# 0pt data engine — sources registry (docs/06). Drives the router, /sources API,
# and the public sourcing-map. access: api | bulk | authorized_web | licensed.
# VERIFY current access/licence/robots per source before relying — terms change.
sources:
  - source_id: gleif
    name: GLEIF (LEI)
    market: global
    access: api
    cadence: daily
    licence: "open (CC0) — VERIFY"
    entities: [company]
    fields: [lei, legal_name, address, status]
    base_url: https://api.gleif.org
    robots_ok: true
    notes: "cross-border key"

  - source_id: brreg
    name: Brønnøysundregistrene (Enhetsregisteret)
    market: NO
    access: api
    cadence: daily
    licence: "NLOD open — VERIFY"
    entities: [company]
    fields: [name, status, address, nace]
    base_url: https://data.brreg.no
    robots_ok: true
    notes: "open API + bulk download"

  - source_id: companies_house
    name: Companies House
    market: GB
    access: api
    cadence: daily
    licence: "free, API key required — VERIFY"
    entities: [company, officers, financials]
    fields: [name, status, address, officers]
    base_url: https://api.company-information.service.gov.uk
    robots_ok: true
    notes: "key via env COMPANIES_HOUSE_API_KEY"

  - source_id: prh
    name: PRH avoindata (Trade Register)
    market: FI
    access: api
    cadence: daily
    licence: "CC-BY — VERIFY"
    entities: [company]
    fields: [name, status]
    base_url: https://avoindata.prh.fi
    robots_ok: true
    notes: "connector pending verification"

  - source_id: cvr
    name: CVR / Virk
    market: DK
    access: api
    cadence: daily
    licence: "terms apply (Virk) — VERIFY"
    entities: [company]
    fields: [name, status]
    base_url: https://datacvr.virk.dk
    robots_ok: true
    notes: "connector pending verification"

  - source_id: bolagsverket
    name: Bolagsverket
    market: SE
    access: licensed
    cadence: daily
    licence: "restricted for bulk — partner/licensed route"
    entities: [company]
    fields: [name, status]
    base_url: https://bolagsverket.se
    robots_ok: true
    notes: "no bulk scrape; licensed/partner only"

  - source_id: rdw
    name: RDW open vehicle data
    market: NL
    access: bulk
    cadence: daily
    licence: "open — VERIFY"
    entities: [vehicle]
    fields: [make, model, year, specs]
    base_url: https://opendata.rdw.nl
    robots_ok: true
    notes: "technical/fleet vehicle data, not owner PII"

  - source_id: opensanctions
    name: OpenSanctions
    market: global
    access: bulk
    cadence: daily
    licence: "open — VERIFY commercial terms"
    entities: [company, person]
    fields: [sanction, pep]
    base_url: https://www.opensanctions.org
    robots_ok: true
    notes: "screening/diligence enrichment"