flappa-doormal 2.8.0 → 2.10.0

package/dist/index.d.mts

@@ -218,6 +218,28 @@ type LineEndsWithPattern = {
  * - `lineEndsWith` - Match line endings
  */
 type PatternType = RegexPattern | TemplatePattern | LineStartsWithPattern | LineStartsAfterPattern | LineEndsWithPattern;
+/**
+ * Pattern type key names for split rules.
+ *
+ * Use this array to dynamically iterate over pattern types in UIs,
+ * or use the `PatternTypeKey` type for type-safe string unions.
+ *
+ * @example
+ * // Build a dropdown/select in UI
+ * PATTERN_TYPE_KEYS.map(key => <option value={key}>{key}</option>)
+ *
+ * @example
+ * // Type-safe pattern key validation
+ * const validateKey = (k: string): k is PatternTypeKey =>
+ *   (PATTERN_TYPE_KEYS as readonly string[]).includes(k);
+ */
+declare const PATTERN_TYPE_KEYS: readonly ["lineStartsWith", "lineStartsAfter", "lineEndsWith", "template", "regex"];
+/**
+ * String union of pattern type key names.
+ *
+ * Derived from `PATTERN_TYPE_KEYS` to stay in sync automatically.
+ */
+type PatternTypeKey = (typeof PATTERN_TYPE_KEYS)[number];
 /**
  * Configuration for how and where to split content when a pattern matches.
  *
@@ -238,38 +260,9 @@ type SplitBehavior = {
    * - `'first'`: Only split at the first match
    * - `'last'`: Only split at the last match
    *
-   * When `maxSpan` is set, occurrence filtering is applied per sliding
-   * window rather than globally. With `'last'`, the algorithm prefers
-   * longer segments by looking as far ahead as allowed before selecting
-   * the last match in the window.
-   *
    * @default 'all'
    */
   occurrence?: 'first' | 'last' | 'all';
-  /**
-   * Maximum page ID difference allowed when looking ahead for split points.
-   *
-   * Uses a sliding window algorithm that prefers longer segments:
-   * 1. Start from the first page of the current segment
-   * 2. Look for matches within pages where `pageId - startPageId <= maxSpan`
-   * 3. Apply occurrence filter (e.g., 'last') to select a match
-   * 4. Next window starts from the page after the match
-   *
-   * Examples:
-   * - `maxSpan: 1` = look 1 page ahead (segments span at most 2 pages)
-   * - `maxSpan: 2` = look 2 pages ahead (segments span at most 3 pages)
-   * - `undefined` = no limit (entire content treated as one group)
-   *
-   * Note: With non-consecutive page IDs, the algorithm uses actual ID
-   * difference, not array index. Pages 1 and 5 have a difference of 4.
-   *
-   * @example
-   * // Split at last period, looking up to 1 page ahead
-   * // Pages 1,2: split at page 2's last period
-   * // Page 3: split at page 3's last period
-   * { lineEndsWith: ['.'], split: 'after', occurrence: 'last', maxSpan: 1 }
-   */
-  maxSpan?: number;
   /**
    * Enable diacritic-insensitive matching for Arabic text.
    *
@@ -354,12 +347,6 @@ type RuleConstraints = {
    * { lineStartsWith: ['{{bab}}'], split: 'before', meta: { type: 'chapter' } }
    */
   meta?: Record<string, unknown>;
-  /**
-   * Fallback behavior when no matches are found within a maxSpan boundary.
-   * - 'page': Create split points at page boundaries
-   * - undefined: No fallback (current behavior)
-   */
-  fallback?: 'page';
   /**
    * Page-start guard: only allow this rule to match at the START of a page if the
    * previous page's last non-whitespace character matches this pattern.
@@ -388,7 +375,7 @@ type RuleConstraints = {
  * Each rule must specify:
  * - **Pattern** (exactly one): `regex`, `template`, `lineStartsWith`,
  *   `lineStartsAfter`, or `lineEndsWith`
- * - **Split behavior**: `split` (optional, defaults to `'at'`), `occurrence`, `maxSpan`, `fuzzy`
+ * - **Split behavior**: `split` (optional, defaults to `'at'`), `occurrence`, `fuzzy`
  * - **Constraints** (optional): `min`, `max`, `meta`
  *
  * @example
@@ -424,7 +411,6 @@ type SplitRule = PatternType & SplitBehavior & RuleConstraints;
 type Page = {
   /**
    * Unique page/entry ID used for:
-   * - `maxSpan` grouping (segments spanning multiple pages)
    * - `min`/`max` constraint filtering
    * - `from`/`to` tracking in output segments
    */
@@ -625,6 +611,21 @@ type SegmentationOptions = {
    * rule's metadata is used for each segment.
    */
   rules?: SplitRule[];
+  /**
+   * Attach debugging provenance into `segment.meta` indicating which rule and/or breakpoint
+   * created the segment boundary.
+   *
+   * This is opt-in because it increases output size.
+   *
+   * When enabled (default metaKey: `_flappa`), segments may include:
+   * `meta._flappa.rule` and/or `meta._flappa.breakpoint`.
+   */
+  debug?: boolean | {
+    /** Where to store provenance in meta. @default '_flappa' */
+    metaKey?: string;
+    /** Which kinds of provenance to include. @default ['rule','breakpoint'] */
+    include?: Array<'rule' | 'breakpoint'>;
+  };
   /**
    * Maximum pages per segment before breakpoints are applied.
    *
@@ -766,11 +767,51 @@ type Segment = {
   meta?: Record<string, unknown>;
 };
 //#endregion
+//#region src/segmentation/optimize-rules.d.ts
+/**
+ * Result from optimizing rules.
+ */
+type OptimizeResult = {
+  /** Optimized rules (merged and sorted by specificity) */
+  rules: SplitRule[];
+  /** Number of rules that were merged into existing rules */
+  mergedCount: number;
+};
+/**
+ * Optimize split rules by merging compatible rules and sorting by specificity.
+ *
+ * This function:
+ * 1. **Merges compatible rules**: Rules with the same pattern type and identical
+ *    options (meta, fuzzy, min/max, etc.) have their pattern arrays combined
+ * 2. **Deduplicates patterns**: Removes duplicate patterns within each rule
+ * 3. **Sorts by specificity**: Rules with longer patterns come first
+ *
+ * Only array-based pattern types (`lineStartsWith`, `lineStartsAfter`, `lineEndsWith`)
+ * can be merged. `template` and `regex` rules are kept separate.
+ *
+ * @param rules - Array of split rules to optimize
+ * @returns Optimized rules and count of merged rules
+ *
+ * @example
+ * import { optimizeRules } from 'flappa-doormal';
+ *
+ * const { rules, mergedCount } = optimizeRules([
+ *   { lineStartsWith: ['{{kitab}}'], fuzzy: true, meta: { type: 'header' } },
+ *   { lineStartsWith: ['{{bab}}'], fuzzy: true, meta: { type: 'header' } },
+ *   { lineStartsAfter: ['{{numbered}}'], meta: { type: 'entry' } },
+ * ]);
+ *
+ * // rules[0] = { lineStartsWith: ['{{kitab}}', '{{bab}}'], fuzzy: true, meta: { type: 'header' } }
+ * // rules[1] = { lineStartsAfter: ['{{numbered}}'], meta: { type: 'entry' } }
+ * // mergedCount = 1
+ */
+declare const optimizeRules: (rules: SplitRule[]) => OptimizeResult;
+//#endregion
 //#region src/segmentation/pattern-validator.d.ts
 /**
  * Types of validation issues that can be detected.
  */
-type ValidationIssueType = 'missing_braces' | 'unknown_token' | 'duplicate';
+type ValidationIssueType = 'missing_braces' | 'unknown_token' | 'duplicate' | 'empty_pattern';
 /**
  * A validation issue found in a pattern.
  */
@@ -778,6 +819,10 @@ type ValidationIssue = {
   type: ValidationIssueType;
   message: string;
   suggestion?: string;
+  /** The token name involved in the issue (for unknown_token / missing_braces) */
+  token?: string;
+  /** The specific pattern involved (for duplicate) */
+  pattern?: string;
 };
 /**
  * Validation result for a single rule, with issues keyed by pattern type.
@@ -809,6 +854,20 @@ type RuleValidationResult = {
  * // issues[1]?.lineStartsWith?.[0]?.type === 'unknown_token'
  */
 declare const validateRules: (rules: SplitRule[]) => (RuleValidationResult | undefined)[];
+/**
+ * Formats a validation result array into a list of human-readable error messages.
+ *
+ * Useful for displaying validation errors in UIs.
+ *
+ * @param results - The result array from `validateRules()`
+ * @returns Array of formatted error strings
+ *
+ * @example
+ * const issues = validateRules(rules);
+ * const errors = formatValidationReport(issues);
+ * // ["Rule 1, lineStartsWith: Missing {{}} around token..."]
+ */
+declare const formatValidationReport: (results: (RuleValidationResult | undefined)[]) => string[];
 //#endregion
 //#region src/segmentation/replace.d.ts
 /**
@@ -1148,6 +1207,63 @@ declare const getAvailableTokens: () => string[];
  * getTokenPattern('unknown') // → undefined
  */
 declare const getTokenPattern: (tokenName: string) => string | undefined;
+/**
+ * Checks if a pattern (or array of patterns) contains tokens that should
+ * default to fuzzy matching.
+ *
+ * Fuzzy-default tokens are: bab, basmalah, fasl, kitab, naql
+ *
+ * @param patterns - Single pattern string or array of pattern strings
+ * @returns `true` if any pattern contains a fuzzy-default token
+ *
+ * @example
+ * shouldDefaultToFuzzy('{{bab}} الإيمان')     // true
+ * shouldDefaultToFuzzy('{{raqms}} {{dash}}')  // false
+ * shouldDefaultToFuzzy(['{{kitab}}', '{{raqms}}']) // true
+ */
+declare const shouldDefaultToFuzzy: (patterns: string | string[]) => boolean;
+/**
+ * Structure for mapping a token to a capture name.
+ */
+type TokenMapping = {
+  token: string;
+  name: string;
+};
+/**
+ * Apply token mappings to a template string.
+ *
+ * Transforms `{{token}}` into `{{token:name}}` based on the provided mappings.
+ * Useful for applying user-configured capture names to a raw template.
+ *
+ * - Only affects exact matches of `{{token}}`.
+ * - Does NOT affect tokens that already have a capture name (e.g. `{{token:existing}}`).
+ * - Does NOT affect capture-only tokens (e.g. `{{:name}}`).
+ *
+ * @param template - The template string to transform
+ * @param mappings - Array of mappings from token name to capture name
+ * @returns Transformed template string with captures applied
+ *
+ * @example
+ * applyTokenMappings('{{raqms}} {{dash}}', [{ token: 'raqms', name: 'num' }])
+ * // → '{{raqms:num}} {{dash}}'
+ */
+declare const applyTokenMappings: (template: string, mappings: TokenMapping[]) => string;
+/**
+ * Strip token mappings from a template string.
+ *
+ * Transforms `{{token:name}}` back into `{{token}}`.
+ * Also transforms `{{:name}}` patterns (capture-only) into `{{}}` (which is invalid/empty).
+ *
+ * Useful for normalizing templates for storage or comparison.
+ *
+ * @param template - The template string to strip
+ * @returns Template string with capture names removed
+ *
+ * @example
+ * stripTokenMappings('{{raqms:num}} {{dash}}')
+ * // → '{{raqms}} {{dash}}'
+ */
+declare const stripTokenMappings: (template: string) => string;
 //#endregion
 //#region src/analysis/line-starts.d.ts
 type LineStartAnalysisOptions = {
@@ -1346,5 +1462,5 @@ declare function recoverMistakenMarkersForRuns(runs: MarkerRecoveryRun[], opts?:
   segments: Segment[];
 };
 //#endregion
-export { type Breakpoint, type BreakpointRule, type CommonLineStartPattern, type DetectedPattern, type ExpandResult, type LineStartAnalysisOptions, type LineStartPatternExample, type Logger, type MarkerRecoveryReport, type MarkerRecoveryRun, type MarkerRecoverySelector, type Page, type PageRange, type RepeatingSequenceExample, type RepeatingSequenceOptions, type RepeatingSequencePattern, type ReplaceRule, type RuleValidationResult, type Segment, type SegmentationOptions, type SplitRule, TOKEN_PATTERNS, type ValidationIssue, type ValidationIssueType, analyzeCommonLineStarts, analyzeRepeatingSequences, analyzeTextForRule, applyReplacements, containsTokens, detectTokenPatterns, escapeRegex, escapeTemplateBrackets, expandCompositeTokensInTemplate, expandTokens, expandTokensWithCaptures, generateTemplateFromText, getAvailableTokens, getTokenPattern, makeDiacriticInsensitive, recoverMistakenLineStartsAfterMarkers, recoverMistakenMarkersForRuns, segmentPages, suggestPatternConfig, templateToRegex, validateRules };
+export { type Breakpoint, type BreakpointRule, type CommonLineStartPattern, type DetectedPattern, type ExpandResult, type LineStartAnalysisOptions, type LineStartPatternExample, type Logger, type MarkerRecoveryReport, type MarkerRecoveryRun, type MarkerRecoverySelector, type OptimizeResult, PATTERN_TYPE_KEYS, type Page, type PageRange, type PatternTypeKey, type RepeatingSequenceExample, type RepeatingSequenceOptions, type RepeatingSequencePattern, type ReplaceRule, type RuleValidationResult, type Segment, type SegmentationOptions, type SplitRule, TOKEN_PATTERNS, type TokenMapping, type ValidationIssue, type ValidationIssueType, analyzeCommonLineStarts, analyzeRepeatingSequences, analyzeTextForRule, applyReplacements, applyTokenMappings, containsTokens, detectTokenPatterns, escapeRegex, escapeTemplateBrackets, expandCompositeTokensInTemplate, expandTokens, expandTokensWithCaptures, formatValidationReport, generateTemplateFromText, getAvailableTokens, getTokenPattern, makeDiacriticInsensitive, optimizeRules, recoverMistakenLineStartsAfterMarkers, recoverMistakenMarkersForRuns, segmentPages, shouldDefaultToFuzzy, stripTokenMappings, suggestPatternConfig, templateToRegex, validateRules };
 //# sourceMappingURL=index.d.mts.map

package/dist/index.d.mts.map

@@ -1 +1 @@
-{"version":3,"file":"index.d.mts","names":[],"sources":["../src/segmentation/fuzzy.ts","../src/segmentation/types.ts","../src/segmentation/pattern-validator.ts","../src/segmentation/replace.ts","../src/segmentation/segmenter.ts","../src/segmentation/tokens.ts","../src/analysis/line-starts.ts","../src/analysis/repeating-sequences.ts","../src/detection.ts","../src/recovery.ts"],"sourcesContent":[],"mappings":";;AAkEA;AA+FA;;;;;ACnIiB;AA4BG;AA8BM;AAiCC;AAwBH;;;;;;;AAoBC;AA2FzB;AAAkD;AAgIlD;;;;;AAkBA;AAqCA;AA0EY,cD/bC,WC+bqB,EAAA,CAAA,CAAA,EAAA,MAAc,EAAA,GAAA,MAAA;AA8BhD;AAuBA;AA+CA;;;;;;AAsIA;;;;AC9tBA;AAKA;AAUA;;;;;;AAwGA;;;;ACxHA;AA2DA;;;;;;;;AC6SA;;AAAqD,cJnNxC,wBImNwC,EAAA,CAAA,IAAA,EAAA,MAAA,EAAA,GAAA,MAAA;;;;AJlTrD;AA+FA;;;;;ACnIiB;AA4BG;AA8BM;AAiCC;AAwBH;;;;;;;AAoBC;AA2FzB;AAAkD;AAgIlD;;;;;AAkBA,KApXK,YAAA,GAoXW;EAqCJ;EA0EA,KAAA,EAAA,MAAU;AA8BtB,CAAA;AAuBA;AA+CA;;;;;;AAsIA;;;;AC9tBA;AAKA;AAUA;;;;;;AAwGA;;;;ACxHA,KF8CK,eAAA,GE9CkB;EA2DV;EAA4B,QAAA,EAAA,MAAA;CAAgB;;;;;;AC6SzD;;;;;;;;AChTA;AA0QA;AAsDA;AA2CA;AAWA;AAuKA;AA6CA;AAuBA;AAqBA;AAgBA;;;KJlnBK,qBAAA;EKnEO;EAcA,cAAA,EAAA,MAAA,EAAA;AAEZ,CAAA;AAwQA;;;;;;;;AClRA;AAaA;AAOA;AA2OA;;;;;;;;AC9QA;AA+EA;AAgEA;AAuBA;AAiCA;;;;AC7MA;AAKA,KR8GK,sBAAA,GQ9GwB;EAChB;EACF,eAAA,EAAA,MAAA,EAAA;CACG;;;AAId;AA2BE;AAmnBF;;;;;;;;;AAsDA;;;;;;KRrkBK,mBAAA;;;;;;;;;;;;;;KAeA,WAAA,GACC,eACA,kBACA,wBACA,yBACA;;;;;;;KAYD,aAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;KA+EO,SAAA;;;;;;;KAYP,eAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;YAyCS;;;;;;;;;;;;SAaH;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;KA8DC,SAAA,GAAY,cAAc,gBAAgB;;;;;;;;;;;;;KAkB1C,IAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;KAqCA,cAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;YAqCE;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;KAqCF,UAAA,YAAsB;;;;;;;;;;;;;;;;;;;;;;;;;UA8BjB,MAAA;;;;;;;;;;;;;;;;;;;;;;KAuBL,WAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;KA+CA,mBAAA;;;;;;YAME;;;;;;;;UASF;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;gBA8CM;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;WAwDL;;;;;;;;;;;;;;;;KAiBD,OAAA;;;;;;;;;;;;;;;;;;;;;;;;;;SA6BD;;;;AA1uBM;AA4BG;AA8BM;AAyDrB,KCpIO,mBAAA,GDoIY,gBAAA,GAAA,eAAA,GAAA,WAAA;AAAA;;;AAkBlB,KCjJM,eAAA,GDiJN;EACA,IAAA,ECjJI,mBDiJJ;EACA,OAAA,EAAA,MAAA;EAAmB,UAAA,CAAA,EAAA,MAAA;AAAA,CAAA;AA2FzB;AAAkD;AAgIlD;;AAAsC,KCpW1B,oBAAA,GDoW0B;EAAgB,cAAA,CAAA,EAAA,CCnWhC,eDmWgC,GAAA,SAAA,CAAA,EAAA;EAAe,eAAA,CAAA,EAAA,CClW9C,eDkW8C,GAAA,SAAA,CAAA,EAAA;EAkBzD,YAAI,CAAA,EAAA,CCnXI,eDmXJ,GAAA,SAAA,CAAA,EAAA;EAqCJ,QAAA,CAAA,ECvZG,eDuZW;AA0E1B,CAAA;AA8BA;AAuBA;AA+CA;;;;;;AAsIA;;;;AC9tBA;AAKA;AAUA;;;;;AAI8B,cAoGjB,aApGiB,EAAA,CAAA,KAAA,EAoGO,SApGP,EAAA,EAAA,GAAA,CAoGsB,oBApGtB,GAAA,SAAA,CAAA,EAAA;;;AFkC9B;AA+FA;;;;;ACnIiB;AA4BG;AA8BM;AAiCC;AAuCtB,KEpJO,WAAA,GAAc,WFoJV,CEpJsB,mBFoJtB,CAAA,SAAA,CAAA,CAAA,CAAA,MAAA,CAAA;;;;;;;AAKS;AA2FzB;AAAkD;AAgIlD;AAAwB,cEzTX,iBFyTW,EAAA,CAAA,KAAA,EEzTiB,IFyTjB,EAAA,EAAA,KAAA,CAAA,EEzTiC,WFyTjC,EAAA,EAAA,GEzTiD,IFyTjD,EAAA;;;;;AAkBxB;AAqCA;AA0EA;AA8BA;AAuBA;AA+CA;;;;;;AAsIA;;;;AC9tBA;AAKA;AAUA;;;;;;AAwGA;;;;ACxHA;AA2DA;;;;;;;;AC6SA;;;;;;;;AChTA;AA0QA;AAsDA;AA2CA;AAWA;AAuKA;AA6CA;AAuBA;AAqBA;AAgBA;cDtVa,sBAAuB,iBAAiB,wBAAmB;;;;AJlTxE;AA+FA;;;;;ACnIiB;AA4BG;AA8BM;AAiCC;AAwBH;;;;;;;AAoBC;AA2FzB;AAAkD;AAgIlD;;;;;AAkBA;AAqCA;AA0EA;AA8BA;AAuBA;AA+CA;;;;;;AAsIA;;;;AC9tBA;AAKA;AAUA;;;;;;AAwGA;;;;ACxHA;AA2DA;;;;;;;;AC6SA;AAAoC,cChTvB,sBDgTuB,EAAA,CAAA,OAAA,EAAA,MAAA,EAAA,GAAA,MAAA;;;;;;;AChTpC;AA0QA;AAsDA;AA2CA;AAWA;AAuKA;AA6CA;AAuBA;AAqBa,cA5WA,+BA4WsD,EAAA,CAAA,QAAA,EAAA,MAAA,EAAA,GAAA,MAAA;AAgBnE;;;;ACrrBA;AAcA;AAEA;AAwQA;;;;;;;;AClRA;AAaA;AAOA;AA2OA;;;;;;;cF0Ga,gBAAgB;AGxX7B;AA+EA;AAgEA;AAuBA;AAiCA;;;;AC7MA;AAKA;;;;;;AAOY,cJ6ZC,cI7ZmB,EAAA,CAAA,KAQpB,EAAA,MAMC,EAAK,GAAA,OAAA;AAahB;AAmnBF;;;;;AAO2B,KJ7Of,YAAA,GI6Oe;EAEd;;;AA6Cb;;EAEgF,OAAA,EAAA,MAAA;EACnE;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;cJxHA,mHAIV;;;;;;;;;;;;;;;;;;;;cAyCU;;;;;;;;;;;;;;;;;;;;;;cAuBA,uCAAmC;;;;;;;;;;;;;cAqBnC;;;;;;;;;;;;;;;cAgBA;;;ALxoBA,KM7CD,wBAAA,GN6C8E;EA+F7E,IAAA,CAAA,EAAA,MAAA;;;;ECnIR,WAAA,CAAA,EAAA,MAAY;EA4BZ,wBAAe,CAAA,EAAA,OAAA;EA8Bf,yBAAqB,CAAA,EAAA,OAAA;EAiCrB,MAAA,CAAA,EAAA,aAAA,GAAsB,OAAA;EAwBtB,UAAA,CAAA,EAAA,CAAA,IAAA,EAAA,MAAmB,EAAA,MAAA,EAAA,MAAA,EAAA,GAAA,OAAA;EAenB,cAAW,CAAA,EKjIK,MLiIL,EAAA;EACV,UAAA,CAAA,EAAA,OAAA,GAAA,OAAA;CACA;AACA,KKhIM,uBAAA,GLgIN;EACA,IAAA,EAAA,MAAA;EACA,MAAA,EAAA,MAAA;CAAmB;AAYpB,KK5IO,sBAAA,GL4IM;EA+EN,OAAA,EAAA,MAAS;EAYhB,KAAA,EAAA,MAAA;EAoHO,QAAA,EKxVE,uBLwVO,EAAA;CAAG;;;;AAkBZ,cKrGC,uBLqGG,EAAA,CAAA,KAAA,EKpGL,ILoGK,EAAA,EAAA,OAAA,CAAA,EKnGH,wBLmGG,EAAA,GKlGb,sBLkGa,EAAA;;;AAjQX,KMtHO,wBAAA,GNsHY;EAenB,WAAA,CAAA,EAAW,MAAA;EACV,WAAA,CAAA,EAAA,MAAA;EACA,QAAA,CAAA,EAAA,MAAA;EACA,IAAA,CAAA,EAAA,MAAA;EACA,yBAAA,CAAA,EAAA,OAAA;EACA,YAAA,CAAA,EAAA,OAAA;EAAmB,UAAA,CAAA,EAAA,OAAA,GAAA,OAAA;EAYpB,WAAA,CAAA,EAAA,MAAa;EA+EN,YAAS,CAAA,EAAA,MAAA;EAYhB,iBAAA,CAAe,EAAA,MAAA;AAoHpB,CAAA;AAAwB,KMxVZ,wBAAA,GNwVY;EAAc,IAAA,EAAA,MAAA;EAAgB,OAAA,EAAA,MAAA;EAAe,MAAA,EAAA,MAAA;EAkBzD,YAAI,EAAA,MAAA,EAAA;AAqChB,CAAA;AA0EY,KMldA,wBAAA,GNkdsB;EA8BjB,OAAA,EAAM,MAAA;EAuBX,KAAA,EAAA,MAAA;EA+CA,QAAA,EMnjBE,wBNmjBiB,EAAA;CAMjB;;;AAgId;;;;AC9tBY,cK6QC,yBL7QkB,EAAA,CAAA,KAAA,EK8QpB,IL9QoB,EAAA,EAAA,OAAA,CAAA,EK+QjB,wBL/QiB,EAAA,GKgR5B,wBLhR4B,EAAA;;;;AFqD/B;AA+FA;;;;;ACnIiB;AA4BG;AA+Df,KO7GO,eAAA,GP6Ge;EAwBtB;EAeA,KAAA,EAAA,MAAA;EACC;EACA,KAAA,EAAA,MAAA;EACA;EACA,KAAA,EAAA,MAAA;EACA;EAAmB,QAAA,EAAA,MAAA;AAAA,CAAA;AA2FzB;AAAkD;AAgIlD;;;;;AAkBA;AAqCA;AA0EA;AA8BA;AAuBA;AA+CA;;;AA6DkB,cOvkBL,mBPukBK,EAAA,CAAA,IAAA,EAAA,MAAA,EAAA,GOvkB8B,ePukB9B,EAAA;;;AAyElB;;;;AC9tBA;AAKA;AAUA;;;;;AAI8B,cM2HjB,wBN3HiB,EAAA,CAAA,IAAA,EAAA,MAAA,EAAA,QAAA,EM2HmC,eN3HnC,EAAA,EAAA,GAAA,MAAA;AAoG9B;;;;ACxHA;AA2DA;AAAyC,cK2G5B,oBL3G4B,EAAA,CAAA,QAAA,EK4G3B,eL5G2B,EAAA,EAAA,GAAA;EAAgB,WAAA,EAAA,gBAAA,GAAA,iBAAA;EAAgB,KAAA,EAAA,OAAA;EAAI,QAAA,CAAA,EAAA,MAAA;;;;AC6S7E;;;;AAAwE,cIjK3D,kBJiK2D,EAAA,CAAA,IAAA,EAAA,MAAA,EAAA,GAAA;;;;EChT3D,QAAA,CAAA,EAAA,MAAA;EA0QA,QAAA,EGpHC,eHoHD,EAAA;AAsDb,CAAA,GAAa,IAAA;;;ALlUA,KS5DD,sBAAA,GT4D8E;EA+F7E,IAAA,EAAA,cAAA;;;;ECnIR,KAAA,CAAA,EAAA,OAAY,GAAA,YAAA;EA4BZ,QAAA,EAAA,MAAA,EAAe;AAAA,CAAA,GA8Bf;EAiCA,IAAA,EAAA,WAAA;EAwBA,SAAA,EAAA,CAAA,IAAA,EQxIwC,SRwIrB,EAAA,KAAA,EAAA,MAAA,EAAA,GAAA,OAAA;AAAA,CAAA;AAgBlB,KQtJM,iBAAA,GRsJN;EACA,OAAA,EQtJO,mBRsJP;EACA,KAAA,EQtJK,IRsJL,EAAA;EACA,QAAA,EQtJQ,ORsJR,EAAA;EACA,QAAA,EQtJQ,sBRsJR;CAAmB;AAYpB,KQ/JO,oBAAA,GR+JM;EA+EN,OAAA,EAAA;IAYP,IAAA,EAAA,YAAe,GAAA,wBAsDH;IA8DL,SAAS,EAAA,MAAA;IAAG,aAAA,EAAA,MAAA;IAAc,SAAA,EAAA,MAAA;IAAgB,UAAA,EAAA,MAAA;EAAe,CAAA;EAkBzD,KAAA,CAAA,EQxXA,KRwXI,CAAA;IAqCJ,SAAA,EAAA,MAAc;IA0Ed,QAAA,EAAU,MAAA;IA8BL,aAAM,EAAA,MAAA;IAuBX,UAAW,EAAA,MAAA;EA+CX,CAAA,CAAA;EAME,OAAA,EQ3kBD,KR2kBC,CAAA;IASF,IAAA,EAAA,MAAA;IA8CM,oBAAA,EAAA,MAAA;IAwDL,sBAAA,CAAA,EAAA,MAAA;IAAM,qBAAA,CAAA,EAAA,MAAA;IAiBP,YAAO,EAAA,MA6BR;;;;IC3vBC,KAAA,CAAA,EAAA,MAAA,EAAA;EAKA,CAAA,CAAA;EAUA,MAAA,EAAA,MAAA,EAAA;EACU,QAAA,EAAA,MAAA,EAAA;CACC;KOiBlB,oBAAA,GPhBe,MAAA,GAAA,YAAA,GAAA,qBAAA;AACL,iBOgoBC,qCAAA,CPhoBD,KAAA,EOioBJ,IPjoBI,EAAA,EAAA,QAAA,EOkoBD,OPloBC,EAAA,EAAA,OAAA,EOmoBF,mBPnoBE,EAAA,QAAA,EOooBD,sBPpoBC,EAAA,KAAA,EAAA;EAAe,IAAA,CAAA,EAAA,YAAA,GAAA,wBAAA;EAoGjB,gBA0CZ,CAAA,EOyf0B,oBPniByB;;UOqiBvC;YAAgC;AN7pB7C,CAAA;AA2Da,iBM+oBG,6BAAA,CNznBf,IAAA,EM0nBS,iBN1nBT,EAAA,EAAA,IAtBwE,CAsBxE,EAAA;EAtBwC,IAAA,CAAA,EAAA,YAAA,GAAA,wBAAA;EAAgB,gBAAA,CAAA,EMipBuB,oBNjpBvB;CAAgB,CAAA,EAAA;EAAI,MAAA,EMkpBhE,oBNlpBgE;YMkpBhC"}
+{"version":3,"file":"index.d.mts","names":[],"sources":["../src/segmentation/fuzzy.ts","../src/segmentation/types.ts","../src/segmentation/optimize-rules.ts","../src/segmentation/pattern-validator.ts","../src/segmentation/replace.ts","../src/segmentation/segmenter.ts","../src/segmentation/tokens.ts","../src/analysis/line-starts.ts","../src/analysis/repeating-sequences.ts","../src/detection.ts","../src/recovery.ts"],"sourcesContent":[],"mappings":";;AAkEA;AA+FA;;;;;ACnIiB;AA4BG;AA8BM;AAiCC;AAwBH;;;;;;;AAqCxB;AAOA;AAAgE;AA6DhE;AAAkD;AAyHlD;;;;;AAkBY,cDnUC,WCmUG,EAAA,CAAA,CAAA,EAAA,MAAA,EAAA,GAAA,MAAA;AAoChB;AA0EA;AA8BA;AAuBA;AA+CA;;;;;;;AAwJA;;;;AC5tBA;AAsGA;;;;AC5GA;AAKA;AAcA;;;;;;AA8GA;AAwDA;;;;AC1LA;AA2DA;AAAyC,cJ0F5B,wBI1F4B,EAAA,CAAA,IAAA,EAAA,MAAA,EAAA,GAAA,MAAA;;;;AJLzC;AA+FA;;;;;ACnIiB;AA4BG;AA8BM;AAiCC;AAwBH;;;;;;;AAqCxB;AAOA;AAAgE;AA6DhE;AAAkD;AAyHlD;;;KArVK,YAAA,GAqViD;EAAe;EAkBzD,KAAA,EAAI,MAAA;AAoChB,CAAA;AA0EA;AA8BA;AAuBA;AA+CA;;;;;;;AAwJA;;;;AC5tBA;AAsGA;;;;AC5GA;AAKA;AAcA;;KF0BK,eAAA,GExBkB;EACH;EACL,QAAA,EAAA,MAAA;CAAe;AA0G9B;AAwDA;;;;AC1LA;AA2DA;;;;;;;;AC+SA;;;;;;;;AClTA;AA0QA;AAsDA;AA2CA,KLvVK,qBAAA,GK0VJ;EAQW;EAuKC,cAAA,EAAA,MAAA,EAAA;AA6Cb,CAAA;AAuBA;AAqBA;AAgBA;AA8BA;AAWA;AAoBA;AA6BA;;;;AC/wBA;AAcA;AAEA;AAwQA;;;;;;;;AClRA;AAaA;AAOA;AA2OA;;;;KPjKK,sBAAA,GOoKsB;;;;ACjR3B;AA+EA;AAgEA;AAuBA;AAiCA;;;;AC7MA;AAKA;;;;;;AAOA;AA2BE;AAmnBF;;KT/gBK,mBAAA,GSihBS;EACD;EACC,YAAA,EAAA,MAAA,EAAA;CAGa;;;;AA+C3B;;;;;;;KTtjBK,WAAA,GACC,eACA,kBACA,wBACA,yBACA;;;;;;;;;;;;;;;;cAiBO;;;;;;KAOD,cAAA,WAAyB;;;;;;;KAYhC,aAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;KAiDO,SAAA;;;;;;;KAYP,eAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;YAyCS;;;;;;;;;;;;SAaH;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;KAuDC,SAAA,GAAY,cAAc,gBAAgB;;;;;;;;;;;;;KAkB1C,IAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;KAoCA,cAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;YAqCE;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;KAqCF,UAAA,YAAsB;;;;;;;;;;;;;;;;;;;;;;;;;UA8BjB,MAAA;;;;;;;;;;;;;;;;;;;;;;KAuBL,WAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;KA+CA,mBAAA;;;;;;YAME;;;;;;;;UASF;;;;;;;;;;;;;;cAiBY;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;gBA+CN;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;WAwDL;;;;;;;;;;;;;;;;KAiBD,OAAA;;;;;;;;;;;;;;;;;;;;;;;;;;SA6BD;;;;AA3nBa;;;AAkBlB,KChJM,cAAA,GDgJN;EACA;EACA,KAAA,EChJK,SDgJL,EAAA;EAAmB;EAiBZ,WAAA,EAAA,MAAA;AAOb,CAAA;AAAgE;AA6DhE;AAAkD;AAyHlD;;;;;AAkBA;AAoCA;AA0EA;AA8BA;AAuBA;AA+CA;;;;;;;AAwJA;;;;AC5tBA;AAsGA;;;cAAa,uBAAwB,gBAAc;;;AD3FlC;AA4BG;AA8BM;AAyDrB,KEpIO,mBAAA,GFoIY,gBAAA,GAAA,eAAA,GAAA,WAAA,GAAA,eAAA;AAAA;;;AAkBlB,KEjJM,eAAA,GFiJN;EACA,IAAA,EEjJI,mBFiJJ;EACA,OAAA,EAAA,MAAA;EAAmB,UAAA,CAAA,EAAA,MAAA;EAiBZ;EAOD,KAAA,CAAA,EAAA,MAAA;EAYP;EAiDO,OAAA,CAAA,EAAA,MAAS;AAA6B,CAAA;AAyHlD;;;;AAAqE,KEnVzD,oBAAA,GFmVyD;EAkBzD,cAAI,CAAA,EAAA,CEpWM,eFoWN,GAAA,SAAA,CAAA,EAAA;EAoCJ,eAAA,CAAA,EAAc,CEvYH,eF4aT,GAAA,SAAS,CAAA,EAAA;EAqCX,YAAA,CAAU,EAAA,CEhdF,eFgdc,GAAA,SAAc,CAAA,EAAA;EA8B/B,QAAA,CAAM,EE7eR,eF6eQ;AAuBvB,CAAA;AA+CA;;;;;;;AAwJA;;;;AC5tBA;AAsGA;;;;AC5GA;AAKA;AAcA;AACsB,cA6GT,aA7GS,EAAA,CAAA,KAAA,EA6Ge,SA7Gf,EAAA,EAAA,GAAA,CA6G8B,oBA7G9B,GAAA,SAAA,CAAA,EAAA;;;;;AA6GtB;AAwDA;;;;AC1LA;AA2DA;;;AAAyE,cD+H5D,sBC/H4D,EAAA,CAAA,OAAA,EAAA,CD+HxB,oBC/HwB,GAAA,SAAA,CAAA,EAAA,EAAA,GAAA,MAAA,EAAA;;;AJLzE;AA+FA;;;;;ACnIiB;AA4BG;AA8BM;AAiCC;AAuCtB,KGpJO,WAAA,GAAc,WHoJV,CGpJsB,mBHoJtB,CAAA,SAAA,CAAA,CAAA,CAAA,MAAA,CAAA;;;;;;;AAsBhB;AAOA;AAAgE;AA6DhE;AAYK,cG/LQ,iBHwOC,EAAA,CAAA,KAaH,EGrP8B,IHqPxB,EAAA,EAAA,KAAA,CAAA,EGrPwC,WHqPxC,EAAA,EAAA,GGrPwD,IHqPxD,EAAA;;;;;;;AAyEjB;AAoCA;AA0EA;AA8BA;AAuBA;AA+CA;;;;;;;AAwJA;;;;AC5tBA;AAsGA;;;;AC5GA;AAKA;AAcA;;;;;;AA8GA;AAwDA;;;;AC1LA;AA2DA;;;;;;;;AC+SA;;;;;;;;AClTA;AA0Qa,cDwCA,YCxCA,EAAA,CAAA,KAaZ,ED2BmC,IC3BnC,EAAA,EAAA,OAAA,ED2BoD,mBC3BpD,EAAA,GD2BuE,OC3BvE,EAAA;;;;ANzRD;AA+FA;;;;;ACnIiB;AA4BG;AA8BM;AAiCC;AAwBH;;;;;;;AAqCxB;AAOA;AAAgE;AA6DhE;AAAkD;AAyHlD;;;;;AAkBA;AAoCA;AA0EA;AA8BA;AAuBA;AA+CA;;;;;;;AAwJA;;;;AC5tBA;AAsGA;;;;AC5GA;AAKA;AAcA;;;;;;AA8GA;AAwDA;;;;AC1LA;AA2Da,cEHA,sBFyBZ,EAAA,CAAA,OAAA,EAAA,MAAA,EAAA,GAAA,MAAA;;;;;;;;ACyRD;;;;;;;cCxCa;AA1Qb;AA0QA;AAsDA;AA2CA;AAWA;AAuKA;AA6CA;AAuBA;AAqBA;AAgBA;AA8BA;AAWA;AAoBA;AA6BA;;;;AC/wBA;AAcA;AAEA;AAwQA;;;;;cDuFa,gBAAgB;;;AEzW7B;AAaA;AAOA;AA2OA;;;;;;;;AC9QA;AA+EA;AAgEa,cHoRA,cGrQZ,EAAA,CAAA,KAfgE,EAAA,MAAA,EAAA,GAAA,OAAe;AAuBhF;AAiCA;;;;AC7MA;AAKY,KJ+aA,YAAA,GI/aiB;EAChB;;;;;EAMD,OAAA,EAAA,MAAA;EA6BP;AAinBL;;;;EAIc,YAAA,EAAA,MAAA,EAAA;EAGa;;;;AA+C3B;EACU,WAAA,EAAA,OAAA;CACsE;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;cJvHnE,mHAIV;;;;;;;;;;;;;;;;;;;;cAyCU;;;;;;;;;;;;;;;;;;;;;;cAuBA,uCAAmC;;;;;;;;;;;;;cAqBnC;;;;;;;;;;;;;;;cAgBA;;;;;;;;;;;;;;;cA8BA;;;;KAWD,YAAA;;;;;;;;;;;;;;;;;;;;;;cAoBC,iDAAkD;;;;;;;;;;;;;;;;cA6BlD;;;ANluBA,KO7CD,wBAAA,GP6C8E;EA+F7E,IAAA,CAAA,EAAA,MAAA;;;;ECnIR,WAAA,CAAA,EAAA,MAAY;EA4BZ,wBAAe,CAAA,EAAA,OAAA;EA8Bf,yBAAqB,CAAA,EAAA,OAAA;EAiCrB,MAAA,CAAA,EAAA,aAAA,GAAsB,OAAA;EAwBtB,UAAA,CAAA,EAAA,CAAA,IAAA,EAAA,MAAmB,EAAA,MAAA,EAAA,MAAA,EAAA,GAAA,OAAA;EAenB,cAAW,CAAA,EMjIK,MNiIL,EAAA;EACV,UAAA,CAAA,EAAA,OAAA,GAAA,OAAA;CACA;AACA,KMhIM,uBAAA,GNgIN;EACA,IAAA,EAAA,MAAA;EACA,MAAA,EAAA,MAAA;CAAmB;AAiBZ,KMjJD,sBAAA,GNiJwG;EAOxG,OAAA,EAAA,MAAA;EAYP,KAAA,EAAA,MAAA;EAiDO,QAAA,EMlNE,uBNkNO,EAAA;AAA6B,CAAA;AAyHlD;;;AAAsD,cMtEzC,uBNsEyC,EAAA,CAAA,KAAA,EMrE3C,INqE2C,EAAA,EAAA,OAAA,CAAA,EMpEzC,wBNoEyC,EAAA,GMnEnD,sBNmEmD,EAAA;;;AAlOjD,KOtHO,wBAAA,GPsHY;EAenB,WAAA,CAAA,EAAW,MAAA;EACV,WAAA,CAAA,EAAA,MAAA;EACA,QAAA,CAAA,EAAA,MAAA;EACA,IAAA,CAAA,EAAA,MAAA;EACA,yBAAA,CAAA,EAAA,OAAA;EACA,YAAA,CAAA,EAAA,OAAA;EAAmB,UAAA,CAAA,EAAA,OAAA,GAAA,OAAA;EAiBZ,WAAA,CAAA,EAAA,MAAuG;EAOxG,YAAA,CAAA,EAAA,MAAc;EAYrB,iBAAa,CAAA,EAAA,MAAA;AAiDlB,CAAA;AAYK,KO9NO,wBAAA,GPuQE;EAoEF,IAAA,EAAA,MAAS;EAAG,OAAA,EAAA,MAAA;EAAc,MAAA,EAAA,MAAA;EAAgB,YAAA,EAAA,MAAA,EAAA;CAAe;AAkBzD,KOtVA,wBAAA,GPsVI;EAoCJ,OAAA,EAAA,MAAA;EA0EA,KAAA,EAAA,MAAU;EA8BL,QAAA,EO/dH,wBP+dS,EAAA;AAuBvB,CAAA;;;;;;AAuMA;cOrda,mCACF,kBACG,6BACX;;;;AR3NH;AA+FA;;;;;ACnIiB;AA4BG;AA+Df,KQ7GO,eAAA,GR6Ge;EAwBtB;EAeA,KAAA,EAAA,MAAA;EACC;EACA,KAAA,EAAA,MAAA;EACA;EACA,KAAA,EAAA,MAAA;EACA;EAAmB,QAAA,EAAA,MAAA;AAiBzB,CAAA;AAOA;AAAgE;AA6DhE;AAAkD;AAyHlD;;;;;AAkBA;AAoCA;AA0EA;AA8BA;AAuBA;AA+CA;AAMc,cQlgBD,mBRkgBC,EAAA,CAAA,IAAA,EAAA,MAAA,EAAA,GQlgBkC,eRkgBlC,EAAA;;;;;;AAkJd;;;;AC5tBA;AAsGA;;;cOkCa,mDAAoD;AN9IjE;AAKA;AAcA;;;;AAIe,cM8IF,oBN9IE,EAAA,CAAA,QAAA,EM+ID,eN/IC,EAAA,EAAA,GAAA;EAAe,WAAA,EAAA,gBAAA,GAAA,iBAAA;EA0GjB,KAAA,EAAA,OAAA;EAwDA,QAAA,CAAA,EAAA,MAAA;;;;AC1Lb;AA2DA;;;AAAyE,cK4I5D,kBL5I4D,EAAA,CAAA,IAAA,EAAA,MAAA,EAAA,GAAA;EAAI,QAAA,EAAA,MAAA;;;;EC+ShE,QAAA,EI5JC,eJ6Nb,EAAA;CAjEmC,GAAA,IAAA;;;ALpTvB,KU5DD,sBAAA,GV4D8E;EA+F7E,IAAA,EAAA,cAAA;;;;ECnIR,KAAA,CAAA,EAAA,OAAY,GAAA,YAAA;EA4BZ,QAAA,EAAA,MAAA,EAAe;AAAA,CAAA,GA8Bf;EAiCA,IAAA,EAAA,WAAA;EAwBA,SAAA,EAAA,CAAA,IAAA,ESxIwC,STwIrB,EAAA,KAAA,EAAA,MAAA,EAAA,GAAA,OAAA;AAAA,CAAA;AAgBlB,KStJM,iBAAA,GTsJN;EACA,OAAA,EStJO,mBTsJP;EACA,KAAA,EStJK,ITsJL,EAAA;EACA,QAAA,EStJQ,OTsJR,EAAA;EACA,QAAA,EStJQ,sBTsJR;CAAmB;AAiBZ,KSpKD,oBAAA,GToKwG;EAOxG,OAAA,EAAA;IAYP,IAAA,EAAA,YAAa,GAAA,wBAAA;IAiDN,SAAS,EAAA,MAAA;IAYhB,aAAA,EAAe,MAAA;IA6GR,SAAS,EAAA,MAAA;IAAG,UAAA,EAAA,MAAA;EAAc,CAAA;EAAgB,KAAA,CAAA,ESzV1C,KTyV0C,CAAA;IAAe,SAAA,EAAA,MAAA;IAkBzD,QAAI,EAAA,MAAA;IAoCJ,aAAc,EAAA,MAAA;IA0Ed,UAAU,EAAA,MAAA;EA8BL,CAAA,CAAA;EAuBL,OAAA,ESxgBC,KTwgBU,CAAA;IA+CX,IAAA,EAAA,MAAA;IAME,oBAAA,EAAA,MAAA;IASF,sBAAA,CAAA,EAAA,MAAA;IAiBY,qBAAA,CAAA,EAAA,MAAA;IA+CN,YAAA,EAAA,MAAA;IAwDL,MAAA,EAAA,WAAA,GAAA,oBAAA,GAAA,WAAA,GAAA,sBAAA,GAAA,qBAAA;IAAM,QAAA,EAAA,OAAA,GAAA,QAAA,GAAA,MAAA;IAiBP,EAAA,CAAA,EAAA,MAAO;;;;EC5tBP,QAAA,EAAA,MAAA,EAAc;AAsG1B,CAAA;KQ1EK,oBAAA;iBAinBW,qCAAA,QACL,kBACG,oBACD,+BACC,4BPlpBd;;EALY,gBAAA,CAAA,EO0pBe,oBP1pBI;AAK/B,CAAA,CAAA,EAAY;EAcA,MAAA,EOyoBC,oBPzoBmB;EACV,QAAA,EOwoBuB,OPxoBvB,EAAA;CACC;AACH,iBOmrBJ,6BAAA,CPnrBI,IAAA,EOorBV,iBPprBU,EAAA,EAAA,IA2GpB,CA3GoB,EAAA;EACL,IAAA,CAAA,EAAA,YAAA,GAAA,wBAAA;EAAe,gBAAA,CAAA,EOorBkD,oBPprBlD;AA0G9B,CAAA,CAAA,EAAa;EAwDA,MAAA,EOmhBA,oBP1eZ;YO0e4C"}