tech.transparencia.document.mxdof.note

{
  "key": "any",
  "type": "record",
  "record": {
    "type": "object",
    "required": [
      "item",
      "codNota",
      "codDiario",
      "edition",
      "createdAt"
    ],
    "properties": {
      "item": {
        "ref": "com.atproto.repo.strongRef",
        "type": "ref",
        "description": "Strong reference to the tech.transparencia.document.item record that holds the universal document metadata (title, retrieval URLs, publisher, dates, jurisdiction)."
      },
      "page": {
        "type": "integer",
        "minimum": 1,
        "description": "First printed page number within the parent diario PDF when available."
      },
      "order": {
        "type": "string",
        "maxLength": 32,
        "description": "Ordering value from the SIDOF feed used to preserve sequence inside the diario/section. Encoded as a decimal string because AT Protocol does not support floats."
      },
      "hasDoc": {
        "type": "boolean",
        "description": "Whether SIDOF reports an attached document artifact beyond HTML/PDF (existeDoc = 'S')."
      },
      "hasPdf": {
        "type": "boolean",
        "description": "Whether SIDOF reports PDF availability for the nota or its enclosing diario (existePdf = 'S')."
      },
      "codNota": {
        "type": "integer",
        "minimum": 1,
        "description": "Primary DOF nota identifier from SIDOF. UNIQUE across all DOF notas. This is the key external identifier for deduplication and for constructing public DOF URLs."
      },
      "edition": {
        "type": "string",
        "maxLength": 32,
        "description": "Edition label for the parent diario. Lowercased token form (the SIDOF API returns capitalized labels; pipelines should normalize on write).",
        "knownValues": [
          "matutina",
          "vespertina",
          "extraordinaria"
        ]
      },
      "hasHtml": {
        "type": "boolean",
        "description": "Whether SIDOF reports an HTML content page for this nota (existeHtml = 'S')."
      },
      "hasImage": {
        "type": "boolean",
        "description": "Whether SIDOF reports image attachments (existeImagen = 'S')."
      },
      "tipoNota": {
        "type": "string",
        "maxLength": 128,
        "description": "Raw tipo_nota from the SIDOF feed when available. Common examples include 'AVISO', but many high-signal normative records arrive with null tipo_nota (the actual document class is then derived by the enrichment layer's tipoActo field).",
        "maxGraphemes": 64
      },
      "codDiario": {
        "type": "integer",
        "minimum": 1,
        "description": "SIDOF identifier for the parent diario (gazette edition). Groups all notas published together in the same daily edition (matutina, vespertina, or extraordinaria)."
      },
      "createdAt": {
        "type": "string",
        "format": "datetime",
        "description": "When this AT Protocol record was created."
      },
      "organismo": {
        "type": "string",
        "maxLength": 512,
        "description": "More specific issuing body from SIDOF (codOrgaDos). Examples: 'SECRETARIA DE ENERGIA', 'INSTITUTO NACIONAL ELECTORAL', 'SUPREMA CORTE DE JUSTICIA DE LA NACION'.",
        "maxGraphemes": 128
      },
      "pageUntil": {
        "type": "integer",
        "minimum": 1,
        "description": "Last printed page number when the nota spans multiple pages."
      },
      "updatedAt": {
        "type": "string",
        "format": "datetime",
        "description": "When this record was last materially updated."
      },
      "codSeccion": {
        "type": "string",
        "maxLength": 128,
        "description": "Section code within the diario as published by SIDOF (e.g., 'PRIMERA', 'SEGUNDA', 'UNICA', 'AVISOS JUDICIALES', 'LICITACIONES'). Free-form; conventions vary by edition.",
        "maxGraphemes": 64
      },
      "dependencia": {
        "type": "string",
        "maxLength": 512,
        "description": "Top-level authority label from SIDOF (nombreCodOrgaUno). Examples: 'PODER EJECUTIVO', 'ORGANISMOS AUTONOMOS', 'AVISOS JUDICIALES Y GENERALES', 'PROCURACIONES'. Kept verbatim from source for provenance; the document.item.issuingBodies array carries the structured form.",
        "maxGraphemes": 128
      },
      "documentClass": {
        "type": "string",
        "maxLength": 64,
        "description": "Broad publication family. Optional at the raw-record level because for many notas it can only be determined from content (and is then mirrored in tech.transparencia.document.mxdof.note.enrichment.documentClass).",
        "knownValues": [
          "normative",
          "judicial",
          "procurement",
          "intergovernmental",
          "planning",
          "administrative",
          "informational",
          "other"
        ]
      },
      "rawImportedAt": {
        "type": "string",
        "format": "datetime",
        "description": "When the raw SIDOF payload was first ingested by the pipeline."
      },
      "authorityLevel": {
        "type": "string",
        "maxLength": 64,
        "description": "Normalized authority tier derived from dependencia/organismo. Useful for analytics without replacing the raw text fields. Open set; pipelines should add new tiers as edge cases appear.",
        "knownValues": [
          "federal_executive",
          "federal_judicial",
          "federal_legislative",
          "autonomous_constitutional_body",
          "state_judicial",
          "state_executive",
          "state_legislative",
          "municipal",
          "state_owned_enterprise",
          "decentralized_body",
          "procurement_section",
          "judicial_notices_section",
          "other"
        ]
      },
      "pdfStoragePath": {
        "type": "string",
        "maxLength": 1024,
        "description": "Internal storage path for the diario PDF when retained in object storage (e.g., 'YYYY/MM/DD/diario_{codDiario}.pdf'). Not a public URL — for analytics provenance only.",
        "maxGraphemes": 256
      },
      "issuingAuthority": {
        "type": "string",
        "maxLength": 512,
        "description": "Normalized human-readable issuer name when the pipeline produces one (e.g., 'Secretaría de Salud' instead of raw 'SECRETARIA DE SALUD'). Optional — many notas only expose dependencia-level information.",
        "maxGraphemes": 128
      },
      "contentTextAvailable": {
        "type": "boolean",
        "description": "Whether normalized plain text was successfully captured by the ingestion pipeline (separate from whether the source published HTML/PDF; reflects what we actually extracted)."
      }
    }
  },
  "description": "Gazette-specific metadata for a single DOF nota. Strong-references the universal document.item record that carries title, retrieval, publisher, and dates. This sidecar only carries fields that wouldn't make sense outside the DOF context (SIDOF codes, matutina/vespertina edition, dependencia/organismo hierarchy, page/order within the diario PDF)."
}