langtell 0.4.0 → 0.5.0

package/dist/{chunk-G44HHVK5.js → chunk-6PWEE3SR.js}

@@ -1,5 +1,5 @@
-import { normalizeBCP47 } from './chunk-OVSPOZ5J.js';
-import { scriptOfProfile } from './chunk-U34Z3ZSV.js';
+import { normalizeBCP47 } from './chunk-YCUSX3GG.js';
+import { scriptOfProfile } from './chunk-BL627TWI.js';
 
 // src/fuse.ts
 var DEFAULT_KIND_WEIGHT = {
@@ -136,5 +136,5 @@ function clamp01(value) {
 }
 
 export { fuse };
-//# sourceMappingURL=chunk-G44HHVK5.js.map
-//# sourceMappingURL=chunk-G44HHVK5.js.map
+//# sourceMappingURL=chunk-6PWEE3SR.js.map
+//# sourceMappingURL=chunk-6PWEE3SR.js.map

package/dist/{chunk-G44HHVK5.js.map → chunk-6PWEE3SR.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,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;AAEhC,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,GACJ,OAAA,CAAQ,IAAA,CAAK,MAAM,CAAA,IAAK,OAAA,CAAQ,IAAA,CAAK,IAAI,CAAA,IAAK,mBAAA,CAAoB,IAAA,CAAK,IAAI,CAAA,IAAK,GAAA;AAClF,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,wBAAwB,OAAO,CAAA;AAE9C,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;AAG1F,IAAA,IAAI,MAAA,KAAW,IAAA,IAAQ,MAAA,CAAO,GAAA,CAAI,MAAM,CAAA,EAAG;AACzC,MAAA,MAAM,KAAA,GAAQ,MAAA,CAAO,GAAA,CAAI,MAAM,CAAA,IAAK,CAAA;AACpC,MAAA,OAAO;AAAA,QACL,QAAA,EAAU,MAAA;AAAA,QACV,UAAA,EAAY,OAAA,CAAQ,KAAA,IAAS,KAAA,GAAQ,IAAA,CAAK,CAAA;AAAA,QAC1C,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;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;AAKA,SAAS,wBAAwB,QAAA,EAAsD;AACrF,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,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-G44HHVK5.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  \"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\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 =\n      weights[item.source] ?? weights[item.kind] ?? DEFAULT_KIND_WEIGHT[item.kind] ?? 0.5;\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);\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.\n    if (pinned !== null && scores.has(pinned)) {\n      const score = scores.get(pinned) ?? 0;\n      return {\n        language: pinned,\n        confidence: clamp01(score / (score + 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/** 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). */\nfunction confidentScriptLanguage(evidence: readonly LanguageEvidence[]): 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    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,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;AAEhC,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,GACJ,OAAA,CAAQ,IAAA,CAAK,MAAM,CAAA,IAAK,OAAA,CAAQ,IAAA,CAAK,IAAI,CAAA,IAAK,mBAAA,CAAoB,IAAA,CAAK,IAAI,CAAA,IAAK,GAAA;AAClF,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,wBAAwB,OAAO,CAAA;AAE9C,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;AAG1F,IAAA,IAAI,MAAA,KAAW,IAAA,IAAQ,MAAA,CAAO,GAAA,CAAI,MAAM,CAAA,EAAG;AACzC,MAAA,MAAM,KAAA,GAAQ,MAAA,CAAO,GAAA,CAAI,MAAM,CAAA,IAAK,CAAA;AACpC,MAAA,OAAO;AAAA,QACL,QAAA,EAAU,MAAA;AAAA,QACV,UAAA,EAAY,OAAA,CAAQ,KAAA,IAAS,KAAA,GAAQ,IAAA,CAAK,CAAA;AAAA,QAC1C,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;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;AAKA,SAAS,wBAAwB,QAAA,EAAsD;AACrF,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,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-6PWEE3SR.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  \"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\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 =\n      weights[item.source] ?? weights[item.kind] ?? DEFAULT_KIND_WEIGHT[item.kind] ?? 0.5;\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);\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.\n    if (pinned !== null && scores.has(pinned)) {\n      const score = scores.get(pinned) ?? 0;\n      return {\n        language: pinned,\n        confidence: clamp01(score / (score + 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/** 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). */\nfunction confidentScriptLanguage(evidence: readonly LanguageEvidence[]): 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    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-KCK3XWCJ.js → chunk-7TDGJOIJ.js}

@@ -1,4 +1,4 @@
-import { classifyBySnippet } from './chunk-U34Z3ZSV.js';
+import { classifyBySnippet } from './chunk-BL627TWI.js';
 
 // src/text.ts
 function evidenceFromText(text, candidates, rung3) {
@@ -31,5 +31,5 @@ function clamp01(value) {
 }
 
 export { evidenceFromText };
-//# sourceMappingURL=chunk-KCK3XWCJ.js.map
-//# sourceMappingURL=chunk-KCK3XWCJ.js.map
+//# sourceMappingURL=chunk-7TDGJOIJ.js.map
+//# sourceMappingURL=chunk-7TDGJOIJ.js.map

package/dist/{chunk-KCK3XWCJ.js.map → chunk-7TDGJOIJ.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-KCK3XWCJ.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-7TDGJOIJ.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-U34Z3ZSV.js → chunk-BL627TWI.js}

@@ -8,6 +8,7 @@ var UNKNOWN = {
 };
 var CYRILLIC_RE = /\p{Script=Cyrillic}/u;
 var LATIN_RE = /\p{Script=Latin}/u;
+var RUNG3_MIN_LENGTH = 24;
 var NOISE_PATTERNS = [
   /\bhttps?:\/\/\S+/gi,
   // full URLs
@@ -126,6 +127,6 @@ function classifyBySnippet(text, candidates, rung3) {
   return byWord ? { ...byWord, discriminating } : UNKNOWN;
 }
 
-export { FRANC_RUNG, classifyBySnippet, scopeCandidates, scriptOfProfile };
-//# sourceMappingURL=chunk-U34Z3ZSV.js.map
-//# sourceMappingURL=chunk-U34Z3ZSV.js.map
+export { FRANC_RUNG, RUNG3_MIN_LENGTH, classifyBySnippet, scopeCandidates, scriptOfProfile };
+//# sourceMappingURL=chunk-BL627TWI.js.map
+//# sourceMappingURL=chunk-BL627TWI.js.map

package/dist/chunk-BL627TWI.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;AAOV,IAAM,gBAAA,GAAmB;AAehC,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;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;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-BL627TWI.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/** 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/**\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 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\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/{chunk-3LDE35U2.js → chunk-FEKBPTHK.js}

@@ -1,4 +1,4 @@
-import { primarySubtag } from './chunk-OVSPOZ5J.js';
+import { primarySubtag } from './chunk-YCUSX3GG.js';
 
 // src/headers.ts
 function evidenceFromHeaders(headers) {
@@ -32,5 +32,5 @@ function isHeaders(headers) {
 }
 
 export { evidenceFromHeaders };
-//# sourceMappingURL=chunk-3LDE35U2.js.map
-//# sourceMappingURL=chunk-3LDE35U2.js.map
+//# sourceMappingURL=chunk-FEKBPTHK.js.map
+//# sourceMappingURL=chunk-FEKBPTHK.js.map

package/dist/{chunk-3LDE35U2.js.map → chunk-FEKBPTHK.js.map}

@@ -1 +1 @@
-{"version":3,"sources":["../src/headers.ts"],"names":[],"mappings":";;;AAIO,SAAS,oBAAoB,OAAA,EAAoD;AACtF,EAAA,IAAI,OAAA,KAAY,MAAA,EAAW,OAAO,EAAC;AAEnC,EAAA,MAAM,KAAA,GAAQ,SAAA,CAAU,OAAA,EAAS,kBAAkB,CAAA;AACnD,EAAA,MAAM,IAAA,GAAO,cAAc,KAAK,CAAA;AAChC,EAAA,IAAI,IAAA,KAAS,IAAA,EAAM,OAAO,EAAC;AAE3B,EAAA,OAAO;AAAA,IACL;AAAA,MACE,IAAA,EAAM,uBAAA;AAAA,MACN,QAAA,EAAU,IAAA;AAAA,MACV,UAAA,EAAY,GAAA;AAAA,MACZ,MAAA,EAAQ,uBAAA;AAAA,MACR,OAAO,KAAA,IAAS;AAAA;AAClB,GACF;AACF;AAEA,SAAS,SAAA,CAAU,SAAoB,IAAA,EAAkC;AACvE,EAAA,IAAI,SAAA,CAAU,OAAO,CAAA,EAAG;AACtB,IAAA,OAAO,OAAA,CAAQ,GAAA,CAAI,IAAI,CAAA,IAAK,MAAA;AAAA,EAC9B;AACA,EAAA,KAAA,MAAW,CAAC,GAAA,EAAK,KAAK,KAAK,MAAA,CAAO,OAAA,CAAQ,OAAO,CAAA,EAAG;AAClD,IAAA,IAAI,GAAA,CAAI,WAAA,EAAY,KAAM,IAAA,EAAM;AAChC,IAAA,IAAI,MAAM,OAAA,CAAQ,KAAK,GAAG,OAAO,KAAA,CAAM,KAAK,GAAG,CAAA;AAC/C,IAAA,OAAO,KAAA,IAAS,MAAA;AAAA,EAClB;AACA,EAAA,OAAO,MAAA;AACT;AAEA,SAAS,UAAU,OAAA,EAAwC;AACzD,EAAA,OAAO,OAAO,OAAA,KAAY,WAAA,IAAe,OAAA,YAAmB,OAAA;AAC9D","file":"chunk-3LDE35U2.js","sourcesContent":["import type { HeaderBag, LanguageEvidence } from \"./types.js\";\nimport { primarySubtag } from \"./internal/bcp47.js\";\n\n/** Producer: the HTTP `Content-Language` response header. */\nexport function evidenceFromHeaders(headers: HeaderBag | undefined): LanguageEvidence[] {\n  if (headers === undefined) return [];\n\n  const value = getHeader(headers, \"content-language\");\n  const lang = primarySubtag(value);\n  if (lang === null) return [];\n\n  return [\n    {\n      kind: \"http-content-language\",\n      language: lang,\n      confidence: 0.8,\n      source: \"http-content-language\",\n      value: value ?? \"\",\n    },\n  ];\n}\n\nfunction getHeader(headers: HeaderBag, name: string): string | undefined {\n  if (isHeaders(headers)) {\n    return headers.get(name) ?? undefined;\n  }\n  for (const [key, value] of Object.entries(headers)) {\n    if (key.toLowerCase() !== name) continue;\n    if (Array.isArray(value)) return value.join(\",\");\n    return value ?? undefined;\n  }\n  return undefined;\n}\n\nfunction isHeaders(headers: HeaderBag): headers is Headers {\n  return typeof Headers !== \"undefined\" && headers instanceof Headers;\n}\n"]}
+{"version":3,"sources":["../src/headers.ts"],"names":[],"mappings":";;;AAIO,SAAS,oBAAoB,OAAA,EAAoD;AACtF,EAAA,IAAI,OAAA,KAAY,MAAA,EAAW,OAAO,EAAC;AAEnC,EAAA,MAAM,KAAA,GAAQ,SAAA,CAAU,OAAA,EAAS,kBAAkB,CAAA;AACnD,EAAA,MAAM,IAAA,GAAO,cAAc,KAAK,CAAA;AAChC,EAAA,IAAI,IAAA,KAAS,IAAA,EAAM,OAAO,EAAC;AAE3B,EAAA,OAAO;AAAA,IACL;AAAA,MACE,IAAA,EAAM,uBAAA;AAAA,MACN,QAAA,EAAU,IAAA;AAAA,MACV,UAAA,EAAY,GAAA;AAAA,MACZ,MAAA,EAAQ,uBAAA;AAAA,MACR,OAAO,KAAA,IAAS;AAAA;AAClB,GACF;AACF;AAEA,SAAS,SAAA,CAAU,SAAoB,IAAA,EAAkC;AACvE,EAAA,IAAI,SAAA,CAAU,OAAO,CAAA,EAAG;AACtB,IAAA,OAAO,OAAA,CAAQ,GAAA,CAAI,IAAI,CAAA,IAAK,MAAA;AAAA,EAC9B;AACA,EAAA,KAAA,MAAW,CAAC,GAAA,EAAK,KAAK,KAAK,MAAA,CAAO,OAAA,CAAQ,OAAO,CAAA,EAAG;AAClD,IAAA,IAAI,GAAA,CAAI,WAAA,EAAY,KAAM,IAAA,EAAM;AAChC,IAAA,IAAI,MAAM,OAAA,CAAQ,KAAK,GAAG,OAAO,KAAA,CAAM,KAAK,GAAG,CAAA;AAC/C,IAAA,OAAO,KAAA,IAAS,MAAA;AAAA,EAClB;AACA,EAAA,OAAO,MAAA;AACT;AAEA,SAAS,UAAU,OAAA,EAAwC;AACzD,EAAA,OAAO,OAAO,OAAA,KAAY,WAAA,IAAe,OAAA,YAAmB,OAAA;AAC9D","file":"chunk-FEKBPTHK.js","sourcesContent":["import type { HeaderBag, LanguageEvidence } from \"./types.js\";\nimport { primarySubtag } from \"./internal/bcp47.js\";\n\n/** Producer: the HTTP `Content-Language` response header. */\nexport function evidenceFromHeaders(headers: HeaderBag | undefined): LanguageEvidence[] {\n  if (headers === undefined) return [];\n\n  const value = getHeader(headers, \"content-language\");\n  const lang = primarySubtag(value);\n  if (lang === null) return [];\n\n  return [\n    {\n      kind: \"http-content-language\",\n      language: lang,\n      confidence: 0.8,\n      source: \"http-content-language\",\n      value: value ?? \"\",\n    },\n  ];\n}\n\nfunction getHeader(headers: HeaderBag, name: string): string | undefined {\n  if (isHeaders(headers)) {\n    return headers.get(name) ?? undefined;\n  }\n  for (const [key, value] of Object.entries(headers)) {\n    if (key.toLowerCase() !== name) continue;\n    if (Array.isArray(value)) return value.join(\",\");\n    return value ?? undefined;\n  }\n  return undefined;\n}\n\nfunction isHeaders(headers: HeaderBag): headers is Headers {\n  return typeof Headers !== \"undefined\" && headers instanceof Headers;\n}\n"]}

package/dist/{chunk-KI4MAI3N.js → chunk-K4MXTIY7.js}

@@ -1,4 +1,4 @@
-import { normalizeBCP47 } from './chunk-OVSPOZ5J.js';
+import { normalizeBCP47 } from './chunk-YCUSX3GG.js';
 
 // src/html.ts
 function evidenceFromHtml(html) {
@@ -23,5 +23,5 @@ function pushTag(out, kind, confidence, raw) {
 }
 
 export { evidenceFromHtml };
-//# sourceMappingURL=chunk-KI4MAI3N.js.map
-//# sourceMappingURL=chunk-KI4MAI3N.js.map
+//# sourceMappingURL=chunk-K4MXTIY7.js.map
+//# sourceMappingURL=chunk-K4MXTIY7.js.map

package/dist/{chunk-KI4MAI3N.js.map → chunk-K4MXTIY7.js.map}

@@ -1 +1 @@
-{"version":3,"sources":["../src/html.ts"],"names":[],"mappings":";;;AAeO,SAAS,iBAAiB,IAAA,EAA8C;AAC7E,EAAA,IAAI,IAAA,KAAS,UAAa,IAAA,CAAK,IAAA,GAAO,MAAA,KAAW,CAAA,SAAU,EAAC;AAE5D,EAAA,MAAM,MAA0B,EAAC;AAEjC,EAAA,MAAM,QAAA,GAAW,sCAAA,CAAuC,IAAA,CAAK,IAAI,IAAI,CAAC,CAAA;AACtE,EAAA,OAAA,CAAQ,GAAA,EAAK,WAAA,EAAa,GAAA,EAAK,QAAQ,CAAA;AAGvC,EAAA,MAAM,kBACJ,qFAAA,CAAsF,IAAA;AAAA,IACpF;AAAA,GACF,GAAI,CAAC,CAAA,IACL,qFAAA,CAAsF,IAAA;AAAA,IACpF;AAAA,MACE,CAAC,CAAA;AACP,EAAA,OAAA,CAAQ,GAAA,EAAK,uBAAA,EAAyB,GAAA,EAAK,eAAe,CAAA;AAG1D,EAAA,MAAM,QAAA,GACJ,4EAAA,CAA6E,IAAA,CAAK,IAAI,CAAA,GAAI,CAAC,CAAA,IAC3F,4EAAA,CAA6E,IAAA,CAAK,IAAI,CAAA,GAAI,CAAC,CAAA;AAC7F,EAAA,OAAA,CAAQ,GAAA,EAAK,gBAAA,EAAkB,GAAA,EAAK,QAAQ,CAAA;AAE5C,EAAA,OAAO,GAAA;AACT;AAEA,SAAS,OAAA,CACP,GAAA,EACA,IAAA,EACA,UAAA,EACA,GAAA,EACM;AACN,EAAA,MAAM,IAAA,GAAO,eAAe,GAAG,CAAA;AAC/B,EAAA,IAAI,SAAS,IAAA,EAAM;AACnB,EAAA,GAAA,CAAI,IAAA,CAAK,EAAE,IAAA,EAAM,QAAA,EAAU,IAAA,EAAM,UAAA,EAAY,MAAA,EAAQ,IAAA,EAAM,KAAA,EAAO,GAAA,IAAO,EAAA,EAAI,CAAA;AAC/E","file":"chunk-KI4MAI3N.js","sourcesContent":["import type { LanguageEvidence } from \"./types.js\";\nimport { normalizeBCP47 } from \"./internal/bcp47.js\";\n\n/**\n * Producer: language clues from an HTML string's metadata.\n *\n * Reads three independent declarations, each emitted as its own evidence item\n * (the fuser weighs them):\n *   - `<html lang>`                          → `html-lang`\n *   - `<meta http-equiv=\"content-language\">` → `meta-content-language`\n *   - `<meta property=\"og:locale\">`          → `meta-og-locale`\n *\n * All tags are BCP-47-normalized (`uk-UA` → `uk`, `en_US` → `en`). Sync and\n * zero-dependency — regex extraction only, never a DOM parse.\n */\nexport function evidenceFromHtml(html: string | undefined): LanguageEvidence[] {\n  if (html === undefined || html.trim().length === 0) return [];\n\n  const out: LanguageEvidence[] = [];\n\n  const htmlLang = /<html\\b[^>]*\\blang=[\"']?([^\"'\\s>]+)/i.exec(html)?.[1];\n  pushTag(out, \"html-lang\", 0.7, htmlLang);\n\n  // <meta http-equiv=\"content-language\" content=\"uk\"> (attribute order varies).\n  const metaContentLang =\n    /<meta\\b[^>]*\\bhttp-equiv=[\"']?content-language[\"']?[^>]*\\bcontent=[\"']?([^\"'\\s>]+)/i.exec(\n      html,\n    )?.[1] ??\n    /<meta\\b[^>]*\\bcontent=[\"']?([^\"'\\s>]+)[\"']?[^>]*\\bhttp-equiv=[\"']?content-language/i.exec(\n      html,\n    )?.[1];\n  pushTag(out, \"meta-content-language\", 0.6, metaContentLang);\n\n  // <meta property=\"og:locale\" content=\"uk_UA\"> (attribute order varies).\n  const ogLocale =\n    /<meta\\b[^>]*\\bproperty=[\"']?og:locale[\"']?[^>]*\\bcontent=[\"']?([^\"'\\s>]+)/i.exec(html)?.[1] ??\n    /<meta\\b[^>]*\\bcontent=[\"']?([^\"'\\s>]+)[\"']?[^>]*\\bproperty=[\"']?og:locale/i.exec(html)?.[1];\n  pushTag(out, \"meta-og-locale\", 0.6, ogLocale);\n\n  return out;\n}\n\nfunction pushTag(\n  out: LanguageEvidence[],\n  kind: \"html-lang\" | \"meta-content-language\" | \"meta-og-locale\",\n  confidence: number,\n  raw: string | undefined,\n): void {\n  const lang = normalizeBCP47(raw);\n  if (lang === null) return;\n  out.push({ kind, language: lang, confidence, source: kind, value: raw ?? \"\" });\n}\n"]}
+{"version":3,"sources":["../src/html.ts"],"names":[],"mappings":";;;AAeO,SAAS,iBAAiB,IAAA,EAA8C;AAC7E,EAAA,IAAI,IAAA,KAAS,UAAa,IAAA,CAAK,IAAA,GAAO,MAAA,KAAW,CAAA,SAAU,EAAC;AAE5D,EAAA,MAAM,MAA0B,EAAC;AAEjC,EAAA,MAAM,QAAA,GAAW,sCAAA,CAAuC,IAAA,CAAK,IAAI,IAAI,CAAC,CAAA;AACtE,EAAA,OAAA,CAAQ,GAAA,EAAK,WAAA,EAAa,GAAA,EAAK,QAAQ,CAAA;AAGvC,EAAA,MAAM,kBACJ,qFAAA,CAAsF,IAAA;AAAA,IACpF;AAAA,GACF,GAAI,CAAC,CAAA,IACL,qFAAA,CAAsF,IAAA;AAAA,IACpF;AAAA,MACE,CAAC,CAAA;AACP,EAAA,OAAA,CAAQ,GAAA,EAAK,uBAAA,EAAyB,GAAA,EAAK,eAAe,CAAA;AAG1D,EAAA,MAAM,QAAA,GACJ,4EAAA,CAA6E,IAAA,CAAK,IAAI,CAAA,GAAI,CAAC,CAAA,IAC3F,4EAAA,CAA6E,IAAA,CAAK,IAAI,CAAA,GAAI,CAAC,CAAA;AAC7F,EAAA,OAAA,CAAQ,GAAA,EAAK,gBAAA,EAAkB,GAAA,EAAK,QAAQ,CAAA;AAE5C,EAAA,OAAO,GAAA;AACT;AAEA,SAAS,OAAA,CACP,GAAA,EACA,IAAA,EACA,UAAA,EACA,GAAA,EACM;AACN,EAAA,MAAM,IAAA,GAAO,eAAe,GAAG,CAAA;AAC/B,EAAA,IAAI,SAAS,IAAA,EAAM;AACnB,EAAA,GAAA,CAAI,IAAA,CAAK,EAAE,IAAA,EAAM,QAAA,EAAU,IAAA,EAAM,UAAA,EAAY,MAAA,EAAQ,IAAA,EAAM,KAAA,EAAO,GAAA,IAAO,EAAA,EAAI,CAAA;AAC/E","file":"chunk-K4MXTIY7.js","sourcesContent":["import type { LanguageEvidence } from \"./types.js\";\nimport { normalizeBCP47 } from \"./internal/bcp47.js\";\n\n/**\n * Producer: language clues from an HTML string's metadata.\n *\n * Reads three independent declarations, each emitted as its own evidence item\n * (the fuser weighs them):\n *   - `<html lang>`                          → `html-lang`\n *   - `<meta http-equiv=\"content-language\">` → `meta-content-language`\n *   - `<meta property=\"og:locale\">`          → `meta-og-locale`\n *\n * All tags are BCP-47-normalized (`uk-UA` → `uk`, `en_US` → `en`). Sync and\n * zero-dependency — regex extraction only, never a DOM parse.\n */\nexport function evidenceFromHtml(html: string | undefined): LanguageEvidence[] {\n  if (html === undefined || html.trim().length === 0) return [];\n\n  const out: LanguageEvidence[] = [];\n\n  const htmlLang = /<html\\b[^>]*\\blang=[\"']?([^\"'\\s>]+)/i.exec(html)?.[1];\n  pushTag(out, \"html-lang\", 0.7, htmlLang);\n\n  // <meta http-equiv=\"content-language\" content=\"uk\"> (attribute order varies).\n  const metaContentLang =\n    /<meta\\b[^>]*\\bhttp-equiv=[\"']?content-language[\"']?[^>]*\\bcontent=[\"']?([^\"'\\s>]+)/i.exec(\n      html,\n    )?.[1] ??\n    /<meta\\b[^>]*\\bcontent=[\"']?([^\"'\\s>]+)[\"']?[^>]*\\bhttp-equiv=[\"']?content-language/i.exec(\n      html,\n    )?.[1];\n  pushTag(out, \"meta-content-language\", 0.6, metaContentLang);\n\n  // <meta property=\"og:locale\" content=\"uk_UA\"> (attribute order varies).\n  const ogLocale =\n    /<meta\\b[^>]*\\bproperty=[\"']?og:locale[\"']?[^>]*\\bcontent=[\"']?([^\"'\\s>]+)/i.exec(html)?.[1] ??\n    /<meta\\b[^>]*\\bcontent=[\"']?([^\"'\\s>]+)[\"']?[^>]*\\bproperty=[\"']?og:locale/i.exec(html)?.[1];\n  pushTag(out, \"meta-og-locale\", 0.6, ogLocale);\n\n  return out;\n}\n\nfunction pushTag(\n  out: LanguageEvidence[],\n  kind: \"html-lang\" | \"meta-content-language\" | \"meta-og-locale\",\n  confidence: number,\n  raw: string | undefined,\n): void {\n  const lang = normalizeBCP47(raw);\n  if (lang === null) return;\n  out.push({ kind, language: lang, confidence, source: kind, value: raw ?? \"\" });\n}\n"]}

package/dist/{chunk-OVSPOZ5J.js → chunk-YCUSX3GG.js}

@@ -54,6 +54,8 @@ var ALIASES = {
   "po polsku": "pl",
   polish: "pl",
   \u043F\u043E\u043B\u044C\u0441\u044C\u043A\u0430: "pl",
+  "\u043F\u043E\u043B\u044C\u0441\u044C\u043A\u0430 \u043C\u043E\u0432\u0430": "pl",
+  "\u043F\u043E-\u043F\u043E\u043B\u044C\u0441\u044C\u043A\u0438": "pl",
   // German
   de: "de",
   deu: "de",
@@ -62,6 +64,8 @@ var ALIASES = {
   "auf deutsch": "de",
   german: "de",
   \u043D\u0456\u043C\u0435\u0446\u044C\u043A\u0430: "de",
+  "\u043D\u0456\u043C\u0435\u0446\u044C\u043A\u0430 \u043C\u043E\u0432\u0430": "de",
+  "\u043F\u043E-\u043D\u0456\u043C\u0435\u0446\u044C\u043A\u0438": "de",
   // French
   fr: "fr",
   fra: "fr",
@@ -70,6 +74,8 @@ var ALIASES = {
   "en fran\xE7ais": "fr",
   french: "fr",
   \u0444\u0440\u0430\u043D\u0446\u0443\u0437\u044C\u043A\u0430: "fr",
+  "\u0444\u0440\u0430\u043D\u0446\u0443\u0437\u044C\u043A\u0430 \u043C\u043E\u0432\u0430": "fr",
+  "\u043F\u043E-\u0444\u0440\u0430\u043D\u0446\u0443\u0437\u044C\u043A\u0438": "fr",
   // Spanish
   es: "es",
   spa: "es",
@@ -78,13 +84,17 @@ var ALIASES = {
   "en espa\xF1ol": "es",
   spanish: "es",
   \u0456\u0441\u043F\u0430\u043D\u0441\u044C\u043A\u0430: "es",
+  "\u0456\u0441\u043F\u0430\u043D\u0441\u044C\u043A\u0430 \u043C\u043E\u0432\u0430": "es",
+  "\u043F\u043E-\u0456\u0441\u043F\u0430\u043D\u0441\u044C\u043A\u0438": "es",
   // Italian
   it: "it",
   ita: "it",
   italiano: "it",
   "in italiano": "it",
   italian: "it",
-  \u0456\u0442\u0430\u043B\u0456\u0439\u0441\u044C\u043A\u0430: "it"
+  \u0456\u0442\u0430\u043B\u0456\u0439\u0441\u044C\u043A\u0430: "it",
+  "\u0456\u0442\u0430\u043B\u0456\u0439\u0441\u044C\u043A\u0430 \u043C\u043E\u0432\u0430": "it",
+  "\u043F\u043E-\u0456\u0442\u0430\u043B\u0456\u0439\u0441\u044C\u043A\u0438": "it"
 };
 function normalizeLanguageCode(input) {
   if (input === void 0 || input === null) return null;
@@ -92,7 +102,7 @@ function normalizeLanguageCode(input) {
   if (cleaned.length === 0) return null;
   return ALIASES[cleaned] ?? null;
 }
-function normalizeBCP47(input) {
+function normalizeBCP47(input, options) {
   if (input === void 0 || input === null) return null;
   const cleaned = input.trim().toLowerCase().replace(/_/g, "-");
   if (cleaned.length === 0) return null;
@@ -100,7 +110,9 @@ function normalizeBCP47(input) {
   if (direct !== void 0) return direct;
   const head = cleaned.split("-")[0];
   if (head === void 0 || head.length === 0) return null;
-  return ALIASES[head] ?? head;
+  const aliased = ALIASES[head];
+  if (aliased !== void 0) return aliased;
+  return options?.unknownHead === "null" ? null : head;
 }
 function primarySubtag(value) {
   if (value === void 0 || value === null) return null;
@@ -111,5 +123,5 @@ function primarySubtag(value) {
 }
 
 export { normalizeBCP47, normalizeLanguageCode, primarySubtag };
-//# sourceMappingURL=chunk-OVSPOZ5J.js.map
-//# sourceMappingURL=chunk-OVSPOZ5J.js.map
+//# sourceMappingURL=chunk-YCUSX3GG.js.map
+//# sourceMappingURL=chunk-YCUSX3GG.js.map

package/dist/chunk-YCUSX3GG.js.map

@@ -0,0 +1 @@
+{"version":3,"sources":["../src/internal/bcp47.ts"],"names":[],"mappings":";AAuBA,IAAM,OAAA,GAAkC;AAAA;AAAA,EAEtC,EAAA,EAAI,IAAA;AAAA,EACJ,EAAA,EAAI,IAAA;AAAA,EACJ,kBAAA,EAAK,IAAA;AAAA,EACL,4DAAA,EAAY,IAAA;AAAA,EACZ,kEAAA,EAAa,IAAA;AAAA,EACb,uFAAA,EAAmB,IAAA;AAAA,EACnB,iFAAA,EAAkB,IAAA;AAAA,EAClB,mGAAA,EAAqB,IAAA;AAAA,EACrB,SAAA,EAAW,IAAA;AAAA,EACX,cAAA,EAAgB,IAAA;AAAA;AAAA,EAGhB,EAAA,EAAI,IAAA;AAAA,EACJ,GAAA,EAAK,IAAA;AAAA,EACL,kBAAA,EAAK,IAAA;AAAA,EACL,0CAAA,EAAS,IAAA;AAAA,EACT,mDAAA,EAAa,IAAA;AAAA,EACb,mDAAA,EAAa,IAAA;AAAA,EACb,qEAAA,EAAgB,IAAA;AAAA,EAChB,yDAAA,EAAc,IAAA;AAAA,EACd,OAAA,EAAS,IAAA;AAAA,EACT,YAAA,EAAc,IAAA;AAAA,EACd,sDAAA,EAAW,IAAA;AAAA,EACX,iFAAA,EAAkB,IAAA;AAAA,EAClB,qEAAA,EAAgB,IAAA;AAAA,EAChB,qEAAA,EAAgB,IAAA;AAAA;AAAA,EAGhB,EAAA,EAAI,IAAA;AAAA,EACJ,GAAA,EAAK,IAAA;AAAA,EACL,4DAAA,EAAY,IAAA;AAAA,EACZ,uFAAA,EAAmB,IAAA;AAAA,EACnB,UAAA,EAAY,IAAA;AAAA,EACZ,eAAA,EAAiB,IAAA;AAAA;AAAA,EAGjB,EAAA,EAAI,IAAA;AAAA,EACJ,GAAA,EAAK,IAAA;AAAA,EACL,sDAAA,EAAW,IAAA;AAAA,EACX,iFAAA,EAAkB,IAAA;AAAA,EAClB,SAAA,EAAW,IAAA;AAAA,EACX,cAAA,EAAgB,IAAA;AAAA;AAAA,EAGhB,EAAA,EAAI,IAAA;AAAA,EACJ,GAAA,EAAK,IAAA;AAAA,EACL,OAAA,EAAS,IAAA;AAAA,EACT,YAAA,EAAc,IAAA;AAAA,EACd,4DAAA,EAAY,IAAA;AAAA,EACZ,4DAAA,EAAY,IAAA;AAAA;AAAA,EAGZ,EAAA,EAAI,IAAA;AAAA,EACJ,GAAA,EAAK,IAAA;AAAA,EACL,MAAA,EAAQ,IAAA;AAAA,EACR,WAAA,EAAa,IAAA;AAAA,EACb,MAAA,EAAQ,IAAA;AAAA,EACR,gDAAA,EAAU,IAAA;AAAA,EACV,2EAAA,EAAiB,IAAA;AAAA,EACjB,+DAAA,EAAe,IAAA;AAAA;AAAA,EAGf,EAAA,EAAI,IAAA;AAAA,EACJ,GAAA,EAAK,IAAA;AAAA,EACL,GAAA,EAAK,IAAA;AAAA,EACL,OAAA,EAAS,IAAA;AAAA,EACT,aAAA,EAAe,IAAA;AAAA,EACf,MAAA,EAAQ,IAAA;AAAA,EACR,gDAAA,EAAU,IAAA;AAAA,EACV,2EAAA,EAAiB,IAAA;AAAA,EACjB,+DAAA,EAAe,IAAA;AAAA;AAAA,EAGf,EAAA,EAAI,IAAA;AAAA,EACJ,GAAA,EAAK,IAAA;AAAA,EACL,aAAA,EAAU,IAAA;AAAA,EACV,QAAA,EAAU,IAAA;AAAA,EACV,gBAAA,EAAe,IAAA;AAAA,EACf,MAAA,EAAQ,IAAA;AAAA,EACR,4DAAA,EAAY,IAAA;AAAA,EACZ,uFAAA,EAAmB,IAAA;AAAA,EACnB,2EAAA,EAAiB,IAAA;AAAA;AAAA,EAGjB,EAAA,EAAI,IAAA;AAAA,EACJ,GAAA,EAAK,IAAA;AAAA,EACL,YAAA,EAAS,IAAA;AAAA,EACT,OAAA,EAAS,IAAA;AAAA,EACT,eAAA,EAAc,IAAA;AAAA,EACd,OAAA,EAAS,IAAA;AAAA,EACT,sDAAA,EAAW,IAAA;AAAA,EACX,iFAAA,EAAkB,IAAA;AAAA,EAClB,qEAAA,EAAgB,IAAA;AAAA;AAAA,EAGhB,EAAA,EAAI,IAAA;AAAA,EACJ,GAAA,EAAK,IAAA;AAAA,EACL,QAAA,EAAU,IAAA;AAAA,EACV,aAAA,EAAe,IAAA;AAAA,EACf,OAAA,EAAS,IAAA;AAAA,EACT,4DAAA,EAAY,IAAA;AAAA,EACZ,uFAAA,EAAmB,IAAA;AAAA,EACnB,2EAAA,EAAiB;AACnB,CAAA;AASO,SAAS,sBAAsB,KAAA,EAAiD;AACrF,EAAA,IAAI,KAAA,KAAU,MAAA,IAAa,KAAA,KAAU,IAAA,EAAM,OAAO,IAAA;AAClD,EAAA,MAAM,OAAA,GAAU,KAAA,CAAM,IAAA,EAAK,CAAE,WAAA,EAAY;AACzC,EAAA,IAAI,OAAA,CAAQ,MAAA,KAAW,CAAA,EAAG,OAAO,IAAA;AACjC,EAAA,OAAO,OAAA,CAAQ,OAAO,CAAA,IAAK,IAAA;AAC7B;AA8BO,SAAS,cAAA,CACd,OACA,OAAA,EACe;AACf,EAAA,IAAI,KAAA,KAAU,MAAA,IAAa,KAAA,KAAU,IAAA,EAAM,OAAO,IAAA;AAClD,EAAA,MAAM,OAAA,GAAU,MAAM,IAAA,EAAK,CAAE,aAAY,CAAE,OAAA,CAAQ,MAAM,GAAG,CAAA;AAC5D,EAAA,IAAI,OAAA,CAAQ,MAAA,KAAW,CAAA,EAAG,OAAO,IAAA;AACjC,EAAA,MAAM,MAAA,GAAS,QAAQ,OAAO,CAAA;AAC9B,EAAA,IAAI,MAAA,KAAW,QAAW,OAAO,MAAA;AACjC,EAAA,MAAM,IAAA,GAAO,OAAA,CAAQ,KAAA,CAAM,GAAG,EAAE,CAAC,CAAA;AACjC,EAAA,IAAI,IAAA,KAAS,MAAA,IAAa,IAAA,CAAK,MAAA,KAAW,GAAG,OAAO,IAAA;AACpD,EAAA,MAAM,OAAA,GAAU,QAAQ,IAAI,CAAA;AAC5B,EAAA,IAAI,OAAA,KAAY,QAAW,OAAO,OAAA;AAClC,EAAA,OAAO,OAAA,EAAS,WAAA,KAAgB,MAAA,GAAS,IAAA,GAAO,IAAA;AAClD;AAWO,SAAS,cAAc,KAAA,EAAiD;AAC7E,EAAA,IAAI,KAAA,KAAU,MAAA,IAAa,KAAA,KAAU,IAAA,EAAM,OAAO,IAAA;AAClD,EAAA,MAAM,QAAQ,KAAA,CAAM,KAAA,CAAM,GAAG,CAAA,CAAE,CAAC,GAAG,IAAA,EAAK;AACxC,EAAA,IAAI,KAAA,KAAU,MAAA,IAAa,KAAA,CAAM,MAAA,KAAW,GAAG,OAAO,IAAA;AAEtD,EAAA,MAAM,MAAM,KAAA,CAAM,KAAA,CAAM,GAAG,CAAA,CAAE,CAAC,GAAG,IAAA,EAAK;AACtC,EAAA,OAAO,eAAe,GAAG,CAAA;AAC3B","file":"chunk-YCUSX3GG.js","sourcesContent":["/**\n * BCP-47 / language-code normalization.\n *\n * Two entry points with deliberately different strictness:\n *  - {@link normalizeBCP47} — for inputs documented to be BCP-47 (`<html lang>`,\n *    hreflang, `Content-Language`): try the full string, then strip a\n *    region/script suffix (`en-US` → `en`, `zh_CN` → `zh`).\n *  - {@link normalizeLanguageCode} — strict exact-match only, for free-text\n *    contexts (URL slugs, link text) where a hyphen split could be a coincidence.\n *\n * Both resolve aliases that appear in the wild (`ua` → `uk`, `rus` → `ru`,\n * localized picker phrases) to a canonical ISO 639-1 code.\n */\n\n/**\n * Aliases mapped to canonical ISO 639-1 codes. Keys are lowercased.\n *\n * Ukrainian is the load-bearing case: most sites use `ua` in URLs even though\n * the ISO code is `uk`. Both are accepted on input; `uk` is always output.\n *\n * Includes localized phrases users see in language pickers (`українською`,\n * `по-русски`, `in english`, …).\n */\nconst ALIASES: Record<string, string> = {\n  // Ukrainian\n  ua: \"uk\",\n  uk: \"uk\",\n  укр: \"uk\",\n  українська: \"uk\",\n  українською: \"uk\",\n  \"українська мова\": \"uk\",\n  \"на українській\": \"uk\",\n  \"українською мовою\": \"uk\",\n  ukrainian: \"uk\",\n  \"in ukrainian\": \"uk\",\n\n  // Russian\n  ru: \"ru\",\n  rus: \"ru\",\n  рус: \"ru\",\n  русский: \"ru\",\n  \"по-русски\": \"ru\",\n  \"по русски\": \"ru\",\n  \"русский язык\": \"ru\",\n  \"на русском\": \"ru\",\n  russian: \"ru\",\n  \"in russian\": \"ru\",\n  російська: \"ru\",\n  \"російська мова\": \"ru\",\n  \"по-російськи\": \"ru\",\n  \"по російськи\": \"ru\",\n\n  // Belarusian\n  be: \"be\",\n  bel: \"be\",\n  беларуская: \"be\",\n  \"беларуская мова\": \"be\",\n  belarusian: \"be\",\n  \"in belarusian\": \"be\",\n\n  // Bulgarian\n  bg: \"bg\",\n  bul: \"bg\",\n  български: \"bg\",\n  \"български език\": \"bg\",\n  bulgarian: \"bg\",\n  \"in bulgarian\": \"bg\",\n\n  // English\n  en: \"en\",\n  eng: \"en\",\n  english: \"en\",\n  \"in english\": \"en\",\n  англійська: \"en\",\n  английский: \"en\",\n\n  // Polish\n  pl: \"pl\",\n  pol: \"pl\",\n  polski: \"pl\",\n  \"po polsku\": \"pl\",\n  polish: \"pl\",\n  польська: \"pl\",\n  \"польська мова\": \"pl\",\n  \"по-польськи\": \"pl\",\n\n  // German\n  de: \"de\",\n  deu: \"de\",\n  ger: \"de\",\n  deutsch: \"de\",\n  \"auf deutsch\": \"de\",\n  german: \"de\",\n  німецька: \"de\",\n  \"німецька мова\": \"de\",\n  \"по-німецьки\": \"de\",\n\n  // French\n  fr: \"fr\",\n  fra: \"fr\",\n  français: \"fr\",\n  francais: \"fr\",\n  \"en français\": \"fr\",\n  french: \"fr\",\n  французька: \"fr\",\n  \"французька мова\": \"fr\",\n  \"по-французьки\": \"fr\",\n\n  // Spanish\n  es: \"es\",\n  spa: \"es\",\n  español: \"es\",\n  espanol: \"es\",\n  \"en español\": \"es\",\n  spanish: \"es\",\n  іспанська: \"es\",\n  \"іспанська мова\": \"es\",\n  \"по-іспанськи\": \"es\",\n\n  // Italian\n  it: \"it\",\n  ita: \"it\",\n  italiano: \"it\",\n  \"in italiano\": \"it\",\n  italian: \"it\",\n  італійська: \"it\",\n  \"італійська мова\": \"it\",\n  \"по-італійськи\": \"it\",\n};\n\n/**\n * Strict, exact-match lookup. Returns `null` for unknown inputs and does NOT\n * fall back to a hyphen prefix. Use anywhere a hyphen split could be a\n * coincidence — URL path segments (`/ru-return-warranty`), title attrs, link\n * text. The phrase aliases (`по-русски`, `in english`) are in the table\n * directly, so exact lookup still finds them.\n */\nexport function normalizeLanguageCode(input: string | undefined | null): string | null {\n  if (input === undefined || input === null) return null;\n  const cleaned = input.trim().toLowerCase();\n  if (cleaned.length === 0) return null;\n  return ALIASES[cleaned] ?? null;\n}\n\n/** Options for {@link normalizeBCP47}. */\nexport interface NormalizeBCP47Options {\n  /**\n   * What to return when the input's primary subtag is not in the alias table.\n   *  - `\"subtag\"` (default) — pass the raw primary subtag through, so a code\n   *    outside the table still resolves to its language (`pt-BR` → `pt`,\n   *    `sv` → `sv`). Best for a permissive normalizer whose roster decides\n   *    relevance downstream.\n   *  - `\"null\"` — treat an unknown head as unsupported and return `null`. Best\n   *    for callers that gate on a fixed alias set and read `null` as \"not a\n   *    language I handle\".\n   */\n  unknownHead?: \"subtag\" | \"null\";\n}\n\n/**\n * BCP-47-aware normalization: try the full string first, then strip a\n * region/script suffix (`en-US` → `en`, `zh_CN` → `zh`). Use ONLY for inputs\n * documented to be BCP-47 — `hreflang`, `<html lang>`, `Content-Language`,\n * `data-lang`/`data-locale` — never for free-text URL slugs.\n *\n * By default, falls back to the raw primary subtag when no alias matches, so a\n * code outside the alias table (e.g. `pt-BR` → `pt`) still resolves to its\n * language; the roster decides relevance downstream. Pass\n * `{ unknownHead: \"null\" }` to instead return `null` for any tag whose head\n * isn't in the table — for callers that treat \"not in my alias set\" as\n * unsupported. The default (`\"subtag\"`) is unchanged.\n */\nexport function normalizeBCP47(\n  input: string | undefined | null,\n  options?: NormalizeBCP47Options,\n): string | null {\n  if (input === undefined || input === null) return null;\n  const cleaned = input.trim().toLowerCase().replace(/_/g, \"-\");\n  if (cleaned.length === 0) return null;\n  const direct = ALIASES[cleaned];\n  if (direct !== undefined) return direct;\n  const head = cleaned.split(\"-\")[0];\n  if (head === undefined || head.length === 0) return null;\n  const aliased = ALIASES[head];\n  if (aliased !== undefined) return aliased;\n  return options?.unknownHead === \"null\" ? null : head;\n}\n\n/**\n * Extract the primary subtag from a BCP-47-ish value, lowercased, then resolve\n * it through the alias table (`ua` → `uk`). Handles `Accept-Language`-style\n * comma lists (`en-US,en;q=0.9` → `en`). Returns `null` for empty/nullish.\n *\n * This is the header/HTML extraction helper: it tolerates the messy shapes those\n * sources carry (comma lists, `q` weights) where {@link normalizeBCP47} expects\n * a single tag.\n */\nexport function primarySubtag(value: string | undefined | null): string | null {\n  if (value === undefined || value === null) return null;\n  const first = value.split(\",\")[0]?.trim();\n  if (first === undefined || first.length === 0) return null;\n  // Drop a `;q=…` weight if present.\n  const tag = first.split(\";\")[0]?.trim();\n  return normalizeBCP47(tag);\n}\n"]}

package/dist/classify.d.ts

@@ -60,6 +60,13 @@ type RungVerdict = Pick<SnippetVerdict, "language" | "margin" | "rung">;
  *  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;
+/** Below this length, trigrams are too noisy to justify a rung-3 verdict. */
+declare const RUNG3_MIN_LENGTH = 24;
+/** 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
+ *  keeps `P` — a stricter caller's profiles stay strictly typed downstream. */
+declare function scopeCandidates<P extends LanguageProfile>(text: string, candidates: readonly P[]): P[];
 /**
  * Classify `text` among `candidates`. Synchronous and allocation-light. Returns
  * `"unknown"` on empty evidence, on a tie inside the candidate set, or when
@@ -74,4 +81,4 @@ type Rung3Resolver<P extends LanguageProfile = LanguageProfile> = (text: string,
  */
 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 };
+export { FRANC_RUNG, RUNG3_MIN_LENGTH, type Rung, type Rung3Resolver, type RungVerdict, type SnippetVerdict, classifyBySnippet, scopeCandidates };

package/dist/classify.js

@@ -1,3 +1,3 @@
-export { FRANC_RUNG, classifyBySnippet } from './chunk-U34Z3ZSV.js';
+export { FRANC_RUNG, RUNG3_MIN_LENGTH, classifyBySnippet, scopeCandidates } from './chunk-BL627TWI.js';
 //# sourceMappingURL=classify.js.map
 //# sourceMappingURL=classify.js.map

package/dist/cyrillic.d.ts

@@ -0,0 +1,53 @@
+/**
+ * `langtell/cyrillic` — a cheap, roster-free Cyrillic language fast-path.
+ *
+ * Where {@link classifyBySnippet} (`langtell/classify`) scores a snippet
+ * *relative to a candidate roster you pass in*, this is the opposite trade: a
+ * fixed, zero-config discriminator for the four Cyrillic languages langtell
+ * profiles — Ukrainian, Russian, Belarusian, Bulgarian — decided purely by
+ * letters distinctive to each, with no profiles, no tokenization, and no franc.
+ * Reach for it when you just need "is this Russian / is this Ukrainian?" on a
+ * hot path and don't want to assemble a candidate set.
+ *
+ * Each language carries letters the others (mostly) don't:
+ *   Ukrainian   — і ї є ґ
+ *   Russian     — ы ё   (ъ э are shared with bg/be and handled separately)
+ *   Belarusian  — ў     (uniquely Belarusian)
+ *   Bulgarian   — ъ used as a vowel in nearly every word
+ *
+ * The shared letters `ъ` and `э` need care: `подъезд` is Russian, `съм
+ * българин` is Bulgarian — both contain `ъ`. We disambiguate by density and
+ * length: a single `ъ` in a short snippet leans RU; multiple `ъ` in longer text
+ * leans BG. A lone `э` with no other distinctives stays `"unknown"` rather than
+ * silently guessing (Russian uses it in loanwords/`Это`, Belarusian in
+ * `гэта`/`сэрца`).
+ *
+ * Zero-dependency and side-effect-free. The cheap heuristic stays cheap; if a
+ * use case needs more than letter signals can give, escalate to
+ * {@link classifyBySnippet} or a franc-backed source.
+ */
+/** The four Cyrillic languages this fast-path tells apart, plus the `"unknown"`
+ *  sentinel when letter signals are insufficient. */
+type CyrillicLanguage = "uk" | "ru" | "be" | "bg" | "unknown";
+/** The verdict from {@link detectCyrillicLanguage}: the chosen language plus the
+ *  raw distinctive-letter tallies that drove a uk-vs-ru decision (informational;
+ *  `ruScore` carries the deciding count for the ru/bg fallbacks too). */
+interface CyrillicVerdict {
+    language: CyrillicLanguage;
+    ukScore: number;
+    ruScore: number;
+}
+/**
+ * Identify the Cyrillic language of `text` by distinctive letters, returning the
+ * chosen language and the uk/ru tallies behind it. `"unknown"` when there is no
+ * Cyrillic evidence, on a uk/ru tie, or when only an ambiguous `э` is present.
+ */
+declare function detectCyrillicLanguage(text: string): CyrillicVerdict;
+/** Convenience predicate: `true` iff {@link detectCyrillicLanguage} calls `text`
+ *  Russian. */
+declare function isRussian(text: string): boolean;
+/** Convenience predicate: `true` iff {@link detectCyrillicLanguage} calls `text`
+ *  Ukrainian. */
+declare function isUkrainian(text: string): boolean;
+
+export { type CyrillicLanguage, type CyrillicVerdict, detectCyrillicLanguage, isRussian, isUkrainian };

package/dist/cyrillic.js

@@ -0,0 +1,64 @@
+// src/cyrillic.ts
+var UK_DISTINCTIVE = /[іїєґ]/gi;
+var RU_DISTINCTIVE = /[ыё]/gi;
+var BE_DISTINCTIVE = /ў/gi;
+var HARD_SIGN = /ъ/gi;
+var E_OBOROT = /э/gi;
+var CYRILLIC = /[\u0400-\u04FF]/g;
+var MIN_CYRILLIC_FOR_FALLBACK = 10;
+var MIN_LEN_FOR_BG = 10;
+function count(text, re) {
+  return (text.match(re) ?? []).length;
+}
+function countSignals(text) {
+  return {
+    ukScore: count(text, UK_DISTINCTIVE),
+    ruDistinctive: count(text, RU_DISTINCTIVE),
+    beScore: count(text, BE_DISTINCTIVE),
+    hardSigns: count(text, HARD_SIGN),
+    eOborot: count(text, E_OBOROT),
+    cyrillicCount: count(text, CYRILLIC)
+  };
+}
+function detectCyrillicLanguage(text) {
+  const { ukScore, ruDistinctive, beScore, hardSigns, eOborot, cyrillicCount } = countSignals(text);
+  if (beScore > 0) {
+    return { language: "be", ukScore, ruScore: ruDistinctive };
+  }
+  if (ukScore > 0 && ruDistinctive > 0) {
+    if (ukScore === ruDistinctive) {
+      return { language: "unknown", ukScore, ruScore: ruDistinctive };
+    }
+    return {
+      language: ukScore > ruDistinctive ? "uk" : "ru",
+      ukScore,
+      ruScore: ruDistinctive
+    };
+  }
+  if (ruDistinctive > 0) {
+    return { language: "ru", ukScore, ruScore: ruDistinctive };
+  }
+  if (ukScore > 0) {
+    return { language: "uk", ukScore, ruScore: 0 };
+  }
+  if (hardSigns >= 2 && text.length >= MIN_LEN_FOR_BG) {
+    return { language: "bg", ukScore: 0, ruScore: hardSigns };
+  }
+  if (cyrillicCount >= MIN_CYRILLIC_FOR_FALLBACK && eOborot === 0) {
+    return { language: "ru", ukScore: 0, ruScore: 0 };
+  }
+  if (hardSigns > 0 && eOborot === 0) {
+    return { language: "ru", ukScore: 0, ruScore: hardSigns };
+  }
+  return { language: "unknown", ukScore: 0, ruScore: 0 };
+}
+function isRussian(text) {
+  return detectCyrillicLanguage(text).language === "ru";
+}
+function isUkrainian(text) {
+  return detectCyrillicLanguage(text).language === "uk";
+}
+
+export { detectCyrillicLanguage, isRussian, isUkrainian };
+//# sourceMappingURL=cyrillic.js.map
+//# sourceMappingURL=cyrillic.js.map

package/dist/cyrillic.js.map

@@ -0,0 +1 @@
+{"version":3,"sources":["../src/cyrillic.ts"],"names":[],"mappings":";AAiCA,IAAM,cAAA,GAAiB,UAAA;AACvB,IAAM,cAAA,GAAiB,QAAA;AACvB,IAAM,cAAA,GAAiB,KAAA;AACvB,IAAM,SAAA,GAAY,KAAA;AAClB,IAAM,QAAA,GAAW,KAAA;AAGjB,IAAM,QAAA,GAAW,kBAAA;AAIjB,IAAM,yBAAA,GAA4B,EAAA;AAGlC,IAAM,cAAA,GAAiB,EAAA;AAWvB,SAAS,KAAA,CAAM,MAAc,EAAA,EAAoB;AAC/C,EAAA,OAAA,CAAQ,IAAA,CAAK,KAAA,CAAM,EAAE,CAAA,IAAK,EAAC,EAAG,MAAA;AAChC;AAcA,SAAS,aAAa,IAAA,EAAuB;AAC3C,EAAA,OAAO;AAAA,IACL,OAAA,EAAS,KAAA,CAAM,IAAA,EAAM,cAAc,CAAA;AAAA,IACnC,aAAA,EAAe,KAAA,CAAM,IAAA,EAAM,cAAc,CAAA;AAAA,IACzC,OAAA,EAAS,KAAA,CAAM,IAAA,EAAM,cAAc,CAAA;AAAA,IACnC,SAAA,EAAW,KAAA,CAAM,IAAA,EAAM,SAAS,CAAA;AAAA,IAChC,OAAA,EAAS,KAAA,CAAM,IAAA,EAAM,QAAQ,CAAA;AAAA,IAC7B,aAAA,EAAe,KAAA,CAAM,IAAA,EAAM,QAAQ;AAAA,GACrC;AACF;AAOO,SAAS,uBAAuB,IAAA,EAA+B;AACpE,EAAA,MAAM,EAAE,SAAS,aAAA,EAAe,OAAA,EAAS,WAAW,OAAA,EAAS,aAAA,EAAc,GAAI,YAAA,CAAa,IAAI,CAAA;AAGhG,EAAA,IAAI,UAAU,CAAA,EAAG;AACf,IAAA,OAAO,EAAE,QAAA,EAAU,IAAA,EAAM,OAAA,EAAS,SAAS,aAAA,EAAc;AAAA,EAC3D;AAIA,EAAA,IAAI,OAAA,GAAU,CAAA,IAAK,aAAA,GAAgB,CAAA,EAAG;AACpC,IAAA,IAAI,YAAY,aAAA,EAAe;AAC7B,MAAA,OAAO,EAAE,QAAA,EAAU,SAAA,EAAW,OAAA,EAAS,SAAS,aAAA,EAAc;AAAA,IAChE;AACA,IAAA,OAAO;AAAA,MACL,QAAA,EAAU,OAAA,GAAU,aAAA,GAAgB,IAAA,GAAO,IAAA;AAAA,MAC3C,OAAA;AAAA,MACA,OAAA,EAAS;AAAA,KACX;AAAA,EACF;AAGA,EAAA,IAAI,gBAAgB,CAAA,EAAG;AACrB,IAAA,OAAO,EAAE,QAAA,EAAU,IAAA,EAAM,OAAA,EAAS,SAAS,aAAA,EAAc;AAAA,EAC3D;AAGA,EAAA,IAAI,UAAU,CAAA,EAAG;AACf,IAAA,OAAO,EAAE,QAAA,EAAU,IAAA,EAAM,OAAA,EAAS,SAAS,CAAA,EAAE;AAAA,EAC/C;AAKA,EAAA,IAAI,SAAA,IAAa,CAAA,IAAK,IAAA,CAAK,MAAA,IAAU,cAAA,EAAgB;AACnD,IAAA,OAAO,EAAE,QAAA,EAAU,IAAA,EAAM,OAAA,EAAS,CAAA,EAAG,SAAS,SAAA,EAAU;AAAA,EAC1D;AAKA,EAAA,IAAI,aAAA,IAAiB,yBAAA,IAA6B,OAAA,KAAY,CAAA,EAAG;AAC/D,IAAA,OAAO,EAAE,QAAA,EAAU,IAAA,EAAM,OAAA,EAAS,CAAA,EAAG,SAAS,CAAA,EAAE;AAAA,EAClD;AAIA,EAAA,IAAI,SAAA,GAAY,CAAA,IAAK,OAAA,KAAY,CAAA,EAAG;AAClC,IAAA,OAAO,EAAE,QAAA,EAAU,IAAA,EAAM,OAAA,EAAS,CAAA,EAAG,SAAS,SAAA,EAAU;AAAA,EAC1D;AAEA,EAAA,OAAO,EAAE,QAAA,EAAU,SAAA,EAAW,OAAA,EAAS,CAAA,EAAG,SAAS,CAAA,EAAE;AACvD;AAIO,SAAS,UAAU,IAAA,EAAuB;AAC/C,EAAA,OAAO,sBAAA,CAAuB,IAAI,CAAA,CAAE,QAAA,KAAa,IAAA;AACnD;AAIO,SAAS,YAAY,IAAA,EAAuB;AACjD,EAAA,OAAO,sBAAA,CAAuB,IAAI,CAAA,CAAE,QAAA,KAAa,IAAA;AACnD","file":"cyrillic.js","sourcesContent":["/**\n * `langtell/cyrillic` — a cheap, roster-free Cyrillic language fast-path.\n *\n * Where {@link classifyBySnippet} (`langtell/classify`) scores a snippet\n * *relative to a candidate roster you pass in*, this is the opposite trade: a\n * fixed, zero-config discriminator for the four Cyrillic languages langtell\n * profiles — Ukrainian, Russian, Belarusian, Bulgarian — decided purely by\n * letters distinctive to each, with no profiles, no tokenization, and no franc.\n * Reach for it when you just need \"is this Russian / is this Ukrainian?\" on a\n * hot path and don't want to assemble a candidate set.\n *\n * Each language carries letters the others (mostly) don't:\n *   Ukrainian   — і ї є ґ\n *   Russian     — ы ё   (ъ э are shared with bg/be and handled separately)\n *   Belarusian  — ў     (uniquely Belarusian)\n *   Bulgarian   — ъ used as a vowel in nearly every word\n *\n * The shared letters `ъ` and `э` need care: `подъезд` is Russian, `съм\n * българин` is Bulgarian — both contain `ъ`. We disambiguate by density and\n * length: a single `ъ` in a short snippet leans RU; multiple `ъ` in longer text\n * leans BG. A lone `э` with no other distinctives stays `\"unknown\"` rather than\n * silently guessing (Russian uses it in loanwords/`Это`, Belarusian in\n * `гэта`/`сэрца`).\n *\n * Zero-dependency and side-effect-free. The cheap heuristic stays cheap; if a\n * use case needs more than letter signals can give, escalate to\n * {@link classifyBySnippet} or a franc-backed source.\n */\n\n/** The four Cyrillic languages this fast-path tells apart, plus the `\"unknown\"`\n *  sentinel when letter signals are insufficient. */\nexport type CyrillicLanguage = \"uk\" | \"ru\" | \"be\" | \"bg\" | \"unknown\";\n\nconst UK_DISTINCTIVE = /[іїєґ]/gi;\nconst RU_DISTINCTIVE = /[ыё]/gi;\nconst BE_DISTINCTIVE = /ў/gi;\nconst HARD_SIGN = /ъ/gi;\nconst E_OBOROT = /э/gi;\n// U+0400–U+04FF is the Cyrillic Unicode block; written as explicit \\u escapes\n// so the range bounds are unambiguous (regexp/no-obscure-range).\nconst CYRILLIC = /[\\u0400-\\u04FF]/g;\n\n/** Minimum Cyrillic-letter count before the fallback guesses a language. Below\n *  this, a short snippet (`Привет`, `Хочу`) is too ambiguous to act on. */\nconst MIN_CYRILLIC_FOR_FALLBACK = 10;\n/** Minimum text length before `ъ`-density is read as Bulgarian. Single-word\n *  Russian samples like `подъезд` (7 chars) would otherwise misclassify. */\nconst MIN_LEN_FOR_BG = 10;\n\n/** The verdict from {@link detectCyrillicLanguage}: the chosen language plus the\n *  raw distinctive-letter tallies that drove a uk-vs-ru decision (informational;\n *  `ruScore` carries the deciding count for the ru/bg fallbacks too). */\nexport interface CyrillicVerdict {\n  language: CyrillicLanguage;\n  ukScore: number;\n  ruScore: number;\n}\n\nfunction count(text: string, re: RegExp): number {\n  return (text.match(re) ?? []).length;\n}\n\n/** Raw letter-signal tallies over `text`, one pass per distinctive class.\n *  Gathered up front so {@link detectCyrillicLanguage} reads as a pure decision\n *  cascade over these counts rather than interleaving counting and branching. */\ninterface Signals {\n  ukScore: number;\n  ruDistinctive: number;\n  beScore: number;\n  hardSigns: number;\n  eOborot: number;\n  cyrillicCount: number;\n}\n\nfunction countSignals(text: string): Signals {\n  return {\n    ukScore: count(text, UK_DISTINCTIVE),\n    ruDistinctive: count(text, RU_DISTINCTIVE),\n    beScore: count(text, BE_DISTINCTIVE),\n    hardSigns: count(text, HARD_SIGN),\n    eOborot: count(text, E_OBOROT),\n    cyrillicCount: count(text, CYRILLIC),\n  };\n}\n\n/**\n * Identify the Cyrillic language of `text` by distinctive letters, returning the\n * chosen language and the uk/ru tallies behind it. `\"unknown\"` when there is no\n * Cyrillic evidence, on a uk/ru tie, or when only an ambiguous `э` is present.\n */\nexport function detectCyrillicLanguage(text: string): CyrillicVerdict {\n  const { ukScore, ruDistinctive, beScore, hardSigns, eOborot, cyrillicCount } = countSignals(text);\n\n  // ў is uniquely Belarusian — strongest single signal.\n  if (beScore > 0) {\n    return { language: \"be\", ukScore, ruScore: ruDistinctive };\n  }\n\n  // Both UA and RU evidence present — a tie is \"unknown\", not a silent UA call\n  // (which would misclassify Belarusian/Bulgarian whenever і or ё balances out).\n  if (ukScore > 0 && ruDistinctive > 0) {\n    if (ukScore === ruDistinctive) {\n      return { language: \"unknown\", ukScore, ruScore: ruDistinctive };\n    }\n    return {\n      language: ukScore > ruDistinctive ? \"uk\" : \"ru\",\n      ukScore,\n      ruScore: ruDistinctive,\n    };\n  }\n\n  // Distinctive RU letters (ы, ё) with no UA evidence — unambiguously RU.\n  if (ruDistinctive > 0) {\n    return { language: \"ru\", ukScore, ruScore: ruDistinctive };\n  }\n\n  // Distinctive UA letters with no RU distinctives — UA.\n  if (ukScore > 0) {\n    return { language: \"uk\", ukScore, ruScore: 0 };\n  }\n\n  // Bulgarian: ъ as a vowel — multiple occurrences in non-trivial text, no UA /\n  // RU distinctives. Length guard keeps short Russian compounds like `подъезд`\n  // from sliding into BG.\n  if (hardSigns >= 2 && text.length >= MIN_LEN_FOR_BG) {\n    return { language: \"bg\", ukScore: 0, ruScore: hardSigns };\n  }\n\n  // Russian fallback: substantial Cyrillic with no UA, no BE distinctives, and\n  // no э (which signals possible Belarusian). Catches short-but-clear Russian\n  // text with none of ы/ё/ъ/э (`Привет, мир`, `Здравствуйте, меня зовут …`).\n  if (cyrillicCount >= MIN_CYRILLIC_FOR_FALLBACK && eOborot === 0) {\n    return { language: \"ru\", ukScore: 0, ruScore: 0 };\n  }\n\n  // Lone ъ (no э, no other distinctives) in shorter text — RU compound-word\n  // pattern (подъезд, объект, съезд).\n  if (hardSigns > 0 && eOborot === 0) {\n    return { language: \"ru\", ukScore: 0, ruScore: hardSigns };\n  }\n\n  return { language: \"unknown\", ukScore: 0, ruScore: 0 };\n}\n\n/** Convenience predicate: `true` iff {@link detectCyrillicLanguage} calls `text`\n *  Russian. */\nexport function isRussian(text: string): boolean {\n  return detectCyrillicLanguage(text).language === \"ru\";\n}\n\n/** Convenience predicate: `true` iff {@link detectCyrillicLanguage} calls `text`\n *  Ukrainian. */\nexport function isUkrainian(text: string): boolean {\n  return detectCyrillicLanguage(text).language === \"uk\";\n}\n"]}

package/dist/franc.js

@@ -1,4 +1,4 @@
-import { scopeCandidates } from './chunk-U34Z3ZSV.js';
+import { scopeCandidates } from './chunk-BL627TWI.js';
 import { francAll } from 'franc';
 
 var RUNG_MIN_LENGTH = 24;

package/dist/fuse.js

@@ -1,5 +1,5 @@
-export { fuse } from './chunk-G44HHVK5.js';
-import './chunk-OVSPOZ5J.js';
-import './chunk-U34Z3ZSV.js';
+export { fuse } from './chunk-6PWEE3SR.js';
+import './chunk-YCUSX3GG.js';
+import './chunk-BL627TWI.js';
 //# sourceMappingURL=fuse.js.map
 //# sourceMappingURL=fuse.js.map

package/dist/headers.js

@@ -1,4 +1,4 @@
-export { evidenceFromHeaders } from './chunk-3LDE35U2.js';
-import './chunk-OVSPOZ5J.js';
+export { evidenceFromHeaders } from './chunk-FEKBPTHK.js';
+import './chunk-YCUSX3GG.js';
 //# sourceMappingURL=headers.js.map
 //# sourceMappingURL=headers.js.map

package/dist/html.js

@@ -1,4 +1,4 @@
-export { evidenceFromHtml } from './chunk-KI4MAI3N.js';
-import './chunk-OVSPOZ5J.js';
+export { evidenceFromHtml } from './chunk-K4MXTIY7.js';
+import './chunk-YCUSX3GG.js';
 //# sourceMappingURL=html.js.map
 //# sourceMappingURL=html.js.map

package/dist/index.d.ts

@@ -35,17 +35,34 @@ declare function compile<const E extends readonly EvidenceSource[] = []>(config?
  * directly, so exact lookup still finds them.
  */
 declare function normalizeLanguageCode(input: string | undefined | null): string | null;
+/** Options for {@link normalizeBCP47}. */
+interface NormalizeBCP47Options {
+    /**
+     * What to return when the input's primary subtag is not in the alias table.
+     *  - `"subtag"` (default) — pass the raw primary subtag through, so a code
+     *    outside the table still resolves to its language (`pt-BR` → `pt`,
+     *    `sv` → `sv`). Best for a permissive normalizer whose roster decides
+     *    relevance downstream.
+     *  - `"null"` — treat an unknown head as unsupported and return `null`. Best
+     *    for callers that gate on a fixed alias set and read `null` as "not a
+     *    language I handle".
+     */
+    unknownHead?: "subtag" | "null";
+}
 /**
  * BCP-47-aware normalization: try the full string first, then strip a
  * region/script suffix (`en-US` → `en`, `zh_CN` → `zh`). Use ONLY for inputs
  * documented to be BCP-47 — `hreflang`, `<html lang>`, `Content-Language`,
  * `data-lang`/`data-locale` — never for free-text URL slugs.
  *
- * Falls back to the raw primary subtag when no alias matches, so a code outside
- * the alias table (e.g. `pt-BR` → `pt`) still resolves to its language. The
- * roster decides relevance downstream.
+ * By default, falls back to the raw primary subtag when no alias matches, so a
+ * code outside the alias table (e.g. `pt-BR` → `pt`) still resolves to its
+ * language; the roster decides relevance downstream. Pass
+ * `{ unknownHead: "null" }` to instead return `null` for any tag whose head
+ * isn't in the table — for callers that treat "not in my alias set" as
+ * unsupported. The default (`"subtag"`) is unchanged.
  */
-declare function normalizeBCP47(input: string | undefined | null): string | null;
+declare function normalizeBCP47(input: string | undefined | null, options?: NormalizeBCP47Options): string | null;
 /**
  * Extract the primary subtag from a BCP-47-ish value, lowercased, then resolve
  * it through the alias table (`ua` → `uk`). Handles `Accept-Language`-style
@@ -57,4 +74,4 @@ declare function normalizeBCP47(input: string | undefined | null): string | null
  */
 declare function primarySubtag(value: string | undefined | null): string | null;
 
-export { DetectFn, DetectorConfig, EvidenceSource, compile, normalizeBCP47, normalizeLanguageCode, primarySubtag };
+export { DetectFn, DetectorConfig, EvidenceSource, type NormalizeBCP47Options, compile, normalizeBCP47, normalizeLanguageCode, primarySubtag };

package/dist/index.js

@@ -1,13 +1,13 @@
-import { evidenceFromText } from './chunk-KCK3XWCJ.js';
-export { evidenceFromText } from './chunk-KCK3XWCJ.js';
-import { evidenceFromHtml } from './chunk-KI4MAI3N.js';
-export { evidenceFromHtml } from './chunk-KI4MAI3N.js';
-import { evidenceFromHeaders } from './chunk-3LDE35U2.js';
-export { evidenceFromHeaders } from './chunk-3LDE35U2.js';
-import { fuse } from './chunk-G44HHVK5.js';
-export { fuse } from './chunk-G44HHVK5.js';
-export { normalizeBCP47, normalizeLanguageCode, primarySubtag } from './chunk-OVSPOZ5J.js';
-import './chunk-U34Z3ZSV.js';
+import { evidenceFromText } from './chunk-7TDGJOIJ.js';
+export { evidenceFromText } from './chunk-7TDGJOIJ.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-6PWEE3SR.js';
+export { fuse } from './chunk-6PWEE3SR.js';
+export { normalizeBCP47, normalizeLanguageCode, primarySubtag } from './chunk-YCUSX3GG.js';
+import './chunk-BL627TWI.js';
 
 // src/compile.ts
 function builtIns(candidates) {

package/dist/text.js

@@ -1,4 +1,4 @@
-export { evidenceFromText } from './chunk-KCK3XWCJ.js';
-import './chunk-U34Z3ZSV.js';
+export { evidenceFromText } from './chunk-7TDGJOIJ.js';
+import './chunk-BL627TWI.js';
 //# sourceMappingURL=text.js.map
 //# sourceMappingURL=text.js.map

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "langtell",
-  "version": "0.4.0",
+  "version": "0.5.0",
   "description": "Tell me the language — evidence-fusion language detection for short strings, with an auditable confidence trail.",
   "type": "module",
   "license": "MIT",
@@ -65,6 +65,10 @@
       "types": "./dist/chrome-ai.d.ts",
       "import": "./dist/chrome-ai.js"
     },
+    "./cyrillic": {
+      "types": "./dist/cyrillic.d.ts",
+      "import": "./dist/cyrillic.js"
+    },
     "./package.json": "./package.json"
   },
   "files": [

package/dist/chunk-OVSPOZ5J.js.map

@@ -1 +0,0 @@
-{"version":3,"sources":["../src/internal/bcp47.ts"],"names":[],"mappings":";AAuBA,IAAM,OAAA,GAAkC;AAAA;AAAA,EAEtC,EAAA,EAAI,IAAA;AAAA,EACJ,EAAA,EAAI,IAAA;AAAA,EACJ,kBAAA,EAAK,IAAA;AAAA,EACL,4DAAA,EAAY,IAAA;AAAA,EACZ,kEAAA,EAAa,IAAA;AAAA,EACb,uFAAA,EAAmB,IAAA;AAAA,EACnB,iFAAA,EAAkB,IAAA;AAAA,EAClB,mGAAA,EAAqB,IAAA;AAAA,EACrB,SAAA,EAAW,IAAA;AAAA,EACX,cAAA,EAAgB,IAAA;AAAA;AAAA,EAGhB,EAAA,EAAI,IAAA;AAAA,EACJ,GAAA,EAAK,IAAA;AAAA,EACL,kBAAA,EAAK,IAAA;AAAA,EACL,0CAAA,EAAS,IAAA;AAAA,EACT,mDAAA,EAAa,IAAA;AAAA,EACb,mDAAA,EAAa,IAAA;AAAA,EACb,qEAAA,EAAgB,IAAA;AAAA,EAChB,yDAAA,EAAc,IAAA;AAAA,EACd,OAAA,EAAS,IAAA;AAAA,EACT,YAAA,EAAc,IAAA;AAAA,EACd,sDAAA,EAAW,IAAA;AAAA,EACX,iFAAA,EAAkB,IAAA;AAAA,EAClB,qEAAA,EAAgB,IAAA;AAAA,EAChB,qEAAA,EAAgB,IAAA;AAAA;AAAA,EAGhB,EAAA,EAAI,IAAA;AAAA,EACJ,GAAA,EAAK,IAAA;AAAA,EACL,4DAAA,EAAY,IAAA;AAAA,EACZ,uFAAA,EAAmB,IAAA;AAAA,EACnB,UAAA,EAAY,IAAA;AAAA,EACZ,eAAA,EAAiB,IAAA;AAAA;AAAA,EAGjB,EAAA,EAAI,IAAA;AAAA,EACJ,GAAA,EAAK,IAAA;AAAA,EACL,sDAAA,EAAW,IAAA;AAAA,EACX,iFAAA,EAAkB,IAAA;AAAA,EAClB,SAAA,EAAW,IAAA;AAAA,EACX,cAAA,EAAgB,IAAA;AAAA;AAAA,EAGhB,EAAA,EAAI,IAAA;AAAA,EACJ,GAAA,EAAK,IAAA;AAAA,EACL,OAAA,EAAS,IAAA;AAAA,EACT,YAAA,EAAc,IAAA;AAAA,EACd,4DAAA,EAAY,IAAA;AAAA,EACZ,4DAAA,EAAY,IAAA;AAAA;AAAA,EAGZ,EAAA,EAAI,IAAA;AAAA,EACJ,GAAA,EAAK,IAAA;AAAA,EACL,MAAA,EAAQ,IAAA;AAAA,EACR,WAAA,EAAa,IAAA;AAAA,EACb,MAAA,EAAQ,IAAA;AAAA,EACR,gDAAA,EAAU,IAAA;AAAA;AAAA,EAGV,EAAA,EAAI,IAAA;AAAA,EACJ,GAAA,EAAK,IAAA;AAAA,EACL,GAAA,EAAK,IAAA;AAAA,EACL,OAAA,EAAS,IAAA;AAAA,EACT,aAAA,EAAe,IAAA;AAAA,EACf,MAAA,EAAQ,IAAA;AAAA,EACR,gDAAA,EAAU,IAAA;AAAA;AAAA,EAGV,EAAA,EAAI,IAAA;AAAA,EACJ,GAAA,EAAK,IAAA;AAAA,EACL,aAAA,EAAU,IAAA;AAAA,EACV,QAAA,EAAU,IAAA;AAAA,EACV,gBAAA,EAAe,IAAA;AAAA,EACf,MAAA,EAAQ,IAAA;AAAA,EACR,4DAAA,EAAY,IAAA;AAAA;AAAA,EAGZ,EAAA,EAAI,IAAA;AAAA,EACJ,GAAA,EAAK,IAAA;AAAA,EACL,YAAA,EAAS,IAAA;AAAA,EACT,OAAA,EAAS,IAAA;AAAA,EACT,eAAA,EAAc,IAAA;AAAA,EACd,OAAA,EAAS,IAAA;AAAA,EACT,sDAAA,EAAW,IAAA;AAAA;AAAA,EAGX,EAAA,EAAI,IAAA;AAAA,EACJ,GAAA,EAAK,IAAA;AAAA,EACL,QAAA,EAAU,IAAA;AAAA,EACV,aAAA,EAAe,IAAA;AAAA,EACf,OAAA,EAAS,IAAA;AAAA,EACT,4DAAA,EAAY;AACd,CAAA;AASO,SAAS,sBAAsB,KAAA,EAAiD;AACrF,EAAA,IAAI,KAAA,KAAU,MAAA,IAAa,KAAA,KAAU,IAAA,EAAM,OAAO,IAAA;AAClD,EAAA,MAAM,OAAA,GAAU,KAAA,CAAM,IAAA,EAAK,CAAE,WAAA,EAAY;AACzC,EAAA,IAAI,OAAA,CAAQ,MAAA,KAAW,CAAA,EAAG,OAAO,IAAA;AACjC,EAAA,OAAO,OAAA,CAAQ,OAAO,CAAA,IAAK,IAAA;AAC7B;AAYO,SAAS,eAAe,KAAA,EAAiD;AAC9E,EAAA,IAAI,KAAA,KAAU,MAAA,IAAa,KAAA,KAAU,IAAA,EAAM,OAAO,IAAA;AAClD,EAAA,MAAM,OAAA,GAAU,MAAM,IAAA,EAAK,CAAE,aAAY,CAAE,OAAA,CAAQ,MAAM,GAAG,CAAA;AAC5D,EAAA,IAAI,OAAA,CAAQ,MAAA,KAAW,CAAA,EAAG,OAAO,IAAA;AACjC,EAAA,MAAM,MAAA,GAAS,QAAQ,OAAO,CAAA;AAC9B,EAAA,IAAI,MAAA,KAAW,QAAW,OAAO,MAAA;AACjC,EAAA,MAAM,IAAA,GAAO,OAAA,CAAQ,KAAA,CAAM,GAAG,EAAE,CAAC,CAAA;AACjC,EAAA,IAAI,IAAA,KAAS,MAAA,IAAa,IAAA,CAAK,MAAA,KAAW,GAAG,OAAO,IAAA;AACpD,EAAA,OAAO,OAAA,CAAQ,IAAI,CAAA,IAAK,IAAA;AAC1B;AAWO,SAAS,cAAc,KAAA,EAAiD;AAC7E,EAAA,IAAI,KAAA,KAAU,MAAA,IAAa,KAAA,KAAU,IAAA,EAAM,OAAO,IAAA;AAClD,EAAA,MAAM,QAAQ,KAAA,CAAM,KAAA,CAAM,GAAG,CAAA,CAAE,CAAC,GAAG,IAAA,EAAK;AACxC,EAAA,IAAI,KAAA,KAAU,MAAA,IAAa,KAAA,CAAM,MAAA,KAAW,GAAG,OAAO,IAAA;AAEtD,EAAA,MAAM,MAAM,KAAA,CAAM,KAAA,CAAM,GAAG,CAAA,CAAE,CAAC,GAAG,IAAA,EAAK;AACtC,EAAA,OAAO,eAAe,GAAG,CAAA;AAC3B","file":"chunk-OVSPOZ5J.js","sourcesContent":["/**\n * BCP-47 / language-code normalization.\n *\n * Two entry points with deliberately different strictness:\n *  - {@link normalizeBCP47} — for inputs documented to be BCP-47 (`<html lang>`,\n *    hreflang, `Content-Language`): try the full string, then strip a\n *    region/script suffix (`en-US` → `en`, `zh_CN` → `zh`).\n *  - {@link normalizeLanguageCode} — strict exact-match only, for free-text\n *    contexts (URL slugs, link text) where a hyphen split could be a coincidence.\n *\n * Both resolve aliases that appear in the wild (`ua` → `uk`, `rus` → `ru`,\n * localized picker phrases) to a canonical ISO 639-1 code.\n */\n\n/**\n * Aliases mapped to canonical ISO 639-1 codes. Keys are lowercased.\n *\n * Ukrainian is the load-bearing case: most sites use `ua` in URLs even though\n * the ISO code is `uk`. Both are accepted on input; `uk` is always output.\n *\n * Includes localized phrases users see in language pickers (`українською`,\n * `по-русски`, `in english`, …).\n */\nconst ALIASES: Record<string, string> = {\n  // Ukrainian\n  ua: \"uk\",\n  uk: \"uk\",\n  укр: \"uk\",\n  українська: \"uk\",\n  українською: \"uk\",\n  \"українська мова\": \"uk\",\n  \"на українській\": \"uk\",\n  \"українською мовою\": \"uk\",\n  ukrainian: \"uk\",\n  \"in ukrainian\": \"uk\",\n\n  // Russian\n  ru: \"ru\",\n  rus: \"ru\",\n  рус: \"ru\",\n  русский: \"ru\",\n  \"по-русски\": \"ru\",\n  \"по русски\": \"ru\",\n  \"русский язык\": \"ru\",\n  \"на русском\": \"ru\",\n  russian: \"ru\",\n  \"in russian\": \"ru\",\n  російська: \"ru\",\n  \"російська мова\": \"ru\",\n  \"по-російськи\": \"ru\",\n  \"по російськи\": \"ru\",\n\n  // Belarusian\n  be: \"be\",\n  bel: \"be\",\n  беларуская: \"be\",\n  \"беларуская мова\": \"be\",\n  belarusian: \"be\",\n  \"in belarusian\": \"be\",\n\n  // Bulgarian\n  bg: \"bg\",\n  bul: \"bg\",\n  български: \"bg\",\n  \"български език\": \"bg\",\n  bulgarian: \"bg\",\n  \"in bulgarian\": \"bg\",\n\n  // English\n  en: \"en\",\n  eng: \"en\",\n  english: \"en\",\n  \"in english\": \"en\",\n  англійська: \"en\",\n  английский: \"en\",\n\n  // Polish\n  pl: \"pl\",\n  pol: \"pl\",\n  polski: \"pl\",\n  \"po polsku\": \"pl\",\n  polish: \"pl\",\n  польська: \"pl\",\n\n  // German\n  de: \"de\",\n  deu: \"de\",\n  ger: \"de\",\n  deutsch: \"de\",\n  \"auf deutsch\": \"de\",\n  german: \"de\",\n  німецька: \"de\",\n\n  // French\n  fr: \"fr\",\n  fra: \"fr\",\n  français: \"fr\",\n  francais: \"fr\",\n  \"en français\": \"fr\",\n  french: \"fr\",\n  французька: \"fr\",\n\n  // Spanish\n  es: \"es\",\n  spa: \"es\",\n  español: \"es\",\n  espanol: \"es\",\n  \"en español\": \"es\",\n  spanish: \"es\",\n  іспанська: \"es\",\n\n  // Italian\n  it: \"it\",\n  ita: \"it\",\n  italiano: \"it\",\n  \"in italiano\": \"it\",\n  italian: \"it\",\n  італійська: \"it\",\n};\n\n/**\n * Strict, exact-match lookup. Returns `null` for unknown inputs and does NOT\n * fall back to a hyphen prefix. Use anywhere a hyphen split could be a\n * coincidence — URL path segments (`/ru-return-warranty`), title attrs, link\n * text. The phrase aliases (`по-русски`, `in english`) are in the table\n * directly, so exact lookup still finds them.\n */\nexport function normalizeLanguageCode(input: string | undefined | null): string | null {\n  if (input === undefined || input === null) return null;\n  const cleaned = input.trim().toLowerCase();\n  if (cleaned.length === 0) return null;\n  return ALIASES[cleaned] ?? null;\n}\n\n/**\n * BCP-47-aware normalization: try the full string first, then strip a\n * region/script suffix (`en-US` → `en`, `zh_CN` → `zh`). Use ONLY for inputs\n * documented to be BCP-47 — `hreflang`, `<html lang>`, `Content-Language`,\n * `data-lang`/`data-locale` — never for free-text URL slugs.\n *\n * Falls back to the raw primary subtag when no alias matches, so a code outside\n * the alias table (e.g. `pt-BR` → `pt`) still resolves to its language. The\n * roster decides relevance downstream.\n */\nexport function normalizeBCP47(input: string | undefined | null): string | null {\n  if (input === undefined || input === null) return null;\n  const cleaned = input.trim().toLowerCase().replace(/_/g, \"-\");\n  if (cleaned.length === 0) return null;\n  const direct = ALIASES[cleaned];\n  if (direct !== undefined) return direct;\n  const head = cleaned.split(\"-\")[0];\n  if (head === undefined || head.length === 0) return null;\n  return ALIASES[head] ?? head;\n}\n\n/**\n * Extract the primary subtag from a BCP-47-ish value, lowercased, then resolve\n * it through the alias table (`ua` → `uk`). Handles `Accept-Language`-style\n * comma lists (`en-US,en;q=0.9` → `en`). Returns `null` for empty/nullish.\n *\n * This is the header/HTML extraction helper: it tolerates the messy shapes those\n * sources carry (comma lists, `q` weights) where {@link normalizeBCP47} expects\n * a single tag.\n */\nexport function primarySubtag(value: string | undefined | null): string | null {\n  if (value === undefined || value === null) return null;\n  const first = value.split(\",\")[0]?.trim();\n  if (first === undefined || first.length === 0) return null;\n  // Drop a `;q=…` weight if present.\n  const tag = first.split(\";\")[0]?.trim();\n  return normalizeBCP47(tag);\n}\n"]}

package/dist/chunk-U34Z3ZSV.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;AAmBA,IAAM,WAAA,GAAc,sBAAA;AACpB,IAAM,QAAA,GAAW,mBAAA;AAsBjB,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;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;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-U34Z3ZSV.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/** 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/**\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 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\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"]}