Function generateQuestions

benchmarks/src/questions/index.ts:27–55

()

 *   Examples: "How many records?", "List the field names", "What is the last record's field?"
 */
export function generateQuestions(): Question[] {
  const questions: Question[] = []
  const idGen = createIdGenerator()
  const getId = () => idGen.next().value

  // Get datasets with proper typing
  const tabular = (ACCURACY_DATASETS.find(d => d.name === 'tabular')?.data.employees as Employee[]) ?? []
  const nested = (ACCURACY_DATASETS.find(d => d.name === 'nested')?.data.orders as Order[]) ?? []
  const analytics = (ACCURACY_DATASETS.find(d => d.name === 'analytics')?.data.metrics as AnalyticsMetric[]) ?? []
  const github = (ACCURACY_DATASETS.find(d => d.name === 'github')?.data.repositories as Repository[]) ?? []
  const eventLogs = (ACCURACY_DATASETS.find(d => d.name === 'event-logs')?.data.logs as EventLog[]) ?? []
  const nestedConfig = ACCURACY_DATASETS.find(d => d.name === 'nested-config')?.data as NestedConfig | undefined

  // Generate questions for each dataset
  questions.push(...generateTabularQuestions(tabular, getId))
  questions.push(...generateNestedQuestions(nested, getId))
  questions.push(...generateAnalyticsQuestions(analytics, getId))
  questions.push(...generateGithubQuestions(github, getId))
  questions.push(...generateEventLogsQuestions(eventLogs, getId))
  questions.push(...generateNestedConfigQuestions(nestedConfig, getId))

  // Generate structure-awareness questions (tests format-native affordances)
  questions.push(...generateStructureQuestions(tabular, nested, analytics, github, eventLogs, getId))

  // Generate structural-validation questions (tests ability to detect corrupted data)
  questions.push(...generateStructuralValidationQuestions(getId))

  return questions
}