issue.schema.json

{
    "$schema": "http://json-schema.org/draft-06/schema#",
    "$id": "https://impresso.github.io/impresso-schemas/json/newspaper/issue.schema.json",
    "description": "Logical representation of the contents of a newspaper issue.",
    "title": "Newspaper Issue",
    "type": "object",
    "properties": {
        "id": {
            "type": "string",
            "description": "Canonical ID of the newspaper issue (e.g. GDL-1900-01-02-a)"
        },
        "cdt": {
            "type": "string",
            "description": "Creation date timestamp (of the JSON file)."
        },
        "i": {
            "type": "array",
            "items": {
                "type": "object",
                "description": "A content item (e.g. article, advertisement, etc.)",
                "properties": {
                    "m": {
                        "description": "Metadata about the content item.",
                        "$ref": "#/definitions/metadata"
                    },
                    "c": {
                        "type": "array",
                        "description": "Coordinates of image-region corresponding to the content-item depending on its type (if `tp == image`).",
                        "minItems":4,
                        "items": {
                            "type": "integer"
                        }
                    }
                },
                "required": ["m"]
            },
            "description": "The content items contained in the newspaper issue."
        },
        "s": {
            "description": "The text style as defined in the OCR output. \nEach style consists of:\n - a name (`id`)\n - a type-face (`f`)\n - a font-size (`fs`)\n - a color (`rgb`).",
            "type": "array",
            "items": {
                "type": "object",
                "properties": {
                    "rgb": {
                        "type": "array",
                        "description": "Color of the text (in RGB).",
                        "items": {
                            "type": "integer"
                        },
                        "minItems": 3
                    },
                    "f": {
                        "type": "string",
                        "description": "Font name"
                    },
                    "fs": {
                        "type": "number",
                        "description": "Font size"
                    },
                    "id": {
                        "type": "integer",
                        "description": "Local ID of the style"
                    }
                },
                "required": ["id"]
            }
        },
        "pp": {
            "type": "array",
            "description": "Canonical IDs of pages in the issue, without file extension (e.g. GDL-1900-01-02-a-p0004).",
            "items": {
                "type": "string"
            }
        },
        "n": {
          "type": "string",
          "description": "Notes."
        },
        "ar": {
          "type": "string",
          "description": "Access rights. Three possible situations are defined:\n1. open public: access without NDA, user could redistribute (as defined per Terms of Use)\n2. open private: access without an NDA, user cannot redistribute (private/academic use only)\n3. closed : accessible only upon signing an NDA, user cannot redistribute",
          "enum": ["open_public", "open_private", "closed"]
        }, 
        "iiif_manifest_uri": {
            "type": "string",
            "description": "URI for the issue's manifest in the IIIF Presentation API, if the corresponding IIIF server has one."
        }
    },
    "required": ["id", "cdt", "i", "pp", "ar"],
    "definitions":{
        "metadata": {
            "type":"object",
            "properties": {
                "id": {
                    "type": "string",
                    "description": "Content item ID (e.g. `GDL-1900-01-02-a-i0001`)."
                },
                "l": {
                    "type": "string",
                    "description": "Language of the content item."
                },
                "pp": {
                    "type": "array",
                    "items": {
                        "type": "integer"
                    },
                    "description": "Page numbers over which the content item spans."
                },
                "t": {
                    "type": "string",
                    "description": "Title of the content item."
                },
                "tp": {
                    "type": "string",
                    "description": "Type of the content item.",
                    "enum": ["article", "ad", "image", "table", "death_notice", "weather", "page"]
                },
                "iiif_link": {
                  "type": "string",
                  "description": "IIIF image link, depending on content item type (if `tp == image`). Should follow the format: '{scheme}://{server}/{prefix}/{identifier}/info.json'."
                },
                "ro": {
                    "type": "integer",
                    "description": "Reading order index of the content item, for the table of contents view on the interface. If not defined, the CI number (after 'i' in the ID) should be used."
                }
            },
            "required": ["id","pp", "tp"]
        }
    }
}