code-gauge 2.0.0 → 3.0.0

package/dist/cliConfig.js.map

@@ -1 +1 @@
-{"version":3,"file":"cliConfig.js","names":[],"sources":["../src/cliConfig.ts"],"sourcesContent":["import { readFile, stat } from 'node:fs/promises';\nimport path from 'node:path';\nimport { defaultDuplicationOptions } from './duplication.js';\nimport type { DuplicationOptions } from './types.js';\n\n/** Risk thresholds; a finding is reported when the measured value is greater than or equal to the threshold. */\nexport interface Thresholds {\n  fileLoc: number;\n  functionLoc: number;\n  componentLoc: number;\n  cognitive: number;\n  cyclomatic: number;\n  call: number;\n  import: number;\n  fanOut: number;\n  parameter: number;\n  duplicateBlock: number;\n  /** Percentage (1-100) of a file's code lines (comments/blanks excluded) covered by duplicates. */\n  duplicationRatioPercent: number;\n  /** Number of cross-file duplicate block groups a file participates in. */\n  crossFileDuplicateBlock: number;\n  transitiveDependency: number;\n  structuralBreadth: number;\n  structuralCoordination: number;\n  stateMutation: number;\n  duplicateSymbolGroup: number;\n}\n\n// Defaults tuned against blind human labels across five representative WillBooster/WillBoosterLab\n// repositories to maximize F1 (precision without sacrificing recall); see PR for the evaluation.\nexport const defaultThresholds: Thresholds = {\n  fileLoc: 500,\n  functionLoc: 120,\n  componentLoc: 350,\n  cognitive: 25,\n  cyclomatic: 20,\n  call: 50,\n  import: 25,\n  fanOut: 10,\n  parameter: 8,\n  duplicateBlock: 2,\n  duplicationRatioPercent: 30,\n  crossFileDuplicateBlock: 2,\n  transitiveDependency: 25,\n  structuralBreadth: 8,\n  structuralCoordination: 300,\n  stateMutation: 50,\n  duplicateSymbolGroup: 5,\n};\n\nexport const defaultMaxFindings = 20;\nexport const configFileName = 'code-gauge.config.json';\n\n/**\n * Profile keys for per-language and React-specific threshold overrides. A file resolves its\n * thresholds as base → its language profile → the `react` profile (when it contains a component).\n */\nexport const profileKeys = [\n  'javascript',\n  'jsx',\n  'typescript',\n  'tsx',\n  'python',\n  'go',\n  'rust',\n  'java',\n  'ruby',\n  'c',\n  'cpp',\n  'react',\n] as const;\nexport type ProfileKey = (typeof profileKeys)[number];\n\n/**\n * Built-in per-profile overrides, calibrated because some metric distributions differ sharply by\n * language/type: Python treats every binding as an assignment (so `stateMutation` runs ~10x higher)\n * and coordinates more per file, while React files import roughly twice as many sources as pure TS.\n */\nexport const defaultProfileThresholds: Partial<Record<ProfileKey, Partial<Thresholds>>> = {\n  python: { stateMutation: 90, structuralCoordination: 350 },\n  // Ruby scores state mutation via assignments like Python (bindings are assignments).\n  ruby: { stateMutation: 90, structuralCoordination: 350 },\n  react: { import: 30 },\n};\n\n/** Shape of the JSON configuration file. All fields are optional and fall back to the built-in defaults. */\nexport interface CodeGaugeConfig {\n  thresholds?: Partial<Thresholds>;\n  /** Duplication detection settings applied to every measured file. */\n  duplication?: DuplicationOptions;\n  /** Per-profile overrides keyed by language name or `react`; merged over `thresholds` for matching files. */\n  languageThresholds?: Partial<Record<ProfileKey, Partial<Thresholds>>>;\n  maxFindings?: number;\n  largestFiles?: number;\n  includeTests?: boolean;\n  failOnRisk?: boolean;\n  failOnError?: boolean;\n  tsconfig?: string;\n}\n\n/** Options after merging command-line flags, the configuration file, and the built-in defaults. */\nexport interface ResolvedOptions {\n  thresholds: Thresholds;\n  duplication: Required<DuplicationOptions>;\n  profileThresholds: Partial<Record<ProfileKey, Partial<Thresholds>>>;\n  maxFindings: number;\n  /** Number of largest files by code LOC to list; 0 disables the section. */\n  largestFiles: number;\n  includeTests: boolean;\n  failOnRisk: boolean;\n  failOnError: boolean;\n  json: boolean;\n  tsconfig?: string;\n}\n\n/**\n * Resolves the thresholds for a single file: the base thresholds overlaid with its language profile\n * and then, when the file contains a React component, the `react` profile.\n */\nexport function resolveThresholds(options: ResolvedOptions, language: string, isReact: boolean): Thresholds {\n  let thresholds = options.thresholds;\n  const languageOverride = options.profileThresholds[language as ProfileKey];\n  if (languageOverride) {\n    thresholds = { ...thresholds, ...languageOverride };\n  }\n  if (isReact && options.profileThresholds.react) {\n    thresholds = { ...thresholds, ...options.profileThresholds.react };\n  }\n  return thresholds;\n}\n\n/** Raw command-line options; every threshold is undefined unless the user passed the flag. */\nexport interface CliOptions {\n  config?: string;\n  fileLocThreshold?: number;\n  functionLocThreshold?: number;\n  componentLocThreshold?: number;\n  cognitiveThreshold?: number;\n  cyclomaticThreshold?: number;\n  callThreshold?: number;\n  importThreshold?: number;\n  fanOutThreshold?: number;\n  parameterThreshold?: number;\n  duplicateBlockThreshold?: number;\n  duplicationRatioPercentThreshold?: number;\n  crossFileDuplicateBlockThreshold?: number;\n  duplicationMinTokens?: number;\n  duplicationMaxGapTokens?: number;\n  duplicationMinSimilarityPercent?: number;\n  transitiveDependencyThreshold?: number;\n  structuralBreadthThreshold?: number;\n  structuralCoordinationThreshold?: number;\n  stateMutationThreshold?: number;\n  duplicateSymbolGroupThreshold?: number;\n  maxFindings?: number;\n  largestFiles?: number;\n  includeTests?: boolean;\n  failOnRisk?: boolean;\n  failOnError?: boolean;\n  json?: boolean;\n  tsconfig?: string;\n}\n\n/** Maps each threshold to the matching command-line flag; the config key equals the flag without the `-threshold` suffix. */\nconst thresholdCliKeys: Record<keyof Thresholds, keyof CliOptions> = {\n  fileLoc: 'fileLocThreshold',\n  functionLoc: 'functionLocThreshold',\n  componentLoc: 'componentLocThreshold',\n  cognitive: 'cognitiveThreshold',\n  cyclomatic: 'cyclomaticThreshold',\n  call: 'callThreshold',\n  import: 'importThreshold',\n  fanOut: 'fanOutThreshold',\n  parameter: 'parameterThreshold',\n  duplicateBlock: 'duplicateBlockThreshold',\n  duplicationRatioPercent: 'duplicationRatioPercentThreshold',\n  crossFileDuplicateBlock: 'crossFileDuplicateBlockThreshold',\n  transitiveDependency: 'transitiveDependencyThreshold',\n  structuralBreadth: 'structuralBreadthThreshold',\n  structuralCoordination: 'structuralCoordinationThreshold',\n  stateMutation: 'stateMutationThreshold',\n  duplicateSymbolGroup: 'duplicateSymbolGroupThreshold',\n};\n\n/** Resolves options with precedence command-line flags > configuration file > built-in defaults. */\nexport function resolveOptions(cli: CliOptions, config: CodeGaugeConfig): ResolvedOptions {\n  const thresholds = { ...defaultThresholds };\n  for (const key of Object.keys(thresholds) as (keyof Thresholds)[]) {\n    thresholds[key] = (cli[thresholdCliKeys[key]] as number | undefined) ?? config.thresholds?.[key] ?? thresholds[key];\n  }\n\n  return {\n    thresholds,\n    duplication: {\n      minTokens: cli.duplicationMinTokens ?? config.duplication?.minTokens ?? defaultDuplicationOptions.minTokens,\n      maxGapTokens:\n        cli.duplicationMaxGapTokens ?? config.duplication?.maxGapTokens ?? defaultDuplicationOptions.maxGapTokens,\n      minSimilarityPercent:\n        cli.duplicationMinSimilarityPercent ??\n        config.duplication?.minSimilarityPercent ??\n        defaultDuplicationOptions.minSimilarityPercent,\n    },\n    profileThresholds: mergeProfileThresholds(defaultProfileThresholds, config.languageThresholds),\n    maxFindings: cli.maxFindings ?? config.maxFindings ?? defaultMaxFindings,\n    largestFiles: cli.largestFiles ?? config.largestFiles ?? 0,\n    includeTests: cli.includeTests ?? config.includeTests ?? false,\n    failOnRisk: cli.failOnRisk ?? config.failOnRisk ?? false,\n    failOnError: cli.failOnError ?? config.failOnError ?? false,\n    json: cli.json ?? false,\n    tsconfig: cli.tsconfig ?? config.tsconfig,\n  };\n}\n\n/** Merges user-supplied per-profile overrides on top of the built-in ones, per profile. */\nfunction mergeProfileThresholds(\n  defaults: Partial<Record<ProfileKey, Partial<Thresholds>>>,\n  overrides: Partial<Record<ProfileKey, Partial<Thresholds>>> | undefined\n): Partial<Record<ProfileKey, Partial<Thresholds>>> {\n  const merged: Partial<Record<ProfileKey, Partial<Thresholds>>> = {};\n  for (const key of profileKeys) {\n    const combined = { ...defaults[key], ...overrides?.[key] };\n    if (Object.keys(combined).length > 0) {\n      merged[key] = combined;\n    }\n  }\n  return merged;\n}\n\n/**\n * Loads the configuration file. An explicit path must exist; otherwise the nearest\n * `code-gauge.config.json` is searched by walking up from the target directory.\n */\nexport async function loadConfig(explicitPath: string | undefined, targetDirectory: string): Promise<CodeGaugeConfig> {\n  const configFile = explicitPath ?? (await findNearestConfig(targetDirectory));\n  if (!configFile) {\n    return {};\n  }\n\n  let content;\n  try {\n    content = await readFile(configFile, 'utf8');\n  } catch (error) {\n    if (explicitPath) {\n      throw new Error(`Cannot read config file \"${configFile}\": ${formatError(error)}`);\n    }\n    return {};\n  }\n\n  let parsed: unknown;\n  try {\n    parsed = JSON.parse(content);\n  } catch (error) {\n    throw new Error(`Invalid JSON in config file \"${configFile}\": ${formatError(error)}`);\n  }\n\n  return validateConfig(parsed, configFile);\n}\n\nasync function findNearestConfig(targetDirectory: string): Promise<string | undefined> {\n  let currentDirectory = targetDirectory;\n  while (true) {\n    const configFile = path.join(currentDirectory, configFileName);\n    if (await fileExists(configFile)) {\n      return configFile;\n    }\n\n    const parentDirectory = path.dirname(currentDirectory);\n    if (parentDirectory === currentDirectory) {\n      return undefined;\n    }\n    currentDirectory = parentDirectory;\n  }\n}\n\nasync function fileExists(file: string): Promise<boolean> {\n  try {\n    const fileStat = await stat(file);\n    return fileStat.isFile();\n  } catch {\n    return false;\n  }\n}\n\nfunction validateConfig(value: unknown, configFile: string): CodeGaugeConfig {\n  if (typeof value !== 'object' || value === null || Array.isArray(value)) {\n    throw new Error(`Config file \"${configFile}\" must contain a JSON object.`);\n  }\n\n  const raw = value as Record<string, unknown>;\n  const config: CodeGaugeConfig = {};\n\n  if (raw.thresholds !== undefined) {\n    config.thresholds = validateThresholdObject(raw.thresholds, 'thresholds', configFile);\n  }\n\n  if (raw.duplication !== undefined) {\n    config.duplication = validateDuplicationObject(raw.duplication, configFile);\n  }\n\n  if (raw.languageThresholds !== undefined) {\n    if (\n      typeof raw.languageThresholds !== 'object' ||\n      raw.languageThresholds === null ||\n      Array.isArray(raw.languageThresholds)\n    ) {\n      throw new Error(`Config file \"${configFile}\": \"languageThresholds\" must be an object.`);\n    }\n    const languageThresholds: Partial<Record<ProfileKey, Partial<Thresholds>>> = {};\n    for (const [profile, thresholds] of Object.entries(raw.languageThresholds as Record<string, unknown>)) {\n      if (!(profileKeys as readonly string[]).includes(profile)) {\n        throw new Error(\n          `Config file \"${configFile}\": unknown language profile \"${profile}\" (expected one of ${profileKeys.join(', ')}).`\n        );\n      }\n      languageThresholds[profile as ProfileKey] = validateThresholdObject(\n        thresholds,\n        `languageThresholds.${profile}`,\n        configFile\n      );\n    }\n    config.languageThresholds = languageThresholds;\n  }\n\n  if (raw.maxFindings !== undefined) {\n    config.maxFindings = requirePositiveInteger(raw.maxFindings, 'maxFindings', configFile);\n  }\n  if (raw.largestFiles !== undefined) {\n    config.largestFiles = requirePositiveInteger(raw.largestFiles, 'largestFiles', configFile);\n  }\n  for (const key of ['includeTests', 'failOnRisk', 'failOnError'] as const) {\n    if (raw[key] !== undefined) {\n      config[key] = requireBoolean(raw[key], key, configFile);\n    }\n  }\n  if (raw.tsconfig !== undefined) {\n    if (typeof raw.tsconfig !== 'string') {\n      throw new TypeError(`Config file \"${configFile}\": \"tsconfig\" must be a string.`);\n    }\n    config.tsconfig = raw.tsconfig;\n  }\n\n  return config;\n}\n\nfunction validateThresholdObject(value: unknown, label: string, configFile: string): Partial<Thresholds> {\n  if (typeof value !== 'object' || value === null || Array.isArray(value)) {\n    throw new Error(`Config file \"${configFile}\": \"${label}\" must be an object.`);\n  }\n  const thresholds: Partial<Thresholds> = {};\n  for (const [key, threshold] of Object.entries(value as Record<string, unknown>)) {\n    if (!(key in defaultThresholds)) {\n      throw new Error(`Config file \"${configFile}\": unknown threshold \"${key}\" in \"${label}\".`);\n    }\n    const parsed = requirePositiveInteger(threshold, `${label}.${key}`, configFile);\n    if (key === 'duplicationRatioPercent' && parsed > 100) {\n      throw new Error(`Config file \"${configFile}\": \"${label}.${key}\" must be between 1 and 100.`);\n    }\n    thresholds[key as keyof Thresholds] = parsed;\n  }\n  return thresholds;\n}\n\nfunction validateDuplicationObject(value: unknown, configFile: string): DuplicationOptions {\n  if (typeof value !== 'object' || value === null || Array.isArray(value)) {\n    throw new Error(`Config file \"${configFile}\": \"duplication\" must be an object.`);\n  }\n  const duplication: DuplicationOptions = {};\n  for (const [key, setting] of Object.entries(value as Record<string, unknown>)) {\n    if (key === 'minTokens') {\n      duplication.minTokens = requirePositiveInteger(setting, 'duplication.minTokens', configFile);\n    } else if (key === 'maxGapTokens') {\n      // 0 is meaningful: it disables gapped-clone merging.\n      duplication.maxGapTokens = requireNonNegativeInteger(setting, 'duplication.maxGapTokens', configFile);\n    } else if (key === 'minSimilarityPercent') {\n      const parsed = requirePositiveInteger(setting, 'duplication.minSimilarityPercent', configFile);\n      if (parsed > 100) {\n        throw new Error(`Config file \"${configFile}\": \"duplication.minSimilarityPercent\" must be between 1 and 100.`);\n      }\n      duplication.minSimilarityPercent = parsed;\n    } else {\n      throw new Error(\n        `Config file \"${configFile}\": unknown setting \"${key}\" in \"duplication\" (expected minTokens, maxGapTokens, or minSimilarityPercent).`\n      );\n    }\n  }\n  return duplication;\n}\n\nfunction requireNonNegativeInteger(value: unknown, key: string, configFile: string): number {\n  if (typeof value !== 'number' || !Number.isSafeInteger(value) || value < 0) {\n    throw new Error(`Config file \"${configFile}\": \"${key}\" must be a non-negative integer.`);\n  }\n  return value;\n}\n\nfunction requirePositiveInteger(value: unknown, key: string, configFile: string): number {\n  if (typeof value !== 'number' || !Number.isSafeInteger(value) || value < 1) {\n    throw new Error(`Config file \"${configFile}\": \"${key}\" must be a positive integer.`);\n  }\n  return value;\n}\n\nfunction requireBoolean(value: unknown, key: string, configFile: string): boolean {\n  if (typeof value !== 'boolean') {\n    throw new TypeError(`Config file \"${configFile}\": \"${key}\" must be a boolean.`);\n  }\n  return value;\n}\n\nfunction formatError(error: unknown): string {\n  return error instanceof Error ? error.message : String(error);\n}\n"],"mappings":"4IA8BA,MAAa,EAAgC,CAC3C,QAAS,IACT,YAAa,IACb,aAAc,IACd,UAAW,GACX,WAAY,GACZ,KAAM,GACN,OAAQ,GACR,OAAQ,GACR,UAAW,EACX,eAAgB,EAChB,wBAAyB,GACzB,wBAAyB,EACzB,qBAAsB,GACtB,kBAAmB,EACnB,uBAAwB,IACxB,cAAe,GACf,qBAAsB,CACxB,EAGa,EAAiB,yBAMjB,EAAc,CACzB,aACA,MACA,aACA,MACA,SACA,KACA,OACA,OACA,OACA,IACA,MACA,OACF,EAQa,EAA6E,CACxF,OAAQ,CAAE,cAAe,GAAI,uBAAwB,GAAI,EAEzD,KAAM,CAAE,cAAe,GAAI,uBAAwB,GAAI,EACvD,MAAO,CAAE,OAAQ,EAAG,CACtB,EAoCA,SAAgB,EAAkB,EAA0B,EAAkB,EAA8B,CAC1G,IAAI,EAAa,EAAQ,WACnB,EAAmB,EAAQ,kBAAkB,GAOnD,OANI,IACF,EAAa,CAAE,GAAG,EAAY,GAAG,CAAiB,GAEhD,GAAW,EAAQ,kBAAkB,QACvC,EAAa,CAAE,GAAG,EAAY,GAAG,EAAQ,kBAAkB,KAAM,GAE5D,CACT,CAmCA,MAAM,EAA+D,CACnE,QAAS,mBACT,YAAa,uBACb,aAAc,wBACd,UAAW,qBACX,WAAY,sBACZ,KAAM,gBACN,OAAQ,kBACR,OAAQ,kBACR,UAAW,qBACX,eAAgB,0BAChB,wBAAyB,mCACzB,wBAAyB,mCACzB,qBAAsB,gCACtB,kBAAmB,6BACnB,uBAAwB,kCACxB,cAAe,yBACf,qBAAsB,+BACxB,EAGA,SAAgB,EAAe,EAAiB,EAA0C,CACxF,IAAM,EAAa,CAAE,GAAG,CAAkB,EAC1C,IAAK,IAAM,KAAO,OAAO,KAAK,CAAU,EACtC,EAAW,GAAQ,EAAI,EAAiB,KAAgC,EAAO,aAAa,IAAQ,EAAW,GAGjH,MAAO,CACL,aACA,YAAa,CACX,UAAW,EAAI,sBAAwB,EAAO,aAAa,WAAa,EAA0B,UAClG,aACE,EAAI,yBAA2B,EAAO,aAAa,cAAgB,EAA0B,aAC/F,qBACE,EAAI,iCACJ,EAAO,aAAa,sBACpB,EAA0B,oBAC9B,EACA,kBAAmB,EAAuB,EAA0B,EAAO,kBAAkB,EAC7F,YAAa,EAAI,aAAe,EAAO,aAAA,GACvC,aAAc,EAAI,cAAgB,EAAO,cAAgB,EACzD,aAAc,EAAI,cAAgB,EAAO,cAAgB,GACzD,WAAY,EAAI,YAAc,EAAO,YAAc,GACnD,YAAa,EAAI,aAAe,EAAO,aAAe,GACtD,KAAM,EAAI,MAAQ,GAClB,SAAU,EAAI,UAAY,EAAO,QACnC,CACF,CAGA,SAAS,EACP,EACA,EACkD,CAClD,IAAM,EAA2D,CAAC,EAClE,IAAK,IAAM,KAAO,EAAa,CAC7B,IAAM,EAAW,CAAE,GAAG,EAAS,GAAM,GAAG,IAAY,EAAK,EACrD,OAAO,KAAK,CAAQ,CAAC,CAAC,OAAS,IACjC,EAAO,GAAO,EAElB,CACA,OAAO,CACT,CAMA,eAAsB,EAAW,EAAkC,EAAmD,CACpH,IAAM,EAAa,GAAiB,MAAM,EAAkB,CAAe,EAC3E,GAAI,CAAC,EACH,MAAO,CAAC,EAGV,IAAI,EACJ,GAAI,CACF,EAAU,MAAM,EAAS,EAAY,MAAM,CAC7C,OAAS,EAAO,CACd,GAAI,EACF,MAAU,MAAM,4BAA4B,EAAW,KAAK,EAAY,CAAK,GAAG,EAElF,MAAO,CAAC,CACV,CAEA,IAAI,EACJ,GAAI,CACF,EAAS,KAAK,MAAM,CAAO,CAC7B,OAAS,EAAO,CACd,MAAU,MAAM,gCAAgC,EAAW,KAAK,EAAY,CAAK,GAAG,CACtF,CAEA,OAAO,EAAe,EAAQ,CAAU,CAC1C,CAEA,eAAe,EAAkB,EAAsD,CACrF,IAAI,EAAmB,EACvB,OAAa,CACX,IAAM,EAAa,EAAK,KAAK,EAAkB,CAAc,EAC7D,GAAI,MAAM,EAAW,CAAU,EAC7B,OAAO,EAGT,IAAM,EAAkB,EAAK,QAAQ,CAAgB,EACrD,GAAI,IAAoB,EACtB,OAEF,EAAmB,CACrB,CACF,CAEA,eAAe,EAAW,EAAgC,CACxD,GAAI,CAEF,OAAO,MADgB,EAAK,CAAI,EAAA,CAChB,OAAO,CACzB,MAAQ,CACN,MAAO,EACT,CACF,CAEA,SAAS,EAAe,EAAgB,EAAqC,CAC3E,GAAI,OAAO,GAAU,WAAY,GAAkB,MAAM,QAAQ,CAAK,EACpE,MAAU,MAAM,gBAAgB,EAAW,8BAA8B,EAG3E,IAAM,EAAM,EACN,EAA0B,CAAC,EAUjC,GARI,EAAI,aAAe,IAAA,KACrB,EAAO,WAAa,EAAwB,EAAI,WAAY,aAAc,CAAU,GAGlF,EAAI,cAAgB,IAAA,KACtB,EAAO,YAAc,EAA0B,EAAI,YAAa,CAAU,GAGxE,EAAI,qBAAuB,IAAA,GAAW,CACxC,GACE,OAAO,EAAI,oBAAuB,UAClC,EAAI,qBAAuB,MAC3B,MAAM,QAAQ,EAAI,kBAAkB,EAEpC,MAAU,MAAM,gBAAgB,EAAW,2CAA2C,EAExF,IAAM,EAAuE,CAAC,EAC9E,IAAK,GAAM,CAAC,EAAS,KAAe,OAAO,QAAQ,EAAI,kBAA6C,EAAG,CACrG,GAAI,CAAE,EAAkC,SAAS,CAAO,EACtD,MAAU,MACR,gBAAgB,EAAW,+BAA+B,EAAQ,qBAAqB,EAAY,KAAK,IAAI,EAAE,GAChH,EAEF,EAAmB,GAAyB,EAC1C,EACA,sBAAsB,IACtB,CACF,CACF,CACA,EAAO,mBAAqB,CAC9B,CAEI,EAAI,cAAgB,IAAA,KACtB,EAAO,YAAc,EAAuB,EAAI,YAAa,cAAe,CAAU,GAEpF,EAAI,eAAiB,IAAA,KACvB,EAAO,aAAe,EAAuB,EAAI,aAAc,eAAgB,CAAU,GAE3F,IAAK,IAAM,IAAO,CAAC,eAAgB,aAAc,aAAa,EACxD,EAAI,KAAS,IAAA,KACf,EAAO,GAAO,EAAe,EAAI,GAAM,EAAK,CAAU,GAG1D,GAAI,EAAI,WAAa,IAAA,GAAW,CAC9B,GAAI,OAAO,EAAI,UAAa,SAC1B,MAAU,UAAU,gBAAgB,EAAW,gCAAgC,EAEjF,EAAO,SAAW,EAAI,QACxB,CAEA,OAAO,CACT,CAEA,SAAS,EAAwB,EAAgB,EAAe,EAAyC,CACvG,GAAI,OAAO,GAAU,WAAY,GAAkB,MAAM,QAAQ,CAAK,EACpE,MAAU,MAAM,gBAAgB,EAAW,MAAM,EAAM,qBAAqB,EAE9E,IAAM,EAAkC,CAAC,EACzC,IAAK,GAAM,CAAC,EAAK,KAAc,OAAO,QAAQ,CAAgC,EAAG,CAC/E,GAAI,EAAE,KAAO,GACX,MAAU,MAAM,gBAAgB,EAAW,wBAAwB,EAAI,QAAQ,EAAM,GAAG,EAE1F,IAAM,EAAS,EAAuB,EAAW,GAAG,EAAM,GAAG,IAAO,CAAU,EAC9E,GAAI,IAAQ,2BAA6B,EAAS,IAChD,MAAU,MAAM,gBAAgB,EAAW,MAAM,EAAM,GAAG,EAAI,6BAA6B,EAE7F,EAAW,GAA2B,CACxC,CACA,OAAO,CACT,CAEA,SAAS,EAA0B,EAAgB,EAAwC,CACzF,GAAI,OAAO,GAAU,WAAY,GAAkB,MAAM,QAAQ,CAAK,EACpE,MAAU,MAAM,gBAAgB,EAAW,oCAAoC,EAEjF,IAAM,EAAkC,CAAC,EACzC,IAAK,GAAM,CAAC,EAAK,KAAY,OAAO,QAAQ,CAAgC,EAC1E,GAAI,IAAQ,YACV,EAAY,UAAY,EAAuB,EAAS,wBAAyB,CAAU,OACtF,GAAI,IAAQ,eAEjB,EAAY,aAAe,EAA0B,EAAS,2BAA4B,CAAU,OAC/F,GAAI,IAAQ,uBAAwB,CACzC,IAAM,EAAS,EAAuB,EAAS,mCAAoC,CAAU,EAC7F,GAAI,EAAS,IACX,MAAU,MAAM,gBAAgB,EAAW,iEAAiE,EAE9G,EAAY,qBAAuB,CACrC,MACE,MAAU,MACR,gBAAgB,EAAW,sBAAsB,EAAI,gFACvD,EAGJ,OAAO,CACT,CAEA,SAAS,EAA0B,EAAgB,EAAa,EAA4B,CAC1F,GAAI,OAAO,GAAU,UAAY,CAAC,OAAO,cAAc,CAAK,GAAK,EAAQ,EACvE,MAAU,MAAM,gBAAgB,EAAW,MAAM,EAAI,kCAAkC,EAEzF,OAAO,CACT,CAEA,SAAS,EAAuB,EAAgB,EAAa,EAA4B,CACvF,GAAI,OAAO,GAAU,UAAY,CAAC,OAAO,cAAc,CAAK,GAAK,EAAQ,EACvE,MAAU,MAAM,gBAAgB,EAAW,MAAM,EAAI,8BAA8B,EAErF,OAAO,CACT,CAEA,SAAS,EAAe,EAAgB,EAAa,EAA6B,CAChF,GAAI,OAAO,GAAU,UACnB,MAAU,UAAU,gBAAgB,EAAW,MAAM,EAAI,qBAAqB,EAEhF,OAAO,CACT,CAEA,SAAS,EAAY,EAAwB,CAC3C,OAAO,aAAiB,MAAQ,EAAM,QAAU,OAAO,CAAK,CAC9D"}
+{"version":3,"file":"cliConfig.js","names":[],"sources":["../src/cliConfig.ts"],"sourcesContent":["import { readFile, stat } from 'node:fs/promises';\nimport path from 'node:path';\nimport { defaultDuplicationOptions } from './duplication.js';\nimport type { DuplicationOptions } from './types.js';\n\nexport const configFileName = 'code-gauge.config.json';\nexport const defaultTopFileCount = 10;\n\n/** Shape of the JSON configuration file. All fields are optional and fall back to the built-in defaults. */\nexport interface CodeGaugeConfig {\n  /** Duplication detection settings applied to every measured file. */\n  duplication?: DuplicationOptions;\n  /** Refactoring-candidate ranking settings. */\n  rank?: { top?: number };\n  includeTests?: boolean;\n  failOnError?: boolean;\n}\n\n/** Raw command-line options; every field is undefined unless the user passed the flag. */\nexport interface CliOptions {\n  config?: string;\n  top?: number;\n  duplicationMinTokens?: number;\n  duplicationMaxGapTokens?: number;\n  duplicationMinSimilarityPercent?: number;\n  includeTests?: boolean;\n  failOnError?: boolean;\n  json?: boolean;\n}\n\n/** Options after merging command-line flags, the configuration file, and the built-in defaults. */\nexport interface ResolvedOptions {\n  duplication: Required<DuplicationOptions>;\n  /** Number of top-ranked files to report. */\n  top: number;\n  includeTests: boolean;\n  failOnError: boolean;\n  json: boolean;\n}\n\n/** Resolves options with precedence command-line flags > configuration file > built-in defaults. */\nexport function resolveOptions(cli: CliOptions, config: CodeGaugeConfig): ResolvedOptions {\n  return {\n    duplication: {\n      minTokens: cli.duplicationMinTokens ?? config.duplication?.minTokens ?? defaultDuplicationOptions.minTokens,\n      maxGapTokens:\n        cli.duplicationMaxGapTokens ?? config.duplication?.maxGapTokens ?? defaultDuplicationOptions.maxGapTokens,\n      minSimilarityPercent:\n        cli.duplicationMinSimilarityPercent ??\n        config.duplication?.minSimilarityPercent ??\n        defaultDuplicationOptions.minSimilarityPercent,\n    },\n    top: cli.top ?? config.rank?.top ?? defaultTopFileCount,\n    includeTests: cli.includeTests ?? config.includeTests ?? false,\n    failOnError: cli.failOnError ?? config.failOnError ?? false,\n    json: cli.json ?? false,\n  };\n}\n\n/**\n * Loads the configuration file. An explicit path must exist; otherwise the nearest\n * `code-gauge.config.json` is searched by walking up from the target directory.\n */\nexport async function loadConfig(explicitPath: string | undefined, targetDirectory: string): Promise<CodeGaugeConfig> {\n  const configFile = explicitPath ?? (await findNearestConfig(targetDirectory));\n  if (!configFile) {\n    return {};\n  }\n\n  let content;\n  try {\n    content = await readFile(configFile, 'utf8');\n  } catch (error) {\n    if (explicitPath) {\n      throw new Error(`Cannot read config file \"${configFile}\": ${formatError(error)}`);\n    }\n    return {};\n  }\n\n  let parsed: unknown;\n  try {\n    parsed = JSON.parse(content);\n  } catch (error) {\n    throw new Error(`Invalid JSON in config file \"${configFile}\": ${formatError(error)}`);\n  }\n\n  return validateConfig(parsed, configFile);\n}\n\nasync function findNearestConfig(targetDirectory: string): Promise<string | undefined> {\n  let currentDirectory = targetDirectory;\n  while (true) {\n    const configFile = path.join(currentDirectory, configFileName);\n    if (await fileExists(configFile)) {\n      return configFile;\n    }\n\n    const parentDirectory = path.dirname(currentDirectory);\n    if (parentDirectory === currentDirectory) {\n      return undefined;\n    }\n    currentDirectory = parentDirectory;\n  }\n}\n\nasync function fileExists(file: string): Promise<boolean> {\n  try {\n    const fileStat = await stat(file);\n    return fileStat.isFile();\n  } catch {\n    return false;\n  }\n}\n\nfunction validateConfig(value: unknown, configFile: string): CodeGaugeConfig {\n  if (typeof value !== 'object' || value === null || Array.isArray(value)) {\n    throw new Error(`Config file \"${configFile}\" must contain a JSON object.`);\n  }\n\n  const raw = value as Record<string, unknown>;\n  const knownKeys = new Set(['duplication', 'rank', 'includeTests', 'failOnError']);\n  for (const key of Object.keys(raw)) {\n    if (!knownKeys.has(key)) {\n      throw new Error(`Config file \"${configFile}\": unknown setting \"${key}\" (expected ${[...knownKeys].join(', ')}).`);\n    }\n  }\n  const config: CodeGaugeConfig = {};\n\n  if (raw.duplication !== undefined) {\n    config.duplication = validateDuplicationObject(raw.duplication, configFile);\n  }\n\n  if (raw.rank !== undefined) {\n    config.rank = validateRankObject(raw.rank, configFile);\n  }\n\n  for (const key of ['includeTests', 'failOnError'] as const) {\n    if (raw[key] !== undefined) {\n      config[key] = requireBoolean(raw[key], key, configFile);\n    }\n  }\n\n  return config;\n}\n\nfunction validateRankObject(value: unknown, configFile: string): { top?: number } {\n  if (typeof value !== 'object' || value === null || Array.isArray(value)) {\n    throw new Error(`Config file \"${configFile}\": \"rank\" must be an object.`);\n  }\n  const rank: { top?: number } = {};\n  for (const [key, setting] of Object.entries(value as Record<string, unknown>)) {\n    if (key !== 'top') {\n      throw new Error(`Config file \"${configFile}\": unknown setting \"${key}\" in \"rank\" (expected top).`);\n    }\n    rank.top = requirePositiveInteger(setting, 'rank.top', configFile);\n  }\n  return rank;\n}\n\nfunction validateDuplicationObject(value: unknown, configFile: string): DuplicationOptions {\n  if (typeof value !== 'object' || value === null || Array.isArray(value)) {\n    throw new Error(`Config file \"${configFile}\": \"duplication\" must be an object.`);\n  }\n  const duplication: DuplicationOptions = {};\n  for (const [key, setting] of Object.entries(value as Record<string, unknown>)) {\n    if (key === 'minTokens') {\n      duplication.minTokens = requirePositiveInteger(setting, 'duplication.minTokens', configFile);\n    } else if (key === 'maxGapTokens') {\n      // 0 is meaningful: it disables gapped-clone merging.\n      duplication.maxGapTokens = requireNonNegativeInteger(setting, 'duplication.maxGapTokens', configFile);\n    } else if (key === 'minSimilarityPercent') {\n      const parsed = requirePositiveInteger(setting, 'duplication.minSimilarityPercent', configFile);\n      if (parsed > 100) {\n        throw new Error(`Config file \"${configFile}\": \"duplication.minSimilarityPercent\" must be between 1 and 100.`);\n      }\n      duplication.minSimilarityPercent = parsed;\n    } else {\n      throw new Error(\n        `Config file \"${configFile}\": unknown setting \"${key}\" in \"duplication\" (expected minTokens, maxGapTokens, or minSimilarityPercent).`\n      );\n    }\n  }\n  return duplication;\n}\n\nfunction requireNonNegativeInteger(value: unknown, key: string, configFile: string): number {\n  if (typeof value !== 'number' || !Number.isSafeInteger(value) || value < 0) {\n    throw new Error(`Config file \"${configFile}\": \"${key}\" must be a non-negative integer.`);\n  }\n  return value;\n}\n\nfunction requirePositiveInteger(value: unknown, key: string, configFile: string): number {\n  if (typeof value !== 'number' || !Number.isSafeInteger(value) || value < 1) {\n    throw new Error(`Config file \"${configFile}\": \"${key}\" must be a positive integer.`);\n  }\n  return value;\n}\n\nfunction requireBoolean(value: unknown, key: string, configFile: string): boolean {\n  if (typeof value !== 'boolean') {\n    throw new TypeError(`Config file \"${configFile}\": \"${key}\" must be a boolean.`);\n  }\n  return value;\n}\n\nfunction formatError(error: unknown): string {\n  return error instanceof Error ? error.message : String(error);\n}\n"],"mappings":"4IAKA,MAAa,EAAiB,yBAoC9B,SAAgB,EAAe,EAAiB,EAA0C,CACxF,MAAO,CACL,YAAa,CACX,UAAW,EAAI,sBAAwB,EAAO,aAAa,WAAa,EAA0B,UAClG,aACE,EAAI,yBAA2B,EAAO,aAAa,cAAgB,EAA0B,aAC/F,qBACE,EAAI,iCACJ,EAAO,aAAa,sBACpB,EAA0B,oBAC9B,EACA,IAAK,EAAI,KAAO,EAAO,MAAM,KAAA,GAC7B,aAAc,EAAI,cAAgB,EAAO,cAAgB,GACzD,YAAa,EAAI,aAAe,EAAO,aAAe,GACtD,KAAM,EAAI,MAAQ,EACpB,CACF,CAMA,eAAsB,EAAW,EAAkC,EAAmD,CACpH,IAAM,EAAa,GAAiB,MAAM,EAAkB,CAAe,EAC3E,GAAI,CAAC,EACH,MAAO,CAAC,EAGV,IAAI,EACJ,GAAI,CACF,EAAU,MAAM,EAAS,EAAY,MAAM,CAC7C,OAAS,EAAO,CACd,GAAI,EACF,MAAU,MAAM,4BAA4B,EAAW,KAAK,EAAY,CAAK,GAAG,EAElF,MAAO,CAAC,CACV,CAEA,IAAI,EACJ,GAAI,CACF,EAAS,KAAK,MAAM,CAAO,CAC7B,OAAS,EAAO,CACd,MAAU,MAAM,gCAAgC,EAAW,KAAK,EAAY,CAAK,GAAG,CACtF,CAEA,OAAO,EAAe,EAAQ,CAAU,CAC1C,CAEA,eAAe,EAAkB,EAAsD,CACrF,IAAI,EAAmB,EACvB,OAAa,CACX,IAAM,EAAa,EAAK,KAAK,EAAkB,CAAc,EAC7D,GAAI,MAAM,EAAW,CAAU,EAC7B,OAAO,EAGT,IAAM,EAAkB,EAAK,QAAQ,CAAgB,EACrD,GAAI,IAAoB,EACtB,OAEF,EAAmB,CACrB,CACF,CAEA,eAAe,EAAW,EAAgC,CACxD,GAAI,CAEF,OAAO,MADgB,EAAK,CAAI,EAAA,CAChB,OAAO,CACzB,MAAQ,CACN,MAAO,EACT,CACF,CAEA,SAAS,EAAe,EAAgB,EAAqC,CAC3E,GAAI,OAAO,GAAU,WAAY,GAAkB,MAAM,QAAQ,CAAK,EACpE,MAAU,MAAM,gBAAgB,EAAW,8BAA8B,EAG3E,IAAM,EAAM,EACN,EAAY,IAAI,IAAI,CAAC,cAAe,OAAQ,eAAgB,aAAa,CAAC,EAChF,IAAK,IAAM,KAAO,OAAO,KAAK,CAAG,EAC/B,GAAI,CAAC,EAAU,IAAI,CAAG,EACpB,MAAU,MAAM,gBAAgB,EAAW,sBAAsB,EAAI,cAAc,CAAC,GAAG,CAAS,CAAC,CAAC,KAAK,IAAI,EAAE,GAAG,EAGpH,IAAM,EAA0B,CAAC,EAE7B,EAAI,cAAgB,IAAA,KACtB,EAAO,YAAc,EAA0B,EAAI,YAAa,CAAU,GAGxE,EAAI,OAAS,IAAA,KACf,EAAO,KAAO,EAAmB,EAAI,KAAM,CAAU,GAGvD,IAAK,IAAM,IAAO,CAAC,eAAgB,aAAa,EAC1C,EAAI,KAAS,IAAA,KACf,EAAO,GAAO,EAAe,EAAI,GAAM,EAAK,CAAU,GAI1D,OAAO,CACT,CAEA,SAAS,EAAmB,EAAgB,EAAsC,CAChF,GAAI,OAAO,GAAU,WAAY,GAAkB,MAAM,QAAQ,CAAK,EACpE,MAAU,MAAM,gBAAgB,EAAW,6BAA6B,EAE1E,IAAM,EAAyB,CAAC,EAChC,IAAK,GAAM,CAAC,EAAK,KAAY,OAAO,QAAQ,CAAgC,EAAG,CAC7E,GAAI,IAAQ,MACV,MAAU,MAAM,gBAAgB,EAAW,sBAAsB,EAAI,4BAA4B,EAEnG,EAAK,IAAM,EAAuB,EAAS,WAAY,CAAU,CACnE,CACA,OAAO,CACT,CAEA,SAAS,EAA0B,EAAgB,EAAwC,CACzF,GAAI,OAAO,GAAU,WAAY,GAAkB,MAAM,QAAQ,CAAK,EACpE,MAAU,MAAM,gBAAgB,EAAW,oCAAoC,EAEjF,IAAM,EAAkC,CAAC,EACzC,IAAK,GAAM,CAAC,EAAK,KAAY,OAAO,QAAQ,CAAgC,EAC1E,GAAI,IAAQ,YACV,EAAY,UAAY,EAAuB,EAAS,wBAAyB,CAAU,OACtF,GAAI,IAAQ,eAEjB,EAAY,aAAe,EAA0B,EAAS,2BAA4B,CAAU,OAC/F,GAAI,IAAQ,uBAAwB,CACzC,IAAM,EAAS,EAAuB,EAAS,mCAAoC,CAAU,EAC7F,GAAI,EAAS,IACX,MAAU,MAAM,gBAAgB,EAAW,iEAAiE,EAE9G,EAAY,qBAAuB,CACrC,MACE,MAAU,MACR,gBAAgB,EAAW,sBAAsB,EAAI,gFACvD,EAGJ,OAAO,CACT,CAEA,SAAS,EAA0B,EAAgB,EAAa,EAA4B,CAC1F,GAAI,OAAO,GAAU,UAAY,CAAC,OAAO,cAAc,CAAK,GAAK,EAAQ,EACvE,MAAU,MAAM,gBAAgB,EAAW,MAAM,EAAI,kCAAkC,EAEzF,OAAO,CACT,CAEA,SAAS,EAAuB,EAAgB,EAAa,EAA4B,CACvF,GAAI,OAAO,GAAU,UAAY,CAAC,OAAO,cAAc,CAAK,GAAK,EAAQ,EACvE,MAAU,MAAM,gBAAgB,EAAW,MAAM,EAAI,8BAA8B,EAErF,OAAO,CACT,CAEA,SAAS,EAAe,EAAgB,EAAa,EAA6B,CAChF,GAAI,OAAO,GAAU,UACnB,MAAU,UAAU,gBAAgB,EAAW,MAAM,EAAI,qBAAqB,EAEhF,OAAO,CACT,CAEA,SAAS,EAAY,EAAwB,CAC3C,OAAO,aAAiB,MAAQ,EAAM,QAAU,OAAO,CAAK,CAC9D"}

package/dist/crossFileDuplication.cjs

@@ -1,2 +1,2 @@
-"use strict";const e=require("./duplicateSelection.cjs"),t=require("./duplication.cjs");function n(n,s){let c=s?.minTokens??t.defaultDuplicationOptions.minTokens,l=s?.maxGapTokens??t.defaultDuplicationOptions.maxGapTokens,u=n.flatMap(({file:e,candidates:t},n)=>t.map(t=>({...t,regionBucket:n,file:e})));for(let e of r(n,c))u.push(e);return o(a([...e.selectMaximalGroups(u,i,(e,t)=>e.regionBucket-t.regionBucket||e.startIndex-t.startIndex).values()],n,l))}function r(e,n){let r=[],i=[];for(let[n,{tokens:a,containerStatements:o}]of e.entries())a&&o&&(r.push(n),i.push({tokens:a,literalCountPrefix:t.buildLiteralCountPrefix(a),containers:o}));return i.length<2?[]:t.collectSequenceWindowCandidates(i,n,!0).flatMap(({candidate:t,contextIndex:n})=>{let i=r[n],a=i===void 0?void 0:e[i];return i===void 0||a===void 0?[]:[{...t,regionBucket:i,file:a.file}]})}function i(e){return e.length>=2&&new Set(e.map(e=>e.regionBucket)).size>=2}function a(e,n,r){let i=[],a=0;for(let{tokens:e,candidates:t}of n){i.push(a);let n=e?.length??0;if(!e)for(let e of t)n=Math.max(n,e.endTokenIndex);a+=n+r+1}let o=e.map(e=>e.map(e=>{let t=e.startTokenIndex+(i[e.regionBucket]??0),n=e.endTokenIndex+(i[e.regionBucket]??0);return{file:e.file,segments:[{startTokenIndex:t,endTokenIndex:n}],tokenCount:e.tokenCount,startTokenIndex:t,endTokenIndex:n,startIndex:e.startIndex,endIndex:e.endIndex,startLine:e.startLine,endLine:e.endLine}}).toSorted((e,t)=>e.startTokenIndex-t.startTokenIndex));return t.mergeAdjacentGroups(o,r)}function o(e){let n=[],r=new Map,i=0;for(let a of e){i+=t.countRedundantFragments(a);let e=a.map(({file:e,startLine:t,endLine:n})=>({file:e,startLine:t,endLine:n})).toSorted((e,t)=>e.file.localeCompare(t.file)||e.startLine-t.startLine),o=[...new Set(e.map(({file:e})=>e))];for(let e of o)r.set(e,(r.get(e)??0)+1);n.push({files:o,occurrences:e,tokenCount:a[0]?.tokenCount??0})}return n.sort((e,t)=>t.tokenCount-e.tokenCount||(e.occurrences[0]?.file??``).localeCompare(t.occurrences[0]?.file??``)||(e.occurrences[0]?.startLine??0)-(t.occurrences[0]?.startLine??0)),{duplicateBlockCount:i,duplicateBlockGroupCountByFile:Object.fromEntries(r),groups:n}}exports.measureCrossFileDuplication=n;
+"use strict";const e=require("./duplicateSelection.cjs"),t=require("./duplication.cjs");function n(n,c){let l=c?.minTokens??t.defaultDuplicationOptions.minTokens,u=c?.maxGapTokens??t.defaultDuplicationOptions.maxGapTokens,d=n.flatMap(({file:e,candidates:t},n)=>t.map(t=>({...t,regionBucket:n,file:e})));for(let e of r(n,l))d.push(e);let f=e.selectMaximalGroups(d,i,(e,t)=>e.regionBucket-t.regionBucket||e.startIndex-t.startIndex),p=a(n,u);return s(o([...f.values()],p,u),n,p)}function r(e,n){let r=[],i=[];for(let[n,{tokens:a,containerStatements:o}]of e.entries())a&&o&&(r.push(n),i.push({tokens:a,literalCountPrefix:t.buildLiteralCountPrefix(a),containers:o}));return i.length<2?[]:t.collectSequenceWindowCandidates(i,n,!0).flatMap(({candidate:t,contextIndex:n})=>{let i=r[n],a=i===void 0?void 0:e[i];return i===void 0||a===void 0?[]:[{...t,regionBucket:i,file:a.file}]})}function i(e){return e.length>=2&&new Set(e.map(e=>e.regionBucket)).size>=2}function a(e,t){let n=[],r=0;for(let{tokens:i,candidates:a}of e){n.push(r);let e=i?.length??0;if(!i)for(let t of a)e=Math.max(e,t.endTokenIndex);r+=e+t+1}return n}function o(e,n,r){let i=e.map(e=>e.map(e=>{let t=e.startTokenIndex+(n[e.regionBucket]??0),r=e.endTokenIndex+(n[e.regionBucket]??0);return{file:e.file,segments:[{startTokenIndex:t,endTokenIndex:r}],tokenCount:e.tokenCount,startTokenIndex:t,endTokenIndex:r,startIndex:e.startIndex,endIndex:e.endIndex,startLine:e.startLine,endLine:e.endLine}}).toSorted((e,t)=>e.startTokenIndex-t.startTokenIndex));return t.mergeAdjacentGroups(i,r)}function s(e,n,r){let i=[],a=new Map,o=new Map(n.map((e,t)=>[e.file,{tokens:e.tokens,codeLineNumbers:e.codeLineNumbers,offset:r[t]??0}])),s=new Map,l=0;for(let n of e){l+=t.countRedundantFragments(n);for(let e of n)c(e,o,s);let e=n.map(({file:e,startLine:t,endLine:n})=>({file:e,startLine:t,endLine:n})).toSorted((e,t)=>e.file.localeCompare(t.file)||e.startLine-t.startLine),r=[...new Set(e.map(({file:e})=>e))];for(let e of r)a.set(e,(a.get(e)??0)+1);i.push({files:r,occurrences:e,tokenCount:n[0]?.tokenCount??0})}return i.sort((e,t)=>t.tokenCount-e.tokenCount||(e.occurrences[0]?.file??``).localeCompare(t.occurrences[0]?.file??``)||(e.occurrences[0]?.startLine??0)-(t.occurrences[0]?.startLine??0)),{duplicateBlockCount:l,duplicateBlockGroupCountByFile:Object.fromEntries(a),duplicateLineNumbersByFile:Object.fromEntries([...s].map(([e,t])=>[e,[...t].toSorted((e,t)=>e-t)])),groups:i}}function c(e,n,r){let i=n.get(e.file);if(!i?.tokens)return;let a=r.get(e.file);a||(a=new Set,r.set(e.file,a));for(let n of e.segments)t.collectSegmentLines({startTokenIndex:n.startTokenIndex-i.offset,endTokenIndex:n.endTokenIndex-i.offset},i.tokens,i.codeLineNumbers,a)}exports.measureCrossFileDuplication=n;
 //# sourceMappingURL=crossFileDuplication.cjs.map

package/dist/crossFileDuplication.cjs.map

@@ -1 +1 @@
-{"version":3,"file":"crossFileDuplication.cjs","names":["defaultDuplicationOptions","selectMaximalGroups","buildLiteralCountPrefix","collectSequenceWindowCandidates","mergeAdjacentGroups","countRedundantFragments"],"sources":["../src/crossFileDuplication.ts"],"sourcesContent":["import { selectMaximalGroups } from './duplicateSelection.js';\nimport {\n  buildLiteralCountPrefix,\n  collectSequenceWindowCandidates,\n  countRedundantFragments,\n  defaultDuplicationOptions,\n  mergeAdjacentGroups,\n  type CountedOccurrence,\n  type CrossFileDuplicateCandidate,\n  type CrossFileDuplicationFileData,\n  type SequenceWindowContext,\n} from './duplication.js';\nimport type { DuplicationOptions } from './types.js';\n\nexport interface CrossFileDuplicationSourceFile extends Partial<CrossFileDuplicationFileData> {\n  file: string;\n  candidates: CrossFileDuplicateCandidate[];\n}\n\nexport interface CrossFileDuplicateOccurrence {\n  endLine: number;\n  file: string;\n  startLine: number;\n}\n\nexport interface CrossFileDuplicateBlockGroup {\n  files: string[];\n  occurrences: CrossFileDuplicateOccurrence[];\n  /** Matched token count of one occurrence (all occurrences share it; gaps are not counted). */\n  tokenCount: number;\n}\n\nexport interface CrossFileDuplicationMetrics {\n  /** Number of redundant copies across all groups, counted per matched fragment like within-file. */\n  duplicateBlockCount: number;\n  /** Groups the file participates in, keyed by the file name passed in. */\n  duplicateBlockGroupCountByFile: Record<string, number>;\n  groups: CrossFileDuplicateBlockGroup[];\n}\n\ninterface SelectableCandidate extends CrossFileDuplicateCandidate {\n  regionBucket: number;\n  file: string;\n}\n\n/** A cross-file occurrence: a within-file occurrence in the project-wide token index space. */\ninterface CrossFileOccurrence extends CountedOccurrence {\n  file: string;\n}\n\n/**\n * Detects code regions duplicated across files. Per-file candidates (whole block subtrees and full\n * container runs, fingerprinted with the same normalization as within-file duplication) are joined\n * by a project-level window index over per-statement fingerprint sequences (CPD-style), so a\n * copy-pasted partial statement run embedded in different surrounding code is matched even though\n * no single file can know it repeats elsewhere. Candidates are grouped by fingerprint, and only\n * maximal, non-overlapping regions whose group spans at least two files are counted. Groups that\n * shrink to a single file during selection are shed — a within-file repeat is already reported by\n * that file's own duplication metrics. Groups separated by a small token gap within each file then\n * merge into gapped (Type-3) clone groups under `maxGapTokens`, exactly like within-file merging.\n */\nexport function measureCrossFileDuplication(\n  files: CrossFileDuplicationSourceFile[],\n  options?: DuplicationOptions\n): CrossFileDuplicationMetrics {\n  const minTokens = options?.minTokens ?? defaultDuplicationOptions.minTokens;\n  const maxGapTokens = options?.maxGapTokens ?? defaultDuplicationOptions.maxGapTokens;\n  const candidates: SelectableCandidate[] = files.flatMap(({ file, candidates }, fileIndex) =>\n    candidates.map((candidate) => ({ ...candidate, regionBucket: fileIndex, file }))\n  );\n  // Pushed one by one: spreading the project-scale window-candidate array as call arguments\n  // overflows V8's argument limit (~124k) and crashes on Node, though Bun/JSC tolerates it.\n  for (const candidate of collectWindowCandidates(files, minTokens)) {\n    candidates.push(candidate);\n  }\n  const counted = selectMaximalGroups(\n    candidates,\n    spansMultipleFiles,\n    // File index and position break coverage ties deterministically.\n    (left, right) => left.regionBucket - right.regionBucket || left.startIndex - right.startIndex\n  );\n  return summarize(mergeGapAdjacentGroups([...counted.values()], files, maxGapTokens));\n}\n\n/** Repeated sub-windows of sibling statements matched across the whole project's files. */\nfunction collectWindowCandidates(files: CrossFileDuplicationSourceFile[], minTokens: number): SelectableCandidate[] {\n  const fileIndexByContext: number[] = [];\n  const contexts: SequenceWindowContext[] = [];\n  for (const [fileIndex, { tokens, containerStatements }] of files.entries()) {\n    if (tokens && containerStatements) {\n      fileIndexByContext.push(fileIndex);\n      contexts.push({ tokens, literalCountPrefix: buildLiteralCountPrefix(tokens), containers: containerStatements });\n    }\n  }\n  if (contexts.length < 2) {\n    return [];\n  }\n  return collectSequenceWindowCandidates(contexts, minTokens, true).flatMap(({ candidate, contextIndex }) => {\n    const fileIndex = fileIndexByContext[contextIndex];\n    const file = fileIndex === undefined ? undefined : files[fileIndex];\n    return fileIndex === undefined || file === undefined\n      ? []\n      : [{ ...candidate, regionBucket: fileIndex, file: file.file }];\n  });\n}\n\nfunction spansMultipleFiles(group: SelectableCandidate[]): boolean {\n  return group.length >= 2 && new Set(group.map((candidate) => candidate.regionBucket)).size >= 2;\n}\n\n/**\n * Reuses the within-file gapped (Type-3) merging by mapping every occurrence into one project-wide\n * token index space: each file's tokens are offset by more than `maxGapTokens` past the previous\n * file's, so occurrences in different files are never gap-adjacent and pairs always stay within\n * one file.\n */\nfunction mergeGapAdjacentGroups(\n  groups: SelectableCandidate[][],\n  files: CrossFileDuplicationSourceFile[],\n  maxGapTokens: number\n): CrossFileOccurrence[][] {\n  const tokenOffsets: number[] = [];\n  let offset = 0;\n  for (const { tokens, candidates } of files) {\n    tokenOffsets.push(offset);\n    // Accumulated in a loop: spreading a project-scale candidate array as call arguments would\n    // overflow V8's argument limit (~124k) and crash on Node.\n    let tokenCount = tokens?.length ?? 0;\n    if (!tokens) {\n      for (const candidate of candidates) {\n        tokenCount = Math.max(tokenCount, candidate.endTokenIndex);\n      }\n    }\n    offset += tokenCount + maxGapTokens + 1;\n  }\n  const occurrenceGroups = groups.map((group) =>\n    group\n      .map((candidate): CrossFileOccurrence => {\n        const start = candidate.startTokenIndex + (tokenOffsets[candidate.regionBucket] ?? 0);\n        const end = candidate.endTokenIndex + (tokenOffsets[candidate.regionBucket] ?? 0);\n        return {\n          file: candidate.file,\n          segments: [{ startTokenIndex: start, endTokenIndex: end }],\n          tokenCount: candidate.tokenCount,\n          startTokenIndex: start,\n          endTokenIndex: end,\n          startIndex: candidate.startIndex,\n          endIndex: candidate.endIndex,\n          startLine: candidate.startLine,\n          endLine: candidate.endLine,\n        };\n      })\n      .toSorted((left, right) => left.startTokenIndex - right.startTokenIndex)\n  );\n  return mergeAdjacentGroups(occurrenceGroups, maxGapTokens);\n}\n\nfunction summarize(groups: CrossFileOccurrence[][]): CrossFileDuplicationMetrics {\n  const reported: CrossFileDuplicateBlockGroup[] = [];\n  // Accumulated in a Map: file names are arbitrary strings, and a plain object would read\n  // inherited properties for names like \"constructor\".\n  const groupCountByFile = new Map<string, number>();\n  let duplicateBlockCount = 0;\n  for (const group of groups) {\n    // Mirrors within-file counting: each redundant occurrence contributes one count per matched\n    // fragment, gapped merging consolidates the grouping without halving the count, and spans a\n    // partial merge shares between a retained group and the merged group count once.\n    duplicateBlockCount += countRedundantFragments(group);\n    const occurrences = group\n      .map(({ file, startLine, endLine }) => ({ file, startLine, endLine }))\n      .toSorted((left, right) => left.file.localeCompare(right.file) || left.startLine - right.startLine);\n    const files = [...new Set(occurrences.map(({ file }) => file))];\n    for (const file of files) {\n      groupCountByFile.set(file, (groupCountByFile.get(file) ?? 0) + 1);\n    }\n    reported.push({ files, occurrences, tokenCount: group[0]?.tokenCount ?? 0 });\n  }\n  reported.sort(\n    (left, right) =>\n      right.tokenCount - left.tokenCount ||\n      (left.occurrences[0]?.file ?? '').localeCompare(right.occurrences[0]?.file ?? '') ||\n      (left.occurrences[0]?.startLine ?? 0) - (right.occurrences[0]?.startLine ?? 0)\n  );\n  return {\n    duplicateBlockCount,\n    duplicateBlockGroupCountByFile: Object.fromEntries(groupCountByFile),\n    groups: reported,\n  };\n}\n"],"mappings":"wFA6DA,SAAgB,EACd,EACA,EAC6B,CAC7B,IAAM,EAAY,GAAS,WAAaA,EAAAA,0BAA0B,UAC5D,EAAe,GAAS,cAAgBA,EAAAA,0BAA0B,aAClE,EAAoC,EAAM,SAAS,CAAE,OAAM,cAAc,IAC7E,EAAW,IAAK,IAAe,CAAE,GAAG,EAAW,aAAc,EAAW,MAAK,EAAE,CACjF,EAGA,IAAK,IAAM,KAAa,EAAwB,EAAO,CAAS,EAC9D,EAAW,KAAK,CAAS,EAQ3B,OAAO,EAAU,EAAuB,CAAC,GANzBC,EAAAA,oBACd,EACA,GAEC,EAAM,IAAU,EAAK,aAAe,EAAM,cAAgB,EAAK,WAAa,EAAM,UAEnC,CAAC,CAAC,OAAO,CAAC,EAAG,EAAO,CAAY,CAAC,CACrF,CAGA,SAAS,EAAwB,EAAyC,EAA0C,CAClH,IAAM,EAA+B,CAAC,EAChC,EAAoC,CAAC,EAC3C,IAAK,GAAM,CAAC,EAAW,CAAE,SAAQ,0BAA0B,EAAM,QAAQ,EACnE,GAAU,IACZ,EAAmB,KAAK,CAAS,EACjC,EAAS,KAAK,CAAE,SAAQ,mBAAoBC,EAAAA,wBAAwB,CAAM,EAAG,WAAY,CAAoB,CAAC,GAMlH,OAHI,EAAS,OAAS,EACb,CAAC,EAEHC,EAAAA,gCAAgC,EAAU,EAAW,EAAI,CAAC,CAAC,SAAS,CAAE,YAAW,kBAAmB,CACzG,IAAM,EAAY,EAAmB,GAC/B,EAAO,IAAc,IAAA,GAAY,IAAA,GAAY,EAAM,GACzD,OAAO,IAAc,IAAA,IAAa,IAAS,IAAA,GACvC,CAAC,EACD,CAAC,CAAE,GAAG,EAAW,aAAc,EAAW,KAAM,EAAK,IAAK,CAAC,CACjE,CAAC,CACH,CAEA,SAAS,EAAmB,EAAuC,CACjE,OAAO,EAAM,QAAU,GAAK,IAAI,IAAI,EAAM,IAAK,GAAc,EAAU,YAAY,CAAC,CAAC,CAAC,MAAQ,CAChG,CAQA,SAAS,EACP,EACA,EACA,EACyB,CACzB,IAAM,EAAyB,CAAC,EAC5B,EAAS,EACb,IAAK,GAAM,CAAE,SAAQ,gBAAgB,EAAO,CAC1C,EAAa,KAAK,CAAM,EAGxB,IAAI,EAAa,GAAQ,QAAU,EACnC,GAAI,CAAC,EACH,IAAK,IAAM,KAAa,EACtB,EAAa,KAAK,IAAI,EAAY,EAAU,aAAa,EAG7D,GAAU,EAAa,EAAe,CACxC,CACA,IAAM,EAAmB,EAAO,IAAK,GACnC,EACG,IAAK,GAAmC,CACvC,IAAM,EAAQ,EAAU,iBAAmB,EAAa,EAAU,eAAiB,GAC7E,EAAM,EAAU,eAAiB,EAAa,EAAU,eAAiB,GAC/E,MAAO,CACL,KAAM,EAAU,KAChB,SAAU,CAAC,CAAE,gBAAiB,EAAO,cAAe,CAAI,CAAC,EACzD,WAAY,EAAU,WACtB,gBAAiB,EACjB,cAAe,EACf,WAAY,EAAU,WACtB,SAAU,EAAU,SACpB,UAAW,EAAU,UACrB,QAAS,EAAU,OACrB,CACF,CAAC,CAAC,CACD,UAAU,EAAM,IAAU,EAAK,gBAAkB,EAAM,eAAe,CAC3E,EACA,OAAOC,EAAAA,oBAAoB,EAAkB,CAAY,CAC3D,CAEA,SAAS,EAAU,EAA8D,CAC/E,IAAM,EAA2C,CAAC,EAG5C,EAAmB,IAAI,IACzB,EAAsB,EAC1B,IAAK,IAAM,KAAS,EAAQ,CAI1B,GAAuBC,EAAAA,wBAAwB,CAAK,EACpD,IAAM,EAAc,EACjB,KAAK,CAAE,OAAM,YAAW,cAAe,CAAE,OAAM,YAAW,SAAQ,EAAE,CAAC,CACrE,UAAU,EAAM,IAAU,EAAK,KAAK,cAAc,EAAM,IAAI,GAAK,EAAK,UAAY,EAAM,SAAS,EAC9F,EAAQ,CAAC,GAAG,IAAI,IAAI,EAAY,KAAK,CAAE,UAAW,CAAI,CAAC,CAAC,EAC9D,IAAK,IAAM,KAAQ,EACjB,EAAiB,IAAI,GAAO,EAAiB,IAAI,CAAI,GAAK,GAAK,CAAC,EAElE,EAAS,KAAK,CAAE,QAAO,cAAa,WAAY,EAAM,EAAE,EAAE,YAAc,CAAE,CAAC,CAC7E,CAOA,OANA,EAAS,MACN,EAAM,IACL,EAAM,WAAa,EAAK,aACvB,EAAK,YAAY,EAAE,EAAE,MAAQ,GAAA,CAAI,cAAc,EAAM,YAAY,EAAE,EAAE,MAAQ,EAAE,IAC/E,EAAK,YAAY,EAAE,EAAE,WAAa,IAAM,EAAM,YAAY,EAAE,EAAE,WAAa,EAChF,EACO,CACL,sBACA,+BAAgC,OAAO,YAAY,CAAgB,EACnE,OAAQ,CACV,CACF"}
+{"version":3,"file":"crossFileDuplication.cjs","names":["defaultDuplicationOptions","selectMaximalGroups","buildLiteralCountPrefix","collectSequenceWindowCandidates","mergeAdjacentGroups","countRedundantFragments"],"sources":["../src/crossFileDuplication.ts"],"sourcesContent":["import { selectMaximalGroups } from './duplicateSelection.js';\nimport {\n  buildLiteralCountPrefix,\n  collectSegmentLines,\n  collectSequenceWindowCandidates,\n  countRedundantFragments,\n  defaultDuplicationOptions,\n  mergeAdjacentGroups,\n  type CountedOccurrence,\n  type CrossFileDuplicateCandidate,\n  type CrossFileDuplicationFileData,\n  type SequenceWindowContext,\n} from './duplication.js';\nimport type { DuplicationOptions } from './types.js';\n\nexport interface CrossFileDuplicationSourceFile extends Partial<CrossFileDuplicationFileData> {\n  file: string;\n  candidates: CrossFileDuplicateCandidate[];\n}\n\nexport interface CrossFileDuplicateOccurrence {\n  endLine: number;\n  file: string;\n  startLine: number;\n}\n\nexport interface CrossFileDuplicateBlockGroup {\n  files: string[];\n  occurrences: CrossFileDuplicateOccurrence[];\n  /** Matched token count of one occurrence (all occurrences share it; gaps are not counted). */\n  tokenCount: number;\n}\n\nexport interface CrossFileDuplicationMetrics {\n  /** Number of redundant copies across all groups, counted per matched fragment like within-file. */\n  duplicateBlockCount: number;\n  /** Groups the file participates in, keyed by the file name passed in. */\n  duplicateBlockGroupCountByFile: Record<string, number>;\n  /**\n   * Per file, the 1-based code lines covered by matched tokens of its cross-file occurrences,\n   * sorted ascending. Exact like within-file duplicateLineNumbers: the unmatched gap of a merged\n   * clone and comment/blank lines inside an occurrence's bounding range are excluded (blank rows\n   * inside multi-row tokens only when the file supplied codeLineNumbers). A file that supplied\n   * only candidates (no `tokens`) has no entry — without its token stream the matched lines are\n   * unknowable, and an approximate bounding range would break this field's exactness.\n   */\n  duplicateLineNumbersByFile: Record<string, number[]>;\n  groups: CrossFileDuplicateBlockGroup[];\n}\n\ninterface SelectableCandidate extends CrossFileDuplicateCandidate {\n  regionBucket: number;\n  file: string;\n}\n\n/** A cross-file occurrence: a within-file occurrence in the project-wide token index space. */\ninterface CrossFileOccurrence extends CountedOccurrence {\n  file: string;\n}\n\n/**\n * Detects code regions duplicated across files. Per-file candidates (whole block subtrees and full\n * container runs, fingerprinted with the same normalization as within-file duplication) are joined\n * by a project-level window index over per-statement fingerprint sequences (CPD-style), so a\n * copy-pasted partial statement run embedded in different surrounding code is matched even though\n * no single file can know it repeats elsewhere. Candidates are grouped by fingerprint, and only\n * maximal, non-overlapping regions whose group spans at least two files are counted. Groups that\n * shrink to a single file during selection are shed — a within-file repeat is already reported by\n * that file's own duplication metrics. Groups separated by a small token gap within each file then\n * merge into gapped (Type-3) clone groups under `maxGapTokens`, exactly like within-file merging.\n */\nexport function measureCrossFileDuplication(\n  files: CrossFileDuplicationSourceFile[],\n  options?: DuplicationOptions\n): CrossFileDuplicationMetrics {\n  const minTokens = options?.minTokens ?? defaultDuplicationOptions.minTokens;\n  const maxGapTokens = options?.maxGapTokens ?? defaultDuplicationOptions.maxGapTokens;\n  const candidates: SelectableCandidate[] = files.flatMap(({ file, candidates }, fileIndex) =>\n    candidates.map((candidate) => ({ ...candidate, regionBucket: fileIndex, file }))\n  );\n  // Pushed one by one: spreading the project-scale window-candidate array as call arguments\n  // overflows V8's argument limit (~124k) and crashes on Node, though Bun/JSC tolerates it.\n  for (const candidate of collectWindowCandidates(files, minTokens)) {\n    candidates.push(candidate);\n  }\n  const counted = selectMaximalGroups(\n    candidates,\n    spansMultipleFiles,\n    // File index and position break coverage ties deterministically.\n    (left, right) => left.regionBucket - right.regionBucket || left.startIndex - right.startIndex\n  );\n  const tokenOffsets = computeTokenOffsets(files, maxGapTokens);\n  return summarize(mergeGapAdjacentGroups([...counted.values()], tokenOffsets, maxGapTokens), files, tokenOffsets);\n}\n\n/** Repeated sub-windows of sibling statements matched across the whole project's files. */\nfunction collectWindowCandidates(files: CrossFileDuplicationSourceFile[], minTokens: number): SelectableCandidate[] {\n  const fileIndexByContext: number[] = [];\n  const contexts: SequenceWindowContext[] = [];\n  for (const [fileIndex, { tokens, containerStatements }] of files.entries()) {\n    if (tokens && containerStatements) {\n      fileIndexByContext.push(fileIndex);\n      contexts.push({ tokens, literalCountPrefix: buildLiteralCountPrefix(tokens), containers: containerStatements });\n    }\n  }\n  if (contexts.length < 2) {\n    return [];\n  }\n  return collectSequenceWindowCandidates(contexts, minTokens, true).flatMap(({ candidate, contextIndex }) => {\n    const fileIndex = fileIndexByContext[contextIndex];\n    const file = fileIndex === undefined ? undefined : files[fileIndex];\n    return fileIndex === undefined || file === undefined\n      ? []\n      : [{ ...candidate, regionBucket: fileIndex, file: file.file }];\n  });\n}\n\nfunction spansMultipleFiles(group: SelectableCandidate[]): boolean {\n  return group.length >= 2 && new Set(group.map((candidate) => candidate.regionBucket)).size >= 2;\n}\n\n/**\n * Per-file token offsets that map every file into one project-wide token index space: each file's\n * tokens are offset by more than `maxGapTokens` past the previous file's, so occurrences in\n * different files are never gap-adjacent and merged pairs always stay within one file.\n */\nfunction computeTokenOffsets(files: CrossFileDuplicationSourceFile[], maxGapTokens: number): number[] {\n  const tokenOffsets: number[] = [];\n  let offset = 0;\n  for (const { tokens, candidates } of files) {\n    tokenOffsets.push(offset);\n    // Accumulated in a loop: spreading a project-scale candidate array as call arguments would\n    // overflow V8's argument limit (~124k) and crash on Node.\n    let tokenCount = tokens?.length ?? 0;\n    if (!tokens) {\n      for (const candidate of candidates) {\n        tokenCount = Math.max(tokenCount, candidate.endTokenIndex);\n      }\n    }\n    offset += tokenCount + maxGapTokens + 1;\n  }\n  return tokenOffsets;\n}\n\n/** Reuses the within-file gapped (Type-3) merging in the project-wide token index space. */\nfunction mergeGapAdjacentGroups(\n  groups: SelectableCandidate[][],\n  tokenOffsets: number[],\n  maxGapTokens: number\n): CrossFileOccurrence[][] {\n  const occurrenceGroups = groups.map((group) =>\n    group\n      .map((candidate): CrossFileOccurrence => {\n        const start = candidate.startTokenIndex + (tokenOffsets[candidate.regionBucket] ?? 0);\n        const end = candidate.endTokenIndex + (tokenOffsets[candidate.regionBucket] ?? 0);\n        return {\n          file: candidate.file,\n          segments: [{ startTokenIndex: start, endTokenIndex: end }],\n          tokenCount: candidate.tokenCount,\n          startTokenIndex: start,\n          endTokenIndex: end,\n          startIndex: candidate.startIndex,\n          endIndex: candidate.endIndex,\n          startLine: candidate.startLine,\n          endLine: candidate.endLine,\n        };\n      })\n      .toSorted((left, right) => left.startTokenIndex - right.startTokenIndex)\n  );\n  return mergeAdjacentGroups(occurrenceGroups, maxGapTokens);\n}\n\nfunction summarize(\n  groups: CrossFileOccurrence[][],\n  files: CrossFileDuplicationSourceFile[],\n  tokenOffsets: number[]\n): CrossFileDuplicationMetrics {\n  const reported: CrossFileDuplicateBlockGroup[] = [];\n  // Accumulated in Maps: file names are arbitrary strings, and a plain object would read\n  // inherited properties for names like \"constructor\".\n  const groupCountByFile = new Map<string, number>();\n  const fileDataByName = new Map(\n    files.map((file, index) => [\n      file.file,\n      { tokens: file.tokens, codeLineNumbers: file.codeLineNumbers, offset: tokenOffsets[index] ?? 0 },\n    ])\n  );\n  const lineNumbersByFile = new Map<string, Set<number>>();\n  let duplicateBlockCount = 0;\n  for (const group of groups) {\n    // Mirrors within-file counting: each redundant occurrence contributes one count per matched\n    // fragment, gapped merging consolidates the grouping without halving the count, and spans a\n    // partial merge shares between a retained group and the merged group count once.\n    duplicateBlockCount += countRedundantFragments(group);\n    for (const occurrence of group) {\n      collectOccurrenceLines(occurrence, fileDataByName, lineNumbersByFile);\n    }\n    const occurrences = group\n      .map(({ file, startLine, endLine }) => ({ file, startLine, endLine }))\n      .toSorted((left, right) => left.file.localeCompare(right.file) || left.startLine - right.startLine);\n    const files = [...new Set(occurrences.map(({ file }) => file))];\n    for (const file of files) {\n      groupCountByFile.set(file, (groupCountByFile.get(file) ?? 0) + 1);\n    }\n    reported.push({ files, occurrences, tokenCount: group[0]?.tokenCount ?? 0 });\n  }\n  reported.sort(\n    (left, right) =>\n      right.tokenCount - left.tokenCount ||\n      (left.occurrences[0]?.file ?? '').localeCompare(right.occurrences[0]?.file ?? '') ||\n      (left.occurrences[0]?.startLine ?? 0) - (right.occurrences[0]?.startLine ?? 0)\n  );\n  return {\n    duplicateBlockCount,\n    duplicateBlockGroupCountByFile: Object.fromEntries(groupCountByFile),\n    duplicateLineNumbersByFile: Object.fromEntries(\n      [...lineNumbersByFile].map(([file, lines]) => [file, [...lines].toSorted((left, right) => left - right)])\n    ),\n    groups: reported,\n  };\n}\n\n/**\n * Adds the code lines an occurrence's matched tokens cover to its file's line set, mapping the\n * project-wide token segments back into the file's own token stream. A file that supplied only\n * candidates (no token stream) is skipped rather than approximated from the bounding line range,\n * which would include gap and comment/blank lines and break the field's exactness contract.\n */\nfunction collectOccurrenceLines(\n  occurrence: CrossFileOccurrence,\n  fileDataByName: Map<\n    string,\n    { tokens?: CrossFileDuplicationSourceFile['tokens']; codeLineNumbers?: Set<number>; offset: number }\n  >,\n  lineNumbersByFile: Map<string, Set<number>>\n): void {\n  const fileData = fileDataByName.get(occurrence.file);\n  if (!fileData?.tokens) {\n    return;\n  }\n  let lines = lineNumbersByFile.get(occurrence.file);\n  if (!lines) {\n    lines = new Set();\n    lineNumbersByFile.set(occurrence.file, lines);\n  }\n  for (const segment of occurrence.segments) {\n    collectSegmentLines(\n      {\n        startTokenIndex: segment.startTokenIndex - fileData.offset,\n        endTokenIndex: segment.endTokenIndex - fileData.offset,\n      },\n      fileData.tokens,\n      fileData.codeLineNumbers,\n      lines\n    );\n  }\n}\n"],"mappings":"wFAuEA,SAAgB,EACd,EACA,EAC6B,CAC7B,IAAM,EAAY,GAAS,WAAaA,EAAAA,0BAA0B,UAC5D,EAAe,GAAS,cAAgBA,EAAAA,0BAA0B,aAClE,EAAoC,EAAM,SAAS,CAAE,OAAM,cAAc,IAC7E,EAAW,IAAK,IAAe,CAAE,GAAG,EAAW,aAAc,EAAW,MAAK,EAAE,CACjF,EAGA,IAAK,IAAM,KAAa,EAAwB,EAAO,CAAS,EAC9D,EAAW,KAAK,CAAS,EAE3B,IAAM,EAAUC,EAAAA,oBACd,EACA,GAEC,EAAM,IAAU,EAAK,aAAe,EAAM,cAAgB,EAAK,WAAa,EAAM,UACrF,EACM,EAAe,EAAoB,EAAO,CAAY,EAC5D,OAAO,EAAU,EAAuB,CAAC,GAAG,EAAQ,OAAO,CAAC,EAAG,EAAc,CAAY,EAAG,EAAO,CAAY,CACjH,CAGA,SAAS,EAAwB,EAAyC,EAA0C,CAClH,IAAM,EAA+B,CAAC,EAChC,EAAoC,CAAC,EAC3C,IAAK,GAAM,CAAC,EAAW,CAAE,SAAQ,0BAA0B,EAAM,QAAQ,EACnE,GAAU,IACZ,EAAmB,KAAK,CAAS,EACjC,EAAS,KAAK,CAAE,SAAQ,mBAAoBC,EAAAA,wBAAwB,CAAM,EAAG,WAAY,CAAoB,CAAC,GAMlH,OAHI,EAAS,OAAS,EACb,CAAC,EAEHC,EAAAA,gCAAgC,EAAU,EAAW,EAAI,CAAC,CAAC,SAAS,CAAE,YAAW,kBAAmB,CACzG,IAAM,EAAY,EAAmB,GAC/B,EAAO,IAAc,IAAA,GAAY,IAAA,GAAY,EAAM,GACzD,OAAO,IAAc,IAAA,IAAa,IAAS,IAAA,GACvC,CAAC,EACD,CAAC,CAAE,GAAG,EAAW,aAAc,EAAW,KAAM,EAAK,IAAK,CAAC,CACjE,CAAC,CACH,CAEA,SAAS,EAAmB,EAAuC,CACjE,OAAO,EAAM,QAAU,GAAK,IAAI,IAAI,EAAM,IAAK,GAAc,EAAU,YAAY,CAAC,CAAC,CAAC,MAAQ,CAChG,CAOA,SAAS,EAAoB,EAAyC,EAAgC,CACpG,IAAM,EAAyB,CAAC,EAC5B,EAAS,EACb,IAAK,GAAM,CAAE,SAAQ,gBAAgB,EAAO,CAC1C,EAAa,KAAK,CAAM,EAGxB,IAAI,EAAa,GAAQ,QAAU,EACnC,GAAI,CAAC,EACH,IAAK,IAAM,KAAa,EACtB,EAAa,KAAK,IAAI,EAAY,EAAU,aAAa,EAG7D,GAAU,EAAa,EAAe,CACxC,CACA,OAAO,CACT,CAGA,SAAS,EACP,EACA,EACA,EACyB,CACzB,IAAM,EAAmB,EAAO,IAAK,GACnC,EACG,IAAK,GAAmC,CACvC,IAAM,EAAQ,EAAU,iBAAmB,EAAa,EAAU,eAAiB,GAC7E,EAAM,EAAU,eAAiB,EAAa,EAAU,eAAiB,GAC/E,MAAO,CACL,KAAM,EAAU,KAChB,SAAU,CAAC,CAAE,gBAAiB,EAAO,cAAe,CAAI,CAAC,EACzD,WAAY,EAAU,WACtB,gBAAiB,EACjB,cAAe,EACf,WAAY,EAAU,WACtB,SAAU,EAAU,SACpB,UAAW,EAAU,UACrB,QAAS,EAAU,OACrB,CACF,CAAC,CAAC,CACD,UAAU,EAAM,IAAU,EAAK,gBAAkB,EAAM,eAAe,CAC3E,EACA,OAAOC,EAAAA,oBAAoB,EAAkB,CAAY,CAC3D,CAEA,SAAS,EACP,EACA,EACA,EAC6B,CAC7B,IAAM,EAA2C,CAAC,EAG5C,EAAmB,IAAI,IACvB,EAAiB,IAAI,IACzB,EAAM,KAAK,EAAM,IAAU,CACzB,EAAK,KACL,CAAE,OAAQ,EAAK,OAAQ,gBAAiB,EAAK,gBAAiB,OAAQ,EAAa,IAAU,CAAE,CACjG,CAAC,CACH,EACM,EAAoB,IAAI,IAC1B,EAAsB,EAC1B,IAAK,IAAM,KAAS,EAAQ,CAI1B,GAAuBC,EAAAA,wBAAwB,CAAK,EACpD,IAAK,IAAM,KAAc,EACvB,EAAuB,EAAY,EAAgB,CAAiB,EAEtE,IAAM,EAAc,EACjB,KAAK,CAAE,OAAM,YAAW,cAAe,CAAE,OAAM,YAAW,SAAQ,EAAE,CAAC,CACrE,UAAU,EAAM,IAAU,EAAK,KAAK,cAAc,EAAM,IAAI,GAAK,EAAK,UAAY,EAAM,SAAS,EAC9F,EAAQ,CAAC,GAAG,IAAI,IAAI,EAAY,KAAK,CAAE,UAAW,CAAI,CAAC,CAAC,EAC9D,IAAK,IAAM,KAAQ,EACjB,EAAiB,IAAI,GAAO,EAAiB,IAAI,CAAI,GAAK,GAAK,CAAC,EAElE,EAAS,KAAK,CAAE,QAAO,cAAa,WAAY,EAAM,EAAE,EAAE,YAAc,CAAE,CAAC,CAC7E,CAOA,OANA,EAAS,MACN,EAAM,IACL,EAAM,WAAa,EAAK,aACvB,EAAK,YAAY,EAAE,EAAE,MAAQ,GAAA,CAAI,cAAc,EAAM,YAAY,EAAE,EAAE,MAAQ,EAAE,IAC/E,EAAK,YAAY,EAAE,EAAE,WAAa,IAAM,EAAM,YAAY,EAAE,EAAE,WAAa,EAChF,EACO,CACL,sBACA,+BAAgC,OAAO,YAAY,CAAgB,EACnE,2BAA4B,OAAO,YACjC,CAAC,GAAG,CAAiB,CAAC,CAAC,KAAK,CAAC,EAAM,KAAW,CAAC,EAAM,CAAC,GAAG,CAAK,CAAC,CAAC,UAAU,EAAM,IAAU,EAAO,CAAK,CAAC,CAAC,CAC1G,EACA,OAAQ,CACV,CACF,CAQA,SAAS,EACP,EACA,EAIA,EACM,CACN,IAAM,EAAW,EAAe,IAAI,EAAW,IAAI,EACnD,GAAI,CAAC,GAAU,OACb,OAEF,IAAI,EAAQ,EAAkB,IAAI,EAAW,IAAI,EAC5C,IACH,EAAQ,IAAI,IACZ,EAAkB,IAAI,EAAW,KAAM,CAAK,GAE9C,IAAK,IAAM,KAAW,EAAW,SAC/B,EAAA,oBACE,CACE,gBAAiB,EAAQ,gBAAkB,EAAS,OACpD,cAAe,EAAQ,cAAgB,EAAS,MAClD,EACA,EAAS,OACT,EAAS,gBACT,CACF,CAEJ"}

package/dist/crossFileDuplication.d.ts

@@ -20,6 +20,15 @@ export interface CrossFileDuplicationMetrics {
     duplicateBlockCount: number;
     /** Groups the file participates in, keyed by the file name passed in. */
     duplicateBlockGroupCountByFile: Record<string, number>;
+    /**
+     * Per file, the 1-based code lines covered by matched tokens of its cross-file occurrences,
+     * sorted ascending. Exact like within-file duplicateLineNumbers: the unmatched gap of a merged
+     * clone and comment/blank lines inside an occurrence's bounding range are excluded (blank rows
+     * inside multi-row tokens only when the file supplied codeLineNumbers). A file that supplied
+     * only candidates (no `tokens`) has no entry — without its token stream the matched lines are
+     * unknowable, and an approximate bounding range would break this field's exactness.
+     */
+    duplicateLineNumbersByFile: Record<string, number[]>;
     groups: CrossFileDuplicateBlockGroup[];
 }
 /**

package/dist/crossFileDuplication.js

@@ -1,2 +1,2 @@
-import{selectMaximalGroups as e}from"./duplicateSelection.js";import{buildLiteralCountPrefix as t,collectSequenceWindowCandidates as n,countRedundantFragments as r,defaultDuplicationOptions as i,mergeAdjacentGroups as a}from"./duplication.js";function o(t,n){let r=n?.minTokens??i.minTokens,a=n?.maxGapTokens??i.maxGapTokens,o=t.flatMap(({file:e,candidates:t},n)=>t.map(t=>({...t,regionBucket:n,file:e})));for(let e of s(t,r))o.push(e);return u(l([...e(o,c,(e,t)=>e.regionBucket-t.regionBucket||e.startIndex-t.startIndex).values()],t,a))}function s(e,r){let i=[],a=[];for(let[n,{tokens:r,containerStatements:o}]of e.entries())r&&o&&(i.push(n),a.push({tokens:r,literalCountPrefix:t(r),containers:o}));return a.length<2?[]:n(a,r,!0).flatMap(({candidate:t,contextIndex:n})=>{let r=i[n],a=r===void 0?void 0:e[r];return r===void 0||a===void 0?[]:[{...t,regionBucket:r,file:a.file}]})}function c(e){return e.length>=2&&new Set(e.map(e=>e.regionBucket)).size>=2}function l(e,t,n){let r=[],i=0;for(let{tokens:e,candidates:a}of t){r.push(i);let t=e?.length??0;if(!e)for(let e of a)t=Math.max(t,e.endTokenIndex);i+=t+n+1}let o=e.map(e=>e.map(e=>{let t=e.startTokenIndex+(r[e.regionBucket]??0),n=e.endTokenIndex+(r[e.regionBucket]??0);return{file:e.file,segments:[{startTokenIndex:t,endTokenIndex:n}],tokenCount:e.tokenCount,startTokenIndex:t,endTokenIndex:n,startIndex:e.startIndex,endIndex:e.endIndex,startLine:e.startLine,endLine:e.endLine}}).toSorted((e,t)=>e.startTokenIndex-t.startTokenIndex));return a(o,n)}function u(e){let t=[],n=new Map,i=0;for(let a of e){i+=r(a);let e=a.map(({file:e,startLine:t,endLine:n})=>({file:e,startLine:t,endLine:n})).toSorted((e,t)=>e.file.localeCompare(t.file)||e.startLine-t.startLine),o=[...new Set(e.map(({file:e})=>e))];for(let e of o)n.set(e,(n.get(e)??0)+1);t.push({files:o,occurrences:e,tokenCount:a[0]?.tokenCount??0})}return t.sort((e,t)=>t.tokenCount-e.tokenCount||(e.occurrences[0]?.file??``).localeCompare(t.occurrences[0]?.file??``)||(e.occurrences[0]?.startLine??0)-(t.occurrences[0]?.startLine??0)),{duplicateBlockCount:i,duplicateBlockGroupCountByFile:Object.fromEntries(n),groups:t}}export{o as measureCrossFileDuplication};
+import{selectMaximalGroups as e}from"./duplicateSelection.js";import{buildLiteralCountPrefix as t,collectSegmentLines as n,collectSequenceWindowCandidates as r,countRedundantFragments as i,defaultDuplicationOptions as a,mergeAdjacentGroups as o}from"./duplication.js";function s(t,n){let r=n?.minTokens??a.minTokens,i=n?.maxGapTokens??a.maxGapTokens,o=t.flatMap(({file:e,candidates:t},n)=>t.map(t=>({...t,regionBucket:n,file:e})));for(let e of c(t,r))o.push(e);let s=e(o,l,(e,t)=>e.regionBucket-t.regionBucket||e.startIndex-t.startIndex),p=u(t,i);return f(d([...s.values()],p,i),t,p)}function c(e,n){let i=[],a=[];for(let[n,{tokens:r,containerStatements:o}]of e.entries())r&&o&&(i.push(n),a.push({tokens:r,literalCountPrefix:t(r),containers:o}));return a.length<2?[]:r(a,n,!0).flatMap(({candidate:t,contextIndex:n})=>{let r=i[n],a=r===void 0?void 0:e[r];return r===void 0||a===void 0?[]:[{...t,regionBucket:r,file:a.file}]})}function l(e){return e.length>=2&&new Set(e.map(e=>e.regionBucket)).size>=2}function u(e,t){let n=[],r=0;for(let{tokens:i,candidates:a}of e){n.push(r);let e=i?.length??0;if(!i)for(let t of a)e=Math.max(e,t.endTokenIndex);r+=e+t+1}return n}function d(e,t,n){let r=e.map(e=>e.map(e=>{let n=e.startTokenIndex+(t[e.regionBucket]??0),r=e.endTokenIndex+(t[e.regionBucket]??0);return{file:e.file,segments:[{startTokenIndex:n,endTokenIndex:r}],tokenCount:e.tokenCount,startTokenIndex:n,endTokenIndex:r,startIndex:e.startIndex,endIndex:e.endIndex,startLine:e.startLine,endLine:e.endLine}}).toSorted((e,t)=>e.startTokenIndex-t.startTokenIndex));return o(r,n)}function f(e,t,n){let r=[],a=new Map,o=new Map(t.map((e,t)=>[e.file,{tokens:e.tokens,codeLineNumbers:e.codeLineNumbers,offset:n[t]??0}])),s=new Map,c=0;for(let t of e){c+=i(t);for(let e of t)p(e,o,s);let e=t.map(({file:e,startLine:t,endLine:n})=>({file:e,startLine:t,endLine:n})).toSorted((e,t)=>e.file.localeCompare(t.file)||e.startLine-t.startLine),n=[...new Set(e.map(({file:e})=>e))];for(let e of n)a.set(e,(a.get(e)??0)+1);r.push({files:n,occurrences:e,tokenCount:t[0]?.tokenCount??0})}return r.sort((e,t)=>t.tokenCount-e.tokenCount||(e.occurrences[0]?.file??``).localeCompare(t.occurrences[0]?.file??``)||(e.occurrences[0]?.startLine??0)-(t.occurrences[0]?.startLine??0)),{duplicateBlockCount:c,duplicateBlockGroupCountByFile:Object.fromEntries(a),duplicateLineNumbersByFile:Object.fromEntries([...s].map(([e,t])=>[e,[...t].toSorted((e,t)=>e-t)])),groups:r}}function p(e,t,r){let i=t.get(e.file);if(!i?.tokens)return;let a=r.get(e.file);a||(a=new Set,r.set(e.file,a));for(let t of e.segments)n({startTokenIndex:t.startTokenIndex-i.offset,endTokenIndex:t.endTokenIndex-i.offset},i.tokens,i.codeLineNumbers,a)}export{s as measureCrossFileDuplication};
 //# sourceMappingURL=crossFileDuplication.js.map

package/dist/crossFileDuplication.js.map

@@ -1 +1 @@
-{"version":3,"file":"crossFileDuplication.js","names":[],"sources":["../src/crossFileDuplication.ts"],"sourcesContent":["import { selectMaximalGroups } from './duplicateSelection.js';\nimport {\n  buildLiteralCountPrefix,\n  collectSequenceWindowCandidates,\n  countRedundantFragments,\n  defaultDuplicationOptions,\n  mergeAdjacentGroups,\n  type CountedOccurrence,\n  type CrossFileDuplicateCandidate,\n  type CrossFileDuplicationFileData,\n  type SequenceWindowContext,\n} from './duplication.js';\nimport type { DuplicationOptions } from './types.js';\n\nexport interface CrossFileDuplicationSourceFile extends Partial<CrossFileDuplicationFileData> {\n  file: string;\n  candidates: CrossFileDuplicateCandidate[];\n}\n\nexport interface CrossFileDuplicateOccurrence {\n  endLine: number;\n  file: string;\n  startLine: number;\n}\n\nexport interface CrossFileDuplicateBlockGroup {\n  files: string[];\n  occurrences: CrossFileDuplicateOccurrence[];\n  /** Matched token count of one occurrence (all occurrences share it; gaps are not counted). */\n  tokenCount: number;\n}\n\nexport interface CrossFileDuplicationMetrics {\n  /** Number of redundant copies across all groups, counted per matched fragment like within-file. */\n  duplicateBlockCount: number;\n  /** Groups the file participates in, keyed by the file name passed in. */\n  duplicateBlockGroupCountByFile: Record<string, number>;\n  groups: CrossFileDuplicateBlockGroup[];\n}\n\ninterface SelectableCandidate extends CrossFileDuplicateCandidate {\n  regionBucket: number;\n  file: string;\n}\n\n/** A cross-file occurrence: a within-file occurrence in the project-wide token index space. */\ninterface CrossFileOccurrence extends CountedOccurrence {\n  file: string;\n}\n\n/**\n * Detects code regions duplicated across files. Per-file candidates (whole block subtrees and full\n * container runs, fingerprinted with the same normalization as within-file duplication) are joined\n * by a project-level window index over per-statement fingerprint sequences (CPD-style), so a\n * copy-pasted partial statement run embedded in different surrounding code is matched even though\n * no single file can know it repeats elsewhere. Candidates are grouped by fingerprint, and only\n * maximal, non-overlapping regions whose group spans at least two files are counted. Groups that\n * shrink to a single file during selection are shed — a within-file repeat is already reported by\n * that file's own duplication metrics. Groups separated by a small token gap within each file then\n * merge into gapped (Type-3) clone groups under `maxGapTokens`, exactly like within-file merging.\n */\nexport function measureCrossFileDuplication(\n  files: CrossFileDuplicationSourceFile[],\n  options?: DuplicationOptions\n): CrossFileDuplicationMetrics {\n  const minTokens = options?.minTokens ?? defaultDuplicationOptions.minTokens;\n  const maxGapTokens = options?.maxGapTokens ?? defaultDuplicationOptions.maxGapTokens;\n  const candidates: SelectableCandidate[] = files.flatMap(({ file, candidates }, fileIndex) =>\n    candidates.map((candidate) => ({ ...candidate, regionBucket: fileIndex, file }))\n  );\n  // Pushed one by one: spreading the project-scale window-candidate array as call arguments\n  // overflows V8's argument limit (~124k) and crashes on Node, though Bun/JSC tolerates it.\n  for (const candidate of collectWindowCandidates(files, minTokens)) {\n    candidates.push(candidate);\n  }\n  const counted = selectMaximalGroups(\n    candidates,\n    spansMultipleFiles,\n    // File index and position break coverage ties deterministically.\n    (left, right) => left.regionBucket - right.regionBucket || left.startIndex - right.startIndex\n  );\n  return summarize(mergeGapAdjacentGroups([...counted.values()], files, maxGapTokens));\n}\n\n/** Repeated sub-windows of sibling statements matched across the whole project's files. */\nfunction collectWindowCandidates(files: CrossFileDuplicationSourceFile[], minTokens: number): SelectableCandidate[] {\n  const fileIndexByContext: number[] = [];\n  const contexts: SequenceWindowContext[] = [];\n  for (const [fileIndex, { tokens, containerStatements }] of files.entries()) {\n    if (tokens && containerStatements) {\n      fileIndexByContext.push(fileIndex);\n      contexts.push({ tokens, literalCountPrefix: buildLiteralCountPrefix(tokens), containers: containerStatements });\n    }\n  }\n  if (contexts.length < 2) {\n    return [];\n  }\n  return collectSequenceWindowCandidates(contexts, minTokens, true).flatMap(({ candidate, contextIndex }) => {\n    const fileIndex = fileIndexByContext[contextIndex];\n    const file = fileIndex === undefined ? undefined : files[fileIndex];\n    return fileIndex === undefined || file === undefined\n      ? []\n      : [{ ...candidate, regionBucket: fileIndex, file: file.file }];\n  });\n}\n\nfunction spansMultipleFiles(group: SelectableCandidate[]): boolean {\n  return group.length >= 2 && new Set(group.map((candidate) => candidate.regionBucket)).size >= 2;\n}\n\n/**\n * Reuses the within-file gapped (Type-3) merging by mapping every occurrence into one project-wide\n * token index space: each file's tokens are offset by more than `maxGapTokens` past the previous\n * file's, so occurrences in different files are never gap-adjacent and pairs always stay within\n * one file.\n */\nfunction mergeGapAdjacentGroups(\n  groups: SelectableCandidate[][],\n  files: CrossFileDuplicationSourceFile[],\n  maxGapTokens: number\n): CrossFileOccurrence[][] {\n  const tokenOffsets: number[] = [];\n  let offset = 0;\n  for (const { tokens, candidates } of files) {\n    tokenOffsets.push(offset);\n    // Accumulated in a loop: spreading a project-scale candidate array as call arguments would\n    // overflow V8's argument limit (~124k) and crash on Node.\n    let tokenCount = tokens?.length ?? 0;\n    if (!tokens) {\n      for (const candidate of candidates) {\n        tokenCount = Math.max(tokenCount, candidate.endTokenIndex);\n      }\n    }\n    offset += tokenCount + maxGapTokens + 1;\n  }\n  const occurrenceGroups = groups.map((group) =>\n    group\n      .map((candidate): CrossFileOccurrence => {\n        const start = candidate.startTokenIndex + (tokenOffsets[candidate.regionBucket] ?? 0);\n        const end = candidate.endTokenIndex + (tokenOffsets[candidate.regionBucket] ?? 0);\n        return {\n          file: candidate.file,\n          segments: [{ startTokenIndex: start, endTokenIndex: end }],\n          tokenCount: candidate.tokenCount,\n          startTokenIndex: start,\n          endTokenIndex: end,\n          startIndex: candidate.startIndex,\n          endIndex: candidate.endIndex,\n          startLine: candidate.startLine,\n          endLine: candidate.endLine,\n        };\n      })\n      .toSorted((left, right) => left.startTokenIndex - right.startTokenIndex)\n  );\n  return mergeAdjacentGroups(occurrenceGroups, maxGapTokens);\n}\n\nfunction summarize(groups: CrossFileOccurrence[][]): CrossFileDuplicationMetrics {\n  const reported: CrossFileDuplicateBlockGroup[] = [];\n  // Accumulated in a Map: file names are arbitrary strings, and a plain object would read\n  // inherited properties for names like \"constructor\".\n  const groupCountByFile = new Map<string, number>();\n  let duplicateBlockCount = 0;\n  for (const group of groups) {\n    // Mirrors within-file counting: each redundant occurrence contributes one count per matched\n    // fragment, gapped merging consolidates the grouping without halving the count, and spans a\n    // partial merge shares between a retained group and the merged group count once.\n    duplicateBlockCount += countRedundantFragments(group);\n    const occurrences = group\n      .map(({ file, startLine, endLine }) => ({ file, startLine, endLine }))\n      .toSorted((left, right) => left.file.localeCompare(right.file) || left.startLine - right.startLine);\n    const files = [...new Set(occurrences.map(({ file }) => file))];\n    for (const file of files) {\n      groupCountByFile.set(file, (groupCountByFile.get(file) ?? 0) + 1);\n    }\n    reported.push({ files, occurrences, tokenCount: group[0]?.tokenCount ?? 0 });\n  }\n  reported.sort(\n    (left, right) =>\n      right.tokenCount - left.tokenCount ||\n      (left.occurrences[0]?.file ?? '').localeCompare(right.occurrences[0]?.file ?? '') ||\n      (left.occurrences[0]?.startLine ?? 0) - (right.occurrences[0]?.startLine ?? 0)\n  );\n  return {\n    duplicateBlockCount,\n    duplicateBlockGroupCountByFile: Object.fromEntries(groupCountByFile),\n    groups: reported,\n  };\n}\n"],"mappings":"mPA6DA,SAAgB,EACd,EACA,EAC6B,CAC7B,IAAM,EAAY,GAAS,WAAa,EAA0B,UAC5D,EAAe,GAAS,cAAgB,EAA0B,aAClE,EAAoC,EAAM,SAAS,CAAE,OAAM,cAAc,IAC7E,EAAW,IAAK,IAAe,CAAE,GAAG,EAAW,aAAc,EAAW,MAAK,EAAE,CACjF,EAGA,IAAK,IAAM,KAAa,EAAwB,EAAO,CAAS,EAC9D,EAAW,KAAK,CAAS,EAQ3B,OAAO,EAAU,EAAuB,CAAC,GANzB,EACd,EACA,GAEC,EAAM,IAAU,EAAK,aAAe,EAAM,cAAgB,EAAK,WAAa,EAAM,UAEnC,CAAC,CAAC,OAAO,CAAC,EAAG,EAAO,CAAY,CAAC,CACrF,CAGA,SAAS,EAAwB,EAAyC,EAA0C,CAClH,IAAM,EAA+B,CAAC,EAChC,EAAoC,CAAC,EAC3C,IAAK,GAAM,CAAC,EAAW,CAAE,SAAQ,0BAA0B,EAAM,QAAQ,EACnE,GAAU,IACZ,EAAmB,KAAK,CAAS,EACjC,EAAS,KAAK,CAAE,SAAQ,mBAAoB,EAAwB,CAAM,EAAG,WAAY,CAAoB,CAAC,GAMlH,OAHI,EAAS,OAAS,EACb,CAAC,EAEH,EAAgC,EAAU,EAAW,EAAI,CAAC,CAAC,SAAS,CAAE,YAAW,kBAAmB,CACzG,IAAM,EAAY,EAAmB,GAC/B,EAAO,IAAc,IAAA,GAAY,IAAA,GAAY,EAAM,GACzD,OAAO,IAAc,IAAA,IAAa,IAAS,IAAA,GACvC,CAAC,EACD,CAAC,CAAE,GAAG,EAAW,aAAc,EAAW,KAAM,EAAK,IAAK,CAAC,CACjE,CAAC,CACH,CAEA,SAAS,EAAmB,EAAuC,CACjE,OAAO,EAAM,QAAU,GAAK,IAAI,IAAI,EAAM,IAAK,GAAc,EAAU,YAAY,CAAC,CAAC,CAAC,MAAQ,CAChG,CAQA,SAAS,EACP,EACA,EACA,EACyB,CACzB,IAAM,EAAyB,CAAC,EAC5B,EAAS,EACb,IAAK,GAAM,CAAE,SAAQ,gBAAgB,EAAO,CAC1C,EAAa,KAAK,CAAM,EAGxB,IAAI,EAAa,GAAQ,QAAU,EACnC,GAAI,CAAC,EACH,IAAK,IAAM,KAAa,EACtB,EAAa,KAAK,IAAI,EAAY,EAAU,aAAa,EAG7D,GAAU,EAAa,EAAe,CACxC,CACA,IAAM,EAAmB,EAAO,IAAK,GACnC,EACG,IAAK,GAAmC,CACvC,IAAM,EAAQ,EAAU,iBAAmB,EAAa,EAAU,eAAiB,GAC7E,EAAM,EAAU,eAAiB,EAAa,EAAU,eAAiB,GAC/E,MAAO,CACL,KAAM,EAAU,KAChB,SAAU,CAAC,CAAE,gBAAiB,EAAO,cAAe,CAAI,CAAC,EACzD,WAAY,EAAU,WACtB,gBAAiB,EACjB,cAAe,EACf,WAAY,EAAU,WACtB,SAAU,EAAU,SACpB,UAAW,EAAU,UACrB,QAAS,EAAU,OACrB,CACF,CAAC,CAAC,CACD,UAAU,EAAM,IAAU,EAAK,gBAAkB,EAAM,eAAe,CAC3E,EACA,OAAO,EAAoB,EAAkB,CAAY,CAC3D,CAEA,SAAS,EAAU,EAA8D,CAC/E,IAAM,EAA2C,CAAC,EAG5C,EAAmB,IAAI,IACzB,EAAsB,EAC1B,IAAK,IAAM,KAAS,EAAQ,CAI1B,GAAuB,EAAwB,CAAK,EACpD,IAAM,EAAc,EACjB,KAAK,CAAE,OAAM,YAAW,cAAe,CAAE,OAAM,YAAW,SAAQ,EAAE,CAAC,CACrE,UAAU,EAAM,IAAU,EAAK,KAAK,cAAc,EAAM,IAAI,GAAK,EAAK,UAAY,EAAM,SAAS,EAC9F,EAAQ,CAAC,GAAG,IAAI,IAAI,EAAY,KAAK,CAAE,UAAW,CAAI,CAAC,CAAC,EAC9D,IAAK,IAAM,KAAQ,EACjB,EAAiB,IAAI,GAAO,EAAiB,IAAI,CAAI,GAAK,GAAK,CAAC,EAElE,EAAS,KAAK,CAAE,QAAO,cAAa,WAAY,EAAM,EAAE,EAAE,YAAc,CAAE,CAAC,CAC7E,CAOA,OANA,EAAS,MACN,EAAM,IACL,EAAM,WAAa,EAAK,aACvB,EAAK,YAAY,EAAE,EAAE,MAAQ,GAAA,CAAI,cAAc,EAAM,YAAY,EAAE,EAAE,MAAQ,EAAE,IAC/E,EAAK,YAAY,EAAE,EAAE,WAAa,IAAM,EAAM,YAAY,EAAE,EAAE,WAAa,EAChF,EACO,CACL,sBACA,+BAAgC,OAAO,YAAY,CAAgB,EACnE,OAAQ,CACV,CACF"}
+{"version":3,"file":"crossFileDuplication.js","names":[],"sources":["../src/crossFileDuplication.ts"],"sourcesContent":["import { selectMaximalGroups } from './duplicateSelection.js';\nimport {\n  buildLiteralCountPrefix,\n  collectSegmentLines,\n  collectSequenceWindowCandidates,\n  countRedundantFragments,\n  defaultDuplicationOptions,\n  mergeAdjacentGroups,\n  type CountedOccurrence,\n  type CrossFileDuplicateCandidate,\n  type CrossFileDuplicationFileData,\n  type SequenceWindowContext,\n} from './duplication.js';\nimport type { DuplicationOptions } from './types.js';\n\nexport interface CrossFileDuplicationSourceFile extends Partial<CrossFileDuplicationFileData> {\n  file: string;\n  candidates: CrossFileDuplicateCandidate[];\n}\n\nexport interface CrossFileDuplicateOccurrence {\n  endLine: number;\n  file: string;\n  startLine: number;\n}\n\nexport interface CrossFileDuplicateBlockGroup {\n  files: string[];\n  occurrences: CrossFileDuplicateOccurrence[];\n  /** Matched token count of one occurrence (all occurrences share it; gaps are not counted). */\n  tokenCount: number;\n}\n\nexport interface CrossFileDuplicationMetrics {\n  /** Number of redundant copies across all groups, counted per matched fragment like within-file. */\n  duplicateBlockCount: number;\n  /** Groups the file participates in, keyed by the file name passed in. */\n  duplicateBlockGroupCountByFile: Record<string, number>;\n  /**\n   * Per file, the 1-based code lines covered by matched tokens of its cross-file occurrences,\n   * sorted ascending. Exact like within-file duplicateLineNumbers: the unmatched gap of a merged\n   * clone and comment/blank lines inside an occurrence's bounding range are excluded (blank rows\n   * inside multi-row tokens only when the file supplied codeLineNumbers). A file that supplied\n   * only candidates (no `tokens`) has no entry — without its token stream the matched lines are\n   * unknowable, and an approximate bounding range would break this field's exactness.\n   */\n  duplicateLineNumbersByFile: Record<string, number[]>;\n  groups: CrossFileDuplicateBlockGroup[];\n}\n\ninterface SelectableCandidate extends CrossFileDuplicateCandidate {\n  regionBucket: number;\n  file: string;\n}\n\n/** A cross-file occurrence: a within-file occurrence in the project-wide token index space. */\ninterface CrossFileOccurrence extends CountedOccurrence {\n  file: string;\n}\n\n/**\n * Detects code regions duplicated across files. Per-file candidates (whole block subtrees and full\n * container runs, fingerprinted with the same normalization as within-file duplication) are joined\n * by a project-level window index over per-statement fingerprint sequences (CPD-style), so a\n * copy-pasted partial statement run embedded in different surrounding code is matched even though\n * no single file can know it repeats elsewhere. Candidates are grouped by fingerprint, and only\n * maximal, non-overlapping regions whose group spans at least two files are counted. Groups that\n * shrink to a single file during selection are shed — a within-file repeat is already reported by\n * that file's own duplication metrics. Groups separated by a small token gap within each file then\n * merge into gapped (Type-3) clone groups under `maxGapTokens`, exactly like within-file merging.\n */\nexport function measureCrossFileDuplication(\n  files: CrossFileDuplicationSourceFile[],\n  options?: DuplicationOptions\n): CrossFileDuplicationMetrics {\n  const minTokens = options?.minTokens ?? defaultDuplicationOptions.minTokens;\n  const maxGapTokens = options?.maxGapTokens ?? defaultDuplicationOptions.maxGapTokens;\n  const candidates: SelectableCandidate[] = files.flatMap(({ file, candidates }, fileIndex) =>\n    candidates.map((candidate) => ({ ...candidate, regionBucket: fileIndex, file }))\n  );\n  // Pushed one by one: spreading the project-scale window-candidate array as call arguments\n  // overflows V8's argument limit (~124k) and crashes on Node, though Bun/JSC tolerates it.\n  for (const candidate of collectWindowCandidates(files, minTokens)) {\n    candidates.push(candidate);\n  }\n  const counted = selectMaximalGroups(\n    candidates,\n    spansMultipleFiles,\n    // File index and position break coverage ties deterministically.\n    (left, right) => left.regionBucket - right.regionBucket || left.startIndex - right.startIndex\n  );\n  const tokenOffsets = computeTokenOffsets(files, maxGapTokens);\n  return summarize(mergeGapAdjacentGroups([...counted.values()], tokenOffsets, maxGapTokens), files, tokenOffsets);\n}\n\n/** Repeated sub-windows of sibling statements matched across the whole project's files. */\nfunction collectWindowCandidates(files: CrossFileDuplicationSourceFile[], minTokens: number): SelectableCandidate[] {\n  const fileIndexByContext: number[] = [];\n  const contexts: SequenceWindowContext[] = [];\n  for (const [fileIndex, { tokens, containerStatements }] of files.entries()) {\n    if (tokens && containerStatements) {\n      fileIndexByContext.push(fileIndex);\n      contexts.push({ tokens, literalCountPrefix: buildLiteralCountPrefix(tokens), containers: containerStatements });\n    }\n  }\n  if (contexts.length < 2) {\n    return [];\n  }\n  return collectSequenceWindowCandidates(contexts, minTokens, true).flatMap(({ candidate, contextIndex }) => {\n    const fileIndex = fileIndexByContext[contextIndex];\n    const file = fileIndex === undefined ? undefined : files[fileIndex];\n    return fileIndex === undefined || file === undefined\n      ? []\n      : [{ ...candidate, regionBucket: fileIndex, file: file.file }];\n  });\n}\n\nfunction spansMultipleFiles(group: SelectableCandidate[]): boolean {\n  return group.length >= 2 && new Set(group.map((candidate) => candidate.regionBucket)).size >= 2;\n}\n\n/**\n * Per-file token offsets that map every file into one project-wide token index space: each file's\n * tokens are offset by more than `maxGapTokens` past the previous file's, so occurrences in\n * different files are never gap-adjacent and merged pairs always stay within one file.\n */\nfunction computeTokenOffsets(files: CrossFileDuplicationSourceFile[], maxGapTokens: number): number[] {\n  const tokenOffsets: number[] = [];\n  let offset = 0;\n  for (const { tokens, candidates } of files) {\n    tokenOffsets.push(offset);\n    // Accumulated in a loop: spreading a project-scale candidate array as call arguments would\n    // overflow V8's argument limit (~124k) and crash on Node.\n    let tokenCount = tokens?.length ?? 0;\n    if (!tokens) {\n      for (const candidate of candidates) {\n        tokenCount = Math.max(tokenCount, candidate.endTokenIndex);\n      }\n    }\n    offset += tokenCount + maxGapTokens + 1;\n  }\n  return tokenOffsets;\n}\n\n/** Reuses the within-file gapped (Type-3) merging in the project-wide token index space. */\nfunction mergeGapAdjacentGroups(\n  groups: SelectableCandidate[][],\n  tokenOffsets: number[],\n  maxGapTokens: number\n): CrossFileOccurrence[][] {\n  const occurrenceGroups = groups.map((group) =>\n    group\n      .map((candidate): CrossFileOccurrence => {\n        const start = candidate.startTokenIndex + (tokenOffsets[candidate.regionBucket] ?? 0);\n        const end = candidate.endTokenIndex + (tokenOffsets[candidate.regionBucket] ?? 0);\n        return {\n          file: candidate.file,\n          segments: [{ startTokenIndex: start, endTokenIndex: end }],\n          tokenCount: candidate.tokenCount,\n          startTokenIndex: start,\n          endTokenIndex: end,\n          startIndex: candidate.startIndex,\n          endIndex: candidate.endIndex,\n          startLine: candidate.startLine,\n          endLine: candidate.endLine,\n        };\n      })\n      .toSorted((left, right) => left.startTokenIndex - right.startTokenIndex)\n  );\n  return mergeAdjacentGroups(occurrenceGroups, maxGapTokens);\n}\n\nfunction summarize(\n  groups: CrossFileOccurrence[][],\n  files: CrossFileDuplicationSourceFile[],\n  tokenOffsets: number[]\n): CrossFileDuplicationMetrics {\n  const reported: CrossFileDuplicateBlockGroup[] = [];\n  // Accumulated in Maps: file names are arbitrary strings, and a plain object would read\n  // inherited properties for names like \"constructor\".\n  const groupCountByFile = new Map<string, number>();\n  const fileDataByName = new Map(\n    files.map((file, index) => [\n      file.file,\n      { tokens: file.tokens, codeLineNumbers: file.codeLineNumbers, offset: tokenOffsets[index] ?? 0 },\n    ])\n  );\n  const lineNumbersByFile = new Map<string, Set<number>>();\n  let duplicateBlockCount = 0;\n  for (const group of groups) {\n    // Mirrors within-file counting: each redundant occurrence contributes one count per matched\n    // fragment, gapped merging consolidates the grouping without halving the count, and spans a\n    // partial merge shares between a retained group and the merged group count once.\n    duplicateBlockCount += countRedundantFragments(group);\n    for (const occurrence of group) {\n      collectOccurrenceLines(occurrence, fileDataByName, lineNumbersByFile);\n    }\n    const occurrences = group\n      .map(({ file, startLine, endLine }) => ({ file, startLine, endLine }))\n      .toSorted((left, right) => left.file.localeCompare(right.file) || left.startLine - right.startLine);\n    const files = [...new Set(occurrences.map(({ file }) => file))];\n    for (const file of files) {\n      groupCountByFile.set(file, (groupCountByFile.get(file) ?? 0) + 1);\n    }\n    reported.push({ files, occurrences, tokenCount: group[0]?.tokenCount ?? 0 });\n  }\n  reported.sort(\n    (left, right) =>\n      right.tokenCount - left.tokenCount ||\n      (left.occurrences[0]?.file ?? '').localeCompare(right.occurrences[0]?.file ?? '') ||\n      (left.occurrences[0]?.startLine ?? 0) - (right.occurrences[0]?.startLine ?? 0)\n  );\n  return {\n    duplicateBlockCount,\n    duplicateBlockGroupCountByFile: Object.fromEntries(groupCountByFile),\n    duplicateLineNumbersByFile: Object.fromEntries(\n      [...lineNumbersByFile].map(([file, lines]) => [file, [...lines].toSorted((left, right) => left - right)])\n    ),\n    groups: reported,\n  };\n}\n\n/**\n * Adds the code lines an occurrence's matched tokens cover to its file's line set, mapping the\n * project-wide token segments back into the file's own token stream. A file that supplied only\n * candidates (no token stream) is skipped rather than approximated from the bounding line range,\n * which would include gap and comment/blank lines and break the field's exactness contract.\n */\nfunction collectOccurrenceLines(\n  occurrence: CrossFileOccurrence,\n  fileDataByName: Map<\n    string,\n    { tokens?: CrossFileDuplicationSourceFile['tokens']; codeLineNumbers?: Set<number>; offset: number }\n  >,\n  lineNumbersByFile: Map<string, Set<number>>\n): void {\n  const fileData = fileDataByName.get(occurrence.file);\n  if (!fileData?.tokens) {\n    return;\n  }\n  let lines = lineNumbersByFile.get(occurrence.file);\n  if (!lines) {\n    lines = new Set();\n    lineNumbersByFile.set(occurrence.file, lines);\n  }\n  for (const segment of occurrence.segments) {\n    collectSegmentLines(\n      {\n        startTokenIndex: segment.startTokenIndex - fileData.offset,\n        endTokenIndex: segment.endTokenIndex - fileData.offset,\n      },\n      fileData.tokens,\n      fileData.codeLineNumbers,\n      lines\n    );\n  }\n}\n"],"mappings":"4QAuEA,SAAgB,EACd,EACA,EAC6B,CAC7B,IAAM,EAAY,GAAS,WAAa,EAA0B,UAC5D,EAAe,GAAS,cAAgB,EAA0B,aAClE,EAAoC,EAAM,SAAS,CAAE,OAAM,cAAc,IAC7E,EAAW,IAAK,IAAe,CAAE,GAAG,EAAW,aAAc,EAAW,MAAK,EAAE,CACjF,EAGA,IAAK,IAAM,KAAa,EAAwB,EAAO,CAAS,EAC9D,EAAW,KAAK,CAAS,EAE3B,IAAM,EAAU,EACd,EACA,GAEC,EAAM,IAAU,EAAK,aAAe,EAAM,cAAgB,EAAK,WAAa,EAAM,UACrF,EACM,EAAe,EAAoB,EAAO,CAAY,EAC5D,OAAO,EAAU,EAAuB,CAAC,GAAG,EAAQ,OAAO,CAAC,EAAG,EAAc,CAAY,EAAG,EAAO,CAAY,CACjH,CAGA,SAAS,EAAwB,EAAyC,EAA0C,CAClH,IAAM,EAA+B,CAAC,EAChC,EAAoC,CAAC,EAC3C,IAAK,GAAM,CAAC,EAAW,CAAE,SAAQ,0BAA0B,EAAM,QAAQ,EACnE,GAAU,IACZ,EAAmB,KAAK,CAAS,EACjC,EAAS,KAAK,CAAE,SAAQ,mBAAoB,EAAwB,CAAM,EAAG,WAAY,CAAoB,CAAC,GAMlH,OAHI,EAAS,OAAS,EACb,CAAC,EAEH,EAAgC,EAAU,EAAW,EAAI,CAAC,CAAC,SAAS,CAAE,YAAW,kBAAmB,CACzG,IAAM,EAAY,EAAmB,GAC/B,EAAO,IAAc,IAAA,GAAY,IAAA,GAAY,EAAM,GACzD,OAAO,IAAc,IAAA,IAAa,IAAS,IAAA,GACvC,CAAC,EACD,CAAC,CAAE,GAAG,EAAW,aAAc,EAAW,KAAM,EAAK,IAAK,CAAC,CACjE,CAAC,CACH,CAEA,SAAS,EAAmB,EAAuC,CACjE,OAAO,EAAM,QAAU,GAAK,IAAI,IAAI,EAAM,IAAK,GAAc,EAAU,YAAY,CAAC,CAAC,CAAC,MAAQ,CAChG,CAOA,SAAS,EAAoB,EAAyC,EAAgC,CACpG,IAAM,EAAyB,CAAC,EAC5B,EAAS,EACb,IAAK,GAAM,CAAE,SAAQ,gBAAgB,EAAO,CAC1C,EAAa,KAAK,CAAM,EAGxB,IAAI,EAAa,GAAQ,QAAU,EACnC,GAAI,CAAC,EACH,IAAK,IAAM,KAAa,EACtB,EAAa,KAAK,IAAI,EAAY,EAAU,aAAa,EAG7D,GAAU,EAAa,EAAe,CACxC,CACA,OAAO,CACT,CAGA,SAAS,EACP,EACA,EACA,EACyB,CACzB,IAAM,EAAmB,EAAO,IAAK,GACnC,EACG,IAAK,GAAmC,CACvC,IAAM,EAAQ,EAAU,iBAAmB,EAAa,EAAU,eAAiB,GAC7E,EAAM,EAAU,eAAiB,EAAa,EAAU,eAAiB,GAC/E,MAAO,CACL,KAAM,EAAU,KAChB,SAAU,CAAC,CAAE,gBAAiB,EAAO,cAAe,CAAI,CAAC,EACzD,WAAY,EAAU,WACtB,gBAAiB,EACjB,cAAe,EACf,WAAY,EAAU,WACtB,SAAU,EAAU,SACpB,UAAW,EAAU,UACrB,QAAS,EAAU,OACrB,CACF,CAAC,CAAC,CACD,UAAU,EAAM,IAAU,EAAK,gBAAkB,EAAM,eAAe,CAC3E,EACA,OAAO,EAAoB,EAAkB,CAAY,CAC3D,CAEA,SAAS,EACP,EACA,EACA,EAC6B,CAC7B,IAAM,EAA2C,CAAC,EAG5C,EAAmB,IAAI,IACvB,EAAiB,IAAI,IACzB,EAAM,KAAK,EAAM,IAAU,CACzB,EAAK,KACL,CAAE,OAAQ,EAAK,OAAQ,gBAAiB,EAAK,gBAAiB,OAAQ,EAAa,IAAU,CAAE,CACjG,CAAC,CACH,EACM,EAAoB,IAAI,IAC1B,EAAsB,EAC1B,IAAK,IAAM,KAAS,EAAQ,CAI1B,GAAuB,EAAwB,CAAK,EACpD,IAAK,IAAM,KAAc,EACvB,EAAuB,EAAY,EAAgB,CAAiB,EAEtE,IAAM,EAAc,EACjB,KAAK,CAAE,OAAM,YAAW,cAAe,CAAE,OAAM,YAAW,SAAQ,EAAE,CAAC,CACrE,UAAU,EAAM,IAAU,EAAK,KAAK,cAAc,EAAM,IAAI,GAAK,EAAK,UAAY,EAAM,SAAS,EAC9F,EAAQ,CAAC,GAAG,IAAI,IAAI,EAAY,KAAK,CAAE,UAAW,CAAI,CAAC,CAAC,EAC9D,IAAK,IAAM,KAAQ,EACjB,EAAiB,IAAI,GAAO,EAAiB,IAAI,CAAI,GAAK,GAAK,CAAC,EAElE,EAAS,KAAK,CAAE,QAAO,cAAa,WAAY,EAAM,EAAE,EAAE,YAAc,CAAE,CAAC,CAC7E,CAOA,OANA,EAAS,MACN,EAAM,IACL,EAAM,WAAa,EAAK,aACvB,EAAK,YAAY,EAAE,EAAE,MAAQ,GAAA,CAAI,cAAc,EAAM,YAAY,EAAE,EAAE,MAAQ,EAAE,IAC/E,EAAK,YAAY,EAAE,EAAE,WAAa,IAAM,EAAM,YAAY,EAAE,EAAE,WAAa,EAChF,EACO,CACL,sBACA,+BAAgC,OAAO,YAAY,CAAgB,EACnE,2BAA4B,OAAO,YACjC,CAAC,GAAG,CAAiB,CAAC,CAAC,KAAK,CAAC,EAAM,KAAW,CAAC,EAAM,CAAC,GAAG,CAAK,CAAC,CAAC,UAAU,EAAM,IAAU,EAAO,CAAK,CAAC,CAAC,CAC1G,EACA,OAAQ,CACV,CACF,CAQA,SAAS,EACP,EACA,EAIA,EACM,CACN,IAAM,EAAW,EAAe,IAAI,EAAW,IAAI,EACnD,GAAI,CAAC,GAAU,OACb,OAEF,IAAI,EAAQ,EAAkB,IAAI,EAAW,IAAI,EAC5C,IACH,EAAQ,IAAI,IACZ,EAAkB,IAAI,EAAW,KAAM,CAAK,GAE9C,IAAK,IAAM,KAAW,EAAW,SAC/B,EACE,CACE,gBAAiB,EAAQ,gBAAkB,EAAS,OACpD,cAAe,EAAQ,cAAgB,EAAS,MAClD,EACA,EAAS,OACT,EAAS,gBACT,CACF,CAEJ"}

package/dist/duplication.cjs

@@ -1,2 +1,2 @@
-"use strict";const e=require("./duplicateSelection.cjs"),t=new Set(`statement_block.block.compound_statement.body_statement.constructor_body.do_block.if_statement.for_statement.for_in_statement.enhanced_for_statement.for_range_loop.while_statement.do_statement.try_statement.try_with_resources_statement.with_statement.switch_statement.switch_expression.switch_case.switch_block_statement_group.switch_rule.case_clause.case_statement.match_statement.match_arm.except_clause.catch_clause.finally_clause.elif_clause.ensure.expression_statement.return_statement.return_expression.if_expression.for_expression.while_expression.loop_expression.match_expression.jsx_element.jsx_self_closing_element.if.unless.case.case_match.while.until.for.begin.when`.split(`.`)),n=new Set([`program`,`source_file`,`translation_unit`,`module`,`statement_block`,`block`,`compound_statement`,`body_statement`,`constructor_body`,`class_body`,`block_body`,`do_block`,`do`,`ensure`,`then`,`else`,`case_statement`,`switch_block_statement_group`,`switch_rule`,`expression_case`,`type_case`,`communication_case`,`default_case`]),r=new Set([`identifier`,`constant`,`instance_variable`,`class_variable`,`global_variable`]),i=new Set([`shorthand_property_identifier`,`shorthand_property_identifier_pattern`]),a=new Map([[`number`,`#num`],[`number_literal`,`#num`],[`integer`,`#num`],[`float`,`#num`],[`integer_literal`,`#num`],[`float_literal`,`#num`],[`int_literal`,`#num`],[`rune_literal`,`#char`],[`imaginary_literal`,`#num`],[`decimal_integer_literal`,`#num`],[`hex_integer_literal`,`#num`],[`octal_integer_literal`,`#num`],[`binary_integer_literal`,`#num`],[`decimal_floating_point_literal`,`#num`],[`hex_floating_point_literal`,`#num`],[`string_fragment`,`#str`],[`multiline_string_fragment`,`#str`],[`string_content`,`#str`],[`raw_string_content`,`#str`],[`heredoc_content`,`#str`],[`heredoc_beginning`,`#heredoc`],[`heredoc_end`,`#heredoc`],[`string`,`#str`],[`template_string`,`#str`],[`string_literal`,`#str`],[`interpreted_string_literal`,`#str`],[`raw_string_literal`,`#str`],[`raw_string`,`#str`],[`escape_sequence`,`#str`],[`char_literal`,`#char`],[`character_literal`,`#char`],[`character`,`#char`],[`regex_pattern`,`#regex`]]),o=new Set([`#num`,`#str`,`#char`,`#regex`]),s=new Set([`comment`,`line_comment`,`block_comment`]),c=new Set([`string_fragment`,`multiline_string_fragment`,`string_content`,`raw_string_content`,`escape_sequence`,`heredoc_content`]),l=new Set([`string_fragment`,`multiline_string_fragment`,`string_content`,`raw_string_content`,`escape_sequence`,`heredoc_content`,`string_start`,`string_end`]),u=new Map([[`call_expression`,`function`],[`method_invocation`,`name`],[`call`,`method`],[`attribute`,`attribute`],[`macro_invocation`,`macro`],[`field_access`,`field`],[`new_expression`,`constructor`],[`keyword_argument`,`name`],[`element_value_pair`,`key`],[`generic_function`,`function`],[`template_function`,`name`]]),d={minTokens:40,maxGapTokens:30,minSimilarityPercent:70};function f(e,t){return e*5>=t}function p(t,n,r){let i=r?.minTokens??d.minTokens,a=r?.maxGapTokens??d.maxGapTokens,o=r?.minSimilarityPercent??d.minSimilarityPercent,s=[],c=[],l=[];h(t,s,c,l);let u=S(s),f=[...w(s,u,c,i),...T(s,u,l,i)],p=X(Y(e.selectMaximalGroups(f,e=>e.length>=2)),a),m=k(s,u,c,i,o,p);return re([...p.filter(e=>e.length>0),...m],n,s)}function m(t,n){let r=n?.minTokens??d.minTokens,i=[],a=[],o=[];h(t,i,a,o);let s=S(i),c=w(i,s,a,r);for(let e of o){let t=e[0],n=e.at(-1);!t||!n||n.endTokenIndex-t.startTokenIndex<r||c.push(R(`s:${U(i,s,t.startTokenIndex,n.endTokenIndex)}`,t.startTokenIndex,n.endTokenIndex,t,n))}return{candidates:e.dedupeByRegion(c),tokens:i,containerStatements:o}}function h(e,r,i,a){function o(e){let c=r.length,l=e.childCount===0?void 0:g(e);if(e.childCount===0)_(e,r);else if(l!==void 0)r.push(v(l,y(e,l),e.startPosition.row,e.endPosition.row));else if(!s.has(e.type)){let t=[],r=e.isNamed&&n.has(e.type);for(let n of e.children){let e=o(n);r&&n.isNamed&&!s.has(n.type)&&t.push(e)}r&&t.length>0&&a.push(t)}let u={startTokenIndex:c,endTokenIndex:r.length,startIndex:e.startIndex,endIndex:e.endIndex,startLine:e.startPosition.row+1,endLine:e.endPosition.row+1};return e.isNamed&&t.has(e.type)&&i.push(u),u}o(e)}function g(e){let t=e.isNamed?a.get(e.type):void 0;if(t!==void 0)return e.namedChildren.every(e=>l.has(e.type))?t:void 0}function _(e,t){if(s.has(e.type))return;let n=e.startPosition.row,o=e.endPosition.row;if(e.isNamed&&i.has(e.type)){t.push(v(e.text,void 0,n,o,!0),v(`:`,void 0,n,o),{kind:`id`,text:e.text,textHash:0,textHash2:0,startRow:n,endRow:o});return}if(e.isNamed&&r.has(e.type)&&!C(e)){t.push({kind:`id`,text:e.text,textHash:0,textHash2:0,startRow:n,endRow:o});return}let c=e.isNamed?a.get(e.type):void 0;c===void 0?t.push(v(e.text,void 0,n,o,e.isNamed)):t.push(v(c,y(e,c),n,o))}function v(e,t,n,r,i=!1){let a={kind:`text`,text:e,textHash:K(e),textHash2:q(e),startRow:n,endRow:r};return t!==void 0&&o.has(e)&&(a.literalHash=K(t),a.literalHash2=q(t)),i&&(a.isName=!0),a}function y(e,t){if(t!==`#str`&&t!==`#char`||c.has(e.type))return e.text;let n=e.namedChildren.filter(e=>c.has(e.type));return n.length>0?n.map(e=>e.text).join(``):x(e.text)}const b=new Set([`"`,`'`,"`"]);function x(e){let t=e[0];return e.length>=2&&t!==void 0&&b.has(t)&&e.endsWith(t)?e.slice(1,-1):e}function S(e){let t=new Int32Array(e.length+1);for(let[n,r]of e.entries())t[n+1]=(t[n]??0)+(r.literalHash===void 0?0:1);return t}function C(e){let t=e.parent;if(!t)return!1;if(t.type===`method_reference`||t.type===`call`&&t.childForFieldName(`function`)?.id===e.id||e.type===`constant`&&t.type===`call`&&t.childForFieldName(`receiver`)?.id===e.id||t.type===`method_invocation`&&t.childForFieldName(`object`)?.id===e.id&&/^\p{Lu}/u.test(e.text))return!0;if((t.type===`scoped_identifier`||t.type===`qualified_identifier`)&&(t.childForFieldName(`name`)?.id===e.id||t.childForFieldName(`path`)?.id===e.id)){let e=t;for(;e.parent&&(e.parent.type===`scoped_identifier`||e.parent.type===`qualified_identifier`||e.parent.type===`generic_function`||e.parent.type===`template_function`);)e=e.parent;if(e.parent?.type===`call_expression`&&e.parent.childForFieldName(`function`)?.id===e.id)return!0}if(t.type===`literal_element`&&t.parent?.type===`keyed_element`&&t.parent.namedChild(0)?.id===t.id)return!0;let n=u.get(t.type);return n!==void 0&&t.childForFieldName(n)?.id===e.id}function w(e,t,n,r){let i=[];for(let a of n)a.endTokenIndex-a.startTokenIndex<r||i.push(R(`b:${U(e,t,a.startTokenIndex,a.endTokenIndex)}`,a.startTokenIndex,a.endTokenIndex,a,a));return i}function T(e,t,n,r){return E([{tokens:e,literalCountPrefix:t,containers:n}],r,!1).map(({candidate:e})=>e)}function E(e,t,n){let r=[],i=[],a=[];for(let[t,n]of e.entries())for(let e of n.containers)i.push(t),a.push(e);let o=t=>e[i[t]??0],s=new Map,c=a.map((e,n)=>O(o(n)?.tokens??[],e,t));for(let[e,t]of c.entries()){let n=i[e]??0;for(let[r,i]of t.windowKeysByStart.entries())for(let t of i){if(t===void 0)continue;let i=s.get(t);i?(i.count+=1,i.containerIndex!==e&&(i.containerIndex=-1),i.contextIndex!==n&&(i.contextIndex=-1),i.minStart=Math.min(i.minStart,r),i.maxStart=Math.max(i.maxStart,r)):s.set(t,{count:1,containerIndex:e,contextIndex:n,minStart:r,maxStart:r})}}let l=(e,t)=>{if(e===void 0)return!1;let r=s.get(e);return r===void 0||r.count<2?!1:n?r.contextIndex===-1:r.containerIndex===-1||r.maxStart-r.minStart>=t},u=e=>{let t=c[e.containerIndex]?.statementHashes??[],n=t[e.start];for(let r=e.start+1;r<e.start+e.length;r+=1)if(t[r]!==n)return!0;return!1},d=[];for(let[e,t]of c.entries())for(let[n,r]of t.windowKeysByStart.entries())for(let[i,a]of r.entries()){if(!l(a,i)||!u({containerIndex:e,start:n,length:i}))continue;let r=t.windowKeysByStart[n]?.[i+1],o=t.windowKeysByStart[n-1]?.[i+1];l(r,i+1)||l(o,i+1)||d.push({containerIndex:e,start:n,length:i})}let f=new Set(d.map(D)),p=d;for(;p.length>0;){let e=[];for(let t of p){let n=a[t.containerIndex],s=n?.[t.start],c=n?.[t.start+t.length-1],l=o(t.containerIndex);if(!s||!c||!l)continue;let u=`s:${U(l.tokens,l.literalCountPrefix,s.startTokenIndex,c.endTokenIndex)}`;r.push({candidate:R(u,s.startTokenIndex,c.endTokenIndex,s,c),contextIndex:i[t.containerIndex]??0}),e.push(t)}p=[];for(let t of e)for(let e of[t.start,t.start+1]){let n={containerIndex:t.containerIndex,start:e,length:t.length-1},r=c[t.containerIndex]?.windowKeysByStart[e]?.[n.length];f.has(D(n))||!l(r,n.length)||!u(n)||(f.add(D(n)),p.push(n))}}return r}function D(e){return`${e.containerIndex}:${e.start}:${e.length}`}function O(e,t,n){let r=t.map(t=>W(e,t.startTokenIndex,t.endTokenIndex)),i=[];for(let e=0;e<t.length;e+=1){let a=[],o=5381,s=0,c=Math.min(t.length,e+100);for(let i=e;i<c;i+=1){let c=t[i],l=r[i];if(!c||l===void 0)break;o=J(o,l),s+=c.endTokenIndex-c.startTokenIndex;let u=i-e+1;a[u]=u>=2&&s>=n?J(o,u):void 0}i.push(a)}return{windowKeysByStart:i,statementHashes:r}}function k(e,t,n,r,i,a){if(i>=100)return[];let o=A(n.filter(e=>{let n=e.endTokenIndex-e.startTokenIndex,i=(t[e.endTokenIndex]??0)-(t[e.startTokenIndex]??0);return n>=r&&!f(i,n)}).toSorted((e,t)=>e.startTokenIndex-t.startTokenIndex||t.endTokenIndex-e.endTokenIndex));if(o.length<2)return[];let s=o.map(e=>{let t=[];for(let[n,r]of a.entries())r.some(t=>t.startTokenIndex<e.endTokenIndex&&e.startTokenIndex<t.endTokenIndex)&&t.push(n);return t}),c=new Map,l=o.map(t=>F(e,t,c)),u=l.map(({sequence:e})=>ee(e)),d=te(u),p=o.map((e,t)=>t),m=e=>{let t=e;for(;p[t]!==t;)t=p[t]??t;for(;p[e]!==t;){let n=p[e]??t;p[e]=t,e=n}return t};for(let[e,t]of d){let n=Math.floor(e/u.length),r=e%u.length,a=l[n],o=l[r],c=u[n],d=u[r];if(!(!a||!o||!c||!d)&&!((s[n]?.length??0)>0&&(s[r]?.length??0)>0)&&!(t*100<10*Math.min(c.size,d.size))&&!(I(a,o)*100<=50*Math.max(a.contentTotal,o.contentTotal))&&ne(a.sequence,o.sequence)*100>=i*Math.max(a.sequence.length,o.sequence.length)){let e=m(n),t=m(r);p[Math.max(e,t)]=Math.min(e,t)}}let h=new Map;for(let e of o.keys()){let t=m(e),n=h.get(t)??[];n.push(e),h.set(t,n)}let g=[];for(let e of h.values()){if(e.length<2)continue;let t=e.filter(e=>(s[e]?.length??0)===0),n=e.filter(e=>(s[e]?.length??0)>0);if(n.length===0){g.push(e.flatMap(e=>o[e]?[P(o[e])]:[]));continue}if(t.length===0)continue;let r=t=>e.some(e=>{let n=o[e];return n!==void 0&&t.startTokenIndex<n.endTokenIndex&&n.startTokenIndex<t.endTokenIndex}),i=[...new Set(n.flatMap(e=>s[e]??[]))].filter(e=>{let t=a[e];return t!==void 0&&t.length>0&&t.every(r)}).toSorted((e,t)=>e-t),[c,...l]=i;if(c!==void 0){let t=new Set,n=[];for(let r of e){let e=o[r];if(!e)continue;let c=[];for(let n of i)for(let r of a[n]??[])!t.has(r)&&r.startTokenIndex<e.endTokenIndex&&e.startTokenIndex<r.endTokenIndex&&(t.add(r),c.push({occurrence:r,groupIndex:n}));c.sort((e,t)=>e.occurrence.startTokenIndex-t.occurrence.startTokenIndex||e.occurrence.endTokenIndex-t.occurrence.endTokenIndex);let l=[],u=new Set;for(let{occurrence:e,groupIndex:t}of c)u.has(t)&&(n.push(M(l)),l=[],u.clear()),l.push(e),u.add(t);l.length>0&&n.push(M(l)),c.length===0&&(s[r]?.length??0)===0&&n.push(P(e))}n.sort((e,t)=>e.startTokenIndex-t.startTokenIndex||e.endTokenIndex-t.endTokenIndex);for(let e of n)e.sharedWithMergedGroup=void 0;a[c]=n;for(let e of l)a[e]=[]}else t.length>=2&&g.push(t.flatMap(e=>o[e]?[P(o[e])]:[]))}return g.sort(Z),g}function A(e){let t=[],n=[];for(let r of e){for(;n.length>0&&n.at(-1).range.endTokenIndex<=r.startTokenIndex;)n.pop();let e=n.at(-1);if(e&&e.range.startTokenIndex===r.startTokenIndex&&e.range.endTokenIndex===r.endTokenIndex)continue;let i={range:r,children:[]};e?e.children.push(i):t.push(i),n.push(i)}let r=[],i=e=>{if(j(e))for(let t of e.children)i(t);else r.push(e.range)};for(let e of t)i(e);return r}function j(e){let[t]=e.children;return e.children.length>=2||t!==void 0&&j(t)}function M(e){let t=e[0];if(!t||e.length===1)return t??N();let n=[];for(let t of e.flatMap(e=>e.segments).toSorted((e,t)=>e.startTokenIndex-t.startTokenIndex||e.endTokenIndex-t.endTokenIndex)){let e=n.at(-1);e&&t.startTokenIndex<e.endTokenIndex?e.endTokenIndex=Math.max(e.endTokenIndex,t.endTokenIndex):n.push({...t})}return{segments:n,tokenCount:n.reduce((e,t)=>e+t.endTokenIndex-t.startTokenIndex,0),startTokenIndex:Math.min(...e.map(e=>e.startTokenIndex)),endTokenIndex:Math.max(...e.map(e=>e.endTokenIndex)),startIndex:Math.min(...e.map(e=>e.startIndex)),endIndex:Math.max(...e.map(e=>e.endIndex)),startLine:Math.min(...e.map(e=>e.startLine)),endLine:Math.max(...e.map(e=>e.endLine))}}function N(){return{segments:[],tokenCount:0,startTokenIndex:0,endTokenIndex:0,startIndex:0,endIndex:0,startLine:0,endLine:0}}function P(e){return{segments:[{startTokenIndex:e.startTokenIndex,endTokenIndex:e.endTokenIndex}],tokenCount:e.endTokenIndex-e.startTokenIndex,startTokenIndex:e.startTokenIndex,endTokenIndex:e.endTokenIndex,startIndex:e.startIndex,endIndex:e.endIndex,startLine:e.startLine,endLine:e.endLine}}function F(e,t,n){let r=new Int32Array(t.endTokenIndex-t.startTokenIndex),i=new Map,a=new Map,o=0;for(let s=t.startTokenIndex;s<t.endTokenIndex;s+=1){let c=e[s];if(!c)continue;let l;if(c.kind===`id`){let e=i.get(c.text);e===void 0&&(e=i.size,i.set(c.text,e)),l=-(e+1)}else{let e=`${c.textHash}:${c.textHash2}:${c.literalHash??0}:${c.literalHash2??0}`,t=n.get(e);t===void 0&&(t=n.size,n.set(e,t)),l=t,(c.isName===!0||c.literalHash!==void 0)&&(a.set(l,(a.get(l)??0)+1),o+=1)}r[s-t.startTokenIndex]=l}return{sequence:r,contentCountBySymbol:a,contentTotal:o}}function I(e,t){let[n,r]=e.contentCountBySymbol.size<=t.contentCountBySymbol.size?[e,t]:[t,e],i=0;for(let[e,t]of n.contentCountBySymbol)i+=Math.min(t,r.contentCountBySymbol.get(e)??0);return i}function ee(e){let t=new Set;for(let n=0;n+5<=e.length;n+=1){let r=5381;for(let t=0;t<5;t+=1)r=Math.imul(r,31)+(e[n+t]??0)|0;t.add(r)}return t}function te(e){let t=new Map;for(let[n,r]of e.entries())for(let e of r){let r=t.get(e);r||(r=[],t.set(e,r)),r.push(n)}let n=new Map;for(let r of t.values())for(let t=0;t<r.length;t+=1){let i=r[t]??0;for(let a=t+1;a<r.length;a+=1){let t=i*e.length+(r[a]??0);n.set(t,(n.get(t)??0)+1)}}return n}function ne(e,t){let n=e.length+31>>>5,r=new Map;for(let[t,i]of e.entries()){let e=r.get(i);e||(e=new Uint32Array(n),r.set(i,e));let a=t>>>5;e[a]=(e[a]??0)|1<<(t&31)}let i=new Uint32Array(n);for(let e of t){let t=r.get(e),a=1,o=0;for(let e=0;e<n;e+=1){let n=i[e]??0,r=((t?.[e]??0)|n)>>>0,s=(n<<1|a)>>>0;a=n>>>31;let c=r-s-o;o=+(c<0),i[e]=r&~c}}let a=0;for(let e of i)a+=L(e);return a}function L(e){let t=e-(e>>>1&1431655765);return t=(t&858993459)+(t>>>2&858993459),Math.imul(t+(t>>>4)&252645135,16843009)>>>24&255}function R(e,t,n,r,i){return{fingerprint:e,tokenCount:n-t,startTokenIndex:t,endTokenIndex:n,startIndex:r.startIndex,endIndex:i.endIndex,startLine:r.startLine,endLine:i.endLine}}const z=[],B=[];function V(e){let t=z[e];return t===void 0&&(t=K(`$${e}`),z[e]=t),t}function H(e){let t=B[e];return t===void 0&&(t=q(`$${e}`),B[e]=t),t}function U(e,t,n,r){let[i,a]=G(e,n,r,f((t[r]??0)-(t[n]??0),r-n));return`${i}:${a}:${r-n}`}function W(e,t,n){let[r,i]=G(e,t,n,!1);return r^Math.imul(i,31)}function G(e,t,n,r){let i=new Map,a=5381,o=52711;for(let s=t;s<n;s+=1){let t=e[s];if(!t)continue;let n,c;if(t.kind===`id`){let e=i.get(t.text);e===void 0&&(e=i.size,i.set(t.text,e)),n=V(e),c=H(e)}else n=t.textHash,c=t.textHash2;a=Math.imul(a,31)+n|0,o=Math.imul(o,37)^c,r&&t.literalHash!==void 0&&t.literalHash2!==void 0&&(a=Math.imul(a,31)+t.literalHash|0,o=Math.imul(o,37)^t.literalHash2)}return[a,o]}function K(e){let t=5381;for(let n=0;n<e.length;n+=1)t=Math.imul(t,33)^e.charCodeAt(n);return t}function q(e){let t=-2128831035;for(let n=0;n<e.length;n+=1)t=Math.imul(t^e.charCodeAt(n),16777619);return t}function J(e,t){return Math.imul(e,31)+t}function Y(e){let t=[];for(let n of e.values()){let e=n.map(e=>({segments:[{startTokenIndex:e.startTokenIndex,endTokenIndex:e.endTokenIndex}],tokenCount:e.tokenCount,startTokenIndex:e.startTokenIndex,endTokenIndex:e.endTokenIndex,startIndex:e.startIndex,endIndex:e.endIndex,startLine:e.startLine,endLine:e.endLine}));e.sort((e,t)=>e.startTokenIndex-t.startTokenIndex||e.endTokenIndex-t.endTokenIndex),t.push(e)}return t}function X(e,t){if(t<=0||e.length<2)return e;e.sort(Z);for(let n=!0;n;){n=!1;for(let r=0;r<e.length&&!n;r+=1)for(let i=r+1;i<e.length;i+=1){let a=e[r],o=e[i];if(!a||!o)continue;let s=Q(a,o,t),c=s??Q(o,a,t);if(!c)continue;let l=s?c.firstConsumed:c.secondConsumed,u=s?c.secondConsumed:c.firstConsumed;l&&u?(e[r]=c.merged,e.splice(i,1)):u?e[i]=c.merged:e[r]=c.merged;for(let e of c.pairedRetained)e.sharedWithMergedGroup=!0;e.sort(Z),n=!0;break}}return e}function Z(e,t){let n=e[0],r=t[0];return(n?.startTokenIndex??0)-(r?.startTokenIndex??0)||(n?.endTokenIndex??0)-(r?.endTokenIndex??0)}function Q(e,t,n){let r=e.filter(e=>!e.sharedWithMergedGroup),i=t.filter(e=>!e.sharedWithMergedGroup),a=[],o=0,s=-1;for(let e of i){for(;o<r.length;){let t=r[o];if(t&&t.endTokenIndex+n<e.startTokenIndex)o+=1;else break}let t=r[o];t&&t.endTokenIndex<=e.startTokenIndex&&t.startTokenIndex>=s&&(a.push([t,e]),s=e.endTokenIndex,o+=1)}let c=a.length===e.length,l=a.length===t.length;if(!(a.length<2||!c&&!l))return{merged:a.map(([e,t])=>({...e,sharedWithMergedGroup:void 0,segments:[...e.segments,...t.segments],tokenCount:e.tokenCount+t.tokenCount,endTokenIndex:t.endTokenIndex,endIndex:t.endIndex,endLine:t.endLine})),firstConsumed:c,secondConsumed:l,pairedRetained:c===l?[]:a.map(([e,t])=>c?t:e)}}function $(e){let t=0,n=0,r=!1;for(let i of e){if(i.sharedWithMergedGroup){r=!0;continue}t+=i.segments.length,n=Math.max(n,i.segments.length)}return r?t:t-n}function re(e,t,n){let r=0,i=0,a=[],o=new Set;for(let s of e){r+=$(s);for(let e of s){i=Math.max(i,e.tokenCount);for(let r of e.segments)for(let e=r.startTokenIndex;e<r.endTokenIndex;e+=1){let r=n[e];for(let e=r?.startRow??0;e<=(r?.endRow??-1);e+=1)t.has(e+1)&&o.add(e+1)}}a.push(s.map(({startLine:e,endLine:t})=>({startLine:e,endLine:t})).toSorted((e,t)=>e.startLine-t.startLine))}return a.sort((e,t)=>(e[0]?.startLine??0)-(t[0]?.startLine??0)),{duplicateBlockCount:r,duplicateBlockGroupCount:e.length,duplicateBlockGroups:a,duplicateLineCount:o.size,duplicationRatio:t.size===0?0:o.size/t.size,maxDuplicateBlockSize:i}}exports.buildLiteralCountPrefix=S,exports.collectCrossFileDuplicateCandidates=m,exports.collectSequenceWindowCandidates=E,exports.countRedundantFragments=$,exports.defaultDuplicationOptions=d,exports.measureDuplication=p,exports.mergeAdjacentGroups=X;
+"use strict";const e=require("./duplicateSelection.cjs"),t=new Set(`statement_block.block.compound_statement.body_statement.constructor_body.do_block.if_statement.for_statement.for_in_statement.enhanced_for_statement.for_range_loop.while_statement.do_statement.try_statement.try_with_resources_statement.with_statement.switch_statement.switch_expression.switch_case.switch_block_statement_group.switch_rule.case_clause.case_statement.match_statement.match_arm.except_clause.catch_clause.finally_clause.elif_clause.ensure.expression_statement.return_statement.return_expression.if_expression.for_expression.while_expression.loop_expression.match_expression.jsx_element.jsx_self_closing_element.if.unless.case.case_match.while.until.for.begin.when`.split(`.`)),n=new Set([`program`,`source_file`,`translation_unit`,`module`,`statement_block`,`block`,`compound_statement`,`body_statement`,`constructor_body`,`class_body`,`block_body`,`do_block`,`do`,`ensure`,`then`,`else`,`case_statement`,`switch_block_statement_group`,`switch_rule`,`expression_case`,`type_case`,`communication_case`,`default_case`]),r=new Set([`identifier`,`constant`,`instance_variable`,`class_variable`,`global_variable`]),i=new Set([`shorthand_property_identifier`,`shorthand_property_identifier_pattern`]),a=new Map([[`number`,`#num`],[`number_literal`,`#num`],[`integer`,`#num`],[`float`,`#num`],[`integer_literal`,`#num`],[`float_literal`,`#num`],[`int_literal`,`#num`],[`rune_literal`,`#char`],[`imaginary_literal`,`#num`],[`decimal_integer_literal`,`#num`],[`hex_integer_literal`,`#num`],[`octal_integer_literal`,`#num`],[`binary_integer_literal`,`#num`],[`decimal_floating_point_literal`,`#num`],[`hex_floating_point_literal`,`#num`],[`string_fragment`,`#str`],[`multiline_string_fragment`,`#str`],[`string_content`,`#str`],[`raw_string_content`,`#str`],[`heredoc_content`,`#str`],[`heredoc_beginning`,`#heredoc`],[`heredoc_end`,`#heredoc`],[`string`,`#str`],[`template_string`,`#str`],[`string_literal`,`#str`],[`interpreted_string_literal`,`#str`],[`raw_string_literal`,`#str`],[`raw_string`,`#str`],[`escape_sequence`,`#str`],[`char_literal`,`#char`],[`character_literal`,`#char`],[`character`,`#char`],[`regex_pattern`,`#regex`]]),o=new Set([`#num`,`#str`,`#char`,`#regex`]),s=new Set([`comment`,`line_comment`,`block_comment`]),c=new Set([`string_fragment`,`multiline_string_fragment`,`string_content`,`raw_string_content`,`escape_sequence`,`heredoc_content`]),l=new Set([`string_fragment`,`multiline_string_fragment`,`string_content`,`raw_string_content`,`escape_sequence`,`heredoc_content`,`string_start`,`string_end`]),u=new Map([[`call_expression`,`function`],[`method_invocation`,`name`],[`call`,`method`],[`attribute`,`attribute`],[`macro_invocation`,`macro`],[`field_access`,`field`],[`new_expression`,`constructor`],[`keyword_argument`,`name`],[`element_value_pair`,`key`],[`generic_function`,`function`],[`template_function`,`name`]]),d={minTokens:40,maxGapTokens:30,minSimilarityPercent:70};function f(e,t){return e*5>=t}function p(t,n,r){let i=r?.minTokens??d.minTokens,a=r?.maxGapTokens??d.maxGapTokens,o=r?.minSimilarityPercent??d.minSimilarityPercent,s=[],c=[],l=[];h(t,s,c,l);let u=b(s),f=[...S(s,u,c,i),...C(s,u,l,i)],p=Y(re(e.selectMaximalGroups(f,e=>e.length>=2)),a),m=D(s,u,c,i,o,p);return ie([...p.filter(e=>e.length>0),...m],n,s)}function m(t,n){let r=n?.minTokens??d.minTokens,i=[],a=[],o=[];h(t,i,a,o);let s=b(i),c=S(i,s,a,r);for(let e of o){let t=e[0],n=e.at(-1);!t||!n||n.endTokenIndex-t.startTokenIndex<r||c.push(z(`s:${W(i,s,t.startTokenIndex,n.endTokenIndex)}`,t.startTokenIndex,n.endTokenIndex,t,n))}return{candidates:e.dedupeByRegion(c),tokens:i,containerStatements:o}}function h(e,r,i,a){function o(e){let c=r.length,l=e.childCount===0?void 0:g(e);if(e.childCount===0)ee(e,r);else if(l!==void 0)r.push(_(l,v(e,l),e.startPosition.row,e.endPosition.row));else if(!s.has(e.type)){let t=[],r=e.isNamed&&n.has(e.type);for(let n of e.children){let e=o(n);r&&n.isNamed&&!s.has(n.type)&&t.push(e)}r&&t.length>0&&a.push(t)}let u={startTokenIndex:c,endTokenIndex:r.length,startIndex:e.startIndex,endIndex:e.endIndex,startLine:e.startPosition.row+1,endLine:e.endPosition.row+1};return e.isNamed&&t.has(e.type)&&i.push(u),u}o(e)}function g(e){let t=e.isNamed?a.get(e.type):void 0;if(t!==void 0)return e.namedChildren.every(e=>l.has(e.type))?t:void 0}function ee(e,t){if(s.has(e.type))return;let n=e.startPosition.row,o=e.endPosition.row;if(e.isNamed&&i.has(e.type)){t.push(_(e.text,void 0,n,o,!0),_(`:`,void 0,n,o),{kind:`id`,text:e.text,textHash:0,textHash2:0,startRow:n,endRow:o});return}if(e.isNamed&&r.has(e.type)&&!x(e)){t.push({kind:`id`,text:e.text,textHash:0,textHash2:0,startRow:n,endRow:o});return}let c=e.isNamed?a.get(e.type):void 0;c===void 0?t.push(_(e.text,void 0,n,o,e.isNamed)):t.push(_(c,v(e,c),n,o))}function _(e,t,n,r,i=!1){let a={kind:`text`,text:e,textHash:K(e),textHash2:q(e),startRow:n,endRow:r};return t!==void 0&&o.has(e)&&(a.literalHash=K(t),a.literalHash2=q(t)),i&&(a.isName=!0),a}function v(e,t){if(t!==`#str`&&t!==`#char`||c.has(e.type))return e.text;let n=e.namedChildren.filter(e=>c.has(e.type));return n.length>0?n.map(e=>e.text).join(``):te(e.text)}const y=new Set([`"`,`'`,"`"]);function te(e){let t=e[0];return e.length>=2&&t!==void 0&&y.has(t)&&e.endsWith(t)?e.slice(1,-1):e}function b(e){let t=new Int32Array(e.length+1);for(let[n,r]of e.entries())t[n+1]=(t[n]??0)+(r.literalHash===void 0?0:1);return t}function x(e){let t=e.parent;if(!t)return!1;if(t.type===`method_reference`||t.type===`call`&&t.childForFieldName(`function`)?.id===e.id||e.type===`constant`&&t.type===`call`&&t.childForFieldName(`receiver`)?.id===e.id||t.type===`method_invocation`&&t.childForFieldName(`object`)?.id===e.id&&/^\p{Lu}/u.test(e.text))return!0;if((t.type===`scoped_identifier`||t.type===`qualified_identifier`)&&(t.childForFieldName(`name`)?.id===e.id||t.childForFieldName(`path`)?.id===e.id)){let e=t;for(;e.parent&&(e.parent.type===`scoped_identifier`||e.parent.type===`qualified_identifier`||e.parent.type===`generic_function`||e.parent.type===`template_function`);)e=e.parent;if(e.parent?.type===`call_expression`&&e.parent.childForFieldName(`function`)?.id===e.id)return!0}if(t.type===`literal_element`&&t.parent?.type===`keyed_element`&&t.parent.namedChild(0)?.id===t.id)return!0;let n=u.get(t.type);return n!==void 0&&t.childForFieldName(n)?.id===e.id}function S(e,t,n,r){let i=[];for(let a of n)a.endTokenIndex-a.startTokenIndex<r||i.push(z(`b:${W(e,t,a.startTokenIndex,a.endTokenIndex)}`,a.startTokenIndex,a.endTokenIndex,a,a));return i}function C(e,t,n,r){return w([{tokens:e,literalCountPrefix:t,containers:n}],r,!1).map(({candidate:e})=>e)}function w(e,t,n){let r=[],i=[],a=[];for(let[t,n]of e.entries())for(let e of n.containers)i.push(t),a.push(e);let o=t=>e[i[t]??0],s=new Map,c=a.map((e,n)=>E(o(n)?.tokens??[],e,t));for(let[e,t]of c.entries()){let n=i[e]??0;for(let[r,i]of t.windowKeysByStart.entries())for(let t of i){if(t===void 0)continue;let i=s.get(t);i?(i.count+=1,i.containerIndex!==e&&(i.containerIndex=-1),i.contextIndex!==n&&(i.contextIndex=-1),i.minStart=Math.min(i.minStart,r),i.maxStart=Math.max(i.maxStart,r)):s.set(t,{count:1,containerIndex:e,contextIndex:n,minStart:r,maxStart:r})}}let l=(e,t)=>{if(e===void 0)return!1;let r=s.get(e);return r===void 0||r.count<2?!1:n?r.contextIndex===-1:r.containerIndex===-1||r.maxStart-r.minStart>=t},u=e=>{let t=c[e.containerIndex]?.statementHashes??[],n=t[e.start];for(let r=e.start+1;r<e.start+e.length;r+=1)if(t[r]!==n)return!0;return!1},d=[];for(let[e,t]of c.entries())for(let[n,r]of t.windowKeysByStart.entries())for(let[i,a]of r.entries()){if(!l(a,i)||!u({containerIndex:e,start:n,length:i}))continue;let r=t.windowKeysByStart[n]?.[i+1],o=t.windowKeysByStart[n-1]?.[i+1];l(r,i+1)||l(o,i+1)||d.push({containerIndex:e,start:n,length:i})}let f=new Set(d.map(T)),p=d;for(;p.length>0;){let e=[];for(let t of p){let n=a[t.containerIndex],s=n?.[t.start],c=n?.[t.start+t.length-1],l=o(t.containerIndex);if(!s||!c||!l)continue;let u=`s:${W(l.tokens,l.literalCountPrefix,s.startTokenIndex,c.endTokenIndex)}`;r.push({candidate:z(u,s.startTokenIndex,c.endTokenIndex,s,c),contextIndex:i[t.containerIndex]??0}),e.push(t)}p=[];for(let t of e)for(let e of[t.start,t.start+1]){let n={containerIndex:t.containerIndex,start:e,length:t.length-1},r=c[t.containerIndex]?.windowKeysByStart[e]?.[n.length];f.has(T(n))||!l(r,n.length)||!u(n)||(f.add(T(n)),p.push(n))}}return r}function T(e){return`${e.containerIndex}:${e.start}:${e.length}`}function E(e,t,n){let r=t.map(t=>ne(e,t.startTokenIndex,t.endTokenIndex)),i=[];for(let e=0;e<t.length;e+=1){let a=[],o=5381,s=0,c=Math.min(t.length,e+100);for(let i=e;i<c;i+=1){let c=t[i],l=r[i];if(!c||l===void 0)break;o=J(o,l),s+=c.endTokenIndex-c.startTokenIndex;let u=i-e+1;a[u]=u>=2&&s>=n?J(o,u):void 0}i.push(a)}return{windowKeysByStart:i,statementHashes:r}}function D(e,t,n,r,i,a){if(i>=100)return[];let o=O(n.filter(e=>{let n=e.endTokenIndex-e.startTokenIndex,i=(t[e.endTokenIndex]??0)-(t[e.startTokenIndex]??0);return n>=r&&!f(i,n)}).toSorted((e,t)=>e.startTokenIndex-t.startTokenIndex||t.endTokenIndex-e.endTokenIndex));if(o.length<2)return[];let s=o.map(e=>{let t=[];for(let[n,r]of a.entries())r.some(t=>t.startTokenIndex<e.endTokenIndex&&e.startTokenIndex<t.endTokenIndex)&&t.push(n);return t}),c=new Map,l=o.map(t=>N(e,t,c)),u=l.map(({sequence:e})=>F(e)),d=I(u),p=o.map((e,t)=>t),m=e=>{let t=e;for(;p[t]!==t;)t=p[t]??t;for(;p[e]!==t;){let n=p[e]??t;p[e]=t,e=n}return t};for(let[e,t]of d){let n=Math.floor(e/u.length),r=e%u.length,a=l[n],o=l[r],c=u[n],d=u[r];if(!(!a||!o||!c||!d)&&!((s[n]?.length??0)>0&&(s[r]?.length??0)>0)&&!(t*100<10*Math.min(c.size,d.size))&&!(P(a,o)*100<=50*Math.max(a.contentTotal,o.contentTotal))&&L(a.sequence,o.sequence)*100>=i*Math.max(a.sequence.length,o.sequence.length)){let e=m(n),t=m(r);p[Math.max(e,t)]=Math.min(e,t)}}let h=new Map;for(let e of o.keys()){let t=m(e),n=h.get(t)??[];n.push(e),h.set(t,n)}let g=[];for(let e of h.values()){if(e.length<2)continue;let t=e.filter(e=>(s[e]?.length??0)===0),n=e.filter(e=>(s[e]?.length??0)>0);if(n.length===0){g.push(e.flatMap(e=>o[e]?[M(o[e])]:[]));continue}if(t.length===0)continue;let r=t=>e.some(e=>{let n=o[e];return n!==void 0&&t.startTokenIndex<n.endTokenIndex&&n.startTokenIndex<t.endTokenIndex}),i=[...new Set(n.flatMap(e=>s[e]??[]))].filter(e=>{let t=a[e];return t!==void 0&&t.length>0&&t.every(r)}).toSorted((e,t)=>e-t),[c,...l]=i;if(c!==void 0){let t=new Set,n=[];for(let r of e){let e=o[r];if(!e)continue;let c=[];for(let n of i)for(let r of a[n]??[])!t.has(r)&&r.startTokenIndex<e.endTokenIndex&&e.startTokenIndex<r.endTokenIndex&&(t.add(r),c.push({occurrence:r,groupIndex:n}));c.sort((e,t)=>e.occurrence.startTokenIndex-t.occurrence.startTokenIndex||e.occurrence.endTokenIndex-t.occurrence.endTokenIndex);let l=[],u=new Set;for(let{occurrence:e,groupIndex:t}of c)u.has(t)&&(n.push(A(l)),l=[],u.clear()),l.push(e),u.add(t);l.length>0&&n.push(A(l)),c.length===0&&(s[r]?.length??0)===0&&n.push(M(e))}n.sort((e,t)=>e.startTokenIndex-t.startTokenIndex||e.endTokenIndex-t.endTokenIndex);for(let e of n)e.sharedWithMergedGroup=void 0;a[c]=n;for(let e of l)a[e]=[]}else t.length>=2&&g.push(t.flatMap(e=>o[e]?[M(o[e])]:[]))}return g.sort(X),g}function O(e){let t=[],n=[];for(let r of e){for(;n.length>0&&n.at(-1).range.endTokenIndex<=r.startTokenIndex;)n.pop();let e=n.at(-1);if(e&&e.range.startTokenIndex===r.startTokenIndex&&e.range.endTokenIndex===r.endTokenIndex)continue;let i={range:r,children:[]};e?e.children.push(i):t.push(i),n.push(i)}let r=[],i=e=>{if(k(e))for(let t of e.children)i(t);else r.push(e.range)};for(let e of t)i(e);return r}function k(e){let[t]=e.children;return e.children.length>=2||t!==void 0&&k(t)}function A(e){let t=e[0];if(!t||e.length===1)return t??j();let n=[];for(let t of e.flatMap(e=>e.segments).toSorted((e,t)=>e.startTokenIndex-t.startTokenIndex||e.endTokenIndex-t.endTokenIndex)){let e=n.at(-1);e&&t.startTokenIndex<e.endTokenIndex?e.endTokenIndex=Math.max(e.endTokenIndex,t.endTokenIndex):n.push({...t})}return{segments:n,tokenCount:n.reduce((e,t)=>e+t.endTokenIndex-t.startTokenIndex,0),startTokenIndex:Math.min(...e.map(e=>e.startTokenIndex)),endTokenIndex:Math.max(...e.map(e=>e.endTokenIndex)),startIndex:Math.min(...e.map(e=>e.startIndex)),endIndex:Math.max(...e.map(e=>e.endIndex)),startLine:Math.min(...e.map(e=>e.startLine)),endLine:Math.max(...e.map(e=>e.endLine))}}function j(){return{segments:[],tokenCount:0,startTokenIndex:0,endTokenIndex:0,startIndex:0,endIndex:0,startLine:0,endLine:0}}function M(e){return{segments:[{startTokenIndex:e.startTokenIndex,endTokenIndex:e.endTokenIndex}],tokenCount:e.endTokenIndex-e.startTokenIndex,startTokenIndex:e.startTokenIndex,endTokenIndex:e.endTokenIndex,startIndex:e.startIndex,endIndex:e.endIndex,startLine:e.startLine,endLine:e.endLine}}function N(e,t,n){let r=new Int32Array(t.endTokenIndex-t.startTokenIndex),i=new Map,a=new Map,o=0;for(let s=t.startTokenIndex;s<t.endTokenIndex;s+=1){let c=e[s];if(!c)continue;let l;if(c.kind===`id`){let e=i.get(c.text);e===void 0&&(e=i.size,i.set(c.text,e)),l=-(e+1)}else{let e=`${c.textHash}:${c.textHash2}:${c.literalHash??0}:${c.literalHash2??0}`,t=n.get(e);t===void 0&&(t=n.size,n.set(e,t)),l=t,(c.isName===!0||c.literalHash!==void 0)&&(a.set(l,(a.get(l)??0)+1),o+=1)}r[s-t.startTokenIndex]=l}return{sequence:r,contentCountBySymbol:a,contentTotal:o}}function P(e,t){let[n,r]=e.contentCountBySymbol.size<=t.contentCountBySymbol.size?[e,t]:[t,e],i=0;for(let[e,t]of n.contentCountBySymbol)i+=Math.min(t,r.contentCountBySymbol.get(e)??0);return i}function F(e){let t=new Set;for(let n=0;n+5<=e.length;n+=1){let r=5381;for(let t=0;t<5;t+=1)r=Math.imul(r,31)+(e[n+t]??0)|0;t.add(r)}return t}function I(e){let t=new Map;for(let[n,r]of e.entries())for(let e of r){let r=t.get(e);r||(r=[],t.set(e,r)),r.push(n)}let n=new Map;for(let r of t.values())for(let t=0;t<r.length;t+=1){let i=r[t]??0;for(let a=t+1;a<r.length;a+=1){let t=i*e.length+(r[a]??0);n.set(t,(n.get(t)??0)+1)}}return n}function L(e,t){let n=e.length+31>>>5,r=new Map;for(let[t,i]of e.entries()){let e=r.get(i);e||(e=new Uint32Array(n),r.set(i,e));let a=t>>>5;e[a]=(e[a]??0)|1<<(t&31)}let i=new Uint32Array(n);for(let e of t){let t=r.get(e),a=1,o=0;for(let e=0;e<n;e+=1){let n=i[e]??0,r=((t?.[e]??0)|n)>>>0,s=(n<<1|a)>>>0;a=n>>>31;let c=r-s-o;o=+(c<0),i[e]=r&~c}}let a=0;for(let e of i)a+=R(e);return a}function R(e){let t=e-(e>>>1&1431655765);return t=(t&858993459)+(t>>>2&858993459),Math.imul(t+(t>>>4)&252645135,16843009)>>>24&255}function z(e,t,n,r,i){return{fingerprint:e,tokenCount:n-t,startTokenIndex:t,endTokenIndex:n,startIndex:r.startIndex,endIndex:i.endIndex,startLine:r.startLine,endLine:i.endLine}}const B=[],V=[];function H(e){let t=B[e];return t===void 0&&(t=K(`$${e}`),B[e]=t),t}function U(e){let t=V[e];return t===void 0&&(t=q(`$${e}`),V[e]=t),t}function W(e,t,n,r){let[i,a]=G(e,n,r,f((t[r]??0)-(t[n]??0),r-n));return`${i}:${a}:${r-n}`}function ne(e,t,n){let[r,i]=G(e,t,n,!1);return r^Math.imul(i,31)}function G(e,t,n,r){let i=new Map,a=5381,o=52711;for(let s=t;s<n;s+=1){let t=e[s];if(!t)continue;let n,c;if(t.kind===`id`){let e=i.get(t.text);e===void 0&&(e=i.size,i.set(t.text,e)),n=H(e),c=U(e)}else n=t.textHash,c=t.textHash2;a=Math.imul(a,31)+n|0,o=Math.imul(o,37)^c,r&&t.literalHash!==void 0&&t.literalHash2!==void 0&&(a=Math.imul(a,31)+t.literalHash|0,o=Math.imul(o,37)^t.literalHash2)}return[a,o]}function K(e){let t=5381;for(let n=0;n<e.length;n+=1)t=Math.imul(t,33)^e.charCodeAt(n);return t}function q(e){let t=-2128831035;for(let n=0;n<e.length;n+=1)t=Math.imul(t^e.charCodeAt(n),16777619);return t}function J(e,t){return Math.imul(e,31)+t}function re(e){let t=[];for(let n of e.values()){let e=n.map(e=>({segments:[{startTokenIndex:e.startTokenIndex,endTokenIndex:e.endTokenIndex}],tokenCount:e.tokenCount,startTokenIndex:e.startTokenIndex,endTokenIndex:e.endTokenIndex,startIndex:e.startIndex,endIndex:e.endIndex,startLine:e.startLine,endLine:e.endLine}));e.sort((e,t)=>e.startTokenIndex-t.startTokenIndex||e.endTokenIndex-t.endTokenIndex),t.push(e)}return t}function Y(e,t){if(t<=0||e.length<2)return e;e.sort(X);for(let n=!0;n;){n=!1;for(let r=0;r<e.length&&!n;r+=1)for(let i=r+1;i<e.length;i+=1){let a=e[r],o=e[i];if(!a||!o)continue;let s=Z(a,o,t),c=s??Z(o,a,t);if(!c)continue;let l=s?c.firstConsumed:c.secondConsumed,u=s?c.secondConsumed:c.firstConsumed;l&&u?(e[r]=c.merged,e.splice(i,1)):u?e[i]=c.merged:e[r]=c.merged;for(let e of c.pairedRetained)e.sharedWithMergedGroup=!0;e.sort(X),n=!0;break}}return e}function X(e,t){let n=e[0],r=t[0];return(n?.startTokenIndex??0)-(r?.startTokenIndex??0)||(n?.endTokenIndex??0)-(r?.endTokenIndex??0)}function Z(e,t,n){let r=e.filter(e=>!e.sharedWithMergedGroup),i=t.filter(e=>!e.sharedWithMergedGroup),a=[],o=0,s=-1;for(let e of i){for(;o<r.length;){let t=r[o];if(t&&t.endTokenIndex+n<e.startTokenIndex)o+=1;else break}let t=r[o];t&&t.endTokenIndex<=e.startTokenIndex&&t.startTokenIndex>=s&&(a.push([t,e]),s=e.endTokenIndex,o+=1)}let c=a.length===e.length,l=a.length===t.length;if(!(a.length<2||!c&&!l))return{merged:a.map(([e,t])=>({...e,sharedWithMergedGroup:void 0,segments:[...e.segments,...t.segments],tokenCount:e.tokenCount+t.tokenCount,endTokenIndex:t.endTokenIndex,endIndex:t.endIndex,endLine:t.endLine})),firstConsumed:c,secondConsumed:l,pairedRetained:c===l?[]:a.map(([e,t])=>c?t:e)}}function Q(e){let t=0,n=0,r=!1;for(let i of e){if(i.sharedWithMergedGroup){r=!0;continue}t+=i.segments.length,n=Math.max(n,i.segments.length)}return r?t:t-n}function ie(e,t,n){let r=0,i=0,a=[],o=new Set;for(let s of e){r+=Q(s);for(let e of s){i=Math.max(i,e.tokenCount);for(let r of e.segments)$(r,n,t,o)}a.push(s.map(({startLine:e,endLine:t})=>({startLine:e,endLine:t})).toSorted((e,t)=>e.startLine-t.startLine))}return a.sort((e,t)=>(e[0]?.startLine??0)-(t[0]?.startLine??0)),{duplicateBlockCount:r,duplicateBlockGroupCount:e.length,duplicateBlockGroups:a,duplicateLineCount:o.size,duplicateLineNumbers:[...o].toSorted((e,t)=>e-t),duplicationRatio:t.size===0?0:o.size/t.size,maxDuplicateBlockSize:i}}function $(e,t,n,r){for(let i=e.startTokenIndex;i<e.endTokenIndex;i+=1){let e=t[i];for(let t=e?.startRow??0;t<=(e?.endRow??-1);t+=1)(!n||n.has(t+1))&&r.add(t+1)}}exports.buildLiteralCountPrefix=b,exports.collectCrossFileDuplicateCandidates=m,exports.collectSegmentLines=$,exports.collectSequenceWindowCandidates=w,exports.countRedundantFragments=Q,exports.defaultDuplicationOptions=d,exports.measureDuplication=p,exports.mergeAdjacentGroups=Y;
 //# sourceMappingURL=duplication.cjs.map