langtell 0.3.0 → 0.3.1

package/dist/{chunk-PT7R2BRQ.js → chunk-NQK7CZR2.js}

@@ -1,4 +1,4 @@
-import { classifyBySnippet } from './chunk-NCGZPEDA.js';
+import { classifyBySnippet } from './chunk-WYSCL5J5.js';
 
 // src/text.ts
 function evidenceFromText(text, candidates, rung3) {
@@ -31,5 +31,5 @@ function clamp01(value) {
 }
 
 export { evidenceFromText };
-//# sourceMappingURL=chunk-PT7R2BRQ.js.map
-//# sourceMappingURL=chunk-PT7R2BRQ.js.map
+//# sourceMappingURL=chunk-NQK7CZR2.js.map
+//# sourceMappingURL=chunk-NQK7CZR2.js.map

package/dist/{chunk-PT7R2BRQ.js.map → chunk-NQK7CZR2.js.map}

@@ -1 +1 @@
-{"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-PT7R2BRQ.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"]}
+{"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-NQK7CZR2.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-NCGZPEDA.js → chunk-WYSCL5J5.js}

@@ -127,5 +127,5 @@ function classifyBySnippet(text, candidates, rung3) {
 }
 
 export { FRANC_RUNG, classifyBySnippet, scopeCandidates };
-//# sourceMappingURL=chunk-NCGZPEDA.js.map
-//# sourceMappingURL=chunk-NCGZPEDA.js.map
+//# sourceMappingURL=chunk-WYSCL5J5.js.map
+//# sourceMappingURL=chunk-WYSCL5J5.js.map

package/dist/chunk-WYSCL5J5.js.map

@@ -0,0 +1 @@
+{"version":3,"sources":["../src/internal/classify.ts"],"names":[],"mappings":";AA0BO,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;AAkBjB,IAAM,cAAA,GAAoC;AAAA,EACxC,oBAAA;AAAA;AAAA,EACA,cAAA;AAAA;AAAA,EACA,2CAAA;AAAA;AAAA,EACA;AAAA;AACF,CAAA;AAIO,SAAS,WAAW,IAAA,EAAsB;AAC/C,EAAA,IAAI,GAAA,GAAM,IAAA;AACV,EAAA,KAAA,MAAW,MAAM,cAAA,EAAgB,GAAA,GAAM,GAAA,CAAI,OAAA,CAAQ,IAAI,GAAG,CAAA;AAC1D,EAAA,OAAO,GAAA;AACT;AAKA,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;AAGA,SAAS,cAAc,OAAA,EAAuD;AAC5E,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,aAAA,CAAc,CAAC,CAAA,KAAM,MAAA,IAAU,KAAK,GAAA,CAAI,CAAA,CAAE,IAAI,CAAA,EAAG;AACrD,IAAA,IAAA,CAAK,GAAA,CAAI,EAAE,IAAI,CAAA;AACf,IAAA,MAAA,CAAO,KAAK,CAAC,CAAA;AAAA,EACf;AACA,EAAA,OAAO,MAAA;AACT;AA8BA,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;AAcO,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;AAExC,EAAA,MAAM,QAAA,GAAW,UAAA,CAAW,OAAA,EAAS,MAAM,CAAA;AAC3C,EAAA,IAAI,QAAA,EAAU,OAAO,EAAE,GAAG,UAAU,cAAA,EAAe;AAEnD,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,EAAE,GAAG,MAAA,EAAQ,gBAAe,GAAI,OAAA;AAClD","file":"chunk-WYSCL5J5.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 * 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\";\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/** Below this length, trigrams are too noisy to justify a rung-3 verdict. */\nexport const RUNG3_MIN_LENGTH = 24;\n\n/**\n * Trailing/inline Latin \"noise\" tokens — URLs, @handles, #hashtags — that a\n * Cyrillic title commonly carries (a headline followed by a link or a social\n * handle). These are almost always Latin even on Cyrillic-language content, so\n * left in they can flip {@link dominantScript} to Latin and let genuinely\n * Cyrillic content scope to the wrong roster. Stripped before the script vote\n * AND before the rung tallies so the URL's letters never contribute either.\n *\n * Kept as separate simple patterns (applied in order — schemes/www before bare\n * domains) rather than one big alternation, so each stays readable. ASCII-only\n * `[a-z0-9-]` in the domain pattern means a Cyrillic word is never mistaken for\n * a domain.\n */\nconst NOISE_PATTERNS: readonly RegExp[] = [\n  /\\bhttps?:\\/\\/\\S+/gi, // full URLs\n  /\\bwww\\.\\S+/gi, // www.… without a scheme\n  /\\b[a-z0-9-]+(?:\\.[a-z0-9-]+)+(?:\\/\\S*)?/gi, // bare domains (example.com/path)\n  /[@#][\\p{L}\\p{N}_]+/gu, // @handles and #hashtags\n];\n\n/** Drop URLs / @handles / #hashtags so trailing Latin noise can't outvote the\n *  prose's script or pollute the per-rung tallies. */\nexport function stripNoise(text: string): string {\n  let out = text;\n  for (const re of NOISE_PATTERNS) out = out.replace(re, \" \");\n  return out;\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\n/** The script of a profile's alphabet. */\nfunction profileScript(profile: LanguageProfile): \"cyrillic\" | \"latin\" | 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 (profileScript(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\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, or when\n * nothing is distinctive.\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  const byLetter = letterRung(cleaned, scoped);\n  if (byLetter) return { ...byLetter, discriminating };\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 ? { ...byWord, discriminating } : UNKNOWN;\n}\n"]}

package/dist/classify.d.ts

@@ -51,13 +51,27 @@ type RungVerdict = Pick<SnippetVerdict, "language" | "margin" | "rung">;
  *  {@link classifyBySnippet} by callers that have franc available. Kept as an
  *  injected seam — not a direct import — so this module stays franc-free and
  *  importable without pulling franc's tables. Returns a rung-3 verdict or
- *  `null` (abstain). */
-type Rung3Resolver = (text: string, scoped: readonly LanguageProfile[]) => RungVerdict | null;
+ *  `null` (abstain).
+ *
+ *  Generic over the concrete profile type `P` the caller classifies with, so a
+ *  consumer that defines a stricter profile (e.g. `words` required) can type its
+ *  resolver over that exact shape and hand it to {@link classifyBySnippet} with
+ *  no adapter — the resolver sees `readonly P[]`, the same array the classifier
+ *  scoped from its input. Defaults to {@link LanguageProfile} for callers that
+ *  don't narrow. */
+type Rung3Resolver<P extends LanguageProfile = LanguageProfile> = (text: string, scoped: readonly P[]) => RungVerdict | null;
 /**
  * Classify `text` among `candidates`. Synchronous and allocation-light. Returns
  * `"unknown"` on empty evidence, on a tie inside the candidate set, or when
  * nothing is distinctive.
+ *
+ * Generic over the concrete profile type `P`, inferred from `candidates`. The
+ * optional `rung3` resolver is typed over the same `P`, so a consumer with a
+ * stricter profile (e.g. `words` required) can pass its own resolver directly,
+ * 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.
  */
-declare function classifyBySnippet(text: string, candidates: readonly LanguageProfile[], rung3?: Rung3Resolver): SnippetVerdict;
+declare function classifyBySnippet<P extends LanguageProfile = LanguageProfile>(text: string, candidates: readonly P[], rung3?: Rung3Resolver<P>): SnippetVerdict;
 
 export { FRANC_RUNG, type Rung, type Rung3Resolver, type RungVerdict, type SnippetVerdict, classifyBySnippet };

package/dist/classify.js

@@ -1,3 +1,3 @@
-export { FRANC_RUNG, classifyBySnippet } from './chunk-NCGZPEDA.js';
+export { FRANC_RUNG, classifyBySnippet } from './chunk-WYSCL5J5.js';
 //# sourceMappingURL=classify.js.map
 //# sourceMappingURL=classify.js.map

package/dist/franc.js

@@ -1,4 +1,4 @@
-import { scopeCandidates } from './chunk-NCGZPEDA.js';
+import { scopeCandidates } from './chunk-WYSCL5J5.js';
 import { francAll } from 'franc';
 
 var RUNG_MIN_LENGTH = 24;

package/dist/index.js

@@ -1,5 +1,5 @@
-import { evidenceFromText } from './chunk-PT7R2BRQ.js';
-export { evidenceFromText } from './chunk-PT7R2BRQ.js';
+import { evidenceFromText } from './chunk-NQK7CZR2.js';
+export { evidenceFromText } from './chunk-NQK7CZR2.js';
 import { evidenceFromHtml } from './chunk-KI4MAI3N.js';
 export { evidenceFromHtml } from './chunk-KI4MAI3N.js';
 import { evidenceFromHeaders } from './chunk-3LDE35U2.js';
@@ -7,7 +7,7 @@ export { evidenceFromHeaders } from './chunk-3LDE35U2.js';
 import { fuse } from './chunk-7G3MEXWK.js';
 export { fuse } from './chunk-7G3MEXWK.js';
 export { normalizeBCP47, normalizeLanguageCode, primarySubtag } from './chunk-OVSPOZ5J.js';
-import './chunk-NCGZPEDA.js';
+import './chunk-WYSCL5J5.js';
 
 // src/compile.ts
 function builtIns(candidates) {

package/dist/text.js

@@ -1,4 +1,4 @@
-export { evidenceFromText } from './chunk-PT7R2BRQ.js';
-import './chunk-NCGZPEDA.js';
+export { evidenceFromText } from './chunk-NQK7CZR2.js';
+import './chunk-WYSCL5J5.js';
 //# sourceMappingURL=text.js.map
 //# sourceMappingURL=text.js.map

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "langtell",
-  "version": "0.3.0",
+  "version": "0.3.1",
   "description": "Tell me the language — evidence-fusion language detection for short strings, with an auditable confidence trail.",
   "type": "module",
   "license": "MIT",

package/dist/chunk-NCGZPEDA.js.map

@@ -1 +0,0 @@
-{"version":3,"sources":["../src/internal/classify.ts"],"names":[],"mappings":";AA0BO,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;AAYA,IAAM,WAAA,GAAc,sBAAA;AACpB,IAAM,QAAA,GAAW,mBAAA;AAkBjB,IAAM,cAAA,GAAoC;AAAA,EACxC,oBAAA;AAAA;AAAA,EACA,cAAA;AAAA;AAAA,EACA,2CAAA;AAAA;AAAA,EACA;AAAA;AACF,CAAA;AAIO,SAAS,WAAW,IAAA,EAAsB;AAC/C,EAAA,IAAI,GAAA,GAAM,IAAA;AACV,EAAA,KAAA,MAAW,MAAM,cAAA,EAAgB,GAAA,GAAM,GAAA,CAAI,OAAA,CAAQ,IAAI,GAAG,CAAA;AAC1D,EAAA,OAAO,GAAA;AACT;AAKA,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;AAGA,SAAS,cAAc,OAAA,EAAuD;AAC5E,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;AAIO,SAAS,eAAA,CACd,MACA,UAAA,EACmB;AACnB,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,SAA4B,EAAC;AACnC,EAAA,KAAA,MAAW,KAAK,UAAA,EAAY;AAC1B,IAAA,IAAI,aAAA,CAAc,CAAC,CAAA,KAAM,MAAA,IAAU,KAAK,GAAA,CAAI,CAAA,CAAE,IAAI,CAAA,EAAG;AACrD,IAAA,IAAA,CAAK,GAAA,CAAI,EAAE,IAAI,CAAA;AACf,IAAA,MAAA,CAAO,KAAK,CAAC,CAAA;AAAA,EACf;AACA,EAAA,OAAO,MAAA;AACT;AA8BA,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;AAOO,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;AAExC,EAAA,MAAM,QAAA,GAAW,UAAA,CAAW,OAAA,EAAS,MAAM,CAAA;AAC3C,EAAA,IAAI,QAAA,EAAU,OAAO,EAAE,GAAG,UAAU,cAAA,EAAe;AAEnD,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,EAAE,GAAG,MAAA,EAAQ,gBAAe,GAAI,OAAA;AAClD","file":"chunk-NCGZPEDA.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 * 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\";\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). */\nexport type Rung3Resolver = (\n  text: string,\n  scoped: readonly LanguageProfile[],\n) => RungVerdict | null;\n\nconst CYRILLIC_RE = /\\p{Script=Cyrillic}/u;\nconst LATIN_RE = /\\p{Script=Latin}/u;\n\n/** Below this length, trigrams are too noisy to justify a rung-3 verdict. */\nexport const RUNG3_MIN_LENGTH = 24;\n\n/**\n * Trailing/inline Latin \"noise\" tokens — URLs, @handles, #hashtags — that a\n * Cyrillic title commonly carries (a headline followed by a link or a social\n * handle). These are almost always Latin even on Cyrillic-language content, so\n * left in they can flip {@link dominantScript} to Latin and let genuinely\n * Cyrillic content scope to the wrong roster. Stripped before the script vote\n * AND before the rung tallies so the URL's letters never contribute either.\n *\n * Kept as separate simple patterns (applied in order — schemes/www before bare\n * domains) rather than one big alternation, so each stays readable. ASCII-only\n * `[a-z0-9-]` in the domain pattern means a Cyrillic word is never mistaken for\n * a domain.\n */\nconst NOISE_PATTERNS: readonly RegExp[] = [\n  /\\bhttps?:\\/\\/\\S+/gi, // full URLs\n  /\\bwww\\.\\S+/gi, // www.… without a scheme\n  /\\b[a-z0-9-]+(?:\\.[a-z0-9-]+)+(?:\\/\\S*)?/gi, // bare domains (example.com/path)\n  /[@#][\\p{L}\\p{N}_]+/gu, // @handles and #hashtags\n];\n\n/** Drop URLs / @handles / #hashtags so trailing Latin noise can't outvote the\n *  prose's script or pollute the per-rung tallies. */\nexport function stripNoise(text: string): string {\n  let out = text;\n  for (const re of NOISE_PATTERNS) out = out.replace(re, \" \");\n  return out;\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\n/** The script of a profile's alphabet. */\nfunction profileScript(profile: LanguageProfile): \"cyrillic\" | \"latin\" | 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. */\nexport function scopeCandidates(\n  text: string,\n  candidates: readonly LanguageProfile[],\n): LanguageProfile[] {\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: LanguageProfile[] = [];\n  for (const c of candidates) {\n    if (profileScript(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\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, or when\n * nothing is distinctive.\n */\nexport function classifyBySnippet(\n  text: string,\n  candidates: readonly LanguageProfile[],\n  rung3?: Rung3Resolver,\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  const byLetter = letterRung(cleaned, scoped);\n  if (byLetter) return { ...byLetter, discriminating };\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 ? { ...byWord, discriminating } : UNKNOWN;\n}\n"]}