eyecite-ts 0.3.0 → 0.5.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (43) hide show
  1. package/README.md +179 -10
  2. package/dist/annotate/index.cjs +1 -1
  3. package/dist/annotate/index.cjs.map +1 -1
  4. package/dist/annotate/index.d.cts +14 -1
  5. package/dist/annotate/index.d.cts.map +1 -1
  6. package/dist/annotate/index.d.mts +14 -1
  7. package/dist/annotate/index.d.mts.map +1 -1
  8. package/dist/annotate/index.mjs +1 -1
  9. package/dist/annotate/index.mjs.map +1 -1
  10. package/dist/{citation-DAyM8kNA.d.mts → citation-25ZydLsu.d.mts} +78 -2
  11. package/dist/citation-25ZydLsu.d.mts.map +1 -0
  12. package/dist/{citation-qKSc_Myj.d.cts → citation-Cymq3pJ-.d.cts} +78 -2
  13. package/dist/citation-Cymq3pJ-.d.cts.map +1 -0
  14. package/dist/data/index.cjs +1 -1
  15. package/dist/data/index.cjs.map +1 -1
  16. package/dist/data/index.d.cts +91 -1
  17. package/dist/data/index.d.cts.map +1 -1
  18. package/dist/data/index.d.mts +91 -1
  19. package/dist/data/index.d.mts.map +1 -1
  20. package/dist/data/index.mjs +1 -1
  21. package/dist/data/index.mjs.map +1 -1
  22. package/dist/index.cjs +1 -1
  23. package/dist/index.cjs.map +1 -1
  24. package/dist/index.d.cts +4 -35
  25. package/dist/index.d.cts.map +1 -1
  26. package/dist/index.d.mts +4 -35
  27. package/dist/index.d.mts.map +1 -1
  28. package/dist/index.mjs +1 -1
  29. package/dist/index.mjs.map +1 -1
  30. package/dist/knownCodes-CI-vnoBO.cjs +2 -0
  31. package/dist/knownCodes-CI-vnoBO.cjs.map +1 -0
  32. package/dist/knownCodes-MkDSiR1j.mjs +2 -0
  33. package/dist/knownCodes-MkDSiR1j.mjs.map +1 -0
  34. package/dist/{reporters-DYNnh4O0.mjs → reporters-CZoC98-L.mjs} +1 -1
  35. package/dist/reporters-CZoC98-L.mjs.map +1 -0
  36. package/dist/reporters-Wob0oyD9.cjs +2 -0
  37. package/dist/reporters-Wob0oyD9.cjs.map +1 -0
  38. package/package.json +1 -1
  39. package/dist/citation-DAyM8kNA.d.mts.map +0 -1
  40. package/dist/citation-qKSc_Myj.d.cts.map +0 -1
  41. package/dist/reporters-BclWimmk.cjs +0 -2
  42. package/dist/reporters-BclWimmk.cjs.map +0 -1
  43. package/dist/reporters-DYNnh4O0.mjs.map +0 -1
@@ -95,12 +95,21 @@ interface FullCaseCitation extends CitationBase {
95
95
  type: "case";
96
96
  volume: number | string;
97
97
  reporter: string;
98
- page: number;
98
+ /** Page number — optional for blank page placeholder citations (e.g., "___" or "---") */
99
+ page?: number;
99
100
  pincite?: number;
100
101
  court?: string;
101
102
  year?: number;
102
103
  /** Normalized reporter abbreviation from reporters-db (e.g., "F.2d" vs "F. 2d") */
103
104
  normalizedReporter?: string;
105
+ /**
106
+ * Group identifier for parallel citations (same case in multiple reporters).
107
+ * Populated by Phase 8 (Parallel Linking).
108
+ * Format: ${volume}-${reporter}-${page} (e.g., "410-U.S.-113")
109
+ * All citations in the same parallel group share the same groupId.
110
+ * @example "410-U.S.-113" for parallel group [410 U.S. 113, 93 S. Ct. 705]
111
+ */
112
+ groupId?: string;
104
113
  /** Parallel citations for same case in different reporters */
105
114
  parallelCitations?: Array<{
106
115
  volume: number | string;
@@ -137,17 +146,84 @@ interface FullCaseCitation extends CitationBase {
137
146
  confidence: number;
138
147
  reason: string;
139
148
  }>;
149
+ /**
150
+ * Full span covering citation from case name through closing parenthetical.
151
+ * Populated by Phase 6 (Full Span extraction).
152
+ * @example For "Smith v. Doe, 500 F.2d 123 (2020)", fullSpan covers entire text.
153
+ */
154
+ fullSpan?: Span;
155
+ /**
156
+ * Extracted case name (party names around "v.").
157
+ * Populated by Phase 6 (Full Span extraction).
158
+ * @example "Smith v. Doe" or "United States v. Jones"
159
+ */
160
+ caseName?: string;
161
+ /**
162
+ * Plaintiff party name (text before "v." or procedural prefix).
163
+ * Populated by Phase 7 (Party Name extraction).
164
+ * @example "Smith" from "Smith v. Doe" or "Jones" from "In re Jones"
165
+ */
166
+ plaintiff?: string;
167
+ /**
168
+ * Defendant party name (text after "v.").
169
+ * Populated by Phase 7 (Party Name extraction).
170
+ * @example "Doe" from "Smith v. Doe"
171
+ */
172
+ defendant?: string;
173
+ /**
174
+ * Normalized plaintiff name for matching (lowercase, stripped of noise).
175
+ * Populated by Phase 7 (Party Name extraction).
176
+ * @example "smith" from "The Smith Corp., Inc."
177
+ */
178
+ plaintiffNormalized?: string;
179
+ /**
180
+ * Normalized defendant name for matching (lowercase, stripped of noise).
181
+ * Populated by Phase 7 (Party Name extraction).
182
+ * @example "doe" from "Doe et al."
183
+ */
184
+ defendantNormalized?: string;
185
+ /**
186
+ * Procedural prefix for non-adversarial cases.
187
+ * Populated by Phase 7 (Party Name extraction).
188
+ * @example "In re" from "In re Smith"
189
+ */
190
+ proceduralPrefix?: string;
191
+ /**
192
+ * True when page position contains a blank placeholder ("___" or "---").
193
+ * Populated by Phase 5 (Blank Page support).
194
+ * When true, page field will be undefined and confidence reduced to 0.8.
195
+ */
196
+ hasBlankPage?: boolean;
197
+ /**
198
+ * Disposition or procedural status from parenthetical.
199
+ * Populated by Phase 6 (Complex Parentheticals).
200
+ * @example "en banc", "per curiam"
201
+ */
202
+ disposition?: string;
140
203
  }
141
204
  /**
142
205
  * Statute citation (U.S. Code, state codes, etc.).
143
206
  *
144
207
  * @example "42 U.S.C. § 1983"
208
+ * @example "42 U.S.C. § 1983(a)(1) et seq."
145
209
  */
146
210
  interface StatuteCitation extends CitationBase {
147
211
  type: "statute";
148
212
  title?: number;
149
213
  code: string;
150
214
  section: string;
215
+ /** Subsection/pincite chain, e.g. "(a)(1)(A)" */
216
+ subsection?: string;
217
+ /** 2-letter state code or "US" when unambiguously identified */
218
+ jurisdiction?: string;
219
+ /**
220
+ * Alias for subsection (eyecite-ts convention).
221
+ * Note: this is string (subsection chain), unlike FullCaseCitation.pincite which is number (page offset).
222
+ * The discriminated union on `type` ensures type safety at call sites.
223
+ */
224
+ pincite?: string;
225
+ /** True when "et seq." follows the citation */
226
+ hasEtSeq?: boolean;
151
227
  }
152
228
  /**
153
229
  * Journal citation (law review, legal periodical).
@@ -323,4 +399,4 @@ type CitationOfType<T extends CitationType> = Extract<Citation, {
323
399
  type ExtractorMap = { [K in FullCitationType]: CitationOfType<K> };
324
400
  //#endregion
325
401
  export { TransformationMap as S, StatuteCitation as _, ExtractorMap as a, Warning as b, FullCitation as c, JournalCitation as d, NeutralCitation as f, ShortFormCitationType as g, ShortFormCitation as h, CitationType as i, FullCitationType as l, ShortFormCaseCitation as m, CitationBase as n, FederalRegisterCitation as o, PublicLawCitation as p, CitationOfType as r, FullCaseCitation as s, Citation as t, IdCitation as u, StatutesAtLargeCitation as v, Span as x, SupraCitation as y };
326
- //# sourceMappingURL=citation-qKSc_Myj.d.cts.map
402
+ //# sourceMappingURL=citation-Cymq3pJ-.d.cts.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"citation-Cymq3pJ-.d.cts","names":[],"sources":["../src/types/span.ts","../src/types/citation.ts"],"mappings":";;AAiBA;;;;;;;;;;AAoBA;;;;;;UApBiB,IAAA;;EAEf,UAAA;EAuBiB;EApBjB,QAAA;;EAGA,aAAA;ECpBF;EDuBE,WAAA;AAAA;;;AClBF;;;;UD2BiB,iBAAA;;EAEf,eAAA,EAAiB,GAAA;;EAGjB,eAAA,EAAiB,GAAA;AAAA;;;AAzBnB;;;AAAA,KCZY,YAAA;;;;UAKK,OAAA;;EAEf,KAAA;EDyBF;ECvBE,OAAA;;EAEA,QAAA;IAAY,KAAA;IAAe,GAAA;EAAA;;EAE3B,OAAA;AAAA;;;;UAMe,YAAA;EAnBL;EAqBV,IAAA;EArBU;EAwBV,IAAA,EAAM,IAAA;EAnBR;;;;;;;EA4BE,UAAA;;EAGA,WAAA;;EAGA,aAAA;EApBF;EAuBE,eAAA;;EAGA,QAAA,GAAW,OAAA;AAAA;;;;;;;UASI,gBAAA,SAAyB,YAAA;EACxC,IAAA;EACA,MAAA;EACA,QAAA;EAHF;EAKE,IAAA;EACA,OAAA;EACA,KAAA;EACA,IAAA;;EAGA,kBAAA;;;;;;;;EASA,OAAA;;EAGA,iBAAA,GAAoB,KAAA;IAClB,MAAA;IACA,QAAA;IACA,IAAA;EAAA;;EAIF,MAAA;;EAGA,aAAA;;EAGA,iBAAA;;;;;;EAOA,IAAA;IACE,GAAA;IACA,MAAA;MAAW,IAAA;MAAc,KAAA;MAAgB,GAAA;IAAA;EAAA;;;;;EAO3C,uBAAA,GAA0B,KAAA;IACxB,MAAA;IACA,QAAA;IACA,IAAA;IACA,UAAA;IACA,MAAA;EAAA;EAgEF;AASF;;;;EAjEE,QAAA,GAAW,IAAA;;;;;;EAOX,QAAA;;;;;AAqFF;EA9EE,SAAA;;;;;;EAOA,SAAA;;;;;;EAOA,mBAAA;;;AA4FF;;;EArFE,mBAAA;;;;;;EAOA,gBAAA;EAqFA;AAWF;;;;EAzFE,YAAA;;;;;;EAOA,WAAA;AAAA;;;;;;;UASe,eAAA,SAAwB,YAAA;EACvC,IAAA;EACA,KAAA;EACA,IAAA;EACA,OAAA;EAkGe;EAhGf,UAAA;EAgG+C;EA9F/C,YAAA;;;;;;EAMA,OAAA;EAwGF;EAtGE,QAAA;AAAA;;;;;;;AAiHF;;UAtGiB,eAAA,SAAwB,YAAA;EACvC,IAAA;;EAEA,MAAA;;EAEA,KAAA;;EAEA,MAAA;EA6GF;EA3GE,OAAA;;EAEA,YAAA;;EAEA,IAAA;;EAEA,OAAA;;EAEA,IAAA;AAAA;;AA4HF;;;;;;;UAjHiB,eAAA,SAAwB,YAAA;EACvC,IAAA;;EAEA,IAAA;;EAEA,KAAA;;EAEA,cAAA;AAAA;;;;;;;;;UAWe,iBAAA,SAA0B,YAAA;EACzC,IAAA;EAwGE;EAtGF,QAAA;EA2GU;EAzGV,SAAA;EAyGU;EAvGV,KAAA;AAAA;;;;;AA6GF;;;;UAlGiB,uBAAA,SAAgC,YAAA;EAC/C,IAAA;;EAEA,MAAA;;EAEA,IAAA;;EAEA,IAAA;AAAA;;UAIe,uBAAA,SAAgC,YAAA;EAC/C,IAAA;;EAEA,MAAA;;EAEA,IAAA;EAkFgJ;EAhFhJ,IAAA;AAAA;;;;;;;UASe,UAAA,SAAmB,YAAA;EAClC,IAAA;EACA,OAAA;AAAA;;AAqFF;;;;;UA5EiB,aAAA,SAAsB,YAAA;EACrC,IAAA;;EAEA,SAAA;;EAEA,OAAA;AAAA;;;;;;AA6EF;UApEiB,qBAAA,SAA8B,YAAA;EAC7C,IAAA;EACA,MAAA;EACA,QAAA;EACA,IAAA;EACA,OAAA;AAAA;;;;;;;;;;;;;;;;;;KAoBU,QAAA,GACR,gBAAA,GACA,eAAA,GACA,eAAA,GACA,eAAA,GACA,iBAAA,GACA,uBAAA,GACA,uBAAA,GACA,UAAA,GACA,aAAA,GACA,qBAAA;;;;KAKQ,gBAAA;AAAA,KACA,qBAAA;;;;KAKA,YAAA,GAAe,gBAAA,GAAmB,eAAA,GAAkB,eAAA,GAAkB,eAAA,GAAkB,iBAAA,GAAoB,uBAAA,GAA0B,uBAAA;;;;KAKtI,iBAAA,GAAoB,UAAA,GAAa,aAAA,GAAgB,qBAAA;;;;;;;;;;KAWjD,cAAA,WAAyB,YAAA,IAAgB,OAAA,CAAQ,QAAA;EAAY,IAAA,EAAM,CAAA;AAAA;;;;;KAMnE,YAAA,WACJ,gBAAA,GAAmB,cAAA,CAAe,CAAA"}
@@ -1,2 +1,2 @@
1
- Object.defineProperty(exports,Symbol.toStringTag,{value:`Module`});let e=null;async function t(){if(e)return e;let t=await import(`../../data/reporters.json`,{assert:{type:`json`}}),n=new Map,r=[],i=t.default||t;for(let[e,t]of Object.entries(i))for(let e of t){r.push(e);for(let t of Object.keys(e.editions)){let r=t.toLowerCase();n.has(r)||n.set(r,[]),n.get(r)?.push(e)}for(let[t,r]of Object.entries(e.variations||{})){let r=t.toLowerCase();n.has(r)||n.set(r,[]),n.get(r)?.push(e)}}return e={byAbbreviation:n,all:r},e}function n(){return e}async function r(e){return(await t()).byAbbreviation.get(e.toLowerCase())??[]}exports.findReportersByAbbreviation=r,exports.getReportersSync=n,exports.loadReporters=t;
1
+ Object.defineProperty(exports,Symbol.toStringTag,{value:`Module`});const e=require(`../knownCodes-CI-vnoBO.cjs`);let t=null;async function n(){if(t)return t;let e=await import(`../../data/reporters.json`,{assert:{type:`json`}}),n=new Map,r=[],i=e.default||e;for(let[e,t]of Object.entries(i))for(let e of t){r.push(e);for(let t of Object.keys(e.editions)){let r=t.toLowerCase();n.has(r)||n.set(r,[]),n.get(r)?.push(e)}for(let[t,r]of Object.entries(e.variations||{})){let r=t.toLowerCase();n.has(r)||n.set(r,[]),n.get(r)?.push(e)}}return t={byAbbreviation:n,all:r},t}function r(){return t}async function i(e){return(await n()).byAbbreviation.get(e.toLowerCase())??[]}exports.abbreviatedCodes=e.t,exports.findAbbreviatedCode=e.n,exports.findNamedCode=e.r,exports.findReportersByAbbreviation=i,exports.getReportersSync=r,exports.loadReporters=n,exports.namedCodes=e.i;
2
2
  //# sourceMappingURL=index.cjs.map
@@ -1 +1 @@
1
- {"version":3,"file":"index.cjs","names":[],"sources":["../../src/data/reporters.ts"],"sourcesContent":["/**\n * Reporter database integration for citation validation\n *\n * This module provides lazy-loadable access to the reporters-db database,\n * containing 1200+ court reporters with variant forms. The library works\n * in degraded mode (pattern-based extraction only) if reporters are not loaded.\n *\n * @example\n * // Degraded mode: extraction works without reporter data\n * const citations = await extract(text)\n *\n * @example\n * // Full mode: load reporters for validation\n * await loadReporters()\n * const citations = await extract(text) // Now with reporter validation\n */\n\n/**\n * Edition entry from reporters-db\n *\n * Represents a specific edition of a reporter with start/end dates.\n */\nexport interface ReporterEdition {\n /** Start date in ISO 8601 format */\n start: string | null\n /** End date in ISO 8601 format (null if ongoing) */\n end: string | null\n}\n\n/**\n * Reporter entry from reporters-db\n *\n * Represents a single court reporter with all metadata needed for\n * citation validation and enrichment.\n *\n * Note: The reporters-db structure has the actual data; this interface\n * represents it flexibly to handle all variations in the JSON.\n */\nexport interface ReporterEntry {\n /** Full reporter name (e.g., \"Federal Reporter\") */\n name: string\n /** Citation type: state, federal, specialty, neutral, state_regional, etc. */\n cite_type: string\n /** Editions keyed by abbreviation (e.g., {\"F.2d\": {...}, \"F.3d\": {...}}) */\n editions: Record<string, ReporterEdition>\n /** Variant forms mapped to canonical form (e.g., {\"F. 2d\": \"F.2d\"}) */\n variations?: Record<string, string | undefined>\n /** MLZ jurisdiction identifiers (optional) */\n mlz_jurisdiction?: string[]\n /** Publisher (optional) */\n publisher?: string\n /** Notes (optional) */\n notes?: string\n}\n\n/**\n * In-memory reporter database with fast O(1) lookup\n *\n * Uses Map-based indexing for case-insensitive abbreviation lookup.\n * All variant forms are indexed to support fuzzy matching.\n */\nexport interface ReportersDatabase {\n /** Fast O(1) lookup by abbreviation (lowercase normalized keys) */\n byAbbreviation: Map<string, ReporterEntry[]>\n /** All reporters (for iteration/filtering) */\n all: ReporterEntry[]\n}\n\n/**\n * Cached database instance (null until loadReporters() called)\n */\nlet cached: ReportersDatabase | null = null\n\n/**\n * Load reporter database asynchronously with lazy loading\n *\n * Dynamic import prevents loading 1200+ reporters until explicitly requested.\n * Result is cached after first load for subsequent calls.\n *\n * @returns Promise resolving to indexed reporter database\n *\n * @example\n * const db = await loadReporters()\n * const reporters = db.byAbbreviation.get('f.2d') // Fast O(1) lookup\n */\nexport async function loadReporters(): Promise<ReportersDatabase> {\n if (cached) return cached\n\n // Dynamic import prevents loading until requested (keeps core bundle small)\n const data = await import(\"../../data/reporters.json\", {\n assert: { type: \"json\" },\n })\n\n const byAbbreviation = new Map<string, ReporterEntry[]>()\n const all: ReporterEntry[] = []\n\n // reporters.json structure: { \"A.\": [...], \"F.2d\": [...], ... }\n const reportersData = (data.default || data) as Record<\n string,\n ReporterEntry[]\n >\n\n // Build fast lookup index with lowercase normalization\n for (const [_canonicalAbbr, reporters] of Object.entries(reportersData)) {\n for (const reporter of reporters) {\n all.push(reporter)\n\n // Index by all edition abbreviations\n for (const editionAbbr of Object.keys(reporter.editions)) {\n const key = editionAbbr.toLowerCase()\n if (!byAbbreviation.has(key)) {\n byAbbreviation.set(key, [])\n }\n byAbbreviation.get(key)?.push(reporter)\n }\n\n // Index all variations for fuzzy matching\n for (const [variant, _canonical] of Object.entries(\n reporter.variations || {},\n )) {\n const variantKey = variant.toLowerCase()\n if (!byAbbreviation.has(variantKey)) {\n byAbbreviation.set(variantKey, [])\n }\n byAbbreviation.get(variantKey)?.push(reporter)\n }\n }\n }\n\n cached = {\n byAbbreviation,\n all,\n }\n return cached\n}\n\n/**\n * Get cached reporter database synchronously (degraded mode support)\n *\n * Returns null if reporters not loaded yet. This enables the library to\n * work in degraded mode without reporter validation.\n *\n * @returns Cached database or null if not loaded\n *\n * @example\n * const db = getReportersSync()\n * if (db) {\n * // Full mode: validate citations\n * } else {\n * // Degraded mode: extract without validation\n * }\n */\nexport function getReportersSync(): ReportersDatabase | null {\n return cached\n}\n\n/**\n * Find reporters by abbreviation (case-insensitive)\n *\n * Loads reporter database if not already loaded. Returns all reporters\n * matching the abbreviation (including variant forms).\n *\n * @param abbr - Reporter abbreviation to look up\n * @returns Promise resolving to matching reporters (empty array if none)\n *\n * @example\n * const reporters = await findReportersByAbbreviation('F.2d')\n * // [{ abbreviation: 'F.2d', name: 'Federal Reporter, Second Series', ... }]\n *\n * @example\n * const unknown = await findReportersByAbbreviation('NONEXISTENT')\n * // [] (empty array, not error)\n */\nexport async function findReportersByAbbreviation(\n abbr: string,\n): Promise<ReporterEntry[]> {\n const db = await loadReporters()\n return db.byAbbreviation.get(abbr.toLowerCase()) ?? []\n}\n"],"mappings":"mEAuEA,IAAI,EAAmC,KAcvC,eAAsB,GAA4C,CAChE,GAAI,EAAQ,OAAO,EAGnB,IAAM,EAAO,MAAM,OAAO,4BAA6B,CACrD,OAAQ,CAAE,KAAM,OAAQ,CACzB,EAEK,EAAiB,IAAI,IACrB,EAAuB,EAAE,CAGzB,EAAiB,EAAK,SAAW,EAMvC,IAAK,GAAM,CAAC,EAAgB,KAAc,OAAO,QAAQ,EAAc,CACrE,IAAK,IAAM,KAAY,EAAW,CAChC,EAAI,KAAK,EAAS,CAGlB,IAAK,IAAM,KAAe,OAAO,KAAK,EAAS,SAAS,CAAE,CACxD,IAAM,EAAM,EAAY,aAAa,CAChC,EAAe,IAAI,EAAI,EAC1B,EAAe,IAAI,EAAK,EAAE,CAAC,CAE7B,EAAe,IAAI,EAAI,EAAE,KAAK,EAAS,CAIzC,IAAK,GAAM,CAAC,EAAS,KAAe,OAAO,QACzC,EAAS,YAAc,EAAE,CAC1B,CAAE,CACD,IAAM,EAAa,EAAQ,aAAa,CACnC,EAAe,IAAI,EAAW,EACjC,EAAe,IAAI,EAAY,EAAE,CAAC,CAEpC,EAAe,IAAI,EAAW,EAAE,KAAK,EAAS,EASpD,MAJA,GAAS,CACP,iBACA,MACD,CACM,EAmBT,SAAgB,GAA6C,CAC3D,OAAO,EAoBT,eAAsB,EACpB,EAC0B,CAE1B,OADW,MAAM,GAAe,EACtB,eAAe,IAAI,EAAK,aAAa,CAAC,EAAI,EAAE"}
1
+ {"version":3,"file":"index.cjs","names":[],"sources":["../../src/data/reporters.ts"],"sourcesContent":["/**\n * Reporter database integration for citation validation\n *\n * This module provides lazy-loadable access to the reporters-db database,\n * containing 1200+ court reporters with variant forms. The library works\n * in degraded mode (pattern-based extraction only) if reporters are not loaded.\n *\n * @example\n * // Degraded mode: extraction works without reporter data\n * const citations = await extract(text)\n *\n * @example\n * // Full mode: load reporters for validation\n * await loadReporters()\n * const citations = await extract(text) // Now with reporter validation\n */\n\n/**\n * Edition entry from reporters-db\n *\n * Represents a specific edition of a reporter with start/end dates.\n */\nexport interface ReporterEdition {\n /** Start date in ISO 8601 format */\n start: string | null\n /** End date in ISO 8601 format (null if ongoing) */\n end: string | null\n}\n\n/**\n * Reporter entry from reporters-db\n *\n * Represents a single court reporter with all metadata needed for\n * citation validation and enrichment.\n *\n * Note: The reporters-db structure has the actual data; this interface\n * represents it flexibly to handle all variations in the JSON.\n */\nexport interface ReporterEntry {\n /** Full reporter name (e.g., \"Federal Reporter\") */\n name: string\n /** Citation type: state, federal, specialty, neutral, state_regional, etc. */\n cite_type: string\n /** Editions keyed by abbreviation (e.g., {\"F.2d\": {...}, \"F.3d\": {...}}) */\n editions: Record<string, ReporterEdition>\n /** Variant forms mapped to canonical form (e.g., {\"F. 2d\": \"F.2d\"}) */\n variations?: Record<string, string | undefined>\n /** MLZ jurisdiction identifiers (optional) */\n mlz_jurisdiction?: string[]\n /** Publisher (optional) */\n publisher?: string\n /** Notes (optional) */\n notes?: string\n}\n\n/**\n * In-memory reporter database with fast O(1) lookup\n *\n * Uses Map-based indexing for case-insensitive abbreviation lookup.\n * All variant forms are indexed to support fuzzy matching.\n */\nexport interface ReportersDatabase {\n /** Fast O(1) lookup by abbreviation (lowercase normalized keys) */\n byAbbreviation: Map<string, ReporterEntry[]>\n /** All reporters (for iteration/filtering) */\n all: ReporterEntry[]\n}\n\n/**\n * Cached database instance (null until loadReporters() called)\n */\nlet cached: ReportersDatabase | null = null\n\n/**\n * Load reporter database asynchronously with lazy loading\n *\n * Dynamic import prevents loading 1200+ reporters until explicitly requested.\n * Result is cached after first load for subsequent calls.\n *\n * @returns Promise resolving to indexed reporter database\n *\n * @example\n * const db = await loadReporters()\n * const reporters = db.byAbbreviation.get('f.2d') // Fast O(1) lookup\n */\nexport async function loadReporters(): Promise<ReportersDatabase> {\n if (cached) return cached\n\n // Dynamic import prevents loading until requested (keeps core bundle small)\n const data = await import(\"../../data/reporters.json\", {\n assert: { type: \"json\" },\n })\n\n const byAbbreviation = new Map<string, ReporterEntry[]>()\n const all: ReporterEntry[] = []\n\n // reporters.json structure: { \"A.\": [...], \"F.2d\": [...], ... }\n const reportersData = (data.default || data) as Record<\n string,\n ReporterEntry[]\n >\n\n // Build fast lookup index with lowercase normalization\n for (const [_canonicalAbbr, reporters] of Object.entries(reportersData)) {\n for (const reporter of reporters) {\n all.push(reporter)\n\n // Index by all edition abbreviations\n for (const editionAbbr of Object.keys(reporter.editions)) {\n const key = editionAbbr.toLowerCase()\n if (!byAbbreviation.has(key)) {\n byAbbreviation.set(key, [])\n }\n byAbbreviation.get(key)?.push(reporter)\n }\n\n // Index all variations for fuzzy matching\n for (const [variant, _canonical] of Object.entries(\n reporter.variations || {},\n )) {\n const variantKey = variant.toLowerCase()\n if (!byAbbreviation.has(variantKey)) {\n byAbbreviation.set(variantKey, [])\n }\n byAbbreviation.get(variantKey)?.push(reporter)\n }\n }\n }\n\n cached = {\n byAbbreviation,\n all,\n }\n return cached\n}\n\n/**\n * Get cached reporter database synchronously (degraded mode support)\n *\n * Returns null if reporters not loaded yet. This enables the library to\n * work in degraded mode without reporter validation.\n *\n * @returns Cached database or null if not loaded\n *\n * @example\n * const db = getReportersSync()\n * if (db) {\n * // Full mode: validate citations\n * } else {\n * // Degraded mode: extract without validation\n * }\n */\nexport function getReportersSync(): ReportersDatabase | null {\n return cached\n}\n\n/**\n * Find reporters by abbreviation (case-insensitive)\n *\n * Loads reporter database if not already loaded. Returns all reporters\n * matching the abbreviation (including variant forms).\n *\n * @param abbr - Reporter abbreviation to look up\n * @returns Promise resolving to matching reporters (empty array if none)\n *\n * @example\n * const reporters = await findReportersByAbbreviation('F.2d')\n * // [{ abbreviation: 'F.2d', name: 'Federal Reporter, Second Series', ... }]\n *\n * @example\n * const unknown = await findReportersByAbbreviation('NONEXISTENT')\n * // [] (empty array, not error)\n */\nexport async function findReportersByAbbreviation(\n abbr: string,\n): Promise<ReporterEntry[]> {\n const db = await loadReporters()\n return db.byAbbreviation.get(abbr.toLowerCase()) ?? []\n}\n"],"mappings":"iHAuEA,IAAI,EAAmC,KAcvC,eAAsB,GAA4C,CAChE,GAAI,EAAQ,OAAO,EAGnB,IAAM,EAAO,MAAM,OAAO,4BAA6B,CACrD,OAAQ,CAAE,KAAM,OAAQ,CACzB,EAEK,EAAiB,IAAI,IACrB,EAAuB,EAAE,CAGzB,EAAiB,EAAK,SAAW,EAMvC,IAAK,GAAM,CAAC,EAAgB,KAAc,OAAO,QAAQ,EAAc,CACrE,IAAK,IAAM,KAAY,EAAW,CAChC,EAAI,KAAK,EAAS,CAGlB,IAAK,IAAM,KAAe,OAAO,KAAK,EAAS,SAAS,CAAE,CACxD,IAAM,EAAM,EAAY,aAAa,CAChC,EAAe,IAAI,EAAI,EAC1B,EAAe,IAAI,EAAK,EAAE,CAAC,CAE7B,EAAe,IAAI,EAAI,EAAE,KAAK,EAAS,CAIzC,IAAK,GAAM,CAAC,EAAS,KAAe,OAAO,QACzC,EAAS,YAAc,EAAE,CAC1B,CAAE,CACD,IAAM,EAAa,EAAQ,aAAa,CACnC,EAAe,IAAI,EAAW,EACjC,EAAe,IAAI,EAAY,EAAE,CAAC,CAEpC,EAAe,IAAI,EAAW,EAAE,KAAK,EAAS,EASpD,MAJA,GAAS,CACP,iBACA,MACD,CACM,EAmBT,SAAgB,GAA6C,CAC3D,OAAO,EAoBT,eAAsB,EACpB,EAC0B,CAE1B,OADW,MAAM,GAAe,EACtB,eAAe,IAAI,EAAK,aAAa,CAAC,EAAI,EAAE"}
@@ -112,5 +112,95 @@ declare function getReportersSync(): ReportersDatabase | null;
112
112
  */
113
113
  declare function findReportersByAbbreviation(abbr: string): Promise<ReporterEntry[]>;
114
114
  //#endregion
115
- export { ReporterEdition, ReporterEntry, ReportersDatabase, findReportersByAbbreviation, getReportersSync, loadReporters };
115
+ //#region src/data/knownCodes.d.ts
116
+ /**
117
+ * Known statutory code registry for abbreviated-code jurisdictions
118
+ *
119
+ * Provides a registry of state statutory codes that use abbreviated
120
+ * citation forms (e.g., "R.C. § 1.01", "MCL 750.83"). Used by the
121
+ * citation extractor to identify and normalize state statute citations.
122
+ */
123
+ /**
124
+ * A single entry in the known codes registry.
125
+ *
126
+ * PA has two entries (Pa.C.S. and P.S.) because it has two distinct
127
+ * code families with separate abbreviation sets.
128
+ */
129
+ interface CodeEntry {
130
+ /** Two-letter state abbreviation (e.g., "OH", "MI") */
131
+ jurisdiction: string;
132
+ /** Short canonical abbreviation used internally (e.g., "RC", "MCL") */
133
+ abbreviation: string;
134
+ /** All recognized text patterns that identify this code */
135
+ patterns: string[];
136
+ /** Citation family — determines which citation pattern family this belongs to */
137
+ family: "federal" | "named" | "abbreviated" | "chapterAct" | "prose";
138
+ }
139
+ /**
140
+ * Registry of state statutory codes that use abbreviated citation forms.
141
+ *
142
+ * Covers 12 jurisdictions. Pennsylvania has two entries because it
143
+ * maintains two distinct code families (Pa.C.S. and P.S.).
144
+ *
145
+ * Note: Short 2-letter patterns (GS, IC, PS, RC, FS) may produce false positives
146
+ * in non-legal text (e.g., "GS 5" for government service grade). The extraction
147
+ * layer mitigates this via confidence scoring — citations without a § symbol receive
148
+ * lower confidence (0.85 vs 0.95). Consumers should filter by confidence threshold.
149
+ */
150
+ declare const abbreviatedCodes: CodeEntry[];
151
+ /**
152
+ * Registry of state statutory codes that use named-code citation forms.
153
+ *
154
+ * Named-code jurisdictions identify their code by name in citations (e.g.,
155
+ * "N.Y. Penal Law § 120.05", "Cal. Civ. Proc. Code § 437c"), rather than by
156
+ * a standalone abbreviation. The jurisdiction prefix is handled by the
157
+ * extraction layer; these patterns cover only the code name portion.
158
+ *
159
+ * Ordering note: within each jurisdiction, more specific patterns must come
160
+ * before more general ones (e.g., "Civ. Proc." before "Civ.") so that
161
+ * findNamedCode's longest-match wins correctly.
162
+ *
163
+ * Covers 7 jurisdictions: NY (21 entries), CA (29 entries), TX (29 entries),
164
+ * MD (36 entries), VA (1 entry), AL (1 entry), MA (1 entry).
165
+ */
166
+ declare const namedCodes: CodeEntry[];
167
+ /**
168
+ * Find a CodeEntry by jurisdiction and code name token.
169
+ *
170
+ * Lookup strategy: for each candidate entry in the given jurisdiction,
171
+ * check whether the normalized codeName matches or starts with any of the
172
+ * entry's patterns (case-insensitive). Returns the entry with the longest
173
+ * matching pattern to prefer more specific codes over general ones
174
+ * (e.g., "Civ. Proc." over "Civ.").
175
+ *
176
+ * @param jurisdiction - Two-letter state abbreviation (e.g., "CA", "NY")
177
+ * @param codeName - The code name token to look up (e.g., "Penal", "Civ. Proc.")
178
+ * @returns Matching CodeEntry, or undefined if not found
179
+ *
180
+ * @example
181
+ * findNamedCode('NY', 'Penal') // → NY PEN entry
182
+ * findNamedCode('CA', 'Civ. Proc.') // → CA CCP entry (not CA CIV)
183
+ * findNamedCode('MD', 'Crim. Law') // → MD gcr entry
184
+ * findNamedCode('NY', 'Unknown') // → undefined
185
+ */
186
+ declare function findNamedCode(jurisdiction: string, codeName: string): CodeEntry | undefined;
187
+ /**
188
+ * Find a CodeEntry by an abbreviated text token.
189
+ *
190
+ * Lookup order:
191
+ * 1. Exact case-insensitive match against all patterns
192
+ * 2. Prefix match — returns the entry whose pattern is the longest
193
+ * prefix of `abbrevText` (handles tokens like "RCW" inside longer text)
194
+ *
195
+ * @param abbrevText - The abbreviation token to look up
196
+ * @returns Matching CodeEntry, or undefined if not found
197
+ *
198
+ * @example
199
+ * findAbbreviatedCode('R.C.') // → OH entry
200
+ * findAbbreviatedCode('MCL') // → MI entry
201
+ * findAbbreviatedCode('UNKNOWN') // → undefined
202
+ */
203
+ declare function findAbbreviatedCode(abbrevText: string): CodeEntry | undefined;
204
+ //#endregion
205
+ export { CodeEntry, ReporterEdition, ReporterEntry, ReportersDatabase, abbreviatedCodes, findAbbreviatedCode, findNamedCode, findReportersByAbbreviation, getReportersSync, loadReporters, namedCodes };
116
206
  //# sourceMappingURL=index.d.cts.map
@@ -1 +1 @@
1
- {"version":3,"file":"index.d.cts","names":[],"sources":["../../src/data/reporters.ts"],"mappings":";;AAsBA;;;;;AAgBA;;;;;;;;;;;;;;;UAhBiB,eAAA;;EAEf,KAAA;;EAEA,GAAA;AAAA;;;;;;;;;;UAYe,aAAA;;EAEf,IAAA;;EAEA,SAAA;EA2CF;EAzCE,QAAA,EAAU,MAAA,SAAe,eAAA;;EAEzB,UAAA,GAAa,MAAA;EAuCgC;EArC7C,gBAAA;EAwGc;EAtGd,SAAA;EAsGkC;EApGlC,KAAA;AAAA;;;;;;;UASe,iBAAA;EAkHN;EAhHT,cAAA,EAAgB,GAAA,SAAY,aAAA;;EAE5B,GAAA,EAAK,aAAA;AAAA;;;;;;;;;;;;;iBAoBe,aAAA,CAAA,GAAiB,OAAA,CAAQ,iBAAA;;;;;;;;;;;;;;;;;iBAmE/B,gBAAA,CAAA,GAAoB,iBAAA;;;;;;;;;;;;;;;;;;iBAqBd,2BAAA,CACpB,IAAA,WACC,OAAA,CAAQ,aAAA"}
1
+ {"version":3,"file":"index.d.cts","names":[],"sources":["../../src/data/reporters.ts","../../src/data/knownCodes.ts"],"mappings":";;AAsBA;;;;;AAgBA;;;;;;;;;;;;;;;UAhBiB,eAAA;;EAEf,KAAA;;EAEA,GAAA;AAAA;;;;;;;;;;UAYe,aAAA;;EAEf,IAAA;;EAEA,SAAA;EA2CF;EAzCE,QAAA,EAAU,MAAA,SAAe,eAAA;;EAEzB,UAAA,GAAa,MAAA;EAuCgC;EArC7C,gBAAA;EAwGc;EAtGd,SAAA;EAsGkC;EApGlC,KAAA;AAAA;;;;;;;UASe,iBAAA;EAkHN;EAhHT,cAAA,EAAgB,GAAA,SAAY,aAAA;;EAE5B,GAAA,EAAK,aAAA;AAAA;;;;;;;;;;AC7BP;;;iBDiDsB,aAAA,CAAA,GAAiB,OAAA,CAAQ,iBAAA;;ACyE/C;;;;;AAyuBA;;;;;;;;;AA8DA;iBD7yBgB,gBAAA,CAAA,GAAoB,iBAAA;;;;;;;;;;;;;;;;;;iBAqBd,2BAAA,CACpB,IAAA,WACC,OAAA,CAAQ,aAAA;;;;AAzJX;;;;;AAgBA;;;;;;;UCxBiB,SAAA;;EAEf,YAAA;;EAEA,YAAA;;EAEA,QAAA;;EAEA,MAAA;AAAA;;;;ADuCF;;;;;;;;cCzBa,gBAAA,EAAkB,SAAA;;;;;;;ADiD/B;;;;;AAmEA;;;;cCMa,UAAA,EAAY,SAAA;ADezB;;;;;;;;;;;;AC/JA;;;;;;;AD+JA,iBC0tBgB,aAAA,CAAc,YAAA,UAAsB,QAAA,WAAmB,SAAA;;;AAn2BvE;;;;;AA0HA;;;;;AAyuBA;;;;iBA8DgB,mBAAA,CAAoB,UAAA,WAAqB,SAAA"}
@@ -112,5 +112,95 @@ declare function getReportersSync(): ReportersDatabase | null;
112
112
  */
113
113
  declare function findReportersByAbbreviation(abbr: string): Promise<ReporterEntry[]>;
114
114
  //#endregion
115
- export { ReporterEdition, ReporterEntry, ReportersDatabase, findReportersByAbbreviation, getReportersSync, loadReporters };
115
+ //#region src/data/knownCodes.d.ts
116
+ /**
117
+ * Known statutory code registry for abbreviated-code jurisdictions
118
+ *
119
+ * Provides a registry of state statutory codes that use abbreviated
120
+ * citation forms (e.g., "R.C. § 1.01", "MCL 750.83"). Used by the
121
+ * citation extractor to identify and normalize state statute citations.
122
+ */
123
+ /**
124
+ * A single entry in the known codes registry.
125
+ *
126
+ * PA has two entries (Pa.C.S. and P.S.) because it has two distinct
127
+ * code families with separate abbreviation sets.
128
+ */
129
+ interface CodeEntry {
130
+ /** Two-letter state abbreviation (e.g., "OH", "MI") */
131
+ jurisdiction: string;
132
+ /** Short canonical abbreviation used internally (e.g., "RC", "MCL") */
133
+ abbreviation: string;
134
+ /** All recognized text patterns that identify this code */
135
+ patterns: string[];
136
+ /** Citation family — determines which citation pattern family this belongs to */
137
+ family: "federal" | "named" | "abbreviated" | "chapterAct" | "prose";
138
+ }
139
+ /**
140
+ * Registry of state statutory codes that use abbreviated citation forms.
141
+ *
142
+ * Covers 12 jurisdictions. Pennsylvania has two entries because it
143
+ * maintains two distinct code families (Pa.C.S. and P.S.).
144
+ *
145
+ * Note: Short 2-letter patterns (GS, IC, PS, RC, FS) may produce false positives
146
+ * in non-legal text (e.g., "GS 5" for government service grade). The extraction
147
+ * layer mitigates this via confidence scoring — citations without a § symbol receive
148
+ * lower confidence (0.85 vs 0.95). Consumers should filter by confidence threshold.
149
+ */
150
+ declare const abbreviatedCodes: CodeEntry[];
151
+ /**
152
+ * Registry of state statutory codes that use named-code citation forms.
153
+ *
154
+ * Named-code jurisdictions identify their code by name in citations (e.g.,
155
+ * "N.Y. Penal Law § 120.05", "Cal. Civ. Proc. Code § 437c"), rather than by
156
+ * a standalone abbreviation. The jurisdiction prefix is handled by the
157
+ * extraction layer; these patterns cover only the code name portion.
158
+ *
159
+ * Ordering note: within each jurisdiction, more specific patterns must come
160
+ * before more general ones (e.g., "Civ. Proc." before "Civ.") so that
161
+ * findNamedCode's longest-match wins correctly.
162
+ *
163
+ * Covers 7 jurisdictions: NY (21 entries), CA (29 entries), TX (29 entries),
164
+ * MD (36 entries), VA (1 entry), AL (1 entry), MA (1 entry).
165
+ */
166
+ declare const namedCodes: CodeEntry[];
167
+ /**
168
+ * Find a CodeEntry by jurisdiction and code name token.
169
+ *
170
+ * Lookup strategy: for each candidate entry in the given jurisdiction,
171
+ * check whether the normalized codeName matches or starts with any of the
172
+ * entry's patterns (case-insensitive). Returns the entry with the longest
173
+ * matching pattern to prefer more specific codes over general ones
174
+ * (e.g., "Civ. Proc." over "Civ.").
175
+ *
176
+ * @param jurisdiction - Two-letter state abbreviation (e.g., "CA", "NY")
177
+ * @param codeName - The code name token to look up (e.g., "Penal", "Civ. Proc.")
178
+ * @returns Matching CodeEntry, or undefined if not found
179
+ *
180
+ * @example
181
+ * findNamedCode('NY', 'Penal') // → NY PEN entry
182
+ * findNamedCode('CA', 'Civ. Proc.') // → CA CCP entry (not CA CIV)
183
+ * findNamedCode('MD', 'Crim. Law') // → MD gcr entry
184
+ * findNamedCode('NY', 'Unknown') // → undefined
185
+ */
186
+ declare function findNamedCode(jurisdiction: string, codeName: string): CodeEntry | undefined;
187
+ /**
188
+ * Find a CodeEntry by an abbreviated text token.
189
+ *
190
+ * Lookup order:
191
+ * 1. Exact case-insensitive match against all patterns
192
+ * 2. Prefix match — returns the entry whose pattern is the longest
193
+ * prefix of `abbrevText` (handles tokens like "RCW" inside longer text)
194
+ *
195
+ * @param abbrevText - The abbreviation token to look up
196
+ * @returns Matching CodeEntry, or undefined if not found
197
+ *
198
+ * @example
199
+ * findAbbreviatedCode('R.C.') // → OH entry
200
+ * findAbbreviatedCode('MCL') // → MI entry
201
+ * findAbbreviatedCode('UNKNOWN') // → undefined
202
+ */
203
+ declare function findAbbreviatedCode(abbrevText: string): CodeEntry | undefined;
204
+ //#endregion
205
+ export { CodeEntry, ReporterEdition, ReporterEntry, ReportersDatabase, abbreviatedCodes, findAbbreviatedCode, findNamedCode, findReportersByAbbreviation, getReportersSync, loadReporters, namedCodes };
116
206
  //# sourceMappingURL=index.d.mts.map
@@ -1 +1 @@
1
- {"version":3,"file":"index.d.mts","names":[],"sources":["../../src/data/reporters.ts"],"mappings":";;AAsBA;;;;;AAgBA;;;;;;;;;;;;;;;UAhBiB,eAAA;;EAEf,KAAA;;EAEA,GAAA;AAAA;;;;;;;;;;UAYe,aAAA;;EAEf,IAAA;;EAEA,SAAA;EA2CF;EAzCE,QAAA,EAAU,MAAA,SAAe,eAAA;;EAEzB,UAAA,GAAa,MAAA;EAuCgC;EArC7C,gBAAA;EAwGc;EAtGd,SAAA;EAsGkC;EApGlC,KAAA;AAAA;;;;;;;UASe,iBAAA;EAkHN;EAhHT,cAAA,EAAgB,GAAA,SAAY,aAAA;;EAE5B,GAAA,EAAK,aAAA;AAAA;;;;;;;;;;;;;iBAoBe,aAAA,CAAA,GAAiB,OAAA,CAAQ,iBAAA;;;;;;;;;;;;;;;;;iBAmE/B,gBAAA,CAAA,GAAoB,iBAAA;;;;;;;;;;;;;;;;;;iBAqBd,2BAAA,CACpB,IAAA,WACC,OAAA,CAAQ,aAAA"}
1
+ {"version":3,"file":"index.d.mts","names":[],"sources":["../../src/data/reporters.ts","../../src/data/knownCodes.ts"],"mappings":";;AAsBA;;;;;AAgBA;;;;;;;;;;;;;;;UAhBiB,eAAA;;EAEf,KAAA;;EAEA,GAAA;AAAA;;;;;;;;;;UAYe,aAAA;;EAEf,IAAA;;EAEA,SAAA;EA2CF;EAzCE,QAAA,EAAU,MAAA,SAAe,eAAA;;EAEzB,UAAA,GAAa,MAAA;EAuCgC;EArC7C,gBAAA;EAwGc;EAtGd,SAAA;EAsGkC;EApGlC,KAAA;AAAA;;;;;;;UASe,iBAAA;EAkHN;EAhHT,cAAA,EAAgB,GAAA,SAAY,aAAA;;EAE5B,GAAA,EAAK,aAAA;AAAA;;;;;;;;;;AC7BP;;;iBDiDsB,aAAA,CAAA,GAAiB,OAAA,CAAQ,iBAAA;;ACyE/C;;;;;AAyuBA;;;;;;;;;AA8DA;iBD7yBgB,gBAAA,CAAA,GAAoB,iBAAA;;;;;;;;;;;;;;;;;;iBAqBd,2BAAA,CACpB,IAAA,WACC,OAAA,CAAQ,aAAA;;;;AAzJX;;;;;AAgBA;;;;;;;UCxBiB,SAAA;;EAEf,YAAA;;EAEA,YAAA;;EAEA,QAAA;;EAEA,MAAA;AAAA;;;;ADuCF;;;;;;;;cCzBa,gBAAA,EAAkB,SAAA;;;;;;;ADiD/B;;;;;AAmEA;;;;cCMa,UAAA,EAAY,SAAA;ADezB;;;;;;;;;;;;AC/JA;;;;;;;AD+JA,iBC0tBgB,aAAA,CAAc,YAAA,UAAsB,QAAA,WAAmB,SAAA;;;AAn2BvE;;;;;AA0HA;;;;;AAyuBA;;;;iBA8DgB,mBAAA,CAAoB,UAAA,WAAqB,SAAA"}
@@ -1,2 +1,2 @@
1
- let e=null;async function t(){if(e)return e;let t=await import(`../../data/reporters.json`,{assert:{type:`json`}}),n=new Map,r=[],i=t.default||t;for(let[e,t]of Object.entries(i))for(let e of t){r.push(e);for(let t of Object.keys(e.editions)){let r=t.toLowerCase();n.has(r)||n.set(r,[]),n.get(r)?.push(e)}for(let[t,r]of Object.entries(e.variations||{})){let r=t.toLowerCase();n.has(r)||n.set(r,[]),n.get(r)?.push(e)}}return e={byAbbreviation:n,all:r},e}function n(){return e}async function r(e){return(await t()).byAbbreviation.get(e.toLowerCase())??[]}export{r as findReportersByAbbreviation,n as getReportersSync,t as loadReporters};
1
+ import{i as e,n as t,r as n,t as r}from"../knownCodes-MkDSiR1j.mjs";let i=null;async function a(){if(i)return i;let e=await import(`../../data/reporters.json`,{assert:{type:`json`}}),t=new Map,n=[],r=e.default||e;for(let[e,i]of Object.entries(r))for(let e of i){n.push(e);for(let n of Object.keys(e.editions)){let r=n.toLowerCase();t.has(r)||t.set(r,[]),t.get(r)?.push(e)}for(let[n,r]of Object.entries(e.variations||{})){let r=n.toLowerCase();t.has(r)||t.set(r,[]),t.get(r)?.push(e)}}return i={byAbbreviation:t,all:n},i}function o(){return i}async function s(e){return(await a()).byAbbreviation.get(e.toLowerCase())??[]}export{r as abbreviatedCodes,t as findAbbreviatedCode,n as findNamedCode,s as findReportersByAbbreviation,o as getReportersSync,a as loadReporters,e as namedCodes};
2
2
  //# sourceMappingURL=index.mjs.map
@@ -1 +1 @@
1
- {"version":3,"file":"index.mjs","names":[],"sources":["../../src/data/reporters.ts"],"sourcesContent":["/**\n * Reporter database integration for citation validation\n *\n * This module provides lazy-loadable access to the reporters-db database,\n * containing 1200+ court reporters with variant forms. The library works\n * in degraded mode (pattern-based extraction only) if reporters are not loaded.\n *\n * @example\n * // Degraded mode: extraction works without reporter data\n * const citations = await extract(text)\n *\n * @example\n * // Full mode: load reporters for validation\n * await loadReporters()\n * const citations = await extract(text) // Now with reporter validation\n */\n\n/**\n * Edition entry from reporters-db\n *\n * Represents a specific edition of a reporter with start/end dates.\n */\nexport interface ReporterEdition {\n /** Start date in ISO 8601 format */\n start: string | null\n /** End date in ISO 8601 format (null if ongoing) */\n end: string | null\n}\n\n/**\n * Reporter entry from reporters-db\n *\n * Represents a single court reporter with all metadata needed for\n * citation validation and enrichment.\n *\n * Note: The reporters-db structure has the actual data; this interface\n * represents it flexibly to handle all variations in the JSON.\n */\nexport interface ReporterEntry {\n /** Full reporter name (e.g., \"Federal Reporter\") */\n name: string\n /** Citation type: state, federal, specialty, neutral, state_regional, etc. */\n cite_type: string\n /** Editions keyed by abbreviation (e.g., {\"F.2d\": {...}, \"F.3d\": {...}}) */\n editions: Record<string, ReporterEdition>\n /** Variant forms mapped to canonical form (e.g., {\"F. 2d\": \"F.2d\"}) */\n variations?: Record<string, string | undefined>\n /** MLZ jurisdiction identifiers (optional) */\n mlz_jurisdiction?: string[]\n /** Publisher (optional) */\n publisher?: string\n /** Notes (optional) */\n notes?: string\n}\n\n/**\n * In-memory reporter database with fast O(1) lookup\n *\n * Uses Map-based indexing for case-insensitive abbreviation lookup.\n * All variant forms are indexed to support fuzzy matching.\n */\nexport interface ReportersDatabase {\n /** Fast O(1) lookup by abbreviation (lowercase normalized keys) */\n byAbbreviation: Map<string, ReporterEntry[]>\n /** All reporters (for iteration/filtering) */\n all: ReporterEntry[]\n}\n\n/**\n * Cached database instance (null until loadReporters() called)\n */\nlet cached: ReportersDatabase | null = null\n\n/**\n * Load reporter database asynchronously with lazy loading\n *\n * Dynamic import prevents loading 1200+ reporters until explicitly requested.\n * Result is cached after first load for subsequent calls.\n *\n * @returns Promise resolving to indexed reporter database\n *\n * @example\n * const db = await loadReporters()\n * const reporters = db.byAbbreviation.get('f.2d') // Fast O(1) lookup\n */\nexport async function loadReporters(): Promise<ReportersDatabase> {\n if (cached) return cached\n\n // Dynamic import prevents loading until requested (keeps core bundle small)\n const data = await import(\"../../data/reporters.json\", {\n assert: { type: \"json\" },\n })\n\n const byAbbreviation = new Map<string, ReporterEntry[]>()\n const all: ReporterEntry[] = []\n\n // reporters.json structure: { \"A.\": [...], \"F.2d\": [...], ... }\n const reportersData = (data.default || data) as Record<\n string,\n ReporterEntry[]\n >\n\n // Build fast lookup index with lowercase normalization\n for (const [_canonicalAbbr, reporters] of Object.entries(reportersData)) {\n for (const reporter of reporters) {\n all.push(reporter)\n\n // Index by all edition abbreviations\n for (const editionAbbr of Object.keys(reporter.editions)) {\n const key = editionAbbr.toLowerCase()\n if (!byAbbreviation.has(key)) {\n byAbbreviation.set(key, [])\n }\n byAbbreviation.get(key)?.push(reporter)\n }\n\n // Index all variations for fuzzy matching\n for (const [variant, _canonical] of Object.entries(\n reporter.variations || {},\n )) {\n const variantKey = variant.toLowerCase()\n if (!byAbbreviation.has(variantKey)) {\n byAbbreviation.set(variantKey, [])\n }\n byAbbreviation.get(variantKey)?.push(reporter)\n }\n }\n }\n\n cached = {\n byAbbreviation,\n all,\n }\n return cached\n}\n\n/**\n * Get cached reporter database synchronously (degraded mode support)\n *\n * Returns null if reporters not loaded yet. This enables the library to\n * work in degraded mode without reporter validation.\n *\n * @returns Cached database or null if not loaded\n *\n * @example\n * const db = getReportersSync()\n * if (db) {\n * // Full mode: validate citations\n * } else {\n * // Degraded mode: extract without validation\n * }\n */\nexport function getReportersSync(): ReportersDatabase | null {\n return cached\n}\n\n/**\n * Find reporters by abbreviation (case-insensitive)\n *\n * Loads reporter database if not already loaded. Returns all reporters\n * matching the abbreviation (including variant forms).\n *\n * @param abbr - Reporter abbreviation to look up\n * @returns Promise resolving to matching reporters (empty array if none)\n *\n * @example\n * const reporters = await findReportersByAbbreviation('F.2d')\n * // [{ abbreviation: 'F.2d', name: 'Federal Reporter, Second Series', ... }]\n *\n * @example\n * const unknown = await findReportersByAbbreviation('NONEXISTENT')\n * // [] (empty array, not error)\n */\nexport async function findReportersByAbbreviation(\n abbr: string,\n): Promise<ReporterEntry[]> {\n const db = await loadReporters()\n return db.byAbbreviation.get(abbr.toLowerCase()) ?? []\n}\n"],"mappings":"AAuEA,IAAI,EAAmC,KAcvC,eAAsB,GAA4C,CAChE,GAAI,EAAQ,OAAO,EAGnB,IAAM,EAAO,MAAM,OAAO,4BAA6B,CACrD,OAAQ,CAAE,KAAM,OAAQ,CACzB,EAEK,EAAiB,IAAI,IACrB,EAAuB,EAAE,CAGzB,EAAiB,EAAK,SAAW,EAMvC,IAAK,GAAM,CAAC,EAAgB,KAAc,OAAO,QAAQ,EAAc,CACrE,IAAK,IAAM,KAAY,EAAW,CAChC,EAAI,KAAK,EAAS,CAGlB,IAAK,IAAM,KAAe,OAAO,KAAK,EAAS,SAAS,CAAE,CACxD,IAAM,EAAM,EAAY,aAAa,CAChC,EAAe,IAAI,EAAI,EAC1B,EAAe,IAAI,EAAK,EAAE,CAAC,CAE7B,EAAe,IAAI,EAAI,EAAE,KAAK,EAAS,CAIzC,IAAK,GAAM,CAAC,EAAS,KAAe,OAAO,QACzC,EAAS,YAAc,EAAE,CAC1B,CAAE,CACD,IAAM,EAAa,EAAQ,aAAa,CACnC,EAAe,IAAI,EAAW,EACjC,EAAe,IAAI,EAAY,EAAE,CAAC,CAEpC,EAAe,IAAI,EAAW,EAAE,KAAK,EAAS,EASpD,MAJA,GAAS,CACP,iBACA,MACD,CACM,EAmBT,SAAgB,GAA6C,CAC3D,OAAO,EAoBT,eAAsB,EACpB,EAC0B,CAE1B,OADW,MAAM,GAAe,EACtB,eAAe,IAAI,EAAK,aAAa,CAAC,EAAI,EAAE"}
1
+ {"version":3,"file":"index.mjs","names":[],"sources":["../../src/data/reporters.ts"],"sourcesContent":["/**\n * Reporter database integration for citation validation\n *\n * This module provides lazy-loadable access to the reporters-db database,\n * containing 1200+ court reporters with variant forms. The library works\n * in degraded mode (pattern-based extraction only) if reporters are not loaded.\n *\n * @example\n * // Degraded mode: extraction works without reporter data\n * const citations = await extract(text)\n *\n * @example\n * // Full mode: load reporters for validation\n * await loadReporters()\n * const citations = await extract(text) // Now with reporter validation\n */\n\n/**\n * Edition entry from reporters-db\n *\n * Represents a specific edition of a reporter with start/end dates.\n */\nexport interface ReporterEdition {\n /** Start date in ISO 8601 format */\n start: string | null\n /** End date in ISO 8601 format (null if ongoing) */\n end: string | null\n}\n\n/**\n * Reporter entry from reporters-db\n *\n * Represents a single court reporter with all metadata needed for\n * citation validation and enrichment.\n *\n * Note: The reporters-db structure has the actual data; this interface\n * represents it flexibly to handle all variations in the JSON.\n */\nexport interface ReporterEntry {\n /** Full reporter name (e.g., \"Federal Reporter\") */\n name: string\n /** Citation type: state, federal, specialty, neutral, state_regional, etc. */\n cite_type: string\n /** Editions keyed by abbreviation (e.g., {\"F.2d\": {...}, \"F.3d\": {...}}) */\n editions: Record<string, ReporterEdition>\n /** Variant forms mapped to canonical form (e.g., {\"F. 2d\": \"F.2d\"}) */\n variations?: Record<string, string | undefined>\n /** MLZ jurisdiction identifiers (optional) */\n mlz_jurisdiction?: string[]\n /** Publisher (optional) */\n publisher?: string\n /** Notes (optional) */\n notes?: string\n}\n\n/**\n * In-memory reporter database with fast O(1) lookup\n *\n * Uses Map-based indexing for case-insensitive abbreviation lookup.\n * All variant forms are indexed to support fuzzy matching.\n */\nexport interface ReportersDatabase {\n /** Fast O(1) lookup by abbreviation (lowercase normalized keys) */\n byAbbreviation: Map<string, ReporterEntry[]>\n /** All reporters (for iteration/filtering) */\n all: ReporterEntry[]\n}\n\n/**\n * Cached database instance (null until loadReporters() called)\n */\nlet cached: ReportersDatabase | null = null\n\n/**\n * Load reporter database asynchronously with lazy loading\n *\n * Dynamic import prevents loading 1200+ reporters until explicitly requested.\n * Result is cached after first load for subsequent calls.\n *\n * @returns Promise resolving to indexed reporter database\n *\n * @example\n * const db = await loadReporters()\n * const reporters = db.byAbbreviation.get('f.2d') // Fast O(1) lookup\n */\nexport async function loadReporters(): Promise<ReportersDatabase> {\n if (cached) return cached\n\n // Dynamic import prevents loading until requested (keeps core bundle small)\n const data = await import(\"../../data/reporters.json\", {\n assert: { type: \"json\" },\n })\n\n const byAbbreviation = new Map<string, ReporterEntry[]>()\n const all: ReporterEntry[] = []\n\n // reporters.json structure: { \"A.\": [...], \"F.2d\": [...], ... }\n const reportersData = (data.default || data) as Record<\n string,\n ReporterEntry[]\n >\n\n // Build fast lookup index with lowercase normalization\n for (const [_canonicalAbbr, reporters] of Object.entries(reportersData)) {\n for (const reporter of reporters) {\n all.push(reporter)\n\n // Index by all edition abbreviations\n for (const editionAbbr of Object.keys(reporter.editions)) {\n const key = editionAbbr.toLowerCase()\n if (!byAbbreviation.has(key)) {\n byAbbreviation.set(key, [])\n }\n byAbbreviation.get(key)?.push(reporter)\n }\n\n // Index all variations for fuzzy matching\n for (const [variant, _canonical] of Object.entries(\n reporter.variations || {},\n )) {\n const variantKey = variant.toLowerCase()\n if (!byAbbreviation.has(variantKey)) {\n byAbbreviation.set(variantKey, [])\n }\n byAbbreviation.get(variantKey)?.push(reporter)\n }\n }\n }\n\n cached = {\n byAbbreviation,\n all,\n }\n return cached\n}\n\n/**\n * Get cached reporter database synchronously (degraded mode support)\n *\n * Returns null if reporters not loaded yet. This enables the library to\n * work in degraded mode without reporter validation.\n *\n * @returns Cached database or null if not loaded\n *\n * @example\n * const db = getReportersSync()\n * if (db) {\n * // Full mode: validate citations\n * } else {\n * // Degraded mode: extract without validation\n * }\n */\nexport function getReportersSync(): ReportersDatabase | null {\n return cached\n}\n\n/**\n * Find reporters by abbreviation (case-insensitive)\n *\n * Loads reporter database if not already loaded. Returns all reporters\n * matching the abbreviation (including variant forms).\n *\n * @param abbr - Reporter abbreviation to look up\n * @returns Promise resolving to matching reporters (empty array if none)\n *\n * @example\n * const reporters = await findReportersByAbbreviation('F.2d')\n * // [{ abbreviation: 'F.2d', name: 'Federal Reporter, Second Series', ... }]\n *\n * @example\n * const unknown = await findReportersByAbbreviation('NONEXISTENT')\n * // [] (empty array, not error)\n */\nexport async function findReportersByAbbreviation(\n abbr: string,\n): Promise<ReporterEntry[]> {\n const db = await loadReporters()\n return db.byAbbreviation.get(abbr.toLowerCase()) ?? []\n}\n"],"mappings":"oEAuEA,IAAI,EAAmC,KAcvC,eAAsB,GAA4C,CAChE,GAAI,EAAQ,OAAO,EAGnB,IAAM,EAAO,MAAM,OAAO,4BAA6B,CACrD,OAAQ,CAAE,KAAM,OAAQ,CACzB,EAEK,EAAiB,IAAI,IACrB,EAAuB,EAAE,CAGzB,EAAiB,EAAK,SAAW,EAMvC,IAAK,GAAM,CAAC,EAAgB,KAAc,OAAO,QAAQ,EAAc,CACrE,IAAK,IAAM,KAAY,EAAW,CAChC,EAAI,KAAK,EAAS,CAGlB,IAAK,IAAM,KAAe,OAAO,KAAK,EAAS,SAAS,CAAE,CACxD,IAAM,EAAM,EAAY,aAAa,CAChC,EAAe,IAAI,EAAI,EAC1B,EAAe,IAAI,EAAK,EAAE,CAAC,CAE7B,EAAe,IAAI,EAAI,EAAE,KAAK,EAAS,CAIzC,IAAK,GAAM,CAAC,EAAS,KAAe,OAAO,QACzC,EAAS,YAAc,EAAE,CAC1B,CAAE,CACD,IAAM,EAAa,EAAQ,aAAa,CACnC,EAAe,IAAI,EAAW,EACjC,EAAe,IAAI,EAAY,EAAE,CAAC,CAEpC,EAAe,IAAI,EAAW,EAAE,KAAK,EAAS,EASpD,MAJA,GAAS,CACP,iBACA,MACD,CACM,EAmBT,SAAgB,GAA6C,CAC3D,OAAO,EAoBT,eAAsB,EACpB,EAC0B,CAE1B,OADW,MAAM,GAAe,EACtB,eAAe,IAAI,EAAK,aAAa,CAAC,EAAI,EAAE"}
package/dist/index.cjs CHANGED
@@ -1,2 +1,2 @@
1
- Object.defineProperty(exports,Symbol.toStringTag,{value:`Module`});function e(e){return e.type===`case`||e.type===`statute`||e.type===`journal`||e.type===`neutral`||e.type===`publicLaw`||e.type===`federalRegister`||e.type===`statutesAtLarge`}function t(e){return e.type===`id`||e.type===`supra`||e.type===`shortFormCase`}function n(e){return e.type===`case`}function r(e,t){return e.type===t}function i(e){throw Error(`Unexpected value: ${e}`)}function a(e){return e.replace(/<[^>]+>/g,``)}function o(e){return e.replace(/[\t\n\r]+/g,` `).replace(/ {2,}/g,` `)}function s(e){return e.normalize(`NFKC`)}function c(e){return e.replace(/[\u201C\u201D]/g,`"`).replace(/[\u2018\u2019]/g,`'`)}function l(e,t=[a,o,s,c]){let n=e,r=new Map,i=new Map;for(let t=0;t<=e.length;t++)r.set(t,t),i.set(t,t);for(let e of t){let t=n,a=e(n);if(t!==a){let{newCleanToOriginal:e,newOriginalToClean:o}=u(t,a,r,i);r=e,i=o,n=a}}return{cleaned:n,transformationMap:{cleanToOriginal:r,originalToClean:i},warnings:[]}}function u(e,t,n,r){let i=new Map,a=new Map,o=0,s=0;for(;o<=e.length||s<=t.length;){if(o>=e.length&&s>=t.length){let e=n.get(o)??o;i.set(s,e),a.set(e,s);break}if(o>=e.length){let e=n.get(o)??o;i.set(s,e),s++;continue}if(s>=t.length){let e=n.get(o)??o;a.set(e,s),o++;continue}if(e[o]===t[s]){let e=n.get(o)??o;i.set(s,e),a.set(e,s),o++,s++}else{let r=!1;for(let i=1;i<=20&&!(o+i>=e.length);i++)if(e[o+i]===t[s]){for(let e=0;e<i;e++){let t=n.get(o+e)??o+e;a.set(t,s)}o+=i,r=!0;break}if(r)continue;for(let a=1;a<=20&&!(s+a>=t.length);a++)if(e[o]===t[s+a]){let e=n.get(o)??o;for(let t=0;t<a;t++)i.set(s+t,e);s+=a,r=!0;break}if(r)continue;let c=n.get(o)??o;i.set(s,c),a.set(c,s),o++,s++}}return{newCleanToOriginal:i,newOriginalToClean:a}}const d=[{id:`federal-reporter`,regex:/\b(\d+(?:-\d+)?)\s+(F\.|F\.2d|F\.3d|F\.4th|F\.\s?Supp\.|F\.\s?Supp\.\s?2d|F\.\s?Supp\.\s?3d|F\.\s?Supp\.\s?4th)\s+(\d+)\b/g,description:`Federal Reporter (F., F.2d, F.3d, F.4th, F.Supp., etc.)`,type:`case`},{id:`supreme-court`,regex:/\b(\d+(?:-\d+)?)\s+(U\.\s?S\.|S\.\s?Ct\.|L\.\s?Ed\.(?:\s?2d)?)\s+(\d+)\b/g,description:`U.S. Supreme Court reporters`,type:`case`},{id:`state-reporter`,regex:/\b(\d+(?:-\d+)?)\s+([A-Z][A-Za-z.]+(?:\s?2d|\s?3d|\s?4th|\s?5th)?)\s+(\d+)\b/g,description:`State reporters (broad pattern, validated against reporters-db in Phase 3)`,type:`case`}],f=[{id:`usc`,regex:/\b(\d+)\s+U\.S\.C\.?\s+§+\s*(\d+[A-Za-z]*)\b/g,description:`U.S. Code citations (e.g., "42 U.S.C. § 1983")`,type:`statute`},{id:`state-code`,regex:/\b([A-Z][a-z]+\.?\s+[A-Za-z.]+\s+Code)\s+§\s*(\d+[A-Za-z]*)\b/g,description:`State code citations (broad pattern, e.g., "Cal. Penal Code § 187")`,type:`statute`}],p=[{id:`law-review`,regex:/\b(\d+(?:-\d+)?)\s+([A-Z][A-Za-z.\s]+)\s+(\d+)\b/g,description:`Law review citations (e.g., "120 Harv. L. Rev. 500"), validated against journals-db in Phase 3`,type:`journal`}],m=[{id:`westlaw`,regex:/\b(\d{4})\s+WL\s+(\d+)\b/g,description:`WestLaw citations (e.g., "2021 WL 123456")`,type:`neutral`},{id:`lexis`,regex:/\b(\d{4})\s+U\.S\.\s+LEXIS\s+(\d+)\b/g,description:`LexisNexis citations (e.g., "2021 U.S. LEXIS 5000")`,type:`neutral`},{id:`public-law`,regex:/\bPub\.\s?L\.\s?No\.\s?(\d+-\d+)\b/g,description:`Public Law citations (e.g., "Pub. L. No. 117-58")`,type:`publicLaw`},{id:`federal-register`,regex:/\b(\d+(?:-\d+)?)\s+Fed\.\s?Reg\.\s+(\d+)\b/g,description:`Federal Register citations (e.g., "86 Fed. Reg. 12345")`,type:`federalRegister`},{id:`statutes-at-large`,regex:/\b(\d+(?:-\d+)?)\s+Stat\.\s+(\d+)\b/g,description:`Statutes at Large citations (e.g., "124 Stat. 119")`,type:`statutesAtLarge`},{id:`compact-law-review`,regex:/\b(\d+(?:-\d+)?)\s+([A-Z][A-Za-z.]+L\.(?:Rev|J|Q)\.)\s+(\d+)\b/g,description:`Compact law review citations without spaces (e.g., "93 Harv.L.Rev. 752")`,type:`journal`}],h=[{id:`id`,regex:/\b[Ii]d\.(?:\s+at\s+(\d+))?/g,description:`Id. citations (e.g., "Id." or "Id. at 253")`,type:`case`},{id:`ibid`,regex:/\b[Ii]bid\.(?:\s+at\s+(\d+))?/g,description:`Ibid. citations (e.g., "Ibid." or "Ibid. at 125")`,type:`case`},{id:`supra`,regex:/\b([A-Z][a-zA-Z]+(?:(?:\s+v\.?\s+|\s+)[A-Z][a-zA-Z]+)*)\s*,?\s+supra(?:,?\s+at\s+(\d+))?/g,description:`Supra citations (e.g., "Smith, supra" or "Smith, supra, at 460")`,type:`case`},{id:`shortFormCase`,regex:/\b(\d+(?:-\d+)?)\s+([A-Z][A-Za-z.\s]+?(?:\d[a-z])?)\s+at\s+(\d+)\b/g,description:`Short-form case citations (e.g., "500 F.2d at 125")`,type:`case`}];function g(e,t=[...d,...f,...p,...m,...h]){let n=[];for(let r of t)try{let t=e.matchAll(r.regex);for(let e of t)n.push({text:e[0],span:{cleanStart:e.index,cleanEnd:e.index+e[0].length},type:r.type,patternId:r.id})}catch(e){console.warn(`Pattern ${r.id} threw error, skipping:`,e instanceof Error?e.message:String(e))}return n.sort((e,t)=>e.span.cleanStart-t.span.cleanStart),n}function _(e){let t=Number.parseInt(e,10);return String(t)===e?t:e}const v=/(?:Jan|Feb|Mar|Apr|May|Jun|Jul|Aug|Sep|Sept|Oct|Nov|Dec)\.?/;function y(e){let t=e.replace(/\s*\d{4}\s*$/,``).trim();return t=t.replace(RegExp(`\\s*,?\\s*\\d{1,2}\\s*,?\\s*$`),``).trim(),t=t.replace(RegExp(`\\s*${v.source}\\s*$`),``).trim(),t=t.replace(/,\s*$/,``).trim(),t&&/[A-Za-z]/.test(t)?t:void 0}function b(e,t,n){let{text:r,span:i}=e,a=/^(\d+(?:-\d+)?)\s+([A-Za-z0-9.\s]+)\s+(\d+)/.exec(r);if(!a)throw Error(`Failed to parse case citation: ${r}`);let o=_(a[1]),s=a[2].trim(),c=Number.parseInt(a[3],10),l=/,\s*(\d+)/.exec(r),u=l?Number.parseInt(l[1],10):void 0,d=/\((?:[^)]*\s)?(\d{4})\)/.exec(r),f=d?Number.parseInt(d[1],10):void 0,p=/\(([^)]*[A-Za-z][^)]*)\)/.exec(r),m=p?y(p[1]):void 0;if(n&&f===void 0){let e=n.substring(i.cleanEnd),t=/^(?:,\s*\d+)*\s*\(([^)]+)\)/.exec(e);if(t){let n=t[1],r=/(\d{4})/.exec(n);r&&(f=Number.parseInt(r[1],10));let i=y(n);if(i&&(m=i),u===void 0){let t=/^,\s*(\d+)/.exec(e);t&&(u=Number.parseInt(t[1],10))}}}!m&&/^(?:U\.?\s?S\.|S\.?\s?Ct\.|L\.?\s?Ed\.)/.test(s)&&(m=`scotus`);let h=t.cleanToOriginal.get(i.cleanStart)??i.cleanStart,g=t.cleanToOriginal.get(i.cleanEnd)??i.cleanEnd,v=.5;if(`F.,F.2d,F.3d,F.4th,U.S.,S. Ct.,L. Ed.,P.,P.2d,P.3d,A.,A.2d,A.3d,N.E.,N.E.2d,N.E.3d,N.W.,N.W.2d,S.E.,S.E.2d,S.W.,S.W.2d,S.W.3d,So.,So. 2d,So. 3d`.split(`,`).some(e=>s.includes(e))&&(v+=.3),f!==void 0){let e=new Date().getFullYear();f<=e&&(v+=.2)}return v=Math.min(v,1),{type:`case`,text:r,span:{cleanStart:i.cleanStart,cleanEnd:i.cleanEnd,originalStart:h,originalEnd:g},confidence:v,matchedText:r,processTimeMs:0,patternsChecked:1,volume:o,reporter:s,page:c,pincite:u,court:m,year:f}}function x(e,t){let{text:n,span:r}=e,i=/^(?:(\d+)\s+)?([A-Za-z.\s]+?)\s*§\s*(\d+[A-Za-z0-9-]*)/.exec(n);if(!i)throw Error(`Failed to parse statute citation: ${n}`);let a=i[1]?Number.parseInt(i[1],10):void 0,o=i[2].trim(),s=i[3],c=t.cleanToOriginal.get(r.cleanStart)??r.cleanStart,l=t.cleanToOriginal.get(r.cleanEnd)??r.cleanEnd,u=.5;return[`U.S.C.`,`C.F.R.`,`Cal. Civ. Code`,`Cal. Penal Code`,`N.Y. Civ. Prac. L. & R.`,`Tex. Civ. Prac. & Rem. Code`].some(e=>o.includes(e))&&(u+=.3),u=Math.min(u,1),{type:`statute`,text:n,span:{cleanStart:r.cleanStart,cleanEnd:r.cleanEnd,originalStart:c,originalEnd:l},confidence:u,matchedText:n,processTimeMs:0,patternsChecked:1,title:a,code:o,section:s}}function S(e,t){let{text:n,span:r}=e,i=/^(\d+(?:-\d+)?)\s+([A-Za-z.\s]+?)\s+(\d+)/.exec(n);if(!i)throw Error(`Failed to parse journal citation: ${n}`);let a=i[1],o=/^\d+$/.test(a)?Number.parseInt(a,10):a,s=i[2].trim(),c=Number.parseInt(i[3],10),l=/,\s*(\d+)/.exec(n),u=l?Number.parseInt(l[1],10):void 0,d=t.cleanToOriginal.get(r.cleanStart)??r.cleanStart,f=t.cleanToOriginal.get(r.cleanEnd)??r.cleanEnd;return{type:`journal`,text:n,span:{cleanStart:r.cleanStart,cleanEnd:r.cleanEnd,originalStart:d,originalEnd:f},confidence:.6,matchedText:n,processTimeMs:0,patternsChecked:1,volume:o,journal:s,abbreviation:s,page:c,pincite:u}}function C(e,t){let{text:n,span:r}=e,i=/^(\d{4})\s+(WL|LEXIS|U\.S\.\s+LEXIS)\s+(\d+)/.exec(n);if(!i)throw Error(`Failed to parse neutral citation: ${n}`);let a=Number.parseInt(i[1],10),o=i[2],s=i[3],c=t.cleanToOriginal.get(r.cleanStart)??r.cleanStart,l=t.cleanToOriginal.get(r.cleanEnd)??r.cleanEnd;return{type:`neutral`,text:n,span:{cleanStart:r.cleanStart,cleanEnd:r.cleanEnd,originalStart:c,originalEnd:l},confidence:1,matchedText:n,processTimeMs:0,patternsChecked:1,year:a,court:o,documentNumber:s}}function w(e,t){let{text:n,span:r}=e,i=/Pub\.\s?L\.(?:\s?No\.)?\s?(\d+)-(\d+)/.exec(n);if(!i)throw Error(`Failed to parse public law citation: ${n}`);let a=Number.parseInt(i[1],10),o=Number.parseInt(i[2],10),s=t.cleanToOriginal.get(r.cleanStart)??r.cleanStart,c=t.cleanToOriginal.get(r.cleanEnd)??r.cleanEnd;return{type:`publicLaw`,text:n,span:{cleanStart:r.cleanStart,cleanEnd:r.cleanEnd,originalStart:s,originalEnd:c},confidence:.9,matchedText:n,processTimeMs:0,patternsChecked:1,congress:a,lawNumber:o}}function T(e,t){let{text:n,span:r}=e,i=/^(\d+(?:-\d+)?)\s+Fed\.\s?Reg\.\s+(\d+)/.exec(n);if(!i)throw Error(`Failed to parse Federal Register citation: ${n}`);let a=i[1],o=/^\d+$/.test(a)?Number.parseInt(a,10):a,s=Number.parseInt(i[2],10),c=/\((?:.*?\s)?(\d{4})\)/.exec(n),l=c?Number.parseInt(c[1],10):void 0,u=t.cleanToOriginal.get(r.cleanStart)??r.cleanStart,d=t.cleanToOriginal.get(r.cleanEnd)??r.cleanEnd;return{type:`federalRegister`,text:n,span:{cleanStart:r.cleanStart,cleanEnd:r.cleanEnd,originalStart:u,originalEnd:d},confidence:.9,matchedText:n,processTimeMs:0,patternsChecked:1,volume:o,page:s,year:l}}function E(e,t){let{text:n,span:r}=e,i=/^(\d+(?:-\d+)?)\s+Stat\.\s+(\d+)/.exec(n);if(!i)throw Error(`Failed to parse Statutes at Large citation: ${n}`);let a=i[1],o=/^\d+$/.test(a)?Number.parseInt(a,10):a,s=Number.parseInt(i[2],10),c=/\((?:.*?\s)?(\d{4})\)/.exec(n),l=c?Number.parseInt(c[1],10):void 0,u=t.cleanToOriginal.get(r.cleanStart)??r.cleanStart,d=t.cleanToOriginal.get(r.cleanEnd)??r.cleanEnd;return{type:`statutesAtLarge`,text:n,span:{cleanStart:r.cleanStart,cleanEnd:r.cleanEnd,originalStart:u,originalEnd:d},confidence:.9,matchedText:n,processTimeMs:0,patternsChecked:1,volume:o,page:s,year:l}}function D(e,t){let{text:n,span:r}=e,i=/[Ii](?:d|bid)\.(?:\s+at\s+(\d+))?/.exec(n);if(!i)throw Error(`Failed to parse Id. citation: ${n}`);let a=i[1]?Number.parseInt(i[1],10):void 0,o=t.cleanToOriginal.get(r.cleanStart)??r.cleanStart,s=t.cleanToOriginal.get(r.cleanEnd)??r.cleanEnd;return{type:`id`,text:n,span:{cleanStart:r.cleanStart,cleanEnd:r.cleanEnd,originalStart:o,originalEnd:s},confidence:1,matchedText:n,processTimeMs:0,patternsChecked:1,pincite:a}}function O(e,t){let{text:n,span:r}=e,i=/\b([A-Z][a-zA-Z]+(?:(?:\s+v\.?\s+|\s+)[A-Z][a-zA-Z]+)*)\s*,?\s+supra(?:,?\s+at\s+(\d+))?/.exec(n);if(!i)throw Error(`Failed to parse supra citation: ${n}`);let a=i[1],o=i[2]?Number.parseInt(i[2],10):void 0,s=t.cleanToOriginal.get(r.cleanStart)??r.cleanStart,c=t.cleanToOriginal.get(r.cleanEnd)??r.cleanEnd;return{type:`supra`,text:n,span:{cleanStart:r.cleanStart,cleanEnd:r.cleanEnd,originalStart:s,originalEnd:c},confidence:.9,matchedText:n,processTimeMs:0,patternsChecked:1,partyName:a,pincite:o}}function k(e,t){let{text:n,span:r}=e,i=/(\d+(?:-\d+)?)\s+([A-Z][A-Za-z.\s]+?(?:\d[a-z])?)\s+at\s+(\d+)/.exec(n);if(!i)throw Error(`Failed to parse short-form case citation: ${n}`);let a=i[1],o=/^\d+$/.test(a)?Number.parseInt(a,10):a,s=i[2].trim(),c=Number.parseInt(i[3],10),l=t.cleanToOriginal.get(r.cleanStart)??r.cleanStart,u=t.cleanToOriginal.get(r.cleanEnd)??r.cleanEnd;return{type:`shortFormCase`,text:n,span:{cleanStart:r.cleanStart,cleanEnd:r.cleanEnd,originalStart:l,originalEnd:u},confidence:.7,matchedText:n,processTimeMs:0,patternsChecked:1,volume:o,reporter:s,pincite:c}}function A(e,t,n=/\n\n+/g){let r=new Map,i=[0],a;for(;(a=n.exec(e))!==null;)i.push(a.index+a[0].length);i.push(e.length);for(let e=0;e<t.length;e++){let n=t[e].span.originalStart,a=0;for(let e=0;e<i.length-1;e++)if(n>=i[e]&&n<i[e+1]){a=e;break}r.set(e,a)}return r}function j(e,t,n,r){if(r===`none`)return!0;let i=n.get(e),a=n.get(t);return i===void 0||a===void 0?!0:i===a}function M(e,t){if(e.length===0)return t.length;if(t.length===0)return e.length;let n=Array.from({length:e.length+1},()=>Array(t.length+1).fill(0));for(let t=0;t<=e.length;t++)n[t][0]=t;for(let e=0;e<=t.length;e++)n[0][e]=e;for(let r=1;r<=e.length;r++)for(let i=1;i<=t.length;i++)e[r-1]===t[i-1]?n[r][i]=n[r-1][i-1]:n[r][i]=1+Math.min(n[r-1][i],n[r][i-1],n[r-1][i-1]);return n[e.length][t.length]}function N(e,t){let n=e.toLowerCase(),r=t.toLowerCase(),i=M(n,r),a=Math.max(n.length,r.length);return a===0?1:1-i/a}var P=class{constructor(e,t,n={}){this.citations=e,this.text=t,this.options={scopeStrategy:n.scopeStrategy??`paragraph`,autoDetectParagraphs:n.autoDetectParagraphs??!0,paragraphBoundaryPattern:n.paragraphBoundaryPattern??/\n\n+/g,fuzzyPartyMatching:n.fuzzyPartyMatching??!0,partyMatchThreshold:n.partyMatchThreshold??.8,allowNestedResolution:n.allowNestedResolution??!1,reportUnresolved:n.reportUnresolved??!0},this.context={citationIndex:0,allCitations:e,lastFullCitation:void 0,fullCitationHistory:new Map,paragraphMap:new Map},this.options.autoDetectParagraphs&&(this.context.paragraphMap=A(t,e,this.options.paragraphBoundaryPattern))}resolve(){let t=[];for(let n=0;n<this.citations.length;n++){this.context.citationIndex=n;let r=this.citations[n],i;switch(r.type){case`id`:i=this.resolveId(r);break;case`supra`:i=this.resolveSupra(r);break;case`shortFormCase`:i=this.resolveShortFormCase(r);break;default:e(r)&&(this.context.lastFullCitation=n,this.trackFullCitation(r,n));break}t.push({...r,resolution:i})}return t}resolveId(e){let t=this.context.citationIndex,n;for(let e=t-1;e>=0;e--)if(this.citations[e].type===`case`){n=e;break}return n===void 0?this.createFailureResult(`No preceding full case citation found`):this.isWithinScope(n,t)?{resolvedTo:n,confidence:1}:this.createFailureResult(`Antecedent citation outside scope boundary`)}resolveSupra(e){let t=this.context.citationIndex,n=this.normalizePartyName(e.partyName),r;for(let[e,i]of this.context.fullCitationHistory){if(!this.isWithinScope(i,t))continue;let a=N(n,e);(!r||a>r.similarity)&&(r={index:i,similarity:a})}if(!r)return this.createFailureResult(`No full citation found in scope`);if(r.similarity<this.options.partyMatchThreshold)return this.createFailureResult(`Party name similarity ${r.similarity.toFixed(2)} below threshold ${this.options.partyMatchThreshold}`);let i=[];return r.similarity<1&&i.push(`Fuzzy match: similarity ${r.similarity.toFixed(2)}`),{resolvedTo:r.index,confidence:r.similarity,warnings:i.length>0?i:void 0}}resolveShortFormCase(e){let t=this.context.citationIndex;for(let n=t-1;n>=0;n--){let r=this.citations[n];if(r.type===`case`&&r.volume===e.volume&&this.normalizeReporter(r.reporter)===this.normalizeReporter(e.reporter))return this.isWithinScope(n,t)?{resolvedTo:n,confidence:.95}:this.createFailureResult(`Matching citation outside scope boundary`)}return this.createFailureResult(`No matching full case citation found`)}trackFullCitation(e,t){if(e.type===`case`){let n=this.extractPartyName(e);if(n){let e=this.normalizePartyName(n);this.context.fullCitationHistory.set(e,t)}}}extractPartyName(e){let t=e.span.originalStart,n=Math.max(0,t-100),r=this.text.substring(n,t),i=r.match(/([A-Z][a-zA-Z]*(?:\s+[A-Z][a-zA-Z]*)*)\s+v\.?\s+[A-Z][a-zA-Z]*(?:\s+[A-Z][a-zA-Z]*)*,\s*$/);if(i)return this.stripSignalWords(i[1].trim());let a=r.match(/([A-Z][a-zA-Z]*(?:\s+[A-Z][a-zA-Z]*)*),\s*$/);if(a)return this.stripSignalWords(a[1].trim())}stripSignalWords(e){let t=e.replace(/^(?:In(?!\s+re\b)|See(?:\s+[Aa]lso)?|Compare|But(?:\s+[Ss]ee)?|Cf\.?|Also)\s+/i,``).trim();return t.length>0?t:e}normalizePartyName(e){return e.toLowerCase().replace(/\s+/g,` `).trim()}normalizeReporter(e){return e.toLowerCase().replace(/\s+/g,``).replace(/\./g,``)}isWithinScope(e,t){return j(e,t,this.context.paragraphMap,this.options.scopeStrategy)}createFailureResult(e){if(this.options.reportUnresolved)return{resolvedTo:void 0,failureReason:e,confidence:0}}};function F(e,t,n){return new P(e,t,n).resolve()}function I(e,t){let n=performance.now(),{cleaned:r,transformationMap:i,warnings:a}=l(e,t?.cleaners),o=g(r,t?.patterns||[...m,...h,...d,...f,...p]),s=[],c=new Set;for(let e of o){let t=`${e.span.cleanStart}-${e.span.cleanEnd}`;c.has(t)||(c.add(t),s.push(e))}let u=[];for(let e of s){let t;switch(e.type){case`case`:t=e.patternId===`id`||e.patternId===`ibid`?D(e,i):e.patternId===`supra`?O(e,i):e.patternId===`shortFormCase`?k(e,i):b(e,i,r);break;case`statute`:t=x(e,i);break;case`journal`:t=S(e,i);break;case`neutral`:t=C(e,i);break;case`publicLaw`:t=w(e,i);break;case`federalRegister`:t=T(e,i);break;case`statutesAtLarge`:t=E(e,i);break;default:continue}a.length>0&&(t.warnings=[...t.warnings||[],...a]),t.processTimeMs=performance.now()-n,u.push(t)}return t?.resolve?F(u,e,t.resolutionOptions):u}async function L(e,t){return I(e,t)}exports.DocumentResolver=P,exports.assertUnreachable=i,exports.cleanText=l,exports.extractCase=b,exports.extractCitations=I,exports.extractCitationsAsync=L,exports.extractFederalRegister=T,exports.extractJournal=S,exports.extractNeutral=C,exports.extractPublicLaw=w,exports.extractStatute=x,exports.extractStatutesAtLarge=E,exports.isCaseCitation=n,exports.isCitationType=r,exports.isFullCitation=e,exports.isShortFormCitation=t,exports.resolveCitations=F,exports.tokenize=g;
1
+ Object.defineProperty(exports,Symbol.toStringTag,{value:`Module`});const e=require(`./knownCodes-CI-vnoBO.cjs`);function t(e){return e.type===`case`||e.type===`statute`||e.type===`journal`||e.type===`neutral`||e.type===`publicLaw`||e.type===`federalRegister`||e.type===`statutesAtLarge`}function n(e){return e.type===`id`||e.type===`supra`||e.type===`shortFormCase`}function r(e){return e.type===`case`}function i(e,t){return e.type===t}function a(e){throw Error(`Unexpected value: ${e}`)}function o(e){return e.replace(/<[^>]+>/g,``)}function s(e){return e.replace(/[\t\n\r]+/g,` `).replace(/ {2,}/g,` `)}function c(e){return e.normalize(`NFKC`)}function l(e){return e.replace(/[\u201C\u201D]/g,`"`).replace(/[\u2018\u2019]/g,`'`)}function u(e){return e.replace(/[\u2013\u2014]/g,`-`)}function d(e){return e.replace(/&sect;/gi,`§`).replace(/&para;/gi,`¶`).replace(/&amp;/gi,`&`).replace(/&nbsp;/gi,` `).replace(/&lt;/gi,`<`).replace(/&gt;/gi,`>`).replace(/&quot;/gi,`"`).replace(/&apos;/gi,`'`).replace(/&#(\d+);/g,(e,t)=>{let n=Number.parseInt(t,10);return Number.isNaN(n)?e:String.fromCharCode(n)}).replace(/&#x([0-9a-fA-F]+);/g,(e,t)=>{let n=Number.parseInt(t,16);return Number.isNaN(n)?e:String.fromCharCode(n)})}function f(e,t=[o,d,s,c,u,l]){let n=e,r=new Map,i=new Map;for(let t=0;t<=e.length;t++)r.set(t,t),i.set(t,t);for(let e of t){let t=n,a=e(n);if(t!==a){let{newCleanToOriginal:e,newOriginalToClean:o}=p(t,a,r,i);r=e,i=o,n=a}}return{cleaned:n,transformationMap:{cleanToOriginal:r,originalToClean:i},warnings:[]}}function p(e,t,n,r){let i=new Map,a=new Map,o=0,s=0;for(;o<=e.length||s<=t.length;){if(o>=e.length&&s>=t.length){let e=n.get(o)??o;i.set(s,e),a.set(e,s);break}if(o>=e.length){let e=n.get(o)??o;i.set(s,e),s++;continue}if(s>=t.length){let e=n.get(o)??o;a.set(e,s),o++;continue}if(e[o]===t[s]){let e=n.get(o)??o;i.set(s,e),a.set(e,s),o++,s++}else{let r=!1;for(let i=1;i<=20&&!(o+i>=e.length);i++)if(e[o+i]===t[s]){for(let e=0;e<i;e++){let t=n.get(o+e)??o+e;a.set(t,s)}o+=i,r=!0;break}if(r)continue;for(let a=1;a<=20&&!(s+a>=t.length);a++)if(e[o]===t[s+a]){let e=n.get(o)??o;for(let t=0;t<a;t++)i.set(s+t,e);s+=a,r=!0;break}if(r)continue;let c=n.get(o)??o;i.set(s,c),a.set(c,s),o++,s++}}return{newCleanToOriginal:i,newOriginalToClean:a}}const m=[{id:`federal-reporter`,regex:/\b(\d+(?:-\d+)?)\s+(F\.|F\.2d|F\.3d|F\.4th|F\.\s?Supp\.|F\.\s?Supp\.\s?2d|F\.\s?Supp\.\s?3d|F\.\s?Supp\.\s?4th|F\.\s?App'x)\s+(\d+|_{3,}|-{3,})(?=\s|$|\(|,|;|\.)/g,description:`Federal Reporter (F., F.2d, F.3d, F.4th, F.Supp., F.App'x, etc.)`,type:`case`},{id:`supreme-court`,regex:/\b(\d+(?:-\d+)?)\s+(U\.\s?S\.|S\.\s?Ct\.|L\.\s?Ed\.(?:\s?2d)?)\s+(\d+|_{3,}|-{3,})(?=\s|$|\(|,|;|\.)/g,description:`U.S. Supreme Court reporters`,type:`case`},{id:`state-reporter`,regex:/\b(\d+(?:-\d+)?)\s+([A-Z](?:(?! L\.[JQR\s])[A-Za-z.\d\s])+?)\s+(\d+|_{3,}|-{3,})(?=\s|$|\(|,|;|\.)/g,description:`State reporters (broad pattern allowing multi-word reporters, excludes journal patterns with " L.J/Q/Rev", validated against reporters-db in Phase 3)`,type:`case`}],h=[{id:`usc`,regex:/\b(\d+)\s+(?:U\.S\.C\.?|USC)\s*§§?\s*(\d+[A-Za-z0-9-]*(?:\([^)]*\))*(?:\s*et\s+seq\.?)?)/g,description:`U.S. Code citations with optional subsections and et seq. (e.g., "42 U.S.C. § 1983(a)(1) et seq.")`,type:`statute`},{id:`cfr`,regex:/\b(\d+)\s+C\.?F\.?R\.?\s*(?:(?:Part|pt\.)\s+|§§?\s*)(\d+(?:\.\d+)?[A-Za-z0-9-]*(?:\([^)]*\))*(?:\s*et\s+seq\.?)?)/g,description:`Code of Federal Regulations with Part or §, subsections, et seq. (e.g., "12 C.F.R. Part 226", "40 C.F.R. § 122.26(b)(14)")`,type:`statute`},{id:`prose`,regex:/\b[Ss]ection\s+(\d+[A-Za-z0-9-]*(?:\([^)]*\))*)\s+of\s+title\s+(\d+)\b/g,description:`Prose-form federal citations (e.g., "section 1983 of title 42"). Note: MD-style "section X of the Y Article" deferred to PR 3.`,type:`statute`},{id:`named-code`,regex:/\b(N\.?\s*Y\.?|Cal(?:ifornia)?\.?|Tex(?:as)?\.?|Md\.?|Va\.?|Ala(?:bama)?\.?)\s+((?:[A-Za-z.&',\s]+?))\s*§§?\s*(\d+[A-Za-z0-9.:/-]*(?:\([^)]*\))*(?:\s*et\s+seq\.?)?)/g,description:`Named-code state citations (NY, CA, TX, MD, VA, AL) with jurisdiction prefix + code name + §`,type:`statute`},{id:`mass-chapter`,regex:/\b(Mass\.?\s*Gen\.?\s*Laws|M\.?G\.?L\.?A?\.?|A\.?L\.?M\.?|G\.?\s*L\.?)\s+(?:ch\.?|c\.?)\s*(\w+),?\s*§\s*([\w./-]+(?:\([^)]*\))*(?:\s*et\s+seq\.?)?)/g,description:`Massachusetts chapter-based citations (e.g., "Mass. Gen. Laws ch. 93A, § 2")`,type:`statute`},{id:`chapter-act`,regex:/\b(\d+)\s+(?:ILCS|Ill\.?\s*Comp\.?\s*Stat\.?)\s*(?:Ann\.?\s+)?(\d+)\/([^\s(]+(?:\([^)]*\))*(?:\s*et\s+seq\.?)?)/g,description:`Illinois Compiled Statutes chapter-act citations (e.g., "735 ILCS 5/2-1001")`,type:`statute`},{id:`abbreviated-code`,regex:/\b(?:(\d+)\s+)?(Fla\.?\s*Stat(?:utes)?\.?(?:\s*Ann\.?)?|F\.?S\.?|R\.?C\.?|O\.?R\.?C\.?|Ohio\s+Rev\.?\s+Code(?:\s+Ann\.?)?|MCL[AS]?|M\.?C\.?L\.?|Mich\.?\s+Comp\.?\s+Laws(?:\s+(?:Ann|Serv)\.?)?|Utah\s+Code(?:\s+Ann\.?)?|U\.?C\.?A\.?|C\.?R\.?S\.?|Colo\.?\s+Rev\.?\s+Stat\.?(?:\s+Ann\.?)?|RCW|Wash\.?\s+Rev\.?\s+Code(?:\s+Ann\.?)?|G\.?S\.?|N\.?C\.?\s*Gen\.?\s*Stat\.?(?:\s+Ann\.?)?|N\.?C\.?G\.?S\.?|O\.?C\.?G\.?A\.?|Ga\.?\s+Code(?:\s+Ann\.?)?|Pa\.?\s*C\.?S\.?A?\.?|Pa\.?\s+Cons\.?\s+Stat\.?|P\.?S\.?|Ind(?:iana)?\.?\s+Code(?:\s+Ann\.?)?|Burns\s+Ind\.?\s+Code(?:\s+Ann\.?)?|I\.?C\.?|N\.?J\.?\s*S(?:tat)?\.?\s*A?\.?|Del\.?\s*(?:Code(?:\s+Ann\.?)?|C\.?))\s*§?\s*(\d+[A-Za-z0-9.:/-]*(?:\([^)]*\))*(?:\s*et\s+seq\.?)?)/g,description:`Abbreviated state code citations for 12 jurisdictions (FL, OH, MI, UT, CO, WA, NC, GA, PA, IN, NJ, DE)`,type:`statute`}],g=[{id:`law-review`,regex:/\b(\d+(?:-\d+)?)\s+([A-Z][A-Za-z.\s]+)\s+(\d+)\b/g,description:`Law review citations (e.g., "120 Harv. L. Rev. 500"), validated against journals-db in Phase 3`,type:`journal`}],_=[{id:`state-vendor-neutral`,regex:/\b(\d{4})\s+([A-Z]{2}(?:\s+App\.?)?)\s+(\d+)\b/g,description:`State vendor-neutral citations (e.g., "2007 UT 49", "2017 WI 17", "2013 IL 112116")`,type:`neutral`},{id:`westlaw`,regex:/\b(\d{4})\s+WL\s+(\d+)\b/g,description:`WestLaw citations (e.g., "2021 WL 123456")`,type:`neutral`},{id:`lexis`,regex:/\b(\d{4})\s+U\.S\.(?:\s+(?:App|Dist)\.)?\s+LEXIS\s+(\d+)\b/g,description:`LexisNexis citations (e.g., "2021 U.S. LEXIS 5000", "2021 U.S. App. LEXIS 12345", "2021 U.S. Dist. LEXIS 67890")`,type:`neutral`},{id:`public-law`,regex:/\bPub\.\s?L\.(?:\s?No\.)?\s?(\d+-\d+)\b/g,description:`Public Law citations (e.g., "Pub. L. No. 117-58" or "Pub. L. 116-283")`,type:`publicLaw`},{id:`federal-register`,regex:/\b(\d+(?:-\d+)?)\s+Fed\.\s?Reg\.\s+(\d+)\b/g,description:`Federal Register citations (e.g., "86 Fed. Reg. 12345")`,type:`federalRegister`},{id:`statutes-at-large`,regex:/\b(\d+(?:-\d+)?)\s+Stat\.\s+(\d+)\b/g,description:`Statutes at Large citations (e.g., "124 Stat. 119")`,type:`statutesAtLarge`},{id:`compact-law-review`,regex:/\b(\d+(?:-\d+)?)\s+([A-Z][A-Za-z.]+L\.(?:Rev|J|Q)\.)\s+(\d+)\b/g,description:`Compact law review citations without spaces (e.g., "93 Harv.L.Rev. 752")`,type:`journal`}],v=[{id:`id`,regex:/\b[Ii]d\.(?:\s+at\s+(\d+))?/g,description:`Id. citations (e.g., "Id." or "Id. at 253")`,type:`case`},{id:`ibid`,regex:/\b[Ii]bid\.(?:\s+at\s+(\d+))?/g,description:`Ibid. citations (e.g., "Ibid." or "Ibid. at 125")`,type:`case`},{id:`supra`,regex:/\b([A-Z][a-zA-Z]+(?:(?:\s+v\.?\s+|\s+)[A-Z][a-zA-Z]+)*)\s*,?\s+supra(?:,?\s+at\s+(\d+))?/g,description:`Supra citations (e.g., "Smith, supra" or "Smith, supra, at 460")`,type:`case`},{id:`shortFormCase`,regex:/\b(\d+(?:-\d+)?)\s+([A-Z][A-Za-z.\s]+?(?:\d[a-z])?)\s+at\s+(\d+)\b/g,description:`Short-form case citations (e.g., "500 F.2d at 125")`,type:`case`}];function y(e,t=[...m,...h,...g,..._,...v]){let n=[];for(let r of t)try{let t=e.matchAll(r.regex);for(let e of t)n.push({text:e[0],span:{cleanStart:e.index,cleanEnd:e.index+e[0].length},type:r.type,patternId:r.id})}catch(e){console.warn(`Pattern ${r.id} threw error, skipping:`,e instanceof Error?e.message:String(e))}return n.sort((e,t)=>e.span.cleanStart-t.span.cleanStart),n}const b={jan:1,january:1,feb:2,february:2,mar:3,march:3,apr:4,april:4,may:5,jun:6,june:6,jul:7,july:7,aug:8,august:8,sep:9,sept:9,september:9,oct:10,october:10,nov:11,november:11,dec:12,december:12};function x(e){let t=b[e.toLowerCase().replace(/\.$/,``)];if(t===void 0)throw Error(`Invalid month name: ${e}`);return t}function S(e){let{year:t,month:n,day:r}=e;return n!==void 0&&r!==void 0?`${t}-${String(n).padStart(2,`0`)}-${String(r).padStart(2,`0`)}`:n===void 0?String(t):`${t}-${String(n).padStart(2,`0`)}`}function C(e){let t=e.match(/\b(Jan|Feb|Mar|Apr|May|Jun|Jul|Aug|Sep|Sept|Oct|Nov|Dec)\.?\s+(\d{1,2}),?\s+(\d{4})\b/i);if(t){let e=x(t[1]),n=Number.parseInt(t[2],10),r={year:Number.parseInt(t[3],10),month:e,day:n};return{iso:S(r),parsed:r}}let n=e.match(/\b(January|February|March|April|May|June|July|August|September|October|November|December)\s+(\d{1,2}),?\s+(\d{4})\b/i);if(n){let e=x(n[1]),t=Number.parseInt(n[2],10),r={year:Number.parseInt(n[3],10),month:e,day:t};return{iso:S(r),parsed:r}}let r=e.match(/\b(\d{1,2})\/(\d{1,2})\/(\d{4})\b/);if(r){let e=Number.parseInt(r[1],10),t=Number.parseInt(r[2],10),n={year:Number.parseInt(r[3],10),month:e,day:t};return{iso:S(n),parsed:n}}let i=e.match(/\b(\d{4})\b/);if(i){let e={year:Number.parseInt(i[1],10)};return{iso:S(e),parsed:e}}}function ee(e){let t=Number.parseInt(e,10);return String(t)===e?t:e}const w=/(?:Jan|Feb|Mar|Apr|May|Jun|Jul|Aug|Sep|Sept|Oct|Nov|Dec|January|February|March|April|May|June|July|August|September|October|November|December)\.?/,te=/^(\d+(?:-\d+)?)\s+([A-Za-z0-9.\s']+)\s+(\d+|_{3,}|-{3,})/,ne=/^[_-]{3,}$/,re=/,\s*(\d+)/,ie=/\(([^)]+)\)/,ae=/^(?:,\s*\d+(?:-\d+)?)*(?:\s+(?:n|note)\s*\.?\s*\d+)?\s*\(([^)]+)\)/,oe=/^,\s*(\d+(?:-\d+)?)/,T=/\([^)]+\)\s*\((en banc|per curiam)\)/i,se=/^(?:U\.?\s?S\.|S\.?\s?Ct\.|L\.?\s?Ed\.)/,E=/\d\.\s+/g,D=/([A-Z][A-Za-z0-9\s.,'&()/-]+?)\s+v(?:s)?\.?\s+([A-Za-z0-9\s.,'&()/-]+?)\s*,\s*$/,O=/\b(In re|Ex parte|Matter of|Estate of|State ex rel\.|United States ex rel\.|Application of|Petition of)\s+([A-Za-z0-9\s.,'&()/-]+?)\s*,\s*$/i;function k(e){let t=e.replace(/\s*\d{1,2}\/\d{1,2}\/\d{4}\s*$/,``).trim();return t=t.replace(/\s*\d{4}\s*$/,``).trim(),t=t.replace(/\s*,?\s*\d{1,2}\s*,?\s*$/,``).trim(),t=t.replace(RegExp(`\\s*${w.source}\\s*$`,`i`),``).trim(),t=t.replace(/,\s*$/,``).trim(),t&&/[A-Za-z]/.test(t)?t:void 0}function ce(e,t,n=150){let r=Math.max(0,t-n),i=e.substring(r,t),a=r,o=-1,s;for(;(s=E.exec(i))!==null;)o=s.index+s[0].length;o!==-1&&(i=i.substring(o),a=r+o);let c=D.exec(i);if(c&&!c[0].includes(`;`))return{caseName:`${c[1].trim()} v. ${c[2].trim()}`,nameStart:a+c.index};let l=O.exec(i);if(l&&!l[0].includes(`;`))return{caseName:`${l[1]} ${l[2].trim()}`,nameStart:a+l.index}}function le(e,t,n=200){let r=t,i=Math.min(e.length,t+n),a=0,o=!1;for(;r<i;){let t=e[r];if(t===`(`)a++,o=!0,r++;else if(t===`)`){if(a--,r++,a===0){let t=r;for(;t<i&&/\s/.test(e[t]);)t++;if(e[t]===`(`){r=t;continue}let n=e.substring(t,i);if(/^,\s*(aff'd|rev'd|cert\.\s*denied|overruled\s+by|vacated\s+by)/i.test(n)){r=t;continue}return r}}else r++}return o?r:t}function A(e){let t={},n=C(e);n&&(t.date=n,t.year=n.parsed.year);let r=k(e);return r&&(t.court=r),/\ben banc\b/i.test(e)?t.disposition=`en banc`:/\bper curiam\b/i.test(e)&&(t.disposition=`per curiam`),t}function j(e){let t=e;t=t.replace(/\bet\s+al\.?/gi,``),t=t.replace(/\s+d\/b\/a\b.*/gi,``),t=t.replace(/\s+aka\b.*/gi,``);let n=``;for(;n!==t;)n=t,t=t.replace(/,?\s*(Inc|LLC|Corp|Ltd|Co|LLP|LP|P\.C)\.?$/gi,``);return t=t.replace(/^(The|A|An)\s+/i,``),t=t.replace(/\s+/g,` `),t.trim().toLowerCase()}function ue(e){for(let t of[`In re`,`Ex parte`,`Matter of`,`State ex rel.`,`United States ex rel.`,`Application of`,`Petition of`,`Estate of`]){let n=RegExp(`^(${t})\\s+(.+)$`,`i`).exec(e);if(n){let t=n[1],r=n[2];if(/\s+v\.?\s+/i.test(r)){let t=/^(.+?)\s+v\.?\s+(.+)$/i.exec(e);if(t){let e=t[1].trim(),n=t[2].trim();return{plaintiff:e,plaintiffNormalized:j(e),defendant:n,defendantNormalized:j(n)}}}else return{plaintiff:e,plaintiffNormalized:j(r),proceduralPrefix:t}}}let t=/^(.+?)\s+v\.?\s+(.+)$/i.exec(e);if(t){let e=t[1].trim(),n=t[2].trim();return e=e.replace(/^(?:In(?!\s+re\b)|See(?:\s+[Aa]lso)?|Compare|But(?:\s+[Ss]ee)?|Cf\.?|Also)\s+/i,``).trim(),{plaintiff:e||t[1].trim(),plaintiffNormalized:j(e||t[1].trim()),defendant:n,defendantNormalized:j(n)}}return{}}function M(e,t,n){let{text:r,span:i}=e,a=te.exec(r);if(!a)throw Error(`Failed to parse case citation: ${r}`);let o=ee(a[1]),s=a[2].trim(),c=a[3],l=ne.test(c),u=l?void 0:Number.parseInt(c,10),d=l?!0:void 0,f=re.exec(r),p=f?Number.parseInt(f[1],10):void 0,m,h,g,_,v,y,b,x=ie.exec(r);if(x){b=x[1];let e=A(b);m=e.year,h=e.court,g=e.date,_=e.disposition}if(n&&!b){let e=n.substring(i.cleanEnd),t=ae.exec(e);if(t){b=t[1];let n=A(b);if(m=n.year,h=n.court,g=n.date,_=n.disposition,p===void 0){let t=oe.exec(e);t&&(p=Number.parseInt(t[1],10))}}}if(n&&!_){let e=n.substring(i.cleanEnd),t=T.exec(e);t&&(_=t[1].toLowerCase())}if(!h&&se.test(s)&&(h=`scotus`),n){let e=ce(n,i.cleanStart);if(e){v=e.caseName;let r=le(n,i.cleanEnd),a=e.nameStart,o=r>i.cleanEnd?r:i.cleanEnd;y={cleanStart:a,cleanEnd:o,originalStart:t.cleanToOriginal.get(a)??a,originalEnd:t.cleanToOriginal.get(o)??o}}}let S,C,w,E,D;if(v){let e=ue(v);S=e.plaintiff,C=e.plaintiffNormalized,w=e.defendant,E=e.defendantNormalized,D=e.proceduralPrefix}let O=t.cleanToOriginal.get(i.cleanStart)??i.cleanStart,k=t.cleanToOriginal.get(i.cleanEnd)??i.cleanEnd,j=.5;if(`F.,F.2d,F.3d,F.4th,U.S.,S. Ct.,L. Ed.,P.,P.2d,P.3d,A.,A.2d,A.3d,N.E.,N.E.2d,N.E.3d,N.W.,N.W.2d,S.E.,S.E.2d,S.W.,S.W.2d,S.W.3d,So.,So. 2d,So. 3d`.split(`,`).some(e=>s.includes(e))&&(j+=.3),m!==void 0){let e=new Date().getFullYear();m<=e&&(j+=.2)}return j=Math.min(j,1),d&&(j=.8),{type:`case`,text:r,span:{cleanStart:i.cleanStart,cleanEnd:i.cleanEnd,originalStart:O,originalEnd:k},confidence:j,matchedText:r,processTimeMs:0,patternsChecked:1,volume:o,reporter:s,page:u,pincite:p,court:h,year:m,hasBlankPage:d,date:g,fullSpan:y,caseName:v,disposition:_,plaintiff:S,plaintiffNormalized:C,defendant:w,defendantNormalized:E,proceduralPrefix:D}}const N=/^([^(]+?)\s*((?:\([^)]*\))*)$/,P=/\s*et\s+seq\.?\s*$/i;function F(e){let t=e.replace(P,``),n=t!==e,r=t.trim(),i=N.exec(r),a=i?.[2];return i!==null&&a?{section:i[1].trim(),subsection:a,hasEtSeq:n}:{section:r,hasEtSeq:n}}const I=/^(?:(\d+)\s+)?(.+?)\s*§?\s*(\d+[A-Za-z0-9.:/-]*(?:\([^)]*\))*(?:\s*et\s+seq\.?)?)$/;function L(t,n){let{text:r,span:i}=t,a=I.exec(r),o,s,c;a?(o=a[1]?Number.parseInt(a[1],10):void 0,s=a[2].trim(),c=a[3]):(s=r,c=``);let l=e.n(s),u=l?.jurisdiction,d=s,{section:f,subsection:p,hasEtSeq:m}=F(c),h=n.cleanToOriginal.get(i.cleanStart)??i.cleanStart,g=n.cleanToOriginal.get(i.cleanEnd)??i.cleanEnd,_=r.includes(`§`),v;return v=l&&_?.95:l?.85:_?.6:.4,o!==void 0&&(v+=.05),p&&(v+=.05),v=Math.min(v,1),{type:`statute`,text:r,span:{cleanStart:i.cleanStart,cleanEnd:i.cleanEnd,originalStart:h,originalEnd:g},confidence:v,matchedText:r,processTimeMs:0,patternsChecked:1,title:o,code:d,section:f,subsection:p,pincite:p,jurisdiction:u,hasEtSeq:m||void 0}}const R=/^(\d+)\s+(?:ILCS|Ill\.?\s*Comp\.?\s*Stat\.?)\s*(?:Ann\.?\s+)?(\d+)\/(.+)$/;function z(e,t){let{text:n,span:r}=e,i=R.exec(n),a,o,s;i?(a=Number.parseInt(i[1],10),o=i[2],s=i[3]):(o=n,s=``);let{section:c,subsection:l,hasEtSeq:u}=F(s),d=t.cleanToOriginal.get(r.cleanStart)??r.cleanStart,f=t.cleanToOriginal.get(r.cleanEnd)??r.cleanEnd,p=i?.95:.3;return l&&(p+=.05),p=Math.min(p,1),{type:`statute`,text:n,span:{cleanStart:r.cleanStart,cleanEnd:r.cleanEnd,originalStart:d,originalEnd:f},confidence:p,matchedText:n,processTimeMs:0,patternsChecked:1,title:a,code:o,section:c,subsection:l,pincite:l,jurisdiction:i?`IL`:void 0,hasEtSeq:u||void 0}}const B=/^(\d+)\s+(\S+(?:\.\S+)*)\s*§§?\s*(.+)$/,V=/^(\d+)\s+(\S+(?:\.\S+)*)\s+(?:Part|pt\.)\s+(.+)$/;function H(e,t){let{text:n,span:r}=e,i=B.exec(n)??V.exec(n),a,o,s;i?(a=Number.parseInt(i[1],10),o=i[2],s=i[3]):(o=e.patternId===`cfr`?`C.F.R.`:`U.S.C.`,s=n,a=void 0);let{section:c,subsection:l,hasEtSeq:u}=F(s),d=t.cleanToOriginal.get(r.cleanStart)??r.cleanStart,f=t.cleanToOriginal.get(r.cleanEnd)??r.cleanEnd,p=.95;return a!==void 0&&(p+=.05),l&&(p+=.05),p=Math.min(p,1),{type:`statute`,text:n,span:{cleanStart:r.cleanStart,cleanEnd:r.cleanEnd,originalStart:d,originalEnd:f},confidence:p,matchedText:n,processTimeMs:0,patternsChecked:1,title:a,code:o,section:c,subsection:l,pincite:l,jurisdiction:`US`,hasEtSeq:u||void 0}}const U=/^(N\.?\s*Y\.?|Cal(?:ifornia)?\.?|Tex(?:as)?\.?|Md\.?|Va\.?|Ala(?:bama)?\.?)\s+(.*?)\s*§§?\s*(.+)$/s,de=/^(.*?)\s+(?:ch\.?|c\.?)\s*(\w+),?\s*§\s*(.+)$/,fe={"n.y.":`NY`,"n.y":`NY`,ny:`NY`,"cal.":`CA`,cal:`CA`,"california.":`CA`,california:`CA`,"tex.":`TX`,tex:`TX`,"texas.":`TX`,texas:`TX`,"md.":`MD`,md:`MD`,"va.":`VA`,va:`VA`,"ala.":`AL`,ala:`AL`,"alabama.":`AL`,alabama:`AL`};function pe(e){return fe[e.toLowerCase().replace(/\s+/g,``)]}function me(e){return e.replace(/^\s*Code\s+Ann\.\s*,\s*/i,``).replace(/^\s*Code\s*,\s*/i,``).replace(/\s+Code\s*$/i,``).replace(/\s+Ann\.?\s*$/i,``).replace(/,\s*$/,``).trim()}function he(t,n){let{text:r,span:i}=t,a,o,s;if(t.patternId===`mass-chapter`){let e=de.exec(r);e?(a=`MA`,o=e[2],s=e[3]):(o=r,s=``)}else{let t=U.exec(r);if(t){a=pe(t[1]);let n=t[2],r=me(n);o=a&&e.r(a,r)?r:n.trim(),s=t[3]}else o=r,s=``}let{section:c,subsection:l,hasEtSeq:u}=F(s),d=n.cleanToOriginal.get(i.cleanStart)??i.cleanStart,f=n.cleanToOriginal.get(i.cleanEnd)??i.cleanEnd,p=a?.95:.5;return l&&(p+=.05),p=Math.min(p,1),{type:`statute`,text:r,span:{cleanStart:i.cleanStart,cleanEnd:i.cleanEnd,originalStart:d,originalEnd:f},confidence:p,matchedText:r,processTimeMs:0,patternsChecked:1,code:o,section:c,subsection:l,pincite:l,jurisdiction:a,hasEtSeq:u||void 0}}const ge=/[Ss]ection\s+(\d+[A-Za-z0-9-]*)((?:\([^)]*\))*)\s+of\s+title\s+(\d+)/;function _e(e,t){let{text:n,span:r}=e,i=ge.exec(n),a,o,s;i?(a=i[1],o=i[2]||void 0,s=Number.parseInt(i[3],10)):a=n;let c=t.cleanToOriginal.get(r.cleanStart)??r.cleanStart,l=t.cleanToOriginal.get(r.cleanEnd)??r.cleanEnd,u=.85;return s!==void 0&&(u+=.05),o&&(u+=.05),u=Math.min(u,1),{type:`statute`,text:n,span:{cleanStart:r.cleanStart,cleanEnd:r.cleanEnd,originalStart:c,originalEnd:l},confidence:u,matchedText:n,processTimeMs:0,patternsChecked:1,title:s,code:`U.S.C.`,section:a,subsection:o,pincite:o,jurisdiction:`US`}}function ve(e,t){let{text:n,span:r}=e,i=/^(?:(\d+)\s+)?([A-Za-z.\s]+?)\s*§+\s*(\d+[A-Za-z0-9-]*)/.exec(n);if(!i){let e=t.cleanToOriginal.get(r.cleanStart)??r.cleanStart,i=t.cleanToOriginal.get(r.cleanEnd)??r.cleanEnd;return{type:`statute`,text:n,span:{cleanStart:r.cleanStart,cleanEnd:r.cleanEnd,originalStart:e,originalEnd:i},confidence:.3,matchedText:n,processTimeMs:0,patternsChecked:1,code:n,section:``}}let a=i[1]?Number.parseInt(i[1],10):void 0,o=i[2].trim(),s=i[3],c=t.cleanToOriginal.get(r.cleanStart)??r.cleanStart,l=t.cleanToOriginal.get(r.cleanEnd)??r.cleanEnd,u=.5;return[`U.S.C.`,`C.F.R.`,`Cal. Civ. Code`,`Cal. Penal Code`,`N.Y. Civ. Prac. L. & R.`,`Tex. Civ. Prac. & Rem. Code`].some(e=>o.includes(e))&&(u+=.3),u=Math.min(u,1),{type:`statute`,text:n,span:{cleanStart:r.cleanStart,cleanEnd:r.cleanEnd,originalStart:c,originalEnd:l},confidence:u,matchedText:n,processTimeMs:0,patternsChecked:1,title:a,code:o,section:s}}function W(e,t){switch(e.patternId){case`usc`:case`cfr`:return H(e,t);case`prose`:return _e(e,t);case`abbreviated-code`:return L(e,t);case`named-code`:case`mass-chapter`:return he(e,t);case`chapter-act`:return z(e,t);default:return ve(e,t)}}function G(e,t){let{text:n,span:r}=e,i=/^(\d+(?:-\d+)?)\s+([A-Za-z.\s]+?)\s+(\d+)/.exec(n);if(!i)throw Error(`Failed to parse journal citation: ${n}`);let a=i[1],o=/^\d+$/.test(a)?Number.parseInt(a,10):a,s=i[2].trim(),c=Number.parseInt(i[3],10),l=/,\s*(\d+)/.exec(n),u=l?Number.parseInt(l[1],10):void 0,d=t.cleanToOriginal.get(r.cleanStart)??r.cleanStart,f=t.cleanToOriginal.get(r.cleanEnd)??r.cleanEnd;return{type:`journal`,text:n,span:{cleanStart:r.cleanStart,cleanEnd:r.cleanEnd,originalStart:d,originalEnd:f},confidence:.6,matchedText:n,processTimeMs:0,patternsChecked:1,volume:o,journal:s,abbreviation:s,page:c,pincite:u}}function K(e,t){let{text:n,span:r}=e,i=/^(\d{4})\s+(.+?)\s+(\d+)$/.exec(n);if(!i)throw Error(`Failed to parse neutral citation: ${n}`);let a=Number.parseInt(i[1],10),o=i[2],s=i[3],c=t.cleanToOriginal.get(r.cleanStart)??r.cleanStart,l=t.cleanToOriginal.get(r.cleanEnd)??r.cleanEnd;return{type:`neutral`,text:n,span:{cleanStart:r.cleanStart,cleanEnd:r.cleanEnd,originalStart:c,originalEnd:l},confidence:1,matchedText:n,processTimeMs:0,patternsChecked:1,year:a,court:o,documentNumber:s}}function q(e,t){let{text:n,span:r}=e,i=/Pub\.\s?L\.(?:\s?No\.)?\s?(\d+)-(\d+)/.exec(n);if(!i)throw Error(`Failed to parse public law citation: ${n}`);let a=Number.parseInt(i[1],10),o=Number.parseInt(i[2],10),s=t.cleanToOriginal.get(r.cleanStart)??r.cleanStart,c=t.cleanToOriginal.get(r.cleanEnd)??r.cleanEnd;return{type:`publicLaw`,text:n,span:{cleanStart:r.cleanStart,cleanEnd:r.cleanEnd,originalStart:s,originalEnd:c},confidence:.9,matchedText:n,processTimeMs:0,patternsChecked:1,congress:a,lawNumber:o}}function J(e,t){let{text:n,span:r}=e,i=/^(\d+(?:-\d+)?)\s+Fed\.\s?Reg\.\s+(\d+)/.exec(n);if(!i)throw Error(`Failed to parse Federal Register citation: ${n}`);let a=i[1],o=/^\d+$/.test(a)?Number.parseInt(a,10):a,s=Number.parseInt(i[2],10),c=/\((?:.*?\s)?(\d{4})\)/.exec(n),l=c?Number.parseInt(c[1],10):void 0,u=t.cleanToOriginal.get(r.cleanStart)??r.cleanStart,d=t.cleanToOriginal.get(r.cleanEnd)??r.cleanEnd;return{type:`federalRegister`,text:n,span:{cleanStart:r.cleanStart,cleanEnd:r.cleanEnd,originalStart:u,originalEnd:d},confidence:.9,matchedText:n,processTimeMs:0,patternsChecked:1,volume:o,page:s,year:l}}function Y(e,t){let{text:n,span:r}=e,i=/^(\d+(?:-\d+)?)\s+Stat\.\s+(\d+)/.exec(n);if(!i)throw Error(`Failed to parse Statutes at Large citation: ${n}`);let a=i[1],o=/^\d+$/.test(a)?Number.parseInt(a,10):a,s=Number.parseInt(i[2],10),c=/\((?:.*?\s)?(\d{4})\)/.exec(n),l=c?Number.parseInt(c[1],10):void 0,u=t.cleanToOriginal.get(r.cleanStart)??r.cleanStart,d=t.cleanToOriginal.get(r.cleanEnd)??r.cleanEnd;return{type:`statutesAtLarge`,text:n,span:{cleanStart:r.cleanStart,cleanEnd:r.cleanEnd,originalStart:u,originalEnd:d},confidence:.9,matchedText:n,processTimeMs:0,patternsChecked:1,volume:o,page:s,year:l}}function ye(e,t){let{text:n,span:r}=e,i=/[Ii](?:d|bid)\.(?:\s+at\s+(\d+))?/.exec(n);if(!i)throw Error(`Failed to parse Id. citation: ${n}`);let a=i[1]?Number.parseInt(i[1],10):void 0,o=t.cleanToOriginal.get(r.cleanStart)??r.cleanStart,s=t.cleanToOriginal.get(r.cleanEnd)??r.cleanEnd;return{type:`id`,text:n,span:{cleanStart:r.cleanStart,cleanEnd:r.cleanEnd,originalStart:o,originalEnd:s},confidence:1,matchedText:n,processTimeMs:0,patternsChecked:1,pincite:a}}function be(e,t){let{text:n,span:r}=e,i=/\b([A-Z][a-zA-Z]+(?:(?:\s+v\.?\s+|\s+)[A-Z][a-zA-Z]+)*)\s*,?\s+supra(?:,?\s+at\s+(\d+))?/.exec(n);if(!i)throw Error(`Failed to parse supra citation: ${n}`);let a=i[1],o=i[2]?Number.parseInt(i[2],10):void 0,s=t.cleanToOriginal.get(r.cleanStart)??r.cleanStart,c=t.cleanToOriginal.get(r.cleanEnd)??r.cleanEnd;return{type:`supra`,text:n,span:{cleanStart:r.cleanStart,cleanEnd:r.cleanEnd,originalStart:s,originalEnd:c},confidence:.9,matchedText:n,processTimeMs:0,patternsChecked:1,partyName:a,pincite:o}}function xe(e,t){let{text:n,span:r}=e,i=/(\d+(?:-\d+)?)\s+([A-Z][A-Za-z.\s]+?(?:\d[a-z])?)\s+at\s+(\d+)/.exec(n);if(!i)throw Error(`Failed to parse short-form case citation: ${n}`);let a=i[1],o=/^\d+$/.test(a)?Number.parseInt(a,10):a,s=i[2].trim(),c=Number.parseInt(i[3],10),l=t.cleanToOriginal.get(r.cleanStart)??r.cleanStart,u=t.cleanToOriginal.get(r.cleanEnd)??r.cleanEnd;return{type:`shortFormCase`,text:n,span:{cleanStart:r.cleanStart,cleanEnd:r.cleanEnd,originalStart:l,originalEnd:u},confidence:.7,matchedText:n,processTimeMs:0,patternsChecked:1,volume:o,reporter:s,pincite:c}}function Se(e,t,n=/\n\n+/g){let r=new Map,i=[0],a;for(;(a=n.exec(e))!==null;)i.push(a.index+a[0].length);i.push(e.length);for(let e=0;e<t.length;e++){let n=t[e].span.originalStart,a=0;for(let e=0;e<i.length-1;e++)if(n>=i[e]&&n<i[e+1]){a=e;break}r.set(e,a)}return r}function Ce(e,t,n,r){if(r===`none`)return!0;let i=n.get(e),a=n.get(t);return i===void 0||a===void 0?!0:i===a}function X(e,t){if(e.length===0)return t.length;if(t.length===0)return e.length;let n=Array.from({length:e.length+1},()=>Array(t.length+1).fill(0));for(let t=0;t<=e.length;t++)n[t][0]=t;for(let e=0;e<=t.length;e++)n[0][e]=e;for(let r=1;r<=e.length;r++)for(let i=1;i<=t.length;i++)e[r-1]===t[i-1]?n[r][i]=n[r-1][i-1]:n[r][i]=1+Math.min(n[r-1][i],n[r][i-1],n[r-1][i-1]);return n[e.length][t.length]}function we(e,t){let n=e.toLowerCase(),r=t.toLowerCase(),i=X(n,r),a=Math.max(n.length,r.length);return a===0?1:1-i/a}var Z=class{constructor(e,t,n={}){this.citations=e,this.text=t,this.options={scopeStrategy:n.scopeStrategy??`paragraph`,autoDetectParagraphs:n.autoDetectParagraphs??!0,paragraphBoundaryPattern:n.paragraphBoundaryPattern??/\n\n+/g,fuzzyPartyMatching:n.fuzzyPartyMatching??!0,partyMatchThreshold:n.partyMatchThreshold??.8,allowNestedResolution:n.allowNestedResolution??!1,reportUnresolved:n.reportUnresolved??!0},this.context={citationIndex:0,allCitations:e,lastFullCitation:void 0,fullCitationHistory:new Map,paragraphMap:new Map},this.options.autoDetectParagraphs&&(this.context.paragraphMap=Se(t,e,this.options.paragraphBoundaryPattern))}resolve(){let e=[];for(let n=0;n<this.citations.length;n++){this.context.citationIndex=n;let r=this.citations[n],i;switch(r.type){case`id`:i=this.resolveId(r);break;case`supra`:i=this.resolveSupra(r);break;case`shortFormCase`:i=this.resolveShortFormCase(r);break;default:t(r)&&(this.context.lastFullCitation=n,this.trackFullCitation(r,n));break}e.push({...r,resolution:i})}return e}resolveId(e){let t=this.context.citationIndex,n;for(let e=t-1;e>=0;e--)if(this.citations[e].type===`case`){n=e;break}return n===void 0?this.createFailureResult(`No preceding full case citation found`):this.isWithinScope(n,t)?{resolvedTo:n,confidence:1}:this.createFailureResult(`Antecedent citation outside scope boundary`)}resolveSupra(e){let t=this.context.citationIndex,n=this.normalizePartyName(e.partyName),r;for(let[e,i]of this.context.fullCitationHistory){if(!this.isWithinScope(i,t))continue;let a=we(n,e);(!r||a>r.similarity)&&(r={index:i,similarity:a})}if(!r)return this.createFailureResult(`No full citation found in scope`);if(r.similarity<this.options.partyMatchThreshold)return this.createFailureResult(`Party name similarity ${r.similarity.toFixed(2)} below threshold ${this.options.partyMatchThreshold}`);let i=[];return r.similarity<1&&i.push(`Fuzzy match: similarity ${r.similarity.toFixed(2)}`),{resolvedTo:r.index,confidence:r.similarity,warnings:i.length>0?i:void 0}}resolveShortFormCase(e){let t=this.context.citationIndex;for(let n=t-1;n>=0;n--){let r=this.citations[n];if(r.type===`case`&&r.volume===e.volume&&this.normalizeReporter(r.reporter)===this.normalizeReporter(e.reporter))return this.isWithinScope(n,t)?{resolvedTo:n,confidence:.95}:this.createFailureResult(`Matching citation outside scope boundary`)}return this.createFailureResult(`No matching full case citation found`)}trackFullCitation(e,t){if(e.type===`case`&&(e.defendantNormalized&&this.context.fullCitationHistory.set(e.defendantNormalized,t),e.plaintiffNormalized&&this.context.fullCitationHistory.set(e.plaintiffNormalized,t),!e.plaintiffNormalized&&!e.defendantNormalized)){let n=this.extractPartyName(e);if(n){let e=this.normalizePartyName(n);this.context.fullCitationHistory.set(e,t)}}}extractPartyName(e){let t=e.span.originalStart,n=Math.max(0,t-100),r=this.text.substring(n,t),i=r.match(/([A-Z][a-zA-Z]*(?:\s+[A-Z][a-zA-Z]*)*)\s+v\.?\s+[A-Z][a-zA-Z]*(?:\s+[A-Z][a-zA-Z]*)*,\s*$/);if(i)return this.stripSignalWords(i[1].trim());let a=r.match(/([A-Z][a-zA-Z]*(?:\s+[A-Z][a-zA-Z]*)*),\s*$/);if(a)return this.stripSignalWords(a[1].trim())}stripSignalWords(e){let t=e.replace(/^(?:In(?!\s+re\b)|See(?:\s+[Aa]lso)?|Compare|But(?:\s+[Ss]ee)?|Cf\.?|Also)\s+/i,``).trim();return t.length>0?t:e}normalizePartyName(e){return e.toLowerCase().replace(/\s+/g,` `).trim()}normalizeReporter(e){return e.toLowerCase().replace(/\s+/g,``).replace(/\./g,``)}isWithinScope(e,t){return Ce(e,t,this.context.paragraphMap,this.options.scopeStrategy)}createFailureResult(e){if(this.options.reportUnresolved)return{resolvedTo:void 0,failureReason:e,confidence:0}}};function Q(e,t,n){return new Z(e,t,n).resolve()}function Te(e,t=``){let n=new Map;if(e.length===0||t===``)return n;let r=new Set;for(let i=0;i<e.length;i++){let a=e[i];if(a.type!==`case`||r.has(i))continue;let o=[];for(let n=i+1;n<e.length;n++){let s=e[n];if(s.type!==`case`)break;let c=(n===i+1?a:e[n-1]).span.cleanEnd,l=s.span.cleanStart;if(l-c>20)break;let u=t.substring(c,l);if(!u.includes(`,`))break;let d=u.indexOf(`,`);if(u.length-d-1>5||t.substring(a.span.cleanEnd,s.span.cleanEnd).includes(`)`)||!Ee(t,s.span.cleanEnd))break;o.push(n),r.add(n)}o.length>0&&n.set(i,o)}return n}function Ee(e,t){let n=e.substring(t,t+200),r=n.indexOf(`(`);if(r===-1)return!1;let i=0;for(let e=r;e<n.length;e++)if(n[e]===`(`)i++;else if(n[e]===`)`&&(i--,i===0))return!0;return!1}function $(e,t){let n=performance.now(),{cleaned:r,transformationMap:i,warnings:a}=f(e,t?.cleaners),o=y(r,t?.patterns||[..._,...v,...m,...h,...g]),s=[],c=new Set,l=r.length<65536;for(let e of o){let t=l?e.span.cleanStart<<16|e.span.cleanEnd:`${e.span.cleanStart}-${e.span.cleanEnd}`;c.has(t)||(c.add(t),s.push(e))}let u=Te(s,r),d=[];for(let e=0;e<s.length;e++){let t=s[e],o;switch(t.type){case`case`:o=t.patternId===`id`||t.patternId===`ibid`?ye(t,i):t.patternId===`supra`?be(t,i):t.patternId===`shortFormCase`?xe(t,i):M(t,i,r);break;case`statute`:o=W(t,i);break;case`journal`:o=G(t,i);break;case`neutral`:o=K(t,i);break;case`publicLaw`:o=q(t,i);break;case`federalRegister`:o=J(t,i);break;case`statutesAtLarge`:o=Y(t,i);break;default:continue}if(a.length>0&&(o.warnings=[...o.warnings||[],...a]),o.processTimeMs=performance.now()-n,o.type===`case`){let t=u.has(e),n=Array.from(u.values()).some(t=>t.includes(e));if(t||n){let r=e;if(n){for(let[t,n]of u.entries())if(n.includes(e)){r=t;break}}let i=s[r],a=/^(\S+)\s+(.+)\s+(\d+)$/.exec(i.text);if(a){let[,n,r,i]=a;if(o.groupId=`${n}-${r.replace(/\s+/g,`.`)}-${i}`,t){let t=u.get(e);o.parallelCitations=t.map(e=>{let t=s[e],n=/^(\S+)\s+(.+)\s+(\d+)$/.exec(t.text);if(n){let[,e,t,r]=n;return{volume:/^\d+$/.test(e)?Number.parseInt(e,10):e,reporter:t,page:Number.parseInt(r,10)}}return{volume:0,reporter:``,page:0}})}}}}d.push(o)}return t?.resolve?Q(d,e,t.resolutionOptions):d}async function De(e,t){return $(e,t)}exports.DocumentResolver=Z,exports.assertUnreachable=a,exports.cleanText=f,exports.extractCase=M,exports.extractCitations=$,exports.extractCitationsAsync=De,exports.extractFederalRegister=J,exports.extractJournal=G,exports.extractNeutral=K,exports.extractPublicLaw=q,exports.extractStatute=W,exports.extractStatutesAtLarge=Y,exports.isCaseCitation=r,exports.isCitationType=i,exports.isFullCitation=t,exports.isShortFormCitation=n,exports.resolveCitations=Q,exports.tokenize=y;
2
2
  //# sourceMappingURL=index.cjs.map