breakpilot-compliance/admin-compliance/__tests__/ingest-industry-compliance.test.ts

import { describe, it, expect } from 'vitest'
import { readFileSync } from 'fs'
import { resolve } from 'path'

/**
 * Tests for the ingestion script ingest-industry-compliance.sh
 * Validates script structure, URLs, metadata, and configuration.
 */

const SCRIPT_PATH = resolve(__dirname, '../../scripts/ingest-industry-compliance.sh')
let scriptContent: string

try {
  scriptContent = readFileSync(SCRIPT_PATH, 'utf-8')
} catch {
  scriptContent = ''
}

describe('Ingestion Script: ingest-industry-compliance.sh', () => {
  it('should exist and be non-empty', () => {
    expect(scriptContent.length).toBeGreaterThan(0)
  })

  describe('download_pdf function', () => {
    it('should define download_pdf function', () => {
      expect(scriptContent).toContain('download_pdf()')
    })

    it('should use User-Agent header for downloads', () => {
      expect(scriptContent).toContain('Mozilla/5.0')
    })

    it('should follow redirects with -L flag', () => {
      expect(scriptContent).toMatch(/curl.*-L/)
    })

    it('should skip already downloaded files', () => {
      expect(scriptContent).toContain('-f "$target"')
    })
  })

  describe('upload_file function', () => {
    it('should define upload_file function', () => {
      expect(scriptContent).toContain('upload_file()')
    })

    it('should use recursive chunk strategy', () => {
      expect(scriptContent).toContain('chunk_strategy=recursive')
    })

    it('should use chunk_size=512', () => {
      expect(scriptContent).toContain('chunk_size=512')
    })

    it('should use chunk_overlap=50', () => {
      expect(scriptContent).toContain('chunk_overlap=50')
    })

    it('should validate minimum file size', () => {
      expect(scriptContent).toContain('"$filesize" -lt 100')
    })
  })

  describe('IFRS Downloads', () => {
    it('should download IFRS DE from EUR-Lex', () => {
      expect(scriptContent).toContain(
        'https://eur-lex.europa.eu/legal-content/DE/TXT/PDF/?uri=CELEX:32023R1803'
      )
    })

    it('should download IFRS EN from EUR-Lex', () => {
      expect(scriptContent).toContain(
        'https://eur-lex.europa.eu/legal-content/EN/TXT/PDF/?uri=CELEX:32023R1803'
      )
    })

    it('should save IFRS DE with correct filename', () => {
      expect(scriptContent).toContain('ifrs_regulation_2023_1803_de.pdf')
    })

    it('should save IFRS EN with correct filename', () => {
      expect(scriptContent).toContain('ifrs_regulation_2023_1803_en.pdf')
    })
  })

  describe('EFRAG Download', () => {
    it('should download EFRAG Endorsement Status Report', () => {
      expect(scriptContent).toContain('efrag.org')
    })

    it('should save as efrag_endorsement_status_2025.pdf', () => {
      expect(scriptContent).toContain('efrag_endorsement_status_2025.pdf')
    })
  })

  describe('ENISA Downloads', () => {
    it('should download ENISA from new URL pattern', () => {
      expect(scriptContent).toContain('enisa.europa.eu/sites/default/files/publications')
    })

    it('should NOT use old Plone-style URLs', () => {
      expect(scriptContent).not.toContain('@@download/fullReport')
    })
  })

  describe('IFRS Metadata', () => {
    it('should include CELEX number 32023R1803', () => {
      expect(scriptContent).toContain('"celex":"32023R1803"')
    })

    it('should tag as regulation_short EU_IFRS', () => {
      expect(scriptContent).toContain('"regulation_short":"EU_IFRS"')
    })

    it('should set category to rechnungslegung', () => {
      expect(scriptContent).toContain('"category":"rechnungslegung"')
    })

    it('should include endorsement note', () => {
      expect(scriptContent).toContain('EU-endorsed IFRS')
    })

    it('should set license to public_law', () => {
      expect(scriptContent).toContain('"license":"public_law"')
    })
  })

  describe('EFRAG Metadata', () => {
    it('should set source_id to efrag', () => {
      expect(scriptContent).toContain('"source_id":"efrag"')
    })

    it('should include EFRAG attribution', () => {
      expect(scriptContent).toContain('European Financial Reporting Advisory Group')
    })
  })

  describe('Target Collections', () => {
    it('should reference bp_compliance_ce', () => {
      expect(scriptContent).toContain('bp_compliance_ce')
    })

    it('should reference bp_compliance_datenschutz', () => {
      expect(scriptContent).toContain('bp_compliance_datenschutz')
    })
  })

  describe('Verification Phase', () => {
    it('should have a phase_verify function', () => {
      expect(scriptContent).toContain('phase_verify')
    })

    it('should test search for IFRS', () => {
      expect(scriptContent).toContain('IFRS Rechnungslegung EU endorsed')
    })

    it('should test search for EFRAG', () => {
      expect(scriptContent).toContain('EFRAG endorsement status')
    })
  })

  describe('Curl Configuration', () => {
    it('should set max-time to 600 seconds', () => {
      expect(scriptContent).toContain('--max-time 600')
    })
  })
})