Språkbanken Text resource (corpus / lexicon / model / analysis / utility)

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://raw.githubusercontent.com/api-evangelist/university-of-gothenburg/main/json-schema/university-of-gothenburg-sbx-resource.json",
  "title": "Språkbanken Text resource (corpus / lexicon / model / analysis / utility)",
  "description": "The record shape returned by the Språkbanken Text Metadata API v3 for every catalogued resource. DERIVED on 2026-09-01 from the live response to GET https://ws.spraakbanken.gu.se/ws/metadata/v3/ (HTTP 200, 2,531,491 bytes, 1,499 resource ids), cross-checked against the published OpenAPI at openapi/_original/university-of-gothenburg-metadata-api-openapi.json. Field presence and types are observed, not assumed; only fields present on every sampled record are marked required.",
  "x-provenance": {
    "generated": "2026-09-01",
    "method": "derived",
    "source": "GET https://ws.spraakbanken.gu.se/ws/metadata/v3/ — HTTP 200, 2026-09-01. Sample stored at examples/university-of-gothenburg-metadata-list-ids-example.json.",
    "x-operator": "institution"
  },
  "type": "object",
  "required": ["id", "name", "type"],
  "properties": {
    "id": { "type": "string", "description": "Stable lower-case resource id, e.g. \"abotidning\". The value returned by /list-ids." },
    "type": { "type": "string", "enum": ["corpus", "lexicon", "model", "analysis", "utility", "collection"] },
    "name": { "$ref": "#/$defs/localizedString" },
    "short_description": { "$ref": "#/$defs/localizedString" },
    "has_description": { "type": "boolean" },
    "doi": { "type": "string", "description": "DataCite DOI. Språkbanken Text mints under prefix 10.23695 as DataCite client snd.sprkb." },
    "updated": { "type": "string", "format": "date" },
    "origin": { "type": "string", "description": "Originating unit, e.g. \"sbx\" for Språkbanken Text." },
    "unlisted": { "type": "boolean" },
    "trainingdata": { "type": "boolean" },
    "size": {
      "type": "object",
      "description": "Counts vary by resource type; corpora report tokens and sentences.",
      "additionalProperties": { "type": ["integer", "string"] }
    },
    "languages": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "code": { "type": "string", "description": "ISO 639-3 language code." },
          "name": { "$ref": "#/$defs/localizedString" }
        }
      }
    },
    "in_collections": { "type": "array", "items": { "type": "string" } },
    "successors": { "type": "array", "items": { "type": "string" } },
    "downloads": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "url": { "type": "string", "format": "uri" },
          "type": { "type": "string" },
          "format": { "type": "string" },
          "size": { "type": ["integer", "string"] },
          "licence": { "type": "string" }
        }
      }
    },
    "interfaces": {
      "type": "array",
      "description": "Where the resource can be used interactively — typically a Korp or Karp deep link on a gu.se host.",
      "items": {
        "type": "object",
        "properties": {
          "access": { "type": "string", "format": "uri" },
          "licence": { "type": "string" }
        }
      }
    },
    "contact_info": {
      "type": "object",
      "properties": {
        "name": { "type": "string" },
        "email": { "type": "string", "format": "email" },
        "affiliation": { "type": "object" }
      }
    },
    "other_references": { "type": "array", "items": { "type": "string" } }
  },
  "$defs": {
    "localizedString": {
      "type": "object",
      "description": "Every human-readable string in this API is a language map. Swedish is always present; English usually is. A consumer that expects a bare string will break.",
      "properties": {
        "swe": { "type": "string" },
        "eng": { "type": "string" }
      },
      "additionalProperties": { "type": "string" }
    }
  }
}