{
    "$schema": "http://json-schema.org/draft-07/schema",
    "$id": "https://burrito.bible/schema/common.schema.json",
    "$$target": [
        "common.schema.json#/definitions/languageTag",
        "common.schema.json#/definitions/localizedText",
        "common.schema.json#/definitions/rodCode"
    ],
    "title": "Common Definitions",
    "description": "Common definitions for use by other parts of the schema.",
    "definitions": {
        "timestamp": {
            "type": "string",
            "pattern": "^[12][0-9]{3}(-[01][0-9](-[0123][0-9])?)?$"
        },
        "url": {
            "type": "string",
            "pattern": "^((http(s)?|ftp)://)[^\\s$]+$",
            "minLength": 1,
            "description": "A valid **Uniform Resource Locator**.",
            "examples": ["https://example.com"]
        },
        "xToken": {
            "type": "string",
            "pattern": "^x-[a-z][A-za-z0-9]*$",
            "description": "User-defined token, prefixed with x-"
        },
        "idAuthorityLabel": {
            "type": "string",
            "pattern": "^[a-z][a-z0-9\\-]*[a-z0-9]$",
            "description": "A Label for an ID authority (internal to the document)"
        },
        "bareId": {
            "type": "string",
            "pattern": "^\\S+$",
            "description": "Opaque system-specific identifier, without prefix."
        },
        "prefixedId": {
            "type": "string",
            "pattern": "^[0-9a-zA-Z][0-9a-zA-Z\\-]{1,31}::\\S+$",
            "description": "Opaque system-specific identifier, prefixed with the name of the system as declared in idAuthorities."
        },
        "revisionString": {
            "type": "string",
            "pattern": "^[0-9A-Za-z]([0-9A-Za-z_.:\\-]{0,62}[0-9A-Za-z])?$",
            "description": "Opaque system-specific revision identifier."
        },
        "languageTag": {
            "type": "string",
            "pattern": "^(((en-GB-oed|i-ami|i-bnn|i-default|i-enochian|i-hak|i-klingon|i-lux|i-mingo|i-navajo|i-pwn|i-tao|i-tay|i-tsu|sgn-BE-FR|sgn-BE-NL|sgn-CH-DE)|(art-lojban|cel-gaulish|no-bok|no-nyn|zh-guoyu|zh-hakka|zh-min|zh-min-nan|zh-xiang))|((([A-Za-z]{2,3}(-([A-Za-z]{3}(-[A-Za-z]{3}){0,2}))?)|[A-Za-z]{4}|[A-Za-z]{5,8})(-([A-Za-z]{4}))?(-([A-Za-z]{2}|[0-9]{3}))?(-([A-Za-z0-9]{5,8}|[0-9][A-Za-z0-9]{3}))*(-([0-9A-WY-Za-wy-z](-[A-Za-z0-9]{2,8})+))*(-(x(-[A-Za-z0-9]{1,8})+))?)|(x(-[A-Za-z0-9]{1,8})+))$",
            "minLength": 2,
            "description": "A valid IETF language tag as specified by BCP 47."
        },
        "countryCode": {
            "type": "string",
            "pattern": "^[A-Z][A-Z]$",
            "minLength": 2,
            "maxLength": 2,
            "description": "The upper-case ISO 3166-2 code for the country."
        },
        "rodCode": {
            "type": "string",
            "pattern": "^[0-9]{5}$",
            "minLength": 5,
            "maxLength": 5,
            "description": "A five-digit code from the Registry of Dialects."
        },
        "trimmedText": {
            "type": "string",
            "pattern": "^\\S(.*\\S)?$",
            "description": "A string without surrounding whitespace characters."
        },
        "localizedText": {
            "type": "object",
            "additionalProperties": {
                "$ref": "#/definitions/trimmedText"
            },
            "propertyNames": {
                "$ref": "#/definitions/languageTag"
            },
            "minProperties": 1,
            "description": "A textual string specified in one or multiple languages, indexed by IETF language tag."
        },
        "simplifiedXHTML": {
            "type": "string",
            "contentMediaType": "text/xml",
            "minLength": 4,
            "allOf": [
                {
                    "$comment": "Check top-level block elements. This is imperfect and is liable to skip over tags if a <li> or nested <blockquote> is present, but fully validating XML using RegEx is impossible, and this suffices for the common case of simple formatted text.",
                    "pattern": "^((<(p|h1|h2|h3)\\s*/>|<p\\s*>([^<]|<[^p])*</p\\s*>|<h1\\s*>([^<]|<[^h])*</h1\\s*>|<h2\\s*>([^<]|<[^h])*</h2\\s*>|<h3\\s*>([^<]|<[^h])*</h3\\s*>|<ol\\s*>\\s*((<li\\s*/>|<li\\s*>.*</li\\s*>)\\s*)+</ol\\s*>|<ul\\s*>\\s*((<li\\s*/>|<li\\s*>.*</li\\s*>)\\s*)+</ul\\s*>|<blockquote\\s*>(<(p|h1|h2|h3)\\s*/>|<(p|h[123])\\s*>([^<]|<[^ph])*</(p|h[123])\\s*>|<ol\\s*>(<li\\s*/>|<li\\s*>.*</li\\s*>)+</ol\\s*>|<ul\\s*>(<li\\s*/>|<li\\s*>.*</li\\s*>)+</ul\\s*>|<blockquote\\s*>.+</blockquote\\s*>)+</blockquote\\s*>)\\s*)+$"
                },
                {
                    "$comment": "Ensure that no invalid tags are present, check inline markup in <p> and <h#> (noting that <li> may contain pretty much anything), and prevent improper nesting of <li> tags.",
                    "pattern": "^([^<]|<(p|h[123]|a|br|strong|b|em|i)\\s*/>|</?(a|br|strong|b|em|i|blockquote)\\s*>|<(p|h[123])\\s*>([^<]|<img(\\s+(alt|src)=(\"[^<\"]*\"|'[^<']*'))+\\s*(/>|>\\s*</img\\s*>)|<a\\s+href=(\"[^<\"]+\"|'[^<']+')\\s*/?>|</?(a|br|strong|b|em|i)\\s*/?>)*</(p|h[123])\\s*>|<[ou]l\\s*>(\\s|<li\\s*/>)*<li\\s*/?>|</li\\s*>(\\s|<li\\s*/>)*(<li\\s*>|</[ou]l\\s*>))+$"
                }
            ],
            "description": "A rich text string specified in a limited subset of XHTML."
        },
        "localizedRichText": {
            "type": "object",
            "additionalProperties": {
                "$ref": "#/definitions/simplifiedXHTML"
            },
            "propertyNames": {
                "$ref": "#/definitions/languageTag"
            },
            "minProperties": 1,
            "description": "A simplified XHTML string specified in one or multiple languages, indexed by IETF language tag."
        },
        "bookId": {
            "type": "string",
            "pattern": "^[A-Z0-9]{3}$",
            "minLength": 3,
            "maxLength": 3,
            "enum": [
                "GEN",
                "EXO",
                "LEV",
                "NUM",
                "DEU",
                "JOS",
                "JDG",
                "RUT",
                "1SA",
                "2SA",
                "1KI",
                "2KI",
                "1CH",
                "2CH",
                "EZR",
                "NEH",
                "EST",
                "JOB",
                "PSA",
                "PRO",
                "ECC",
                "SNG",
                "ISA",
                "JER",
                "LAM",
                "EZK",
                "DAN",
                "HOS",
                "JOL",
                "AMO",
                "OBA",
                "JON",
                "MIC",
                "NAM",
                "HAB",
                "ZEP",
                "HAG",
                "ZEC",
                "MAL",
                "MAT",
                "MRK",
                "LUK",
                "JHN",
                "ACT",
                "ROM",
                "1CO",
                "2CO",
                "GAL",
                "EPH",
                "PHP",
                "COL",
                "1TH",
                "2TH",
                "1TI",
                "2TI",
                "TIT",
                "PHM",
                "HEB",
                "JAS",
                "1PE",
                "2PE",
                "1JN",
                "2JN",
                "3JN",
                "JUD",
                "REV",
                "TOB",
                "JDT",
                "ESG",
                "WIS",
                "SIR",
                "BAR",
                "LJE",
                "S3Y",
                "SUS",
                "BEL",
                "1MA",
                "2MA",
                "3MA",
                "4MA",
                "1ES",
                "2ES",
                "MAN",
                "PS2",
                "ODA",
                "PSS",
                "JSA",
                "JDB",
                "TBS",
                "SST",
                "DNT",
                "BLT",
                "EZA",
                "5EZ",
                "6EZ",
                "DAG",
                "PS3",
                "2BA",
                "LBA",
                "JUB",
                "ENO",
                "1MQ",
                "2MQ",
                "3MQ",
                "REP",
                "4BA",
                "LAO"
            ],
            "description": "A USFM book code consisting of three uppercase alphanumerics."
        },
        "path": {
            "type": "string",
            "pattern": "^[^\\/:?*\"><|]+(/[^\\/:?*\"><|]+)*$",
            "description": "A file path, delimited by forward slashes."
        },
        "mimeType": {
            "type": "string",
            "pattern": "^[\\-a-z0-9]+/[\\-a-z0-9+]+$",
            "description": "An IANA media type (also known as MIME type)"
        }
    }
}