schema_version: 3
provider: chain
name: text-akoma-normalize
version: 0.1.0

# Capability provided by this module.
#
# Normalises heterogeneous legal-document sources (gesetze-im-internet
# XML, EUR-Lex FORMEX, landesrecht-berlin HTML) to a structured
# representation aligned with Akoma Ntoso 1.0 (OASIS LegalDocML).
#
# v0.1.0 ships the gesetze-im-internet (BMJ) XML adapter only.
# HTML and FORMEX adapters are planned for 0.2/0.3 without an
# interface break — the output schema is forward-compatible.
provides:
  - capability: text.akoma_normalize
    version: 0.1.0

inputs:
  content:
    type: bytes
    description:
      en: |
        Source bytes of one legal-document file. Supported MIME types
        in v0.1.0:
          application/xml         (gesetze-im-internet BMJ schema)
          text/xml                (alias)
        Planned for 0.2+:
          text/html               (landesrecht-berlin)
          application/x-formex+xml (EUR-Lex FORMEX-4)
      de: |
        Rohbytes einer Rechtsdokument-Datei. Unterstützte MIME-Typen
        in v0.1.0:
          application/xml          (gesetze-im-internet BMJ-Schema)
          text/xml                 (alias)
        Geplant ab 0.2:
          text/html                (landesrecht-berlin)
          application/x-formex+xml (EUR-Lex FORMEX-4)
  mime:
    type: text
    optional: true
    description:
      en: |
        Optional MIME type hint. If omitted, the module inspects
        the leading bytes to choose an adapter. Pass explicitly
        when the source content-type is known (e.g. from
        http.request's `content_type` output).
      de: |
        Optionaler MIME-Typ-Hinweis. Ohne Hinweis erkennt das Modul
        den Typ aus den Anfangsbytes. Explizit übergeben, wenn der
        Quell-Content-Type bekannt ist (z.B. aus http.request's
        Output `content_type`).

outputs:
  norm:
    type: json
    description:
      en: |
        JSON-encoded NormalizedNorm:
          {
            schema_version: "0.1",
            adapter: "gesetze-im-internet-xml",
            adapter_version: "0.1.0",
            eli: "eli/bund/<jurabk>/<paragraph>",
            jurabk: "GewO",
            paragraph: "§ 14",
            title: "Anzeigepflicht",
            paragraphs: [{ number, text }],
            source_sha256: "...",
            normalized_sha256: "...",
            akoma_xml: "<akomaNtoso>...</akomaNtoso>"   // v0.2+, omitted in 0.1
          }
        eli is synthetic in 0.1 — Germany lacks an official Bund-level
        ELI registrar. Synthesis rule documented in MODULE.md.
      de: |
        JSON-codiertes NormalizedNorm (Felder s. EN).
        eli ist in 0.1 synthetisch — Deutschland hat noch keinen offiziellen
        ELI-Registrar auf Bundesebene. Syntheseregel in MODULE.md.

# Permissions required.
#
# Pure in-WASM normalisation: quick-xml + sha2. No filesystem,
# no network. The empty list makes this explicit; the hub enforces it.
permissions: []

# MIME-type allow-list for the `content` input. Studio reads this
# through ModuleInfoResponse.accepts_mime as the OS file-picker filter.
accepts_mime:
  - application/xml
  - text/xml