From 8116f74b8756cbe39f3c41b16502457d32802f49 Mon Sep 17 00:00:00 2001 From: Jason Desrosiers Date: Sun, 30 Jul 2023 19:59:22 -0700 Subject: [PATCH] Use custom toc and heading-links remark plugins --- .eslintrc => .eslintrc.json | 1 + README.md | 37 +- build/build.js | 37 +- build/remark-headings.js | 97 ++++ build/remark-number-headings.js | 47 -- build/remark-reference-links.js | 21 + build/remark-section-links.js | 43 -- build/remark-table-of-contents.js | 65 +++ jsonschema-core.md | 713 ++++++++++++++++++------------ jsonschema-validation.md | 281 +++++++----- package.json | 8 +- 11 files changed, 828 insertions(+), 522 deletions(-) rename .eslintrc => .eslintrc.json (94%) create mode 100644 build/remark-headings.js delete mode 100644 build/remark-number-headings.js create mode 100644 build/remark-reference-links.js delete mode 100644 build/remark-section-links.js create mode 100644 build/remark-table-of-contents.js diff --git a/.eslintrc b/.eslintrc.json similarity index 94% rename from .eslintrc rename to .eslintrc.json index 5b6c9f31..585b9d92 100644 --- a/.eslintrc +++ b/.eslintrc.json @@ -22,6 +22,7 @@ "generator-star-spacing": ["error", { "before": false, "after": true }], "indent": ["error", 2, { "ignoreComments": true, "SwitchCase": 1 }], "linebreak-style": "error", + "no-console": ["error", { "allow": ["error"] }], "no-trailing-spaces": "error", "no-unused-vars": ["error", { "argsIgnorePattern": "_.*" }], "prefer-const": ["error", { "destructuring": "all" }], diff --git a/README.md b/README.md index c8e013e7..f74eec02 100644 --- a/README.md +++ b/README.md @@ -43,19 +43,38 @@ features they make available to you. - [remark-gfm](https://github.com/remarkjs/remark-gfm) -- Adds support for Github Flavored Markdown specific markdown features such as autolink literals, footnotes, strikethrough, tables, and tasklists. -- [remark-number-headings](/json-schema-org/json-schema-spec/blob/main/remark-number-headings.js) - -- Adds hierarchical section numbers to headings. -- [remark-toc](https://github.com/remarkjs/remark-toc) -- Adds a table of - contents in a section with a header called "Table of Contents". +- [remark-heading-id](https://github.com/imcuttle/remark-heading-id) -- Adds + support for `{#my-anchor}` syntax to add an `id` to an element so it can be + referenced using URI fragment syntax. +- [remark-headings](/json-schema-org/json-schema-spec/blob/main/remark-headings.js) + -- A collection of enhancements for headings. + - Adds hierarchical section numbers to headings. + - Use the `[Appendix]` prefix on headings that should be numbered as an + appendix. + - Adds id anchors to headers that don't have one + - Example: `#section-2-13` + - Example: `#appendix-a` + - Makes the heading a link utilizing its anchor +- [remark-reference-links](/json-schema-org/json-schema-spec/blob/main/remark-reference-link.js) + -- Adds new syntax for referencing a section of the spec using the section + number as the link text. + - Example: + ```markdown + ## Foo {#foo} + + ## Bar + This is covered in {{foo}} // --> Renders to "This is covered in [Section + 2.3](#foo)" + - Link text will use "Section" or "Appendix" as needed + ``` +- [remark-table-of-contents](/json-schema-org/json-schema-spec/blob/main/remark-table-of-contents.js) + -- Adds a table of contents in a section with a header called "Table of + Contents". - [remark-torchlight](https://github.com/torchlight-api/remark-torchlight) -- Syntax highlighting and more using https://torchlight.dev. Features include line numbers and line highlighting. -- [rehype-slug](https://github.com/rehypejs/rehype-slug) -- Adds `id` anchors to - header so they can be linked to with URI fragment syntax. -- [rehype-autolink-headings](https://github.com/rehypejs/rehype-autolink-headings) - -- Makes headings clickable. - [remark-flexible-containers](https://github.com/ipikuka/remark-flexible-containers) - -- Add a callout box using the following syntax. Supported container types are + - Add a callout box using the following syntax. Supported container types are `warning`, `note`, and `experimental`. ``` diff --git a/build/build.js b/build/build.js index ddc39d7c..6fce20ab 100644 --- a/build/build.js +++ b/build/build.js @@ -2,20 +2,17 @@ import dotenv from "dotenv"; import { readFileSync, writeFileSync } from "node:fs"; import { reporter } from "vfile-reporter"; import { remark } from "remark"; -import rehypeAutolinkHeadings from "rehype-autolink-headings"; -import rehypeSlug from "rehype-slug"; -import rehypeStringify from "rehype-stringify"; import remarkFlexibleContainers from "remark-flexible-containers"; import remarkGfm from "remark-gfm"; import remarkHeadingId from "remark-heading-id"; -import remarkHeadings from "@vcarl/remark-headings"; -import remarkNumberHeadings from "./remark-number-headings.js"; +import remarkHeadings from "./remark-headings.js"; import remarkPresetLintMarkdownStyleGuide from "remark-preset-lint-markdown-style-guide"; import remarkRehype from "remark-rehype"; -import remarkSectionLinks from "./remark-section-links.js"; -import remarkToc from "remark-toc"; +import remarkReferenceLinks from "./remark-reference-links.js"; +import remarkTableOfContents from "./remark-table-of-contents.js"; +import remarkTorchLight from "remark-torchlight"; import remarkValidateLinks from "remark-validate-links"; -import torchLight from "remark-torchlight"; +import rehypeStringify from "rehype-stringify"; dotenv.config(); @@ -25,26 +22,20 @@ dotenv.config(); const html = await remark() .use(remarkPresetLintMarkdownStyleGuide) .use(remarkGfm) - .use(torchLight) - .use(remarkFlexibleContainers) .use(remarkHeadingId) - .use(remarkNumberHeadings, { + .use(remarkHeadings, { startDepth: 2, - skip: ["Abstract", "Note to Readers", "Table of Contents", "Authors' Addresses", "\\[.*\\]", "draft-.*"], - appendixToken: "[Appendix]", - appendixPrefix: "Appendix" + skip: ["Abstract", "Note to Readers", "Table of Contents", "Authors' Addresses", "\\[.*\\]", "draft-.*"] }) - .use(remarkHeadings) - .use(remarkSectionLinks) - .use(remarkToc, { - tight: true, - heading: "Table of Contents", - skip: "\\[.*\\]|draft-.*" + .use(remarkReferenceLinks) + .use(remarkFlexibleContainers) + .use(remarkTorchLight) + .use(remarkTableOfContents, { + startDepth: 2, + skip: ["Abstract", "Note to Readers", "\\[.*\\]", "Authors' Addresses", "draft-.*"] }) .use(remarkValidateLinks) .use(remarkRehype) - .use(rehypeSlug) - .use(rehypeAutolinkHeadings, { behavior: "wrap" }) .use(rehypeStringify) .process(md); @@ -122,7 +113,7 @@ dotenv.config(); - ${String(html)} + ${html.toString()} `); diff --git a/build/remark-headings.js b/build/remark-headings.js new file mode 100644 index 00000000..6cecefcd --- /dev/null +++ b/build/remark-headings.js @@ -0,0 +1,97 @@ +import { visit } from "unist-util-visit"; +import { link, text } from "mdast-builder"; +import { findAndReplace } from "mdast-util-find-and-replace"; +import { toString as nodeToString } from "mdast-util-to-string"; + + +const defaultOptions = { + startDepth: 1, + skip: [], + appendixToken: "[Appendix]", + appendixPrefix: "Appendix" +}; + +const remarkNumberHeadings = (options) => (tree, file) => { + options = { ...defaultOptions, ...options }; + options.skip = new RegExp(`^(${options.skip.join("|")})$`, "u"); + + // Auto-number headings + let sectionNumbers = []; + + visit(tree, "heading", (headingNode) => { + if (headingNode.depth < options.startDepth) { + return; + } + + const headingText = nodeToString(headingNode); + if (options.skip.test(headingText)) { + return; + } + + if (!("data" in headingNode)) { + headingNode.data = {}; + } + + if (!("hProperties" in headingNode.data)) { + headingNode.data.hProperties = {}; + } + + if (headingText.startsWith(options.appendixToken)) { + findAndReplace(headingNode, [options.appendixToken]); + + const currentIndex = typeof sectionNumbers[headingNode.depth] === "string" + ? sectionNumbers[headingNode.depth] + : "@"; + sectionNumbers[headingNode.depth] = String.fromCharCode(currentIndex.charCodeAt(0) + 1); + sectionNumbers = sectionNumbers.slice(0, headingNode.depth + 1); + + const sectionNumber = sectionNumbers.slice(options.startDepth, headingNode.depth + 1).join("."); + headingNode.data.section = `${options.appendixPrefix} ${sectionNumber}`; + + headingNode.children.splice(0, 0, text(`${headingNode.data.section}. `)); + } else { + sectionNumbers[headingNode.depth] = (sectionNumbers[headingNode.depth] ?? 0) + 1; + sectionNumbers = sectionNumbers.slice(0, headingNode.depth + 1); + + const sectionNumber = sectionNumbers.slice(options.startDepth, headingNode.depth + 1).join("."); + const prefix = typeof sectionNumbers[options.startDepth] === "string" + ? options.appendixPrefix + : "Section"; + headingNode.data.section = `${prefix} ${sectionNumber}`; + + headingNode.children.splice(0, 0, text(`${sectionNumber}. `)); + } + + if (!("id" in headingNode.data)) { + const sectionSlug = headingNode.data?.id + ?? headingNode.data.section.replaceAll(/[ .]/g, "-").toLowerCase(); + headingNode.data.hProperties.id = sectionSlug; + headingNode.data.id = sectionSlug; + } + }); + + // Build headings data used by ./remark-reference-links.js + if (!("data" in file)) { + file.data = {}; + } + + file.data.headings = {}; + + visit(tree, "heading", (headingNode) => { + if (headingNode.data?.id) { + if (headingNode.data.id in file.data.headings) { + file.message(`Found duplicate heading id "${headingNode.data.id}"`); + } + file.data.headings[headingNode.data.id] = headingNode; + } + }); + + // Make heading a link + visit(tree, "heading", (headingNode) => { + if (headingNode.data?.id) { + headingNode.children = [link(`#${headingNode.data.id}`, "", headingNode.children)]; + } + }); +}; + +export default remarkNumberHeadings; diff --git a/build/remark-number-headings.js b/build/remark-number-headings.js deleted file mode 100644 index 30800774..00000000 --- a/build/remark-number-headings.js +++ /dev/null @@ -1,47 +0,0 @@ -import { visit } from "unist-util-visit"; - - -const defaultOptions = { - startDepth: 1, - skip: [] -}; - -const remarkNumberHeadings = (options) => (tree) => { - options = { ...defaultOptions, ...options }; - options.skip = new RegExp(`^(${options.skip.join("|")})$`, "u"); - - let sectionNumbers = []; - - visit(tree, "heading", (node) => { - if (node.depth < options.startDepth) { - return; - } - - visit(node, "text", (textNode) => { - let text = textNode.value ? textNode.value.trim() : ""; - - if (options.skip.test(text)) { - return; - } - - if (text.startsWith(options.appendixToken)) { - const currentIndex = typeof sectionNumbers[node.depth] === "string" - ? sectionNumbers[node.depth] - : "@"; - sectionNumbers[node.depth] = String.fromCharCode(currentIndex.charCodeAt(0) + 1); - sectionNumbers = sectionNumbers.slice(0, node.depth + 1); - - const sectionNumber = sectionNumbers.slice(options.startDepth, node.depth + 1).join("."); - textNode.value = `${options.appendixPrefix} ${sectionNumber}. ${text.slice(options.appendixToken.length + 1)}`; - } else { - sectionNumbers[node.depth] = (sectionNumbers[node.depth] ?? 0) + 1; - sectionNumbers = sectionNumbers.slice(0, node.depth + 1); - - const sectionNumber = sectionNumbers.slice(options.startDepth, node.depth + 1).join("."); - textNode.value = `${sectionNumber}. ${text}`; - } - }); - }); -}; - -export default remarkNumberHeadings; diff --git a/build/remark-reference-links.js b/build/remark-reference-links.js new file mode 100644 index 00000000..16af2928 --- /dev/null +++ b/build/remark-reference-links.js @@ -0,0 +1,21 @@ +import { text, link } from "mdast-builder"; +import { toString as nodeToString } from "mdast-util-to-string"; +import { findAndReplace } from "mdast-util-find-and-replace"; + + +const referenceLink = /\{\{(?.*?)\}\}/ug; + +const remarkReferenceLinks = () => (tree, file) => { + findAndReplace(tree, [referenceLink, (value, id) => { + // file.data.headings comes from ./remark-headings.js + if (!(id in file.data.headings)) { + throw Error(`ReferenceLinkError: No header found with id "${id}"`); + } + + const headerText = nodeToString(file.data.headings[id]); + const linkText = text(file.data.headings[id].data.section); + return link(`#${id}`, headerText, [linkText]); + }]); +}; + +export default remarkReferenceLinks; diff --git a/build/remark-section-links.js b/build/remark-section-links.js deleted file mode 100644 index 1c41e042..00000000 --- a/build/remark-section-links.js +++ /dev/null @@ -1,43 +0,0 @@ -import { visit } from "unist-util-visit"; - - -const sectionLink = /\{\{(?.*?)\}\}/u; - -const remarkSectionLinks = (options) => (tree, vfile) => { - // Heading data comes from @vcarl/remark-headings - const headings = {}; - for (const heading of vfile.data.headings) { - if (heading?.data?.id) { - headings[heading.data.id] = heading.value; - } - } - - visit(tree, "text", (node, index, parent) => { - const match = node.value.match(sectionLink); - - if (match) { - if (!(match.groups.id in headings)) { - throw Error(`SectionLinkError: No header found with id "${match.groups.id}"`) - } - const headerText = headings[match.groups.id]; - - const beforeNode = { type: "text", value: node.value.slice(0, match.index) }; - const afterNode = { type: "text", value: node.value.slice(match.index + match[0].length) }; - const linkNode = { - type: "link", - title: headerText, - url: `#${match.groups.id}`, - children: [ - { - type: "text", - value: "Section " + headerText.slice(0, headerText.indexOf(". ")) - } - ] - }; - - parent.children.splice(index, 1, beforeNode, linkNode, afterNode); - } - }); -}; - -export default remarkSectionLinks; diff --git a/build/remark-table-of-contents.js b/build/remark-table-of-contents.js new file mode 100644 index 00000000..3fbb3bde --- /dev/null +++ b/build/remark-table-of-contents.js @@ -0,0 +1,65 @@ +import { visit } from "unist-util-visit"; +import { list, listItem } from "mdast-builder"; +import { toString as nodeToString } from "mdast-util-to-string"; + + +const defaultOptions = { + heading: "Table of Contents", + startDepth: 1, + skip: [] +}; + +const remarkTableOfContents = (options) => (tree, file) => { + options = { ...defaultOptions, ...options }; + options.skip.push(options.heading); + options.skip = new RegExp(`^(${options.skip.join("|")})$`, "u"); + + let insertTableOfContents; + + const tableOfContents = list("unordered"); + let currentList = tableOfContents; + const listStack = [currentList]; + let currentDepth = options.startDepth; + + visit(tree, "heading", (headingNode, index, parent) => { + const headingText = nodeToString(headingNode); + + if (headingText === options.heading) { + insertTableOfContents = () => { + parent.children.splice(index + 1, 0, tableOfContents); + }; + } + + if (headingNode.depth < options.startDepth) { + return; + } + + while (headingNode.depth > currentDepth) { + const newList = list("unordered"); + listStack.push(newList); + currentList.children.push(newList); + currentList = newList; + currentDepth++; + } + + while (headingNode.depth < currentDepth) { + listStack.pop(); + currentList = listStack[listStack.length - 1]; + currentDepth--; + } + + if (options.skip.test(headingText)) { + return; + } + + currentList.children.push(listItem(headingNode.children)); + }); + + if (insertTableOfContents) { + insertTableOfContents(); + } else { + file.message(`Table of Contents not added. Add a heading with the text "${options.heading}" or set the 'heading' option to use a different heading.`); + } +}; + +export default remarkTableOfContents; diff --git a/jsonschema-core.md b/jsonschema-core.md index 83997d53..58898e59 100644 --- a/jsonschema-core.md +++ b/jsonschema-core.md @@ -1,6 +1,7 @@ # JSON Schema: A Media Type for Describing JSON Documents ## Abstract + JSON Schema defines the media type `application/schema+json`, a JSON-based format for describing the structure of JSON data. JSON Schema asserts what a JSON document must look like, ways to extract information from it, and how to @@ -9,6 +10,7 @@ additional feature-rich integration with `application/schema+json` beyond what can be offered for `application/json` documents. ## Note to Readers + The issues list for this draft can be found at . @@ -20,6 +22,7 @@ the homepage, or email the document editors. ## Table of Contents ## Introduction + JSON Schema is a JSON media type for defining the structure of JSON data. JSON Schema is intended to define validation, documentation, hyperlink navigation, and interaction control of JSON data. @@ -33,6 +36,7 @@ Other specifications define the vocabularies that perform assertions about validation, linking, annotation, navigation, and interaction. ## Conventions and Terminology + The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL NOT", "SHOULD", "SHOULD NOT", "RECOMMENDED", "MAY", and "OPTIONAL" in this document are to be interpreted as described in [RFC 2119](#rfc2119). @@ -42,6 +46,7 @@ The terms "JSON", "JSON text", "JSON value", "member", "element", "object", document are to be interpreted as defined in [RFC 8259](#rfc8259). ## Overview + This document proposes a new media type `application/schema+json` to identify a JSON Schema for describing JSON data. It also proposes a further optional media type, `application/schema-instance+json`, to provide additional integration @@ -87,12 +92,12 @@ that document's purpose. ## Definitions ### JSON Document + A JSON document is an information resource (series of octets) described by the `application/json` media type. In JSON Schema, the terms "JSON document", "JSON text", and "JSON value" are -interchangeable because of the data model it defines in -{{instance-data-model}}. +interchangeable because of the data model it defines in {{data-model}}. JSON Schema is only defined over JSON documents. However, any document or memory structure that can be parsed into or processed according to the JSON Schema data @@ -109,7 +114,7 @@ including media types with the `+json` structured syntax suffix. Among these, this specification defines the `application/schema-instance+json` media type which defines handling for fragments in the IRI. -#### Instance Data Model {#instance-data-model} +#### Instance Data Model {#data-model} JSON Schema interprets documents according to a data model. A JSON value interpreted according to this data model is called an "instance". @@ -133,23 +138,23 @@ string: A string of Unicode code points, from the JSON "string" value Whitespace and formatting concerns, including different lexical representations of numbers that are equal within the data model, are thus outside the scope of -JSON Schema. JSON Schema [vocabularies](#81-meta-schemas-and-vocabularies) that -wish to work with such differences in lexical representations SHOULD define -keywords to precisely interpret formatted strings within the data model rather -than relying on having the original JSON representation Unicode characters -available. +JSON Schema. JSON Schema [vocabularies](#vocabulary) that wish to work with such +differences in lexical representations SHOULD define keywords to precisely +interpret formatted strings within the data model rather than relying on having +the original JSON representation Unicode characters available. Since an object cannot have two properties with the same key, behavior for a JSON document that tries to define two properties with the same key in a single object is undefined. Note that JSON Schema vocabularies are free to define their own extended type -system. This should not be confused with the core data model types defined -here. As an example, "integer" is a reasonable type for a vocabulary to define -as a value for a keyword, but the data model makes no distinction between -integers and other numbers. +system. This should not be confused with the core data model types defined here. +As an example, "integer" is a reasonable type for a vocabulary to define as a +value for a keyword, but the data model makes no distinction between integers +and other numbers. #### Instance Equality + Two JSON instances are said to be equal if and only if they are of the same type and have the same value according to the data model. Specifically, this means: @@ -159,8 +164,8 @@ and have the same value according to the data model. Specifically, this means: - both are strings, and are the same codepoint-for-codepoint; or - both are numbers, and have the same mathematical value; or - both are arrays, and have an equal value item-for-item; or -- both are objects, and each property in one has exactly one property with -a key equal to the other's, and that other property has an equal value. +- both are objects, and each property in one has exactly one property with a key + equal to the other's, and that other property has an equal value. Implied in this definition is that arrays must be the same length, objects must have the same number of members, properties in objects are unordered, there is @@ -169,6 +174,7 @@ differences (indentation, placement of commas, trailing zeros) are insignificant. #### Non-JSON Instances + It is possible to use JSON Schema with a superset of the JSON Schema data model, where an instance may be outside any of the six JSON data types. @@ -179,7 +185,8 @@ A custom vocabulary may define support for a superset of the core data model. The schema itself may only be expressible in this superset; for example, to make use of the `const` keyword. -### JSON Schema Documents +### JSON Schema Documents {#schema-document} + A JSON Schema document, or simply a schema, is a JSON document used to describe an instance. A schema can itself be interpreted as an instance, but SHOULD always be given the media type `application/schema+json` rather than @@ -190,9 +197,9 @@ provided by `application/schema-instance+json`. A JSON Schema MUST be an object or a boolean. #### JSON Schema Objects and Keywords -Object properties that are applied to the instance are called keywords, -or schema keywords. Broadly speaking, keywords fall into one of five -categories: + +Object properties that are applied to the instance are called keywords, or +schema keywords. Broadly speaking, keywords fall into one of five categories: identifiers: control schema identification through setting a IRI for the schema and/or changing how the base IRI is determined @@ -219,19 +226,20 @@ companions, are free to define other behaviors as well. A JSON Schema MAY contain properties which are not schema keywords or are not recognized as schema keywords. The behavior of such keywords is governed by -{{unknown-keywords}}. +{{unrecognized}}. An empty schema is a JSON Schema with no properties. #### Boolean JSON Schemas + The boolean schema values `true` and `false` are trivial schemas that always produce themselves as assertion results, regardless of the instance value. They never produce annotation results. These boolean schemas exist to clarify schema author intent and facilitate -schema processing optimizations. They behave identically to the following -schema objects (where `not` is part of the subschema application vocabulary -defined in this document). +schema processing optimizations. They behave identically to the following schema +objects (where `not` is part of the subschema application vocabulary defined in +this document). `true`: Always passes validation, as if the empty schema `{}` @@ -242,6 +250,7 @@ equivalents to the `false` schema. Using the boolean values ensures that the intent is clear to both human readers and implementations. #### Schema Vocabularies + A schema vocabulary, or simply a vocabulary, is a set of keywords, their syntax, and their semantics. A vocabulary is generally organized around a particular purpose. Different uses of JSON Schema, such as validation, hypermedia, or user @@ -261,6 +270,7 @@ organizations, a vocabulary specification need not be published outside of its scope of use. #### Meta-Schemas + A schema that itself describes a schema is called a meta-schema. Meta-schemas are used to validate JSON Schemas and specify which vocabularies they are using. @@ -271,7 +281,8 @@ conformance more strictly or more loosely than the vocabularies' specifications call for. Meta-schemas may also describe and validate additional keywords that are not part of a formal vocabulary. -#### Root Schema and Subschemas and Resources +#### Root Schema and Subschemas and Resources {#root} + A JSON Schema resource is a schema which is [canonically](#rfc6596) identified by an [absolute IRI](#rfc3987). Schema resources MAY also be identified by IRIs, including IRIs with fragments, if the resulting secondary resource (as defined @@ -281,7 +292,7 @@ in another. Any such IRIs with fragments are considered to be non-canonical. The root schema is the schema that comprises the entire JSON document in question. The root schema is always a schema resource, where the IRI is -determined as described in {{initial-base-iri}}.[^1] +determined as described in {{initial-base}}.[^1] [^1]: Note that documents that embed schemas in another format will not have a root schema resource in this sense. Exactly how such usages fit with the JSON @@ -303,17 +314,18 @@ schema titled "root" is the root schema. As with the root schema, a subschema is either an object or a boolean. -As discussed in {{id-keyword}}, a JSON Schema document -can contain multiple JSON Schema resources. When used without qualification, -the term "root schema" refers to the document's root schema. In some cases, -resource root schemas are discussed. A resource's root schema is its top-level -schema object, which would also be a document root schema if the resource were -to be extracted to a standalone JSON Schema document. +As discussed in {{id-keyword}}, a JSON Schema document can contain multiple JSON +Schema resources. When used without qualification, the term "root schema" refers +to the document's root schema. In some cases, resource root schemas are +discussed. A resource's root schema is its top-level schema object, which would +also be a document root schema if the resource were to be extracted to a +standalone JSON Schema document. Whether multiple schema resources are embedded or linked with a reference, they are processed in the same way, with the same available behaviors. -## Fragment Identifiers {#fragment-identifiers} +## Fragment Identifiers {#fragments} + In accordance with section 3.1 of [RFC 6839](#rfc6839), the syntax and semantics of fragment identifiers specified for any +json media type SHOULD be as specified for `application/json`. (At publication of this document, there is no @@ -324,8 +336,8 @@ identifier structures: plain names and JSON Pointers. The `application/schema-instance+json` media type supports one fragment identifier structure: JSON Pointers. -The use of JSON Pointers as IRI fragment identifiers is described in -[RFC 6901](#rfc6901). For `application/schema+json`, which supports two fragment +The use of JSON Pointers as IRI fragment identifiers is described in [RFC +6901](#rfc6901). For `application/schema+json`, which supports two fragment identifier syntaxes, fragment identifiers matching the JSON Pointer syntax, including the empty string, MUST be interpreted as JSON Pointer fragment identifiers. @@ -346,29 +358,33 @@ interpreted as plain name fragment identifiers. Defining and referencing a plain name fragment identifier within an `application/schema+json` document are specified in the [`$anchor` -keyword](#822-defining-location-independent-identifiers) section. +keyword](#anchors) section. ## General Considerations ### Range of JSON Values + An instance may be any valid JSON value as defined by [JSON](#rfc8259). JSON Schema imposes no restrictions on type: JSON Schema can describe any JSON value, including, for example, null. -### Programming Language Independence +### Programming Language Independence {#language} + JSON Schema is programming language agnostic, and supports the full range of values described in the data model. Be aware, however, that some languages and JSON parsers may not be able to represent in memory the full range of values describable by JSON. -### Mathematical Integers +### Mathematical Integers {#integers} + Some programming languages and parsers use different internal representations for floating point numbers than they do for integers. For consistency, integer JSON numbers SHOULD NOT be encoded with a fractional part. -### Regular Expressions +### Regular Expressions {#regex} + Keywords MAY use regular expressions to express constraints, or constrain the instance value to be a regular expression. These regular expressions SHOULD be valid according to the regular expression dialect described in [ECMA-262, @@ -387,13 +403,13 @@ schema authors SHOULD limit themselves to the following regular expression tokens: - individual Unicode characters, as defined by the [JSON -specification](#rfc8259); + specification](#rfc8259); - simple character classes ([abc]), range character classes ([a-z]); - complemented character classes ([^abc], [^a-z]); - simple quantifiers: "+" (one or more), "*" (zero or more), "?" (zero or one), -and their lazy versions ("+?", "*?", "??"); + and their lazy versions ("+?", "*?", "??"); - range quantifiers: "{x}" (exactly x occurrences), "{x,y}" (at least x, at most -y, occurrences), {x,} (x occurrences or more), and their lazy versions; + y, occurrences), {x,} (x occurrences or more), and their lazy versions; - the beginning-of-input ("^") and end-of-input ("$") anchors; - simple grouping ("(...)") and alternation ("|"). @@ -401,7 +417,8 @@ Finally, implementations MUST NOT take regular expressions to be anchored, neither at the beginning nor at the end. This means, for instance, the pattern "es" matches "expression". -### Extending JSON Schema +### Extending JSON Schema {#extending} + Additional schema keywords and schema vocabularies MAY be defined by any entity. Save for explicit agreement, schema authors SHALL NOT expect these additional keywords and vocabularies to be supported by implementations that do not @@ -411,7 +428,8 @@ Implementations MAY provide the ability to register or load handlers for vocabularies that they do not support directly. The exact mechanism for registering and implementing such handlers is implementation-dependent. -#### Explicit annotation keywords +#### Explicit annotation keywords {#explicit-annotations} + The values of keywords which begin with "x-" MUST be collected as annotations. Keywords which begin with "x-" symbol MUST NOT affect evaluation of a schema in @@ -420,13 +438,15 @@ any way other than annotation collection. Consequently, the "x-" prefix is reserved for this purpose, and extension vocabularies MUST NOT define any keywords which begin with this prefix. -#### Handling of unrecognized or unsupported keywords {#unknown-keywords} +#### Handling of unrecognized or unsupported keywords {#unrecognized} + Implementations SHOULD treat keywords they do not recognize, or that they recognize but do not support, as annotations, where the value of the keyword is the value of the annotation. Whether an implementation collects these annotations or not, they MUST otherwise ignore the keywords. ## Keyword Behaviors + JSON Schema keywords fall into several general behavior categories. Assertions validate that an instance satisfies constraints, producing a boolean result. Annotations attach information that applications may use in any way they see @@ -442,12 +462,12 @@ other behaviors for specialized purposes. Evaluating an instance against a schema involves processing all of the keywords in the schema against the appropriate locations within the instance. Typically, applicator keywords are processed until a schema object with no applicators (and -therefore no subschemas) is reached. The appropriate location in the instance -is evaluated against the assertion and annotation keywords in the schema object. +therefore no subschemas) is reached. The appropriate location in the instance is +evaluated against the assertion and annotation keywords in the schema object. The interactions of those keyword results to produce the schema object results -are governed by {{annotations-and-assertions}}, while the -relationship of subschema results to the results of the applicator keyword that -applied them is described by {{applicators}}. +are governed by {{annot-assert}}, while the relationship of subschema results to +the results of the applicator keyword that applied them is described by +{{applicators}}. Evaluation of a parent schema object can complete once all of its subschemas have been evaluated, although in some circumstances evaluation may be @@ -456,15 +476,15 @@ some assertion result short-circuiting is not possible due to the need to examine all subschemas for annotation collection, including those that cannot further change the assertion result. -### Lexical Scope and Dynamic Scope +### Lexical Scope and Dynamic Scope {#scopes} While most JSON Schema keywords can be evaluated on their own, or at most need to take into account the values or results of adjacent keywords in the same schema object, a few have more complex behavior. The lexical scope of a keyword is determined by the nested JSON data structure -of objects and arrays. The largest such scope is an entire schema document. -The smallest scope is a single schema object with no subschemas. +of objects and arrays. The largest such scope is an entire schema document. The +smallest scope is a single schema object with no subschemas. Keywords MAY be defined with a partial value, such as a IRI-reference, which must be resolved against another value, such as another IRI-reference or a full @@ -493,21 +513,21 @@ parent, rather than examining the local lexically enclosing parent. The concept of dynamic scope is primarily used with `$dynamicRef` and `$dynamicAnchor`, and should be considered an advanced feature and used with -caution when defining additional keywords. It also appears when reporting -errors and collected annotations, as it may be possible to revisit the same -lexical scope repeatedly with different dynamic scopes. In such cases, it is -important to inform the user of the evaluation path that produced the error or -annotation. +caution when defining additional keywords. It also appears when reporting errors +and collected annotations, as it may be possible to revisit the same lexical +scope repeatedly with different dynamic scopes. In such cases, it is important +to inform the user of the evaluation path that produced the error or annotation. ### Keyword Interactions + Keyword behavior MAY be defined in terms of the annotation results of -[subschemas](#435-root-schema-and-subschemas-and-resources) and/or adjacent -keywords (keywords within the same schema object) and their subschemas. Such -keywords MUST NOT result in a circular dependency. Keywords MAY modify their -behavior based on the presence or absence of another keyword in the same [schema -object](#43-json-schema-documents). +[subschemas](#root) and/or adjacent keywords (keywords within the same schema +object) and their subschemas. Such keywords MUST NOT result in a circular +dependency. Keywords MAY modify their behavior based on the presence or absence +of another keyword in the same [schema object](#schema-document). ### Default Behaviors {#default-behaviors} + A missing keyword MUST NOT produce a false assertion result, MUST NOT produce annotation results, and MUST NOT cause any other schema to be evaluated as part of its own behavioral definition. However, given that missing keywords do not @@ -524,17 +544,18 @@ Because annotation collection can add significant cost in terms of both computation and memory, implementations MAY opt out of this feature. Keywords that are specified in terms of collected annotations SHOULD describe reasonable alternate approaches when appropriate. This approach is demonstrated by the -[`items`](#10312-items) and -[`additionalProperties`](#10323-additionalproperties) keywords in this document. +[`items`](#items) and [`additionalProperties`](#additionalproperties) keywords +in this document. Note that when no such alternate approach is possible for a keyword, implementations that do not support annotation collections will not be able to support those keywords or vocabularies that contain them. ### Identifiers + Identifiers define IRIs for a schema, or affect how such IRIs are resolved in -[references](#824-schema-references), or both. The Core vocabulary defined in -this document defines several identifying keywords, most notably `$id`. +[references](#referenced), or both. The Core vocabulary defined in this document +defines several identifying keywords, most notably `$id`. Canonical schema IRIs MUST NOT change while processing an instance, but keywords that affect IRI-reference resolution MAY have behavior that is only fully @@ -547,13 +568,13 @@ to the matching `$dynamicRef` keyword, leaving the behavior of `$ref` undisturbed. ### Applicators {#applicators} + Applicators allow for building more complex schemas than can be accomplished with a single schema object. Evaluation of an instance against a [schema -document](#43-json-schema-documents) begins by applying the [root -schema](#435-root-schema-and-subschemas-and-resources) to the complete instance -document. From there, keywords known as applicators are used to determine which -additional schemas are applied. Such schemas may be applied in-place to the -current location, or to a child location. +document](#schema-document) begins by applying the [root schema](#root) to the +complete instance document. From there, keywords known as applicators are used +to determine which additional schemas are applied. Such schemas may be applied +in-place to the current location, or to a child location. The schemas to be applied may be present as subschemas comprising all or part of the keyword's value. Alternatively, an applicator may refer to a schema @@ -561,22 +582,21 @@ elsewhere in the same schema document, or in a different one. The mechanism for identifying such referenced schemas is defined by the keyword. Applicator keywords also define how subschema or referenced schema boolean -[assertion](#76-assertions) results are modified and/or combined to produce the +[assertion](#assertions) results are modified and/or combined to produce the boolean result of the applicator. Applicators may apply any boolean logic operation to the assertion results of subschemas, but MUST NOT introduce new assertion conditions of their own. -[Annotation](#77-annotations) results from subschemas are preserved in -accordance with {{collecting-annotations}} so that -applications can decide how to interpret multiple values. Applicator keywords -do not play a direct role in this preservation. +[Annotation](#annotations) results from subschemas are preserved in accordance +with {{collect}} so that applications can decide how to interpret multiple +values. Applicator keywords do not play a direct role in this preservation. + +#### Referenced and Referencing Schemas {#referenced} -#### Referenced and Referencing Schemas -As noted in {{applicators}}, an applicator keyword may refer to a -schema to be applied, rather than including it as a subschema in the -applicator's value. In such situations, the schema being applied is known as -the referenced schema, while the schema containing the applicator keyword is the -referencing schema. +As noted in {{applicators}}, an applicator keyword may refer to a schema to be +applied, rather than including it as a subschema in the applicator's value. In +such situations, the schema being applied is known as the referenced schema, +while the schema containing the applicator keyword is the referencing schema. While root schemas and subschemas are static concepts based on a schema's position within a schema document, referenced and referencing schemas are @@ -584,14 +604,14 @@ dynamic. Different pairs of schemas may find themselves in various referenced and referencing arrangements during the evaluation of an instance against a schema. -For some by-reference applicators, such as -[`$ref`](#8241-direct-references-with-ref), the referenced schema can be -determined by static analysis of the schema document's lexical scope. Others, -such as `$dynamicRef` (with `$dynamicAnchor`), may make use of dynamic scoping, -and therefore only be resolvable in the process of evaluating the schema with an -instance. +For some by-reference applicators, such as [`$ref`](#ref), the referenced schema +can be determined by static analysis of the schema document's lexical scope. +Others, such as `$dynamicRef` (with `$dynamicAnchor`), may make use of dynamic +scoping, and therefore only be resolvable in the process of evaluating the +schema with an instance. + +### Assertions {#assertions} -### Assertions JSON Schema can be used to assert constraints on a JSON document, which either passes or fails the assertions. This approach can be used to validate conformance with the constraints, or document what is needed to satisfy them. @@ -602,6 +622,7 @@ instance against schema assertions. An instance can only fail an assertion that is present in the schema. #### Assertions and Instance Primitive Types + Most assertions only constrain values within a certain primitive type. When the type of the instance is not of the type targeted by the keyword, the instance is considered to conform to the assertion. @@ -612,8 +633,8 @@ are too long) from being valid. If the instance is a number, boolean, null, array, or object, then it is valid against this assertion. This behavior allows keywords to be used more easily with instances that can be -of multiple primitive types. The companion validation vocabulary also includes -a `type` keyword which can independently restrict the instance to one or more +of multiple primitive types. The companion validation vocabulary also includes a +`type` keyword which can independently restrict the instance to one or more primitive types. This allows for a concise expression of use cases such as a function that might return either a string of a certain length or a null value: @@ -630,7 +651,8 @@ not actually allow null values. Each keyword is evaluated separately unless explicitly specified otherwise, so if `maxLength` restricted the instance to strings, then including `"null"` in `type` would not have any useful effect. -### Annotations +### Annotations {#annotations} + JSON Schema can annotate an instance with information, whenever the instance validates against the schema object containing the annotation, and all of its parent schema objects. The information can be a simple value, or can be @@ -657,7 +679,8 @@ even if they cannot change the overall assertion result. The only exception is that subschemas of a schema object that has failed validation MAY be skipped, as annotations are not retained for failing schemas. -#### Collecting Annotations {#collecting-annotations} +#### Collecting Annotations {#collect} + Annotations are collected by keywords that explicitly define annotation-collecting behavior. Note that boolean schemas cannot produce annotations as they do not make use of keywords. @@ -667,12 +690,13 @@ A collected annotation MUST include the following information: - The name of the keyword that produces the annotation - The instance location to which it is attached, as a JSON Pointer - The evaluation path, indicating how reference keywords such as `$ref` were -followed to reach the absolute schema location. + followed to reach the absolute schema location. - The absolute schema location of the attaching keyword, as a IRI. This MAY be -omitted if it is the same as the evaluation path from above. + omitted if it is the same as the evaluation path from above. - The attached value(s) ##### Distinguishing Among Multiple Values + Applications MAY make decisions on which of multiple annotation values to use based on the schema location that contributed the value. This is intended to allow flexible usage. Collecting the schema location facilitates such usage. @@ -723,9 +747,9 @@ Note that some lines are wrapped for clarity. In this example, both Feature A and Feature B make use of the re-usable "enabledToggle" schema. That schema uses the `title`, `description`, and -`default` annotations. Therefore the application has to decide how to handle -the additional `default` value for Feature A, and the additional `description` -value for Feature B. +`default` annotations. Therefore the application has to decide how to handle the +additional `default` value for Feature A, and the additional `description` value +for Feature B. The application programmer and the schema author need to agree on the usage. For this example, let's assume that they agree that the most specific `default` @@ -752,7 +776,8 @@ might take. For example, an application may consider the presence of two different values for `default` to be an error, regardless of their schema locations. -##### Annotations and Assertions {#annotations-and-assertions} +##### Annotations and Assertions {#annot-assert} + Schema objects that produce a false assertion result MUST NOT produce any annotation results, whether from their own keywords or from keywords in subschemas. @@ -781,6 +806,7 @@ annotation "String Value" is kept, as the instance passes the string type assertions. ### Reserved Locations + A fourth category of keywords simply reserve a location to hold re-usable components or data of interest to schema authors that is not suitable for re-use. These keywords do not affect validation or annotation results. Their @@ -788,11 +814,12 @@ purpose in the core vocabulary is to ensure that locations are available for certain purposes and will not be redefined by extension keywords. While these keywords do not directly affect results, as explained in -{{non-schema-references}} unrecognized extension keywords that reserve -locations for re-usable schemas may have undesirable interactions with -references in certain circumstances. +{{non-schemas}} unrecognized extension keywords that reserve locations for +re-usable schemas may have undesirable interactions with references in certain +circumstances. ### Loading Instance Data + While none of the vocabularies defined as part of this or the associated documents define a keyword which may target and/or load instance data, it is possible that other vocabularies may wish to do so. @@ -803,7 +830,8 @@ examine parts of an instance outside the current evaluation location. Keywords that allow adjusting the location using a Relative JSON Pointer SHOULD default to using the current location if a default is desireable. -## The JSON Schema Core Vocabulary {#core-vocabulary} +## The JSON Schema Core Vocabulary {#core} + Keywords declared in this section, which all begin with "$", make up the JSON Schema Core vocabulary. These keywords are either required in order to process any schema or meta-schema, including those split across multiple documents, or @@ -811,9 +839,9 @@ exist to reserve keywords for purposes that require guaranteed interoperability. The Core vocabulary MUST be considered mandatory at all times, in order to bootstrap the processing of further vocabularies. Meta-schemas that use the -[`$vocabulary`](#81-meta-schemas-and-vocabularies) keyword to declare the -vocabularies in use MUST explicitly list the Core vocabulary, which MUST have a -value of true indicating that it is required. +[`$vocabulary`](#vocabulary) keyword to declare the vocabularies in use MUST +explicitly list the Core vocabulary, which MUST have a value of true indicating +that it is required. The behavior of a false value for this vocabulary (and only this vocabulary) is undefined, as is the behavior when `$vocabulary` is present but the Core @@ -833,7 +861,8 @@ The current IRI for the corresponding meta-schema is: The "$" prefix is reserved for use by the Core vocabulary. Vocabulary extensions MUST NOT define new keywords that begin with "$". -### Meta-Schemas and Vocabularies +### Meta-Schemas and Vocabularies {#vocabulary} + Two concepts, meta-schemas and vocabularies, are used to inform an implementation how to interpret a schema. Every schema has a meta-schema, which can be declared using the `$schema` keyword. @@ -861,7 +890,8 @@ vocabulary's keywords. Meta-schema authoring is an advanced usage of JSON Schema, so the design of meta-schema features emphasizes flexibility over simplicity. -#### The $schema Keyword +#### The $schema Keyword {#keyword-schema} + The `$schema` keyword is both used as a JSON Schema dialect identifier and as the identifier of a resource which is itself a JSON Schema, which describes the set of valid schemas written for this particular dialect. @@ -882,12 +912,13 @@ the following options: - Refuse to process the schema, as with unsupported required vocabularies - Assume a specific, documented meta-schema - Document the process by which it examines the schema and determines which of a -specific set of meta-schemas to assume + specific set of meta-schemas to assume Values for this property are defined elsewhere in this and other documents, and by other parties. #### The $vocabulary Keyword + The `$vocabulary` keyword is used in meta-schemas to identify the vocabularies available for use in schemas described by that meta-schema, and whether each vocabulary is required or optional. Together, this information forms a dialect. @@ -913,13 +944,14 @@ the vocabulary MUST be considered to be required. If the value is false, then the vocabulary MUST be considered to be optional. ##### Required, optional, and omitted vocabularies + A schema is said to use a dialect and its constituent vocabularies if it is associated with a meta-schema defining the dialect with `$vocabulary`, either through `$schema`, through appropriately defined media type parameters or link relation types, or through documented default implementation-defined behavior in the absence of an explicit meta-schema. If a meta-schema does not contain `$vocabulary`, the set of vocabularies in use is determined according to -{{default-vocabularies}}. +{{default-vocabs}}. Any vocabulary in use by a schema and understood by the implementation MUST be processed in a manner consistent with the semantic definitions contained within @@ -927,22 +959,23 @@ the vocabulary, regardless of whether that vocabulary is required or optional. Any vocabulary that is not present in `$vocabulary` MUST NOT be made available for use in schemas described by that meta-schema, except for the core vocabulary -as specified by the introduction to {{core-vocabulary}}. +as specified by the introduction to {{core}}. Implementations that do not support a vocabulary required by a schema MUST refuse to process that schema. Implementations that do not support a vocabulary that is optionally used by a schema SHOULD proceed with processing the schema. The keywords will be -considered to be unrecognized keywords as addressed by -{{unknown-keywords}}. Note that since the recommended behavior for such -keywords is to collect them as annotations, vocabularies consisting only of -annotations will have the same behavior when used optionally whether the -implementation supports them or not. This allows annotation-only vocabularies to -be supported without custom code, even in implementations that do not support -providing custom code for extension vocabularies. +considered to be unrecognized keywords as addressed by {{unrecognized}}. Note +that since the recommended behavior for such keywords is to collect them as +annotations, vocabularies consisting only of annotations will have the same +behavior when used optionally whether the implementation supports them or not. +This allows annotation-only vocabularies to be supported without custom code, +even in implementations that do not support providing custom code for extension +vocabularies. ##### Vocabularies are schema resource-scoped + The `$vocabulary` keyword SHOULD be used in the root schema of any schema resource intended for use as a meta-schema. It MUST NOT appear in subschemas. @@ -952,6 +985,7 @@ own meta-schema M' without requiring the validator to understand the vocabularies declared by M. ##### Vocabulary and non-vocabulary keywords + Keywords from different vocabularies, as well as non-vocabulary extension keywords, can have identical names. These are not considered to be the same keyword from the perspective of enabling or disabling them through @@ -963,9 +997,10 @@ governed by `$vocabulary` even in implementations that do not support any extension vocabularies. Guidance regarding vocabularies with identically-named keywords is provided in -[Appendix D.1](#d1-best-practices-for-vocabulary-and-meta-schema-authors). +{{vocab-practices}}. + +##### Default vocabularies {#default-vocabs} -##### Default vocabularies {#default-vocabularies} If `$vocabulary` is absent, an implementation MAY determine behavior based on the meta-schema if it is recognized from the IRI value of the referring schema's `$schema` keyword. This is how behavior (such as Hyper-Schema usage) has been @@ -981,12 +1016,13 @@ For example, an implementation that is a validator SHOULD assume the use of all vocabularies in this specification and the companion Validation specification. ##### Non-inheritability of vocabularies + Note that the processing restrictions on `$vocabulary` mean that meta-schemas that reference other meta-schemas using `$ref` or similar keywords do not automatically inherit the vocabulary declarations of those other meta-schemas. All such declarations must be repeated in the root of each schema document intended for use as a meta-schema. This is demonstrated in [the example -meta-schema](#d2-example-meta-schema-with-vocabulary-declarations).[^3] +meta-schema](#example-meta-schema).[^3] [^3]: This requirement allows implementations to find all vocabulary requirement information in a single place for each meta-schema. As schema extensibility @@ -996,12 +1032,14 @@ possibilities and search for vocabularies in referenced meta-schemas would be overly burdensome. #### Updates to Meta-Schema and Vocabulary IRIs + Updated vocabulary and meta-schema IRIs MAY be published between specification drafts in order to correct errors. Implementations SHOULD consider IRIs dated after this specification draft and before the next to indicate the same syntax and semantics as those listed here. ### Base IRI, Anchors, and Dereferencing + To differentiate between schemas in a vast ecosystem, schemas are identified by [IRI](#rfc3987), and can embed references to other schemas by specifying their IRI. @@ -1011,6 +1049,7 @@ used to construct a relative IRI-reference. For these keywords, it is necessary to establish a base IRI in order to resolve the reference. #### The $id Keyword {#id-keyword} + The `$id` keyword identifies a schema resource with its [canonical](#rfc6596) IRI. @@ -1035,17 +1074,19 @@ a relative IRI-reference, the base IRI for resolving that reference is the IRI of the parent schema resource. Note that an `$id` consisting of an empty IRI or of the empty fragment only will result in the embedded resource having the same IRI as the encapsulating resource, which SHOULD be considered an error per -{{duplicate-identifiers}}. +{{duplicate-iris}}. If no parent schema object explicitly identifies itself as a resource with `$id`, the base IRI is that of the entire document, as established by the steps -given in the [previous section.](initial-base-iri) +given in the [previous section.](initial-base) ##### Identifying the root schema + The root schema of a JSON Schema document SHOULD contain an `$id` keyword with an [absolute-IRI](#rfc3987) (containing a scheme, but no fragment). -#### Defining location-independent identifiers +#### Defining location-independent identifiers {#anchors} + Using JSON Pointer fragments requires knowledge of the structure of the schema. When writing schema documents with the intention to provide re-usable schemas, it may be preferable to use a plain name fragment that is not tied to any @@ -1066,32 +1107,31 @@ Separately from the usual usage of IRIs, `$dynamicAnchor` indicates that the fragment is an extension point when used with the `$dynamicRef` keyword. This low-level, advanced feature makes it easier to extend recursive schemas such as the meta-schemas, without imposing any particular semantics on that extension. -See the section on [`$dynamicRef`](#8242-dynamic-references-with-dynamicref) -for details. +See the section on [`$dynamicRef`](#dynamic-ref) for details. In most cases, the normal fragment behavior both suffices and is more intuitive. Therefore it is RECOMMENDED that `$anchor` be used to create plain name fragments unless there is a clear need for `$dynamicAnchor`. If present, the value of these keywords MUST be a string and MUST conform to the -plain name fragment identifier syntax defined in -{{fragment-identifiers}}.[^4] +plain name fragment identifier syntax defined in {{fragments}}.[^4] [^4]: Note that the anchor string does not include the "#" character, as it is not a IRI-reference. An `$anchor`: "foo" becomes the fragment `#foo` when used in a IRI. See below for full examples. -#### Duplicate schema identifiers {#duplicate-identifiers} +#### Duplicate schema identifiers {#duplicate-iris} + A schema MAY (and likely will) have multiple IRIs, but there is no way for an IRI to identify more than one schema. When multiple schemas attempt to identify as the same IRI through the use of `$id`, `$anchor`, `$dynamicAnchor`, or any other mechanism, implementations SHOULD raise an error condition. Otherwise the result is undefined, and even if documented will not be interoperable. -#### Schema References -Several keywords can be used to reference a schema which is to be applied to the -current instance location. `$ref` and `$dynamicRef` are applicator keywords, -applying the referenced schema to the instance. +#### Schema References {#references} Several keywords can be used to reference a +schema which is to be applied to the current instance location. `$ref` and +`$dynamicRef` are applicator keywords, applying the referenced schema to the +instance. As the values of `$ref` and `$dynamicRef` are IRI References, this allows the possibility to externalise or divide a schema across multiple files, and @@ -1103,7 +1143,8 @@ if it is a network-addressable URL, and implementations SHOULD NOT assume they should perform a network operation when they encounter a network-addressable IRI. -##### Direct References with $ref +##### Direct References with $ref {#ref} + The `$ref` keyword is an applicator that is used to reference a statically identified schema. Its results are the results of the referenced schema.[^5] @@ -1115,7 +1156,8 @@ Resolved against the current IRI base, it produces the IRI of the schema to apply. This resolution is safe to perform on schema load, as the process of evaluating an instance cannot change how the reference resolves. -##### Dynamic References with $dynamicRef +##### Dynamic References with $dynamicRef {#dynamic-ref} + The `$dynamicRef` keyword is an applicator that allows for deferring the full resolution until runtime, at which point it is resolved each time it is encountered while evaluating an instance. @@ -1126,23 +1168,22 @@ reference themselves). The extension point is defined with `$dynamicAnchor` and only exhibits runtime dynamic behavior when referenced with `$dynamicRef`. The value of the `$dynamicRef` property MUST be a string which is a -IRI-Reference that contains a valid [plain name -fragment](#822-defining-location-independent-identifiers). Resolved against the -current IRI base, it indicates the schema resource used as the starting point -for runtime resolution. This initial resolution is safe to perform on schema -load. +IRI-Reference that contains a valid [plain name fragment](#anchors). Resolved +against the current IRI base, it indicates the schema resource used as the +starting point for runtime resolution. This initial resolution is safe to +perform on schema load. The schema to apply is the outermost schema resource in the [dynamic -scope](#71-lexical-scope-and-dynamic-scope) that defines a `$dynamicAnchor` that -matches the plain name fragment in the initially resolved IRI. +scope](#scopes) that defines a `$dynamicAnchor` that matches the plain name +fragment in the initially resolved IRI. -For a full example using these keyword, see [Appendix -C](#appendix-c-example-of-recursive-schema-extension).[^6] +For a full example using these keyword, see {{recursive-example}}.[^6] [^6]: The difference between the hyper-schema meta-schema in pre-2019 drafts and an this draft dramatically demonstrates the utility of these keywords. -#### Schema Re-Use With $defs +#### Schema Re-Use With $defs {#defs} + The `$defs` keyword reserves a location for schema authors to inline re-usable JSON Schemas into a more general schema. The keyword does not directly affect the validation result. @@ -1167,6 +1208,7 @@ the positive integer constraint is a subschema in `$defs`: ``` ### Comments With $comment + This keyword reserves a location for comments from schema authors to readers or maintainers of the schema. @@ -1176,9 +1218,9 @@ and editing this keyword. The value of this keyword MAY be used in debug or error output which is intended for developers making use of schemas. Schema vocabularies SHOULD allow `$comment` within any object containing -vocabulary keywords. Implementations MAY assume `$comment` is allowed unless -the vocabulary specifically forbids it. Vocabularies MUST NOT specify any -effect of `$comment` beyond what is described in this specification. +vocabulary keywords. Implementations MAY assume `$comment` is allowed unless the +vocabulary specifically forbids it. Vocabularies MUST NOT specify any effect of +`$comment` beyond what is described in this specification. Tools that translate other media types or programming languages to and from `application/schema+json` MAY choose to convert that media type or programming @@ -1198,7 +1240,8 @@ MUST NOT be collected as an annotation result. ### Loading a Schema -#### Initial Base IRI {#initial-base-iri} +#### Initial Base IRI {#initial-base} + [RFC 3987 Section 6.5](#rfc3987) and [RFC 3986 Section 5.1](#rfc3986) defines how to determine the default base IRI of a document. @@ -1212,8 +1255,8 @@ and [RFC 3986 section 5](#rfc3986). If no source is known, or no IRI scheme is known for the source, a suitable implementation-specific default IRI MAY be used as described in [RFC 3987 -Section 6.5](#rfc3987) and [RFC 3986 Section 5.1.4](#rfc3986). It is -RECOMMENDED that implementations document any default base IRI that they assume. +Section 6.5](#rfc3987) and [RFC 3986 Section 5.1.4](#rfc3986). It is RECOMMENDED +that implementations document any default base IRI that they assume. If a schema object is embedded in a document of another media type, then the initial base IRI is determined according to the rules of that media type. @@ -1223,22 +1266,24 @@ schema, this base IRI SHOULD be considered the canonical IRI of the schema document's root schema resource. #### Loading a referenced schema + The use of IRIs to identify remote schemas does not necessarily mean anything is downloaded, but instead JSON Schema implementations SHOULD understand ahead of time which schemas they will be using, and the IRIs that identify them. When schemas are downloaded, for example by a generic user-agent that does not know until runtime which schemas to download, see [Usage for -Hypermedia](#951-usage-for-hypermedia). +Hypermedia](#hypermedia). Implementations SHOULD be able to associate arbitrary IRIs with an arbitrary schema and/or automatically associate a schema's `$id`-given IRI, depending on the trust that the validator has in the schema. Such IRIs and schemas can be supplied to an implementation prior to processing instances, or may be noted within a schema document as it is processed, producing associations as shown in -[Appendix A](#appendix-a-schema-identification-examples). +{{idexamples}}. #### Detecting a Meta-Schema + Implementations MUST recognize a schema as a meta-schema if it is being examined because it was identified as such by another schema's `$schema` keyword. This means that a single schema document might sometimes be considered a regular @@ -1257,9 +1302,10 @@ Meta-schema authors MUST NOT expect such features to be interoperable across implementations. ### Dereferencing + Schemas can be identified by any IRI that has been given to them, including a -JSON Pointer or their IRI given directly by `$id`. In all cases, dereferencing -a `$ref` reference involves first resolving its value as a IRI reference against +JSON Pointer or their IRI given directly by `$id`. In all cases, dereferencing a +`$ref` reference involves first resolving its value as a IRI reference against the current base IRI per [RFC 3986](#rfc3986). If the resulting IRI identifies a schema within the current document, or within @@ -1304,7 +1350,8 @@ described by Hyper-Schema, it is expected that new schemas will be added to the system dynamically, so placing an absolute requirement of pre-loading schema documents is not feasible. -#### JSON Pointer fragments and embedded schema resources {#json-pointer-embedded} +#### JSON Pointer fragments and embedded schema resources {#embedded} + Since JSON Pointer IRI fragments are constructed based on the structure of the schema document, an embedded schema resource and its subschemas can be identified by JSON Pointer fragments relative to either its own canonical IRI, @@ -1312,8 +1359,8 @@ or relative to any containing resource's IRI. Conceptually, a set of linked schema resources should behave identically whether each resource is a separate document connected with [schema -references](#824-schema-references), or is structured as a single document with -one or more schema resources embedded as subschemas. +references](#referenced), or is structured as a single document with one or more +schema resources embedded as subschemas. Since IRIs involving JSON Pointer fragments relative to the parent schema resource's IRI cease to be valid when the embedded schema is moved to a separate @@ -1392,9 +1439,10 @@ behavior (, Further examples of such non-canonical IRI construction, as well as the appropriate canonical IRI-based fragments to use instead, are provided in -[Appendix A](#appendix-a-schema-identification-examples). +{{idexamples}}. ### Compound Documents + A Compound Schema Document is defined as a JSON document (sometimes called a "bundled" schema) which has multiple embedded JSON Schema Resources bundled into the same document to ease transportation. @@ -1404,6 +1452,7 @@ following standard schema loading and processing requirements, including determining vocabulary support. #### Bundling + The bundling process for creating a Compound Schema Document is defined as taking references (such as `$ref`) to an external Schema Resource and embedding the referenced Schema Resources within the referring document. Bundling SHOULD @@ -1442,6 +1491,7 @@ hand, potentially without individual Schema Resources existing on their own previously. #### Differing and Default Dialects + When multiple schema resources are present in a single document, schema resources which do not define with which dialect they should be processed MUST be processed with the same dialect as the enclosing resource. @@ -1451,6 +1501,7 @@ resources MAY specify different processing dialects using the `$schema` values from their enclosing resource. #### Validating + Given that a Compound Schema Document may have embedded resources which identify as using different dialects, these documents SHOULD NOT be validated by applying a meta-schema to the Compound Schema Document as an instance. It is RECOMMENDED @@ -1470,19 +1521,20 @@ meta-schema. ### Caveats #### Guarding Against Infinite Recursion + A schema MUST NOT be run into an infinite loop against an instance. For example, if two schemas `#alice` and `#bob` both have an `allOf` property that refers to the other, a naive validator might get stuck in an infinite recursive loop trying to validate the instance. Schemas SHOULD NOT make use of infinite recursive nesting like this; the behavior is undefined. -#### References to Possible Non-Schemas {#non-schema-references} +#### References to Possible Non-Schemas {#non-schemas} + Subschema objects (or booleans) are recognized by their use with known -applicator keywords or with location-reserving keywords such as -[`$defs`](#825-schema-re-use-with-defs) that take one or more subschemas as a -value. These keywords may be `$defs` and the standard applicators from this -document, or extension keywords from a known vocabulary, or -implementation-specific custom keywords. +applicator keywords or with location-reserving keywords such as [`$defs`](#defs) +that take one or more subschemas as a value. These keywords may be `$defs` and +the standard applicators from this document, or extension keywords from a known +vocabulary, or implementation-specific custom keywords. Multi-level structures of unknown keywords are capable of introducing nested subschemas, which would be subject to the processing rules for `$id`. Therefore, @@ -1507,13 +1559,15 @@ relied upon for interoperability. ### Associating Instances and Schemas -#### Usage for Hypermedia +#### Usage for Hypermedia {#hypermedia} + JSON has been adopted widely by HTTP servers for automated APIs and robots. This section describes how to enhance processing of JSON documents in a more RESTful manner when used with protocols that support media types and [Web linking](#rfc8288). ##### Linking to a Schema + It is RECOMMENDED that instances described by a schema provide a link to a downloadable JSON Schema using the link relation "describedby", as defined by [Linked Data Protocol 1.0, section 8.1](#w3crec-ldp-20150226). @@ -1526,6 +1580,7 @@ Link: ; rel="describedby" ``` ##### Usage Over HTTP + When used for hypermedia systems over a network, [HTTP](#rfc7231) is frequently the protocol of choice for distributing schemas. Misbehaving clients can pose problems for server maintainers if they pull a schema over the network more @@ -1550,6 +1605,7 @@ Clients SHOULD be able to make requests with a "From" header so that server operators can contact the owner of a potentially misbehaving script. ## A Vocabulary for Applying Subschemas + This section defines a vocabulary of applicator keywords that are RECOMMENDED for use as the basis of other vocabularies. @@ -1559,9 +1615,11 @@ vocabulary as if its IRI were present with a value of true. The current IRI for this vocabulary, known as the Applicator vocabulary, is: `https://json-schema.org/draft/next/vocab/applicator`. -The current IRI for the corresponding meta-schema is: `https://json-schema.org/draft/next/meta/applicator`. +The current IRI for the corresponding meta-schema is: +`https://json-schema.org/draft/next/meta/applicator`. ### Keyword Independence + Schema keywords typically operate independently, without affecting each other's outcomes. @@ -1569,12 +1627,13 @@ For schema author convenience, there are some exceptions among the keywords in this vocabulary: - `additionalProperties`, whose behavior is defined in terms of `properties` and -`patternProperties` + `patternProperties` - `items`, whose behavior is defined in terms of `prefixItems` - `contains`, whose behavior is affected by the presence and value of -`minContains` + `minContains` + +### Keywords for Applying Subschemas in Place {#in-place} -### Keywords for Applying Subschemas in Place These keywords apply subschemas to the same location in the instance as the parent schema is being applied. They allow combining or modifying the subschema results in various ways. @@ -1583,14 +1642,16 @@ Subschemas of these keywords evaluate the instance completely independently such that the results of one such subschema MUST NOT impact the results of sibling subschemas. Therefore subschemas may be applied in any order. -#### Keywords for Applying Subschemas With Logic +#### Keywords for Applying Subschemas With Logic {#logic} + These keywords correspond to logical operators for combining or modifying the boolean assertion results of the subschemas. They have no direct impact on annotation collection, although they enable the same annotation keyword to be applied to an instance location with different values. Annotation keywords define their own rules for combining such values. -##### allOf +##### allOf {#allof} + This keyword's value MUST be a non-empty array. Each item of the array MUST be a valid JSON Schema. @@ -1598,6 +1659,7 @@ An instance validates successfully against this keyword if it validates successfully against all schemas defined by this keyword's value. ##### anyOf + This keyword's value MUST be a non-empty array. Each item of the array MUST be a valid JSON Schema. @@ -1607,26 +1669,29 @@ that when annotations are being collected, all subschemas MUST be examined so that annotations are collected from each subschema that validates successfully. ##### oneOf + This keyword's value MUST be a non-empty array. Each item of the array MUST be a valid JSON Schema. An instance validates successfully against this keyword if it validates successfully against exactly one schema defined by this keyword's value. -##### not +##### not {#not} + This keyword's value MUST be a valid JSON Schema. An instance is valid against this keyword if it fails to validate successfully against the schema defined by this keyword. -#### Keywords for Applying Subschemas Conditionally +#### Keywords for Applying Subschemas Conditionally {#conditional} + Three of these keywords work together to implement conditional application of a subschema based on the outcome of another subschema. The fourth is a shortcut for a specific conditional case. `if`, `then`, and `else` MUST NOT interact with each other across subschema -boundaries. In other words, an `if` in one branch of an `allOf` MUST NOT have -an impact on a `then` or `else` in another branch. +boundaries. In other words, an `if` in one branch of an `allOf` MUST NOT have an +impact on a `then` or `else` in another branch. There is no default behavior for `if`, `then`, or `else` when they are not present. In particular, they MUST NOT be treated as if present with an empty @@ -1634,6 +1699,7 @@ schema, and when `if` is not present, both `then` and `else` MUST be entirely ignored. ##### if + This keyword's value MUST be a valid JSON Schema. This validation outcome of this keyword's subschema has no direct effect on the @@ -1646,11 +1712,12 @@ be valid against the subschema value of the `then` keyword, if present. Instances that fail to validate against this keyword's subschema MUST also be valid against the subschema value of the `else` keyword, if present. -If [annotations](#77-annotations) are being collected, they are collected from -this keyword's subschema in the usual way, including when the keyword is present +If [annotations](#annotations) are being collected, they are collected from this +keyword's subschema in the usual way, including when the keyword is present without either `then` or `else`. ##### then + This keyword's value MUST be a valid JSON Schema. When `if` is present, and the instance successfully validates against its @@ -1663,6 +1730,7 @@ against this keyword, for either validation or annotation collection purposes, in such cases. ##### else + This keyword's value MUST be a valid JSON Schema. When `if` is present, and the instance fails to validate against its subschema, @@ -1675,6 +1743,7 @@ the instance against this keyword, for either validation or annotation collection purposes, in such cases. ##### dependentSchemas + This keyword specifies subschemas that are evaluated if the instance is an object and contains a certain property. @@ -1688,6 +1757,7 @@ property. Omitting this keyword has the same behavior as an empty object. ##### propertyDependencies + This keyword specifies subschemas that are evaluated if the instance is an object and contains a certain property with a certain string value. @@ -1702,6 +1772,7 @@ property. Omitting this keyword has the same behavior as an empty object. ### Keywords for Applying Subschemas to Child Instances + Each of these keywords defines a rule for applying its subschema(s) to child instances, specifically object properties and array items, and combining their results. @@ -1709,6 +1780,7 @@ results. #### Keywords for Applying Subschemas to Arrays ##### prefixItems + The value of "prefixItems` MUST be a non-empty array of valid JSON Schemas. Validation succeeds if each element of the instance validates against the @@ -1719,12 +1791,12 @@ and the instance value are affected by this keyword. This keyword produces an annotation value which is the largest index to which this keyword applied a subschema. The value MAY be a boolean true if a subschema was applied to every index of the instance, such as is produced by the `items` -keyword. This annotation affects the behavior of `items` and -`unevaluatedItems`. +keyword. This annotation affects the behavior of `items` and `unevaluatedItems`. Omitting this keyword has the same assertion behavior as an empty array. -##### items +##### items {#items} + The value of `items` MUST be a valid JSON Schema. This keyword applies its subschema to all instance elements at indexes greater @@ -1754,6 +1826,7 @@ collection MUST do so. #### Keywords for Applying Subschemas to Objects ##### properties + The value of `properties` MUST be an object. Each value of this object MUST be a valid JSON Schema. @@ -1769,6 +1842,7 @@ the Unevaluated vocabulary. Omitting this keyword has the same assertion behavior as an empty object. ##### patternProperties + The value of `patternProperties` MUST be an object. Each property name of this object SHOULD be a valid regular expression, according to the ECMA-262 regular expression dialect. Each property value of this object MUST be a valid JSON @@ -1787,7 +1861,8 @@ behavior of `additionalProperties` (in this vocabulary) and Omitting this keyword has the same assertion behavior as an empty object. -##### additionalProperties +##### additionalProperties {#additionalproperties} + The value of `additionalProperties` MUST be a valid JSON Schema. The behavior of this keyword depends on the presence and annotation results of @@ -1821,6 +1896,7 @@ Record](https://github.com/json-schema-org/json-schema-spec/tree/HEAD/adr/2022-0 for further details. ##### propertyNames + The value of `propertyNames` MUST be a valid JSON Schema. If the instance is an object, this keyword validates if every property name in @@ -1832,6 +1908,7 @@ Omitting this keyword has the same behavior as an empty schema. #### Other Keywords for Applying Subschemas ##### maxContains + The value of this keyword MUST be a non-negative integer. This keyword modifies the behavior of `contains` within the same schema object, @@ -1841,6 +1918,7 @@ Validation MUST always succeed against this keyword. The value of this keyword is used as its annotation result. ##### minContains + The value of this keyword MUST be a non-negative integer. This keyword modifies the behavior of `contains` within the same schema object, @@ -1849,11 +1927,12 @@ as described below in the section for that keyword. Validation MUST always succeed against this keyword. The value of this keyword is used as its annotation result. -Per {{default-behaviors}}, omitted keywords MUST NOT produce annotation -results. However, as described in the section for `contains`, the absence of -this keyword's annotation causes `contains` to assume a minimum value of 1. +Per {{default-behaviors}}, omitted keywords MUST NOT produce annotation results. +However, as described in the section for `contains`, the absence of this +keyword's annotation causes `contains` to assume a minimum value of 1. ##### contains + The value of this keyword MUST be a valid JSON Schema. This keyword applies its subschema to array elements or object property values. @@ -1890,6 +1969,7 @@ use by other keywords. This is to ensure that all possible annotations are collected. ## A Vocabulary for Unevaluated Locations + The purpose of these keywords is to enable schema authors to apply subschemas to array items or object properties that have not been successfully evaluated against any dynamic-scope subschema of any adjacent keywords. @@ -1925,16 +2005,18 @@ The current IRI for the corresponding meta-schema is: `https://json-schema.org/draft/next/meta/unevaluated`. ### Keyword Independence + Schema keywords typically operate independently, without affecting each other's outcomes. However, the keywords in this vocabulary are notable exceptions: - `unevaluatedItems`, whose behavior is defined in terms of annotations from -`prefixItems`, `items`, `contains`, and itself + `prefixItems`, `items`, `contains`, and itself - `unevaluatedProperties`, whose behavior is defined in terms of annotations -from `properties`, `patternProperties`, `additionalProperties`, `contains`, and -itself + from `properties`, `patternProperties`, `additionalProperties`, `contains`, + and itself + +### unevaluatedItems {#unevaluateditems} -### unevaluatedItems The value of `unevaluatedItems` MUST be a valid JSON Schema. The behavior of this keyword depends on the annotation results of adjacent @@ -1942,10 +2024,8 @@ keywords that apply to the instance location being validated. Specifically, the annotations from `prefixItems`, `items`, and `contains`, which can come from those keywords when they are adjacent to the `unevaluatedItems` keyword. Those three annotations, as well as `unevaluatedItems`, can also result from any and -all adjacent [in-place -applicator](#102-keywords-for-applying-subschemas-in-place) keywords. This -includes but is not limited to the in-place applicators defined in this -document. +all adjacent [in-place applicator](#in-place) keywords. This includes but is not +limited to the in-place applicators defined in this document. If no relevant annotations are present, the `unevaluatedItems` subschema MUST be applied to all locations in the array. If a boolean true value is present from @@ -1966,7 +2046,8 @@ the behavior of `items`. This annotation affects the behavior of Omitting this keyword has the same assertion behavior as an empty schema. -### unevaluatedProperties +### unevaluatedProperties {#unevaluatedproperties} + The value of `unevaluatedProperties` MUST be a valid JSON Schema. The behavior of this keyword depends on the annotation results of adjacent @@ -1975,9 +2056,8 @@ annotations from `properties`, `patternProperties`, `contains`, and `additionalProperties`, which can come from those keywords when they are adjacent to the `unevaluatedProperties` keyword. Those four annotations, as well as `unevaluatedProperties`, can also result from any and all adjacent [in-place -applicator](#102-keywords-for-applying-subschemas-in-place) keywords. This -includes but is not limited to the in-place applicators defined in this -document. +applicator](#in-place) keywords. This includes but is not limited to the +in-place applicators defined in this document. Validation with `unevaluatedProperties` applies only to the child values of instance names that do not appear in the `properties`, `patternProperties`, @@ -1998,13 +2078,15 @@ validated by this keyword's subschema. This annotation affects the behavior of Omitting this keyword has the same assertion behavior as an empty schema. -## Output Formatting +## Output Formatting {#output} + JSON Schema is defined to be platform-independent. As such, to increase compatibility across platforms, implementations SHOULD conform to a standard validation output format. This section describes the minimum requirements that consumers will need to properly interpret validation results. ### Format + JSON Schema output is defined using the JSON Schema data instance model as described in section 4.2.1. Implementations MAY deviate from this as supported by their specific languages and platforms, however it is RECOMMENDED that the @@ -2012,6 +2094,7 @@ output be convertible to the JSON format defined herein via serialization or other means. ### Output Formats + This specification defines three output formats. See the "Output Structure" section for the requirements of each format. @@ -2028,6 +2111,7 @@ of the "list" or "hierarchical" formats. Implementations SHOULD specify in their documentation which formats they support. ### Minimum Information + Beyond the simplistic "flag" output, additional information is useful to aid in debugging a schema or instance. Each sub-result SHOULD contain the information contained within this section at a minimum. @@ -2038,6 +2122,7 @@ unit. Implementations MAY elect to provide additional information. #### Evaluation path + The evaluation path to the schema object that produced the output unit. The value MUST be expressed as a JSON Pointer, and it MUST include any by-reference applicators such as `$ref` or `$dynamicRef`.[^13] @@ -2055,11 +2140,12 @@ due to the inclusion of these by-reference applicator keywords. The JSON key for this information is "evaluationPath". #### Schema Location + The absolute, dereferenced location of the schema object that produced the -output unit. The value MUST be expressed using the canonical IRI of the -relevant schema resource plus a JSON Pointer fragment that indicates the schema -object that produced the output. It MUST NOT include by-reference applicators -such as `$ref` or `$dynamicRef`.[^14] +output unit. The value MUST be expressed using the canonical IRI of the relevant +schema resource plus a JSON Pointer fragment that indicates the schema object +that produced the output. It MUST NOT include by-reference applicators such as +`$ref` or `$dynamicRef`.[^14] [^14]: Note that "absolute" here is in the sense of "absolute filesystem path" (meaning the complete location) rather than the "absolute-IRI" terminology from @@ -2073,12 +2159,14 @@ https://example.com/schemas/common#/$defs/allOf/1 The JSON key for this information is "schemaLocation". #### Instance Location + The location of the JSON value within the instance being validated. The value MUST be expressed as a JSON Pointer. The JSON key for this information is "instanceLocation". #### Errors + Any errors produced by the validation. This property MUST NOT be included if the validation was successful. The value for this property MUST be an object where the keys are the names of keywords and the values are the error message produced @@ -2098,6 +2186,7 @@ Implementations will need to provide this. The JSON key for this information is "errors". #### Annotations + Any annotations produced by the evaluation. This property MUST NOT be included if the validation result of the containing subschema was unsuccessful. @@ -2110,6 +2199,7 @@ list of keywords, whereas `title` produces a string). The JSON key for this information is "annotations". #### Dropped Annotations + Any annotations produced and subsequently dropped by the evaluation due to an unsuccessful validation result of the containing subschema. This property MAY be included if the validation result of the containing subschema was unsuccessful. @@ -2129,6 +2219,7 @@ list of keywords, whereas `title` produces a string). The JSON key for this information is "droppedAnnotations". #### Results from Subschemas + Evaluation results generated by applying a subschema to the instance or a child of the instance. Keywords which have multiple subschemas (e.g. `anyOf`) will generally generate an output unit for each subschema. In order to accommodate @@ -2225,15 +2316,15 @@ Passing instance The failing instance will produce the following errors: - The value at `/foo` evaluated at `/properties/foo/allOf/0` by following the -path `/properties/foo/allOf/0` by the `required` keyword is missing the property -`unspecified-prop`. + path `/properties/foo/allOf/0` by the `required` keyword is missing the + property `unspecified-prop`. - The value at `/foo/foo-prop` evaluated at -`/properties/foo/allOf/1/properties/foo-prop` by following the path -`/properties/foo/allOf/1/properties/foo-prop` by the `const` keyword is not the -constant value 1. + `/properties/foo/allOf/1/properties/foo-prop` by following the path + `/properties/foo/allOf/1/properties/foo-prop` by the `const` keyword is not + the constant value 1. - The value at `/bar/bar-prop` evaluated at `/$defs/bar/properties/bar-prop` by -following the path `/properties/bar/$ref/properties/bar-prop` by the `type` -keyword is not a number.[^16][^17] + following the path `/properties/bar/$ref/properties/bar-prop` by the `type` + keyword is not a number.[^16][^17] [^16]: `minimum` doesn't produce an error because it only operates on instances that are numbers. @@ -2246,28 +2337,29 @@ allows their users to craft their own messages. The passing instance will produce the following annotations: - The keyword `title` evaluated at `` by following the path `` will produce -`"root"`. + `"root"`. - The keyword `properties` evaluated at `` by following the path `` will produce -`["foo", "bar"]`. + `["foo", "bar"]`. - The keyword `title` evaluated at `/properties/foo` by following the path -`/properties/foo` will produce `"foo-title"`. + `/properties/foo` will produce `"foo-title"`. - The keyword `properties` evaluated at `/properties/foo/allOf/1` by following -the path `/properties/foo/allOf/1` will produce `["foo-prop"]`. + the path `/properties/foo/allOf/1` will produce `["foo-prop"]`. - The keyword `additionalProperties` evaluated at `/properties/foo/allOf/1` by -following the path `/properties/foo/allOf/1` will produce -`["unspecified-prop"]`. + following the path `/properties/foo/allOf/1` will produce + `["unspecified-prop"]`. - The keyword `title` evaluated at `/properties/foo/allOf/1/properties/foo-prop` -by following the path `/properties/foo/allOf/1/properties/foo-prop` will produce -`"foo-prop-title"`. + by following the path `/properties/foo/allOf/1/properties/foo-prop` will + produce `"foo-prop-title"`. - The keyword `title` evaluated at `/$defs/bar` by following the path -`/properties/bar/$ref` will produce `"bar-title"`. + `/properties/bar/$ref` will produce `"bar-title"`. - The keyword `properties` evaluated at `/$defs/bar` by following the path -`/properties/var/$ref` will produce `["bar-prop"]`. + `/properties/var/$ref` will produce `["bar-prop"]`. - The keyword `title` evaluated at `/$defs/bar/properties/bar-prop` by following -the path `/properties/bar/$ref/properties/bar-prop` will produce -`"bar-prop-title"`. + the path `/properties/bar/$ref/properties/bar-prop` will produce + `"bar-prop-title"`. #### Flag + In the simplest case, merely the boolean result for the "valid" valid property needs to be fulfilled. For this format, all other information is explicitly omitted. @@ -2285,6 +2377,7 @@ keyword contains five subschemas, and the second one passes, there is no need to check the other three. The logic can simply return with success. #### List + The "List" structure is a flat list of output units contained within a root output unit. @@ -2402,6 +2495,7 @@ Passing results ``` #### Hierarchical + The "Hierarchical" structure is a tree structure that follows the evaluation path during the validation process. Typically, it will resemble the schema as if all referenced schemas were inlined in place of their associated by-reference @@ -2599,10 +2693,12 @@ Passing results (annotations) ``` #### Output validation schemas + For convenience, JSON Schema has been provided to validate output generated by implementations. Its IRI is: . -## Security Considerations {#security-considerations} +## Security Considerations {#security} + Both schemas and instances are JSON values. As such, all security considerations defined in [RFC 8259](#rfc8259) apply. @@ -2633,6 +2729,7 @@ action based on `$comment` contents. ## IANA Considerations ### application/schema+json + The proposed MIME media type for JSON Schema is defined as follows: Type name:: application @@ -2644,15 +2741,15 @@ Required parameters:: N/A Encoding considerations:: Encoding considerations are identical to those specified for the `application/json` media type. See [JSON](#rfc8259). -Security considerations:: See {{security-considerations}} above. +Security considerations:: See {{security}} above. -Interoperability considerations:: See Sections -[6.2](#62-programming-language-independence), [6.3](#63-mathematical-integers), -and [6.4](#64-regular-expressions) above. +Interoperability considerations:: See Sections [6.2](#language), +[6.3](#integers), and [6.4](#regex) above. -Fragment identifier considerations:: See {{fragment-identifiers}} +Fragment identifier considerations:: See {{fragments}} ### application/schema-instance+json + The proposed MIME media type for JSON Schema Instances that require a JSON Schema-specific media type is defined as follows: @@ -2665,107 +2762,125 @@ Required parameters:: N/A Encoding considerations:: Encoding considerations are identical to those specified for the `application/json` media type. See [JSON](#rfc8259). -Security considerations:: See {{security-considerations}} above. +Security considerations:: See {{security}} above. -Interoperability considerations:: See Sections -[6.2](#62-programming-language-independence), [6.3](#63-mathematical-integers), -and [6.4](#64-regular-expressions) above. +Interoperability considerations:: See Sections [6.2](#language), +[6.3](#integers), and [6.4](#regex) above. -Fragment identifier considerations:: See {{fragment-identifiers}} +Fragment identifier considerations:: See {{fragments}} ## References ### Normative References -#### [RFC2119] +#### [RFC2119] {#rfc2119} + Bradner, S., "Key words for use in RFCs to Indicate Requirement Levels", BCP 14, RFC 2119, DOI 10.17487/RFC2119, March 1997, <>. -#### [RFC3986] +#### [RFC3986] {#rfc3986} + Berners-Lee, T., Fielding, R., and L. Masinter, "Uniform Resource Identifier (URI): Generic Syntax", STD 66, RFC 3986, DOI 10.17487/RFC3986, January 2005, <>. -#### [RFC3987] +#### [RFC3987] {#rfc3987} + Duerst, M. and M. Suignard, "Internationalized Resource Identifiers (IRIs)", RFC 3987, DOI 10.17487/RFC3987, January 2005, <>. -#### [RFC6839] +#### [RFC6839] {#rfc6839} + Hansen, T. and A. Melnikov, "Additional Media Type Structured Syntax Suffixes", RFC 6839, DOI 10.17487/RFC6839, January 2013, <>. -#### [RFC6901] +#### [RFC6901] {#rfc6901} + Bryan, P., Ed., Zyp, K., and M. Nottingham, Ed., "JavaScript Object Notation (JSON) Pointer", RFC 6901, DOI 10.17487/RFC6901, April 2013, <>. -#### [RFC8259] +#### [RFC8259] {#rfc8259} + Bray, T., Ed., "The JavaScript Object Notation (JSON) Data Interchange Format", STD 90, RFC 8259, DOI 10.17487/RFC8259, December 2017, <>. -#### [W3C.REC-ldp-20150226] +#### [W3C.REC-ldp-20150226] {#w3crec-ldp-20150226} + Malhotra, A., Ed., Arwe, J., Ed., and S. Speicher, Ed., "Linked Data Platform 1.0", W3C REC REC-ldp-20150226, W3C REC-ldp-20150226, 26 February 2015, <>. -#### [ecma262] +#### [ecma262] {#ecma262} + "ECMA-262, 11th edition specification", June 2020, <>. ### Informative References -#### [RFC6596] +#### [RFC6596] {#rfc6596} + Ohye, M. and J. Kupke, "The Canonical Link Relation", RFC 6596, DOI 10.17487/RFC6596, April 2012, <>. -#### [RFC7049] +#### [RFC7049] {#rfc7049} + Bormann, C. and P. Hoffman, "Concise Binary Object Representation (CBOR)", RFC 7049, DOI 10.17487/RFC7049, October 2013, <>. -#### [RFC7231] +#### [RFC7231] {#rfc7231} + Fielding, R., Ed. and J. Reschke, Ed., "Hypertext Transfer Protocol (HTTP/1.1): Semantics and Content", RFC 7231, DOI 10.17487/RFC7231, June 2014, <>. -#### [RFC8288] +#### [RFC8288] {#rfc8288} + Nottingham, M., "Web Linking", RFC 8288, DOI 10.17487/RFC8288, October 2017, <>. #### [W3C.WD-fragid-best-practices-20121025] +{#w3cwd-fragid-best-practices-20121025} + Tennison, J., Ed., "Best Practices for Fragment Identifiers and Media Type Definitions", W3C WD WD-fragid-best-practices-20121025, W3C WD-fragid-best-practices-20121025, 25 October 2012, <>. -#### [W3C.REC-xptr-framework-20030325] +#### [W3C.REC-xptr-framework-20030325] {#w3crec-xptr-framework-20030325} + Maler, E., Ed., Marsh, J., Ed., Walsh, N., Ed., and P. Grosso, Ed., "XPointer Framework", W3C REC REC-xptr-framework-20030325, W3C REC-xptr-framework-20030325, 25 March 2003, <>. -#### [json-schema-validation] +#### [json-schema-validation] {#json-schema-validation} + Wright, A., Andrews, H., and B. Hutton, "JSON Schema Validation: A Vocabulary for Structural Validation of JSON", Work in Progress, Internet-Draft, draft-bhutton-json-schema-validation-01, June 2022, <>. -#### [json-hyper-schema] +#### [json-hyper-schema] {#json-hyper-schema} + Andrews, H. and A. Wright, "JSON Hyper-Schema: A Vocabulary for Hypermedia Annotation of JSON", Work in Progress, Internet-Draft, draft-handrews-json-schema-hyperschema-02, November 2017, <>. -#### [xml-names] +#### [xml-names] {#xml-names} + Bray, T., Ed., Hollander, D., Ed., Layman, A., Ed., and R. Tobin, Ed., "Namespaces in XML 1.1 (Second Edition)", August 2006, <>. -## [Appendix] Schema identification examples +## [Appendix] Schema identification examples {#idexamples} + Consider the following schema, which shows `$id` being used to identify both the root schema and various subschemas, and `$anchor` being used to define plain name fragment identifiers. @@ -2794,39 +2909,46 @@ name fragment identifiers. The schemas at the following IRI-encoded [JSON Pointers](#rfc6901) (relative to the root schema) have the following base IRIs, and are identifiable by any -listed IRI in accordance with {{fragment-identifiers}} and -#section(json-pointer-embedded) above. +listed IRI in accordance with {{fragments}} and {{embedded}} above. `#` (document root): canonical (and base) IRI: `https://example.com/root.json` -canonical resource IRI plus pointer fragment: `https://example.com/root.json#` +- canonical resource IRI plus pointer fragment: `https://example.com/root.json#` -`#/$defs/A`: base IRI: `https://example.com/root.json` canonical resource IRI -plus plain fragment: `https://example.com/root.json#foo` canonical resource IRI -plus pointer fragment: `https://example.com/root.json#/$defs/A` +`#/$defs/A`: base IRI: `https://example.com/root.json` +- canonical resource IRI plus plain fragment: + `https://example.com/root.json#foo` +- canonical resource IRI plus pointer fragment: + `https://example.com/root.json#/$defs/A` `#/$defs/B`: canonical (and base) `IRI: https://example.com/other.json` -canonical resource IRI plus pointer fragment: `https://example.com/other.json#` -base IRI of enclosing (root.json) resource plus fragment: -`https://example.com/root.json#/$defs/B` - -`#/$defs/B/$defs/X`: base IRI: `https://example.com/other.json` canonical -resource IRI plus plain fragment: `https://example.com/other.json#bar` canonical -resource IRI plus pointer fragment: `https://example.com/other.json#/$defs/X` -base IRI of enclosing (root.json) resource plus fragment: -`https://example.com/root.json#/$defs/B/$defs/X` +- canonical resource IRI plus pointer fragment: + `https://example.com/other.json#` +- base IRI of enclosing (root.json) resource plus fragment: + `https://example.com/root.json#/$defs/B` + +`#/$defs/B/$defs/X`: base IRI: `https://example.com/other.json` +- canonical resource IRI plus plain fragment: + `https://example.com/other.json#bar` +- canonical resource IRI plus pointer fragment: + `https://example.com/other.json#/$defs/X` +- base IRI of enclosing (root.json) resource plus fragment: + `https://example.com/root.json#/$defs/B/$defs/X` `#/$defs/B/$defs/Y`: canonical (and base) IRI: -`https://example.com/t/inner.json` canonical IRI plus plain fragment: -`https://example.com/t/inner.json#bar` canonical IRI plus pointer fragment: -`https://example.com/t/inner.json#` base IRI of enclosing (other.json) resource -plus fragment: `https://example.com/other.json#/$defs/Y` base IRI of enclosing -(root.json) resource plus fragment: -`https://example.com/root.json#/$defs/B/$defs/Y` +`https://example.com/t/inner.json` +- canonical IRI plus plain fragment: `https://example.com/t/inner.json#bar` +- canonical IRI plus pointer fragment: `https://example.com/t/inner.json#` +- base IRI of enclosing (other.json) resource plus fragment: + `https://example.com/other.json#/$defs/Y` +- base IRI of enclosing (root.json) resource plus fragment: + `https://example.com/root.json#/$defs/B/$defs/Y` `#/$defs/C`: canonical (and base) IRI: -`urn:uuid:ee564b8a-7a87-4125-8c96-e9f123d6766f` canonical IRI plus pointer -fragment: `urn:uuid:ee564b8a-7a87-4125-8c96-e9f123d6766f#` base IRI of enclosing -(root.json) resource plus fragment: `https://example.com/root.json#/$defs/C` +`urn:uuid:ee564b8a-7a87-4125-8c96-e9f123d6766f` +- canonical IRI plus pointer fragment: + `urn:uuid:ee564b8a-7a87-4125-8c96-e9f123d6766f#` +- base IRI of enclosing (root.json) resource plus fragment: + `https://example.com/root.json#/$defs/C` Note: The fragment part of the IRI does not make it canonical or non-canonical, rather, the base IRI used (as part of the full IRI with any fragment) is what @@ -2834,14 +2956,16 @@ determines the canonical nature of the resulting full IRI.[^18] [^18]: Multiple "canonical" IRIs? We Acknowledge this is potentially confusing, and direct you to read the CREF located in the [JSON Pointer fragments and -embedded schema resources](#json-pointer-embedded) section for further comments. +embedded schema resources](#embedded) section for further comments. ## [Appendix] Manipulating schema documents and references + Various tools have been created to rearrange schema documents based on how and where references (`$ref`) appear. This appendix discusses which use cases and actions are compliant with this specification. ### Bundling schema resources into a single document + A set of schema resources intended for use together can be organized with each in its own schema document, all in the same schema document, or any granularity of document grouping in between. @@ -2864,6 +2988,7 @@ schemas under `$defs` do not affect behavior, assuming they are each unique, as they do not appear in the canonical IRIs for the embedded resources. ### Reference removal is not always safe + Attempting to remove all references and produce a single schema document does not, in all cases, produce a schema with identical behavior to the original form. @@ -2875,7 +3000,8 @@ scope of this specification to determine or provide a set of safe `$ref` removal transformations, as they depend not only on the schema structure but also on the intended usage. -## [Appendix] Example of recursive schema extension +## [Appendix] Example of recursive schema extension {#recursive-example} + Consider the following two schemas describing a simple recursive tree structure, where each node in the tree can have a "data" field of any type. The first schema allows and ignores other instance properties. The second is more strict @@ -2973,7 +3099,8 @@ any sort of correlation in JSON structure. ## [Appendix] Working with vocabularies -### Best practices for vocabulary and meta-schema authors +### Best practices for vocabulary and meta-schema authors {#vocab-practices} + Vocabulary authors should take care to avoid keyword name collisions if the vocabulary is intended for broad use, and potentially combined with other vocabularies. JSON Schema does not provide any formal namespacing system, but @@ -3000,8 +3127,8 @@ forbid additional keywords, and MUST not forbid any keywords from the Core vocabulary. It is recommended that meta-schema authors reference each vocabulary's -meta-schema using the [`allOf`](#10211-allof) keyword, although other mechanisms -for constructing the meta-schema may be appropriate for certain use cases. +meta-schema using the [`allOf`](#allof) keyword, although other mechanisms for +constructing the meta-schema may be appropriate for certain use cases. The recursive nature of meta-schemas makes the `$dynamicAnchor` and `$dynamicRef` keywords particularly useful for extending existing meta-schemas, @@ -3021,7 +3148,8 @@ resulting behavior is undefined. Meta-schemas intended for local use, with no need to test for vocabulary support in arbitrary implementations, can safely omit `$vocabulary` entirely. -### Example meta-schema with vocabulary declarations +### Example meta-schema with vocabulary declarations {#example-meta-schema} + This meta-schema explicitly declares both the Core and Applicator vocabularies, together with an extension vocabulary, and combines their meta-schemas with an `allOf`. The extension vocabulary's meta-schema, which describes only the @@ -3114,6 +3242,7 @@ annotation, as explained in the [Validation specification](#json-schema-validation). ## [Appendix] References and generative use cases + While the presence of references is expected to be transparent to validation results, generative use cases such as code generators and UI renderers often consider references to be semantically significant. @@ -3163,6 +3292,7 @@ This style of usage requires the annotation to be in the same object as the reference, which must be recognizable as a reference. ## [Appendix] Acknowledgments + Thanks to Gary Court, Francis Galiegue, Kris Zyp, Geraint Luff, and Henry Andrews for their work on the initial drafts of JSON Schema. @@ -3172,6 +3302,7 @@ Sturgeon, Shawn Silverman, and Karen Etheridge for their submissions and patches to the document. ## [Appendix] Change Log[^19] + [^19]: This section to be removed before leaving Internet-Draft status. ### draft-bhutton-json-schema-next @@ -3182,7 +3313,7 @@ to the document. ### draft-bhutton-json-schema-01 - Improve and clarify the `type`, `contains`, `unevaluatedProperties`, and -`unevaluatedItems` keyword explanations + `unevaluatedItems` keyword explanations - Clarify various aspects of "canonical URIs" - Comment on ambiguity around annotations and `additionalProperties` - Clarify Vocabularies need not be formally defined @@ -3194,7 +3325,7 @@ to the document. - Array-value `items` functionality is now `prefixItems` - `items` subsumes the old function of `additionalItems` - `contains` annotation behavior, and `contains` and `unevaluatedItems` -interactions now specified + interactions now specified - Rename $recursive* to $dynamic*, with behavior modification - $dynamicAnchor defines a fragment like $anchor - $dynamic* (previously $recursive) no longer use runtime base URI determination @@ -3204,33 +3335,33 @@ interactions now specified - Remove media type parameters - Specify Unknown keywords are collected as annotations - Moved `unevaluatedItems` and `unevaluatedProperties` from core into their own -vocabulary + vocabulary ### draft-handrews-json-schema-02 - Update to RFC 8259 for JSON specification - Moved `definitions` from the Validation specification here as `$defs` - Moved applicator keywords from the Validation specification as their own -vocabulary + vocabulary - Moved the schema form of `dependencies` from the Validation specification as -`dependentSchemas` + `dependentSchemas` - Formalized annotation collection - Specified recommended output formats - Defined keyword interactions in terms of annotation and assertion results - Added `unevaluatedProperties` and `unevaluatedItems` - Define `$ref` behavior in terms of the assertion, applicator, and annotation -model + model - Allow keywords adjacent to `$ref` - Note undefined behavior for `$ref` targets involving unknown keywords - Add recursive referencing, primarily for meta-schema extension - Add the concept of formal vocabularies, and how they can be recognized through -meta-schemas + meta-schemas - Additional guidance on initial base URIs beyond network retrieval - Allow "schema" media type parameter for `application/schema+json` - Better explanation of media type parameters and the HTTP Accept header - Use `$id` to establish canonical and base absolute-URIs only, no fragments - Replace plain-name-fragment-only form of `$id` with `$anchor` - Clarified that the behavior of JSON Pointers across `$id` boundary is -unreliable + unreliable ### draft-handrews-json-schema-01 - This draft is purely a clarification with no functional changes @@ -3238,18 +3369,18 @@ unreliable - Clarified $id by use cases - Exhaustive schema identification examples - Replaced "external referencing" with how and when an implementation might know -of a schema from another document + of a schema from another document - Replaced "internal referencing" with how an implementation should recognized -schema identifiers during parsing + schema identifiers during parsing - Dereferencing the former "internal" or "external" references is always the -same process + same process - Minor formatting improvements ### draft-handrews-json-schema-00 - Make the concept of a schema keyword vocabulary more clear - Note that the concept of "integer" is from a vocabulary, not the data model - Classify keywords as assertions or annotations and describe their general -behavior + behavior - Explain the boolean schemas in terms of generalized assertions - Reserve `$comment` for non-user-visible notes about the schema - Wording improvements around `$id` and fragments @@ -3264,7 +3395,7 @@ behavior - Changed `id` to `$id`; all core keywords prefixed with "$" - Clarify and formalize fragments for `application/schema+json` - Note applicability to formats such as CBOR that can be represented in the JSON -data model + data model ### draft-wright-json-schema-00 - Updated references to JSON diff --git a/jsonschema-validation.md b/jsonschema-validation.md index 60ead15a..3d5ed61f 100644 --- a/jsonschema-validation.md +++ b/jsonschema-validation.md @@ -1,6 +1,7 @@ # JSON Schema Validation: A Vocabulary for Structural Validation of JSON ## Abstract + JSON Schema (application/schema+json) has several purposes, one of which is JSON instance validation. This document specifies a vocabulary for JSON Schema to describe the meaning of JSON documents, provide hints for user interfaces @@ -8,6 +9,7 @@ working with JSON data, and to make assertions about what a valid document must look like. ## Note to Readers + The issues list for this draft can be found at . @@ -19,6 +21,7 @@ the homepage, or email the document editors. ## Table of Contents ## Introduction + JSON Schema can be used to require that a given JSON document (an instance) satisfies a certain number of criteria. These criteria are asserted by using keywords described in this specification. In addition, a set of keywords is also @@ -40,6 +43,7 @@ Elements in an array value are said to be unique if no two elements of this array are [equal](#json-schema). ## Overview + JSON Schema validation asserts constraints on the structure of instance data. An instance location that satisfies all asserted constraints is then annotated with any keywords that contain non-assertion information, such as descriptive @@ -53,31 +57,34 @@ document-wide validation process. This specification defines a set of assertion keywords, as well as a small vocabulary of metadata keywords that can be used to annotate the JSON instance -with useful information. The {{format-vocabulary}} keyword is intended -primarily as an annotation, but can optionally be used as an assertion. The -{{content-vocabulary}} keywords +with useful information. The {{format}} keyword is intended primarily as an +annotation, but can optionally be used as an assertion. The {{content}} keywords are annotations for working with documents embedded as JSON strings. ## Interoperability Considerations ### Validation of String Instances + It should be noted that the nul character (\u0000) is valid in a JSON string. An instance to validate may contain a string value with this character, regardless of the ability of the underlying programming language to deal with such data. ### Validation of Numeric Instances + The JSON specification allows numbers with arbitrary precision, and JSON Schema does not add any such bounds. This means that numeric instances processed by JSON Schema can be arbitrarily large and/or have an arbitrarily long decimal part, regardless of the ability of the underlying programming language to deal with such data. -### Regular Expressions +### Regular Expressions {#regexinterop} + Keywords that use regular expressions, or constrain the instance value to be a regular expression, are subject to the interoperability considerations for regular expressions in the [JSON Schema Core](#json-schema) specification. -## Meta-Schema +## Meta-Schema {#meta-schema} + The current IRI for the default JSON Schema dialect meta-schema is `https://json-schema.org/draft/next/schema`. For schema author convenience, this meta-schema describes a dialect consisting of all vocabularies defined in this @@ -93,6 +100,7 @@ after this specification draft and before the next to indicate the same syntax and semantics as those listed here. ## A Vocabulary for Structural Validation + Validation keywords in a schema impose requirements for successful validation of an instance. These keywords are all assertions without any annotation behavior. @@ -105,9 +113,10 @@ The current IRI for this vocabulary, known as the Validation vocabulary, is: The current IRI for the corresponding meta-schema is: `https://json-schema.org/draft/next/meta/validation`. -### Validation Keywords for Any Instance Type +### Validation Keywords for Any Instance Type {#general} #### type + The value of this keyword MUST be either a string or an array. If it is an array, elements of the array MUST be strings and MUST be unique. @@ -120,7 +129,8 @@ its type matches the type represented by the value of the string. If the value of "type" is an array, then an instance validates successfully if its type matches any of the types indicated by the strings in the array. -#### enum +#### enum {#enum} + The value of this keyword MUST be an array. This array SHOULD have at least one element. Elements in the array SHOULD be unique. @@ -130,23 +140,26 @@ one of the elements in this keyword's array value. Elements in the array might be of any type, including null. #### const + The value of this keyword MAY be of any type, including null. -Use of this keyword is functionally equivalent to an [`enum`](#612-enum) with a +Use of this keyword is functionally equivalent to an [`enum`](#enum) with a single value. An instance validates successfully against this keyword if its value is equal to the value of the keyword. -### Validation Keywords for Numeric Instances (number and integer) +### Validation Keywords for Numeric Instances (number and integer) {#numeric} #### multipleOf + The value of `multipleOf` MUST be a number, strictly greater than 0. A numeric instance is valid only if division by this keyword's value results in an integer. #### maximum + The value of `maximum` MUST be a number, representing an inclusive upper limit for a numeric instance. @@ -154,6 +167,7 @@ If the instance is a number, then this keyword validates only if the instance is less than or exactly equal to `maximum`. #### exclusiveMaximum + The value of `exclusiveMaximum` MUST be a number, representing an exclusive upper limit for a numeric instance. @@ -161,6 +175,7 @@ If the instance is a number, then the instance is valid only if it has a value strictly less than (not equal to) `exclusiveMaximum`. #### minimum + The value of `minimum` MUST be a number, representing an inclusive lower limit for a numeric instance. @@ -168,15 +183,17 @@ If the instance is a number, then this keyword validates only if the instance is greater than or exactly equal to `minimum`. #### exclusiveMinimum + The value of `exclusiveMinimum` MUST be a number, representing an exclusive lower limit for a numeric instance. If the instance is a number, then the instance is valid only if it has a value strictly greater than (not equal to) `exclusiveMinimum`. -### Validation Keywords for Strings +### Validation Keywords for Strings {#string} #### maxLength + The value of this keyword MUST be a non-negative integer. A string instance is valid against this keyword if its length is less than, or @@ -186,6 +203,7 @@ The length of a string instance is defined as the number of its characters as defined by [RFC 8259](#rfc8259). #### minLength + The value of this keyword MUST be a non-negative integer. A string instance is valid against this keyword if its length is greater than, @@ -196,7 +214,8 @@ defined by [RFC 8259](#rfc8259). Omitting this keyword has the same behavior as a value of 0. -#### pattern +#### pattern {#pattern} + The value of this keyword MUST be a string. This string SHOULD be a valid regular expression, according to the ECMA-262 regular expression dialect. @@ -206,12 +225,14 @@ instance successfully. Recall: regular expressions are not implicitly anchored. ### Validation Keywords for Arrays #### maxItems + The value of this keyword MUST be a non-negative integer. An array instance is valid against `maxItems` if its size is less than, or equal to, the value of this keyword. #### minItems + The value of this keyword MUST be a non-negative integer. An array instance is valid against `minItems` if its size is greater than, or @@ -220,6 +241,7 @@ equal to, the value of this keyword. Omitting this keyword has the same behavior as a value of 0. #### uniqueItems + The value of this keyword MUST be a boolean. If this keyword has boolean value false, the instance validates successfully. If @@ -231,12 +253,14 @@ Omitting this keyword has the same behavior as a value of false. ### Validation Keywords for Objects #### maxProperties + The value of this keyword MUST be a non-negative integer. An object instance is valid against `maxProperties` if its number of properties is less than, or equal to, the value of this keyword. #### minProperties + The value of this keyword MUST be a non-negative integer. An object instance is valid against `minProperties` if its number of properties @@ -245,6 +269,7 @@ is greater than, or equal to, the value of this keyword. Omitting this keyword has the same behavior as a value of 0. #### required + The value of this keyword MUST be an array. Elements of this array, if any, MUST be strings, and MUST be unique. @@ -254,6 +279,7 @@ the name of a property in the instance. Omitting this keyword has the same behavior as an empty array. #### dependentRequired + The value of this keyword MUST be an object. Properties in this object, if any, MUST be arrays. Elements in each array, if any, MUST be strings, and MUST be unique. @@ -268,9 +294,10 @@ the name of a property in the instance. Omitting this keyword has the same behavior as an empty object. -## Vocabularies for Semantic Content With format {#format-vocabulary} +## Vocabularies for Semantic Content With format {#format} ### Foreword + Structural validation alone may be insufficient to allow an application to correctly utilize certain values. The `format` annotation keyword is defined to allow schema authors to convey semantic information for a fixed subset of values @@ -311,12 +338,13 @@ functionally equivalent to specifying only the Format-Assertion vocabulary since its requirements are a superset of the Format-Annotation vocabulary. ### Implementation Requirements + The `format` keyword functions as defined by the vocabulary which is referenced. -#### Format-Annotation Vocabulary -The value of format MUST be collected as an annotation, if the implementation -supports annotation collection. This enables application-level validation when -schema validation is unavailable or inadequate. +#### Format-Annotation Vocabulary The value of format MUST be collected as an +annotation, if the implementation supports annotation collection. This enables +application-level validation when schema validation is unavailable or +inadequate. Implementations MAY still treat `format` as an assertion in addition to an annotation and attempt to validate the value's conformance to the specified @@ -332,9 +360,9 @@ full validation support when the Format-Assertion vocabulary is not specified. When the implementation is configured for assertion behavior, it: - SHOULD provide an implementation-specific best effort validation for each -format attribute defined below; + format attribute defined below; - MAY choose to implement validation of any or all format attributes as a no-op -by always producing a validation result of true;[^3] + by always producing a validation result of true;[^3] [^3]: This matches the current reality of implementations, which provide widely varying levels of validation, including no validation at all, for some or all @@ -343,6 +371,7 @@ annotation behavior and performing semantic validation in the application, which is the recommended best practice. #### Format-Assertion Vocabulary + When the Format-Assertion vocabulary is declared with a value of true, implementations MUST provide full validation support for all of the formats defined by this specificaion. Implementations that cannot provide full @@ -350,12 +379,12 @@ validation support MUST refuse to process the schema. An implementation that supports the Format-Assertion vocabulary: - MUST still collect `format` as an annotation if the implementation supports -annotation collection; + annotation collection; - MUST evaluate `format` as an assertion; - MUST implement syntactic validation for all format attributes defined in this -specification, and for any additional format attributes that it recognizes, such -that there exist possible instance values of the correct type that will fail -validation. The requirement for minimal validation of format attributes is + specification, and for any additional format attributes that it recognizes, +such that there exist possible instance values of the correct type that will +fail validation. The requirement for minimal validation of format attributes is intentionally vague and permissive, due to the complexity involved in many of the attributes. Note in particular that the requirement is limited to syntactic checking; it is not to be expected that an implementation would send an email, @@ -375,7 +404,7 @@ It is RECOMMENDED that implementations use a common parsing library for each format, or a well-known regular expression. Implementations SHOULD clearly document how and to what degree each format attribute is validated. -The [standard core and validation meta-schema](#5-meta-schema) includes this +The [standard core and validation meta-schema](#meta-schema) includes this vocabulary in its `$vocabulary` keyword with a value of false, since by default implementations are not required to support this keyword as an assertion. Supporting the format vocabulary with a value of true is understood to greatly @@ -383,6 +412,7 @@ increase code size and in some cases execution time, and will not be appropriate for all implementations. #### Custom format attributes + Implementations MAY support custom format attributes. Save for agreement between parties, schema authors SHALL NOT expect a peer implementation to support such custom format attributes. An implementation MUST NOT fail to collect unknown @@ -398,6 +428,7 @@ desired. ### Defined Formats #### Dates, Times, and Duration + These attributes apply to string instances. Date and time format names are derived from [RFC 3339, section 5.6](#rfc3339). @@ -408,13 +439,13 @@ Implementations supporting formats SHOULD implement support for the following attributes: - *date-time:* A string instance is valid against this attribute if it is a -valid representation according to the "date-time" ABNF rule (referenced above) + valid representation according to the "date-time" ABNF rule (referenced above) - *date:* A string instance is valid against this attribute if it is a valid -representation according to the "full-date" ABNF rule (referenced above) + representation according to the "full-date" ABNF rule (referenced above) - *time:* A string instance is valid against this attribute if it is a valid -representation according to the "full-time" ABNF rule (referenced above) + representation according to the "full-time" ABNF rule (referenced above) - *duration:* A string instance is valid against this attribute if it is a valid -representation according to the "duration" ABNF rule (referenced above) + representation according to the "duration" ABNF rule (referenced above) Implementations MAY support additional attributes using the other format names defined anywhere in that RFC. If "full-date" or "full-time" are implemented, the @@ -430,6 +461,7 @@ implementation requirements will become more flexible in general, or these will likely either be promoted to fully specified attributes or dropped. #### Email Addresses + These attributes apply to string instances. A string instance is valid against these attributes if it is a valid Internet @@ -437,48 +469,49 @@ email address as follows: - *email:* As defined by the "Mailbox" ABNF rule in [RFC 5321, section 4.1.2](#rfc5321). - *idn-email:* As defined by the extended "Mailbox" ABNF rule in [RFC 6531, -section 3.3](#rfc6531). Note that all strings valid against the "email" -attribute are also valid against the "idn-email" attribute. + section 3.3](#rfc6531). Note that all strings valid against the "email" + attribute are also valid against the "idn-email" attribute. #### Hostnames + These attributes apply to string instances. A string instance is valid against these attributes if it is a valid representation for an Internet hostname as follows: - *hostname:* As defined by [RFC 1123, section 2.1](#rfc1123), including host -names produced using the Punycode algorithm specified in [RFC 5891, section -4.4](#rfc5891). + names produced using the Punycode algorithm specified in [RFC 5891, section + 4.4](#rfc5891). - *idn-hostname:* As defined by either RFC 1123 as for hostname, or an -internationalized hostname as defined by [RFC 5890, section 2.3.2.3](#rfc5890). -Note that all strings valid against the "hostname" attribute are also valid -against the "idn-hostname" attribute. + internationalized hostname as defined by [RFC 5890, section + 2.3.2.3](#rfc5890). Note that all strings valid against the "hostname" + attribute are also valid against the "idn-hostname" attribute. #### IP Addresses + These attributes apply to string instances. A string instance is valid against these attributes if it is a valid representation of an IP address as follows: - *ipv4:* An IPv4 address according to the "dotted-quad" ABNF syntax as defined -in [RFC 2673, section 3.2](#rfc2673). + in [RFC 2673, section 3.2](#rfc2673). - *ipv6:* An IPv6 address as defined in [RFC 4291, section 2.2](#rfc4291). -#### Resource Identifiers -These attributes apply to string instances. +#### Resource Identifiers These attributes apply to string instances. - *uri:* A string instance is valid against this attribute if it is a valid IRI, -according to [Appendix RFC3987](#rfc3987). + according to [RFC3987](#rfc3987). - *uri-reference:* A string instance is valid against this attribute if it is a -valid URI Reference (either a URI or a relative-reference), according to -[Appendix RFC3986](#rfc3986). + valid URI Reference (either a URI or a relative-reference), according to + [RFC3986](#rfc3986). - *iri:* A string instance is valid against this attribute if it is a valid IRI, -according to [Appendix RFC3987](#rfc3987). + according to [RFC3987](#rfc3987). - *iri-reference:* A string instance is valid against this attribute if it is a -valid IRI Reference (either an IRI or a relative-reference), according to -[Appendix RFC3987](#rfc3987). + valid IRI Reference (either an IRI or a relative-reference), according to + [RFC3987](#rfc3987). - *uuid:* A string instance is valid against this attribute if it is a valid -string representation of a UUID, according to [Appendix RFC4122](#rfc4122). + string representation of a UUID, according to [RFC4122](#rfc4122). Note that all valid URIs are valid IRIs, and all valid URI References are also valid IRI References. @@ -489,38 +522,42 @@ example is "f81d4fae-7dec-11d0-a765-00a0c91e6bf6". For UUIDs as URNs, use the the URI scheme and URN namespace. #### uri-template + This attribute applies to string instances. A string instance is valid against this attribute if it is a valid URI Template -(of any level), according to [Appendix RFC6570](#rfc6570). +(of any level), according to [RFC6570](#rfc6570). Note that URI Templates may be used for IRIs; there is no separate IRI Template specification. #### JSON Pointers + These attributes apply to string instances. - *json-pointer:* A string instance is valid against this attribute if it is a -valid JSON string representation of a JSON Pointer, according to [RFC 6901, -section 5](#rfc6901). + valid JSON string representation of a JSON Pointer, according to [RFC 6901, + section 5](#rfc6901). - *relative-json-pointer:* A string instance is valid against this attribute if -it is a valid [Relative JSON Pointer](#relative-json-pointer). To allow for both -absolute and relative JSON Pointers, use `anyOf` or `oneOf` to indicate support -for either format. + it is a valid [Relative JSON Pointer](#relative-json-pointer). To allow for + both absolute and relative JSON Pointers, use `anyOf` or `oneOf` to indicate + support for either format. #### regex + This attribute applies to string instances. A regular expression, which SHOULD be valid according to the [ECMA-262](#ecma262) regular expression dialect. Implementations that validate formats MUST accept at least the subset of -ECMA-262 defined in the [Regular Expressions](#43-regular-expressions) section -of this specification, and SHOULD accept all valid ECMA-262 expressions. +ECMA-262 defined in {{regexinterop}}), and SHOULD accept all valid ECMA-262 +expressions. -## A Vocabulary for the Contents of String-Encoded Data {#content-vocabulary} +## A Vocabulary for the Contents of String-Encoded Data {#content} ### Foreword + Annotations defined in this section indicate that an instance contains non-JSON data encoded in a JSON string. @@ -540,6 +577,7 @@ The current IRI for the corresponding meta-schema is: `https://json-schema.org/draft/next/meta/content`. ### Implementation Requirements + Due to security and performance concerns, as well as the open-ended nature of possible content types, implementations MUST NOT automatically decode, parse, and/or validate the string contents. Applications are expected to use these @@ -549,6 +587,7 @@ All keywords in this section apply only to strings, and have no effect on other data types. ### contentEncoding + If the instance value is a string, this property defines that the string SHOULD be interpreted as encoded binary data and applications wishing to decode it SHOULD do so using the encoding named by this property. @@ -574,6 +613,7 @@ needed in order to represent the content in a UTF-8 string. The value of this property MUST be a string. ### contentMediaType + If the instance is a string, this property indicates the media type of the contents of the string. If `contentEncoding` is present, this property describes the decoded string. @@ -582,6 +622,7 @@ The value of this property MUST be a string, which MUST be a media type, as defined by [RFC 2046](#rfc2046). ### contentSchema + If the instance is a string, and if `contentMediaType` is present, this property contains a schema which describes the structure of the string. @@ -597,6 +638,7 @@ safe if the schema is an embedded resource with both `$schema` and an absolute-IRI `$id`. ### Example + Here is an example schema, illustrating the use of `contentEncoding` and `contentMediaType`: @@ -662,11 +704,11 @@ structures: first the header, and then the payload. Since the JWT media type ensures that the JWT can be represented in a JSON string, there is no need for further encoding or decoding. -## A Vocabulary for Basic Meta-Data Annotations -These general-purpose annotation keywords provide commonly used information for -documentation and user interface display purposes. They are not intended to form -a comprehensive set of features. Rather, additional vocabularies can be defined -for more complex annotation-based applications. +## A Vocabulary for Basic Meta-Data Annotations These general-purpose annotation +keywords provide commonly used information for documentation and user interface +display purposes. They are not intended to form a comprehensive set of features. +Rather, additional vocabularies can be defined for more complex annotation-based +applications. Meta-schemas that do not use `$vocabulary` SHOULD be considered to require this vocabulary as if its IRI were present with a value of true. @@ -678,6 +720,7 @@ The current IRI for the corresponding meta-schema is: `https://json-schema.org/draft/next/meta/meta-data`. ### title and description + The value of both of these keywords MUST be a string. Both of these keywords can be used to decorate a user interface with information @@ -686,6 +729,7 @@ short, whereas a description will provide explanation about the purpose of the instance described by this schema. ### default + There are no restrictions placed on the value of this keyword. When multiple occurrences of this keyword are applicable to a single sub-instance, implementations SHOULD remove duplicates. @@ -695,6 +739,7 @@ particular schema. It is RECOMMENDED that a default value be valid against the associated schema. ### deprecated + The value of this keyword MUST be a boolean. When multiple occurrences of this keyword are applicable to a single sub-instance, applications SHOULD consider the instance location to be deprecated if any occurrence specifies a true value. @@ -714,6 +759,7 @@ containing array or object is not. Omitting this keyword has the same behavior as a value of false. ### readOnly and writeOnly + The value of these keywords MUST be a boolean. When multiple occurrences of these keywords are applicable to a single sub-instance, the resulting behavior SHOULD be as for a true value if any occurrence specifies a true value, and @@ -748,6 +794,7 @@ they are typed for write-only fields. Omitting these keywords has the same behavior as values of false. ### examples + The value of this keyword MUST be an array. There are no restrictions placed on the values within the array. When multiple occurrences of this keyword are applicable to a single sub-instance, implementations MUST provide a flat array @@ -760,7 +807,8 @@ these values be valid against the associated schema. Implementations MAY use the value(s) of `default`, if present, as an additional example. If `examples` is absent, `default` MAY still be used in this manner. -## Security Considerations +## Security Considerations {#security} + JSON Schema validation defines a vocabulary for JSON Schema core and concerns all the security considerations listed there. @@ -787,102 +835,122 @@ ECMAScript encoded within a JSON string. ### Normative References -#### [RFC2119] +#### [RFC2119] {#rfc2119} + Bradner, S., "Key words for use in RFCs to Indicate Requirement Levels", BCP 14, RFC 2119, DOI 10.17487/RFC2119, March 1997, <>. -#### [RFC1123] +#### [RFC1123] {#rfc1123} + Braden, R., Ed., "Requirements for Internet Hosts - Application and Support", STD 3, RFC 1123, DOI 10.17487/RFC1123, October 1989, <>. -#### [RFC2045] +#### [RFC2045] {#rfc2045} + Freed, N. and N. Borenstein, "Multipurpose Internet Mail Extensions (MIME) Part One: Format of Internet Message Bodies", RFC 2045, DOI 10.17487/RFC2045, November 1996, <>. -#### [RFC2046] +#### [RFC2046] {#rfc2046} + Freed, N. and N. Borenstein, "Multipurpose Internet Mail Extensions (MIME) Part Two: Media Types", RFC 2046, DOI 10.17487/RFC2046, November 1996, <>. -#### [RFC2673] +#### [RFC2673] {#rfc2673} + Crawford, M., "Binary Labels in the Domain Name System", RFC 2673, DOI 10.17487/RFC2673, August 1999, <>. -#### [RFC3339] +#### [RFC3339] {#rfc3339} + Klyne, G. and C. Newman, "Date and Time on the Internet: Timestamps", RFC 3339, DOI 10.17487/RFC3339, July 2002, <>. -#### [RFC3986] +#### [RFC3986] {#rfc3986} + Berners-Lee, T., Fielding, R., and L. Masinter, "Uniform Resource Identifier (URI): Generic Syntax", STD 66, RFC 3986, DOI 10.17487/RFC3986, January 2005, <>. -#### [RFC3987] +#### [RFC3987] {#rfc3987} + Duerst, M. and M. Suignard, "Internationalized Resource Identifiers (IRIs)", RFC 3987, DOI 10.17487/RFC3987, January 2005, <>. -#### [RFC4122] +#### [RFC4122] {#rfc4122} + Leach, P., Mealling, M., and R. Salz, "A Universally Unique IDentifier (UUID) URN Namespace", RFC 4122, DOI 10.17487/RFC4122, July 2005, <>. -#### [RFC4291] +#### [RFC4291] {#rfc4291} + Hinden, R. and S. Deering, "IP Version 6 Addressing Architecture", RFC 4291, DOI 10.17487/RFC4291, February 2006, <>. -#### [RFC4648] +#### [RFC4648] {#rfc4648} + Josefsson, S., "The Base16, Base32, and Base64 Data Encodings", RFC 4648, DOI 10.17487/RFC4648, October 2006, <>. -#### [RFC5321] +#### [RFC5321] {#rfc5321} + Klensin, J., "Simple Mail Transfer Protocol", RFC 5321, DOI 10.17487/RFC5321, October 2008, <>. -#### [RFC5890] +#### [RFC5890] {#rfc5890} + Klensin, J., "Internationalized Domain Names for Applications (IDNA): Definitions and Document Framework", RFC 5890, DOI 10.17487/RFC5890, August 2010, <>. -#### [RFC5891] +#### [RFC5891] {#rfc5891} + Klensin, J., "Internationalized Domain Names in Applications (IDNA): Protocol", RFC 5891, DOI 10.17487/RFC5891, August 2010, <>. -#### [RFC6570] +#### [RFC6570] {#rfc6570} + Gregorio, J., Fielding, R., Hadley, M., Nottingham, M., and D. Orchard, "URI Template", RFC 6570, DOI 10.17487/RFC6570, March 2012, <>. -#### [RFC6531] +#### [RFC6531] {#rfc6531} Yao, J. and W. Mao, "SMTP Extension for Internationalized Email", RFC 6531, DOI 10.17487/RFC6531, February 2012, <>. -#### [RFC6901] +#### [RFC6901] {#rfc6901} + Bryan, P., Ed., Zyp, K., and M. Nottingham, Ed., "JavaScript Object Notation (JSON) Pointer", RFC 6901, DOI 10.17487/RFC6901, April 2013, <>. -#### [RFC8259] +#### [RFC8259] {#rfc8259} + Bray, T., Ed., "The JavaScript Object Notation (JSON) Data Interchange Format", STD 90, RFC 8259, DOI 10.17487/RFC8259, December 2017, <>. -#### [ecma262] -"ECMA-262, 11th edition specification", June 2020, +#### [ecma262] {#ecma262} + +ECMA-262, 11th edition specification", June 2020, <>. -#### [relative-json-pointer] +#### [relative-json-pointer] {#relative-json-pointer} + Luff, G., Andrews, H., and B. Hutton, Ed., "Relative JSON Pointers", Work in Progress, Internet-Draft, draft-handrews-relative-json-pointer-01, December 2020, <>. -#### [json-schema] +#### [json-schema] {#json-schema} + Wright, A., Andrews, H., Hutton, B., and G. Dennis, "JSON Schema: A Media Type for Describing JSON Documents", Work in Progress, Internet-Draft, draft-bhutton-json-schema-01, June 2022, @@ -890,44 +958,47 @@ draft-bhutton-json-schema-01, June 2022, ### Informative References -#### [RFC4329] +#### [RFC4329] {#rfc4329} + Hoehrmann, B., "Scripting Media Types", RFC 4329, DOI 10.17487/RFC4329, April 2006, <>. ## [Appendix] Keywords Moved from Validation to Core + Several keywords have been moved from this document into the [Core Specification](#json-schema) starting with draft 2019-09, in some cases with re-naming or other changes. This affects the following former validation keywords: - *`definitions`* Renamed to `$defs` to match `$ref` and be shorter to type. -Schema vocabulary authors SHOULD NOT define a `definitions` keyword with -different behavior in order to avoid invalidating schemas that still use the -older name. While `definitions` is absent in the single-vocabulary meta-schemas -referenced by this document, it remains present in the default meta-schema, and -implementations SHOULD assume that `$defs` and `definitions` have the same -behavior when that meta-schema is used. + Schema vocabulary authors SHOULD NOT define a `definitions` keyword with + different behavior in order to avoid invalidating schemas that still use the + older name. While `definitions` is absent in the single-vocabulary + meta-schemas referenced by this document, it remains present in the default + meta-schema, and implementations SHOULD assume that `$defs` and `definitions` + have the same behavior when that meta-schema is used. - *`allOf`, `anyOf`, `oneOf`, `not`, `if`, `then`, `else`, `items`, -`additionalItems`, `contains`, `propertyNames`, `properties`, -`patternProperties`, `additionalProperties`* All of these keywords apply -subschemas to the instance and combine their results, without asserting any -conditions of their own. Without assertion keywords, these applicators can only -cause assertion failures by using the false boolean schema, or by inverting the -result of the true boolean schema (or equivalent schema objects). For this -reason, they are better defined as a generic mechanism on which validation, -hyper-schema, and extension vocabularies can all be based. + `additionalItems`, `contains`, `propertyNames`, `properties`, + `patternProperties`, `additionalProperties`* All of these keywords apply + subschemas to the instance and combine their results, without asserting any + conditions of their own. Without assertion keywords, these applicators can + only cause assertion failures by using the false boolean schema, or by + inverting the result of the true boolean schema (or equivalent schema + objects). For this reason, they are better defined as a generic mechanism on + which validation, hyper-schema, and extension vocabularies can all be based. - *`maxContains`, `minContains`* These keywords modify the behavior of -`contains`, and are therefore grouped with it in the applicator vocabulary. + `contains`, and are therefore grouped with it in the applicator vocabulary. - *`dependencies`* This keyword had two different modes of behavior, which made -it relatively challenging to implement and reason about. The schema form has -been moved to Core and renamed to `dependentSchemas`, as part of the applicator -vocabulary. It is analogous to `properties`, except that instead of applying its -subschema to the property value, it applies it to the object containing the -property. The property name array form is retained here and renamed to -`dependentRequired`, as it is an assertion which is a shortcut for the -conditional use of the `required` assertion keyword. + it relatively challenging to implement and reason about. The schema form has + been moved to Core and renamed to `dependentSchemas`, as part of the + applicator vocabulary. It is analogous to `properties`, except that instead of + applying its subschema to the property value, it applies it to the object + containing the property. The property name array form is retained here and + renamed to `dependentRequired`, as it is an assertion which is a shortcut for + the conditional use of the `required` assertion keyword. ## [Appendix] Acknowledgments + Thanks to Gary Court, Francis Galiegue, Kris Zyp, Geraint Luff, and Henry Andrews for their work on the initial drafts of JSON Schema. @@ -955,7 +1026,7 @@ to the document. - Grouped keywords into formal vocabularies - Update `format` implementation requirements in terms of vocabularies - By default, `format` MUST NOT be validated, although validation can be - enabled + enabled - A vocabulary declaration can be used to require `format` validation - Moved `definitions` to the core spec as `$defs` - Moved applicator keywords to the core spec diff --git a/package.json b/package.json index 36b667b9..fded7279 100644 --- a/package.json +++ b/package.json @@ -12,9 +12,9 @@ }, "license": "MIT", "dependencies": { - "@vcarl/remark-headings": "^0.1.0", - "rehype-autolink-headings": "^6.1.1", - "rehype-slug": "^5.1.0", + "mdast-builder": "^1.1.1", + "mdast-util-find-and-replace": "^3.0.0", + "mdast-util-to-string": "^4.0.0", "rehype-stringify": "^9.0.3", "remark": "^14.0.3", "remark-flexible-containers": "^1.0.6", @@ -22,9 +22,9 @@ "remark-heading-id": "^1.0.0", "remark-preset-lint-markdown-style-guide": "^5.1.3", "remark-rehype": "^10.1.0", - "remark-toc": "^8.0.1", "remark-torchlight": "^0.0.5", "remark-validate-links": "^12.1.1", + "unist-builder": "^4.0.0", "vfile-reporter": "^8.0.0" }, "devDependencies": {