wiki-graph-core 0.3.1

package/dist/archive/search-index/search-tokenizer.js

@@ -0,0 +1,225 @@
+import { createHash } from "crypto";
+const HAN_RUN_RE = new RegExp("\\p{Script=Han}+", "gu");
+const LATIN_OR_NUMBER_RE = /[\p{Script=Latin}\p{Number}]+/gu;
+const ZERO_WIDTH_RE = /[\u200B-\u200D\u2060\uFEFF]/gu;
+const CONTROL_RE = /[\p{Cc}\p{Cf}]/gu;
+const WHITESPACE_RE = /\s+/gu;
+const HAN_RE = new RegExp("^\\p{Script=Han}+$", "u");
+const ASCII_ALNUM_RE = /^[a-z0-9]+$/u;
+const CHINESE_STOPWORDS = /* @__PURE__ */ new Set([
+  "\u7684",
+  "\u5730",
+  "\u5F97",
+  "\u4E86",
+  "\u7740",
+  "\u8FC7",
+  "\u548C",
+  "\u4E0E",
+  "\u53CA",
+  "\u6216",
+  "\u800C",
+  "\u5728",
+  "\u662F",
+  "\u4E3A",
+  "\u4EE5",
+  "\u4E8E",
+  "\u5BF9",
+  "\u4E2D",
+  "\u4E0A",
+  "\u4E0B",
+  "\u7B49"
+]);
+const ENGLISH_STOPWORDS = /* @__PURE__ */ new Set([
+  "a",
+  "an",
+  "and",
+  "are",
+  "as",
+  "at",
+  "be",
+  "been",
+  "being",
+  "by",
+  "can",
+  "could",
+  "did",
+  "do",
+  "does",
+  "for",
+  "from",
+  "had",
+  "has",
+  "have",
+  "in",
+  "is",
+  "may",
+  "might",
+  "of",
+  "on",
+  "or",
+  "should",
+  "the",
+  "to",
+  "was",
+  "were",
+  "will",
+  "with",
+  "would"
+]);
+const IRREGULAR_LEMMAS = /* @__PURE__ */ new Map([
+  ["am", "be"],
+  ["are", "be"],
+  ["is", "be"],
+  ["was", "be"],
+  ["were", "be"],
+  ["been", "be"],
+  ["being", "be"],
+  ["has", "have"],
+  ["had", "have"],
+  ["does", "do"],
+  ["did", "do"],
+  ["done", "do"]
+]);
+function normalizeSearchText(value) {
+  return value.normalize("NFKC").replace(ZERO_WIDTH_RE, "").replace(CONTROL_RE, " ").replace(WHITESPACE_RE, " ").trim();
+}
+function createSearchTokenPlan(value) {
+  const normalized = normalizeSearchText(value);
+  const tier1 = [];
+  const tier2 = [];
+  const tier3 = [];
+  for (const raw of createHanTokens(normalized, "phrase")) {
+    tier1.push(createToken(raw, "hp", 1));
+  }
+  for (const raw of createHanTokens(normalized, "bigram")) {
+    tier1.push(createToken(raw, "h2", 1));
+  }
+  for (const raw of createHanTokens(normalized, "trigram")) {
+    tier1.push(createToken(raw, "h3", 1));
+  }
+  for (const raw of createSegmenterTokens(normalized)) {
+    tier1.push(createToken(raw, "hw", 1));
+  }
+  for (const raw of createLatinTokens(normalized)) {
+    tier1.push(createToken(raw, "le", 1));
+    const stem = stemEnglish(raw);
+    if (stem !== raw && !ENGLISH_STOPWORDS.has(stem)) {
+      tier2.push(createToken(stem, "ls", 2));
+    }
+  }
+  for (const raw of createHanTokens(normalized, "char")) {
+    tier3.push(createToken(raw, "hc", 3));
+  }
+  return {
+    tier1: dedupeTokens(tier1),
+    tier2: dedupeTokens(tier2),
+    tier3: dedupeTokens(tier3)
+  };
+}
+function listSearchPlanTerms(plan) {
+  return [
+    ...new Set(
+      [...plan.tier1, ...plan.tier2, ...plan.tier3].map((token) => token.raw)
+    )
+  ];
+}
+function hasSearchTokens(plan) {
+  return plan.tier1.length > 0 || plan.tier2.length > 0 || plan.tier3.length > 0;
+}
+function createHanTokens(value, kind) {
+  const tokens = [];
+  for (const match of value.matchAll(HAN_RUN_RE)) {
+    const run = [...match[0]];
+    if (kind === "phrase") {
+      if (run.length >= 2) {
+        tokens.push(run.join(""));
+      }
+      continue;
+    }
+    if (kind === "char") {
+      tokens.push(...run.filter((token) => !CHINESE_STOPWORDS.has(token)));
+      continue;
+    }
+    const size = kind === "bigram" ? 2 : 3;
+    if (run.length < size) {
+      continue;
+    }
+    for (let index = 0; index <= run.length - size; index += 1) {
+      tokens.push(run.slice(index, index + size).join(""));
+    }
+  }
+  return tokens;
+}
+function createLatinTokens(value) {
+  return [...value.toLowerCase().matchAll(LATIN_OR_NUMBER_RE)].map((match) => match[0]).filter((token) => !ENGLISH_STOPWORDS.has(token));
+}
+function createSegmenterTokens(value) {
+  if (typeof Intl.Segmenter !== "function") {
+    return [];
+  }
+  const segmenter = new Intl.Segmenter("zh-CN", { granularity: "word" });
+  const tokens = [];
+  for (const segment of segmenter.segment(value)) {
+    const token = normalizeSearchText(segment.segment).toLowerCase();
+    if (segment.isWordLike === true && [...token].length >= 2 && HAN_RE.test(token)) {
+      tokens.push(token);
+    }
+  }
+  return tokens;
+}
+function createToken(raw, prefix, tier) {
+  const normalized = normalizeSearchText(raw).toLowerCase();
+  const digest = createHash("sha256").update(normalized).digest("hex").slice(0, 20);
+  return {
+    encoded: `${prefix}${digest}`,
+    raw: normalized,
+    tier
+  };
+}
+function dedupeTokens(tokens) {
+  const seen = /* @__PURE__ */ new Set();
+  const result = [];
+  for (const token of tokens) {
+    if (seen.has(token.encoded)) {
+      continue;
+    }
+    seen.add(token.encoded);
+    result.push(token);
+  }
+  return result;
+}
+function stemEnglish(token) {
+  const lemma = IRREGULAR_LEMMAS.get(token);
+  if (lemma !== void 0) {
+    return lemma;
+  }
+  if (!ASCII_ALNUM_RE.test(token) || /\d/u.test(token) || token.length < 4) {
+    return token;
+  }
+  return porterStem(token);
+}
+function porterStem(value) {
+  let token = value;
+  if (token.endsWith("ies") && token.length > 4) {
+    token = `${token.slice(0, -3)}y`;
+  } else if (token.endsWith("ing") && token.length > 5) {
+    token = token.slice(0, -3);
+  } else if (token.endsWith("ed") && token.length > 4) {
+    token = token.slice(0, -2);
+  } else if (token.endsWith("es") && token.length > 4) {
+    token = token.slice(0, -2);
+  } else if (token.endsWith("s") && token.length > 4) {
+    token = token.slice(0, -1);
+  }
+  if (token.length > 3 && token.at(-1) === token.at(-2) && /[bcdfghjklmnpqrstvwxyz]/u.test(token.at(-1))) {
+    token = token.slice(0, -1);
+  }
+  return token;
+}
+export {
+  createSearchTokenPlan,
+  hasSearchTokens,
+  listSearchPlanTerms,
+  normalizeSearchText
+};
+//# sourceMappingURL=search-tokenizer.js.map

package/dist/archive/search-index/search-tokenizer.js.map

@@ -0,0 +1 @@
+{"version":3,"sources":["../../../src/archive/search-index/search-tokenizer.ts"],"sourcesContent":["import { createHash } from \"crypto\";\n\nexport interface SearchToken {\n  readonly encoded: string;\n  readonly raw: string;\n  readonly tier: 1 | 2 | 3;\n}\n\nexport interface SearchTokenPlan {\n  readonly tier1: readonly SearchToken[];\n  readonly tier2: readonly SearchToken[];\n  readonly tier3: readonly SearchToken[];\n}\n\nconst HAN_RUN_RE = /\\p{Script=Han}+/gu;\nconst LATIN_OR_NUMBER_RE = /[\\p{Script=Latin}\\p{Number}]+/gu;\nconst ZERO_WIDTH_RE = /[\\u200B-\\u200D\\u2060\\uFEFF]/gu;\nconst CONTROL_RE = /[\\p{Cc}\\p{Cf}]/gu;\nconst WHITESPACE_RE = /\\s+/gu;\nconst HAN_RE = /^\\p{Script=Han}+$/u;\nconst ASCII_ALNUM_RE = /^[a-z0-9]+$/u;\n\nconst CHINESE_STOPWORDS = new Set([\n  \"的\",\n  \"地\",\n  \"得\",\n  \"了\",\n  \"着\",\n  \"过\",\n  \"和\",\n  \"与\",\n  \"及\",\n  \"或\",\n  \"而\",\n  \"在\",\n  \"是\",\n  \"为\",\n  \"以\",\n  \"于\",\n  \"对\",\n  \"中\",\n  \"上\",\n  \"下\",\n  \"等\",\n]);\n\nconst ENGLISH_STOPWORDS = new Set([\n  \"a\",\n  \"an\",\n  \"and\",\n  \"are\",\n  \"as\",\n  \"at\",\n  \"be\",\n  \"been\",\n  \"being\",\n  \"by\",\n  \"can\",\n  \"could\",\n  \"did\",\n  \"do\",\n  \"does\",\n  \"for\",\n  \"from\",\n  \"had\",\n  \"has\",\n  \"have\",\n  \"in\",\n  \"is\",\n  \"may\",\n  \"might\",\n  \"of\",\n  \"on\",\n  \"or\",\n  \"should\",\n  \"the\",\n  \"to\",\n  \"was\",\n  \"were\",\n  \"will\",\n  \"with\",\n  \"would\",\n]);\n\nconst IRREGULAR_LEMMAS = new Map([\n  [\"am\", \"be\"],\n  [\"are\", \"be\"],\n  [\"is\", \"be\"],\n  [\"was\", \"be\"],\n  [\"were\", \"be\"],\n  [\"been\", \"be\"],\n  [\"being\", \"be\"],\n  [\"has\", \"have\"],\n  [\"had\", \"have\"],\n  [\"does\", \"do\"],\n  [\"did\", \"do\"],\n  [\"done\", \"do\"],\n]);\n\nexport function normalizeSearchText(value: string): string {\n  return value\n    .normalize(\"NFKC\")\n    .replace(ZERO_WIDTH_RE, \"\")\n    .replace(CONTROL_RE, \" \")\n    .replace(WHITESPACE_RE, \" \")\n    .trim();\n}\n\nexport function createSearchTokenPlan(value: string): SearchTokenPlan {\n  const normalized = normalizeSearchText(value);\n  const tier1: SearchToken[] = [];\n  const tier2: SearchToken[] = [];\n  const tier3: SearchToken[] = [];\n\n  for (const raw of createHanTokens(normalized, \"phrase\")) {\n    tier1.push(createToken(raw, \"hp\", 1));\n  }\n  for (const raw of createHanTokens(normalized, \"bigram\")) {\n    tier1.push(createToken(raw, \"h2\", 1));\n  }\n  for (const raw of createHanTokens(normalized, \"trigram\")) {\n    tier1.push(createToken(raw, \"h3\", 1));\n  }\n  for (const raw of createSegmenterTokens(normalized)) {\n    tier1.push(createToken(raw, \"hw\", 1));\n  }\n  for (const raw of createLatinTokens(normalized)) {\n    tier1.push(createToken(raw, \"le\", 1));\n    const stem = stemEnglish(raw);\n\n    if (stem !== raw && !ENGLISH_STOPWORDS.has(stem)) {\n      tier2.push(createToken(stem, \"ls\", 2));\n    }\n  }\n  for (const raw of createHanTokens(normalized, \"char\")) {\n    tier3.push(createToken(raw, \"hc\", 3));\n  }\n\n  return {\n    tier1: dedupeTokens(tier1),\n    tier2: dedupeTokens(tier2),\n    tier3: dedupeTokens(tier3),\n  };\n}\n\nexport function listSearchPlanTerms(plan: SearchTokenPlan): readonly string[] {\n  return [\n    ...new Set(\n      [...plan.tier1, ...plan.tier2, ...plan.tier3].map((token) => token.raw),\n    ),\n  ];\n}\n\nexport function hasSearchTokens(plan: SearchTokenPlan): boolean {\n  return (\n    plan.tier1.length > 0 || plan.tier2.length > 0 || plan.tier3.length > 0\n  );\n}\n\nfunction createHanTokens(\n  value: string,\n  kind: \"bigram\" | \"char\" | \"phrase\" | \"trigram\",\n): readonly string[] {\n  const tokens: string[] = [];\n\n  for (const match of value.matchAll(HAN_RUN_RE)) {\n    const run = [...match[0]];\n\n    if (kind === \"phrase\") {\n      if (run.length >= 2) {\n        tokens.push(run.join(\"\"));\n      }\n      continue;\n    }\n    if (kind === \"char\") {\n      tokens.push(...run.filter((token) => !CHINESE_STOPWORDS.has(token)));\n      continue;\n    }\n\n    const size = kind === \"bigram\" ? 2 : 3;\n\n    if (run.length < size) {\n      continue;\n    }\n    for (let index = 0; index <= run.length - size; index += 1) {\n      tokens.push(run.slice(index, index + size).join(\"\"));\n    }\n  }\n\n  return tokens;\n}\n\nfunction createLatinTokens(value: string): readonly string[] {\n  return [...value.toLowerCase().matchAll(LATIN_OR_NUMBER_RE)]\n    .map((match) => match[0])\n    .filter((token) => !ENGLISH_STOPWORDS.has(token));\n}\n\nfunction createSegmenterTokens(value: string): readonly string[] {\n  if (typeof Intl.Segmenter !== \"function\") {\n    return [];\n  }\n\n  const segmenter = new Intl.Segmenter(\"zh-CN\", { granularity: \"word\" });\n  const tokens: string[] = [];\n\n  for (const segment of segmenter.segment(value)) {\n    const token = normalizeSearchText(segment.segment).toLowerCase();\n\n    if (\n      segment.isWordLike === true &&\n      [...token].length >= 2 &&\n      HAN_RE.test(token)\n    ) {\n      tokens.push(token);\n    }\n  }\n\n  return tokens;\n}\n\nfunction createToken(\n  raw: string,\n  prefix: string,\n  tier: 1 | 2 | 3,\n): SearchToken {\n  const normalized = normalizeSearchText(raw).toLowerCase();\n  const digest = createHash(\"sha256\")\n    .update(normalized)\n    .digest(\"hex\")\n    .slice(0, 20);\n\n  return {\n    encoded: `${prefix}${digest}`,\n    raw: normalized,\n    tier,\n  };\n}\n\nfunction dedupeTokens(tokens: readonly SearchToken[]): readonly SearchToken[] {\n  const seen = new Set<string>();\n  const result: SearchToken[] = [];\n\n  for (const token of tokens) {\n    if (seen.has(token.encoded)) {\n      continue;\n    }\n\n    seen.add(token.encoded);\n    result.push(token);\n  }\n\n  return result;\n}\n\nfunction stemEnglish(token: string): string {\n  const lemma = IRREGULAR_LEMMAS.get(token);\n\n  if (lemma !== undefined) {\n    return lemma;\n  }\n  if (!ASCII_ALNUM_RE.test(token) || /\\d/u.test(token) || token.length < 4) {\n    return token;\n  }\n\n  return porterStem(token);\n}\n\nfunction porterStem(value: string): string {\n  // A deliberately small Porter-like stemmer: enough for weak recall tokens,\n  // not intended to replace exact Latin tokens or final ranking.\n  let token = value;\n\n  if (token.endsWith(\"ies\") && token.length > 4) {\n    token = `${token.slice(0, -3)}y`;\n  } else if (token.endsWith(\"ing\") && token.length > 5) {\n    token = token.slice(0, -3);\n  } else if (token.endsWith(\"ed\") && token.length > 4) {\n    token = token.slice(0, -2);\n  } else if (token.endsWith(\"es\") && token.length > 4) {\n    token = token.slice(0, -2);\n  } else if (token.endsWith(\"s\") && token.length > 4) {\n    token = token.slice(0, -1);\n  }\n\n  if (\n    token.length > 3 &&\n    token.at(-1) === token.at(-2) &&\n    /[bcdfghjklmnpqrstvwxyz]/u.test(token.at(-1)!)\n  ) {\n    token = token.slice(0, -1);\n  }\n\n  return token;\n}\n"],"mappings":"AAAA,SAAS,kBAAkB;AAc3B,MAAM,aAAa,WAAC,oBAAgB,IAAE;AACtC,MAAM,qBAAqB;AAC3B,MAAM,gBAAgB;AACtB,MAAM,aAAa;AACnB,MAAM,gBAAgB;AACtB,MAAM,SAAS,WAAC,sBAAkB,GAAC;AACnC,MAAM,iBAAiB;AAEvB,MAAM,oBAAoB,oBAAI,IAAI;AAAA,EAChC;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AACF,CAAC;AAED,MAAM,oBAAoB,oBAAI,IAAI;AAAA,EAChC;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AAAA,EACA;AACF,CAAC;AAED,MAAM,mBAAmB,oBAAI,IAAI;AAAA,EAC/B,CAAC,MAAM,IAAI;AAAA,EACX,CAAC,OAAO,IAAI;AAAA,EACZ,CAAC,MAAM,IAAI;AAAA,EACX,CAAC,OAAO,IAAI;AAAA,EACZ,CAAC,QAAQ,IAAI;AAAA,EACb,CAAC,QAAQ,IAAI;AAAA,EACb,CAAC,SAAS,IAAI;AAAA,EACd,CAAC,OAAO,MAAM;AAAA,EACd,CAAC,OAAO,MAAM;AAAA,EACd,CAAC,QAAQ,IAAI;AAAA,EACb,CAAC,OAAO,IAAI;AAAA,EACZ,CAAC,QAAQ,IAAI;AACf,CAAC;AAEM,SAAS,oBAAoB,OAAuB;AACzD,SAAO,MACJ,UAAU,MAAM,EAChB,QAAQ,eAAe,EAAE,EACzB,QAAQ,YAAY,GAAG,EACvB,QAAQ,eAAe,GAAG,EAC1B,KAAK;AACV;AAEO,SAAS,sBAAsB,OAAgC;AACpE,QAAM,aAAa,oBAAoB,KAAK;AAC5C,QAAM,QAAuB,CAAC;AAC9B,QAAM,QAAuB,CAAC;AAC9B,QAAM,QAAuB,CAAC;AAE9B,aAAW,OAAO,gBAAgB,YAAY,QAAQ,GAAG;AACvD,UAAM,KAAK,YAAY,KAAK,MAAM,CAAC,CAAC;AAAA,EACtC;AACA,aAAW,OAAO,gBAAgB,YAAY,QAAQ,GAAG;AACvD,UAAM,KAAK,YAAY,KAAK,MAAM,CAAC,CAAC;AAAA,EACtC;AACA,aAAW,OAAO,gBAAgB,YAAY,SAAS,GAAG;AACxD,UAAM,KAAK,YAAY,KAAK,MAAM,CAAC,CAAC;AAAA,EACtC;AACA,aAAW,OAAO,sBAAsB,UAAU,GAAG;AACnD,UAAM,KAAK,YAAY,KAAK,MAAM,CAAC,CAAC;AAAA,EACtC;AACA,aAAW,OAAO,kBAAkB,UAAU,GAAG;AAC/C,UAAM,KAAK,YAAY,KAAK,MAAM,CAAC,CAAC;AACpC,UAAM,OAAO,YAAY,GAAG;AAE5B,QAAI,SAAS,OAAO,CAAC,kBAAkB,IAAI,IAAI,GAAG;AAChD,YAAM,KAAK,YAAY,MAAM,MAAM,CAAC,CAAC;AAAA,IACvC;AAAA,EACF;AACA,aAAW,OAAO,gBAAgB,YAAY,MAAM,GAAG;AACrD,UAAM,KAAK,YAAY,KAAK,MAAM,CAAC,CAAC;AAAA,EACtC;AAEA,SAAO;AAAA,IACL,OAAO,aAAa,KAAK;AAAA,IACzB,OAAO,aAAa,KAAK;AAAA,IACzB,OAAO,aAAa,KAAK;AAAA,EAC3B;AACF;AAEO,SAAS,oBAAoB,MAA0C;AAC5E,SAAO;AAAA,IACL,GAAG,IAAI;AAAA,MACL,CAAC,GAAG,KAAK,OAAO,GAAG,KAAK,OAAO,GAAG,KAAK,KAAK,EAAE,IAAI,CAAC,UAAU,MAAM,GAAG;AAAA,IACxE;AAAA,EACF;AACF;AAEO,SAAS,gBAAgB,MAAgC;AAC9D,SACE,KAAK,MAAM,SAAS,KAAK,KAAK,MAAM,SAAS,KAAK,KAAK,MAAM,SAAS;AAE1E;AAEA,SAAS,gBACP,OACA,MACmB;AACnB,QAAM,SAAmB,CAAC;AAE1B,aAAW,SAAS,MAAM,SAAS,UAAU,GAAG;AAC9C,UAAM,MAAM,CAAC,GAAG,MAAM,CAAC,CAAC;AAExB,QAAI,SAAS,UAAU;AACrB,UAAI,IAAI,UAAU,GAAG;AACnB,eAAO,KAAK,IAAI,KAAK,EAAE,CAAC;AAAA,MAC1B;AACA;AAAA,IACF;AACA,QAAI,SAAS,QAAQ;AACnB,aAAO,KAAK,GAAG,IAAI,OAAO,CAAC,UAAU,CAAC,kBAAkB,IAAI,KAAK,CAAC,CAAC;AACnE;AAAA,IACF;AAEA,UAAM,OAAO,SAAS,WAAW,IAAI;AAErC,QAAI,IAAI,SAAS,MAAM;AACrB;AAAA,IACF;AACA,aAAS,QAAQ,GAAG,SAAS,IAAI,SAAS,MAAM,SAAS,GAAG;AAC1D,aAAO,KAAK,IAAI,MAAM,OAAO,QAAQ,IAAI,EAAE,KAAK,EAAE,CAAC;AAAA,IACrD;AAAA,EACF;AAEA,SAAO;AACT;AAEA,SAAS,kBAAkB,OAAkC;AAC3D,SAAO,CAAC,GAAG,MAAM,YAAY,EAAE,SAAS,kBAAkB,CAAC,EACxD,IAAI,CAAC,UAAU,MAAM,CAAC,CAAC,EACvB,OAAO,CAAC,UAAU,CAAC,kBAAkB,IAAI,KAAK,CAAC;AACpD;AAEA,SAAS,sBAAsB,OAAkC;AAC/D,MAAI,OAAO,KAAK,cAAc,YAAY;AACxC,WAAO,CAAC;AAAA,EACV;AAEA,QAAM,YAAY,IAAI,KAAK,UAAU,SAAS,EAAE,aAAa,OAAO,CAAC;AACrE,QAAM,SAAmB,CAAC;AAE1B,aAAW,WAAW,UAAU,QAAQ,KAAK,GAAG;AAC9C,UAAM,QAAQ,oBAAoB,QAAQ,OAAO,EAAE,YAAY;AAE/D,QACE,QAAQ,eAAe,QACvB,CAAC,GAAG,KAAK,EAAE,UAAU,KACrB,OAAO,KAAK,KAAK,GACjB;AACA,aAAO,KAAK,KAAK;AAAA,IACnB;AAAA,EACF;AAEA,SAAO;AACT;AAEA,SAAS,YACP,KACA,QACA,MACa;AACb,QAAM,aAAa,oBAAoB,GAAG,EAAE,YAAY;AACxD,QAAM,SAAS,WAAW,QAAQ,EAC/B,OAAO,UAAU,EACjB,OAAO,KAAK,EACZ,MAAM,GAAG,EAAE;AAEd,SAAO;AAAA,IACL,SAAS,GAAG,MAAM,GAAG,MAAM;AAAA,IAC3B,KAAK;AAAA,IACL;AAAA,EACF;AACF;AAEA,SAAS,aAAa,QAAwD;AAC5E,QAAM,OAAO,oBAAI,IAAY;AAC7B,QAAM,SAAwB,CAAC;AAE/B,aAAW,SAAS,QAAQ;AAC1B,QAAI,KAAK,IAAI,MAAM,OAAO,GAAG;AAC3B;AAAA,IACF;AAEA,SAAK,IAAI,MAAM,OAAO;AACtB,WAAO,KAAK,KAAK;AAAA,EACnB;AAEA,SAAO;AACT;AAEA,SAAS,YAAY,OAAuB;AAC1C,QAAM,QAAQ,iBAAiB,IAAI,KAAK;AAExC,MAAI,UAAU,QAAW;AACvB,WAAO;AAAA,EACT;AACA,MAAI,CAAC,eAAe,KAAK,KAAK,KAAK,MAAM,KAAK,KAAK,KAAK,MAAM,SAAS,GAAG;AACxE,WAAO;AAAA,EACT;AAEA,SAAO,WAAW,KAAK;AACzB;AAEA,SAAS,WAAW,OAAuB;AAGzC,MAAI,QAAQ;AAEZ,MAAI,MAAM,SAAS,KAAK,KAAK,MAAM,SAAS,GAAG;AAC7C,YAAQ,GAAG,MAAM,MAAM,GAAG,EAAE,CAAC;AAAA,EAC/B,WAAW,MAAM,SAAS,KAAK,KAAK,MAAM,SAAS,GAAG;AACpD,YAAQ,MAAM,MAAM,GAAG,EAAE;AAAA,EAC3B,WAAW,MAAM,SAAS,IAAI,KAAK,MAAM,SAAS,GAAG;AACnD,YAAQ,MAAM,MAAM,GAAG,EAAE;AAAA,EAC3B,WAAW,MAAM,SAAS,IAAI,KAAK,MAAM,SAAS,GAAG;AACnD,YAAQ,MAAM,MAAM,GAAG,EAAE;AAAA,EAC3B,WAAW,MAAM,SAAS,GAAG,KAAK,MAAM,SAAS,GAAG;AAClD,YAAQ,MAAM,MAAM,GAAG,EAAE;AAAA,EAC3B;AAEA,MACE,MAAM,SAAS,KACf,MAAM,GAAG,EAAE,MAAM,MAAM,GAAG,EAAE,KAC5B,2BAA2B,KAAK,MAAM,GAAG,EAAE,CAAE,GAC7C;AACA,YAAQ,MAAM,MAAM,GAAG,EAAE;AAAA,EAC3B;AAEA,SAAO;AACT;","names":[]}

package/dist/common/cli-command.d.ts

@@ -0,0 +1,4 @@
+declare const CLI_PRIMARY_COMMAND = "wg";
+declare const CLI_FULL_COMMAND = "wikigraph";
+
+export { CLI_FULL_COMMAND, CLI_PRIMARY_COMMAND };

package/dist/common/cli-command.js

@@ -0,0 +1,7 @@
+const CLI_PRIMARY_COMMAND = "wg";
+const CLI_FULL_COMMAND = "wikigraph";
+export {
+  CLI_FULL_COMMAND,
+  CLI_PRIMARY_COMMAND
+};
+//# sourceMappingURL=cli-command.js.map

package/dist/common/cli-command.js.map

@@ -0,0 +1 @@
+{"version":3,"sources":["../../src/common/cli-command.ts"],"sourcesContent":["export const CLI_PRIMARY_COMMAND = \"wg\";\nexport const CLI_FULL_COMMAND = \"wikigraph\";\n"],"mappings":"AAAO,MAAM,sBAAsB;AAC5B,MAAM,mBAAmB;","names":[]}

package/dist/common/data-dir.d.ts

@@ -0,0 +1,3 @@
+declare function resolveDataDirPath(): string;
+
+export { resolveDataDirPath };

package/dist/common/data-dir.js

@@ -0,0 +1,48 @@
+import { existsSync, statSync } from "fs";
+import { fileURLToPath } from "url";
+import { dirname, join, parse, resolve } from "path";
+function resolveDataDirPath() {
+  const injectedPath = globalThis.__WIKIGRAPH_DATA_DIR__;
+  if (typeof injectedPath === "string" && injectedPath !== "") {
+    return injectedPath;
+  }
+  const moduleDataDirPath = resolveDataDirPathFromModule();
+  if (moduleDataDirPath !== void 0) {
+    return moduleDataDirPath;
+  }
+  return resolveDataDirPathFromWorkingDirectory();
+}
+function resolveDataDirPathFromModule() {
+  const moduleDirectoryPath = dirname(fileURLToPath(import.meta.url));
+  for (const candidatePath of [
+    resolve(moduleDirectoryPath, "../../data"),
+    resolve(moduleDirectoryPath, "../data")
+  ]) {
+    if (existsSync(candidatePath) && statSync(candidatePath).isDirectory()) {
+      return candidatePath;
+    }
+  }
+  return void 0;
+}
+function resolveDataDirPathFromWorkingDirectory() {
+  let currentDirectoryPath = process.cwd();
+  const rootDirectoryPath = parse(currentDirectoryPath).root;
+  while (true) {
+    for (const candidatePath of [
+      join(currentDirectoryPath, "data"),
+      join(currentDirectoryPath, "packages", "core", "data")
+    ]) {
+      if (existsSync(candidatePath) && statSync(candidatePath).isDirectory()) {
+        return candidatePath;
+      }
+    }
+    if (currentDirectoryPath === rootDirectoryPath) {
+      throw new Error("Could not locate data directory");
+    }
+    currentDirectoryPath = dirname(currentDirectoryPath);
+  }
+}
+export {
+  resolveDataDirPath
+};
+//# sourceMappingURL=data-dir.js.map

package/dist/common/data-dir.js.map

@@ -0,0 +1 @@
+{"version":3,"sources":["../../src/common/data-dir.ts"],"sourcesContent":["import { existsSync, statSync } from \"fs\";\nimport { fileURLToPath } from \"url\";\nimport { dirname, join, parse, resolve } from \"path\";\n\nexport function resolveDataDirPath(): string {\n  const injectedPath = (globalThis as { __WIKIGRAPH_DATA_DIR__?: unknown })\n    .__WIKIGRAPH_DATA_DIR__;\n\n  if (typeof injectedPath === \"string\" && injectedPath !== \"\") {\n    return injectedPath;\n  }\n\n  const moduleDataDirPath = resolveDataDirPathFromModule();\n  if (moduleDataDirPath !== undefined) {\n    return moduleDataDirPath;\n  }\n\n  return resolveDataDirPathFromWorkingDirectory();\n}\n\nfunction resolveDataDirPathFromModule(): string | undefined {\n  const moduleDirectoryPath = dirname(fileURLToPath(import.meta.url));\n\n  for (const candidatePath of [\n    resolve(moduleDirectoryPath, \"../../data\"),\n    resolve(moduleDirectoryPath, \"../data\"),\n  ]) {\n    if (existsSync(candidatePath) && statSync(candidatePath).isDirectory()) {\n      return candidatePath;\n    }\n  }\n\n  return undefined;\n}\n\nfunction resolveDataDirPathFromWorkingDirectory(): string {\n  let currentDirectoryPath = process.cwd();\n  const rootDirectoryPath = parse(currentDirectoryPath).root;\n\n  while (true) {\n    for (const candidatePath of [\n      join(currentDirectoryPath, \"data\"),\n      join(currentDirectoryPath, \"packages\", \"core\", \"data\"),\n    ]) {\n      if (existsSync(candidatePath) && statSync(candidatePath).isDirectory()) {\n        return candidatePath;\n      }\n    }\n\n    if (currentDirectoryPath === rootDirectoryPath) {\n      throw new Error(\"Could not locate data directory\");\n    }\n\n    currentDirectoryPath = dirname(currentDirectoryPath);\n  }\n}\n"],"mappings":"AAAA,SAAS,YAAY,gBAAgB;AACrC,SAAS,qBAAqB;AAC9B,SAAS,SAAS,MAAM,OAAO,eAAe;AAEvC,SAAS,qBAA6B;AAC3C,QAAM,eAAgB,WACnB;AAEH,MAAI,OAAO,iBAAiB,YAAY,iBAAiB,IAAI;AAC3D,WAAO;AAAA,EACT;AAEA,QAAM,oBAAoB,6BAA6B;AACvD,MAAI,sBAAsB,QAAW;AACnC,WAAO;AAAA,EACT;AAEA,SAAO,uCAAuC;AAChD;AAEA,SAAS,+BAAmD;AAC1D,QAAM,sBAAsB,QAAQ,cAAc,YAAY,GAAG,CAAC;AAElE,aAAW,iBAAiB;AAAA,IAC1B,QAAQ,qBAAqB,YAAY;AAAA,IACzC,QAAQ,qBAAqB,SAAS;AAAA,EACxC,GAAG;AACD,QAAI,WAAW,aAAa,KAAK,SAAS,aAAa,EAAE,YAAY,GAAG;AACtE,aAAO;AAAA,IACT;AAAA,EACF;AAEA,SAAO;AACT;AAEA,SAAS,yCAAiD;AACxD,MAAI,uBAAuB,QAAQ,IAAI;AACvC,QAAM,oBAAoB,MAAM,oBAAoB,EAAE;AAEtD,SAAO,MAAM;AACX,eAAW,iBAAiB;AAAA,MAC1B,KAAK,sBAAsB,MAAM;AAAA,MACjC,KAAK,sBAAsB,YAAY,QAAQ,MAAM;AAAA,IACvD,GAAG;AACD,UAAI,WAAW,aAAa,KAAK,SAAS,aAAa,EAAE,YAAY,GAAG;AACtE,eAAO;AAAA,MACT;AAAA,IACF;AAEA,QAAI,yBAAyB,mBAAmB;AAC9C,YAAM,IAAI,MAAM,iCAAiC;AAAA,IACnD;AAEA,2BAAuB,QAAQ,oBAAoB;AAAA,EACrD;AACF;","names":[]}

package/dist/common/language.d.ts

@@ -0,0 +1,55 @@
+declare enum Language {
+    Arabic = "Arabic",
+    Danish = "Danish",
+    Dutch = "Dutch",
+    English = "English",
+    Finnish = "Finnish",
+    French = "French",
+    German = "German",
+    Hindi = "Hindi",
+    Indonesian = "Indonesian",
+    Italian = "Italian",
+    Japanese = "Japanese",
+    Korean = "Korean",
+    Norwegian = "Norwegian",
+    Polish = "Polish",
+    Portuguese = "Portuguese",
+    Russian = "Russian",
+    SimplifiedChinese = "Simplified Chinese",
+    Spanish = "Spanish",
+    Swedish = "Swedish",
+    Thai = "Thai",
+    TraditionalChinese = "Traditional Chinese",
+    Turkish = "Turkish",
+    Vietnamese = "Vietnamese"
+}
+declare enum LanguageCode {
+    Arabic = "ar",
+    Chinese = "zh",
+    Danish = "da",
+    Dutch = "nl",
+    English = "en",
+    Finnish = "fi",
+    French = "fr",
+    German = "de",
+    Hindi = "hi",
+    Indonesian = "id",
+    Italian = "it",
+    Japanese = "ja",
+    Korean = "ko",
+    Norwegian = "no",
+    Polish = "pl",
+    Portuguese = "pt",
+    Russian = "ru",
+    Spanish = "es",
+    Swedish = "sv",
+    Thai = "th",
+    Turkish = "tr",
+    Vietnamese = "vi"
+}
+declare function getLanguageCode(language: Language): LanguageCode;
+declare function formatLanguageForPrompt(code: LanguageCode): Language;
+declare function normalizeLanguageCode(language: Language | string | null | undefined): LanguageCode | undefined;
+declare function getWikipageLanguageCode(language: Language | string | null | undefined): "en" | "zh" | undefined;
+
+export { Language, LanguageCode, formatLanguageForPrompt, getLanguageCode, getWikipageLanguageCode, normalizeLanguageCode };

package/dist/common/language.js

@@ -0,0 +1,208 @@
+var Language = /* @__PURE__ */ ((Language2) => {
+  Language2["Arabic"] = "Arabic";
+  Language2["Danish"] = "Danish";
+  Language2["Dutch"] = "Dutch";
+  Language2["English"] = "English";
+  Language2["Finnish"] = "Finnish";
+  Language2["French"] = "French";
+  Language2["German"] = "German";
+  Language2["Hindi"] = "Hindi";
+  Language2["Indonesian"] = "Indonesian";
+  Language2["Italian"] = "Italian";
+  Language2["Japanese"] = "Japanese";
+  Language2["Korean"] = "Korean";
+  Language2["Norwegian"] = "Norwegian";
+  Language2["Polish"] = "Polish";
+  Language2["Portuguese"] = "Portuguese";
+  Language2["Russian"] = "Russian";
+  Language2["SimplifiedChinese"] = "Simplified Chinese";
+  Language2["Spanish"] = "Spanish";
+  Language2["Swedish"] = "Swedish";
+  Language2["Thai"] = "Thai";
+  Language2["TraditionalChinese"] = "Traditional Chinese";
+  Language2["Turkish"] = "Turkish";
+  Language2["Vietnamese"] = "Vietnamese";
+  return Language2;
+})(Language || {});
+var LanguageCode = /* @__PURE__ */ ((LanguageCode2) => {
+  LanguageCode2["Arabic"] = "ar";
+  LanguageCode2["Chinese"] = "zh";
+  LanguageCode2["Danish"] = "da";
+  LanguageCode2["Dutch"] = "nl";
+  LanguageCode2["English"] = "en";
+  LanguageCode2["Finnish"] = "fi";
+  LanguageCode2["French"] = "fr";
+  LanguageCode2["German"] = "de";
+  LanguageCode2["Hindi"] = "hi";
+  LanguageCode2["Indonesian"] = "id";
+  LanguageCode2["Italian"] = "it";
+  LanguageCode2["Japanese"] = "ja";
+  LanguageCode2["Korean"] = "ko";
+  LanguageCode2["Norwegian"] = "no";
+  LanguageCode2["Polish"] = "pl";
+  LanguageCode2["Portuguese"] = "pt";
+  LanguageCode2["Russian"] = "ru";
+  LanguageCode2["Spanish"] = "es";
+  LanguageCode2["Swedish"] = "sv";
+  LanguageCode2["Thai"] = "th";
+  LanguageCode2["Turkish"] = "tr";
+  LanguageCode2["Vietnamese"] = "vi";
+  return LanguageCode2;
+})(LanguageCode || {});
+const LANGUAGE_TO_CODE = {
+  ["Arabic" /* Arabic */]: "ar" /* Arabic */,
+  ["Danish" /* Danish */]: "da" /* Danish */,
+  ["Dutch" /* Dutch */]: "nl" /* Dutch */,
+  ["English" /* English */]: "en" /* English */,
+  ["Finnish" /* Finnish */]: "fi" /* Finnish */,
+  ["French" /* French */]: "fr" /* French */,
+  ["German" /* German */]: "de" /* German */,
+  ["Hindi" /* Hindi */]: "hi" /* Hindi */,
+  ["Indonesian" /* Indonesian */]: "id" /* Indonesian */,
+  ["Italian" /* Italian */]: "it" /* Italian */,
+  ["Japanese" /* Japanese */]: "ja" /* Japanese */,
+  ["Korean" /* Korean */]: "ko" /* Korean */,
+  ["Norwegian" /* Norwegian */]: "no" /* Norwegian */,
+  ["Polish" /* Polish */]: "pl" /* Polish */,
+  ["Portuguese" /* Portuguese */]: "pt" /* Portuguese */,
+  ["Russian" /* Russian */]: "ru" /* Russian */,
+  ["Simplified Chinese" /* SimplifiedChinese */]: "zh" /* Chinese */,
+  ["Spanish" /* Spanish */]: "es" /* Spanish */,
+  ["Swedish" /* Swedish */]: "sv" /* Swedish */,
+  ["Thai" /* Thai */]: "th" /* Thai */,
+  ["Traditional Chinese" /* TraditionalChinese */]: "zh" /* Chinese */,
+  ["Turkish" /* Turkish */]: "tr" /* Turkish */,
+  ["Vietnamese" /* Vietnamese */]: "vi" /* Vietnamese */
+};
+const LANGUAGE_CODE_TO_PROMPT_LANGUAGE = {
+  ["ar" /* Arabic */]: "Arabic" /* Arabic */,
+  ["zh" /* Chinese */]: "Simplified Chinese" /* SimplifiedChinese */,
+  ["da" /* Danish */]: "Danish" /* Danish */,
+  ["nl" /* Dutch */]: "Dutch" /* Dutch */,
+  ["en" /* English */]: "English" /* English */,
+  ["fi" /* Finnish */]: "Finnish" /* Finnish */,
+  ["fr" /* French */]: "French" /* French */,
+  ["de" /* German */]: "German" /* German */,
+  ["hi" /* Hindi */]: "Hindi" /* Hindi */,
+  ["id" /* Indonesian */]: "Indonesian" /* Indonesian */,
+  ["it" /* Italian */]: "Italian" /* Italian */,
+  ["ja" /* Japanese */]: "Japanese" /* Japanese */,
+  ["ko" /* Korean */]: "Korean" /* Korean */,
+  ["no" /* Norwegian */]: "Norwegian" /* Norwegian */,
+  ["pl" /* Polish */]: "Polish" /* Polish */,
+  ["pt" /* Portuguese */]: "Portuguese" /* Portuguese */,
+  ["ru" /* Russian */]: "Russian" /* Russian */,
+  ["es" /* Spanish */]: "Spanish" /* Spanish */,
+  ["sv" /* Swedish */]: "Swedish" /* Swedish */,
+  ["th" /* Thai */]: "Thai" /* Thai */,
+  ["tr" /* Turkish */]: "Turkish" /* Turkish */,
+  ["vi" /* Vietnamese */]: "Vietnamese" /* Vietnamese */
+};
+const LANGUAGE_CODE_ALIASES = /* @__PURE__ */ new Map([
+  ["ar", "ar" /* Arabic */],
+  ["ara", "ar" /* Arabic */],
+  ["arabic", "ar" /* Arabic */],
+  ["da", "da" /* Danish */],
+  ["danish", "da" /* Danish */],
+  ["de", "de" /* German */],
+  ["deu", "de" /* German */],
+  ["dut", "nl" /* Dutch */],
+  ["dutch", "nl" /* Dutch */],
+  ["en", "en" /* English */],
+  ["eng", "en" /* English */],
+  ["english", "en" /* English */],
+  ["fi", "fi" /* Finnish */],
+  ["fin", "fi" /* Finnish */],
+  ["finnish", "fi" /* Finnish */],
+  ["fr", "fr" /* French */],
+  ["fra", "fr" /* French */],
+  ["fre", "fr" /* French */],
+  ["french", "fr" /* French */],
+  ["ger", "de" /* German */],
+  ["german", "de" /* German */],
+  ["hi", "hi" /* Hindi */],
+  ["hin", "hi" /* Hindi */],
+  ["hindi", "hi" /* Hindi */],
+  ["id", "id" /* Indonesian */],
+  ["ind", "id" /* Indonesian */],
+  ["indonesian", "id" /* Indonesian */],
+  ["it", "it" /* Italian */],
+  ["ita", "it" /* Italian */],
+  ["italian", "it" /* Italian */],
+  ["ja", "ja" /* Japanese */],
+  ["japanese", "ja" /* Japanese */],
+  ["jpn", "ja" /* Japanese */],
+  ["ko", "ko" /* Korean */],
+  ["kor", "ko" /* Korean */],
+  ["korean", "ko" /* Korean */],
+  ["nl", "nl" /* Dutch */],
+  ["no", "no" /* Norwegian */],
+  ["nor", "no" /* Norwegian */],
+  ["norwegian", "no" /* Norwegian */],
+  ["pl", "pl" /* Polish */],
+  ["pol", "pl" /* Polish */],
+  ["polish", "pl" /* Polish */],
+  ["por", "pt" /* Portuguese */],
+  ["portuguese", "pt" /* Portuguese */],
+  ["pt", "pt" /* Portuguese */],
+  ["ru", "ru" /* Russian */],
+  ["rus", "ru" /* Russian */],
+  ["russian", "ru" /* Russian */],
+  ["spa", "es" /* Spanish */],
+  ["spanish", "es" /* Spanish */],
+  ["es", "es" /* Spanish */],
+  ["sv", "sv" /* Swedish */],
+  ["swe", "sv" /* Swedish */],
+  ["swedish", "sv" /* Swedish */],
+  ["th", "th" /* Thai */],
+  ["tha", "th" /* Thai */],
+  ["thai", "th" /* Thai */],
+  ["tr", "tr" /* Turkish */],
+  ["tur", "tr" /* Turkish */],
+  ["turkish", "tr" /* Turkish */],
+  ["vi", "vi" /* Vietnamese */],
+  ["vie", "vi" /* Vietnamese */],
+  ["vietnamese", "vi" /* Vietnamese */],
+  ["zh", "zh" /* Chinese */],
+  ["zh-cn", "zh" /* Chinese */],
+  ["zh-hans", "zh" /* Chinese */],
+  ["zh-sg", "zh" /* Chinese */],
+  ["zh-tw", "zh" /* Chinese */],
+  ["zh-hant", "zh" /* Chinese */],
+  ["zh-hk", "zh" /* Chinese */],
+  ["cn", "zh" /* Chinese */],
+  ["chi", "zh" /* Chinese */],
+  ["chinese", "zh" /* Chinese */],
+  ["simplified chinese", "zh" /* Chinese */],
+  ["traditional chinese", "zh" /* Chinese */],
+  ["zho", "zh" /* Chinese */]
+]);
+function getLanguageCode(language) {
+  return LANGUAGE_TO_CODE[language];
+}
+function formatLanguageForPrompt(code) {
+  return LANGUAGE_CODE_TO_PROMPT_LANGUAGE[code];
+}
+function normalizeLanguageCode(language) {
+  const normalized = language?.trim().toLowerCase().replaceAll("_", "-");
+  if (normalized === void 0 || normalized === "") {
+    return void 0;
+  }
+  return LANGUAGE_CODE_ALIASES.get(normalized);
+}
+function getWikipageLanguageCode(language) {
+  const code = normalizeLanguageCode(language);
+  if (code === "en" /* English */ || code === "zh" /* Chinese */) {
+    return code;
+  }
+  return void 0;
+}
+export {
+  Language,
+  LanguageCode,
+  formatLanguageForPrompt,
+  getLanguageCode,
+  getWikipageLanguageCode,
+  normalizeLanguageCode
+};
+//# sourceMappingURL=language.js.map

package/dist/common/language.js.map

@@ -0,0 +1 @@
+{"version":3,"sources":["../../src/common/language.ts"],"sourcesContent":["export enum Language {\n  Arabic = \"Arabic\",\n  Danish = \"Danish\",\n  Dutch = \"Dutch\",\n  English = \"English\",\n  Finnish = \"Finnish\",\n  French = \"French\",\n  German = \"German\",\n  Hindi = \"Hindi\",\n  Indonesian = \"Indonesian\",\n  Italian = \"Italian\",\n  Japanese = \"Japanese\",\n  Korean = \"Korean\",\n  Norwegian = \"Norwegian\",\n  Polish = \"Polish\",\n  Portuguese = \"Portuguese\",\n  Russian = \"Russian\",\n  SimplifiedChinese = \"Simplified Chinese\",\n  Spanish = \"Spanish\",\n  Swedish = \"Swedish\",\n  Thai = \"Thai\",\n  TraditionalChinese = \"Traditional Chinese\",\n  Turkish = \"Turkish\",\n  Vietnamese = \"Vietnamese\",\n}\n\nexport enum LanguageCode {\n  Arabic = \"ar\",\n  Chinese = \"zh\",\n  Danish = \"da\",\n  Dutch = \"nl\",\n  English = \"en\",\n  Finnish = \"fi\",\n  French = \"fr\",\n  German = \"de\",\n  Hindi = \"hi\",\n  Indonesian = \"id\",\n  Italian = \"it\",\n  Japanese = \"ja\",\n  Korean = \"ko\",\n  Norwegian = \"no\",\n  Polish = \"pl\",\n  Portuguese = \"pt\",\n  Russian = \"ru\",\n  Spanish = \"es\",\n  Swedish = \"sv\",\n  Thai = \"th\",\n  Turkish = \"tr\",\n  Vietnamese = \"vi\",\n}\n\nconst LANGUAGE_TO_CODE = {\n  [Language.Arabic]: LanguageCode.Arabic,\n  [Language.Danish]: LanguageCode.Danish,\n  [Language.Dutch]: LanguageCode.Dutch,\n  [Language.English]: LanguageCode.English,\n  [Language.Finnish]: LanguageCode.Finnish,\n  [Language.French]: LanguageCode.French,\n  [Language.German]: LanguageCode.German,\n  [Language.Hindi]: LanguageCode.Hindi,\n  [Language.Indonesian]: LanguageCode.Indonesian,\n  [Language.Italian]: LanguageCode.Italian,\n  [Language.Japanese]: LanguageCode.Japanese,\n  [Language.Korean]: LanguageCode.Korean,\n  [Language.Norwegian]: LanguageCode.Norwegian,\n  [Language.Polish]: LanguageCode.Polish,\n  [Language.Portuguese]: LanguageCode.Portuguese,\n  [Language.Russian]: LanguageCode.Russian,\n  [Language.SimplifiedChinese]: LanguageCode.Chinese,\n  [Language.Spanish]: LanguageCode.Spanish,\n  [Language.Swedish]: LanguageCode.Swedish,\n  [Language.Thai]: LanguageCode.Thai,\n  [Language.TraditionalChinese]: LanguageCode.Chinese,\n  [Language.Turkish]: LanguageCode.Turkish,\n  [Language.Vietnamese]: LanguageCode.Vietnamese,\n} satisfies Record<Language, LanguageCode>;\n\nconst LANGUAGE_CODE_TO_PROMPT_LANGUAGE = {\n  [LanguageCode.Arabic]: Language.Arabic,\n  [LanguageCode.Chinese]: Language.SimplifiedChinese,\n  [LanguageCode.Danish]: Language.Danish,\n  [LanguageCode.Dutch]: Language.Dutch,\n  [LanguageCode.English]: Language.English,\n  [LanguageCode.Finnish]: Language.Finnish,\n  [LanguageCode.French]: Language.French,\n  [LanguageCode.German]: Language.German,\n  [LanguageCode.Hindi]: Language.Hindi,\n  [LanguageCode.Indonesian]: Language.Indonesian,\n  [LanguageCode.Italian]: Language.Italian,\n  [LanguageCode.Japanese]: Language.Japanese,\n  [LanguageCode.Korean]: Language.Korean,\n  [LanguageCode.Norwegian]: Language.Norwegian,\n  [LanguageCode.Polish]: Language.Polish,\n  [LanguageCode.Portuguese]: Language.Portuguese,\n  [LanguageCode.Russian]: Language.Russian,\n  [LanguageCode.Spanish]: Language.Spanish,\n  [LanguageCode.Swedish]: Language.Swedish,\n  [LanguageCode.Thai]: Language.Thai,\n  [LanguageCode.Turkish]: Language.Turkish,\n  [LanguageCode.Vietnamese]: Language.Vietnamese,\n} satisfies Record<LanguageCode, Language>;\n\nconst LANGUAGE_CODE_ALIASES = new Map<string, LanguageCode>([\n  [\"ar\", LanguageCode.Arabic],\n  [\"ara\", LanguageCode.Arabic],\n  [\"arabic\", LanguageCode.Arabic],\n  [\"da\", LanguageCode.Danish],\n  [\"danish\", LanguageCode.Danish],\n  [\"de\", LanguageCode.German],\n  [\"deu\", LanguageCode.German],\n  [\"dut\", LanguageCode.Dutch],\n  [\"dutch\", LanguageCode.Dutch],\n  [\"en\", LanguageCode.English],\n  [\"eng\", LanguageCode.English],\n  [\"english\", LanguageCode.English],\n  [\"fi\", LanguageCode.Finnish],\n  [\"fin\", LanguageCode.Finnish],\n  [\"finnish\", LanguageCode.Finnish],\n  [\"fr\", LanguageCode.French],\n  [\"fra\", LanguageCode.French],\n  [\"fre\", LanguageCode.French],\n  [\"french\", LanguageCode.French],\n  [\"ger\", LanguageCode.German],\n  [\"german\", LanguageCode.German],\n  [\"hi\", LanguageCode.Hindi],\n  [\"hin\", LanguageCode.Hindi],\n  [\"hindi\", LanguageCode.Hindi],\n  [\"id\", LanguageCode.Indonesian],\n  [\"ind\", LanguageCode.Indonesian],\n  [\"indonesian\", LanguageCode.Indonesian],\n  [\"it\", LanguageCode.Italian],\n  [\"ita\", LanguageCode.Italian],\n  [\"italian\", LanguageCode.Italian],\n  [\"ja\", LanguageCode.Japanese],\n  [\"japanese\", LanguageCode.Japanese],\n  [\"jpn\", LanguageCode.Japanese],\n  [\"ko\", LanguageCode.Korean],\n  [\"kor\", LanguageCode.Korean],\n  [\"korean\", LanguageCode.Korean],\n  [\"nl\", LanguageCode.Dutch],\n  [\"no\", LanguageCode.Norwegian],\n  [\"nor\", LanguageCode.Norwegian],\n  [\"norwegian\", LanguageCode.Norwegian],\n  [\"pl\", LanguageCode.Polish],\n  [\"pol\", LanguageCode.Polish],\n  [\"polish\", LanguageCode.Polish],\n  [\"por\", LanguageCode.Portuguese],\n  [\"portuguese\", LanguageCode.Portuguese],\n  [\"pt\", LanguageCode.Portuguese],\n  [\"ru\", LanguageCode.Russian],\n  [\"rus\", LanguageCode.Russian],\n  [\"russian\", LanguageCode.Russian],\n  [\"spa\", LanguageCode.Spanish],\n  [\"spanish\", LanguageCode.Spanish],\n  [\"es\", LanguageCode.Spanish],\n  [\"sv\", LanguageCode.Swedish],\n  [\"swe\", LanguageCode.Swedish],\n  [\"swedish\", LanguageCode.Swedish],\n  [\"th\", LanguageCode.Thai],\n  [\"tha\", LanguageCode.Thai],\n  [\"thai\", LanguageCode.Thai],\n  [\"tr\", LanguageCode.Turkish],\n  [\"tur\", LanguageCode.Turkish],\n  [\"turkish\", LanguageCode.Turkish],\n  [\"vi\", LanguageCode.Vietnamese],\n  [\"vie\", LanguageCode.Vietnamese],\n  [\"vietnamese\", LanguageCode.Vietnamese],\n  [\"zh\", LanguageCode.Chinese],\n  [\"zh-cn\", LanguageCode.Chinese],\n  [\"zh-hans\", LanguageCode.Chinese],\n  [\"zh-sg\", LanguageCode.Chinese],\n  [\"zh-tw\", LanguageCode.Chinese],\n  [\"zh-hant\", LanguageCode.Chinese],\n  [\"zh-hk\", LanguageCode.Chinese],\n  [\"cn\", LanguageCode.Chinese],\n  [\"chi\", LanguageCode.Chinese],\n  [\"chinese\", LanguageCode.Chinese],\n  [\"simplified chinese\", LanguageCode.Chinese],\n  [\"traditional chinese\", LanguageCode.Chinese],\n  [\"zho\", LanguageCode.Chinese],\n]);\n\nexport function getLanguageCode(language: Language): LanguageCode {\n  return LANGUAGE_TO_CODE[language];\n}\n\nexport function formatLanguageForPrompt(code: LanguageCode): Language {\n  return LANGUAGE_CODE_TO_PROMPT_LANGUAGE[code];\n}\n\nexport function normalizeLanguageCode(\n  language: Language | string | null | undefined,\n): LanguageCode | undefined {\n  const normalized = language?.trim().toLowerCase().replaceAll(\"_\", \"-\");\n\n  if (normalized === undefined || normalized === \"\") {\n    return undefined;\n  }\n\n  return LANGUAGE_CODE_ALIASES.get(normalized);\n}\n\nexport function getWikipageLanguageCode(\n  language: Language | string | null | undefined,\n): \"en\" | \"zh\" | undefined {\n  const code = normalizeLanguageCode(language);\n\n  if (code === LanguageCode.English || code === LanguageCode.Chinese) {\n    return code;\n  }\n\n  return undefined;\n}\n"],"mappings":"AAAO,IAAK,WAAL,kBAAKA,cAAL;AACL,EAAAA,UAAA,YAAS;AACT,EAAAA,UAAA,YAAS;AACT,EAAAA,UAAA,WAAQ;AACR,EAAAA,UAAA,aAAU;AACV,EAAAA,UAAA,aAAU;AACV,EAAAA,UAAA,YAAS;AACT,EAAAA,UAAA,YAAS;AACT,EAAAA,UAAA,WAAQ;AACR,EAAAA,UAAA,gBAAa;AACb,EAAAA,UAAA,aAAU;AACV,EAAAA,UAAA,cAAW;AACX,EAAAA,UAAA,YAAS;AACT,EAAAA,UAAA,eAAY;AACZ,EAAAA,UAAA,YAAS;AACT,EAAAA,UAAA,gBAAa;AACb,EAAAA,UAAA,aAAU;AACV,EAAAA,UAAA,uBAAoB;AACpB,EAAAA,UAAA,aAAU;AACV,EAAAA,UAAA,aAAU;AACV,EAAAA,UAAA,UAAO;AACP,EAAAA,UAAA,wBAAqB;AACrB,EAAAA,UAAA,aAAU;AACV,EAAAA,UAAA,gBAAa;AAvBH,SAAAA;AAAA,GAAA;AA0BL,IAAK,eAAL,kBAAKC,kBAAL;AACL,EAAAA,cAAA,YAAS;AACT,EAAAA,cAAA,aAAU;AACV,EAAAA,cAAA,YAAS;AACT,EAAAA,cAAA,WAAQ;AACR,EAAAA,cAAA,aAAU;AACV,EAAAA,cAAA,aAAU;AACV,EAAAA,cAAA,YAAS;AACT,EAAAA,cAAA,YAAS;AACT,EAAAA,cAAA,WAAQ;AACR,EAAAA,cAAA,gBAAa;AACb,EAAAA,cAAA,aAAU;AACV,EAAAA,cAAA,cAAW;AACX,EAAAA,cAAA,YAAS;AACT,EAAAA,cAAA,eAAY;AACZ,EAAAA,cAAA,YAAS;AACT,EAAAA,cAAA,gBAAa;AACb,EAAAA,cAAA,aAAU;AACV,EAAAA,cAAA,aAAU;AACV,EAAAA,cAAA,aAAU;AACV,EAAAA,cAAA,UAAO;AACP,EAAAA,cAAA,aAAU;AACV,EAAAA,cAAA,gBAAa;AAtBH,SAAAA;AAAA,GAAA;AAyBZ,MAAM,mBAAmB;AAAA,EACvB,CAAC,qBAAe,GAAG;AAAA,EACnB,CAAC,qBAAe,GAAG;AAAA,EACnB,CAAC,mBAAc,GAAG;AAAA,EAClB,CAAC,uBAAgB,GAAG;AAAA,EACpB,CAAC,uBAAgB,GAAG;AAAA,EACpB,CAAC,qBAAe,GAAG;AAAA,EACnB,CAAC,qBAAe,GAAG;AAAA,EACnB,CAAC,mBAAc,GAAG;AAAA,EAClB,CAAC,6BAAmB,GAAG;AAAA,EACvB,CAAC,uBAAgB,GAAG;AAAA,EACpB,CAAC,yBAAiB,GAAG;AAAA,EACrB,CAAC,qBAAe,GAAG;AAAA,EACnB,CAAC,2BAAkB,GAAG;AAAA,EACtB,CAAC,qBAAe,GAAG;AAAA,EACnB,CAAC,6BAAmB,GAAG;AAAA,EACvB,CAAC,uBAAgB,GAAG;AAAA,EACpB,CAAC,4CAA0B,GAAG;AAAA,EAC9B,CAAC,uBAAgB,GAAG;AAAA,EACpB,CAAC,uBAAgB,GAAG;AAAA,EACpB,CAAC,iBAAa,GAAG;AAAA,EACjB,CAAC,8CAA2B,GAAG;AAAA,EAC/B,CAAC,uBAAgB,GAAG;AAAA,EACpB,CAAC,6BAAmB,GAAG;AACzB;AAEA,MAAM,mCAAmC;AAAA,EACvC,CAAC,iBAAmB,GAAG;AAAA,EACvB,CAAC,kBAAoB,GAAG;AAAA,EACxB,CAAC,iBAAmB,GAAG;AAAA,EACvB,CAAC,gBAAkB,GAAG;AAAA,EACtB,CAAC,kBAAoB,GAAG;AAAA,EACxB,CAAC,kBAAoB,GAAG;AAAA,EACxB,CAAC,iBAAmB,GAAG;AAAA,EACvB,CAAC,iBAAmB,GAAG;AAAA,EACvB,CAAC,gBAAkB,GAAG;AAAA,EACtB,CAAC,qBAAuB,GAAG;AAAA,EAC3B,CAAC,kBAAoB,GAAG;AAAA,EACxB,CAAC,mBAAqB,GAAG;AAAA,EACzB,CAAC,iBAAmB,GAAG;AAAA,EACvB,CAAC,oBAAsB,GAAG;AAAA,EAC1B,CAAC,iBAAmB,GAAG;AAAA,EACvB,CAAC,qBAAuB,GAAG;AAAA,EAC3B,CAAC,kBAAoB,GAAG;AAAA,EACxB,CAAC,kBAAoB,GAAG;AAAA,EACxB,CAAC,kBAAoB,GAAG;AAAA,EACxB,CAAC,eAAiB,GAAG;AAAA,EACrB,CAAC,kBAAoB,GAAG;AAAA,EACxB,CAAC,qBAAuB,GAAG;AAC7B;AAEA,MAAM,wBAAwB,oBAAI,IAA0B;AAAA,EAC1D,CAAC,MAAM,iBAAmB;AAAA,EAC1B,CAAC,OAAO,iBAAmB;AAAA,EAC3B,CAAC,UAAU,iBAAmB;AAAA,EAC9B,CAAC,MAAM,iBAAmB;AAAA,EAC1B,CAAC,UAAU,iBAAmB;AAAA,EAC9B,CAAC,MAAM,iBAAmB;AAAA,EAC1B,CAAC,OAAO,iBAAmB;AAAA,EAC3B,CAAC,OAAO,gBAAkB;AAAA,EAC1B,CAAC,SAAS,gBAAkB;AAAA,EAC5B,CAAC,MAAM,kBAAoB;AAAA,EAC3B,CAAC,OAAO,kBAAoB;AAAA,EAC5B,CAAC,WAAW,kBAAoB;AAAA,EAChC,CAAC,MAAM,kBAAoB;AAAA,EAC3B,CAAC,OAAO,kBAAoB;AAAA,EAC5B,CAAC,WAAW,kBAAoB;AAAA,EAChC,CAAC,MAAM,iBAAmB;AAAA,EAC1B,CAAC,OAAO,iBAAmB;AAAA,EAC3B,CAAC,OAAO,iBAAmB;AAAA,EAC3B,CAAC,UAAU,iBAAmB;AAAA,EAC9B,CAAC,OAAO,iBAAmB;AAAA,EAC3B,CAAC,UAAU,iBAAmB;AAAA,EAC9B,CAAC,MAAM,gBAAkB;AAAA,EACzB,CAAC,OAAO,gBAAkB;AAAA,EAC1B,CAAC,SAAS,gBAAkB;AAAA,EAC5B,CAAC,MAAM,qBAAuB;AAAA,EAC9B,CAAC,OAAO,qBAAuB;AAAA,EAC/B,CAAC,cAAc,qBAAuB;AAAA,EACtC,CAAC,MAAM,kBAAoB;AAAA,EAC3B,CAAC,OAAO,kBAAoB;AAAA,EAC5B,CAAC,WAAW,kBAAoB;AAAA,EAChC,CAAC,MAAM,mBAAqB;AAAA,EAC5B,CAAC,YAAY,mBAAqB;AAAA,EAClC,CAAC,OAAO,mBAAqB;AAAA,EAC7B,CAAC,MAAM,iBAAmB;AAAA,EAC1B,CAAC,OAAO,iBAAmB;AAAA,EAC3B,CAAC,UAAU,iBAAmB;AAAA,EAC9B,CAAC,MAAM,gBAAkB;AAAA,EACzB,CAAC,MAAM,oBAAsB;AAAA,EAC7B,CAAC,OAAO,oBAAsB;AAAA,EAC9B,CAAC,aAAa,oBAAsB;AAAA,EACpC,CAAC,MAAM,iBAAmB;AAAA,EAC1B,CAAC,OAAO,iBAAmB;AAAA,EAC3B,CAAC,UAAU,iBAAmB;AAAA,EAC9B,CAAC,OAAO,qBAAuB;AAAA,EAC/B,CAAC,cAAc,qBAAuB;AAAA,EACtC,CAAC,MAAM,qBAAuB;AAAA,EAC9B,CAAC,MAAM,kBAAoB;AAAA,EAC3B,CAAC,OAAO,kBAAoB;AAAA,EAC5B,CAAC,WAAW,kBAAoB;AAAA,EAChC,CAAC,OAAO,kBAAoB;AAAA,EAC5B,CAAC,WAAW,kBAAoB;AAAA,EAChC,CAAC,MAAM,kBAAoB;AAAA,EAC3B,CAAC,MAAM,kBAAoB;AAAA,EAC3B,CAAC,OAAO,kBAAoB;AAAA,EAC5B,CAAC,WAAW,kBAAoB;AAAA,EAChC,CAAC,MAAM,eAAiB;AAAA,EACxB,CAAC,OAAO,eAAiB;AAAA,EACzB,CAAC,QAAQ,eAAiB;AAAA,EAC1B,CAAC,MAAM,kBAAoB;AAAA,EAC3B,CAAC,OAAO,kBAAoB;AAAA,EAC5B,CAAC,WAAW,kBAAoB;AAAA,EAChC,CAAC,MAAM,qBAAuB;AAAA,EAC9B,CAAC,OAAO,qBAAuB;AAAA,EAC/B,CAAC,cAAc,qBAAuB;AAAA,EACtC,CAAC,MAAM,kBAAoB;AAAA,EAC3B,CAAC,SAAS,kBAAoB;AAAA,EAC9B,CAAC,WAAW,kBAAoB;AAAA,EAChC,CAAC,SAAS,kBAAoB;AAAA,EAC9B,CAAC,SAAS,kBAAoB;AAAA,EAC9B,CAAC,WAAW,kBAAoB;AAAA,EAChC,CAAC,SAAS,kBAAoB;AAAA,EAC9B,CAAC,MAAM,kBAAoB;AAAA,EAC3B,CAAC,OAAO,kBAAoB;AAAA,EAC5B,CAAC,WAAW,kBAAoB;AAAA,EAChC,CAAC,sBAAsB,kBAAoB;AAAA,EAC3C,CAAC,uBAAuB,kBAAoB;AAAA,EAC5C,CAAC,OAAO,kBAAoB;AAC9B,CAAC;AAEM,SAAS,gBAAgB,UAAkC;AAChE,SAAO,iBAAiB,QAAQ;AAClC;AAEO,SAAS,wBAAwB,MAA8B;AACpE,SAAO,iCAAiC,IAAI;AAC9C;AAEO,SAAS,sBACd,UAC0B;AAC1B,QAAM,aAAa,UAAU,KAAK,EAAE,YAAY,EAAE,WAAW,KAAK,GAAG;AAErE,MAAI,eAAe,UAAa,eAAe,IAAI;AACjD,WAAO;AAAA,EACT;AAEA,SAAO,sBAAsB,IAAI,UAAU;AAC7C;AAEO,SAAS,wBACd,UACyB;AACzB,QAAM,OAAO,sBAAsB,QAAQ;AAE3C,MAAI,SAAS,sBAAwB,SAAS,oBAAsB;AAClE,WAAO;AAAA,EACT;AAEA,SAAO;AACT;","names":["Language","LanguageCode"]}

package/dist/common/llm-scope.d.ts

@@ -0,0 +1,19 @@
+declare enum WikiGraphScope {
+    EditorCompress = "serial-generation/editor-compress",
+    EditorReview = "serial-generation/editor-review",
+    EditorReviewGuide = "serial-generation/editor-review-guide",
+    ReaderChoice = "serial-generation/reader-choice",
+    ReaderExtraction = "serial-generation/reader-extraction"
+}
+declare const WIKI_GRAPH_SCOPES: readonly [WikiGraphScope.EditorCompress, WikiGraphScope.EditorReview, WikiGraphScope.EditorReviewGuide, WikiGraphScope.ReaderChoice, WikiGraphScope.ReaderExtraction];
+declare const WIKI_GRAPH_EDITOR_SCOPES: Readonly<{
+    compress: WikiGraphScope.EditorCompress;
+    review: WikiGraphScope.EditorReview;
+    reviewGuide: WikiGraphScope.EditorReviewGuide;
+}>;
+declare const WIKI_GRAPH_READER_SCOPES: Readonly<{
+    choice: WikiGraphScope.ReaderChoice;
+    extraction: WikiGraphScope.ReaderExtraction;
+}>;
+
+export { WIKI_GRAPH_EDITOR_SCOPES, WIKI_GRAPH_READER_SCOPES, WIKI_GRAPH_SCOPES, WikiGraphScope };