GAAO,MAAA,KAAW,CAAA,SAAU,EAAC;AAC5D,EAAA,IAAI,eAAe,MAAA,IAAa,UAAA,CAAW,MAAA,KAAW,CAAA,SAAU,EAAC;AAEjE,EAAA,MAAM,OAAA,GAAU,iBAAA,CAAkB,IAAA,EAAM,UAAA,EAAY,OAAO,OAAO,CAAA;AAClE,EAAA,IAAI,OAAA,CAAQ,QAAA,KAAa,SAAA,EAAW,OAAO,EAAC;AAE5C,EAAA,MAAM,IAAA,GAAyB;AAAA,IAC7B,IAAA,EAAM,cAAA;AAAA,IACN,UAAU,OAAA,CAAQ,QAAA;AAAA,IAClB,UAAA,EAAY,kBAAA,CAAmB,OAAA,CAAQ,MAAA,EAAQ,QAAQ,IAAI,CAAA;AAAA,IAC3D,MAAA,EAAQ,cAAA;AAAA,IACR,OAAO,IAAA,CAAK,IAAA,EAAK,CAAE,KAAA,CAAM,GAAG,EAAE;AAAA,GAChC;AAIA,EAAA,IAAI,CAAC,OAAA,CAAQ,cAAA,EAAgB,IAAA,CAAK,cAAA,GAAiB,KAAA;AACnD,EAAA,OAAO,CAAC,IAAI,CAAA;AACd;AAWA,SAAS,kBAAA,CAAmB,QAAgB,IAAA,EAAoB;AAC9D,EAAA,IAAI,SAAS,CAAA,EAAG;AAEd,IAAA,OAAO,OAAA,CAAQ,GAAA,GAAM,IAAA,CAAK,GAAA,CAAI,IAAA,CAAK,GAAA,CAAI,MAAA,EAAQ,CAAC,CAAA,EAAG,CAAC,CAAA,GAAI,IAAI,CAAA;AAAA,EAC9D;AACA,EAAA,MAAM,IAAA,GAAO,IAAA,CAAK,GAAA,CAAI,MAAA,EAAQ,CAAC,CAAA;AAC/B,EAAA,OAAO,OAAA,CAAQ,MAAO,IAAA,CAAK,GAAA,CAAI,MAAM,CAAC,CAAA,GAAI,IAAK,IAAI,CAAA;AACrD;AAEA,SAAS,QAAQ,KAAA,EAAuB;AACtC,EAAA,IAAI,CAAC,MAAA,CAAO,QAAA,CAAS,KAAK,GAAG,OAAO,CAAA;AACpC,EAAA,IAAI,KAAA,GAAQ,GAAG,OAAO,CAAA;AACtB,EAAA,IAAI,KAAA,GAAQ,GAAG,OAAO,CAAA;AACtB,EAAA,OAAO,KAAA;AACT","file":"chunk-66W4QJGT.js","sourcesContent":["import type { LanguageEvidence, LanguageProfile } from \"./types.js\";\nimport {\n  classifyBySnippet,\n  type ClassifyOptions,\n  type Rung,\n  type Rung3Resolver,\n} from \"./internal/classify.js\";\n\n/**\n * Producer: candidate-relative script + lexical signals from the title text.\n *\n * Wraps the ported snippet classifier ({@link classifyBySnippet}): noise strip →\n * dominant-script scope → distinctive letters (rung 1) → function words (2a) →\n * frequent words (2b). The `candidates` roster makes scoring roster-relative —\n * `і` decides Ukrainian only when Russian is also a candidate. Sync and\n * zero-dependency; the optional franc rung is injected via `rung3`.\n *\n * Emits at most one `kind: \"title-script\"` evidence item. The classifier's\n * integer `margin` (the winner's lead over the runner-up) maps to a 0..1\n * `confidence`: a verdict at all means the dominant script and the deciding rung\n * agreed, so the floor is high; a wider lead nudges it up. With no candidates\n * (or no usable distinctive signal) it abstains — emitting nothing rather than a\n * coarse \"unknown\", since the roster decides relevance.\n */\nexport function evidenceFromText(\n  text: string | undefined,\n  candidates?: readonly LanguageProfile[],\n  rung3?: Rung3Resolver,\n  options?: ClassifyOptions,\n): LanguageEvidence[] {\n  if (text === undefined || text.trim().length === 0) return [];\n  if (candidates === undefined || candidates.length === 0) return [];\n\n  const verdict = classifyBySnippet(text, candidates, rung3, options);\n  if (verdict.language === \"unknown\") return [];\n\n  const item: LanguageEvidence = {\n    kind: \"title-script\",\n    language: verdict.language,\n    confidence: marginToConfidence(verdict.margin, verdict.rung),\n    source: \"title-script\",\n    value: text.trim().slice(0, 80),\n  };\n  // Surface only the meaningful negative: the script was owned by ≤1 candidate,\n  // so it didn't choose between candidates. The discriminating case stays narrow\n  // (flag omitted). `fuse({ nonDiscriminatingScript: \"unknown\" })` reads this.\n  if (!verdict.discriminating) item.discriminating = false;\n  return [item];\n}\n\n/**\n * Map the classifier's per-rung lead to a 0..1 confidence.\n *\n * Rungs 1–2 carry an integer count of distinctive items (≥1). A verdict already\n * means script + rung agreed, so the floor is high (0.6) and each extra\n * distinctive item adds up to a 0.35 bonus, saturating by a lead of 4. Rung 3\n * (franc) carries franc's own 0..1 score-gap, which is weaker evidence, so it is\n * scaled into a 0.4..0.75 band.\n */\nfunction marginToConfidence(margin: number, rung: Rung): number {\n  if (rung === 3) {\n    // franc score-gap is already 0..1; weaker than the distinctive rungs.\n    return clamp01(0.4 + Math.min(Math.max(margin, 0), 1) * 0.35);\n  }\n  const lead = Math.max(margin, 1);\n  return clamp01(0.6 + (Math.min(lead, 4) / 4) * 0.35);\n}\n\nfunction clamp01(value: number): number {\n  if (!Number.isFinite(value)) return 0;\n  if (value < 0) return 0;\n  if (value > 1) return 1;\n  return value;\n}\n"]}

package/dist/{chunk-LUSZIBTZ.js → chunk-OUYN7BWC.js}

@@ -1,5 +1,5 @@
 import { normalizeBCP47 } from './chunk-YCUSX3GG.js';
-import { scriptOfProfile } from './chunk-SOTZVW3I.js';
+import { scriptOfProfile } from './chunk-VWKQLGB4.js';
 
 // src/fuse.ts
 var DEFAULT_KIND_WEIGHT = {
@@ -146,5 +146,5 @@ function clamp01(value) {
 }
 
 export { fuse };
-//# sourceMappingURL=chunk-LUSZIBTZ.js.map
-//# sourceMappingURL=chunk-LUSZIBTZ.js.map
+//# sourceMappingURL=chunk-OUYN7BWC.js.map
+//# sourceMappingURL=chunk-OUYN7BWC.js.map

package/dist/{chunk-LUSZIBTZ.js.map → chunk-OUYN7BWC.js.map}

@@ -1 +1 @@
-{"version":3,"sources":["../src/fuse.ts"],"names":[],"mappings":";;;;AA2BA,IAAM,mBAAA,GAA8C;AAAA,EAClD,cAAA,EAAgB,CAAA;AAAA,EAChB,iBAAA,EAAmB,CAAA;AAAA,EACnB,WAAA,EAAa,CAAA;AAAA,EACb,cAAA,EAAgB,GAAA;AAAA,EAChB,KAAA,EAAO,GAAA;AAAA,EACP,WAAA,EAAa,IAAA;AAAA,EACb,uBAAA,EAAyB,GAAA;AAAA,EACzB,uBAAA,EAAyB,IAAA;AAAA,EACzB,gBAAA,EAAkB,IAAA;AAAA,EAClB,WAAA,EAAa;AACf,CAAA;AAKA,IAAM,+BAAe,IAAI,GAAA,CAAY,CAAC,cAAA,EAAgB,OAAA,EAAS,WAAW,CAAC,CAAA;AAI3E,IAAM,uBAAA,GAA0B,GAAA;AAGhC,IAAM,oBAAA,GAAuB,GAAA;AAE7B,IAAM,iBAAA,GAAoB,IAAA;AAC1B,IAAM,UAAA,GAAa,IAAA;AAcZ,SAAS,IAAA,CACd,QAAA,EACA,OAAA,GAAuB,EAAC,EACR;AAChB,EAAA,MAAM,OAAA,GAAU,OAAA,CAAQ,OAAA,IAAW,EAAC;AACpC,EAAA,MAAM,UAAA,GAAa,iBAAA,CAAkB,QAAA,EAAU,OAAA,CAAQ,UAAU,CAAA;AASjE,EAAA,MAAM,OAAA,GACJ,QAAQ,uBAAA,KAA4B,SAAA,GAChC,qBAAqB,UAAA,EAAY,OAAA,CAAQ,UAAU,CAAA,GACnD,UAAA;AAEN,EAAA,MAAM,MAAA,uBAAa,GAAA,EAAoB;AACvC,EAAA,KAAA,MAAW,QAAQ,OAAA,EAAS;AAC1B,IAAA,IAAI,IAAA,CAAK,aAAa,SAAA,EAAW;AACjC,IAAA,MAAM,MAAA,GAAS,SAAA,CAAU,IAAA,EAAM,OAAO,CAAA;AACtC,IAAA,MAAA,CAAO,GAAA,CAAI,IAAA,CAAK,QAAA,EAAA,CAAW,MAAA,CAAO,GAAA,CAAI,IAAA,CAAK,QAAQ,CAAA,IAAK,CAAA,IAAK,OAAA,CAAQ,IAAA,CAAK,UAAU,IAAI,MAAM,CAAA;AAAA,EAChG;AAGA,EAAA,MAAM,MAAA,GAAS,uBAAA,CAAwB,OAAA,EAAS,OAAO,CAAA;AAEvD,EAAA,MAAM,EAAE,IAAA,EAAM,SAAA,EAAW,aAAY,GAAI,MAAA,CAAO,QAAQ,MAAM,CAAA;AAE9D,EAAA,IAAI,SAAS,IAAA,IAAQ,SAAA,GAAY,iBAAA,IAAqB,SAAA,GAAY,cAAc,UAAA,EAAY;AAK1F,IAAA,MAAM,cAAc,MAAA,KAAW,IAAA,GAAQ,OAAO,GAAA,CAAI,MAAM,KAAK,CAAA,GAAK,CAAA;AAClE,IAAA,IAAI,MAAA,KAAW,IAAA,IAAQ,WAAA,GAAc,CAAA,EAAG;AACtC,MAAA,OAAO;AAAA,QACL,QAAA,EAAU,MAAA;AAAA,QACV,UAAA,EAAY,OAAA,CAAQ,WAAA,IAAe,WAAA,GAAc,IAAA,CAAK,CAAA;AAAA,QACtD,QAAA,EAAU,CAAC,GAAG,UAAU;AAAA,OAC1B;AAAA,IACF;AACA,IAAA,OAAO,EAAE,QAAA,EAAU,SAAA,EAAW,UAAA,EAAY,OAAA,CAAQ,SAAS,CAAA,EAAG,QAAA,EAAU,CAAC,GAAG,UAAU,CAAA,EAAE;AAAA,EAC1F;AAEA,EAAA,OAAO;AAAA,IACL,QAAA,EAAU,IAAA;AAAA,IACV,UAAA,EAAY,OAAA,CAAQ,SAAA,IAAa,SAAA,GAAY,cAAc,IAAA,CAAK,CAAA;AAAA,IAChE,QAAA,EAAU,CAAC,GAAG,UAAU;AAAA,GAC1B;AACF;AAsBA,SAAS,SAAA,CAAU,MAAwB,OAAA,EAA0B;AACnE,EAAA,OACE,YAAA,CAAa,OAAA,CAAQ,IAAA,CAAK,MAAM,CAAC,CAAA,IACjC,YAAA,CAAa,OAAA,CAAQ,IAAA,CAAK,IAAI,CAAC,CAAA,IAC/B,mBAAA,CAAoB,IAAA,CAAK,IAAI,CAAA,IAC7B,oBAAA;AAEJ;AAIA,SAAS,aAAa,KAAA,EAA+C;AACnE,EAAA,IAAI,KAAA,KAAU,QAAW,OAAO,MAAA;AAChC,EAAA,OAAO,OAAO,QAAA,CAAS,KAAK,CAAA,IAAK,KAAA,IAAS,IAAI,KAAA,GAAQ,MAAA;AACxD;AAYA,SAAS,iBAAA,CACP,UACA,WAAA,EACoB;AACpB,EAAA,OAAO,QAAA,CAAS,GAAA,CAAI,CAAC,IAAA,KAAS;AAC5B,IAAA,IAAI,IAAA,CAAK,QAAA,KAAa,SAAA,EAAW,OAAO,IAAA;AACxC,IAAA,MAAM,UAAA,GAAa,cAAA,CAAe,IAAA,CAAK,QAAQ,KAAK,IAAA,CAAK,QAAA;AACzD,IAAA,IAAI,UAAA,KAAe,IAAA,CAAK,QAAA,EAAU,OAAO,IAAA;AACzC,IAAA,OAAO,EAAE,GAAG,IAAA,EAAM,QAAA,EAAU,UAAA,EAAW;AAAA,EACzC,CAAC,CAAA;AACH;AAoBA,SAAS,oBAAA,CACP,YACA,UAAA,EACoB;AACpB,EAAA,MAAM,SAAA,GAAY,WAAW,MAAA,CAAO,CAAC,SAAS,CAAC,aAAA,CAAc,IAAA,EAAM,UAAU,CAAC,CAAA;AAE9E,EAAA,MAAM,WAAA,GAAc,4BAAA,CAA6B,UAAA,EAAY,UAAU,CAAA;AACvE,EAAA,IAAI,WAAA,KAAgB,MAAM,OAAO,SAAA;AAEjC,EAAA,MAAM,QAAA,GAAW,YAAA,CAAa,UAAA,IAAc,EAAE,CAAA;AAC9C,EAAA,OAAO,SAAA,CAAU,MAAA,CAAO,CAAC,IAAA,KAAS;AAGhC,IAAA,IAAI,YAAA,CAAa,IAAI,IAAA,CAAK,IAAI,KAAK,IAAA,CAAK,QAAA,KAAa,WAAW,OAAO,IAAA;AACvE,IAAA,MAAM,UAAA,GAAa,QAAA,CAAS,GAAA,CAAI,IAAA,CAAK,QAAQ,CAAA;AAC7C,IAAA,OAAO,UAAA,KAAe,UAAa,UAAA,KAAe,WAAA;AAAA,EACpD,CAAC,CAAA;AACH;AAKA,SAAS,4BAAA,CACP,YACA,UAAA,EACmB;AACnB,EAAA,IAAI,UAAA,KAAe,QAAW,OAAO,IAAA;AACrC,EAAA,MAAM,QAAA,GAAW,aAAa,UAAU,CAAA;AACxC,EAAA,KAAA,MAAW,QAAQ,UAAA,EAAY;AAC7B,IAAA,IAAI,aAAA,CAAc,IAAA,EAAM,UAAU,CAAA,EAAG;AACnC,MAAA,MAAM,MAAA,GAAS,QAAA,CAAS,GAAA,CAAI,IAAA,CAAK,QAAQ,CAAA;AACzC,MAAA,IAAI,MAAA,KAAW,QAAW,OAAO,MAAA;AAAA,IACnC;AAAA,EACF;AACA,EAAA,OAAO,IAAA;AACT;AAIA,SAAS,aAAa,UAAA,EAAiE;AACrF,EAAA,MAAM,GAAA,uBAAU,GAAA,EAAwB;AACxC,EAAA,KAAA,MAAW,KAAK,UAAA,EAAY;AAC1B,IAAA,MAAM,MAAA,GAAS,gBAAgB,CAAC,CAAA;AAChC,IAAA,IAAI,WAAW,IAAA,EAAM,GAAA,CAAI,GAAA,CAAI,CAAA,CAAE,MAAM,MAAM,CAAA;AAAA,EAC7C;AACA,EAAA,OAAO,GAAA;AACT;AAUA,SAAS,aAAA,CAAc,MAAwB,GAAA,EAA2C;AACxF,EAAA,IAAI,IAAA,CAAK,mBAAmB,KAAA,IAAS,CAAC,aAAa,GAAA,CAAI,IAAA,CAAK,IAAI,CAAA,EAAG,OAAO,KAAA;AAC1E,EAAA,OAAO,CAAC,GAAA,CAAI,IAAA;AAAA,IACV,CAAC,KAAA,KACC,KAAA,CAAM,QAAA,KAAa,IAAA,CAAK,QAAA,IACxB,KAAA,CAAM,QAAA,KAAa,SAAA,IACnB,CAAC,YAAA,CAAa,GAAA,CAAI,MAAM,IAAI;AAAA,GAChC;AACF;AAQA,SAAS,uBAAA,CACP,UACA,OAAA,EACe;AACf,EAAA,IAAI,IAAA,GAAsB,IAAA;AAC1B,EAAA,IAAI,cAAA,GAAiB,CAAA;AACrB,EAAA,KAAA,MAAW,QAAQ,QAAA,EAAU;AAC3B,IAAA,IAAI,IAAA,CAAK,aAAa,SAAA,IAAa,CAAC,aAAa,GAAA,CAAI,IAAA,CAAK,IAAI,CAAA,EAAG;AACjE,IAAA,IAAI,SAAA,CAAU,IAAA,EAAM,OAAO,CAAA,KAAM,CAAA,EAAG;AACpC,IAAA,MAAM,CAAA,GAAI,OAAA,CAAQ,IAAA,CAAK,UAAU,CAAA;AACjC,IAAA,IAAI,IAAI,uBAAA,EAAyB;AACjC,IAAA,IAAI,IAAI,cAAA,EAAgB;AACtB,MAAA,cAAA,GAAiB,CAAA;AACjB,MAAA,IAAA,GAAO,IAAA,CAAK,QAAA;AAAA,IACd,CAAA,MAAA,IAAW,CAAA,KAAM,cAAA,IAAkB,IAAA,CAAK,aAAa,IAAA,EAAM;AAEzD,MAAA,IAAA,GAAO,IAAA;AAAA,IACT;AAAA,EACF;AACA,EAAA,OAAO,IAAA;AACT;AAQA,SAAS,MAAA,CACP,QACA,MAAA,EACiE;AACjE,EAAA,IAAI,IAAA,GAAsB,IAAA;AAC1B,EAAA,IAAI,SAAA,GAAY,CAAA;AAChB,EAAA,IAAI,WAAA,GAAc,CAAA;AAClB,EAAA,MAAM,cAAc,MAAA,KAAW,IAAA,GAAQ,OAAO,GAAA,CAAI,MAAM,KAAK,CAAA,GAAK,CAAA;AAElE,EAAA,KAAA,MAAW,CAAC,QAAA,EAAU,GAAG,CAAA,IAAK,MAAA,EAAQ;AAEpC,IAAA,MAAM,KAAA,GAAQ,WAAW,IAAA,IAAQ,QAAA,KAAa,SAAS,IAAA,CAAK,GAAA,CAAI,GAAA,EAAK,WAAW,CAAA,GAAI,GAAA;AACpF,IAAA,IAAI,QAAQ,SAAA,EAAW;AACrB,MAAA,WAAA,GAAc,SAAA;AACd,MAAA,SAAA,GAAY,KAAA;AACZ,MAAA,IAAA,GAAO,QAAA;AAAA,IACT,CAAA,MAAA,IAAW,QAAQ,WAAA,EAAa;AAC9B,MAAA,WAAA,GAAc,KAAA;AAAA,IAChB;AAAA,EACF;AAEA,EAAA,IAAI,WAAW,IAAA,IAAQ,IAAA,KAAS,UAAU,SAAA,KAAc,WAAA,IAAe,cAAc,CAAA,EAAG;AACtF,IAAA,WAAA,GAAc,SAAA;AACd,IAAA,IAAA,GAAO,MAAA;AACP,IAAA,SAAA,GAAY,WAAA;AAAA,EACd;AACA,EAAA,OAAO,EAAE,IAAA,EAAM,SAAA,EAAW,WAAA,EAAY;AACxC;AAEA,SAAS,QAAQ,KAAA,EAAuB;AACtC,EAAA,IAAI,CAAC,MAAA,CAAO,QAAA,CAAS,KAAK,GAAG,OAAO,CAAA;AACpC,EAAA,IAAI,KAAA,GAAQ,GAAG,OAAO,CAAA;AACtB,EAAA,IAAI,KAAA,GAAQ,GAAG,OAAO,CAAA;AACtB,EAAA,OAAO,KAAA;AACT","file":"chunk-LUSZIBTZ.js","sourcesContent":["import type {\n  Classification,\n  LanguageEvidence,\n  LanguageProfile,\n  NonDiscriminatingScript,\n  Weights,\n} from \"./types.js\";\nimport { normalizeBCP47 } from \"./internal/bcp47.js\";\nimport { scriptOfProfile, type ScriptName } from \"./internal/classify.js\";\n\nexport interface FuseOptions {\n  weights?: Weights;\n  /** The candidate roster. When present, incoming evidence tags are normalized\n   *  into it (`uk-UA` → `uk`, `ua` → `uk`) so context signals (page/header\n   *  locale) land on the same code the text rungs use. */\n  candidates?: readonly LanguageProfile[];\n  /** How to resolve a *non-discriminating* script read (one flagged\n   *  `discriminating: false` — its winning script owned by ≤1 roster candidate).\n   *  Default `\"candidate\"` keeps current behavior; `\"unknown\"` drops such a read\n   *  unless non-script evidence corroborates the same language. See\n   *  {@link NonDiscriminatingScript}. */\n  nonDiscriminatingScript?: NonDiscriminatingScript;\n}\n\n/** Default per-kind weights. Clear lexical signal (script, explicit locale)\n *  outweighs contextual signal (page tags, headers). Callers override per\n *  `source` id or `kind` via {@link FuseOptions.weights}. */\nconst DEFAULT_KIND_WEIGHT: Record<string, number> = {\n  \"title-script\": 1,\n  \"explicit-locale\": 1,\n  \"chrome-ai\": 1,\n  \"source-prior\": 0.7,\n  franc: 0.7,\n  \"node-lang\": 0.65,\n  \"http-content-language\": 0.6,\n  \"meta-content-language\": 0.55,\n  \"meta-og-locale\": 0.55,\n  \"html-lang\": 0.5,\n};\n\n/** Evidence kinds that constitute *clear script evidence* — a verdict the text\n *  classifier or an on-device model reached by actually reading the string. The\n *  guard below forbids weaker page/header *context* from flipping these. */\nconst SCRIPT_KINDS = new Set<string>([\"title-script\", \"franc\", \"chrome-ai\"]);\n\n/** A script verdict this confident is treated as settled — context may add to it\n *  but must not flip the winner to a different language. */\nconst SCRIPT_CONFIDENCE_FLOOR = 0.6;\n\n/** Weight for a kind absent from {@link DEFAULT_KIND_WEIGHT}. */\nconst FALLBACK_KIND_WEIGHT = 0.5;\n\nconst MIN_WINNING_SCORE = 0.35;\nconst MIN_MARGIN = 0.12;\n\n/**\n * Combine evidence into a single weighted verdict with an audit trail.\n *\n * Three steps:\n *  1. Normalize each item's language tag into the candidate roster (BCP-47:\n *     `uk-UA`/`ua` → `uk`) so text, page, and header signals agree on a code.\n *  2. Weighted argmax over languages (caller weights override per `source`/`kind`).\n *  3. Apply the guard **context must never override clear script evidence**: when\n *     the text classifier (or an on-device model) confidently read one language,\n *     weaker page/header context for a *different* language cannot win — a\n *     Ukrainian page chrome does not make a Latin/English title Ukrainian.\n */\nexport function fuse(\n  evidence: readonly LanguageEvidence[],\n  options: FuseOptions = {},\n): Classification {\n  const weights = options.weights ?? {};\n  const normalized = normalizeEvidence(evidence, options.candidates);\n\n  // Under `\"unknown\"`, a non-discriminating script read scores nothing on its own\n  // — it's dropped from the tally and the pin below — but stays in the trail. AND\n  // context written in a *different script* than that title is dropped too: a\n  // foreign-script title's language is never named by page/transport context in\n  // another script (a Latin title on a Ukrainian page is a foreign title in a\n  // Ukrainian UI, not a Ukrainian title). The full `normalized` set is still\n  // returned as evidence.\n  const scoring =\n    options.nonDiscriminatingScript === \"unknown\"\n      ? filterForUnknownMode(normalized, options.candidates)\n      : normalized;\n\n  const scores = new Map<string, number>();\n  for (const item of scoring) {\n    if (item.language === \"unknown\") continue;\n    const weight = weightFor(item, weights);\n    scores.set(item.language, (scores.get(item.language) ?? 0) + clamp01(item.confidence) * weight);\n  }\n\n  // The context-vs-script guard: a confident script read pins the winner.\n  const pinned = confidentScriptLanguage(scoring, weights);\n\n  const { best, bestScore, secondScore } = argmax(scores, pinned);\n\n  if (best === null || bestScore < MIN_WINNING_SCORE || bestScore - secondScore < MIN_MARGIN) {\n    // A pinned script language still wins even on a thin margin — clear script\n    // evidence is never demoted to \"unknown\" by competing context. The score must\n    // be positive, not merely present: a language that scored nothing is not a\n    // verdict, and naming it here would be naming it at confidence 0.\n    const pinnedScore = pinned !== null ? (scores.get(pinned) ?? 0) : 0;\n    if (pinned !== null && pinnedScore > 0) {\n      return {\n        language: pinned,\n        confidence: clamp01(pinnedScore / (pinnedScore + 0.15)),\n        evidence: [...normalized],\n      };\n    }\n    return { language: \"unknown\", confidence: clamp01(bestScore), evidence: [...normalized] };\n  }\n\n  return {\n    language: best,\n    confidence: clamp01(bestScore / (bestScore + secondScore + 0.15)),\n    evidence: [...normalized],\n  };\n}\n\n/**\n * The multiplier for one evidence item: the caller's override by `source`, then\n * by `kind`, then the per-kind default.\n *\n * An override that is not a *usable* multiplier — not a finite number, or\n * negative — is **ignored**, and resolution falls through to the next step as if\n * the caller had not set it. Such a value is garbage input, not a stronger way to\n * say \"this signal always wins\": `Infinity` has no coherent meaning in a weighted\n * sum (against a 0-confidence item it yields `NaN`, which makes its language\n * unrankable) and it collapses the confidence ratio below to `Infinity/Infinity`;\n * a negative weight scores evidence *against* its own language, which this model\n * has no meaning for. Honoring either would name a language at a confidence the\n * `0..1` contract forbids, so the documented default is used instead.\n *\n * `0` **is** usable and is honored: it is how a caller silences a signal.\n *\n * Every weight this returns is therefore finite and ≥ 0, so — with confidences\n * clamped to `0..1` — every score is finite and ≥ 0 and the confidence ratios in\n * {@link fuse} are always well-defined.\n */\nfunction weightFor(item: LanguageEvidence, weights: Weights): number {\n  return (\n    usableWeight(weights[item.source]) ??\n    usableWeight(weights[item.kind]) ??\n    DEFAULT_KIND_WEIGHT[item.kind] ??\n    FALLBACK_KIND_WEIGHT\n  );\n}\n\n/** The value itself when it can serve as a weight (finite, non-negative), else\n *  `undefined` so the caller's `??` chain falls through to the default. */\nfunction usableWeight(value: number | undefined): number | undefined {\n  if (value === undefined) return undefined;\n  return Number.isFinite(value) && value >= 0 ? value : undefined;\n}\n\n/** Normalize each item's tag into the roster's code space (BCP-47-aware). Items\n *  already `\"unknown\"` pass through untouched. Tags are BCP-47-normalized\n *  (`en-US` → `en`, `ua` → `uk`) so text, page, and header signals land on the\n *  same code. The normalized code is kept even when it falls outside the roster —\n *  argmax simply won't favor an out-of-roster context tag, but it stays in the\n *  audit trail.\n *\n *  The roster is accepted (and reserved) so a future revision can fold roster\n *  aliasing in without a signature change; today BCP-47 normalization alone\n *  reconciles the codes the producers emit. */\nfunction normalizeEvidence(\n  evidence: readonly LanguageEvidence[],\n  _candidates: readonly LanguageProfile[] | undefined,\n): LanguageEvidence[] {\n  return evidence.map((item) => {\n    if (item.language === \"unknown\") return item;\n    const normalized = normalizeBCP47(item.language) ?? item.language;\n    if (normalized === item.language) return item;\n    return { ...item, language: normalized };\n  });\n}\n\n/**\n * The scoring set under `nonDiscriminatingScript: \"unknown\"`. Two cuts:\n *\n *  1. Drop every *neutralized* non-discriminating script read (see\n *     {@link isNeutralized}) — it names a language only by being the lone\n *     candidate in its script, with nothing corroborating it.\n *  2. Drop context (page/transport) evidence whose language is in a **different\n *     script** than such a neutralized title. A foreign-script title's language\n *     is not the page's language: a Latin title on a `lang=\"uk\"` page must not\n *     resolve to `uk`. Same-script context (an explicit `en` `Content-Language`\n *     for a Latin title) survives and may still name — or, among same-script\n *     candidates, disambiguate — the title.\n *\n * The second cut needs each language's script, which is derived from the\n * candidate roster's alphabets. When `candidates` is absent the scripts can't be\n * derived, so the cut is skipped and behavior falls back to cut 1 alone (the\n * 0.3.0 behavior) — never throwing.\n */\nfunction filterForUnknownMode(\n  normalized: readonly LanguageEvidence[],\n  candidates: readonly LanguageProfile[] | undefined,\n): LanguageEvidence[] {\n  const surviving = normalized.filter((item) => !isNeutralized(item, normalized));\n\n  const titleScript = nonDiscriminatingTitleScript(normalized, candidates);\n  if (titleScript === null) return surviving;\n\n  const scriptOf = scriptByCode(candidates ?? []);\n  return surviving.filter((item) => {\n    // Keep the script reads themselves and anything whose script we can't place;\n    // only cross-script *context* in a known, different script is excluded.\n    if (SCRIPT_KINDS.has(item.kind) || item.language === \"unknown\") return true;\n    const itemScript = scriptOf.get(item.language);\n    return itemScript === undefined || itemScript === titleScript;\n  });\n}\n\n/** The script of the title under `\"unknown\"` mode, or `null` when there is no\n *  neutralized non-discriminating script read to anchor on (so no cross-script\n *  cut applies) or the roster can't place that read's language. */\nfunction nonDiscriminatingTitleScript(\n  normalized: readonly LanguageEvidence[],\n  candidates: readonly LanguageProfile[] | undefined,\n): ScriptName | null {\n  if (candidates === undefined) return null;\n  const scriptOf = scriptByCode(candidates);\n  for (const item of normalized) {\n    if (isNeutralized(item, normalized)) {\n      const script = scriptOf.get(item.language);\n      if (script !== undefined) return script;\n    }\n  }\n  return null;\n}\n\n/** Map each roster code to the script of its alphabet (Cyrillic/Latin). Codes\n *  whose alphabet carries no Cyrillic/Latin letter are omitted. */\nfunction scriptByCode(candidates: readonly LanguageProfile[]): Map<string, ScriptName> {\n  const map = new Map<string, ScriptName>();\n  for (const c of candidates) {\n    const script = scriptOfProfile(c);\n    if (script !== null) map.set(c.code, script);\n  }\n  return map;\n}\n\n/**\n * Whether a non-discriminating script read should score nothing (mode\n * `\"unknown\"`). True when `item` is a script kind flagged `discriminating:\n * false` (its winning script is owned by ≤1 roster candidate) AND no *non-script*\n * evidence corroborates its language. Corroboration must come from context kinds\n * (page tags, headers): two lone-candidate script reads agreeing is still two\n * defaults, not real evidence — so script kinds never corroborate one another.\n */\nfunction isNeutralized(item: LanguageEvidence, all: readonly LanguageEvidence[]): boolean {\n  if (item.discriminating !== false || !SCRIPT_KINDS.has(item.kind)) return false;\n  return !all.some(\n    (other) =>\n      other.language === item.language &&\n      other.language !== \"unknown\" &&\n      !SCRIPT_KINDS.has(other.kind),\n  );\n}\n\n/** The language of a *clear script* read confident enough to pin the verdict, or\n *  `null` when none qualifies. When two script reads disagree, the higher-\n *  confidence one pins (a tie leaves nothing pinned — argmax decides normally).\n *\n *  A read the caller weighed to `0` is silenced *here too*: it contributes no\n *  score, so it must not veto the rest of the evidence either. */\nfunction confidentScriptLanguage(\n  evidence: readonly LanguageEvidence[],\n  weights: Weights,\n): string | null {\n  let best: string | null = null;\n  let bestConfidence = 0;\n  for (const item of evidence) {\n    if (item.language === \"unknown\" || !SCRIPT_KINDS.has(item.kind)) continue;\n    if (weightFor(item, weights) === 0) continue;\n    const c = clamp01(item.confidence);\n    if (c < SCRIPT_CONFIDENCE_FLOOR) continue;\n    if (c > bestConfidence) {\n      bestConfidence = c;\n      best = item.language;\n    } else if (c === bestConfidence && item.language !== best) {\n      // Two equally-confident script reads for different languages — ambiguous.\n      best = null;\n    }\n  }\n  return best;\n}\n\n/**\n * Weighted argmax. When `pinned` is set (a confident script language), any\n * *other* language's score may only come from context kinds; that score is\n * capped so it can never exceed the pinned language. This enforces the guard\n * without discarding the context from the audit trail.\n */\nfunction argmax(\n  scores: Map<string, number>,\n  pinned: string | null,\n): { best: string | null; bestScore: number; secondScore: number } {\n  let best: string | null = null;\n  let bestScore = 0;\n  let secondScore = 0;\n  const pinnedScore = pinned !== null ? (scores.get(pinned) ?? 0) : 0;\n\n  for (const [language, raw] of scores) {\n    // Guard: a non-pinned language cannot out-score the pinned one.\n    const score = pinned !== null && language !== pinned ? Math.min(raw, pinnedScore) : raw;\n    if (score > bestScore) {\n      secondScore = bestScore;\n      bestScore = score;\n      best = language;\n    } else if (score > secondScore) {\n      secondScore = score;\n    }\n  }\n  // On a pinned tie (pinned capped equal to a context language), prefer pinned.\n  if (pinned !== null && best !== pinned && bestScore === pinnedScore && pinnedScore > 0) {\n    secondScore = bestScore;\n    best = pinned;\n    bestScore = pinnedScore;\n  }\n  return { best, bestScore, secondScore };\n}\n\nfunction clamp01(value: number): number {\n  if (!Number.isFinite(value)) return 0;\n  if (value < 0) return 0;\n  if (value > 1) return 1;\n  return value;\n}\n"]}
+{"version":3,"sources":["../src/fuse.ts"],"names":[],"mappings":";;;;AA2BA,IAAM,mBAAA,GAA8C;AAAA,EAClD,cAAA,EAAgB,CAAA;AAAA,EAChB,iBAAA,EAAmB,CAAA;AAAA,EACnB,WAAA,EAAa,CAAA;AAAA,EACb,cAAA,EAAgB,GAAA;AAAA,EAChB,KAAA,EAAO,GAAA;AAAA,EACP,WAAA,EAAa,IAAA;AAAA,EACb,uBAAA,EAAyB,GAAA;AAAA,EACzB,uBAAA,EAAyB,IAAA;AAAA,EACzB,gBAAA,EAAkB,IAAA;AAAA,EAClB,WAAA,EAAa;AACf,CAAA;AAKA,IAAM,+BAAe,IAAI,GAAA,CAAY,CAAC,cAAA,EAAgB,OAAA,EAAS,WAAW,CAAC,CAAA;AAI3E,IAAM,uBAAA,GAA0B,GAAA;AAGhC,IAAM,oBAAA,GAAuB,GAAA;AAE7B,IAAM,iBAAA,GAAoB,IAAA;AAC1B,IAAM,UAAA,GAAa,IAAA;AAcZ,SAAS,IAAA,CACd,QAAA,EACA,OAAA,GAAuB,EAAC,EACR;AAChB,EAAA,MAAM,OAAA,GAAU,OAAA,CAAQ,OAAA,IAAW,EAAC;AACpC,EAAA,MAAM,UAAA,GAAa,iBAAA,CAAkB,QAAA,EAAU,OAAA,CAAQ,UAAU,CAAA;AASjE,EAAA,MAAM,OAAA,GACJ,QAAQ,uBAAA,KAA4B,SAAA,GAChC,qBAAqB,UAAA,EAAY,OAAA,CAAQ,UAAU,CAAA,GACnD,UAAA;AAEN,EAAA,MAAM,MAAA,uBAAa,GAAA,EAAoB;AACvC,EAAA,KAAA,MAAW,QAAQ,OAAA,EAAS;AAC1B,IAAA,IAAI,IAAA,CAAK,aAAa,SAAA,EAAW;AACjC,IAAA,MAAM,MAAA,GAAS,SAAA,CAAU,IAAA,EAAM,OAAO,CAAA;AACtC,IAAA,MAAA,CAAO,GAAA,CAAI,IAAA,CAAK,QAAA,EAAA,CAAW,MAAA,CAAO,GAAA,CAAI,IAAA,CAAK,QAAQ,CAAA,IAAK,CAAA,IAAK,OAAA,CAAQ,IAAA,CAAK,UAAU,IAAI,MAAM,CAAA;AAAA,EAChG;AAGA,EAAA,MAAM,MAAA,GAAS,uBAAA,CAAwB,OAAA,EAAS,OAAO,CAAA;AAEvD,EAAA,MAAM,EAAE,IAAA,EAAM,SAAA,EAAW,aAAY,GAAI,MAAA,CAAO,QAAQ,MAAM,CAAA;AAE9D,EAAA,IAAI,SAAS,IAAA,IAAQ,SAAA,GAAY,iBAAA,IAAqB,SAAA,GAAY,cAAc,UAAA,EAAY;AAK1F,IAAA,MAAM,cAAc,MAAA,KAAW,IAAA,GAAQ,OAAO,GAAA,CAAI,MAAM,KAAK,CAAA,GAAK,CAAA;AAClE,IAAA,IAAI,MAAA,KAAW,IAAA,IAAQ,WAAA,GAAc,CAAA,EAAG;AACtC,MAAA,OAAO;AAAA,QACL,QAAA,EAAU,MAAA;AAAA,QACV,UAAA,EAAY,OAAA,CAAQ,WAAA,IAAe,WAAA,GAAc,IAAA,CAAK,CAAA;AAAA,QACtD,QAAA,EAAU,CAAC,GAAG,UAAU;AAAA,OAC1B;AAAA,IACF;AACA,IAAA,OAAO,EAAE,QAAA,EAAU,SAAA,EAAW,UAAA,EAAY,OAAA,CAAQ,SAAS,CAAA,EAAG,QAAA,EAAU,CAAC,GAAG,UAAU,CAAA,EAAE;AAAA,EAC1F;AAEA,EAAA,OAAO;AAAA,IACL,QAAA,EAAU,IAAA;AAAA,IACV,UAAA,EAAY,OAAA,CAAQ,SAAA,IAAa,SAAA,GAAY,cAAc,IAAA,CAAK,CAAA;AAAA,IAChE,QAAA,EAAU,CAAC,GAAG,UAAU;AAAA,GAC1B;AACF;AAsBA,SAAS,SAAA,CAAU,MAAwB,OAAA,EAA0B;AACnE,EAAA,OACE,YAAA,CAAa,OAAA,CAAQ,IAAA,CAAK,MAAM,CAAC,CAAA,IACjC,YAAA,CAAa,OAAA,CAAQ,IAAA,CAAK,IAAI,CAAC,CAAA,IAC/B,mBAAA,CAAoB,IAAA,CAAK,IAAI,CAAA,IAC7B,oBAAA;AAEJ;AAIA,SAAS,aAAa,KAAA,EAA+C;AACnE,EAAA,IAAI,KAAA,KAAU,QAAW,OAAO,MAAA;AAChC,EAAA,OAAO,OAAO,QAAA,CAAS,KAAK,CAAA,IAAK,KAAA,IAAS,IAAI,KAAA,GAAQ,MAAA;AACxD;AAYA,SAAS,iBAAA,CACP,UACA,WAAA,EACoB;AACpB,EAAA,OAAO,QAAA,CAAS,GAAA,CAAI,CAAC,IAAA,KAAS;AAC5B,IAAA,IAAI,IAAA,CAAK,QAAA,KAAa,SAAA,EAAW,OAAO,IAAA;AACxC,IAAA,MAAM,UAAA,GAAa,cAAA,CAAe,IAAA,CAAK,QAAQ,KAAK,IAAA,CAAK,QAAA;AACzD,IAAA,IAAI,UAAA,KAAe,IAAA,CAAK,QAAA,EAAU,OAAO,IAAA;AACzC,IAAA,OAAO,EAAE,GAAG,IAAA,EAAM,QAAA,EAAU,UAAA,EAAW;AAAA,EACzC,CAAC,CAAA;AACH;AAoBA,SAAS,oBAAA,CACP,YACA,UAAA,EACoB;AACpB,EAAA,MAAM,SAAA,GAAY,WAAW,MAAA,CAAO,CAAC,SAAS,CAAC,aAAA,CAAc,IAAA,EAAM,UAAU,CAAC,CAAA;AAE9E,EAAA,MAAM,WAAA,GAAc,4BAAA,CAA6B,UAAA,EAAY,UAAU,CAAA;AACvE,EAAA,IAAI,WAAA,KAAgB,MAAM,OAAO,SAAA;AAEjC,EAAA,MAAM,QAAA,GAAW,YAAA,CAAa,UAAA,IAAc,EAAE,CAAA;AAC9C,EAAA,OAAO,SAAA,CAAU,MAAA,CAAO,CAAC,IAAA,KAAS;AAGhC,IAAA,IAAI,YAAA,CAAa,IAAI,IAAA,CAAK,IAAI,KAAK,IAAA,CAAK,QAAA,KAAa,WAAW,OAAO,IAAA;AACvE,IAAA,MAAM,UAAA,GAAa,QAAA,CAAS,GAAA,CAAI,IAAA,CAAK,QAAQ,CAAA;AAC7C,IAAA,OAAO,UAAA,KAAe,UAAa,UAAA,KAAe,WAAA;AAAA,EACpD,CAAC,CAAA;AACH;AAKA,SAAS,4BAAA,CACP,YACA,UAAA,EACmB;AACnB,EAAA,IAAI,UAAA,KAAe,QAAW,OAAO,IAAA;AACrC,EAAA,MAAM,QAAA,GAAW,aAAa,UAAU,CAAA;AACxC,EAAA,KAAA,MAAW,QAAQ,UAAA,EAAY;AAC7B,IAAA,IAAI,aAAA,CAAc,IAAA,EAAM,UAAU,CAAA,EAAG;AACnC,MAAA,MAAM,MAAA,GAAS,QAAA,CAAS,GAAA,CAAI,IAAA,CAAK,QAAQ,CAAA;AACzC,MAAA,IAAI,MAAA,KAAW,QAAW,OAAO,MAAA;AAAA,IACnC;AAAA,EACF;AACA,EAAA,OAAO,IAAA;AACT;AAIA,SAAS,aAAa,UAAA,EAAiE;AACrF,EAAA,MAAM,GAAA,uBAAU,GAAA,EAAwB;AACxC,EAAA,KAAA,MAAW,KAAK,UAAA,EAAY;AAC1B,IAAA,MAAM,MAAA,GAAS,gBAAgB,CAAC,CAAA;AAChC,IAAA,IAAI,WAAW,IAAA,EAAM,GAAA,CAAI,GAAA,CAAI,CAAA,CAAE,MAAM,MAAM,CAAA;AAAA,EAC7C;AACA,EAAA,OAAO,GAAA;AACT;AAUA,SAAS,aAAA,CAAc,MAAwB,GAAA,EAA2C;AACxF,EAAA,IAAI,IAAA,CAAK,mBAAmB,KAAA,IAAS,CAAC,aAAa,GAAA,CAAI,IAAA,CAAK,IAAI,CAAA,EAAG,OAAO,KAAA;AAC1E,EAAA,OAAO,CAAC,GAAA,CAAI,IAAA;AAAA,IACV,CAAC,KAAA,KACC,KAAA,CAAM,QAAA,KAAa,IAAA,CAAK,QAAA,IACxB,KAAA,CAAM,QAAA,KAAa,SAAA,IACnB,CAAC,YAAA,CAAa,GAAA,CAAI,MAAM,IAAI;AAAA,GAChC;AACF;AAQA,SAAS,uBAAA,CACP,UACA,OAAA,EACe;AACf,EAAA,IAAI,IAAA,GAAsB,IAAA;AAC1B,EAAA,IAAI,cAAA,GAAiB,CAAA;AACrB,EAAA,KAAA,MAAW,QAAQ,QAAA,EAAU;AAC3B,IAAA,IAAI,IAAA,CAAK,aAAa,SAAA,IAAa,CAAC,aAAa,GAAA,CAAI,IAAA,CAAK,IAAI,CAAA,EAAG;AACjE,IAAA,IAAI,SAAA,CAAU,IAAA,EAAM,OAAO,CAAA,KAAM,CAAA,EAAG;AACpC,IAAA,MAAM,CAAA,GAAI,OAAA,CAAQ,IAAA,CAAK,UAAU,CAAA;AACjC,IAAA,IAAI,IAAI,uBAAA,EAAyB;AACjC,IAAA,IAAI,IAAI,cAAA,EAAgB;AACtB,MAAA,cAAA,GAAiB,CAAA;AACjB,MAAA,IAAA,GAAO,IAAA,CAAK,QAAA;AAAA,IACd,CAAA,MAAA,IAAW,CAAA,KAAM,cAAA,IAAkB,IAAA,CAAK,aAAa,IAAA,EAAM;AAEzD,MAAA,IAAA,GAAO,IAAA;AAAA,IACT;AAAA,EACF;AACA,EAAA,OAAO,IAAA;AACT;AAQA,SAAS,MAAA,CACP,QACA,MAAA,EACiE;AACjE,EAAA,IAAI,IAAA,GAAsB,IAAA;AAC1B,EAAA,IAAI,SAAA,GAAY,CAAA;AAChB,EAAA,IAAI,WAAA,GAAc,CAAA;AAClB,EAAA,MAAM,cAAc,MAAA,KAAW,IAAA,GAAQ,OAAO,GAAA,CAAI,MAAM,KAAK,CAAA,GAAK,CAAA;AAElE,EAAA,KAAA,MAAW,CAAC,QAAA,EAAU,GAAG,CAAA,IAAK,MAAA,EAAQ;AAEpC,IAAA,MAAM,KAAA,GAAQ,WAAW,IAAA,IAAQ,QAAA,KAAa,SAAS,IAAA,CAAK,GAAA,CAAI,GAAA,EAAK,WAAW,CAAA,GAAI,GAAA;AACpF,IAAA,IAAI,QAAQ,SAAA,EAAW;AACrB,MAAA,WAAA,GAAc,SAAA;AACd,MAAA,SAAA,GAAY,KAAA;AACZ,MAAA,IAAA,GAAO,QAAA;AAAA,IACT,CAAA,MAAA,IAAW,QAAQ,WAAA,EAAa;AAC9B,MAAA,WAAA,GAAc,KAAA;AAAA,IAChB;AAAA,EACF;AAEA,EAAA,IAAI,WAAW,IAAA,IAAQ,IAAA,KAAS,UAAU,SAAA,KAAc,WAAA,IAAe,cAAc,CAAA,EAAG;AACtF,IAAA,WAAA,GAAc,SAAA;AACd,IAAA,IAAA,GAAO,MAAA;AACP,IAAA,SAAA,GAAY,WAAA;AAAA,EACd;AACA,EAAA,OAAO,EAAE,IAAA,EAAM,SAAA,EAAW,WAAA,EAAY;AACxC;AAEA,SAAS,QAAQ,KAAA,EAAuB;AACtC,EAAA,IAAI,CAAC,MAAA,CAAO,QAAA,CAAS,KAAK,GAAG,OAAO,CAAA;AACpC,EAAA,IAAI,KAAA,GAAQ,GAAG,OAAO,CAAA;AACtB,EAAA,IAAI,KAAA,GAAQ,GAAG,OAAO,CAAA;AACtB,EAAA,OAAO,KAAA;AACT","file":"chunk-OUYN7BWC.js","sourcesContent":["import type {\n  Classification,\n  LanguageEvidence,\n  LanguageProfile,\n  NonDiscriminatingScript,\n  Weights,\n} from \"./types.js\";\nimport { normalizeBCP47 } from \"./internal/bcp47.js\";\nimport { scriptOfProfile, type ScriptName } from \"./internal/classify.js\";\n\nexport interface FuseOptions {\n  weights?: Weights;\n  /** The candidate roster. When present, incoming evidence tags are normalized\n   *  into it (`uk-UA` → `uk`, `ua` → `uk`) so context signals (page/header\n   *  locale) land on the same code the text rungs use. */\n  candidates?: readonly LanguageProfile[];\n  /** How to resolve a *non-discriminating* script read (one flagged\n   *  `discriminating: false` — its winning script owned by ≤1 roster candidate).\n   *  Default `\"candidate\"` keeps current behavior; `\"unknown\"` drops such a read\n   *  unless non-script evidence corroborates the same language. See\n   *  {@link NonDiscriminatingScript}. */\n  nonDiscriminatingScript?: NonDiscriminatingScript;\n}\n\n/** Default per-kind weights. Clear lexical signal (script, explicit locale)\n *  outweighs contextual signal (page tags, headers). Callers override per\n *  `source` id or `kind` via {@link FuseOptions.weights}. */\nconst DEFAULT_KIND_WEIGHT: Record<string, number> = {\n  \"title-script\": 1,\n  \"explicit-locale\": 1,\n  \"chrome-ai\": 1,\n  \"source-prior\": 0.7,\n  franc: 0.7,\n  \"node-lang\": 0.65,\n  \"http-content-language\": 0.6,\n  \"meta-content-language\": 0.55,\n  \"meta-og-locale\": 0.55,\n  \"html-lang\": 0.5,\n};\n\n/** Evidence kinds that constitute *clear script evidence* — a verdict the text\n *  classifier or an on-device model reached by actually reading the string. The\n *  guard below forbids weaker page/header *context* from flipping these. */\nconst SCRIPT_KINDS = new Set<string>([\"title-script\", \"franc\", \"chrome-ai\"]);\n\n/** A script verdict this confident is treated as settled — context may add to it\n *  but must not flip the winner to a different language. */\nconst SCRIPT_CONFIDENCE_FLOOR = 0.6;\n\n/** Weight for a kind absent from {@link DEFAULT_KIND_WEIGHT}. */\nconst FALLBACK_KIND_WEIGHT = 0.5;\n\nconst MIN_WINNING_SCORE = 0.35;\nconst MIN_MARGIN = 0.12;\n\n/**\n * Combine evidence into a single weighted verdict with an audit trail.\n *\n * Three steps:\n *  1. Normalize each item's language tag into the candidate roster (BCP-47:\n *     `uk-UA`/`ua` → `uk`) so text, page, and header signals agree on a code.\n *  2. Weighted argmax over languages (caller weights override per `source`/`kind`).\n *  3. Apply the guard **context must never override clear script evidence**: when\n *     the text classifier (or an on-device model) confidently read one language,\n *     weaker page/header context for a *different* language cannot win — a\n *     Ukrainian page chrome does not make a Latin/English title Ukrainian.\n */\nexport function fuse(\n  evidence: readonly LanguageEvidence[],\n  options: FuseOptions = {},\n): Classification {\n  const weights = options.weights ?? {};\n  const normalized = normalizeEvidence(evidence, options.candidates);\n\n  // Under `\"unknown\"`, a non-discriminating script read scores nothing on its own\n  // — it's dropped from the tally and the pin below — but stays in the trail. AND\n  // context written in a *different script* than that title is dropped too: a\n  // foreign-script title's language is never named by page/transport context in\n  // another script (a Latin title on a Ukrainian page is a foreign title in a\n  // Ukrainian UI, not a Ukrainian title). The full `normalized` set is still\n  // returned as evidence.\n  const scoring =\n    options.nonDiscriminatingScript === \"unknown\"\n      ? filterForUnknownMode(normalized, options.candidates)\n      : normalized;\n\n  const scores = new Map<string, number>();\n  for (const item of scoring) {\n    if (item.language === \"unknown\") continue;\n    const weight = weightFor(item, weights);\n    scores.set(item.language, (scores.get(item.language) ?? 0) + clamp01(item.confidence) * weight);\n  }\n\n  // The context-vs-script guard: a confident script read pins the winner.\n  const pinned = confidentScriptLanguage(scoring, weights);\n\n  const { best, bestScore, secondScore } = argmax(scores, pinned);\n\n  if (best === null || bestScore < MIN_WINNING_SCORE || bestScore - secondScore < MIN_MARGIN) {\n    // A pinned script language still wins even on a thin margin — clear script\n    // evidence is never demoted to \"unknown\" by competing context. The score must\n    // be positive, not merely present: a language that scored nothing is not a\n    // verdict, and naming it here would be naming it at confidence 0.\n    const pinnedScore = pinned !== null ? (scores.get(pinned) ?? 0) : 0;\n    if (pinned !== null && pinnedScore > 0) {\n      return {\n        language: pinned,\n        confidence: clamp01(pinnedScore / (pinnedScore + 0.15)),\n        evidence: [...normalized],\n      };\n    }\n    return { language: \"unknown\", confidence: clamp01(bestScore), evidence: [...normalized] };\n  }\n\n  return {\n    language: best,\n    confidence: clamp01(bestScore / (bestScore + secondScore + 0.15)),\n    evidence: [...normalized],\n  };\n}\n\n/**\n * The multiplier for one evidence item: the caller's override by `source`, then\n * by `kind`, then the per-kind default.\n *\n * An override that is not a *usable* multiplier — not a finite number, or\n * negative — is **ignored**, and resolution falls through to the next step as if\n * the caller had not set it. Such a value is garbage input, not a stronger way to\n * say \"this signal always wins\": `Infinity` has no coherent meaning in a weighted\n * sum (against a 0-confidence item it yields `NaN`, which makes its language\n * unrankable) and it collapses the confidence ratio below to `Infinity/Infinity`;\n * a negative weight scores evidence *against* its own language, which this model\n * has no meaning for. Honoring either would name a language at a confidence the\n * `0..1` contract forbids, so the documented default is used instead.\n *\n * `0` **is** usable and is honored: it is how a caller silences a signal.\n *\n * Every weight this returns is therefore finite and ≥ 0, so — with confidences\n * clamped to `0..1` — every score is finite and ≥ 0 and the confidence ratios in\n * {@link fuse} are always well-defined.\n */\nfunction weightFor(item: LanguageEvidence, weights: Weights): number {\n  return (\n    usableWeight(weights[item.source]) ??\n    usableWeight(weights[item.kind]) ??\n    DEFAULT_KIND_WEIGHT[item.kind] ??\n    FALLBACK_KIND_WEIGHT\n  );\n}\n\n/** The value itself when it can serve as a weight (finite, non-negative), else\n *  `undefined` so the caller's `??` chain falls through to the default. */\nfunction usableWeight(value: number | undefined): number | undefined {\n  if (value === undefined) return undefined;\n  return Number.isFinite(value) && value >= 0 ? value : undefined;\n}\n\n/** Normalize each item's tag into the roster's code space (BCP-47-aware). Items\n *  already `\"unknown\"` pass through untouched. Tags are BCP-47-normalized\n *  (`en-US` → `en`, `ua` → `uk`) so text, page, and header signals land on the\n *  same code. The normalized code is kept even when it falls outside the roster —\n *  argmax simply won't favor an out-of-roster context tag, but it stays in the\n *  audit trail.\n *\n *  The roster is accepted (and reserved) so a future revision can fold roster\n *  aliasing in without a signature change; today BCP-47 normalization alone\n *  reconciles the codes the producers emit. */\nfunction normalizeEvidence(\n  evidence: readonly LanguageEvidence[],\n  _candidates: readonly LanguageProfile[] | undefined,\n): LanguageEvidence[] {\n  return evidence.map((item) => {\n    if (item.language === \"unknown\") return item;\n    const normalized = normalizeBCP47(item.language) ?? item.language;\n    if (normalized === item.language) return item;\n    return { ...item, language: normalized };\n  });\n}\n\n/**\n * The scoring set under `nonDiscriminatingScript: \"unknown\"`. Two cuts:\n *\n *  1. Drop every *neutralized* non-discriminating script read (see\n *     {@link isNeutralized}) — it names a language only by being the lone\n *     candidate in its script, with nothing corroborating it.\n *  2. Drop context (page/transport) evidence whose language is in a **different\n *     script** than such a neutralized title. A foreign-script title's language\n *     is not the page's language: a Latin title on a `lang=\"uk\"` page must not\n *     resolve to `uk`. Same-script context (an explicit `en` `Content-Language`\n *     for a Latin title) survives and may still name — or, among same-script\n *     candidates, disambiguate — the title.\n *\n * The second cut needs each language's script, which is derived from the\n * candidate roster's alphabets. When `candidates` is absent the scripts can't be\n * derived, so the cut is skipped and behavior falls back to cut 1 alone (the\n * 0.3.0 behavior) — never throwing.\n */\nfunction filterForUnknownMode(\n  normalized: readonly LanguageEvidence[],\n  candidates: readonly LanguageProfile[] | undefined,\n): LanguageEvidence[] {\n  const surviving = normalized.filter((item) => !isNeutralized(item, normalized));\n\n  const titleScript = nonDiscriminatingTitleScript(normalized, candidates);\n  if (titleScript === null) return surviving;\n\n  const scriptOf = scriptByCode(candidates ?? []);\n  return surviving.filter((item) => {\n    // Keep the script reads themselves and anything whose script we can't place;\n    // only cross-script *context* in a known, different script is excluded.\n    if (SCRIPT_KINDS.has(item.kind) || item.language === \"unknown\") return true;\n    const itemScript = scriptOf.get(item.language);\n    return itemScript === undefined || itemScript === titleScript;\n  });\n}\n\n/** The script of the title under `\"unknown\"` mode, or `null` when there is no\n *  neutralized non-discriminating script read to anchor on (so no cross-script\n *  cut applies) or the roster can't place that read's language. */\nfunction nonDiscriminatingTitleScript(\n  normalized: readonly LanguageEvidence[],\n  candidates: readonly LanguageProfile[] | undefined,\n): ScriptName | null {\n  if (candidates === undefined) return null;\n  const scriptOf = scriptByCode(candidates);\n  for (const item of normalized) {\n    if (isNeutralized(item, normalized)) {\n      const script = scriptOf.get(item.language);\n      if (script !== undefined) return script;\n    }\n  }\n  return null;\n}\n\n/** Map each roster code to the script of its alphabet (Cyrillic/Latin). Codes\n *  whose alphabet carries no Cyrillic/Latin letter are omitted. */\nfunction scriptByCode(candidates: readonly LanguageProfile[]): Map<string, ScriptName> {\n  const map = new Map<string, ScriptName>();\n  for (const c of candidates) {\n    const script = scriptOfProfile(c);\n    if (script !== null) map.set(c.code, script);\n  }\n  return map;\n}\n\n/**\n * Whether a non-discriminating script read should score nothing (mode\n * `\"unknown\"`). True when `item` is a script kind flagged `discriminating:\n * false` (its winning script is owned by ≤1 roster candidate) AND no *non-script*\n * evidence corroborates its language. Corroboration must come from context kinds\n * (page tags, headers): two lone-candidate script reads agreeing is still two\n * defaults, not real evidence — so script kinds never corroborate one another.\n */\nfunction isNeutralized(item: LanguageEvidence, all: readonly LanguageEvidence[]): boolean {\n  if (item.discriminating !== false || !SCRIPT_KINDS.has(item.kind)) return false;\n  return !all.some(\n    (other) =>\n      other.language === item.language &&\n      other.language !== \"unknown\" &&\n      !SCRIPT_KINDS.has(other.kind),\n  );\n}\n\n/** The language of a *clear script* read confident enough to pin the verdict, or\n *  `null` when none qualifies. When two script reads disagree, the higher-\n *  confidence one pins (a tie leaves nothing pinned — argmax decides normally).\n *\n *  A read the caller weighed to `0` is silenced *here too*: it contributes no\n *  score, so it must not veto the rest of the evidence either. */\nfunction confidentScriptLanguage(\n  evidence: readonly LanguageEvidence[],\n  weights: Weights,\n): string | null {\n  let best: string | null = null;\n  let bestConfidence = 0;\n  for (const item of evidence) {\n    if (item.language === \"unknown\" || !SCRIPT_KINDS.has(item.kind)) continue;\n    if (weightFor(item, weights) === 0) continue;\n    const c = clamp01(item.confidence);\n    if (c < SCRIPT_CONFIDENCE_FLOOR) continue;\n    if (c > bestConfidence) {\n      bestConfidence = c;\n      best = item.language;\n    } else if (c === bestConfidence && item.language !== best) {\n      // Two equally-confident script reads for different languages — ambiguous.\n      best = null;\n    }\n  }\n  return best;\n}\n\n/**\n * Weighted argmax. When `pinned` is set (a confident script language), any\n * *other* language's score may only come from context kinds; that score is\n * capped so it can never exceed the pinned language. This enforces the guard\n * without discarding the context from the audit trail.\n */\nfunction argmax(\n  scores: Map<string, number>,\n  pinned: string | null,\n): { best: string | null; bestScore: number; secondScore: number } {\n  let best: string | null = null;\n  let bestScore = 0;\n  let secondScore = 0;\n  const pinnedScore = pinned !== null ? (scores.get(pinned) ?? 0) : 0;\n\n  for (const [language, raw] of scores) {\n    // Guard: a non-pinned language cannot out-score the pinned one.\n    const score = pinned !== null && language !== pinned ? Math.min(raw, pinnedScore) : raw;\n    if (score > bestScore) {\n      secondScore = bestScore;\n      bestScore = score;\n      best = language;\n    } else if (score > secondScore) {\n      secondScore = score;\n    }\n  }\n  // On a pinned tie (pinned capped equal to a context language), prefer pinned.\n  if (pinned !== null && best !== pinned && bestScore === pinnedScore && pinnedScore > 0) {\n    secondScore = bestScore;\n    best = pinned;\n    bestScore = pinnedScore;\n  }\n  return { best, bestScore, secondScore };\n}\n\nfunction clamp01(value: number): number {\n  if (!Number.isFinite(value)) return 0;\n  if (value < 0) return 0;\n  if (value > 1) return 1;\n  return value;\n}\n"]}

package/dist/{chunk-SOTZVW3I.js → chunk-VWKQLGB4.js}

@@ -11,6 +11,7 @@ var UNKNOWN = {
 var CYRILLIC_RE = /\p{Script=Cyrillic}/u;
 var LATIN_RE = /\p{Script=Latin}/u;
 var RUNG3_MIN_LENGTH = 24;
+var MINORITY_MIN_LETTERS = 8;
 function dominantScript(text) {
   let cyr = 0;
   let lat = 0;
@@ -21,6 +22,37 @@ function dominantScript(text) {
   if (cyr === 0 && lat === 0) return null;
   return cyr >= lat ? "cyrillic" : "latin";
 }
+var SCRIPT_RE = { cyrillic: CYRILLIC_RE, latin: LATIN_RE };
+var OTHER_SCRIPT = { cyrillic: "latin", latin: "cyrillic" };
+var SCRIPT_WORD_RE = {
+  cyrillic: /[\p{Script=Cyrillic}\p{M}'ʼ’-]*\p{Script=Cyrillic}[\p{Script=Cyrillic}\p{M}'ʼ’-]*/gu,
+  latin: /[\p{Script=Latin}\p{M}'’-]*\p{Script=Latin}[\p{Script=Latin}\p{M}'’-]*/gu
+};
+function scriptSpan(text, script) {
+  return (text.match(SCRIPT_WORD_RE[script]) ?? []).join(" ");
+}
+function countLetters(text, script) {
+  let n = 0;
+  for (const ch of text) if (SCRIPT_RE[script].test(ch)) n += 1;
+  return n;
+}
+function textInScope(text, scoped) {
+  const first = scoped[0];
+  const script = first === void 0 ? null : scriptOfProfile(first);
+  if (script === null) return text;
+  if (!SCRIPT_RE[OTHER_SCRIPT[script]].test(text)) return text;
+  return scriptSpan(text, script);
+}
+function candidatesIn(candidates, script) {
+  const seen = /* @__PURE__ */ new Set();
+  const out = [];
+  for (const c of candidates) {
+    if (scriptOfProfile(c) !== script || seen.has(c.code)) continue;
+    seen.add(c.code);
+    out.push(c);
+  }
+  return out;
+}
 function scriptOfProfile(profile) {
   for (const ch of profile.alphabet) {
     if (CYRILLIC_RE.test(ch)) return "cyrillic";
@@ -31,14 +63,7 @@ function scriptOfProfile(profile) {
 function scopeCandidates(text, candidates) {
   const script = dominantScript(text);
   if (script === null) return [];
-  const seen = /* @__PURE__ */ new Set();
-  const scoped = [];
-  for (const c of candidates) {
-    if (scriptOfProfile(c) !== script || seen.has(c.code)) continue;
-    seen.add(c.code);
-    scoped.push(c);
-  }
-  return scoped;
+  return candidatesIn(candidates, script);
 }
 var CONTRADICTION_SHARE = 0.02;
 var NO_CONTRADICTION = { letters: [], share: 0 };
@@ -133,12 +158,16 @@ function wordRung(tokens, scoped, tier, rung) {
   );
   return r ? { language: r.code, margin: r.margin, rung } : null;
 }
-function classifyBySnippet(text, candidates, rung3) {
+function classifyBySnippet(text, candidates, rung3, options = {}) {
   if (!text || candidates.length === 0) return UNKNOWN;
   const cleaned = stripNoise(text);
   const scoped = scopeCandidates(cleaned, candidates);
   if (scoped.length === 0) return UNKNOWN;
   const discriminating = scoped.length >= 2;
+  if (options.isolateScripts && !discriminating) {
+    const minority = minorityVerdict(cleaned, candidates, scoped);
+    if (minority) return minority;
+  }
   let alphabet;
   const settle = (verdict) => {
     const winner = scoped.find((c) => c.code === verdict.language);
@@ -150,10 +179,26 @@ function classifyBySnippet(text, candidates, rung3) {
   if (byLetter) return settle(byLetter);
   const tokens = tokenize(cleaned);
   if (tokens.length === 0) return UNKNOWN;
-  const byWord = wordRung(tokens, scoped, "function", "2a") ?? wordRung(tokens, scoped, "frequent", "2b") ?? rung3?.(cleaned, scoped);
+  const byWord = wordRung(tokens, scoped, "function", "2a") ?? wordRung(tokens, scoped, "frequent", "2b") ?? rung3?.(options.isolateScripts ? textInScope(cleaned, scoped) : cleaned, scoped);
   return byWord ? settle(byWord) : UNKNOWN;
 }
+function minorityVerdict(cleaned, candidates, dominant) {
+  const first = dominant[0];
+  const dominantScriptName = first === void 0 ? null : scriptOfProfile(first);
+  if (dominantScriptName === null) return null;
+  const script = OTHER_SCRIPT[dominantScriptName];
+  const scoped = candidatesIn(candidates, script);
+  if (scoped.length < 2) return null;
+  const span = scriptSpan(stripQuoted(cleaned), script);
+  if (countLetters(span, script) < MINORITY_MIN_LETTERS) return null;
+  const verdict = letterRung(span, scoped) ?? wordRung(tokenize(span), scoped, "function", "2a") ?? wordRung(tokenize(span), scoped, "frequent", "2b");
+  if (!verdict) return null;
+  const winner = scoped.find((c) => c.code === verdict.language);
+  const alphabet = alphabetOfScrubbed(stripQuoted(cleaned));
+  if (winner && contradictionOf(alphabet, winner).share >= CONTRADICTION_SHARE) return null;
+  return { ...verdict, discriminating: true };
+}
 
-export { CONTRADICTION_SHARE, FRANC_RUNG, RUNG3_MIN_LENGTH, classifyBySnippet, contradiction, contradictionOf, scopeCandidates, scriptOfProfile, textAlphabet };
-//# sourceMappingURL=chunk-SOTZVW3I.js.map
-//# sourceMappingURL=chunk-SOTZVW3I.js.map
+export { CONTRADICTION_SHARE, FRANC_RUNG, MINORITY_MIN_LETTERS, RUNG3_MIN_LENGTH, classifyBySnippet, contradiction, contradictionOf, scopeCandidates, scriptOfProfile, textAlphabet, textInScope };
+//# sourceMappingURL=chunk-VWKQLGB4.js.map
+//# sourceMappingURL=chunk-VWKQLGB4.js.map

package/dist/chunk-VWKQLGB4.js.map

@@ -0,0 +1 @@
+{"version":3,"sources":["../src/internal/classify.ts"],"names":[],"mappings":";;;AAsCO,IAAM,UAAA,GAAa;AA0B1B,IAAM,OAAA,GAA0B;AAAA,EAC9B,QAAA,EAAU,SAAA;AAAA,EACV,MAAA,EAAQ,CAAA;AAAA,EACR,IAAA,EAAM,IAAA;AAAA,EACN,cAAA,EAAgB;AAClB,CAAA;AAmBA,IAAM,WAAA,GAAc,sBAAA;AACpB,IAAM,QAAA,GAAW,mBAAA;AAOV,IAAM,gBAAA,GAAmB;AAKzB,IAAM,oBAAA,GAAuB;AA8BpC,SAAS,eAAe,IAAA,EAA2C;AACjE,EAAA,IAAI,GAAA,GAAM,CAAA;AACV,EAAA,IAAI,GAAA,GAAM,CAAA;AACV,EAAA,KAAA,MAAW,EAAA,IAAM,UAAA,CAAW,IAAI,CAAA,EAAG;AACjC,IAAA,IAAI,WAAA,CAAY,IAAA,CAAK,EAAE,CAAA,EAAG,GAAA,IAAO,CAAA;AAAA,SAAA,IACxB,QAAA,CAAS,IAAA,CAAK,EAAE,CAAA,EAAG,GAAA,IAAO,CAAA;AAAA,EACrC;AACA,EAAA,IAAI,GAAA,KAAQ,CAAA,IAAK,GAAA,KAAQ,CAAA,EAAG,OAAO,IAAA;AACnC,EAAA,OAAO,GAAA,IAAO,MAAM,UAAA,GAAa,OAAA;AACnC;AAEA,IAAM,SAAA,GAAwC,EAAE,QAAA,EAAU,WAAA,EAAa,OAAO,QAAA,EAAS;AACvF,IAAM,YAAA,GAA+C,EAAE,QAAA,EAAU,OAAA,EAAS,OAAO,UAAA,EAAW;AAI5F,IAAM,cAAA,GAA6C;AAAA,EACjD,QAAA,EAAU,qFAAA;AAAA,EACV,KAAA,EAAO;AACT,CAAA;AAGA,SAAS,UAAA,CAAW,MAAc,MAAA,EAA4B;AAC5D,EAAA,OAAA,CAAQ,IAAA,CAAK,MAAM,cAAA,CAAe,MAAM,CAAC,CAAA,IAAK,EAAC,EAAG,IAAA,CAAK,GAAG,CAAA;AAC5D;AAEA,SAAS,YAAA,CAAa,MAAc,MAAA,EAA4B;AAC9D,EAAA,IAAI,CAAA,GAAI,CAAA;AACR,EAAA,KAAA,MAAW,EAAA,IAAM,MAAM,IAAI,SAAA,CAAU,MAAM,CAAA,CAAE,IAAA,CAAK,EAAE,CAAA,EAAG,CAAA,IAAK,CAAA;AAC5D,EAAA,OAAO,CAAA;AACT;AAaO,SAAS,WAAA,CAAY,MAAc,MAAA,EAA4C;AACpF,EAAA,MAAM,KAAA,GAAQ,OAAO,CAAC,CAAA;AACtB,EAAA,MAAM,MAAA,GAAS,KAAA,KAAU,MAAA,GAAY,IAAA,GAAO,gBAAgB,KAAK,CAAA;AACjE,EAAA,IAAI,MAAA,KAAW,MAAM,OAAO,IAAA;AAC5B,EAAA,IAAI,CAAC,UAAU,YAAA,CAAa,MAAM,CAAC,CAAA,CAAE,IAAA,CAAK,IAAI,CAAA,EAAG,OAAO,IAAA;AACxD,EAAA,OAAO,UAAA,CAAW,MAAM,MAAM,CAAA;AAChC;AAGA,SAAS,YAAA,CACP,YACA,MAAA,EACK;AACL,EAAA,MAAM,IAAA,uBAAW,GAAA,EAAY;AAC7B,EAAA,MAAM,MAAW,EAAC;AAClB,EAAA,KAAA,MAAW,KAAK,UAAA,EAAY;AAC1B,IAAA,IAAI,eAAA,CAAgB,CAAC,CAAA,KAAM,MAAA,IAAU,KAAK,GAAA,CAAI,CAAA,CAAE,IAAI,CAAA,EAAG;AACvD,IAAA,IAAA,CAAK,GAAA,CAAI,EAAE,IAAI,CAAA;AACf,IAAA,GAAA,CAAI,KAAK,CAAC,CAAA;AAAA,EACZ;AACA,EAAA,OAAO,GAAA;AACT;AAMO,SAAS,gBAAgB,OAAA,EAA6C;AAC3E,EAAA,KAAA,MAAW,EAAA,IAAM,QAAQ,QAAA,EAAU;AACjC,IAAA,IAAI,WAAA,CAAY,IAAA,CAAK,EAAE,CAAA,EAAG,OAAO,UAAA;AACjC,IAAA,IAAI,QAAA,CAAS,IAAA,CAAK,EAAE,CAAA,EAAG,OAAO,OAAA;AAAA,EAChC;AACA,EAAA,OAAO,IAAA;AACT;AAMO,SAAS,eAAA,CACd,MACA,UAAA,EACK;AACL,EAAA,MAAM,MAAA,GAAS,eAAe,IAAI,CAAA;AAClC,EAAA,IAAI,MAAA,KAAW,IAAA,EAAM,OAAO,EAAC;AAI7B,EAAA,OAAO,YAAA,CAAa,YAAY,MAAM,CAAA;AACxC;AA2CO,IAAM,mBAAA,GAAsB;AAmBnC,IAAM,mBAAkC,EAAE,OAAA,EAAS,EAAC,EAAG,OAAO,CAAA,EAAE;AAGhE,SAAS,mBAAmB,QAAA,EAAgC;AAC1D,EAAA,MAAM,MAAA,uBAAa,GAAA,EAAoB;AACvC,EAAA,KAAA,MAAW,EAAA,IAAM,QAAA,CAAS,WAAA,EAAY,EAAG;AACvC,IAAA,IAAI,CAAC,YAAY,IAAA,CAAK,EAAE,KAAK,CAAC,QAAA,CAAS,IAAA,CAAK,EAAE,CAAA,EAAG;AACjD,IAAA,MAAA,CAAO,IAAI,EAAA,EAAA,CAAK,MAAA,CAAO,IAAI,EAAE,CAAA,IAAK,KAAK,CAAC,CAAA;AAAA,EAC1C;AACA,EAAA,OAAO,MAAA;AACT;AAeO,SAAS,aAAa,IAAA,EAA4B;AACvD,EAAA,OAAO,kBAAA,CAAmB,WAAA,CAAY,UAAA,CAAW,IAAI,CAAC,CAAC,CAAA;AACzD;AASO,SAAS,eAAA,CAAgB,UAAwB,OAAA,EAAyC;AAC/F,EAAA,MAAM,MAAA,GAAS,gBAAgB,OAAO,CAAA;AACtC,EAAA,IAAI,MAAA,KAAW,MAAM,OAAO,gBAAA;AAC5B,EAAA,MAAM,QAAA,GAAW,MAAA,KAAW,UAAA,GAAa,WAAA,GAAc,QAAA;AAKvD,EAAA,MAAM,MAAM,IAAI,GAAA,CAAI,QAAQ,QAAA,IAAY,OAAA,CAAQ,SAAS,EAAA,CAAG,CAAA;AAC5D,EAAA,MAAM,UAAoB,EAAC;AAC3B,EAAA,IAAI,OAAA,GAAU,CAAA;AACd,EAAA,IAAI,KAAA,GAAQ,CAAA;AACZ,EAAA,KAAA,MAAW,CAAC,EAAA,EAAI,KAAK,CAAA,IAAK,QAAA,EAAU;AAGlC,IAAA,IAAI,CAAC,QAAA,CAAS,IAAA,CAAK,EAAE,CAAA,EAAG;AACxB,IAAA,KAAA,IAAS,KAAA;AACT,IAAA,IAAI,GAAA,CAAI,GAAA,CAAI,EAAE,CAAA,EAAG;AACjB,IAAA,OAAA,IAAW,KAAA;AACX,IAAA,OAAA,CAAQ,KAAK,EAAE,CAAA;AAAA,EACjB;AACA,EAAA,OAAO,EAAE,OAAA,EAAS,KAAA,EAAO,UAAU,CAAA,GAAI,CAAA,GAAI,UAAU,KAAA,EAAM;AAC7D;AAkBO,SAAS,aAAA,CAAc,MAAc,OAAA,EAAyC;AACnF,EAAA,OAAO,eAAA,CAAgB,YAAA,CAAa,IAAI,CAAA,EAAG,OAAO,CAAA;AACpD;AAQA,SAAS,SAAS,IAAA,EAAwB;AACxC,EAAA,OAAO,KAAK,WAAA,EAAY,CAAE,KAAA,CAAM,UAAU,KAAK,EAAC;AAClD;AAOA,SAAS,KAAA,CAAM,OAAyB,UAAA,EAAwD;AAC9F,EAAA,MAAM,MAAA,GAAS,IAAI,GAAA,CAAoB,UAAA,CAAW,GAAA,CAAI,CAAC,CAAA,KAAM,CAAC,CAAA,CAAE,IAAA,EAAM,CAAC,CAAC,CAAC,CAAA;AACzE,EAAA,KAAA,MAAW,QAAQ,KAAA,EAAO;AACxB,IAAA,IAAI,KAAA,GAAuB,IAAA;AAC3B,IAAA,IAAI,MAAA,GAAS,CAAA;AACb,IAAA,KAAA,MAAW,KAAK,UAAA,EAAY;AAC1B,MAAA,IAAI,CAAA,CAAE,GAAA,CAAI,GAAA,CAAI,IAAI,CAAA,EAAG;AACnB,QAAA,MAAA,IAAU,CAAA;AACV,QAAA,IAAI,SAAS,CAAA,EAAG;AACd,UAAA,KAAA,GAAQ,IAAA;AACR,UAAA;AAAA,QACF;AACA,QAAA,KAAA,GAAQ,CAAA,CAAE,IAAA;AAAA,MACZ;AAAA,IACF;AACA,IAAA,IAAI,KAAA,KAAU,IAAA,EAAM,MAAA,CAAO,GAAA,CAAI,KAAA,EAAA,CAAQ,OAAO,GAAA,CAAI,KAAK,CAAA,IAAK,CAAA,IAAK,CAAC,CAAA;AAAA,EACpE;AACA,EAAA,OAAO,MAAA;AACT;AAGA,SAAS,OAAO,MAAA,EAAsE;AACpF,EAAA,IAAI,GAAA,GAAM,EAAA;AACV,EAAA,IAAI,MAAA,GAAS,EAAA;AACb,EAAA,IAAI,IAAA,GAAsB,IAAA;AAC1B,EAAA,KAAA,MAAW,CAAC,CAAA,EAAG,KAAK,CAAA,IAAK,MAAA,EAAQ;AAC/B,IAAA,IAAI,QAAQ,GAAA,EAAK;AACf,MAAA,MAAA,GAAS,GAAA;AACT,MAAA,GAAA,GAAM,KAAA;AACN,MAAA,IAAA,GAAO,CAAA;AAAA,IACT,CAAA,MAAA,IAAW,QAAQ,MAAA,EAAQ;AACzB,MAAA,MAAA,GAAS,KAAA;AAAA,IACX;AAAA,EACF;AACA,EAAA,IAAI,IAAA,KAAS,IAAA,IAAQ,GAAA,GAAM,CAAA,EAAG,OAAO,IAAA;AACrC,EAAA,MAAM,MAAA,GAAS,GAAA,GAAM,IAAA,CAAK,GAAA,CAAI,QAAQ,CAAC,CAAA;AACvC,EAAA,OAAO,MAAA,IAAU,CAAA,GAAI,EAAE,IAAA,EAAM,QAAO,GAAI,IAAA;AAC1C;AAEA,SAAS,aAAA,CACP,YACA,IAAA,EACc;AACd,EAAA,OAAO,UAAA,CAAW,GAAA,CAAI,CAAC,CAAA,MAAO,EAAE,IAAA,EAAM,CAAA,CAAE,IAAA,EAAM,GAAA,EAAK,IAAI,GAAA,CAAI,IAAA,CAAK,CAAC,CAAC,GAAE,CAAE,CAAA;AACxE;AAIA,SAAS,UAAA,CAAW,MAAc,MAAA,EAAwD;AACxF,EAAA,MAAM,CAAA,GAAI,MAAA;AAAA,IACR,KAAA;AAAA,MACE,KAAK,WAAA,EAAY;AAAA,MACjB,aAAA,CAAc,QAAQ,CAAC,CAAA,KAAM,EAAE,QAAA,IAAY,CAAA,CAAE,SAAS,EAAA,CAAG;AAAA;AAC3D,GACF;AACA,EAAA,OAAO,CAAA,GAAI,EAAE,QAAA,EAAU,CAAA,CAAE,IAAA,EAAM,QAAQ,CAAA,CAAE,MAAA,EAAQ,IAAA,EAAM,CAAA,EAAE,GAAI,IAAA;AAC/D;AAGA,SAAS,QAAA,CACP,MAAA,EACA,MAAA,EACA,IAAA,EACA,IAAA,EACoB;AACpB,EAAA,MAAM,CAAA,GAAI,MAAA;AAAA,IACR,KAAA;AAAA,MACE,MAAA;AAAA,MACA,aAAA,CAAc,QAAQ,CAAC,CAAA,KAAM,EAAE,KAAA,GAAQ,IAAI,CAAA,IAAK,EAAE;AAAA;AACpD,GACF;AACA,EAAA,OAAO,CAAA,GAAI,EAAE,QAAA,EAAU,CAAA,CAAE,MAAM,MAAA,EAAQ,CAAA,CAAE,MAAA,EAAQ,IAAA,EAAK,GAAI,IAAA;AAC5D;AAkBO,SAAS,kBACd,IAAA,EACA,UAAA,EACA,KAAA,EACA,OAAA,GAA2B,EAAC,EACZ;AAChB,EAAA,IAAI,CAAC,IAAA,IAAQ,UAAA,CAAW,MAAA,KAAW,GAAG,OAAO,OAAA;AAI7C,EAAA,MAAM,OAAA,GAAU,WAAW,IAAI,CAAA;AAG/B,EAAA,MAAM,MAAA,GAAS,eAAA,CAAgB,OAAA,EAAS,UAAU,CAAA;AAClD,EAAA,IAAI,MAAA,CAAO,MAAA,KAAW,CAAA,EAAG,OAAO,OAAA;AAKhC,EAAA,MAAM,cAAA,GAAiB,OAAO,MAAA,IAAU,CAAA;AAExC,EAAA,IAAI,OAAA,CAAQ,cAAA,IAAkB,CAAC,cAAA,EAAgB;AAC7C,IAAA,MAAM,QAAA,GAAW,eAAA,CAAgB,OAAA,EAAS,UAAA,EAAY,MAAM,CAAA;AAC5D,IAAA,IAAI,UAAU,OAAO,QAAA;AAAA,EACvB;AAsBA,EAAA,IAAI,QAAA;AACJ,EAAA,MAAM,MAAA,GAAS,CAAC,OAAA,KAAyC;AACvD,IAAA,MAAM,MAAA,GAAS,OAAO,IAAA,CAAK,CAAC,MAAM,CAAA,CAAE,IAAA,KAAS,QAAQ,QAAQ,CAAA;AAC7D,IAAA,QAAA,KAAa,kBAAA,CAAmB,WAAA,CAAY,OAAO,CAAC,CAAA;AACpD,IAAA,IAAI,UAAU,eAAA,CAAgB,QAAA,EAAU,MAAM,CAAA,CAAE,KAAA,IAAS,qBAAqB,OAAO,OAAA;AACrF,IAAA,OAAO,EAAE,GAAG,OAAA,EAAS,cAAA,EAAe;AAAA,EACtC,CAAA;AAEA,EAAA,MAAM,QAAA,GAAW,UAAA,CAAW,OAAA,EAAS,MAAM,CAAA;AAC3C,EAAA,IAAI,QAAA,EAAU,OAAO,MAAA,CAAO,QAAQ,CAAA;AAEpC,EAAA,MAAM,MAAA,GAAS,SAAS,OAAO,CAAA;AAC/B,EAAA,IAAI,MAAA,CAAO,MAAA,KAAW,CAAA,EAAG,OAAO,OAAA;AAEhC,EAAA,MAAM,MAAA,GACJ,SAAS,MAAA,EAAQ,MAAA,EAAQ,YAAY,IAAI,CAAA,IACzC,SAAS,MAAA,EAAQ,MAAA,EAAQ,YAAY,IAAI,CAAA,IACzC,QAAQ,OAAA,CAAQ,cAAA,GAAiB,YAAY,OAAA,EAAS,MAAM,CAAA,GAAI,OAAA,EAAS,MAAM,CAAA;AACjF,EAAA,OAAO,MAAA,GAAS,MAAA,CAAO,MAAM,CAAA,GAAI,OAAA;AACnC;AAUA,SAAS,eAAA,CACP,OAAA,EACA,UAAA,EACA,QAAA,EACuB;AACvB,EAAA,MAAM,KAAA,GAAQ,SAAS,CAAC,CAAA;AACxB,EAAA,MAAM,kBAAA,GAAqB,KAAA,KAAU,MAAA,GAAY,IAAA,GAAO,gBAAgB,KAAK,CAAA;AAC7E,EAAA,IAAI,kBAAA,KAAuB,MAAM,OAAO,IAAA;AACxC,EAAA,MAAM,MAAA,GAAS,aAAa,kBAAkB,CAAA;AAC9C,EAAA,MAAM,MAAA,GAAS,YAAA,CAAa,UAAA,EAAY,MAAM,CAAA;AAC9C,EAAA,IAAI,MAAA,CAAO,MAAA,GAAS,CAAA,EAAG,OAAO,IAAA;AAG9B,EAAA,MAAM,IAAA,GAAO,UAAA,CAAW,WAAA,CAAY,OAAO,GAAG,MAAM,CAAA;AACpD,EAAA,IAAI,YAAA,CAAa,IAAA,EAAM,MAAM,CAAA,GAAI,sBAAsB,OAAO,IAAA;AAE9D,EAAA,MAAM,UACJ,UAAA,CAAW,IAAA,EAAM,MAAM,CAAA,IACvB,QAAA,CAAS,SAAS,IAAI,CAAA,EAAG,QAAQ,UAAA,EAAY,IAAI,KACjD,QAAA,CAAS,QAAA,CAAS,IAAI,CAAA,EAAG,MAAA,EAAQ,YAAY,IAAI,CAAA;AACnD,EAAA,IAAI,CAAC,SAAS,OAAO,IAAA;AACrB,EAAA,MAAM,MAAA,GAAS,OAAO,IAAA,CAAK,CAAC,MAAM,CAAA,CAAE,IAAA,KAAS,QAAQ,QAAQ,CAAA;AAC7D,EAAA,MAAM,QAAA,GAAW,kBAAA,CAAmB,WAAA,CAAY,OAAO,CAAC,CAAA;AACxD,EAAA,IAAI,UAAU,eAAA,CAAgB,QAAA,EAAU,MAAM,CAAA,CAAE,KAAA,IAAS,qBAAqB,OAAO,IAAA;AACrF,EAAA,OAAO,EAAE,GAAG,OAAA,EAAS,cAAA,EAAgB,IAAA,EAAK;AAC5C","file":"chunk-VWKQLGB4.js","sourcesContent":["/**\n * Per-snippet language classification by candidate-set-relative set-difference.\n *\n * A ladder of rungs; the first rung whose leader clears a lead (margin) of ≥1\n * wins; otherwise `\"unknown\"`:\n *\n *   1   alphabet       — characters distinctive within the candidate set\n *   2a  function words — curated grammatical markers (highest precision)\n *   2b  frequent words — corpus content words\n *   3   franc          — optional trigram backstop for the distinctive-free\n *                        residual, injected as a resolver (this module stays\n *                        franc-free and importable without franc's tables)\n *\n * \"Distinctive\" is ALWAYS relative to the candidate set: a signal counts for a\n * candidate iff it appears in that candidate's profile and in NO other\n * candidate's. So `і` decides {uk, ru} (only uk has it) but is inert in\n * {uk, be} (both have it), and the word `и` decides {uk, ru} even though the\n * *letter* `и` is shared. Nothing is precomputed — uniqueness is the runtime\n * output, never stored.\n *\n * Above the ladder sits one veto. Ownership is additive evidence and can only\n * ever argue FOR a candidate, which leaves a closed set defenceless against text\n * written in a language it does not contain: Belarusian handed to {uk, ru} spends\n * its `і`s electing Ukrainian while its `ы`/`ў`/`э` — letters Ukrainian does not\n * have at all — count for nobody and stop nothing. So a winner is checked against\n * the text one last time, and a winner whose own alphabet cannot account for\n * {@link CONTRADICTION_SHARE} of it loses to `\"unknown\"`.\n *\n * Adapted to langtell's {@link LanguageProfile} shape: the `words` and `iso6393`\n * fields are optional here, so a bare `{ code, alphabet }` profile still\n * classifies on rung 1.\n */\nimport type { LanguageProfile } from \"../types.js\";\nimport { stripNoise, stripQuoted } from \"./scrub.js\";\n\n// Re-exported so the classifier stays the one door onto its own preprocessing.\nexport { stripNoise, stripQuoted } from \"./scrub.js\";\n\nexport const FRANC_RUNG = 3;\n\n/** Which rung decided a verdict; `null` when unknown. */\nexport type Rung = 1 | \"2a\" | \"2b\" | typeof FRANC_RUNG | null;\n\nexport interface SnippetVerdict {\n  /** Winning language code, or the sentinel `\"unknown\"`. */\n  language: string;\n  /** Lead of the winner over the runner-up, in the rung's own unit (distinctive\n   *  char/word count for rungs 1–2; franc score-gap for rung 3). 0 when unknown. */\n  margin: number;\n  /** Which rung decided; `null` when unknown. */\n  rung: Rung;\n  /** Whether ≥2 same-script candidates were in scope when the verdict was\n   *  reached. `true` ⇒ the distinctive-letter/word machinery actually chose\n   *  between candidates; `false` ⇒ the winner was the lone candidate in its\n   *  script, selected by script alone (no evidence it is *distinctively* that\n   *  language). `false` for `\"unknown\"`. */\n  discriminating: boolean;\n}\n\n/** A rung's verdict before {@link classifyBySnippet} stamps on the scope-derived\n *  `discriminating` flag (which a single rung can't know — it depends on how many\n *  same-script candidates were scoped). */\nexport type RungVerdict = Pick<SnippetVerdict, \"language\" | \"margin\" | \"rung\">;\n\nconst UNKNOWN: SnippetVerdict = {\n  language: \"unknown\",\n  margin: 0,\n  rung: null,\n  discriminating: false,\n};\n\n/** Resolver for rung 3 (the optional trigram backstop), injected into\n *  {@link classifyBySnippet} by callers that have franc available. Kept as an\n *  injected seam — not a direct import — so this module stays franc-free and\n *  importable without pulling franc's tables. Returns a rung-3 verdict or\n *  `null` (abstain).\n *\n *  Generic over the concrete profile type `P` the caller classifies with, so a\n *  consumer that defines a stricter profile (e.g. `words` required) can type its\n *  resolver over that exact shape and hand it to {@link classifyBySnippet} with\n *  no adapter — the resolver sees `readonly P[]`, the same array the classifier\n *  scoped from its input. Defaults to {@link LanguageProfile} for callers that\n *  don't narrow. */\nexport type Rung3Resolver<P extends LanguageProfile = LanguageProfile> = (\n  text: string,\n  scoped: readonly P[],\n) => RungVerdict | null;\n\nconst CYRILLIC_RE = /\\p{Script=Cyrillic}/u;\nconst LATIN_RE = /\\p{Script=Latin}/u;\n\n/** A coarse script bucket — the only two the candidate-relative classifier\n *  distinguishes today. `null` means \"no letters / undetermined\". */\nexport type ScriptName = \"cyrillic\" | \"latin\";\n\n/** Below this length, trigrams are too noisy to justify a rung-3 verdict. */\nexport const RUNG3_MIN_LENGTH = 24;\n\n/** Under {@link ClassifyOptions.isolateScripts}, the fewest letters a minority\n *  script must carry before it is classified on its own. A quoted word\n *  («привет») stays below it; a clause («Самые дешевые») clears it. */\nexport const MINORITY_MIN_LETTERS = 8;\n\n/** Options for {@link classifyBySnippet}. */\nexport interface ClassifyOptions {\n  /**\n   * Judge each script on its own evidence. Off by default; when on:\n   *\n   * - **A discriminating minority beats a non-discriminating majority.** When\n   *   the dominant script holds a lone candidate (its win is decided by script\n   *   alone, not evidence) and another script in the text holds ≥2 candidates\n   *   and at least {@link MINORITY_MIN_LETTERS} letters, that script's span is\n   *   classified on its own with rungs 1–2. A verdict there is returned; an\n   *   abstention falls back to the dominant-script verdict unchanged. Rung 3\n   *   never runs on the minority span — it is short by construction, and short\n   *   spans are where trigrams misread.\n   * - **The rung-3 resolver reads only the scope's own script** (see\n   *   {@link textInScope}), so another script's letters can't lift a short span\n   *   over a resolver's length floor nor add noise to its trigrams.\n   *\n   * Without this, «Самые дешевые в Украине | Victron Multiplus II 48V 6k5va»\n   * resolves to the lone Latin candidate (22 Latin letters outvote 20\n   * Cyrillic), and «Interview with Володимир Зеленський on CNN» reaches a\n   * trigram backstop on 42 characters when its Cyrillic is a 20-character name.\n   */\n  isolateScripts?: boolean;\n}\n\n/** The script most of `text` is written in, or `null` if it carries no letters.\n *  Noise (URLs/handles/hashtags) is stripped first so a single trailing link\n *  can't flip a multi-word Cyrillic title's vote to Latin. */\nfunction dominantScript(text: string): \"cyrillic\" | \"latin\" | null {\n  let cyr = 0;\n  let lat = 0;\n  for (const ch of stripNoise(text)) {\n    if (CYRILLIC_RE.test(ch)) cyr += 1;\n    else if (LATIN_RE.test(ch)) lat += 1;\n  }\n  if (cyr === 0 && lat === 0) return null;\n  return cyr >= lat ? \"cyrillic\" : \"latin\";\n}\n\nconst SCRIPT_RE: Record<ScriptName, RegExp> = { cyrillic: CYRILLIC_RE, latin: LATIN_RE };\nconst OTHER_SCRIPT: Record<ScriptName, ScriptName> = { cyrillic: \"latin\", latin: \"cyrillic\" };\n\n/** Word runs carrying at least one letter of the script, with the marks,\n *  apostrophes and hyphens that spell words inside it (`п'ять`, `Най-евтините`). */\nconst SCRIPT_WORD_RE: Record<ScriptName, RegExp> = {\n  cyrillic: /[\\p{Script=Cyrillic}\\p{M}'ʼ’-]*\\p{Script=Cyrillic}[\\p{Script=Cyrillic}\\p{M}'ʼ’-]*/gu,\n  latin: /[\\p{Script=Latin}\\p{M}'’-]*\\p{Script=Latin}[\\p{Script=Latin}\\p{M}'’-]*/gu,\n};\n\n/** The text's words in one script, space-joined. */\nfunction scriptSpan(text: string, script: ScriptName): string {\n  return (text.match(SCRIPT_WORD_RE[script]) ?? []).join(\" \");\n}\n\nfunction countLetters(text: string, script: ScriptName): number {\n  let n = 0;\n  for (const ch of text) if (SCRIPT_RE[script].test(ch)) n += 1;\n  return n;\n}\n\n/**\n * The part of `text` a scope can be judged on: its words in the scope's script,\n * when the text also carries letters of another script; otherwise `text`\n * unchanged.\n *\n * What a rung-3 resolver receives under {@link ClassifyOptions.isolateScripts}.\n * Exported so an off-path resolver (an oracle over raw candidates) feeds its\n * backstop exactly what the classifier would. Single-script text is passed\n * through byte-for-byte: rewriting it (dropping punctuation and digits) would\n * shift trigram scores on the common case for no gain.\n */\nexport function textInScope(text: string, scoped: readonly LanguageProfile[]): string {\n  const first = scoped[0];\n  const script = first === undefined ? null : scriptOfProfile(first);\n  if (script === null) return text;\n  if (!SCRIPT_RE[OTHER_SCRIPT[script]].test(text)) return text;\n  return scriptSpan(text, script);\n}\n\n/** Candidates in one script, one per code (see {@link scopeCandidates}). */\nfunction candidatesIn<P extends LanguageProfile>(\n  candidates: readonly P[],\n  script: ScriptName,\n): P[] {\n  const seen = new Set<string>();\n  const out: P[] = [];\n  for (const c of candidates) {\n    if (scriptOfProfile(c) !== script || seen.has(c.code)) continue;\n    seen.add(c.code);\n    out.push(c);\n  }\n  return out;\n}\n\n/** The script a profile's alphabet is written in, or `null` if it carries no\n *  Cyrillic/Latin letter. Exported so the fuser can derive each roster\n *  candidate's script without re-deriving the script regexes — a Latin alphabet\n *  ⇒ `\"latin\"`, a Cyrillic one ⇒ `\"cyrillic\"`. */\nexport function scriptOfProfile(profile: LanguageProfile): ScriptName | null {\n  for (const ch of profile.alphabet) {\n    if (CYRILLIC_RE.test(ch)) return \"cyrillic\";\n    if (LATIN_RE.test(ch)) return \"latin\";\n  }\n  return null;\n}\n\n/** Candidates whose script matches the text's dominant script (others can't tip\n *  the verdict). Empty when the text carries no letters. Generic over the\n *  concrete profile type `P`: the result is a subset of the input array, so it\n *  keeps `P` — a stricter caller's profiles stay strictly typed downstream. */\nexport function scopeCandidates<P extends LanguageProfile>(\n  text: string,\n  candidates: readonly P[],\n): P[] {\n  const script = dominantScript(text);\n  if (script === null) return [];\n  // Keep one profile per code. A language listed twice would otherwise make its\n  // own distinctive chars/words read as \"owned by ≥2 candidates\" in `tally`,\n  // cancelling them out and collapsing the verdict to \"unknown\".\n  return candidatesIn(candidates, script);\n}\n\n/**\n * Per-language set of characters globally unique within `profiles` — present in\n * exactly one profile's alphabet. Relative to the given profile set: the unique\n * set shrinks as languages are added (a second Latin language un-uniques a–z).\n */\nexport function distinctiveChars(profiles: readonly LanguageProfile[]): Map<string, Set<string>> {\n  const owners = new Map<string, string[]>();\n  for (const p of profiles) {\n    for (const ch of new Set(p.alphabet)) {\n      const list = owners.get(ch);\n      if (list) list.push(p.code);\n      else owners.set(ch, [p.code]);\n    }\n  }\n  const result = new Map<string, Set<string>>(profiles.map((p) => [p.code, new Set()]));\n  for (const [ch, codes] of owners) {\n    const [only] = codes;\n    if (codes.length === 1 && only !== undefined) result.get(only)?.add(ch);\n  }\n  return result;\n}\n\n/**\n * Share of a text's letters, in a profile's own script, that the profile's\n * alphabet does not contain — evidence AGAINST that profile.\n *\n * Beyond which a candidate is treated as contradicted by the text. Measured, not\n * picked: across a mixed corpus (Cyrillic siblings + Latin), the three\n * populations separate cleanly.\n *\n *   0.3–0.9 %  an in-language snippet quoting a sibling (a Ukrainian article\n *              carrying a Russian sentence, and vice versa)\n *   1.4–1.5 %  a foreign proper noun in otherwise monolingual prose\n *              (`Нұрсұлтан` in a Russian article, `Ђоковић` in another)\n *   2.3–17 %   text that is simply written in a language nobody on the roster\n *              profiles (Belarusian against {uk, ru}, German against {en})\n *\n * 2 % sits in the gap. It is deliberately nearer the incidental end: the cost of\n * vetoing too eagerly is an `\"unknown\"` a caller escalates, while the cost of\n * vetoing too late is a confident wrong language.\n */\nexport const CONTRADICTION_SHARE = 0.02;\n\n/**\n * A text's own alphabet: each letter it uses, and how often — its script's\n * letters only in the sense that non-letters are simply absent.\n *\n * Insertion-ordered, so a caller rendering it shows letters in the order the\n * reader met them rather than in an order a hash table chose.\n */\nexport type TextAlphabet = ReadonlyMap<string, number>;\n\n/** What one candidate's alphabet cannot account for in a text. */\nexport interface Contradiction {\n  /** The letters, distinct and in first-seen order. Empty when there are none. */\n  readonly letters: readonly string[];\n  /** Their weight, 0..1, against the letters of that candidate's script. */\n  readonly share: number;\n}\n\nconst NO_CONTRADICTION: Contradiction = { letters: [], share: 0 };\n\n/** {@link textAlphabet} over text a caller has already scrubbed. */\nfunction alphabetOfScrubbed(scrubbed: string): TextAlphabet {\n  const counts = new Map<string, number>();\n  for (const ch of scrubbed.toLowerCase()) {\n    if (!CYRILLIC_RE.test(ch) && !LATIN_RE.test(ch)) continue;\n    counts.set(ch, (counts.get(ch) ?? 0) + 1);\n  }\n  return counts;\n}\n\n/**\n * Derive the alphabet a text is written in, before asking anyone to account for\n * it.\n *\n * Derived ONCE and then compared against candidates, rather than re-walking the\n * text per candidate: for a screen reporting on a whole roster that is one pass\n * plus a set lookup each, and — more to the point — it makes \"the text's\n * alphabet\" a thing the caller can hold, print and diff, instead of a number\n * falling out of a comparison.\n *\n * Scrubbed first ({@link stripNoise}, {@link stripQuoted}): a URL's letters and\n * a quotation's letters are in the string without being the string's own.\n */\nexport function textAlphabet(text: string): TextAlphabet {\n  return alphabetOfScrubbed(stripQuoted(stripNoise(text)));\n}\n\n/**\n * Compare a derived {@link TextAlphabet} against one candidate.\n *\n * The primitive form, for a caller holding an alphabet and asking about several\n * candidates — an evidence report, an audit trail, a roster editor showing what\n * each choice would do.\n */\nexport function contradictionOf(alphabet: TextAlphabet, profile: LanguageProfile): Contradiction {\n  const script = scriptOfProfile(profile);\n  if (script === null) return NO_CONTRADICTION;\n  const inScript = script === \"cyrillic\" ? CYRILLIC_RE : LATIN_RE;\n  // `marks` joins the alphabet for the same reason it does at rung 1: an\n  // apostrophe is part of how uk/be spell, not a foreign letter. (It is not a\n  // letter, so it never reaches the alphabet — kept for the profiles whose\n  // marks ever grow to include one.)\n  const own = new Set(profile.alphabet + (profile.marks ?? \"\"));\n  const letters: string[] = [];\n  let foreign = 0;\n  let total = 0;\n  for (const [ch, count] of alphabet) {\n    // Only the candidate's own script is its business: a Cyrillic headline\n    // followed by a Latin brand name is not evidence against either language.\n    if (!inScript.test(ch)) continue;\n    total += count;\n    if (own.has(ch)) continue;\n    foreign += count;\n    letters.push(ch);\n  }\n  return { letters, share: total === 0 ? 0 : foreign / total };\n}\n\n/**\n * How much of `text` a candidate's own alphabet cannot account for.\n *\n * WHY THIS EXISTS AT ALL. The rung ladder is additive: it counts what each\n * candidate uniquely OWNS and never counts what a candidate cannot possibly\n * have written. Those are different questions, and the second one is the only\n * defence a closed set has against a language that is not in it. Belarusian\n * `Мова і культура Беларусі маюць багатую гісторыю` hands `і` to Ukrainian four\n * times over against {uk, ru} — while `ы`, a letter Ukrainian does not have,\n * sits in the same sentence saying the winner cannot be right. Ownership alone\n * cannot see that; this is what sees it.\n *\n * Exported so a caller that has to EXPLAIN a verdict (a diagnostics screen, an\n * audit trail) can show the same letters and the same number the veto acted on,\n * rather than deriving a second, drifting copy of them.\n */\nexport function contradiction(text: string, profile: LanguageProfile): Contradiction {\n  return contradictionOf(textAlphabet(text), profile);\n}\n\ninterface Membership {\n  code: string;\n  set: ReadonlySet<string>;\n}\n\n/** Lowercased Unicode letter-run tokens. Keeps single-char tokens (`і`, `и`). */\nfunction tokenize(text: string): string[] {\n  return text.toLowerCase().match(/\\p{L}+/gu) ?? [];\n}\n\n/**\n * Tally how many items (characters or word tokens) are distinctive to each\n * candidate — present in exactly one candidate's set. Items owned by zero or by\n * ≥2 candidates contribute nothing.\n */\nfunction tally(items: Iterable<string>, membership: readonly Membership[]): Map<string, number> {\n  const scores = new Map<string, number>(membership.map((m) => [m.code, 0]));\n  for (const item of items) {\n    let owner: string | null = null;\n    let owners = 0;\n    for (const m of membership) {\n      if (m.set.has(item)) {\n        owners += 1;\n        if (owners > 1) {\n          owner = null;\n          break;\n        }\n        owner = m.code;\n      }\n    }\n    if (owner !== null) scores.set(owner, (scores.get(owner) ?? 0) + 1);\n  }\n  return scores;\n}\n\n/** The leading candidate and its lead over the runner-up, or `null` if <1. */\nfunction leader(scores: Map<string, number>): { code: string; margin: number } | null {\n  let max = -1;\n  let second = -1;\n  let code: string | null = null;\n  for (const [c, score] of scores) {\n    if (score > max) {\n      second = max;\n      max = score;\n      code = c;\n    } else if (score > second) {\n      second = score;\n    }\n  }\n  if (code === null || max < 1) return null;\n  const margin = max - Math.max(second, 0);\n  return margin >= 1 ? { code, margin } : null;\n}\n\nfunction membershipFor(\n  candidates: readonly LanguageProfile[],\n  pick: (p: LanguageProfile) => Iterable<string>,\n): Membership[] {\n  return candidates.map((c) => ({ code: c.code, set: new Set(pick(c)) }));\n}\n\n/** Rung 1 — characters (alphabet + orthographic {@link LanguageProfile.marks})\n *  distinctive within the scoped candidate set. */\nfunction letterRung(text: string, scoped: readonly LanguageProfile[]): RungVerdict | null {\n  const r = leader(\n    tally(\n      text.toLowerCase(),\n      membershipFor(scoped, (p) => p.alphabet + (p.marks ?? \"\")),\n    ),\n  );\n  return r ? { language: r.code, margin: r.margin, rung: 1 } : null;\n}\n\n/** Rung 2 — distinctive words from the given tier (2a function, 2b frequent). */\nfunction wordRung(\n  tokens: readonly string[],\n  scoped: readonly LanguageProfile[],\n  tier: \"function\" | \"frequent\",\n  rung: \"2a\" | \"2b\",\n): RungVerdict | null {\n  const r = leader(\n    tally(\n      tokens,\n      membershipFor(scoped, (p) => p.words?.[tier] ?? []),\n    ),\n  );\n  return r ? { language: r.code, margin: r.margin, rung } : null;\n}\n\n/**\n * Classify `text` among `candidates`. Synchronous and allocation-light. Returns\n * `\"unknown\"` on empty evidence, on a tie inside the candidate set, when nothing\n * is distinctive, or when the winning candidate is contradicted by the text\n * itself (see {@link contradiction}).\n *\n * Generic over the concrete profile type `P`, inferred from `candidates`. The\n * optional `rung3` resolver is typed over the same `P`, so a consumer with a\n * stricter profile (e.g. `words` required) can pass its own resolver directly,\n * with no adapter — the resolver sees exactly the profiles the caller passed.\n * `P` defaults to {@link LanguageProfile}, so the bare two-argument form and\n * every existing call site are unchanged.\n *\n * `options` opts into behavior that is off by default — see\n * {@link ClassifyOptions}.\n */\nexport function classifyBySnippet<P extends LanguageProfile = LanguageProfile>(\n  text: string,\n  candidates: readonly P[],\n  rung3?: Rung3Resolver<P>,\n  options: ClassifyOptions = {},\n): SnippetVerdict {\n  if (!text || candidates.length === 0) return UNKNOWN;\n\n  // Drop URLs / @handles / #hashtags once, up front: trailing Latin noise must\n  // not flip the dominant-script vote nor pollute the per-rung tallies.\n  const cleaned = stripNoise(text);\n\n  // Restrict to candidates in the text's dominant script.\n  const scoped = scopeCandidates(cleaned, candidates);\n  if (scoped.length === 0) return UNKNOWN;\n\n  // ≥2 same-script candidates means the distinctive machinery actually had a\n  // choice to make; a lone scoped candidate wins by script alone. Stamped onto\n  // whichever rung decides — a single rung can't see the scope size.\n  const discriminating = scoped.length >= 2;\n\n  if (options.isolateScripts && !discriminating) {\n    const minority = minorityVerdict(cleaned, candidates, scoped);\n    if (minority) return minority;\n  }\n\n  /**\n   * A winner the text itself argues against is no winner — see\n   * {@link contradiction}.\n   *\n   * Applied to whichever rung decided, franc's included: every rung answers the\n   * same forced-choice question, so every rung can be forced into the same wrong\n   * answer by a language the roster does not carry. The runner-up is NOT\n   * promoted — a set that could not account for the text does not get a second\n   * guess at it. `\"unknown\"` is the honest answer, and the signal a caller needs\n   * to widen the roster or escalate.\n   *\n   * Measured over the text's alphabet MINUS its quotations, while the rungs\n   * above tallied the text whole. The asymmetry is deliberate and is the whole\n   * point of measuring separately: a quotation is someone else's language and\n   * cannot be held against this author, whereas removing it from the tally would\n   * silently re-decide verdicts that have nothing to do with this veto. One\n   * derivation, computed the first time a rung produces a winner.\n   */\n  // Derived on first use: the texts that never reach a verdict — most of them —\n  // never pay for it.\n  let alphabet: TextAlphabet | undefined;\n  const settle = (verdict: RungVerdict): SnippetVerdict => {\n    const winner = scoped.find((c) => c.code === verdict.language);\n    alphabet ??= alphabetOfScrubbed(stripQuoted(cleaned));\n    if (winner && contradictionOf(alphabet, winner).share >= CONTRADICTION_SHARE) return UNKNOWN;\n    return { ...verdict, discriminating };\n  };\n\n  const byLetter = letterRung(cleaned, scoped);\n  if (byLetter) return settle(byLetter);\n\n  const tokens = tokenize(cleaned);\n  if (tokens.length === 0) return UNKNOWN;\n\n  const byWord =\n    wordRung(tokens, scoped, \"function\", \"2a\") ??\n    wordRung(tokens, scoped, \"frequent\", \"2b\") ??\n    rung3?.(options.isolateScripts ? textInScope(cleaned, scoped) : cleaned, scoped);\n  return byWord ? settle(byWord) : UNKNOWN;\n}\n\n/**\n * Under {@link ClassifyOptions.isolateScripts}: the verdict of a minority\n * script that can actually choose between candidates, when the dominant one\n * cannot. Rungs 1–2 over that script's unquoted span, with the same\n * contradiction veto;\n * `null` when the span is too short, holds fewer than two candidates, or\n * abstains — the caller then keeps the dominant-script verdict.\n */\nfunction minorityVerdict(\n  cleaned: string,\n  candidates: readonly LanguageProfile[],\n  dominant: readonly LanguageProfile[],\n): SnippetVerdict | null {\n  const first = dominant[0];\n  const dominantScriptName = first === undefined ? null : scriptOfProfile(first);\n  if (dominantScriptName === null) return null;\n  const script = OTHER_SCRIPT[dominantScriptName];\n  const scoped = candidatesIn(candidates, script);\n  if (scoped.length < 2) return null;\n  // Quotations are someone else's words: an English title quoting a Russian\n  // slogan is not a Russian title (see {@link stripQuoted}).\n  const span = scriptSpan(stripQuoted(cleaned), script);\n  if (countLetters(span, script) < MINORITY_MIN_LETTERS) return null;\n\n  const verdict =\n    letterRung(span, scoped) ??\n    wordRung(tokenize(span), scoped, \"function\", \"2a\") ??\n    wordRung(tokenize(span), scoped, \"frequent\", \"2b\");\n  if (!verdict) return null;\n  const winner = scoped.find((c) => c.code === verdict.language);\n  const alphabet = alphabetOfScrubbed(stripQuoted(cleaned));\n  if (winner && contradictionOf(alphabet, winner).share >= CONTRADICTION_SHARE) return null;\n  return { ...verdict, discriminating: true };\n}\n"]}

package/dist/classify.d.ts

@@ -1,4 +1,4 @@
-import { L as LanguageProfile } from './types-DkB4436E.js';
+import { L as LanguageProfile } from './types-DbPJ0sxF.js';
 
 /**
  * Per-snippet language classification by candidate-set-relative set-difference.
@@ -70,6 +70,46 @@ type RungVerdict = Pick<SnippetVerdict, "language" | "margin" | "rung">;
 type Rung3Resolver<P extends LanguageProfile = LanguageProfile> = (text: string, scoped: readonly P[]) => RungVerdict | null;
 /** Below this length, trigrams are too noisy to justify a rung-3 verdict. */
 declare const RUNG3_MIN_LENGTH = 24;
+/** Under {@link ClassifyOptions.isolateScripts}, the fewest letters a minority
+ *  script must carry before it is classified on its own. A quoted word
+ *  («привет») stays below it; a clause («Самые дешевые») clears it. */
+declare const MINORITY_MIN_LETTERS = 8;
+/** Options for {@link classifyBySnippet}. */
+interface ClassifyOptions {
+    /**
+     * Judge each script on its own evidence. Off by default; when on:
+     *
+     * - **A discriminating minority beats a non-discriminating majority.** When
+     *   the dominant script holds a lone candidate (its win is decided by script
+     *   alone, not evidence) and another script in the text holds ≥2 candidates
+     *   and at least {@link MINORITY_MIN_LETTERS} letters, that script's span is
+     *   classified on its own with rungs 1–2. A verdict there is returned; an
+     *   abstention falls back to the dominant-script verdict unchanged. Rung 3
+     *   never runs on the minority span — it is short by construction, and short
+     *   spans are where trigrams misread.
+     * - **The rung-3 resolver reads only the scope's own script** (see
+     *   {@link textInScope}), so another script's letters can't lift a short span
+     *   over a resolver's length floor nor add noise to its trigrams.
+     *
+     * Without this, «Самые дешевые в Украине | Victron Multiplus II 48V 6k5va»
+     * resolves to the lone Latin candidate (22 Latin letters outvote 20
+     * Cyrillic), and «Interview with Володимир Зеленський on CNN» reaches a
+     * trigram backstop on 42 characters when its Cyrillic is a 20-character name.
+     */
+    isolateScripts?: boolean;
+}
+/**
+ * The part of `text` a scope can be judged on: its words in the scope's script,
+ * when the text also carries letters of another script; otherwise `text`
+ * unchanged.
+ *
+ * What a rung-3 resolver receives under {@link ClassifyOptions.isolateScripts}.
+ * Exported so an off-path resolver (an oracle over raw candidates) feeds its
+ * backstop exactly what the classifier would. Single-script text is passed
+ * through byte-for-byte: rewriting it (dropping punctuation and digits) would
+ * shift trigram scores on the common case for no gain.
+ */
+declare function textInScope(text: string, scoped: readonly LanguageProfile[]): string;
 /** Candidates whose script matches the text's dominant script (others can't tip
  *  the verdict). Empty when the text carries no letters. Generic over the
  *  concrete profile type `P`: the result is a subset of the input array, so it
@@ -161,7 +201,10 @@ declare function contradiction(text: string, profile: LanguageProfile): Contradi
  * with no adapter — the resolver sees exactly the profiles the caller passed.
  * `P` defaults to {@link LanguageProfile}, so the bare two-argument form and
  * every existing call site are unchanged.
+ *
+ * `options` opts into behavior that is off by default — see
+ * {@link ClassifyOptions}.
  */
-declare function classifyBySnippet<P extends LanguageProfile = LanguageProfile>(text: string, candidates: readonly P[], rung3?: Rung3Resolver<P>): SnippetVerdict;
+declare function classifyBySnippet<P extends LanguageProfile = LanguageProfile>(text: string, candidates: readonly P[], rung3?: Rung3Resolver<P>, options?: ClassifyOptions): SnippetVerdict;
 
-export { CONTRADICTION_SHARE, type Contradiction, FRANC_RUNG, RUNG3_MIN_LENGTH, type Rung, type Rung3Resolver, type RungVerdict, type SnippetVerdict, type TextAlphabet, classifyBySnippet, contradiction, contradictionOf, scopeCandidates, textAlphabet };
+export { CONTRADICTION_SHARE, type ClassifyOptions, type Contradiction, FRANC_RUNG, MINORITY_MIN_LETTERS, RUNG3_MIN_LENGTH, type Rung, type Rung3Resolver, type RungVerdict, type SnippetVerdict, type TextAlphabet, classifyBySnippet, contradiction, contradictionOf, scopeCandidates, textAlphabet, textInScope };

package/dist/classify.js

@@ -1,4 +1,4 @@
-export { CONTRADICTION_SHARE, FRANC_RUNG, RUNG3_MIN_LENGTH, classifyBySnippet, contradiction, contradictionOf, scopeCandidates, textAlphabet } from './chunk-SOTZVW3I.js';
+export { CONTRADICTION_SHARE, FRANC_RUNG, MINORITY_MIN_LETTERS, RUNG3_MIN_LENGTH, classifyBySnippet, contradiction, contradictionOf, scopeCandidates, textAlphabet, textInScope } from './chunk-VWKQLGB4.js';
 import './chunk-2Z7REIOE.js';
 //# sourceMappingURL=classify.js.map
 //# sourceMappingURL=classify.js.map

package/dist/franc.d.ts

@@ -1,10 +1,11 @@
-import { L as LanguageProfile, S as SyncSource, a as LanguageEvidence } from './types-DkB4436E.js';
+import { L as LanguageProfile, S as SyncSource, a as LanguageEvidence } from './types-DbPJ0sxF.js';
+import { ClassifyOptions } from './classify.js';
 
 /**
  * Producer: the franc trigram backstop over `text`, scoped to `candidates`.
  * Synchronous — franc itself is sync. Emits at most one `kind: "franc"` item.
  */
-declare function evidenceFromFranc(text: string | undefined, candidates: readonly LanguageProfile[] | undefined): LanguageEvidence[];
+declare function evidenceFromFranc(text: string | undefined, candidates: readonly LanguageProfile[] | undefined, options?: Pick<ClassifyOptions, "isolateScripts">): LanguageEvidence[];
 /**
  * Build a franc {@link SyncSource} bound to a candidate roster, for use in
  * `compile({ engines: [createFrancEngine(candidates)] })`. franc needs the
@@ -14,7 +15,7 @@ declare function evidenceFromFranc(text: string | undefined, candidates: readonl
  * A `SyncSource` (not async): franc runs in-process and synchronously, so the
  * compiled `detect` stays synchronous — no `await` ceremony on the hot path.
  */
-declare function createFrancEngine(candidates: readonly LanguageProfile[]): SyncSource;
+declare function createFrancEngine(candidates: readonly LanguageProfile[], options?: Pick<ClassifyOptions, "isolateScripts">): SyncSource;
 /**
  * A bare franc engine with no bound roster — it abstains until given candidates.
  * Prefer {@link createFrancEngine} with your roster; this default exists so the

package/dist/franc.js

@@ -1,4 +1,4 @@
-import { scopeCandidates } from './chunk-SOTZVW3I.js';
+import { scopeCandidates, textInScope } from './chunk-VWKQLGB4.js';
 import './chunk-2Z7REIOE.js';
 import { francAll } from 'franc';
 
@@ -17,11 +17,13 @@ function francScore(text, scoped) {
   if (language === void 0) return null;
   return { language, margin: top[1] - (ranked[1]?.[1] ?? 0) };
 }
-function evidenceFromFranc(text, candidates) {
+function evidenceFromFranc(text, candidates, options = {}) {
   if (text === void 0 || text.trim().length < RUNG_MIN_LENGTH) return [];
   if (candidates === void 0 || candidates.length === 0) return [];
   const scoped = scopeCandidates(text, candidates);
-  const scored = francScore(text, scoped);
+  const sample = options.isolateScripts ? textInScope(text, scoped) : text;
+  if (sample.trim().length < RUNG_MIN_LENGTH) return [];
+  const scored = francScore(sample, scoped);
   if (scored === null) return [];
   return [
     {
@@ -34,12 +36,12 @@ function evidenceFromFranc(text, candidates) {
     }
   ];
 }
-function createFrancEngine(candidates) {
+function createFrancEngine(candidates, options = {}) {
   return {
     id: "franc",
     sync: true,
     inputs: ["text"],
-    detect: (input) => evidenceFromFranc(input.text, candidates)
+    detect: (input) => evidenceFromFranc(input.text, candidates, options)
   };
 }
 var francEngine = {

package/dist/franc.js.map

@@ -1 +1 @@
-{"version":3,"sources":["../src/franc.ts"],"names":[],"mappings":";;;;AAmBA,IAAM,eAAA,GAAkB,EAAA;AAExB,IAAM,gBAAA,GAAmB,EAAA;AAEzB,IAAM,iBAAA,GAAoB,GAAA;AAQ1B,SAAS,UAAA,CACP,MACA,MAAA,EAC6C;AAC7C,EAAA,MAAM,KAAA,uBAAY,GAAA,EAAoB;AACtC,EAAA,KAAA,MAAW,CAAA,IAAK,MAAA,EAAQ,IAAI,CAAA,CAAE,OAAA,KAAY,MAAA,EAAW,KAAA,CAAM,GAAA,CAAI,CAAA,CAAE,OAAA,EAAS,CAAA,CAAE,IAAI,CAAA;AAChF,EAAA,IAAI,KAAA,CAAM,IAAA,GAAO,CAAA,EAAG,OAAO,IAAA;AAC3B,EAAA,MAAM,MAAA,GAAS,IAAA,CAAK,KAAA,CAAM,CAAA,EAAG,iBAAiB,CAAA;AAC9C,EAAA,MAAM,MAAA,GAAS,QAAA,CAAS,MAAA,EAAQ,EAAE,IAAA,EAAM,CAAC,GAAG,KAAA,CAAM,IAAA,EAAM,CAAA,EAAG,SAAA,EAAW,kBAAkB,CAAA;AACxF,EAAA,MAAM,GAAA,GAAM,OAAO,CAAC,CAAA;AACpB,EAAA,IAAI,CAAC,GAAA,IAAO,GAAA,CAAI,CAAC,CAAA,KAAM,OAAO,OAAO,IAAA;AACrC,EAAA,MAAM,QAAA,GAAW,KAAA,CAAM,GAAA,CAAI,GAAA,CAAI,CAAC,CAAC,CAAA;AACjC,EAAA,IAAI,QAAA,KAAa,QAAW,OAAO,IAAA;AACnC,EAAA,OAAO,EAAE,QAAA,EAAU,MAAA,EAAQ,GAAA,CAAI,CAAC,CAAA,IAAK,MAAA,CAAO,CAAC,CAAA,GAAI,CAAC,CAAA,IAAK,CAAA,CAAA,EAAG;AAC5D;AAMO,SAAS,iBAAA,CACd,MACA,UAAA,EACoB;AACpB,EAAA,IAAI,IAAA,KAAS,UAAa,IAAA,CAAK,IAAA,GAAO,MAAA,GAAS,eAAA,SAAwB,EAAC;AACxE,EAAA,IAAI,eAAe,MAAA,IAAa,UAAA,CAAW,MAAA,KAAW,CAAA,SAAU,EAAC;AAEjE,EAAA,MAAM,MAAA,GAAS,eAAA,CAAgB,IAAA,EAAM,UAAU,CAAA;AAC/C,EAAA,MAAM,MAAA,GAAS,UAAA,CAAW,IAAA,EAAM,MAAM,CAAA;AACtC,EAAA,IAAI,MAAA,KAAW,IAAA,EAAM,OAAO,EAAC;AAE7B,EAAA,OAAO;AAAA,IACL;AAAA,MACE,IAAA,EAAM,OAAA;AAAA,MACN,UAAU,MAAA,CAAO,QAAA;AAAA;AAAA,MAEjB,UAAA,EAAY,OAAA,CAAQ,GAAA,GAAM,MAAA,CAAO,SAAS,GAAG,CAAA;AAAA,MAC7C,MAAA,EAAQ,OAAA;AAAA,MACR,OAAO,MAAA,CAAO;AAAA;AAChB,GACF;AACF;AAWO,SAAS,kBAAkB,UAAA,EAAoD;AACpF,EAAA,OAAO;AAAA,IACL,EAAA,EAAI,OAAA;AAAA,IACJ,IAAA,EAAM,IAAA;AAAA,IACN,MAAA,EAAQ,CAAC,MAAM,CAAA;AAAA,IACf,QAAQ,CAAC,KAAA,KAAU,iBAAA,CAAkB,KAAA,CAAM,MAAM,UAAU;AAAA,GAC7D;AACF;AAOO,IAAM,WAAA,GAA0B;AAAA,EACrC,EAAA,EAAI,OAAA;AAAA,EACJ,IAAA,EAAM,IAAA;AAAA,EACN,MAAA,EAAQ,CAAC,MAAM,CAAA;AAAA,EACf,QAAQ,CAAC,KAAA,KAAU,iBAAA,CAAkB,KAAA,CAAM,MAAM,MAAS;AAC5D;AAEA,SAAS,QAAQ,KAAA,EAAuB;AACtC,EAAA,IAAI,CAAC,MAAA,CAAO,QAAA,CAAS,KAAK,GAAG,OAAO,CAAA;AACpC,EAAA,IAAI,KAAA,GAAQ,GAAG,OAAO,CAAA;AACtB,EAAA,IAAI,KAAA,GAAQ,GAAG,OAAO,CAAA;AACtB,EAAA,OAAO,KAAA;AACT","file":"franc.js","sourcesContent":["/**\n * `langtell/franc` — the opt-in franc engine (trigram-based detection, ~187\n * languages). Importing this module statically pulls `franc` and its trigram\n * tables, so it lives behind its own subpath; the zero-dependency core never\n * imports it (enforced by an ESLint boundary rule). `franc` is declared as an\n * OPTIONAL peer dependency — install it only if you use this engine.\n *\n * The engine is a candidate-relative *backstop*: franc is scoped to the\n * candidates' ISO 639-3 codes (`only`), runs only on text past a length floor\n * where trigrams are reliable, and emits `kind: \"franc\"` evidence with franc's\n * own score-gap as the confidence. It abstains (emits nothing) when fewer than\n * two candidates carry an `iso6393`, when franc returns `und`, or when the\n * sample is too short.\n */\nimport { francAll } from \"franc\";\nimport type { LanguageEvidence, LanguageProfile, SyncSource } from \"./types.js\";\nimport { scopeCandidates } from \"./internal/classify.js\";\n\n/** Minimum sample length, in characters. Below this trigrams are too noisy. */\nconst RUNG_MIN_LENGTH = 24;\n/** Floor franc itself uses to bail to `und` rather than guess. */\nconst FRANC_MIN_LENGTH = 10;\n/** Cap on text length sent to franc (longer adds cost, not accuracy). */\nconst DEFAULT_MAX_CHARS = 2000;\n\n/**\n * Run franc scoped to the candidates' ISO 639-3 codes, mapping the winner back\n * to its BCP-47 code. Returns `null` when fewer than two candidates carry an\n * `iso6393` code or franc abstains (`und`). The margin is franc's own score-gap\n * (top1 − top2, 0..1).\n */\nfunction francScore(\n  text: string,\n  scoped: readonly LanguageProfile[],\n): { language: string; margin: number } | null {\n  const byIso = new Map<string, string>();\n  for (const c of scoped) if (c.iso6393 !== undefined) byIso.set(c.iso6393, c.code);\n  if (byIso.size < 2) return null;\n  const sample = text.slice(0, DEFAULT_MAX_CHARS);\n  const ranked = francAll(sample, { only: [...byIso.keys()], minLength: FRANC_MIN_LENGTH });\n  const top = ranked[0];\n  if (!top || top[0] === \"und\") return null;\n  const language = byIso.get(top[0]);\n  if (language === undefined) return null;\n  return { language, margin: top[1] - (ranked[1]?.[1] ?? 0) };\n}\n\n/**\n * Producer: the franc trigram backstop over `text`, scoped to `candidates`.\n * Synchronous — franc itself is sync. Emits at most one `kind: \"franc\"` item.\n */\nexport function evidenceFromFranc(\n  text: string | undefined,\n  candidates: readonly LanguageProfile[] | undefined,\n): LanguageEvidence[] {\n  if (text === undefined || text.trim().length < RUNG_MIN_LENGTH) return [];\n  if (candidates === undefined || candidates.length === 0) return [];\n\n  const scoped = scopeCandidates(text, candidates);\n  const scored = francScore(text, scoped);\n  if (scored === null) return [];\n\n  return [\n    {\n      kind: \"franc\",\n      language: scored.language,\n      // franc's score-gap is 0..1; lift it into a usable confidence band.\n      confidence: clamp01(0.4 + scored.margin * 0.5),\n      source: \"franc\",\n      value: scored.language,\n    },\n  ];\n}\n\n/**\n * Build a franc {@link SyncSource} bound to a candidate roster, for use in\n * `compile({ engines: [createFrancEngine(candidates)] })`. franc needs the\n * roster to scope its `only` restriction, so it is bound at construction (the\n * same shape `compile` uses to bind the built-in text producer).\n *\n * A `SyncSource` (not async): franc runs in-process and synchronously, so the\n * compiled `detect` stays synchronous — no `await` ceremony on the hot path.\n */\nexport function createFrancEngine(candidates: readonly LanguageProfile[]): SyncSource {\n  return {\n    id: \"franc\",\n    sync: true,\n    inputs: [\"text\"],\n    detect: (input) => evidenceFromFranc(input.text, candidates),\n  };\n}\n\n/**\n * A bare franc engine with no bound roster — it abstains until given candidates.\n * Prefer {@link createFrancEngine} with your roster; this default exists so the\n * engine has a stable named export and a no-config import works.\n */\nexport const francEngine: SyncSource = {\n  id: \"franc\",\n  sync: true,\n  inputs: [\"text\"],\n  detect: (input) => evidenceFromFranc(input.text, undefined),\n};\n\nfunction clamp01(value: number): number {\n  if (!Number.isFinite(value)) return 0;\n  if (value < 0) return 0;\n  if (value > 1) return 1;\n  return value;\n}\n"]}
+{"version":3,"sources":["../src/franc.ts"],"names":[],"mappings":";;;;AAmBA,IAAM,eAAA,GAAkB,EAAA;AAExB,IAAM,gBAAA,GAAmB,EAAA;AAEzB,IAAM,iBAAA,GAAoB,GAAA;AAQ1B,SAAS,UAAA,CACP,MACA,MAAA,EAC6C;AAC7C,EAAA,MAAM,KAAA,uBAAY,GAAA,EAAoB;AACtC,EAAA,KAAA,MAAW,CAAA,IAAK,MAAA,EAAQ,IAAI,CAAA,CAAE,OAAA,KAAY,MAAA,EAAW,KAAA,CAAM,GAAA,CAAI,CAAA,CAAE,OAAA,EAAS,CAAA,CAAE,IAAI,CAAA;AAChF,EAAA,IAAI,KAAA,CAAM,IAAA,GAAO,CAAA,EAAG,OAAO,IAAA;AAC3B,EAAA,MAAM,MAAA,GAAS,IAAA,CAAK,KAAA,CAAM,CAAA,EAAG,iBAAiB,CAAA;AAC9C,EAAA,MAAM,MAAA,GAAS,QAAA,CAAS,MAAA,EAAQ,EAAE,IAAA,EAAM,CAAC,GAAG,KAAA,CAAM,IAAA,EAAM,CAAA,EAAG,SAAA,EAAW,kBAAkB,CAAA;AACxF,EAAA,MAAM,GAAA,GAAM,OAAO,CAAC,CAAA;AACpB,EAAA,IAAI,CAAC,GAAA,IAAO,GAAA,CAAI,CAAC,CAAA,KAAM,OAAO,OAAO,IAAA;AACrC,EAAA,MAAM,QAAA,GAAW,KAAA,CAAM,GAAA,CAAI,GAAA,CAAI,CAAC,CAAC,CAAA;AACjC,EAAA,IAAI,QAAA,KAAa,QAAW,OAAO,IAAA;AACnC,EAAA,OAAO,EAAE,QAAA,EAAU,MAAA,EAAQ,GAAA,CAAI,CAAC,CAAA,IAAK,MAAA,CAAO,CAAC,CAAA,GAAI,CAAC,CAAA,IAAK,CAAA,CAAA,EAAG;AAC5D;AAMO,SAAS,iBAAA,CACd,IAAA,EACA,UAAA,EACA,OAAA,GAAmD,EAAC,EAChC;AACpB,EAAA,IAAI,IAAA,KAAS,UAAa,IAAA,CAAK,IAAA,GAAO,MAAA,GAAS,eAAA,SAAwB,EAAC;AACxE,EAAA,IAAI,eAAe,MAAA,IAAa,UAAA,CAAW,MAAA,KAAW,CAAA,SAAU,EAAC;AAEjE,EAAA,MAAM,MAAA,GAAS,eAAA,CAAgB,IAAA,EAAM,UAAU,CAAA;AAG/C,EAAA,MAAM,SAAS,OAAA,CAAQ,cAAA,GAAiB,WAAA,CAAY,IAAA,EAAM,MAAM,CAAA,GAAI,IAAA;AACpE,EAAA,IAAI,OAAO,IAAA,EAAK,CAAE,MAAA,GAAS,eAAA,SAAwB,EAAC;AACpD,EAAA,MAAM,MAAA,GAAS,UAAA,CAAW,MAAA,EAAQ,MAAM,CAAA;AACxC,EAAA,IAAI,MAAA,KAAW,IAAA,EAAM,OAAO,EAAC;AAE7B,EAAA,OAAO;AAAA,IACL;AAAA,MACE,IAAA,EAAM,OAAA;AAAA,MACN,UAAU,MAAA,CAAO,QAAA;AAAA;AAAA,MAEjB,UAAA,EAAY,OAAA,CAAQ,GAAA,GAAM,MAAA,CAAO,SAAS,GAAG,CAAA;AAAA,MAC7C,MAAA,EAAQ,OAAA;AAAA,MACR,OAAO,MAAA,CAAO;AAAA;AAChB,GACF;AACF;AAWO,SAAS,iBAAA,CACd,UAAA,EACA,OAAA,GAAmD,EAAC,EACxC;AACZ,EAAA,OAAO;AAAA,IACL,EAAA,EAAI,OAAA;AAAA,IACJ,IAAA,EAAM,IAAA;AAAA,IACN,MAAA,EAAQ,CAAC,MAAM,CAAA;AAAA,IACf,QAAQ,CAAC,KAAA,KAAU,kBAAkB,KAAA,CAAM,IAAA,EAAM,YAAY,OAAO;AAAA,GACtE;AACF;AAOO,IAAM,WAAA,GAA0B;AAAA,EACrC,EAAA,EAAI,OAAA;AAAA,EACJ,IAAA,EAAM,IAAA;AAAA,EACN,MAAA,EAAQ,CAAC,MAAM,CAAA;AAAA,EACf,QAAQ,CAAC,KAAA,KAAU,iBAAA,CAAkB,KAAA,CAAM,MAAM,MAAS;AAC5D;AAEA,SAAS,QAAQ,KAAA,EAAuB;AACtC,EAAA,IAAI,CAAC,MAAA,CAAO,QAAA,CAAS,KAAK,GAAG,OAAO,CAAA;AACpC,EAAA,IAAI,KAAA,GAAQ,GAAG,OAAO,CAAA;AACtB,EAAA,IAAI,KAAA,GAAQ,GAAG,OAAO,CAAA;AACtB,EAAA,OAAO,KAAA;AACT","file":"franc.js","sourcesContent":["/**\n * `langtell/franc` — the opt-in franc engine (trigram-based detection, ~187\n * languages). Importing this module statically pulls `franc` and its trigram\n * tables, so it lives behind its own subpath; the zero-dependency core never\n * imports it (enforced by an ESLint boundary rule). `franc` is declared as an\n * OPTIONAL peer dependency — install it only if you use this engine.\n *\n * The engine is a candidate-relative *backstop*: franc is scoped to the\n * candidates' ISO 639-3 codes (`only`), runs only on text past a length floor\n * where trigrams are reliable, and emits `kind: \"franc\"` evidence with franc's\n * own score-gap as the confidence. It abstains (emits nothing) when fewer than\n * two candidates carry an `iso6393`, when franc returns `und`, or when the\n * sample is too short.\n */\nimport { francAll } from \"franc\";\nimport type { LanguageEvidence, LanguageProfile, SyncSource } from \"./types.js\";\nimport { scopeCandidates, textInScope, type ClassifyOptions } from \"./internal/classify.js\";\n\n/** Minimum sample length, in characters. Below this trigrams are too noisy. */\nconst RUNG_MIN_LENGTH = 24;\n/** Floor franc itself uses to bail to `und` rather than guess. */\nconst FRANC_MIN_LENGTH = 10;\n/** Cap on text length sent to franc (longer adds cost, not accuracy). */\nconst DEFAULT_MAX_CHARS = 2000;\n\n/**\n * Run franc scoped to the candidates' ISO 639-3 codes, mapping the winner back\n * to its BCP-47 code. Returns `null` when fewer than two candidates carry an\n * `iso6393` code or franc abstains (`und`). The margin is franc's own score-gap\n * (top1 − top2, 0..1).\n */\nfunction francScore(\n  text: string,\n  scoped: readonly LanguageProfile[],\n): { language: string; margin: number } | null {\n  const byIso = new Map<string, string>();\n  for (const c of scoped) if (c.iso6393 !== undefined) byIso.set(c.iso6393, c.code);\n  if (byIso.size < 2) return null;\n  const sample = text.slice(0, DEFAULT_MAX_CHARS);\n  const ranked = francAll(sample, { only: [...byIso.keys()], minLength: FRANC_MIN_LENGTH });\n  const top = ranked[0];\n  if (!top || top[0] === \"und\") return null;\n  const language = byIso.get(top[0]);\n  if (language === undefined) return null;\n  return { language, margin: top[1] - (ranked[1]?.[1] ?? 0) };\n}\n\n/**\n * Producer: the franc trigram backstop over `text`, scoped to `candidates`.\n * Synchronous — franc itself is sync. Emits at most one `kind: \"franc\"` item.\n */\nexport function evidenceFromFranc(\n  text: string | undefined,\n  candidates: readonly LanguageProfile[] | undefined,\n  options: Pick<ClassifyOptions, \"isolateScripts\"> = {},\n): LanguageEvidence[] {\n  if (text === undefined || text.trim().length < RUNG_MIN_LENGTH) return [];\n  if (candidates === undefined || candidates.length === 0) return [];\n\n  const scoped = scopeCandidates(text, candidates);\n  // Under `isolateScripts`, franc reads only the scope's own script, and the\n  // length floor is measured on what it reads (see `textInScope`).\n  const sample = options.isolateScripts ? textInScope(text, scoped) : text;\n  if (sample.trim().length < RUNG_MIN_LENGTH) return [];\n  const scored = francScore(sample, scoped);\n  if (scored === null) return [];\n\n  return [\n    {\n      kind: \"franc\",\n      language: scored.language,\n      // franc's score-gap is 0..1; lift it into a usable confidence band.\n      confidence: clamp01(0.4 + scored.margin * 0.5),\n      source: \"franc\",\n      value: scored.language,\n    },\n  ];\n}\n\n/**\n * Build a franc {@link SyncSource} bound to a candidate roster, for use in\n * `compile({ engines: [createFrancEngine(candidates)] })`. franc needs the\n * roster to scope its `only` restriction, so it is bound at construction (the\n * same shape `compile` uses to bind the built-in text producer).\n *\n * A `SyncSource` (not async): franc runs in-process and synchronously, so the\n * compiled `detect` stays synchronous — no `await` ceremony on the hot path.\n */\nexport function createFrancEngine(\n  candidates: readonly LanguageProfile[],\n  options: Pick<ClassifyOptions, \"isolateScripts\"> = {},\n): SyncSource {\n  return {\n    id: \"franc\",\n    sync: true,\n    inputs: [\"text\"],\n    detect: (input) => evidenceFromFranc(input.text, candidates, options),\n  };\n}\n\n/**\n * A bare franc engine with no bound roster — it abstains until given candidates.\n * Prefer {@link createFrancEngine} with your roster; this default exists so the\n * engine has a stable named export and a no-config import works.\n */\nexport const francEngine: SyncSource = {\n  id: \"franc\",\n  sync: true,\n  inputs: [\"text\"],\n  detect: (input) => evidenceFromFranc(input.text, undefined),\n};\n\nfunction clamp01(value: number): number {\n  if (!Number.isFinite(value)) return 0;\n  if (value < 0) return 0;\n  if (value > 1) return 1;\n  return value;\n}\n"]}

package/dist/fuse.d.ts

@@ -1,4 +1,4 @@
-import { W as Weights, L as LanguageProfile, N as NonDiscriminatingScript, a as LanguageEvidence, C as Classification } from './types-DkB4436E.js';
+import { W as Weights, L as LanguageProfile, N as NonDiscriminatingScript, a as LanguageEvidence, C as Classification } from './types-DbPJ0sxF.js';
 
 interface FuseOptions {
     weights?: Weights;

package/dist/fuse.js

@@ -1,6 +1,6 @@
-export { fuse } from './chunk-LUSZIBTZ.js';
+export { fuse } from './chunk-OUYN7BWC.js';
 import './chunk-YCUSX3GG.js';
-import './chunk-SOTZVW3I.js';
+import './chunk-VWKQLGB4.js';
 import './chunk-2Z7REIOE.js';
 //# sourceMappingURL=fuse.js.map
 //# sourceMappingURL=fuse.js.map

package/dist/headers.d.ts

@@ -1,4 +1,4 @@
-import { H as HeaderBag, a as LanguageEvidence } from './types-DkB4436E.js';
+import { H as HeaderBag, a as LanguageEvidence } from './types-DbPJ0sxF.js';
 
 /** Producer: the HTTP `Content-Language` response header. */
 declare function evidenceFromHeaders(headers: HeaderBag | undefined): LanguageEvidence[];

package/dist/html.d.ts

@@ -1,4 +1,4 @@
-import { a as LanguageEvidence } from './types-DkB4436E.js';
+import { a as LanguageEvidence } from './types-DbPJ0sxF.js';
 
 /**
  * Producer: language clues from an HTML string's metadata.

package/dist/index.d.ts

@@ -1,5 +1,5 @@
-import { E as EvidenceSource, D as DetectorConfig, c as DetectFn, a as LanguageEvidence } from './types-DkB4436E.js';
-export { A as AsyncSource, d as AttrBag, C as Classification, e as DetectContext, f as DetectInput, g as EarlyExit, h as EvidenceKind, i as HasAsync, H as HeaderBag, b as LanguageCode, L as LanguageProfile, N as NonDiscriminatingScript, j as SourceInput, S as SyncSource, W as Weights } from './types-DkB4436E.js';
+import { E as EvidenceSource, D as DetectorConfig, c as DetectFn, a as LanguageEvidence } from './types-DbPJ0sxF.js';
+export { A as AsyncSource, d as AttrBag, C as Classification, e as DetectContext, f as DetectInput, g as EarlyExit, h as EvidenceKind, i as HasAsync, H as HeaderBag, b as LanguageCode, L as LanguageProfile, N as NonDiscriminatingScript, j as SourceInput, S as SyncSource, W as Weights } from './types-DbPJ0sxF.js';
 export { FuseOptions, fuse } from './fuse.js';
 export { evidenceFromText } from './text.js';
 export { evidenceFromHtml } from './html.js';

package/dist/index.js

@@ -1,14 +1,14 @@
-import { evidenceFromText } from './chunk-7N545CET.js';
-export { evidenceFromText } from './chunk-7N545CET.js';
+import { evidenceFromText } from './chunk-66W4QJGT.js';
+export { evidenceFromText } from './chunk-66W4QJGT.js';
 import { evidenceFromHtml } from './chunk-K4MXTIY7.js';
 export { evidenceFromHtml } from './chunk-K4MXTIY7.js';
 import { evidenceFromHeaders } from './chunk-FEKBPTHK.js';
 export { evidenceFromHeaders } from './chunk-FEKBPTHK.js';
-import { fuse } from './chunk-LUSZIBTZ.js';
-export { fuse } from './chunk-LUSZIBTZ.js';
+import { fuse } from './chunk-OUYN7BWC.js';
+export { fuse } from './chunk-OUYN7BWC.js';
 import { normalizeBCP47 } from './chunk-YCUSX3GG.js';
 export { normalizeBCP47, normalizeLanguageCode, primarySubtag } from './chunk-YCUSX3GG.js';
-import './chunk-SOTZVW3I.js';
+import './chunk-VWKQLGB4.js';
 import './chunk-2Z7REIOE.js';
 
 // src/node-lang.ts
@@ -32,13 +32,13 @@ function evidenceFromNodeLang(attrs) {
 }
 
 // src/compile.ts
-function builtIns(candidates, nodeLangAttributes) {
+function builtIns(candidates, nodeLangAttributes, isolateScripts) {
   return [
     {
       id: "text",
       sync: true,
       inputs: ["text"],
-      detect: (i) => evidenceFromText(i.text, candidates)
+      detect: (i) => evidenceFromText(i.text, candidates, void 0, { isolateScripts })
     },
     { id: "html", sync: true, inputs: ["html"], detect: (i) => evidenceFromHtml(i.html) },
     {
@@ -64,7 +64,11 @@ function applicable(source, input) {
 }
 function compile(config = {}) {
   const sources = [
-    ...builtIns(config.candidates, config.nodeLangAttributes ?? DEFAULT_NODE_LANG_ATTRIBUTES),
+    ...builtIns(
+      config.candidates,
+      config.nodeLangAttributes ?? DEFAULT_NODE_LANG_ATTRIBUTES,
+      config.isolateScripts ?? false
+    ),
     ...config.engines ?? []
   ];
   const hasAsync = sources.some((source) => !source.sync);

package/dist/index.js.map

@@ -1 +1 @@
-{"version":3,"sources":["../src/node-lang.ts","../src/compile.ts"],"names":["detect"],"mappings":";;;;;;;;;;;;;;AAOA,IAAM,oBAAA,GAAuB,GAAA;AAMtB,IAAM,4BAAA,GAAkD,CAAC,MAAM;AA6B/D,SAAS,qBACd,KAAA,EACoB;AACpB,EAAA,MAAM,MAA0B,EAAC;AACjC,EAAA,KAAA,MAAW,CAAC,SAAA,EAAW,GAAG,KAAK,MAAA,CAAO,OAAA,CAAQ,KAAK,CAAA,EAAG;AACpD,IAAA,IAAI,GAAA,IAAO,IAAA,IAAQ,GAAA,KAAQ,EAAA,EAAI;AAC/B,IAAA,MAAM,QAAA,GAAW,eAAe,GAAG,CAAA;AACnC,IAAA,IAAI,aAAa,IAAA,EAAM;AACvB,IAAA,GAAA,CAAI,IAAA,CAAK;AAAA,MACP,IAAA,EAAM,WAAA;AAAA,MACN,QAAA;AAAA,MACA,UAAA,EAAY,oBAAA;AAAA,MACZ,MAAA,EAAQ,aAAa,SAAS,CAAA,CAAA;AAAA,MAC9B,KAAA,EAAO;AAAA,KACR,CAAA;AAAA,EACH;AACA,EAAA,OAAO,GAAA;AACT;;;ACpCA,SAAS,QAAA,CACP,YACA,kBAAA,EACc;AACd,EAAA,OAAO;AAAA,IACL;AAAA,MACE,EAAA,EAAI,MAAA;AAAA,MACJ,IAAA,EAAM,IAAA;AAAA,MACN,MAAA,EAAQ,CAAC,MAAM,CAAA;AAAA,MACf,QAAQ,CAAC,CAAA,KAAM,gBAAA,CAAiB,CAAA,CAAE,MAAM,UAAU;AAAA,KACpD;AAAA,IACA,EAAE,EAAA,EAAI,MAAA,EAAQ,IAAA,EAAM,MAAM,MAAA,EAAQ,CAAC,MAAM,CAAA,EAAG,QAAQ,CAAC,CAAA,KAAM,gBAAA,CAAiB,CAAA,CAAE,IAAI,CAAA,EAAE;AAAA,IACpF;AAAA,MACE,EAAA,EAAI,SAAA;AAAA,MACJ,IAAA,EAAM,IAAA;AAAA,MACN,MAAA,EAAQ,CAAC,SAAS,CAAA;AAAA,MAClB,MAAA,EAAQ,CAAC,CAAA,KAAM,mBAAA,CAAoB,EAAE,OAAO;AAAA,KAC9C;AAAA,IACA;AAAA,MACE,EAAA,EAAI,WAAA;AAAA,MACJ,IAAA,EAAM,IAAA;AAAA,MACN,MAAA,EAAQ,CAAC,OAAO,CAAA;AAAA,MAChB,MAAA,EAAQ,CAAC,CAAA,KAAM;AACb,QAAA,MAAM,WAAsD,EAAC;AAC7D,QAAA,KAAA,MAAW,QAAQ,kBAAA,EAAoB,QAAA,CAAS,IAAI,CAAA,GAAI,CAAA,CAAE,QAAQ,IAAI,CAAA;AACtE,QAAA,OAAO,qBAAqB,QAAQ,CAAA;AAAA,MACtC;AAAA;AACF,GACF;AACF;AAGA,SAAS,UAAA,CAAW,QAAwB,KAAA,EAA6B;AACvE,EAAA,OAAO,MAAA,CAAO,OAAO,KAAA,CAAM,CAAC,QAAQ,KAAA,CAAM,GAAG,MAAM,MAAS,CAAA;AAC9D;AAQO,SAAS,OAAA,CACd,MAAA,GAA4B,EAAC,EAChB;AACb,EAAA,MAAM,OAAA,GAA4B;AAAA,IAChC,GAAG,QAAA,CAAS,MAAA,CAAO,UAAA,EAAY,MAAA,CAAO,sBAAsB,4BAA4B,CAAA;AAAA,IACxF,GAAI,MAAA,CAAO,OAAA,IAAW;AAAC,GACzB;AACA,EAAA,MAAM,WAAW,OAAA,CAAQ,IAAA,CAAK,CAAC,MAAA,KAAW,CAAC,OAAO,IAAI,CAAA;AACtD,EAAA,MAAM,WAAA,GAA2B;AAAA,IAC/B,SAAS,MAAA,CAAO,OAAA;AAAA,IAChB,YAAY,MAAA,CAAO,UAAA;AAAA,IACnB,yBAAyB,MAAA,CAAO;AAAA,GAClC;AAEA,EAAA,IAAI,CAAC,QAAA,EAAU;AACb,IAAA,MAAMA,OAAAA,GAAS,CAAC,KAAA,KAAuC;AACrD,MAAA,MAAM,WAA+B,EAAC;AACtC,MAAA,KAAA,MAAW,UAAU,OAAA,EAAS;AAC5B,QAAA,IAAI,MAAA,CAAO,IAAA,IAAQ,UAAA,CAAW,MAAA,EAAQ,KAAK,CAAA,EAAG,QAAA,CAAS,IAAA,CAAK,GAAG,MAAA,CAAO,MAAA,CAAO,KAAK,CAAC,CAAA;AAAA,MACrF;AACA,MAAA,OAAO,IAAA,CAAK,UAAU,WAAW,CAAA;AAAA,IACnC,CAAA;AACA,IAAA,OAAOA,OAAAA;AAAA,EACT;AAEA,EAAA,MAAM,MAAA,GAAS,OAAO,KAAA,EAAoB,GAAA,GAAqB,EAAC,KAA+B;AAC7F,IAAA,MAAM,WAA+B,EAAC;AACtC,IAAA,MAAM,UAAyC,EAAC;AAChD,IAAA,KAAA,MAAW,UAAU,OAAA,EAAS;AAC5B,MAAA,IAAI,CAAC,UAAA,CAAW,MAAA,EAAQ,KAAK,CAAA,EAAG;AAChC,MAAA,IAAI,MAAA,CAAO,MAAM,QAAA,CAAS,IAAA,CAAK,GAAG,MAAA,CAAO,MAAA,CAAO,KAAK,CAAC,CAAA;AAAA,WACjD,OAAA,CAAQ,IAAA,CAAK,OAAA,CAAQ,OAAA,CAAQ,OAAO,MAAA,CAAO,KAAA,EAAO,GAAG,CAAC,CAAA,CAAE,KAAA,CAAM,MAAM,EAAE,CAAC,CAAA;AAAA,IAC9E;AACA,IAAA,KAAA,MAAW,KAAA,IAAS,MAAM,OAAA,CAAQ,GAAA,CAAI,OAAO,CAAA,EAAG,QAAA,CAAS,IAAA,CAAK,GAAG,KAAK,CAAA;AACtE,IAAA,OAAO,IAAA,CAAK,UAAU,WAAW,CAAA;AAAA,EACnC,CAAA;AACA,EAAA,OAAO,MAAA;AACT","file":"index.js","sourcesContent":["import type { LanguageEvidence } from \"./types.js\";\nimport { normalizeBCP47 } from \"./internal/bcp47.js\";\n\n/** Confidence for a node-level declaration: above the page-scope tags (a label\n *  on the node itself sits closer to the content than `<html lang>` does), but\n *  still context evidence — {@link fuse}'s guard keeps it from flipping clear\n *  script evidence. */\nconst NODE_LANG_CONFIDENCE = 0.7;\n\n/** The pipeline's default declaration attributes: only the standardized\n *  global `lang`. Vendor labels (Google's `data-rl` and kin) are page-private\n *  `data-*` conventions and must be opted into per detector — see\n *  {@link DetectorConfig.nodeLangAttributes}. */\nexport const DEFAULT_NODE_LANG_ATTRIBUTES: readonly string[] = [\"lang\"];\n\n/**\n * Producer: a per-node declared language — the page's own label for one\n * content node, read from an attribute. The one STANDARDIZED bearer is the\n * global `lang` attribute (BCP-47, inheritable); everything else is a vendor\n * convention the caller opts into — e.g. Google's `data-rl` response-language\n * label on AI-generated answers. No attribute name is built in here: which\n * attributes count as declarations is entirely the caller's choice.\n *\n * The document-scope siblings of this signal live in {@link evidenceFromHtml}\n * (`<html lang>`, `content-language`, `og:locale`); this is the same\n * declaration concept one scope down. Like them it is *context* evidence: the\n * fuser weighs it against text reads, and its script guard keeps a\n * declaration from overriding a confident text read — a mislabeled node loses\n * to clear script evidence, while weak or absent text lets the declaration\n * decide.\n *\n * DOM-free by design — this module never touches an Element. The caller\n * passes the attribute values it extracted, keyed by attribute name\n * (`{ lang: el.getAttribute(\"lang\") }`, `{ \"data-rl\": … }`). Each recognized\n * value becomes one evidence item whose `source` is the attribute name under\n * the `node-lang:` namespace (`node-lang:data-rl`) — namespaced so an\n * attribute that happens to share a name with an engine id or evidence kind\n * can never collide in the {@link FuseOptions.weights} keyspace. That lets\n * weights target one attribute — trust a curated vendor label above an\n * often-stale inherited `lang`, or silence an attribute entirely — instead\n * of the whole kind. Empty and unrecognized values are dropped.\n */\nexport function evidenceFromNodeLang(\n  attrs: Readonly<Record<string, string | null | undefined>>,\n): LanguageEvidence[] {\n  const out: LanguageEvidence[] = [];\n  for (const [attribute, raw] of Object.entries(attrs)) {\n    if (raw == null || raw === \"\") continue;\n    const language = normalizeBCP47(raw);\n    if (language === null) continue;\n    out.push({\n      kind: \"node-lang\",\n      language,\n      confidence: NODE_LANG_CONFIDENCE,\n      source: `node-lang:${attribute}`,\n      value: raw,\n    });\n  }\n  return out;\n}\n","import { evidenceFromHeaders } from \"./headers.js\";\nimport { evidenceFromHtml } from \"./html.js\";\nimport { DEFAULT_NODE_LANG_ATTRIBUTES, evidenceFromNodeLang } from \"./node-lang.js\";\nimport { evidenceFromText } from \"./text.js\";\nimport { fuse, type FuseOptions } from \"./fuse.js\";\nimport type {\n  Classification,\n  DetectContext,\n  DetectFn,\n  DetectInput,\n  DetectorConfig,\n  EvidenceSource,\n  LanguageEvidence,\n  LanguageProfile,\n  SyncSource,\n} from \"./types.js\";\n\n/** The always-on, zero-dependency producers. The text producer is bound to the\n *  configured candidate roster so its scoring is roster-relative (and so it\n *  abstains when no roster was supplied — its signals need candidates). The\n *  node-lang producer is bound to the configured declaration-attribute list\n *  (standard `lang` only, unless the config opts into vendor attributes), and\n *  reads them from `input.attrs` in configured order. */\nfunction builtIns(\n  candidates: readonly LanguageProfile[] | undefined,\n  nodeLangAttributes: readonly string[],\n): SyncSource[] {\n  return [\n    {\n      id: \"text\",\n      sync: true,\n      inputs: [\"text\"],\n      detect: (i) => evidenceFromText(i.text, candidates),\n    },\n    { id: \"html\", sync: true, inputs: [\"html\"], detect: (i) => evidenceFromHtml(i.html) },\n    {\n      id: \"headers\",\n      sync: true,\n      inputs: [\"headers\"],\n      detect: (i) => evidenceFromHeaders(i.headers),\n    },\n    {\n      id: \"node-lang\",\n      sync: true,\n      inputs: [\"attrs\"],\n      detect: (i) => {\n        const declared: Record<string, string | null | undefined> = {};\n        for (const name of nodeLangAttributes) declared[name] = i.attrs?.[name];\n        return evidenceFromNodeLang(declared);\n      },\n    },\n  ];\n}\n\n/** Run a source only when every input it declares is present. */\nfunction applicable(source: EvidenceSource, input: DetectInput): boolean {\n  return source.inputs.every((key) => input[key] !== undefined);\n}\n\n/**\n * Build a configured detector. Does the per-roster setup once and returns a\n * `detect` function whose sync/async shape is fixed by the registered engines\n * (see {@link DetectFn}). The built-in producers are always registered; opt-in\n * engines (franc, chrome-ai) are added via `config.engines`.\n */\nexport function compile<const E extends readonly EvidenceSource[] = []>(\n  config: DetectorConfig<E> = {},\n): DetectFn<E> {\n  const sources: EvidenceSource[] = [\n    ...builtIns(config.candidates, config.nodeLangAttributes ?? DEFAULT_NODE_LANG_ATTRIBUTES),\n    ...(config.engines ?? []),\n  ];\n  const hasAsync = sources.some((source) => !source.sync);\n  const fuseOptions: FuseOptions = {\n    weights: config.weights,\n    candidates: config.candidates,\n    nonDiscriminatingScript: config.nonDiscriminatingScript,\n  };\n\n  if (!hasAsync) {\n    const detect = (input: DetectInput): Classification => {\n      const evidence: LanguageEvidence[] = [];\n      for (const source of sources) {\n        if (source.sync && applicable(source, input)) evidence.push(...source.detect(input));\n      }\n      return fuse(evidence, fuseOptions);\n    };\n    return detect as DetectFn<E>;\n  }\n\n  const detect = async (input: DetectInput, ctx: DetectContext = {}): Promise<Classification> => {\n    const evidence: LanguageEvidence[] = [];\n    const pending: Promise<LanguageEvidence[]>[] = [];\n    for (const source of sources) {\n      if (!applicable(source, input)) continue;\n      if (source.sync) evidence.push(...source.detect(input));\n      else pending.push(Promise.resolve(source.detect(input, ctx)).catch(() => []));\n    }\n    for (const batch of await Promise.all(pending)) evidence.push(...batch);\n    return fuse(evidence, fuseOptions);\n  };\n  return detect as DetectFn<E>;\n}\n"]}
+{"version":3,"sources":["../src/node-lang.ts","../src/compile.ts"],"names":["detect"],"mappings":";;;;;;;;;;;;;;AAOA,IAAM,oBAAA,GAAuB,GAAA;AAMtB,IAAM,4BAAA,GAAkD,CAAC,MAAM;AA6B/D,SAAS,qBACd,KAAA,EACoB;AACpB,EAAA,MAAM,MAA0B,EAAC;AACjC,EAAA,KAAA,MAAW,CAAC,SAAA,EAAW,GAAG,KAAK,MAAA,CAAO,OAAA,CAAQ,KAAK,CAAA,EAAG;AACpD,IAAA,IAAI,GAAA,IAAO,IAAA,IAAQ,GAAA,KAAQ,EAAA,EAAI;AAC/B,IAAA,MAAM,QAAA,GAAW,eAAe,GAAG,CAAA;AACnC,IAAA,IAAI,aAAa,IAAA,EAAM;AACvB,IAAA,GAAA,CAAI,IAAA,CAAK;AAAA,MACP,IAAA,EAAM,WAAA;AAAA,MACN,QAAA;AAAA,MACA,UAAA,EAAY,oBAAA;AAAA,MACZ,MAAA,EAAQ,aAAa,SAAS,CAAA,CAAA;AAAA,MAC9B,KAAA,EAAO;AAAA,KACR,CAAA;AAAA,EACH;AACA,EAAA,OAAO,GAAA;AACT;;;ACpCA,SAAS,QAAA,CACP,UAAA,EACA,kBAAA,EACA,cAAA,EACc;AACd,EAAA,OAAO;AAAA,IACL;AAAA,MACE,EAAA,EAAI,MAAA;AAAA,MACJ,IAAA,EAAM,IAAA;AAAA,MACN,MAAA,EAAQ,CAAC,MAAM,CAAA;AAAA,MACf,MAAA,EAAQ,CAAC,CAAA,KAAM,gBAAA,CAAiB,CAAA,CAAE,MAAM,UAAA,EAAY,MAAA,EAAW,EAAE,cAAA,EAAgB;AAAA,KACnF;AAAA,IACA,EAAE,EAAA,EAAI,MAAA,EAAQ,IAAA,EAAM,MAAM,MAAA,EAAQ,CAAC,MAAM,CAAA,EAAG,QAAQ,CAAC,CAAA,KAAM,gBAAA,CAAiB,CAAA,CAAE,IAAI,CAAA,EAAE;AAAA,IACpF;AAAA,MACE,EAAA,EAAI,SAAA;AAAA,MACJ,IAAA,EAAM,IAAA;AAAA,MACN,MAAA,EAAQ,CAAC,SAAS,CAAA;AAAA,MAClB,MAAA,EAAQ,CAAC,CAAA,KAAM,mBAAA,CAAoB,EAAE,OAAO;AAAA,KAC9C;AAAA,IACA;AAAA,MACE,EAAA,EAAI,WAAA;AAAA,MACJ,IAAA,EAAM,IAAA;AAAA,MACN,MAAA,EAAQ,CAAC,OAAO,CAAA;AAAA,MAChB,MAAA,EAAQ,CAAC,CAAA,KAAM;AACb,QAAA,MAAM,WAAsD,EAAC;AAC7D,QAAA,KAAA,MAAW,QAAQ,kBAAA,EAAoB,QAAA,CAAS,IAAI,CAAA,GAAI,CAAA,CAAE,QAAQ,IAAI,CAAA;AACtE,QAAA,OAAO,qBAAqB,QAAQ,CAAA;AAAA,MACtC;AAAA;AACF,GACF;AACF;AAGA,SAAS,UAAA,CAAW,QAAwB,KAAA,EAA6B;AACvE,EAAA,OAAO,MAAA,CAAO,OAAO,KAAA,CAAM,CAAC,QAAQ,KAAA,CAAM,GAAG,MAAM,MAAS,CAAA;AAC9D;AAQO,SAAS,OAAA,CACd,MAAA,GAA4B,EAAC,EAChB;AACb,EAAA,MAAM,OAAA,GAA4B;AAAA,IAChC,GAAG,QAAA;AAAA,MACD,MAAA,CAAO,UAAA;AAAA,MACP,OAAO,kBAAA,IAAsB,4BAAA;AAAA,MAC7B,OAAO,cAAA,IAAkB;AAAA,KAC3B;AAAA,IACA,GAAI,MAAA,CAAO,OAAA,IAAW;AAAC,GACzB;AACA,EAAA,MAAM,WAAW,OAAA,CAAQ,IAAA,CAAK,CAAC,MAAA,KAAW,CAAC,OAAO,IAAI,CAAA;AACtD,EAAA,MAAM,WAAA,GAA2B;AAAA,IAC/B,SAAS,MAAA,CAAO,OAAA;AAAA,IAChB,YAAY,MAAA,CAAO,UAAA;AAAA,IACnB,yBAAyB,MAAA,CAAO;AAAA,GAClC;AAEA,EAAA,IAAI,CAAC,QAAA,EAAU;AACb,IAAA,MAAMA,OAAAA,GAAS,CAAC,KAAA,KAAuC;AACrD,MAAA,MAAM,WAA+B,EAAC;AACtC,MAAA,KAAA,MAAW,UAAU,OAAA,EAAS;AAC5B,QAAA,IAAI,MAAA,CAAO,IAAA,IAAQ,UAAA,CAAW,MAAA,EAAQ,KAAK,CAAA,EAAG,QAAA,CAAS,IAAA,CAAK,GAAG,MAAA,CAAO,MAAA,CAAO,KAAK,CAAC,CAAA;AAAA,MACrF;AACA,MAAA,OAAO,IAAA,CAAK,UAAU,WAAW,CAAA;AAAA,IACnC,CAAA;AACA,IAAA,OAAOA,OAAAA;AAAA,EACT;AAEA,EAAA,MAAM,MAAA,GAAS,OAAO,KAAA,EAAoB,GAAA,GAAqB,EAAC,KAA+B;AAC7F,IAAA,MAAM,WAA+B,EAAC;AACtC,IAAA,MAAM,UAAyC,EAAC;AAChD,IAAA,KAAA,MAAW,UAAU,OAAA,EAAS;AAC5B,MAAA,IAAI,CAAC,UAAA,CAAW,MAAA,EAAQ,KAAK,CAAA,EAAG;AAChC,MAAA,IAAI,MAAA,CAAO,MAAM,QAAA,CAAS,IAAA,CAAK,GAAG,MAAA,CAAO,MAAA,CAAO,KAAK,CAAC,CAAA;AAAA,WACjD,OAAA,CAAQ,IAAA,CAAK,OAAA,CAAQ,OAAA,CAAQ,OAAO,MAAA,CAAO,KAAA,EAAO,GAAG,CAAC,CAAA,CAAE,KAAA,CAAM,MAAM,EAAE,CAAC,CAAA;AAAA,IAC9E;AACA,IAAA,KAAA,MAAW,KAAA,IAAS,MAAM,OAAA,CAAQ,GAAA,CAAI,OAAO,CAAA,EAAG,QAAA,CAAS,IAAA,CAAK,GAAG,KAAK,CAAA;AACtE,IAAA,OAAO,IAAA,CAAK,UAAU,WAAW,CAAA;AAAA,EACnC,CAAA;AACA,EAAA,OAAO,MAAA;AACT","file":"index.js","sourcesContent":["import type { LanguageEvidence } from \"./types.js\";\nimport { normalizeBCP47 } from \"./internal/bcp47.js\";\n\n/** Confidence for a node-level declaration: above the page-scope tags (a label\n *  on the node itself sits closer to the content than `<html lang>` does), but\n *  still context evidence — {@link fuse}'s guard keeps it from flipping clear\n *  script evidence. */\nconst NODE_LANG_CONFIDENCE = 0.7;\n\n/** The pipeline's default declaration attributes: only the standardized\n *  global `lang`. Vendor labels (Google's `data-rl` and kin) are page-private\n *  `data-*` conventions and must be opted into per detector — see\n *  {@link DetectorConfig.nodeLangAttributes}. */\nexport const DEFAULT_NODE_LANG_ATTRIBUTES: readonly string[] = [\"lang\"];\n\n/**\n * Producer: a per-node declared language — the page's own label for one\n * content node, read from an attribute. The one STANDARDIZED bearer is the\n * global `lang` attribute (BCP-47, inheritable); everything else is a vendor\n * convention the caller opts into — e.g. Google's `data-rl` response-language\n * label on AI-generated answers. No attribute name is built in here: which\n * attributes count as declarations is entirely the caller's choice.\n *\n * The document-scope siblings of this signal live in {@link evidenceFromHtml}\n * (`<html lang>`, `content-language`, `og:locale`); this is the same\n * declaration concept one scope down. Like them it is *context* evidence: the\n * fuser weighs it against text reads, and its script guard keeps a\n * declaration from overriding a confident text read — a mislabeled node loses\n * to clear script evidence, while weak or absent text lets the declaration\n * decide.\n *\n * DOM-free by design — this module never touches an Element. The caller\n * passes the attribute values it extracted, keyed by attribute name\n * (`{ lang: el.getAttribute(\"lang\") }`, `{ \"data-rl\": … }`). Each recognized\n * value becomes one evidence item whose `source` is the attribute name under\n * the `node-lang:` namespace (`node-lang:data-rl`) — namespaced so an\n * attribute that happens to share a name with an engine id or evidence kind\n * can never collide in the {@link FuseOptions.weights} keyspace. That lets\n * weights target one attribute — trust a curated vendor label above an\n * often-stale inherited `lang`, or silence an attribute entirely — instead\n * of the whole kind. Empty and unrecognized values are dropped.\n */\nexport function evidenceFromNodeLang(\n  attrs: Readonly<Record<string, string | null | undefined>>,\n): LanguageEvidence[] {\n  const out: LanguageEvidence[] = [];\n  for (const [attribute, raw] of Object.entries(attrs)) {\n    if (raw == null || raw === \"\") continue;\n    const language = normalizeBCP47(raw);\n    if (language === null) continue;\n    out.push({\n      kind: \"node-lang\",\n      language,\n      confidence: NODE_LANG_CONFIDENCE,\n      source: `node-lang:${attribute}`,\n      value: raw,\n    });\n  }\n  return out;\n}\n","import { evidenceFromHeaders } from \"./headers.js\";\nimport { evidenceFromHtml } from \"./html.js\";\nimport { DEFAULT_NODE_LANG_ATTRIBUTES, evidenceFromNodeLang } from \"./node-lang.js\";\nimport { evidenceFromText } from \"./text.js\";\nimport { fuse, type FuseOptions } from \"./fuse.js\";\nimport type {\n  Classification,\n  DetectContext,\n  DetectFn,\n  DetectInput,\n  DetectorConfig,\n  EvidenceSource,\n  LanguageEvidence,\n  LanguageProfile,\n  SyncSource,\n} from \"./types.js\";\n\n/** The always-on, zero-dependency producers. The text producer is bound to the\n *  configured candidate roster so its scoring is roster-relative (and so it\n *  abstains when no roster was supplied — its signals need candidates). The\n *  node-lang producer is bound to the configured declaration-attribute list\n *  (standard `lang` only, unless the config opts into vendor attributes), and\n *  reads them from `input.attrs` in configured order. */\nfunction builtIns(\n  candidates: readonly LanguageProfile[] | undefined,\n  nodeLangAttributes: readonly string[],\n  isolateScripts: boolean,\n): SyncSource[] {\n  return [\n    {\n      id: \"text\",\n      sync: true,\n      inputs: [\"text\"],\n      detect: (i) => evidenceFromText(i.text, candidates, undefined, { isolateScripts }),\n    },\n    { id: \"html\", sync: true, inputs: [\"html\"], detect: (i) => evidenceFromHtml(i.html) },\n    {\n      id: \"headers\",\n      sync: true,\n      inputs: [\"headers\"],\n      detect: (i) => evidenceFromHeaders(i.headers),\n    },\n    {\n      id: \"node-lang\",\n      sync: true,\n      inputs: [\"attrs\"],\n      detect: (i) => {\n        const declared: Record<string, string | null | undefined> = {};\n        for (const name of nodeLangAttributes) declared[name] = i.attrs?.[name];\n        return evidenceFromNodeLang(declared);\n      },\n    },\n  ];\n}\n\n/** Run a source only when every input it declares is present. */\nfunction applicable(source: EvidenceSource, input: DetectInput): boolean {\n  return source.inputs.every((key) => input[key] !== undefined);\n}\n\n/**\n * Build a configured detector. Does the per-roster setup once and returns a\n * `detect` function whose sync/async shape is fixed by the registered engines\n * (see {@link DetectFn}). The built-in producers are always registered; opt-in\n * engines (franc, chrome-ai) are added via `config.engines`.\n */\nexport function compile<const E extends readonly EvidenceSource[] = []>(\n  config: DetectorConfig<E> = {},\n): DetectFn<E> {\n  const sources: EvidenceSource[] = [\n    ...builtIns(\n      config.candidates,\n      config.nodeLangAttributes ?? DEFAULT_NODE_LANG_ATTRIBUTES,\n      config.isolateScripts ?? false,\n    ),\n    ...(config.engines ?? []),\n  ];\n  const hasAsync = sources.some((source) => !source.sync);\n  const fuseOptions: FuseOptions = {\n    weights: config.weights,\n    candidates: config.candidates,\n    nonDiscriminatingScript: config.nonDiscriminatingScript,\n  };\n\n  if (!hasAsync) {\n    const detect = (input: DetectInput): Classification => {\n      const evidence: LanguageEvidence[] = [];\n      for (const source of sources) {\n        if (source.sync && applicable(source, input)) evidence.push(...source.detect(input));\n      }\n      return fuse(evidence, fuseOptions);\n    };\n    return detect as DetectFn<E>;\n  }\n\n  const detect = async (input: DetectInput, ctx: DetectContext = {}): Promise<Classification> => {\n    const evidence: LanguageEvidence[] = [];\n    const pending: Promise<LanguageEvidence[]>[] = [];\n    for (const source of sources) {\n      if (!applicable(source, input)) continue;\n      if (source.sync) evidence.push(...source.detect(input));\n      else pending.push(Promise.resolve(source.detect(input, ctx)).catch(() => []));\n    }\n    for (const batch of await Promise.all(pending)) evidence.push(...batch);\n    return fuse(evidence, fuseOptions);\n  };\n  return detect as DetectFn<E>;\n}\n"]}

package/dist/profiles.d.ts

@@ -1,4 +1,4 @@
-import { b as LanguageCode, L as LanguageProfile } from './types-DkB4436E.js';
+import { b as LanguageCode, L as LanguageProfile } from './types-DbPJ0sxF.js';
 
 /**
  * `langtell/profiles` — ready-to-use {@link LanguageProfile} data.

package/dist/text.d.ts

@@ -1,5 +1,5 @@
-import { L as LanguageProfile, a as LanguageEvidence } from './types-DkB4436E.js';
-import { Rung3Resolver } from './classify.js';
+import { L as LanguageProfile, a as LanguageEvidence } from './types-DbPJ0sxF.js';
+import { Rung3Resolver, ClassifyOptions } from './classify.js';
 
 /**
  * Producer: candidate-relative script + lexical signals from the title text.
@@ -17,6 +17,6 @@ import { Rung3Resolver } from './classify.js';
  * (or no usable distinctive signal) it abstains — emitting nothing rather than a
  * coarse "unknown", since the roster decides relevance.
  */
-declare function evidenceFromText(text: string | undefined, candidates?: readonly LanguageProfile[], rung3?: Rung3Resolver): LanguageEvidence[];
+declare function evidenceFromText(text: string | undefined, candidates?: readonly LanguageProfile[], rung3?: Rung3Resolver, options?: ClassifyOptions): LanguageEvidence[];
 
 export { evidenceFromText };

package/dist/text.js

@@ -1,5 +1,5 @@
-export { evidenceFromText } from './chunk-7N545CET.js';
-import './chunk-SOTZVW3I.js';
+export { evidenceFromText } from './chunk-66W4QJGT.js';
+import './chunk-VWKQLGB4.js';
 import './chunk-2Z7REIOE.js';
 //# sourceMappingURL=text.js.map
 //# sourceMappingURL=text.js.map

package/dist/{types-DkB4436E.d.ts → types-DbPJ0sxF.d.ts}

@@ -135,6 +135,11 @@ interface DetectorConfig<E extends readonly EvidenceSource[] = []> {
      *  `"candidate"` (current behavior); opt into `"unknown"` for a roster-closed,
      *  evidence-only policy. */
     nonDiscriminatingScript?: NonDiscriminatingScript;
+    /** Forwarded to the built-in text producer's classifier: judge each script on
+     *  its own evidence. Off by default. See `ClassifyOptions.isolateScripts` in
+     *  `langtell/classify`. Opt-in engines take their own option (e.g.
+     *  `createFrancEngine(candidates, { isolateScripts: true })`). */
+    isolateScripts?: boolean;
 }
 /** The compiled detector. Synchronous when every source is sync; `Promise`-typed
  *  the moment an async engine is registered — so callers never guess `await`. */

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "langtell",
-  "version": "0.6.1",
+  "version": "0.7.0",
   "description": "Tell me the language — evidence-fusion language detection for short strings, with an auditable confidence trail.",
   "type": "module",
   "license": "MIT",

package/dist/chunk-7N545CET.js.map

@@ -1 +0,0 @@
-{"version":3,"sources":["../src/text.ts"],"names":[],"mappings":";;;AAmBO,SAAS,gBAAA,CACd,IAAA,EACA,UAAA,EACA,KAAA,EACoB;AACpB,EAAA,IAAI,IAAA,KAAS,UAAa,IAAA,CAAK,IAAA,GAAO,MAAA,KAAW,CAAA,SAAU,EAAC;AAC5D,EAAA,IAAI,eAAe,MAAA,IAAa,UAAA,CAAW,MAAA,KAAW,CAAA,SAAU,EAAC;AAEjE,EAAA,MAAM,OAAA,GAAU,iBAAA,CAAkB,IAAA,EAAM,UAAA,EAAY,KAAK,CAAA;AACzD,EAAA,IAAI,OAAA,CAAQ,QAAA,KAAa,SAAA,EAAW,OAAO,EAAC;AAE5C,EAAA,MAAM,IAAA,GAAyB;AAAA,IAC7B,IAAA,EAAM,cAAA;AAAA,IACN,UAAU,OAAA,CAAQ,QAAA;AAAA,IAClB,UAAA,EAAY,kBAAA,CAAmB,OAAA,CAAQ,MAAA,EAAQ,QAAQ,IAAI,CAAA;AAAA,IAC3D,MAAA,EAAQ,cAAA;AAAA,IACR,OAAO,IAAA,CAAK,IAAA,EAAK,CAAE,KAAA,CAAM,GAAG,EAAE;AAAA,GAChC;AAIA,EAAA,IAAI,CAAC,OAAA,CAAQ,cAAA,EAAgB,IAAA,CAAK,cAAA,GAAiB,KAAA;AACnD,EAAA,OAAO,CAAC,IAAI,CAAA;AACd;AAWA,SAAS,kBAAA,CAAmB,QAAgB,IAAA,EAAoB;AAC9D,EAAA,IAAI,SAAS,CAAA,EAAG;AAEd,IAAA,OAAO,OAAA,CAAQ,GAAA,GAAM,IAAA,CAAK,GAAA,CAAI,IAAA,CAAK,GAAA,CAAI,MAAA,EAAQ,CAAC,CAAA,EAAG,CAAC,CAAA,GAAI,IAAI,CAAA;AAAA,EAC9D;AACA,EAAA,MAAM,IAAA,GAAO,IAAA,CAAK,GAAA,CAAI,MAAA,EAAQ,CAAC,CAAA;AAC/B,EAAA,OAAO,OAAA,CAAQ,MAAO,IAAA,CAAK,GAAA,CAAI,MAAM,CAAC,CAAA,GAAI,IAAK,IAAI,CAAA;AACrD;AAEA,SAAS,QAAQ,KAAA,EAAuB;AACtC,EAAA,IAAI,CAAC,MAAA,CAAO,QAAA,CAAS,KAAK,GAAG,OAAO,CAAA;AACpC,EAAA,IAAI,KAAA,GAAQ,GAAG,OAAO,CAAA;AACtB,EAAA,IAAI,KAAA,GAAQ,GAAG,OAAO,CAAA;AACtB,EAAA,OAAO,KAAA;AACT","file":"chunk-7N545CET.js","sourcesContent":["import type { LanguageEvidence, LanguageProfile } from \"./types.js\";\nimport { classifyBySnippet, type Rung, type Rung3Resolver } from \"./internal/classify.js\";\n\n/**\n * Producer: candidate-relative script + lexical signals from the title text.\n *\n * Wraps the ported snippet classifier ({@link classifyBySnippet}): noise strip →\n * dominant-script scope → distinctive letters (rung 1) → function words (2a) →\n * frequent words (2b). The `candidates` roster makes scoring roster-relative —\n * `і` decides Ukrainian only when Russian is also a candidate. Sync and\n * zero-dependency; the optional franc rung is injected via `rung3`.\n *\n * Emits at most one `kind: \"title-script\"` evidence item. The classifier's\n * integer `margin` (the winner's lead over the runner-up) maps to a 0..1\n * `confidence`: a verdict at all means the dominant script and the deciding rung\n * agreed, so the floor is high; a wider lead nudges it up. With no candidates\n * (or no usable distinctive signal) it abstains — emitting nothing rather than a\n * coarse \"unknown\", since the roster decides relevance.\n */\nexport function evidenceFromText(\n  text: string | undefined,\n  candidates?: readonly LanguageProfile[],\n  rung3?: Rung3Resolver,\n): LanguageEvidence[] {\n  if (text === undefined || text.trim().length === 0) return [];\n  if (candidates === undefined || candidates.length === 0) return [];\n\n  const verdict = classifyBySnippet(text, candidates, rung3);\n  if (verdict.language === \"unknown\") return [];\n\n  const item: LanguageEvidence = {\n    kind: \"title-script\",\n    language: verdict.language,\n    confidence: marginToConfidence(verdict.margin, verdict.rung),\n    source: \"title-script\",\n    value: text.trim().slice(0, 80),\n  };\n  // Surface only the meaningful negative: the script was owned by ≤1 candidate,\n  // so it didn't choose between candidates. The discriminating case stays narrow\n  // (flag omitted). `fuse({ nonDiscriminatingScript: \"unknown\" })` reads this.\n  if (!verdict.discriminating) item.discriminating = false;\n  return [item];\n}\n\n/**\n * Map the classifier's per-rung lead to a 0..1 confidence.\n *\n * Rungs 1–2 carry an integer count of distinctive items (≥1). A verdict already\n * means script + rung agreed, so the floor is high (0.6) and each extra\n * distinctive item adds up to a 0.35 bonus, saturating by a lead of 4. Rung 3\n * (franc) carries franc's own 0..1 score-gap, which is weaker evidence, so it is\n * scaled into a 0.4..0.75 band.\n */\nfunction marginToConfidence(margin: number, rung: Rung): number {\n  if (rung === 3) {\n    // franc score-gap is already 0..1; weaker than the distinctive rungs.\n    return clamp01(0.4 + Math.min(Math.max(margin, 0), 1) * 0.35);\n  }\n  const lead = Math.max(margin, 1);\n  return clamp01(0.6 + (Math.min(lead, 4) / 4) * 0.35);\n}\n\nfunction clamp01(value: number): number {\n  if (!Number.isFinite(value)) return 0;\n  if (value < 0) return 0;\n  if (value > 1) return 1;\n  return value;\n}\n"]}

package/dist/chunk-SOTZVW3I.js.map

@@ -1 +0,0 @@
-{"version":3,"sources":["../src/internal/classify.ts"],"names":[],"mappings":";;;AAsCO,IAAM,UAAA,GAAa;AA0B1B,IAAM,OAAA,GAA0B;AAAA,EAC9B,QAAA,EAAU,SAAA;AAAA,EACV,MAAA,EAAQ,CAAA;AAAA,EACR,IAAA,EAAM,IAAA;AAAA,EACN,cAAA,EAAgB;AAClB,CAAA;AAmBA,IAAM,WAAA,GAAc,sBAAA;AACpB,IAAM,QAAA,GAAW,mBAAA;AAOV,IAAM,gBAAA,GAAmB;AAKhC,SAAS,eAAe,IAAA,EAA2C;AACjE,EAAA,IAAI,GAAA,GAAM,CAAA;AACV,EAAA,IAAI,GAAA,GAAM,CAAA;AACV,EAAA,KAAA,MAAW,EAAA,IAAM,UAAA,CAAW,IAAI,CAAA,EAAG;AACjC,IAAA,IAAI,WAAA,CAAY,IAAA,CAAK,EAAE,CAAA,EAAG,GAAA,IAAO,CAAA;AAAA,SAAA,IACxB,QAAA,CAAS,IAAA,CAAK,EAAE,CAAA,EAAG,GAAA,IAAO,CAAA;AAAA,EACrC;AACA,EAAA,IAAI,GAAA,KAAQ,CAAA,IAAK,GAAA,KAAQ,CAAA,EAAG,OAAO,IAAA;AACnC,EAAA,OAAO,GAAA,IAAO,MAAM,UAAA,GAAa,OAAA;AACnC;AAMO,SAAS,gBAAgB,OAAA,EAA6C;AAC3E,EAAA,KAAA,MAAW,EAAA,IAAM,QAAQ,QAAA,EAAU;AACjC,IAAA,IAAI,WAAA,CAAY,IAAA,CAAK,EAAE,CAAA,EAAG,OAAO,UAAA;AACjC,IAAA,IAAI,QAAA,CAAS,IAAA,CAAK,EAAE,CAAA,EAAG,OAAO,OAAA;AAAA,EAChC;AACA,EAAA,OAAO,IAAA;AACT;AAMO,SAAS,eAAA,CACd,MACA,UAAA,EACK;AACL,EAAA,MAAM,MAAA,GAAS,eAAe,IAAI,CAAA;AAClC,EAAA,IAAI,MAAA,KAAW,IAAA,EAAM,OAAO,EAAC;AAI7B,EAAA,MAAM,IAAA,uBAAW,GAAA,EAAY;AAC7B,EAAA,MAAM,SAAc,EAAC;AACrB,EAAA,KAAA,MAAW,KAAK,UAAA,EAAY;AAC1B,IAAA,IAAI,eAAA,CAAgB,CAAC,CAAA,KAAM,MAAA,IAAU,KAAK,GAAA,CAAI,CAAA,CAAE,IAAI,CAAA,EAAG;AACvD,IAAA,IAAA,CAAK,GAAA,CAAI,EAAE,IAAI,CAAA;AACf,IAAA,MAAA,CAAO,KAAK,CAAC,CAAA;AAAA,EACf;AACA,EAAA,OAAO,MAAA;AACT;AA2CO,IAAM,mBAAA,GAAsB;AAmBnC,IAAM,mBAAkC,EAAE,OAAA,EAAS,EAAC,EAAG,OAAO,CAAA,EAAE;AAGhE,SAAS,mBAAmB,QAAA,EAAgC;AAC1D,EAAA,MAAM,MAAA,uBAAa,GAAA,EAAoB;AACvC,EAAA,KAAA,MAAW,EAAA,IAAM,QAAA,CAAS,WAAA,EAAY,EAAG;AACvC,IAAA,IAAI,CAAC,YAAY,IAAA,CAAK,EAAE,KAAK,CAAC,QAAA,CAAS,IAAA,CAAK,EAAE,CAAA,EAAG;AACjD,IAAA,MAAA,CAAO,IAAI,EAAA,EAAA,CAAK,MAAA,CAAO,IAAI,EAAE,CAAA,IAAK,KAAK,CAAC,CAAA;AAAA,EAC1C;AACA,EAAA,OAAO,MAAA;AACT;AAeO,SAAS,aAAa,IAAA,EAA4B;AACvD,EAAA,OAAO,kBAAA,CAAmB,WAAA,CAAY,UAAA,CAAW,IAAI,CAAC,CAAC,CAAA;AACzD;AASO,SAAS,eAAA,CAAgB,UAAwB,OAAA,EAAyC;AAC/F,EAAA,MAAM,MAAA,GAAS,gBAAgB,OAAO,CAAA;AACtC,EAAA,IAAI,MAAA,KAAW,MAAM,OAAO,gBAAA;AAC5B,EAAA,MAAM,QAAA,GAAW,MAAA,KAAW,UAAA,GAAa,WAAA,GAAc,QAAA;AAKvD,EAAA,MAAM,MAAM,IAAI,GAAA,CAAI,QAAQ,QAAA,IAAY,OAAA,CAAQ,SAAS,EAAA,CAAG,CAAA;AAC5D,EAAA,MAAM,UAAoB,EAAC;AAC3B,EAAA,IAAI,OAAA,GAAU,CAAA;AACd,EAAA,IAAI,KAAA,GAAQ,CAAA;AACZ,EAAA,KAAA,MAAW,CAAC,EAAA,EAAI,KAAK,CAAA,IAAK,QAAA,EAAU;AAGlC,IAAA,IAAI,CAAC,QAAA,CAAS,IAAA,CAAK,EAAE,CAAA,EAAG;AACxB,IAAA,KAAA,IAAS,KAAA;AACT,IAAA,IAAI,GAAA,CAAI,GAAA,CAAI,EAAE,CAAA,EAAG;AACjB,IAAA,OAAA,IAAW,KAAA;AACX,IAAA,OAAA,CAAQ,KAAK,EAAE,CAAA;AAAA,EACjB;AACA,EAAA,OAAO,EAAE,OAAA,EAAS,KAAA,EAAO,UAAU,CAAA,GAAI,CAAA,GAAI,UAAU,KAAA,EAAM;AAC7D;AAkBO,SAAS,aAAA,CAAc,MAAc,OAAA,EAAyC;AACnF,EAAA,OAAO,eAAA,CAAgB,YAAA,CAAa,IAAI,CAAA,EAAG,OAAO,CAAA;AACpD;AAQA,SAAS,SAAS,IAAA,EAAwB;AACxC,EAAA,OAAO,KAAK,WAAA,EAAY,CAAE,KAAA,CAAM,UAAU,KAAK,EAAC;AAClD;AAOA,SAAS,KAAA,CAAM,OAAyB,UAAA,EAAwD;AAC9F,EAAA,MAAM,MAAA,GAAS,IAAI,GAAA,CAAoB,UAAA,CAAW,GAAA,CAAI,CAAC,CAAA,KAAM,CAAC,CAAA,CAAE,IAAA,EAAM,CAAC,CAAC,CAAC,CAAA;AACzE,EAAA,KAAA,MAAW,QAAQ,KAAA,EAAO;AACxB,IAAA,IAAI,KAAA,GAAuB,IAAA;AAC3B,IAAA,IAAI,MAAA,GAAS,CAAA;AACb,IAAA,KAAA,MAAW,KAAK,UAAA,EAAY;AAC1B,MAAA,IAAI,CAAA,CAAE,GAAA,CAAI,GAAA,CAAI,IAAI,CAAA,EAAG;AACnB,QAAA,MAAA,IAAU,CAAA;AACV,QAAA,IAAI,SAAS,CAAA,EAAG;AACd,UAAA,KAAA,GAAQ,IAAA;AACR,UAAA;AAAA,QACF;AACA,QAAA,KAAA,GAAQ,CAAA,CAAE,IAAA;AAAA,MACZ;AAAA,IACF;AACA,IAAA,IAAI,KAAA,KAAU,IAAA,EAAM,MAAA,CAAO,GAAA,CAAI,KAAA,EAAA,CAAQ,OAAO,GAAA,CAAI,KAAK,CAAA,IAAK,CAAA,IAAK,CAAC,CAAA;AAAA,EACpE;AACA,EAAA,OAAO,MAAA;AACT;AAGA,SAAS,OAAO,MAAA,EAAsE;AACpF,EAAA,IAAI,GAAA,GAAM,EAAA;AACV,EAAA,IAAI,MAAA,GAAS,EAAA;AACb,EAAA,IAAI,IAAA,GAAsB,IAAA;AAC1B,EAAA,KAAA,MAAW,CAAC,CAAA,EAAG,KAAK,CAAA,IAAK,MAAA,EAAQ;AAC/B,IAAA,IAAI,QAAQ,GAAA,EAAK;AACf,MAAA,MAAA,GAAS,GAAA;AACT,MAAA,GAAA,GAAM,KAAA;AACN,MAAA,IAAA,GAAO,CAAA;AAAA,IACT,CAAA,MAAA,IAAW,QAAQ,MAAA,EAAQ;AACzB,MAAA,MAAA,GAAS,KAAA;AAAA,IACX;AAAA,EACF;AACA,EAAA,IAAI,IAAA,KAAS,IAAA,IAAQ,GAAA,GAAM,CAAA,EAAG,OAAO,IAAA;AACrC,EAAA,MAAM,MAAA,GAAS,GAAA,GAAM,IAAA,CAAK,GAAA,CAAI,QAAQ,CAAC,CAAA;AACvC,EAAA,OAAO,MAAA,IAAU,CAAA,GAAI,EAAE,IAAA,EAAM,QAAO,GAAI,IAAA;AAC1C;AAEA,SAAS,aAAA,CACP,YACA,IAAA,EACc;AACd,EAAA,OAAO,UAAA,CAAW,GAAA,CAAI,CAAC,CAAA,MAAO,EAAE,IAAA,EAAM,CAAA,CAAE,IAAA,EAAM,GAAA,EAAK,IAAI,GAAA,CAAI,IAAA,CAAK,CAAC,CAAC,GAAE,CAAE,CAAA;AACxE;AAIA,SAAS,UAAA,CAAW,MAAc,MAAA,EAAwD;AACxF,EAAA,MAAM,CAAA,GAAI,MAAA;AAAA,IACR,KAAA;AAAA,MACE,KAAK,WAAA,EAAY;AAAA,MACjB,aAAA,CAAc,QAAQ,CAAC,CAAA,KAAM,EAAE,QAAA,IAAY,CAAA,CAAE,SAAS,EAAA,CAAG;AAAA;AAC3D,GACF;AACA,EAAA,OAAO,CAAA,GAAI,EAAE,QAAA,EAAU,CAAA,CAAE,IAAA,EAAM,QAAQ,CAAA,CAAE,MAAA,EAAQ,IAAA,EAAM,CAAA,EAAE,GAAI,IAAA;AAC/D;AAGA,SAAS,QAAA,CACP,MAAA,EACA,MAAA,EACA,IAAA,EACA,IAAA,EACoB;AACpB,EAAA,MAAM,CAAA,GAAI,MAAA;AAAA,IACR,KAAA;AAAA,MACE,MAAA;AAAA,MACA,aAAA,CAAc,QAAQ,CAAC,CAAA,KAAM,EAAE,KAAA,GAAQ,IAAI,CAAA,IAAK,EAAE;AAAA;AACpD,GACF;AACA,EAAA,OAAO,CAAA,GAAI,EAAE,QAAA,EAAU,CAAA,CAAE,MAAM,MAAA,EAAQ,CAAA,CAAE,MAAA,EAAQ,IAAA,EAAK,GAAI,IAAA;AAC5D;AAeO,SAAS,iBAAA,CACd,IAAA,EACA,UAAA,EACA,KAAA,EACgB;AAChB,EAAA,IAAI,CAAC,IAAA,IAAQ,UAAA,CAAW,MAAA,KAAW,GAAG,OAAO,OAAA;AAI7C,EAAA,MAAM,OAAA,GAAU,WAAW,IAAI,CAAA;AAG/B,EAAA,MAAM,MAAA,GAAS,eAAA,CAAgB,OAAA,EAAS,UAAU,CAAA;AAClD,EAAA,IAAI,MAAA,CAAO,MAAA,KAAW,CAAA,EAAG,OAAO,OAAA;AAKhC,EAAA,MAAM,cAAA,GAAiB,OAAO,MAAA,IAAU,CAAA;AAsBxC,EAAA,IAAI,QAAA;AACJ,EAAA,MAAM,MAAA,GAAS,CAAC,OAAA,KAAyC;AACvD,IAAA,MAAM,MAAA,GAAS,OAAO,IAAA,CAAK,CAAC,MAAM,CAAA,CAAE,IAAA,KAAS,QAAQ,QAAQ,CAAA;AAC7D,IAAA,QAAA,KAAa,kBAAA,CAAmB,WAAA,CAAY,OAAO,CAAC,CAAA;AACpD,IAAA,IAAI,UAAU,eAAA,CAAgB,QAAA,EAAU,MAAM,CAAA,CAAE,KAAA,IAAS,qBAAqB,OAAO,OAAA;AACrF,IAAA,OAAO,EAAE,GAAG,OAAA,EAAS,cAAA,EAAe;AAAA,EACtC,CAAA;AAEA,EAAA,MAAM,QAAA,GAAW,UAAA,CAAW,OAAA,EAAS,MAAM,CAAA;AAC3C,EAAA,IAAI,QAAA,EAAU,OAAO,MAAA,CAAO,QAAQ,CAAA;AAEpC,EAAA,MAAM,MAAA,GAAS,SAAS,OAAO,CAAA;AAC/B,EAAA,IAAI,MAAA,CAAO,MAAA,KAAW,CAAA,EAAG,OAAO,OAAA;AAEhC,EAAA,MAAM,MAAA,GACJ,QAAA,CAAS,MAAA,EAAQ,MAAA,EAAQ,YAAY,IAAI,CAAA,IACzC,QAAA,CAAS,MAAA,EAAQ,QAAQ,UAAA,EAAY,IAAI,CAAA,IACzC,KAAA,GAAQ,SAAS,MAAM,CAAA;AACzB,EAAA,OAAO,MAAA,GAAS,MAAA,CAAO,MAAM,CAAA,GAAI,OAAA;AACnC","file":"chunk-SOTZVW3I.js","sourcesContent":["/**\n * Per-snippet language classification by candidate-set-relative set-difference.\n *\n * A ladder of rungs; the first rung whose leader clears a lead (margin) of ≥1\n * wins; otherwise `\"unknown\"`:\n *\n *   1   alphabet       — characters distinctive within the candidate set\n *   2a  function words — curated grammatical markers (highest precision)\n *   2b  frequent words — corpus content words\n *   3   franc          — optional trigram backstop for the distinctive-free\n *                        residual, injected as a resolver (this module stays\n *                        franc-free and importable without franc's tables)\n *\n * \"Distinctive\" is ALWAYS relative to the candidate set: a signal counts for a\n * candidate iff it appears in that candidate's profile and in NO other\n * candidate's. So `і` decides {uk, ru} (only uk has it) but is inert in\n * {uk, be} (both have it), and the word `и` decides {uk, ru} even though the\n * *letter* `и` is shared. Nothing is precomputed — uniqueness is the runtime\n * output, never stored.\n *\n * Above the ladder sits one veto. Ownership is additive evidence and can only\n * ever argue FOR a candidate, which leaves a closed set defenceless against text\n * written in a language it does not contain: Belarusian handed to {uk, ru} spends\n * its `і`s electing Ukrainian while its `ы`/`ў`/`э` — letters Ukrainian does not\n * have at all — count for nobody and stop nothing. So a winner is checked against\n * the text one last time, and a winner whose own alphabet cannot account for\n * {@link CONTRADICTION_SHARE} of it loses to `\"unknown\"`.\n *\n * Adapted to langtell's {@link LanguageProfile} shape: the `words` and `iso6393`\n * fields are optional here, so a bare `{ code, alphabet }` profile still\n * classifies on rung 1.\n */\nimport type { LanguageProfile } from \"../types.js\";\nimport { stripNoise, stripQuoted } from \"./scrub.js\";\n\n// Re-exported so the classifier stays the one door onto its own preprocessing.\nexport { stripNoise, stripQuoted } from \"./scrub.js\";\n\nexport const FRANC_RUNG = 3;\n\n/** Which rung decided a verdict; `null` when unknown. */\nexport type Rung = 1 | \"2a\" | \"2b\" | typeof FRANC_RUNG | null;\n\nexport interface SnippetVerdict {\n  /** Winning language code, or the sentinel `\"unknown\"`. */\n  language: string;\n  /** Lead of the winner over the runner-up, in the rung's own unit (distinctive\n   *  char/word count for rungs 1–2; franc score-gap for rung 3). 0 when unknown. */\n  margin: number;\n  /** Which rung decided; `null` when unknown. */\n  rung: Rung;\n  /** Whether ≥2 same-script candidates were in scope when the verdict was\n   *  reached. `true` ⇒ the distinctive-letter/word machinery actually chose\n   *  between candidates; `false` ⇒ the winner was the lone candidate in its\n   *  script, selected by script alone (no evidence it is *distinctively* that\n   *  language). `false` for `\"unknown\"`. */\n  discriminating: boolean;\n}\n\n/** A rung's verdict before {@link classifyBySnippet} stamps on the scope-derived\n *  `discriminating` flag (which a single rung can't know — it depends on how many\n *  same-script candidates were scoped). */\nexport type RungVerdict = Pick<SnippetVerdict, \"language\" | \"margin\" | \"rung\">;\n\nconst UNKNOWN: SnippetVerdict = {\n  language: \"unknown\",\n  margin: 0,\n  rung: null,\n  discriminating: false,\n};\n\n/** Resolver for rung 3 (the optional trigram backstop), injected into\n *  {@link classifyBySnippet} by callers that have franc available. Kept as an\n *  injected seam — not a direct import — so this module stays franc-free and\n *  importable without pulling franc's tables. Returns a rung-3 verdict or\n *  `null` (abstain).\n *\n *  Generic over the concrete profile type `P` the caller classifies with, so a\n *  consumer that defines a stricter profile (e.g. `words` required) can type its\n *  resolver over that exact shape and hand it to {@link classifyBySnippet} with\n *  no adapter — the resolver sees `readonly P[]`, the same array the classifier\n *  scoped from its input. Defaults to {@link LanguageProfile} for callers that\n *  don't narrow. */\nexport type Rung3Resolver<P extends LanguageProfile = LanguageProfile> = (\n  text: string,\n  scoped: readonly P[],\n) => RungVerdict | null;\n\nconst CYRILLIC_RE = /\\p{Script=Cyrillic}/u;\nconst LATIN_RE = /\\p{Script=Latin}/u;\n\n/** A coarse script bucket — the only two the candidate-relative classifier\n *  distinguishes today. `null` means \"no letters / undetermined\". */\nexport type ScriptName = \"cyrillic\" | \"latin\";\n\n/** Below this length, trigrams are too noisy to justify a rung-3 verdict. */\nexport const RUNG3_MIN_LENGTH = 24;\n\n/** The script most of `text` is written in, or `null` if it carries no letters.\n *  Noise (URLs/handles/hashtags) is stripped first so a single trailing link\n *  can't flip a multi-word Cyrillic title's vote to Latin. */\nfunction dominantScript(text: string): \"cyrillic\" | \"latin\" | null {\n  let cyr = 0;\n  let lat = 0;\n  for (const ch of stripNoise(text)) {\n    if (CYRILLIC_RE.test(ch)) cyr += 1;\n    else if (LATIN_RE.test(ch)) lat += 1;\n  }\n  if (cyr === 0 && lat === 0) return null;\n  return cyr >= lat ? \"cyrillic\" : \"latin\";\n}\n\n/** The script a profile's alphabet is written in, or `null` if it carries no\n *  Cyrillic/Latin letter. Exported so the fuser can derive each roster\n *  candidate's script without re-deriving the script regexes — a Latin alphabet\n *  ⇒ `\"latin\"`, a Cyrillic one ⇒ `\"cyrillic\"`. */\nexport function scriptOfProfile(profile: LanguageProfile): ScriptName | null {\n  for (const ch of profile.alphabet) {\n    if (CYRILLIC_RE.test(ch)) return \"cyrillic\";\n    if (LATIN_RE.test(ch)) return \"latin\";\n  }\n  return null;\n}\n\n/** Candidates whose script matches the text's dominant script (others can't tip\n *  the verdict). Empty when the text carries no letters. Generic over the\n *  concrete profile type `P`: the result is a subset of the input array, so it\n *  keeps `P` — a stricter caller's profiles stay strictly typed downstream. */\nexport function scopeCandidates<P extends LanguageProfile>(\n  text: string,\n  candidates: readonly P[],\n): P[] {\n  const script = dominantScript(text);\n  if (script === null) return [];\n  // Keep one profile per code. A language listed twice would otherwise make its\n  // own distinctive chars/words read as \"owned by ≥2 candidates\" in `tally`,\n  // cancelling them out and collapsing the verdict to \"unknown\".\n  const seen = new Set<string>();\n  const scoped: P[] = [];\n  for (const c of candidates) {\n    if (scriptOfProfile(c) !== script || seen.has(c.code)) continue;\n    seen.add(c.code);\n    scoped.push(c);\n  }\n  return scoped;\n}\n\n/**\n * Per-language set of characters globally unique within `profiles` — present in\n * exactly one profile's alphabet. Relative to the given profile set: the unique\n * set shrinks as languages are added (a second Latin language un-uniques a–z).\n */\nexport function distinctiveChars(profiles: readonly LanguageProfile[]): Map<string, Set<string>> {\n  const owners = new Map<string, string[]>();\n  for (const p of profiles) {\n    for (const ch of new Set(p.alphabet)) {\n      const list = owners.get(ch);\n      if (list) list.push(p.code);\n      else owners.set(ch, [p.code]);\n    }\n  }\n  const result = new Map<string, Set<string>>(profiles.map((p) => [p.code, new Set()]));\n  for (const [ch, codes] of owners) {\n    const [only] = codes;\n    if (codes.length === 1 && only !== undefined) result.get(only)?.add(ch);\n  }\n  return result;\n}\n\n/**\n * Share of a text's letters, in a profile's own script, that the profile's\n * alphabet does not contain — evidence AGAINST that profile.\n *\n * Beyond which a candidate is treated as contradicted by the text. Measured, not\n * picked: across a mixed corpus (Cyrillic siblings + Latin), the three\n * populations separate cleanly.\n *\n *   0.3–0.9 %  an in-language snippet quoting a sibling (a Ukrainian article\n *              carrying a Russian sentence, and vice versa)\n *   1.4–1.5 %  a foreign proper noun in otherwise monolingual prose\n *              (`Нұрсұлтан` in a Russian article, `Ђоковић` in another)\n *   2.3–17 %   text that is simply written in a language nobody on the roster\n *              profiles (Belarusian against {uk, ru}, German against {en})\n *\n * 2 % sits in the gap. It is deliberately nearer the incidental end: the cost of\n * vetoing too eagerly is an `\"unknown\"` a caller escalates, while the cost of\n * vetoing too late is a confident wrong language.\n */\nexport const CONTRADICTION_SHARE = 0.02;\n\n/**\n * A text's own alphabet: each letter it uses, and how often — its script's\n * letters only in the sense that non-letters are simply absent.\n *\n * Insertion-ordered, so a caller rendering it shows letters in the order the\n * reader met them rather than in an order a hash table chose.\n */\nexport type TextAlphabet = ReadonlyMap<string, number>;\n\n/** What one candidate's alphabet cannot account for in a text. */\nexport interface Contradiction {\n  /** The letters, distinct and in first-seen order. Empty when there are none. */\n  readonly letters: readonly string[];\n  /** Their weight, 0..1, against the letters of that candidate's script. */\n  readonly share: number;\n}\n\nconst NO_CONTRADICTION: Contradiction = { letters: [], share: 0 };\n\n/** {@link textAlphabet} over text a caller has already scrubbed. */\nfunction alphabetOfScrubbed(scrubbed: string): TextAlphabet {\n  const counts = new Map<string, number>();\n  for (const ch of scrubbed.toLowerCase()) {\n    if (!CYRILLIC_RE.test(ch) && !LATIN_RE.test(ch)) continue;\n    counts.set(ch, (counts.get(ch) ?? 0) + 1);\n  }\n  return counts;\n}\n\n/**\n * Derive the alphabet a text is written in, before asking anyone to account for\n * it.\n *\n * Derived ONCE and then compared against candidates, rather than re-walking the\n * text per candidate: for a screen reporting on a whole roster that is one pass\n * plus a set lookup each, and — more to the point — it makes \"the text's\n * alphabet\" a thing the caller can hold, print and diff, instead of a number\n * falling out of a comparison.\n *\n * Scrubbed first ({@link stripNoise}, {@link stripQuoted}): a URL's letters and\n * a quotation's letters are in the string without being the string's own.\n */\nexport function textAlphabet(text: string): TextAlphabet {\n  return alphabetOfScrubbed(stripQuoted(stripNoise(text)));\n}\n\n/**\n * Compare a derived {@link TextAlphabet} against one candidate.\n *\n * The primitive form, for a caller holding an alphabet and asking about several\n * candidates — an evidence report, an audit trail, a roster editor showing what\n * each choice would do.\n */\nexport function contradictionOf(alphabet: TextAlphabet, profile: LanguageProfile): Contradiction {\n  const script = scriptOfProfile(profile);\n  if (script === null) return NO_CONTRADICTION;\n  const inScript = script === \"cyrillic\" ? CYRILLIC_RE : LATIN_RE;\n  // `marks` joins the alphabet for the same reason it does at rung 1: an\n  // apostrophe is part of how uk/be spell, not a foreign letter. (It is not a\n  // letter, so it never reaches the alphabet — kept for the profiles whose\n  // marks ever grow to include one.)\n  const own = new Set(profile.alphabet + (profile.marks ?? \"\"));\n  const letters: string[] = [];\n  let foreign = 0;\n  let total = 0;\n  for (const [ch, count] of alphabet) {\n    // Only the candidate's own script is its business: a Cyrillic headline\n    // followed by a Latin brand name is not evidence against either language.\n    if (!inScript.test(ch)) continue;\n    total += count;\n    if (own.has(ch)) continue;\n    foreign += count;\n    letters.push(ch);\n  }\n  return { letters, share: total === 0 ? 0 : foreign / total };\n}\n\n/**\n * How much of `text` a candidate's own alphabet cannot account for.\n *\n * WHY THIS EXISTS AT ALL. The rung ladder is additive: it counts what each\n * candidate uniquely OWNS and never counts what a candidate cannot possibly\n * have written. Those are different questions, and the second one is the only\n * defence a closed set has against a language that is not in it. Belarusian\n * `Мова і культура Беларусі маюць багатую гісторыю` hands `і` to Ukrainian four\n * times over against {uk, ru} — while `ы`, a letter Ukrainian does not have,\n * sits in the same sentence saying the winner cannot be right. Ownership alone\n * cannot see that; this is what sees it.\n *\n * Exported so a caller that has to EXPLAIN a verdict (a diagnostics screen, an\n * audit trail) can show the same letters and the same number the veto acted on,\n * rather than deriving a second, drifting copy of them.\n */\nexport function contradiction(text: string, profile: LanguageProfile): Contradiction {\n  return contradictionOf(textAlphabet(text), profile);\n}\n\ninterface Membership {\n  code: string;\n  set: ReadonlySet<string>;\n}\n\n/** Lowercased Unicode letter-run tokens. Keeps single-char tokens (`і`, `и`). */\nfunction tokenize(text: string): string[] {\n  return text.toLowerCase().match(/\\p{L}+/gu) ?? [];\n}\n\n/**\n * Tally how many items (characters or word tokens) are distinctive to each\n * candidate — present in exactly one candidate's set. Items owned by zero or by\n * ≥2 candidates contribute nothing.\n */\nfunction tally(items: Iterable<string>, membership: readonly Membership[]): Map<string, number> {\n  const scores = new Map<string, number>(membership.map((m) => [m.code, 0]));\n  for (const item of items) {\n    let owner: string | null = null;\n    let owners = 0;\n    for (const m of membership) {\n      if (m.set.has(item)) {\n        owners += 1;\n        if (owners > 1) {\n          owner = null;\n          break;\n        }\n        owner = m.code;\n      }\n    }\n    if (owner !== null) scores.set(owner, (scores.get(owner) ?? 0) + 1);\n  }\n  return scores;\n}\n\n/** The leading candidate and its lead over the runner-up, or `null` if <1. */\nfunction leader(scores: Map<string, number>): { code: string; margin: number } | null {\n  let max = -1;\n  let second = -1;\n  let code: string | null = null;\n  for (const [c, score] of scores) {\n    if (score > max) {\n      second = max;\n      max = score;\n      code = c;\n    } else if (score > second) {\n      second = score;\n    }\n  }\n  if (code === null || max < 1) return null;\n  const margin = max - Math.max(second, 0);\n  return margin >= 1 ? { code, margin } : null;\n}\n\nfunction membershipFor(\n  candidates: readonly LanguageProfile[],\n  pick: (p: LanguageProfile) => Iterable<string>,\n): Membership[] {\n  return candidates.map((c) => ({ code: c.code, set: new Set(pick(c)) }));\n}\n\n/** Rung 1 — characters (alphabet + orthographic {@link LanguageProfile.marks})\n *  distinctive within the scoped candidate set. */\nfunction letterRung(text: string, scoped: readonly LanguageProfile[]): RungVerdict | null {\n  const r = leader(\n    tally(\n      text.toLowerCase(),\n      membershipFor(scoped, (p) => p.alphabet + (p.marks ?? \"\")),\n    ),\n  );\n  return r ? { language: r.code, margin: r.margin, rung: 1 } : null;\n}\n\n/** Rung 2 — distinctive words from the given tier (2a function, 2b frequent). */\nfunction wordRung(\n  tokens: readonly string[],\n  scoped: readonly LanguageProfile[],\n  tier: \"function\" | \"frequent\",\n  rung: \"2a\" | \"2b\",\n): RungVerdict | null {\n  const r = leader(\n    tally(\n      tokens,\n      membershipFor(scoped, (p) => p.words?.[tier] ?? []),\n    ),\n  );\n  return r ? { language: r.code, margin: r.margin, rung } : null;\n}\n\n/**\n * Classify `text` among `candidates`. Synchronous and allocation-light. Returns\n * `\"unknown\"` on empty evidence, on a tie inside the candidate set, when nothing\n * is distinctive, or when the winning candidate is contradicted by the text\n * itself (see {@link contradiction}).\n *\n * Generic over the concrete profile type `P`, inferred from `candidates`. The\n * optional `rung3` resolver is typed over the same `P`, so a consumer with a\n * stricter profile (e.g. `words` required) can pass its own resolver directly,\n * with no adapter — the resolver sees exactly the profiles the caller passed.\n * `P` defaults to {@link LanguageProfile}, so the bare two-argument form and\n * every existing call site are unchanged.\n */\nexport function classifyBySnippet<P extends LanguageProfile = LanguageProfile>(\n  text: string,\n  candidates: readonly P[],\n  rung3?: Rung3Resolver<P>,\n): SnippetVerdict {\n  if (!text || candidates.length === 0) return UNKNOWN;\n\n  // Drop URLs / @handles / #hashtags once, up front: trailing Latin noise must\n  // not flip the dominant-script vote nor pollute the per-rung tallies.\n  const cleaned = stripNoise(text);\n\n  // Restrict to candidates in the text's dominant script.\n  const scoped = scopeCandidates(cleaned, candidates);\n  if (scoped.length === 0) return UNKNOWN;\n\n  // ≥2 same-script candidates means the distinctive machinery actually had a\n  // choice to make; a lone scoped candidate wins by script alone. Stamped onto\n  // whichever rung decides — a single rung can't see the scope size.\n  const discriminating = scoped.length >= 2;\n\n  /**\n   * A winner the text itself argues against is no winner — see\n   * {@link contradiction}.\n   *\n   * Applied to whichever rung decided, franc's included: every rung answers the\n   * same forced-choice question, so every rung can be forced into the same wrong\n   * answer by a language the roster does not carry. The runner-up is NOT\n   * promoted — a set that could not account for the text does not get a second\n   * guess at it. `\"unknown\"` is the honest answer, and the signal a caller needs\n   * to widen the roster or escalate.\n   *\n   * Measured over the text's alphabet MINUS its quotations, while the rungs\n   * above tallied the text whole. The asymmetry is deliberate and is the whole\n   * point of measuring separately: a quotation is someone else's language and\n   * cannot be held against this author, whereas removing it from the tally would\n   * silently re-decide verdicts that have nothing to do with this veto. One\n   * derivation, computed the first time a rung produces a winner.\n   */\n  // Derived on first use: the texts that never reach a verdict — most of them —\n  // never pay for it.\n  let alphabet: TextAlphabet | undefined;\n  const settle = (verdict: RungVerdict): SnippetVerdict => {\n    const winner = scoped.find((c) => c.code === verdict.language);\n    alphabet ??= alphabetOfScrubbed(stripQuoted(cleaned));\n    if (winner && contradictionOf(alphabet, winner).share >= CONTRADICTION_SHARE) return UNKNOWN;\n    return { ...verdict, discriminating };\n  };\n\n  const byLetter = letterRung(cleaned, scoped);\n  if (byLetter) return settle(byLetter);\n\n  const tokens = tokenize(cleaned);\n  if (tokens.length === 0) return UNKNOWN;\n\n  const byWord =\n    wordRung(tokens, scoped, \"function\", \"2a\") ??\n    wordRung(tokens, scoped, \"frequent\", \"2b\") ??\n    rung3?.(cleaned, scoped);\n  return byWord ? settle(byWord) : UNKNOWN;\n}\n"]}